Drones doi: 10.3390/drones10070516

Authors: Panfeng Wang Xinjun Wang Shuhan Huang Haoran Yang Qingfu Liang Adilai Wufu Pingan Jiang

Unmanned aerial vehicle (UAV) multispectral imagery provides a promising approach for field-scale retrieval of soil organic matter (SOM) during the bare-soil period. However, tillage-induced surface heterogeneity is often overlooked. This heterogeneity may alter soil spectral responses and model performance. This study examined the effects of surface tillage status on UAV-based SOM retrieval in farmland. UAV multispectral imagery and 108 topsoil samples were collected during the bare-soil period. The SOM values ranged from 1.37 to 30.95 g/kg. Analyses were conducted under three tillage-status settings: undifferentiated tillage status, plowed-leveled status, and plowed-unleveled status. Spectral and textural features were extracted and selected using a genetic algorithm. These features were then used to develop SOM retrieval models with random forest regression, extreme gradient boosting, and support vector regression. For the six original multispectral bands, the correlations between SOM and band reflectance differed among tillage-status settings. They were weak under the undifferentiated tillage status. They were significantly negative under the plowed-leveled status and significantly positive under the plowed-unleveled status. Texture-derived indicators and standard normal variate analysis suggested that the positive correlations under the plowed-unleveled status may be partly associated with surface-structure-related spectral amplitude effects. Integrating textural features improved the overall test-set accuracy metrics. However, statistically detectable reductions in absolute prediction error were mainly observed under the plowed-unleveled status. On the random-split held-out test set, the highest R2 values reached 0.84 and 0.85 under the plowed-leveled and plowed-unleveled statuses, respectively. These results indicate that surface tillage status is an important source of surface heterogeneity. It should therefore be explicitly considered in UAV-based SOM retrieval under the present study conditions.

Drones doi: 10.3390/drones10070515

Authors: Shuanli Jia Naiming Qi Zheng Li Long He Rui Zhou Yanfang Liu

Multiple unmanned aerial vehicles (UAVs) performing cooperative missions in complex environments face challenges such as difficult cooperative decision-making, stringent spatiotemporal consistency constraints, and environmental uncertainty. The cooperative mission considered in this paper aims to enable multiple UAVs to simultaneously arrive at multiple constant-velocity moving targets. To address these challenges, this paper proposes a multi-agent guided soft actor–critic (MAGSAC) deep reinforcement learning algorithm. Under the centralized training with decentralized execution (CTDE) framework, a Guider network is introduced to guide the local actor network in learning coordinated strategies, thereby alleviating the non-stationarity of multi-agent decision-making under uncertain environments. An estimated time of arrival (ETA)-based spatiotemporal coordination reward function is designed to promote synchronized arrival. To address sparse rewards, a hindsight experience replay (HER) mechanism based on backward trajectory reconstruction is developed, and a delayed collision-constraint activation mechanism is incorporated to improve convergence while maintaining flight safety. Simulation results show that MAGSAC outperforms existing mainstream algorithms in synchronization success rate, temporal synchronization accuracy, and safety.

Drones doi: 10.3390/drones10070514

Authors: Svetoslav Dimitrov Rumen Krastev Stanislav Slavov Sergey Ranchev Vasil Kavardzhikov

This study addresses the lack of integrated methodologies for qualifying additively manufactured polymer lifting attachments for UAV cargo operations under the EASA Specific category. A Design–Verify–Validate framework was developed to combine operational requirements, regulatory mapping to SORA Operational Safety Objective #05, material and manufacturing considerations, nonlinear finite element analysis, and experimental validation. The framework was demonstrated through the complete development of a 241 g FDM-printed PLA+ dual-bill gravitational hook for 50 kg Working Load Limit operations on the DJI Agras T50 platform (DJI, Shenzhen, China). Nonlinear finite element analysis was used to identify critical stress concentrations, while quasi-static testing of three identical specimens yielded an average failure load of 183 ± 9 kg, corresponding to an experimental safety factor of 3.66 ± 0.17. Functional testing on a suspended UAV platform confirmed reliable kinematic performance at incremental loads of 5 kg, 25 kg, and 50 kg. The results demonstrate that the proposed framework can generate coherent, standards-aligned verification evidence under quasi-static loading conditions. Structural validation in this study was limited to this loading regime. While demonstrated on a 50 kg WLL gravitational hook using unreinforced PLA+ as a proof-of-concept material, the methodology can be adapted in future work to other UAV platforms, geometries, and higher-performance materials.

Drones doi: 10.3390/drones10070513

Authors: Časlav Stefanović Dušan Stefanović Danijel Đosić Aleksandar Marković

This paper investigates the performance of drone-to-ground (D–G) communication links under generalized composite fading conditions in urban environments. A unified analytical framework based on single-scattering single-shadowing (SS–SS), double-scattering single-shadowing (DS–SS), and double-scattering double-shadowing (DS–DS) fading models is adopted to accurately characterize the combined effects of multipath scattering, shadowing, and propagation nonlinearity, while also encompassing experimentally validated D–G channel models as special cases. Novel closed-form and integral-form expressions for end-to-end SNR statistics are derived, enabling the evaluation of outage probability (OP), average bit error rate (BER), and ergodic capacity (C). The analysis further provides physical insights into the influence of fading severity, nonlinearity, and shadowing parameters through a comparative investigation of the SS–SS, DS–SS, and DS–DS models. All analytical results are verified through extensive Monte Carlo simulations. Numerical results confirm the accuracy and flexibility of the proposed framework, highlighting its potential application in the analysis, optimization, and design of beyond-5G and future 6G drone-assisted wireless networks.

Drones doi: 10.3390/drones10070512

Authors: J. E. Durán-Delfín C. D. García-Beltrán M. E. Guerrero-Sánchez H. Abaunza O. Hernández-González G. Valencia-Palomo

This work presents a nonlinear dynamic model and an energy-based control strategy for a coaxial vertical take-off and landing Unmanned Aerial Vehicle (UAV) equipped with independently tilting propulsion units. The proposed model captures the full six-degree-of-freedom motion of the vehicle and explicitly incorporates the forces and moments produced by the coaxial thrust-vectoring propulsion system, as well as the additional force components induced by the two-degree-of-freedom thrust vectoring mechanism. To regulate the vehicle during hover, cruise, and transition maneuvers, a passivity-based control framework formulated in terms of unit quaternions is developed. The control law simultaneously stabilizes the translational and rotational subsystems without relying on model linearization. In order to map the virtual control forces and torques into physically realizable actuator commands, a nonlinear control allocation procedure is introduced. This allocation scheme enables independent angular positioning of the propulsion units while computing the corresponding motor angular velocities. The effectiveness of the proposed modeling and control framework is assessed through three-dimensional dynamic simulations and numerical experiments, demonstrating accurate trajectory tracking, autonomous UAV landing capabilities, and smooth transitions between flight regimes for thrust-vectored UAV platforms.

Drones doi: 10.3390/drones10070511

Authors: Alexander Bychkov Stanislav Eroshenko Alexey Romanov

Over the past decade, drone-based aerial inspection of overhead power lines has proven superior to traditional ground-based methods. However, in flatland areas, it remains costlier, as total expenses include not only flights but also extensive mission planning. Operators must select takeoff zones and conduct flights in compliance with weather conditions and numerous regulations. Automating mission planning can reduce operator workload, lower the risk of rule violations, and boost inspection efficiency. This paper introduces a framework for automating power line inspection route planning. It selects takeoff areas and generates drone routes for specified line segments, which meet all regulatory requirements. The framework incorporates a novel method for automatic pole-type identification using satellite imagery. The approach combines a YOLO detector, trained on synthetic data, with an expert system, resulting in a 36.9% improvement in performance (on the tested dataset) compared to prior solutions. The final solution was implemented as an open-source QGIS plugin. The experimental results demonstrate that the automated path-planning approach successfully generates inspection routes for line segments exceeding 50 km (135 poles) and increases the number of inspected poles by 58.7%, enabling the capture of power line insulators, which can then be automatically segmented and analyzed using machine learning algorithms.

Drones doi: 10.3390/drones10070510

Authors: Robert Dianovský Pavol Pecho Andrej Novák Martin Bugaj

Stratospheric solar-powered unmanned aerial vehicles (UAVs), commonly operated as High-Altitude Pseudo-Satellites (HAPS), promise satellite-like persistence for Earth observation, communications and remote sensing, but their feasibility is governed by a tight coupling between solar energy availability and onboard energy demand. This study presents an energy-balance simulation framework that predicts the diurnal charge–discharge behaviour and endurance of solar-powered UAVs. The framework couples a physics-based environmental irradiance model—astronomical solar position, an air-mass and pressure-scaled broadband atmospheric transmission and an eccentricity-corrected extraterrestrial irradiance—with a wing-geometry photovoltaic collection model that reduces the airfoil camber, planform, dihedral and cell layout of a real wing to three scalar coefficients, replacing the flat-plate assumption common in solar-UAV sizing. The closed-form collection coefficient captures the full dependence of collected power on sun position and aircraft heading and admits an exact orbit-averaging result for circular loiter. The model is implemented as a reproducible, modular tool with single-day, annual and global analysis modes. It is validated against a ground-based photovoltaic charging campaign conducted on the as-built Aurora solar UAV demonstrator (5.6 m span, 8 kg) over three clear-sky days spanning a 90-day seasonal range: predicted and measured wing-collected power agree with a Pearson correlation of 0.998, a coefficient of determination of 0.993, an RMS error of 6.0% and a daily-energy agreement within 3.5%. A structured residual identifies an unmodelled photovoltaic temperature effect bounded at the 6% level. The framework provides HAPS designers and operators with a transparent, validated tool for feasibility screening, component selection and mission planning across latitude and season.

Drones doi: 10.3390/drones10070509

Authors: Liangliang Huai Meixiu Lin Caili Wang Peng Yun Bo Li

Tracking highly maneuverable UAVs in complex maritime environments faces multiple challenges: dynamic sea surface interference and low-altitude occlusion make UAV motion trajectories difficult to predict; the strong maneuvering behavior of UAVs imposes high demands on tracking real-time performance and accuracy; and marine environmental noise and unstable shipborne sensor data lead to measurement incompleteness. These factors collectively limit the adaptability and robustness of existing maneuvering UAV tracking methods in complex maritime scenarios. In this context, accurate model recognition for UAVs becomes a key factor in improving tracking performance. Traditional interactive multiple model (IMM) methods rely on probabilistic weighting for model selection, suffering from response delays during UAV maneuvers, and fixed model sets cannot adapt to diverse maneuvering scenarios, resulting in degraded UAV velocity estimation accuracy. To address the above issues, this study proposes a dual long short-term memory (LSTM) cooperative network architecture, targeting the two key problems of incomplete measurements in shipborne radar measurements and inaccurate model probability estimation, and presents corresponding solutions. First, an online-trained LSTM-based incomplete-measurement compensation method is proposed, which achieves real-time fitting and restoration of historical measurement data, providing continuous and stable measurement inputs for shipborne platform UAV tracking in maritime environments. Second, building on this, an LSTM-based UAV model recognition method is developed to directly identify the UAV’s current motion model from multi-frame historical measurement information, effectively reducing maneuvering delays. Furthermore, GPS data is used to generate optimal model probabilities as training labels, thereby improving model reliability. Simulation results show that, under incomplete-measurement conditions, the proposed method can effectively reconstruct missing measurements and ensure measurement continuity. Under complete-measurement conditions, the proposed LSTM-based model recognition method significantly improves UAV model recognition accuracy and three-dimensional velocity estimation performance, demonstrating the effectiveness of deep learning for maneuvering UAV tracking from shipborne platforms in maritime environments.

Drones doi: 10.3390/drones10070508

Authors: Xudong Zhang Junqiang Bai Kang Chen Xinzhuang Chen

Safe-separation-and-collision-avoidance unmanned aerial vehicle (UAV) swarms are increasingly used for inspection, emergency response, environmental monitoring, and search-and-rescue support in cluttered airspace where communication links may be delayed, degraded, or intermittently unavailable. These applications require heterogeneous vehicles to maintain situational awareness, allocate tasks, and avoid hazards under partial observability and changing team topology. To address these challenges, this paper proposes a Hierarchical Graph-Attention Multi-Agent Reinforcement Learning architecture (HG-MARL) for safe-separation-and-collision-avoidance heterogeneous UAV swarm coordination. The proposed framework decomposes the task into high-level resource allocation and low-level local-control execution, uses graph attention for changing swarm topology, and applies Transformer memory, action masking, potential-field reward shaping, and domain-randomized simulation training. In the multi-scenario simulation summaries, HG-MARL achieves 92.9%, 89.8%, and 82.6% task success in Scenarios A–C, respectively, improving upon MAPPO by 15.1, 21.4, and 20.1 percentage points. Summary-statistic Welch tests show that all six HG-MARL comparisons against MAPPO and QMIX yield p<0.01 with large effect sizes. Fair-control, reward-sensitivity, communication-degradation, safety-ablation, training-stability, latency, and transfer-oriented stress tests further support the contributions of the integrated architecture. The validation scope is simulator-based, with platform-level flight/HIL evaluation discussed as future work. These results suggest that HG-MARL is a promising simulation-validated framework for civilian UAV swarm coordination in collision-and-separation-critical and communication-degraded environments.

Drones doi: 10.3390/drones10070507

Authors: Weichao Yang Yuqing Lu Dawei Wang Yixin He Yi Jin Li Li

Post-disaster emergency communication networks often suffer from coverage degradationand limited network observability, which makes it difficult to maintain reliable connectivityfor evacuees. Existing UAV-assisted communication methods usually rely on network-sidevisible metrics for deployment decisions. As a result, they may overlook evacuees whosecommunication demands are hidden in coverage blind zones or observation blind zonesalong predefined evacuation corridors. To address this problem, this paper proposes asensing-assisted UAV-BS recovery method for invisible evacuee demand. The methodconstructs an invisible-demand map by combining sensed evacuee states, ground coverageconditions, network observation states, and evacuation urgency. It further introducesan evacuation-flow demand map to describe continuous communication demand alongevacuation corridors. These two maps are combined to guide temporary UAV-BS accessrecovery. The simulation results show that the proposed method achieves the best overallbalance among invisible-demand recovery, evacuation-path coverage, and edge evacueerate. Compared with the blind-zone-only baseline, it improves DCR (demand coverageratio) from 0.365 to 0.373, DW-EPC (demand-weighted evacuation-path coverage) from0.286 to 0.316, and the fifth-percentile evacuee rate from 1.559 to 1.672 bps/Hz. Theproposed method also shows more stable performance under sensing-output uncertaintyand constrained UAV response radius.

Drones doi: 10.3390/drones10070506

Authors: Songlin Liu Xinyu Zhu Tingyu Zhu Yuehao Yan Rui Hao Yuanfan Wang

Typhoon-eye sensing places unmanned aerial vehicle (UAV) swarms in a setting where the wind field that carries the target signal also displaces aircraft, drains energy, weakens links, and increases failure risk. A rule that improves only routing or only motion can therefore move the swarm into another failure mode. This paper proposes a risk-driven cross-layer coordination scheme for such missions. A bounded risk index, computed from isolation, connectivity loss, and wind intensity, acts as a supervisory variable for multi-hop reachability maintenance, isolated-node recovery, and layered altitude adaptation. For evaluation, graph reachability is separated from useful data return through a degraded multi-hop aggregation model that includes distance loss, wind-dependent reliability, rain-induced packet loss, relay forwarding loss, and mothership collection capacity. The simulator combines a bounded Holland-type storm field, stochastic turbulence, nonlinear propulsion energy consumption, and wind-dependent structural failure. Against three literature-inspired baselines, two AI-inspired comparators, and six ablation variants, the method keeps a balanced profile across connectivity, isolation, wind exposure, data collection, and survival. In 30-run steady-state robustness tests under heavy-rain attenuation, the full strategy showed clear gains over routing-only and multi-agent reinforcement learning (MARL)-routing comparators in connectivity and isolation, but did not uniformly dominate topology reconstruction or the multi-agent deep deterministic policy gradient–artificial potential field (MADDPG-APF) recovery comparator. The results indicate that, in storm-dominated swarm sensing, resilience comes mainly from coordinating exposure reduction with topology stabilization, rather than from optimizing a single layer.

Drones doi: 10.3390/drones10070505

Authors: Chang Liu Shan Wang

Autonomous obstacle avoidance for UAVs in dynamic obstacle-dominated complex environments must address time-varying local collision risks from multiple directions under the constraints imposed by local sensing, environmental uncertainty, execution safety, and limited onboard computation. Planning-based methods often require frequent replanning or explicit obstacle prediction, whereas conventional reinforcement learning policies may produce myopic decisions under partial observability. To address these limitations, this study proposes a dynamic obstacle-avoidance framework that combines a temporal LiDAR representation with safety-aware action correction in recurrent reinforcement learning. Multi-layer LiDAR observations are constructed using sector-wise minimum pooling. Adjacent two-frame stacking and a CNN-LSTM architecture are then used to extract local geometric structures and short-term dynamic cues, and a velocity-control policy is optimized using Recurrent PPO. In addition, a smooth velocity-projection safety shield is introduced to modify policy outputs and reduce collision risk during both training and policy execution. Experiments conducted in mixed static–dynamic obstacle scenarios based on Gym-PyBullet-Drones show that the proposed method achieves an average success rate of 91.9% across four test configurations, with an average online computation time of 0.78 ms. Ablation studies further support the contributions of two-frame observations, LSTM-based temporal modeling, and the safety shield.

Drones doi: 10.3390/drones10070504

Authors: Beibei Cui Mingyang Wang Pengpeng Dong Lei Zhang Kunpeng Zhang Liang Zhao

With the continuous expansion of unmanned aerial vehicle (UAV) applications, generating near-optimal paths and achieving effective obstacle avoidance in complex environments remain highly challenging tasks. To address the problems of multi-objective path planning and obstacle detection for UAV flight missions in orchard environments, this paper proposes a novel hybrid algorithmic framework named NeuroJPS-A. The main scientific contribution is the synergistic integration of neural combinatorial optimization, 3D-JPS, and adaptive APF, enabling task-aware obstacle avoidance and closed-loop trajectory adjustment. This method introduces neural combinatorial optimization from the TSP into the 3D-JPS algorithm, optimizing the search mechanism of the traditional JPS and further shortening the UAV’s globally planned path length. In addition, this study integrates the proposed algorithm with the APF to solve the local dynamic obstacle avoidance problem. Quantitative results show that NeuroJPS-A reduces path length by 10% and the number of turns by 47.8% in 2D, and achieves a 24.9% shorter path and 22% of A*’s computation time in 3D. To verify the performance of the proposed method, comprehensive simulation experiments were conducted. The experimental results demonstrate that the NeuroJPS-A algorithm enables UAVs to quickly and effectively generate optimal planned routes, ensuring safe navigation in complex orchard environments and preventing collisions during flight missions.

Drones doi: 10.3390/drones10070503

Authors: Saleem Alsaraireh Mustafa Al-Fayoumi Mohammad Alnabhan

The increasing deployment of Unmanned Aerial Vehicles (UAVs) in critical operations exposes them to cyberattacks. Although deep learning-based Intrusion Detection Systems (IDSs) are effective, they are susceptible to adversarial attacks that manipulate input features to avoid detection. Conventional feature selection methods do not distinguish between features critical to model accuracy and those essential for preserving cyberattack operational validity. To address this, we propose a Dual-Impact Feature Selection (DIFS) framework for robust UAV-IDS models. Our approach evaluates features based on two criteria: the first is Model Performance Impact (MPI), using Integrated Gradients (IG) and Local Interpretable Model-agnostic Explanations (LIME) to measure feature influence on detection accuracy, and the second is Functionality Preservation Criterion (FPC), a clustering-based method that assesses whether a feature is indispensable for cyberattack execution. Features with high MPI and FPC are identified as Dual-Impact Features (DIFs). We generate constrained adversarial attacks that perturb these DIFs to create realistic evasion samples. Using these samples for adversarial training, we develop three robust UAV-IDS Convolutional Neural Network (CNN) models. Evaluated on three UAV network intrusion datasets, our framework demonstrates improved resilience. The models achieve up to 99.8% detection accuracy while reducing Attack Success Rate (ASR) to as low as 0.002, supporting their potential for designing adversary-resistant detection systems for UAV networks.

Drones doi: 10.3390/drones10070502

Authors: Yong Yang Yujie Fu Bowen Wang Kaijun Xu Weiqi Feng

With the rapid growth in e-commerce demand, increasing pressure on same-day delivery, and rising last-mile logistics costs, UAV-based logistics systems have emerged as a promising solution for efficient transportation in complex environments. In mountainous regions, however, irregular terrain, limited infrastructure accessibility, and strict flight constraints significantly increase the difficulty of logistics planning. To address these challenges, this study proposes a two-layer collaborative optimization framework for multi-center UAV logistics delivery systems. At the lower level, a multi-center site selection model was developed to determine the optimal distribution center locations and assign task areas. A trajectory cost matrix was constructed by comprehensively considering multiple constraints. The model was solved using a hybrid strategy that combines chaotic initialization and local enhancement based on the elite saDE method to improve the Starfish Optimization Algorithm, called the Mixed-Strategy Improved Starfish Optimization Algorithm (MISFOA), thereby generating feasible three-dimensional flight trajectories between local nodes. At the upper level, an improved Adaptive Large Neighborhood Search (IALNS) algorithm is applied to perform UAV mission assignment and route scheduling within each distribution center, based on the trajectory cost matrix pre-calculated at the lower level. The proposed framework achieves effective information exchange and hierarchical coupling between center selection and scheduling at the distribution level, thereby enabling unified optimization of the multi-center location and coordinated dispatch system. Simulation results demonstrate that the proposed method significantly improves delivery efficiency and solution quality in complex mountainous environments while ensuring trajectory feasibility and operational safety. This model provides a scalable and practical optimization framework for low-altitude logistics network planning under complex constraints.

Drones doi: 10.3390/drones10070501

Authors: Hailong Xi Le Ru Wenfei Wang Jiwei Tian

Deep learning-based perception is fundamental to Unmanned Aerial Vehicles (UAVs), yet it remains vulnerable to physical adversarial patches. Existing methods for generating adversarial patches typically rely on localized key features, making them highly fragile under partial occlusion, a common scenario in UAV operations due to environmental obstruction and viewpoint variation. To address this limitation, we propose Multi-Scale Feature Dispersion (MSFD), an information-theoretic framework for generating robust adversarial patches under incomplete observations. MSFD maximizes information entropy to promote statistically uniform perturbations, while spatial autocorrelation introduces structural redundancy to preserve attack effectiveness when critical regions are occluded. Additionally, a multi-scale consistency constraint ensures robustness across varying flight altitudes. Experiments on the VisDrone dataset and in high-fidelity AirSim environments demonstrate that MSFD achieves an attack success rate (ASR) of 45.6% under 50% occlusion, whereas existing methods degrade to near-zero performance. These results highlight the importance of feature dispersion in adversarial robustness and provide a principled approach for evaluating perception security in real-world UAV scenarios.

Drones doi: 10.3390/drones10070500

Authors: Zhaochen Wang Rouwan Wu Yuxiang Liu Yudong Huang Shen Yan Maojun Zhang

Accurate geolocalization of ground targets from unmanned aerial vehicles (UAVs) is critically limited by pose estimation errors and the scarcity of active ranging sensors. To address these challenges, we propose a pipeline that integrates reference image cropping, robust cross-view matching, and geographic projection to estimate real-world coordinates using 2.5D reference maps. For evaluation, we introduce SkyPin, the first large-scale benchmark of its kind, designed to comprehensively test UAV-based localization methods. It comprises UAV imagery from eight diverse environments, featuring both visible and thermal infrared modalities under a wide range of conditions, including variations in weather, time of day, flight altitude, and camera perspective. All ground targets are annotated with centimeter-accuracy Real-Time Kinematic (RTK) coordinates. We establish a comprehensive benchmark by evaluating a series of feature matching methods combined with different projection strategies, allowing systematic comparison of algorithm performance. Representative results show that RoMa combined with PnP-based raytracing achieves the best overall performance, reaching a median 2D error of 0.87 m and Recall@5m values of 0.94 and 0.98 on RGB and thermal infrared UAV-map settings, respectively. Further analysis reveals that performance degrades in challenging mountainous scenes and under large viewing-angle variations, highlighting terrain relief and UAV perspective changes as remaining critical challenges for robust target geo-localization. The full dataset and implementation code will be made publicly available to facilitate future research in UAV-based geolocalization.

Drones doi: 10.3390/drones10070498

Authors: Yuankui Wang Zhiwei Sun Xiange Tian Yuhang Jia Hao Li Bohan Wang Dahai Zhang Peng Qian

In this paper, a Gaussian process-based model predictive control (GP-MPC) method is proposed, which aims to enhance the trajectory tracking performance of autonomous underwater vehicles (AUVs). This method can compensate for internal errors and external disturbances based on a limited amount of data. Firstly, numerical models of the AUV are presented. Then, the offline GP-MPC algorithm and online GP-MPC algorithm are presented and described. Meanwhile, the current disturbances and initial errors are also considered. The circular trajectory, L-shaped steering trajectory, and lemniscate trajectory are tracked to evaluate the trajectory tracking performances of different algorithms. Compared with proportional–integral–derivative (PID) and nominal MPC algorithms, the GP-MPC algorithms show reduced root mean square error (over 40%) and reduced maximum error (over 40%) in both position and yaw angle when performing different trajectory tracking tasks. Finally, real-time pool experiments are conducted to validate the implementation feasibility of the GP-corrected MPC framework on a physical AUV under surface three-degrees-of-freedom motion, while the online GP-MPC is evaluated through numerical simulations.

Drones doi: 10.3390/drones10070499

Authors: Jingsen Zhang Biao Hou Xing Yuan

Autonomous drone navigation relies on onboard sensors to perceive obstacle information in real time. However, indoor environments contain abundant wall structures that occlude the sensor’s field of view, rendering obstacle information within occluded regions undetectable to the drone. Existing trajectory planning algorithms fail to adequately account for the safety risks introduced by sensor occlusion. To address this limitation, this article proposes a novel trajectory planning framework to enhance drone flight performance in indoor environments. Specifically, a 3D occupancy grid map is first constructed from sensor data, and an initial trajectory is generated from the current position to the goal. A sensor occlusion detection algorithm then classifies the current scene into three categories: occlusion-free, partial occlusion, and full occlusion. For occlusion-free scenarios, the initial trajectory is directly forwarded to the controller. For partial and full occlusion cases, an occlusion-aware trajectory replanning algorithm generates multiple candidate trajectories in unknown regions. These candidates are evaluated by a scoring function comprising three metrics: safety, efficiency, and smoothness. Upon detection of a collision between the currently executing initial trajectory and an obstacle, the active trajectory is immediately switched to the highest-scoring candidate trajectory, thereby ensuring both flight safety and navigation efficiency of the drone. Extensive experiments are conducted across multiple occlusion scene configurations to validate the performance of the proposed method. Experimental results demonstrate that the proposed method is capable of providing safe and efficient trajectories for drones under both partial occlusion and full occlusion conditions.

Drones doi: 10.3390/drones10070497

Authors: Izabelle de Lima e Lima Marta Laura de Souza Alexandre Ana Karla da Silva Oliveira Rodnei Rizzo Carlos Augusto Alves Cardoso Silva Peterson Ricardo Fiorio

Remotely Piloted Aircrafts (RPAs) equipped with multispectral sensors have emerged as promising tools for estimating foliar nitrogen content (TFN). So, this study applied a methodological approach aimed at simulating UAV multispectral data using hyperspectral leaf data obtained in a controlled environment, with the objective of evaluating its predictive potential and its transferability to field data collected by UAVs for TFN estimation. To this end, spectral bands and spectral indices (SIs) equivalent to those of UAV-mounted sensors were simulated based on hyperspectral data acquired by a benchtop sensor, and subsequently used in modeling via Partial Least Squares Regression (PLSR) and Random Forest (RF). The results showed similar performance across the levels, with R2 values of 0.75 and 0.76 for PLSR and RF on the UAV data, and 0.75 and 0.74 for PLSR and RF on the simulated data, respectively. The RF model also performed well in cross-domain validation, with R2 = 0.70 when calibrated with simulated data and applied to UAV data. Furthermore, the simulated data maintained high predictive power even with a reduced sample size. It is con

Drones doi: 10.3390/drones10070496

Authors: Yingran Zhao Wenju Hu

To tackle the dynamic assignment problem of unmanned aerial vehicle (UAV) swarms, a merged coordination-optimized pigeon-inspired optimization (MCOPIO) algorithm based on the pigeon-inspired optimization (PIO) algorithm is proposed in this paper. The algorithm disrupts the original pigeon distribution via random grouping and performs mutual learning and optimization within the new groups. After dynamic optimization, the underperforming pigeons are discarded, and the flock is reorganized. Subsequently, the two stages of the basic PIO are integrated through a dynamic factor. These improvements overcome the limitations of the basic PIO algorithm, such as insufficient global search capability, poor stability, and disconnection between the two algorithm stages. Comparative experiments are conducted with the state-of-the-art intelligent computing algorithms, such as the basic PIO, particle swarm optimization (PSO), genetic algorithm (GA), and improved consensus-based bundle algorithm (ICBBA), the comparative results verify the feasibility and effectiveness of our improved PIO for UAV swarm dynamic task allocation.

Drones doi: 10.3390/drones10070495

Authors: Juan Valdiviezo Jaime Aguilar-Lome María Jaramillo-Carrión Luis Ángel Ruiz Lia Ramos-Fernández

Rice brown spot, caused by Bipolaris oryzae, is an important constraint for rice production and requires timely field-scale monitoring. This study evaluated the use of multispectral bands acquired with a UAV-mounted sensor, together with vegetation indices, combined with machine-learning models to estimate rice brown spot severity under field conditions in Lambayeque and Cajamarca, Peru. A total of 37 sampling observations were collected across the vegetative, flowering, and milk-ripening stages. Spectral variables were extracted from UAV orthomosaics and related to field-based disease severity assessments. The strongest correlations with severity were observed for NDRE (r = −0.83) and NPCI (r = 0.77). Three regression models were evaluated using leave-one-out cross-validation (LOOCV): support vector regression with radial basis function kernel (SVR-rbf), support vector regression with linear kernel (SVR-linear), and Random Forest (RF). The SVR-linear model showed the lowest prediction error using NDRE, GREEN, and BLUE as predictors (R2_CV = 0.76; RMSE_CV = 1.31), although its performance was very similar to that of SVR-rbf and RF. These results indicate that UAV-derived multispectral information can support plot-level estimation of rice brown spot severity. However, model performance should be interpreted cautiously because of the small dataset, heterogeneous disease conditions, and moderate prediction accuracy. Further studies with larger and independent datasets are needed to improve robustness and transferability.

Drones doi: 10.3390/drones10070494

Authors: Zheng Fang Pengtao Zhang Xiaolin Fan Yan Liu

This paper investigates the path-planning problem of unmanned aerial vehicles (UAVs) for logistics delivery in urban environments. The impact of real-time obstacle avoidance and path smoothness on the flyability of UAVs remains a challenge in existing research. To address the issue that the path generated by the traditional Rapidly exploring Random Tree (RRT) algorithm exhibits a sudden slope change at connection points, which makes the UAV non-flyable, this paper proposes an improved algorithm that combines the traditional RRT algorithm with Bézier curves. The proposed real-time path generation strategy consists of two stages. The first stage constructs the environment model. The second stage integrates the RRT algorithm with Bézier curves, enabling the generated route to achieve real-time obstacle avoidance while being smooth and free of curvature discontinuities. Simulation experiments compare the improved algorithm with the traditional RRT algorithm and global path optimization methods. The experimental results show that the improved algorithm has the advantage of real-time obstacle avoidance, and the generated route is smooth at connection points with no curvature discontinuities, thereby ensuring good flyability.

Drones doi: 10.3390/drones10070493

Authors: Junxi Zhu Xitong Zhou Zheng Zi Yuan Xie Xiaokun Jiang Zhizhou Zhang

Mountain search-and-rescue missions require multiple unmanned aerial vehicles (UAVs) to cooperate efficiently under limited communication and constrained operational resources. Existing multi-UAV search methods often rely on centralized task allocation or explicit coordination mechanisms, while exhaustive coverage strategies may allocate excessive search effort to low-value regions, reducing search efficiency in large-scale environments. To address these challenges, this paper proposes a probability-guided and pheromone-assisted distributed cooperative search framework that enables autonomous UAV decision-making without centralized control. Each UAV independently selects its motion according to local observations, prior target probability, and digital pheromone information, while intermittent communication and occupancy-map fusion enable implicit coordination through local interactions. The proposed framework balances target-oriented exploitation and spatial exploration by combining probability attraction with pheromone repulsion, thereby suppressing redundant revisits while maintaining effective distributed cooperation. It is evaluated through representative two-dimensional mountain search simulations under distance-limited communication constraints. In the baseline (2km×2km) scenario, the proposed framework achieves search success rates comparable to conventional coverage-based methods while reducing the average search cost from 1074.2 and 1005.0 steps to 581.9 steps. As the search environment expands, its performance advantage becomes increasingly pronounced, demonstrating higher search efficiency and improved mission reliability under limited search resources. Parameter sensitivity and scalability analyses further show that the proposed framework maintains favorable robustness and cooperative efficiency across different parameter settings and search scales. These results demonstrate that the proposed distributed search framework provides an effective and scalable solution for multi-UAV mountain search-and-rescue missions under limited communication and operational resources.

Drones doi: 10.3390/drones10070492

Authors: Chenshuo Ma Shenao Du Pengyang Wu Wenhao Tong Ziyu Yan Anxi Yu

Scene matching-based localization systems (SMLSs) offer an effective solution to the failure of Global Navigation Satellite System (GNSS) positioning in complex environments. This paper designs and implements a vision-based autonomous localization system for unmanned aerial vehicles (UAVs), compatible with both optical and infrared sensors, delivering high frame rates and high-precision positioning performance. First, to address the issue of uneven texture distribution in natural terrain features, an adaptive expansion sliding window model is constructed to accurately extract texture-rich regions, which effectively improves matching precision. Second, considering the differences in edge characteristics between optical and infrared images, the Sobel operator and Scharr operator are introduced, respectively, to construct gradient features, achieving high-precision, high-frame-rate heterogeneous image matching. Furthermore, to significantly improve the system frame rate, this paper designs an embedded parallel acceleration strategy based on a multi-core CPU architecture. The strategy achieves task-level concurrency between the front-end stages (pre-correction and feature refinement) and matching, and implements parallel optimization for feature construction and correlation computation within the matching module. On the algorithmic level, the correlation computation is further accelerated by replacing spatial-domain convolution with frequency-domain multiplication. Finally, the algorithm is deployed on an RK3588 embedded platform. The effectiveness of the proposed system is validated using offline flight data from a medium-altitude fixed-wing UAV and real-time flight experiments with a low-altitude rotary-wing UAV. In the medium-altitude UAV flight data validation, optical visual localization achieves an average position error of 20.94 m with a processing time of 0.123 s/frame, while infrared visual localization yields a position error of 11.77 m at 0.128 s/frame. In the low-altitude UAV flight experiment, optical visual localization achieves an average position error of 9.68 m at 0.15 s/frame, and infrared visual localization achieves an average position error of 11.22 m at 0.15 s/frame.

Drones doi: 10.3390/drones10070491

Authors: Dongyang Wang Jiankun Shi Yantao Lu Jinchao Chen Chenglie Du

Large vision–language models have advanced embodied navigation by integrating visual perception with natural-language reasoning. However, vision-and-language navigation (VLN) for unmanned aerial vehicles in low-altitude urban airspaces remains challenging due to occluded views, dynamic layouts, limited communication bandwidth, and partial observability. Existing methods mainly focus on single-agent egocentric navigation and lack explicit modeling of uncertainty and inter-agent dependencies in collaborative multi-UAV settings. We propose Collaborative Low-Altitude Space Navigation (Co-LASN), a dynamic Bayesian network-based framework for collaborative VLN in embodied multi-agent systems. Co-LASN jointly models environmental dynamics, linguistic constraints, and inter-agent dependencies in a unified probabilistic representation, allowing each UAV to update its belief state and incorporate information from neighboring agents when making navigation decisions. Experiments on a low-altitude subset of the HaL-13k benchmark show that, under the evaluated simulation protocol, Co-LASN achieves higher navigation metrics than single-agent and partially collaborative baselines. In the 3-agent setting, Co-LASN increases the any-success rate (ASR) from 12.37% to 15.23% and reduces the min navigation error (MNE) from 99.86 to 89.46. These results demonstrate the relative effectiveness of belief-aware collaboration within the evaluated simulation setting.

Drones doi: 10.3390/drones10070490

Authors: Johan H. F. Castenschiold Mækir B. Gullbein Sjúrður Hammer Morten Frederiksen

Unoccupied Aerial Systems (UASs) offer great potential for monitoring breeding colonial seabirds. However, survey flights need to be planned carefully to maximize detection of birds, allow for reliable counts, and minimize disturbance. In this study, we evaluated UAS-based monitoring for the most numerous seabird species in the Faroe Islands, the northern fulmar (Fulmarus glacialis), assessing both disturbance and optimal viewing angles. We found that behavioral disturbance could be minimized by adhering to a set of strict operating protocols, including strategic and flexible flight paths that ensured UAS distances remained above vigilance thresholds, allowing for initial habituation and limiting responses to the presence of the UAS. During surveys, quantifiable behavioral alterations (vigilance) were observed at distances ≤57.5 m in mixed areas containing both incubating and resting individuals, and ≤32.9 m in areas with only incubating individuals. At greater distances, only light responses (head turning) occurred. To optimize monitoring efficiency, we found that a slight downward camera tilt of −13.8° consistently provided the highest bird visibility, detecting 93% of individuals. Complete visibility was achieved by covering a range from −30° to −1.3°, depending on terrain type and bird age group, highlighting the observation angle as a critical factor for reliable surveys in the investigated complex topography. Overall, these results will provide a strong foundation for further research into tailored flight and survey protocols for cliff-nesting seabirds utilizing UAS technology.

Drones doi: 10.3390/drones10070488

Authors: Xuehao Huang Jiayu Yuan Chen Tian Nanxing Chen Haijing Qi Aihong Tan Enhui Zheng

Satellite signal interruptions disable unmanned aerial vehicle (UAV) navigation, making visual localization a vital alternative. To improve robustness in oblique flight paths and complex environments, we propose the UAV visual geo-localization network with transformer and hypergraph feature aggregation enhancement (HTGL). First, we enhanced feature extraction capabilities by optimizing the downsampling strategy and attention allocation mechanism in the backbone network. Second, we designed the Hypergraph Feature Aggregation Enhancement (HFAE) module based on hypergraph-based adaptive correlation enhancement (HyperACE) to improve the model’s ability to capture higher-order correlations. Furthermore, we constructed the Complex Scene Rotation dataset (CSR10) and proposed a method for simulating winter scenes, thereby overcoming the limitations of existing research in terms of scenes, flight directions, and seasons. Additionally, two evaluation metrics—pixel distance root mean square error (PD-RMSE) and geographic distance root mean square error (GD-RMSE)—were introduced to enable a comprehensive assessment of algorithm performance. Experimental results show that HTGL achieved RDS scores of 85.95% (+1.4%), 83.64% (+4.1%), and 91.52% (+1.49%) on the UL14, UL14_ROT, and CSR10 datasets, respectively, demonstrating strong robustness in rotated and complex scenes. Actual deployment and flight tests on the Jetson Orin NX platform further validated the model’s excellent engineering practicality.

Drones doi: 10.3390/drones10070489

Authors: Yan Kang Tingwei Ji Fangfang Xie Chenglou Liu Zihao Yuan

Gain-scheduled and cascaded proportional–integral–derivative (PID) autopilots remain common practical baselines for fixed-wing unmanned aerial vehicles (UAVs), but training one shared learned controller for heading, altitude, and true airspeed across several maneuvers remains difficult. We study this problem under a strict reach-then-hold benchmark in which all the active channels must enter prescribed green bands and remain there for a terminal hold window. The proposed training recipe combines proximal policy optimization (PPO) with a tri-band maneuver-tracking reward and an outer bounded reward reweighting (BDR) step that updates the base reward weights from recent violation summaries under a Kullback–Leibler (KL) gate. In the JSBSim F-16 six-degree-of-freedom dynamics model, used here as a challenging surrogate benchmark for fixed-wing UAV autopilot learning, the learned controller transfers across a fixed five-lesson sequence, reaches strict success rates of 0.966 on turn and 0.921 on climb, and issues substantially smaller executed-command updates than the shared fixed-gain PID reference used here. Under the reported lesson sequence and step budget, fixed-weight PPO and a reweighting-only variant stall under the same envelopes, while speed remains the main bottleneck for both controllers. We further report exploratory long-horizon tracking, difficult-command stress checks, and an added command-filtered nonlinear dynamic-surface-control (CF-DSC) reference without retraining the learned policy. The CF-DSC results confirm that advanced non-reinforcement-learning (non-RL) controllers can be strong reference methods; therefore, within this reported simulator setup, BDR should be read as a practical and inspectable reward-scheduling heuristic for shared triad tracking rather than as a proof of superiority over all classical, nonlinear, or model-based controllers.

Drones doi: 10.3390/drones10070487

Authors: Yan Lyu Zhiyu Fan Xueyong Xu Di Tang Guanyu Gao Weiwei Wu Yanfeng He

UAV swarms provide a flexible sensing platform for smart-city crowd surveillance, but cooperative aerial monitoring remains challenging due to dynamic pedestrian distributions, partial observability, and the trade-off between visual coverage and recognition accuracy. In particular, flying at higher altitudes increases the field of view but reduces recognition accuracy, while low-altitude flight improves visual quality at the cost of limited coverage. To address these challenges, this paper proposes an environment-aware cooperative navigation framework that integrates spatiotemporal density prediction with multi-agent reinforcement learning. The surveillance area is modeled as a spatiotemporal graph, where sparse and partial UAV observations are used to predict future pedestrian-density maps and confidence intervals. The predicted density and uncertainty, together with empirical recognition error, UAV position, flight height, battery state, and historical observations, are incorporated into MARL-based policy learning. The learned policy enables UAVs to cooperatively adjust movement and altitude decisions under the centralized training and decentralized execution paradigm. Extensive simulations in UAV-based crowd surveillance environments demonstrate that the proposed framework achieves a more favorable coverage–error trade-off than representative heuristic, prediction-based, single-agent reinforcement learning, and multi-agent reinforcement learning baselines. The results show that prediction-aware and accuracy-aware cooperation improves pedestrian-level surveillance performance under dynamic and partially observable crowd distributions.

Drones doi: 10.3390/drones10070486

Authors: Ruizhi Zhang Jinghua Hou Yan Shi Xiping Dai Ke Zhang Jingjing Diao

Robust unmanned aerial vehicle (UAV) detection in real low-altitude anti-UAV scenarios remains challenging due to motion blur, extreme illumination, cluttered backgrounds, and tiny target sizes. Most existing UAV detectors rely on RGB imagery, but their performance often degrades severely under these adverse conditions. Event cameras, as a neuromorphic sensing modality, capture motion-sensitive responses with high temporal resolution and thus provide complementary cues for robust UAV detection. However, existing RGB–event fusion detectors usually employ homogeneous feature extraction and generic fusion mechanisms, which are insufficient to handle heterogeneous modality degradation and exploit reliable cross-modal cues. To address this limitation, we propose SMG-UAV, a sparse mutual guided RGB–event fusion network for robust small-UAV detection. The proposed method integrates a hybrid dual-branch backbone for modality-specific representation learning, a Sparse Mutual Guided Bridge for bidirectional sparse cross-modal refinement, and a Selective Gated Pyramid Neck for multiscale enhancement of weak UAV responses. Experiments on the Florence RGB-Event Drone Dataset (FRED) and the Neuromorphic-RGB Drone Detection Dataset (NeRDD) demonstrate that SMG-UAV achieves state-of-the-art performance, outperforming the strongest competing method by an average of 5.2 points in AP50, while delivering stronger robustness under multiple challenging anti-UAV conditions.

Drones doi: 10.3390/drones10070485

Authors: Paawan Kumar Pritish Kumar Varadwaj Suneel Yadav

Modern agriculture in developing regions faces significant challenges due to labor scarcity and the health hazards associated with the manual application of chemical treatments. This study presents the design, development, and techno-economic evaluation of an experimental hexacopter unmanned ariel vehicle (UAV) platform specifically tailored for crop protection on fragmented, smallholder farmlands. The research aims to bridge the gap between expensive imported technology and the practical needs of small-scale farmers by providing a cost-effective, locally manufacturable solution. The methodology involved the integration of a modular spraying system and optimized control architecture into a high-stability hexacopter frame. Experimental evaluations focused on flight stability, payload capacity, and spray uniformity using water-sensitive media. The results indicate that the developed platform achieves high coverage efficiency while significantly reducing chemical waste compared to traditional manual methods. Furthermore, the economic analysis suggests that the operational costs are substantially lower than those of comparable imported systems, offering a favorable payback period within a few crop seasons. These findings demonstrate that an indigenous UAV spraying platform can enhance both operational safety and economic feasibility for smallholder agriculture.

Drones doi: 10.3390/drones10070484

Authors: Bo Lang Huamin Yang Ruoning Xu Hongzhi Li

In response to the challenges in UAV-oriented ground small-object localization and detection, including the easy loss of tiny target features, insufficient scale adaptability, severe interference from complex backgrounds, as well as high missed and false detection rates and the inadequate localization accuracy of the conventional YOLOv11n model in such scenarios, this paper takes YOLOv11n as the basic framework and performs systematic optimization from three aspects, network structure, core modules, and feature enhancement, proposing a lightweight small-object-enhanced detection algorithm named YOLOSO for UAV applications. By introducing a P2 high-resolution feature branch with a stride of 4, a four-scale detection structure consisting of P2-P3-P4-P5 is constructed, which reduces the minimum detection stride from 8 to 4 and alleviates the loss of detailed feature information for ultra-tiny targets. A bidirectional “top-down + bottom-up” multi-scale feature fusion strategy is utilized to improve the complementation between deep semantic information and shallow detailed features, while the core modules C3k2SO and C2PSASO are optimized and redesigned, respectively; by adjusting the channel compression ratio (0.25 for shallow modules and 0.75 for deep modules in C3k2SO; 0.25 in C2PSASO), optimizing the convolution kernel configuration (combining 1 × 3 and 3 × 1 convolutions), increasing the number of attention heads (from 4 to 8), and introducing residual connections with a 1 × 1 convolutional branch, the refinement and focusing ability of small-object feature extraction are improved. Additionally, an Enhanced Dual-branch Convolutional Block Attention Module (ED-CBAM) is proposed to further suppress background interference. Experimental results on the VisDrone2019-DET dataset demonstrate that the proposed YOLOSO contains 3.56M parameters and maintains a lightweight structure, attaining P, R, and mAP50 values of 47.2%, 36.8%, and 37.3% in the test set, which are 4.5 percentage points, 4.8 percentage points, and 3.7 percentage points higher than those of the baseline YOLOv11n (42.7%, 32.0% and 33.6%), respectively. Meanwhile, the medium-to-large version YOLOSO-S (14.85M parameters, 45.3% mAP50) reduces the number of parameters by 53.6% compared with the same-scale Rtdetr-L (32.0M) while achieving significantly better performance (37.8% mAP50). Experiments on the DOTAv1 dataset further confirm the generalization of YOLOSO, achieving 62.2% precision and 27.3% mAP50, outperforming all compared YOLO models. Evaluated on the DOTA-v1 dataset, YOLOSO achieves a feasible FPS of 20.53. Although slightly slower than mainstream lightweight YOLO models, the substantial accuracy gains fully offset the minor inference speed loss, and such performance trade-off is acceptable for practical UAV deployment. Ablation experiments verify that structural optimization (2.8 percentage points mAP50 improvement, from 33.6% to 36.4%) and the proposed C2PSASO (0.7 percentage points mAP50 improvement to 34.3%) and C3k2SO (1.4 percentage points mAP50 improvement to 35.0%) modules all contribute positive performance gains with favorable complementarity. While retaining lightweight characteristics, the model effectively enhances the detection accuracy of small objects in unmanned aerial vehicle scenarios and can provide technical references for practical applications such as remote sensing monitoring and security patrolling.

Drones doi: 10.3390/drones10070483

Authors: Jianjie Qiu Yichao Cai Hao Li Lei Ni Kai Yuan Siyuan Cui

Multi-UAV cooperative search with static unknown targets requires both efficient regional allocation and responsive local maneuvering. However, single-level learning methods often suffer from redundant coverage, unclear division of labor, and unstable training. This paper proposes a high- and low-level decoupled reinforcement learning method for multi-UAV cooperative search. The high level periodically generates UAV-specific regional goals from visitation maps, target-existence belief maps, and UAV positions, while a spatial self-attention module enhances the representation of unvisited regions, high-belief target areas, and UAV distributions. The low level performs discrete steering actions based on local observations and high-level contexts, supported by a structured reward that encourages coverage, target discovery, goal-oriented progress, repeated-visit suppression, and boundary-safe motion. Simulation experiments are conducted in a two-dimensional grid environment with static targets and ideal sensing. Under this simplified simulation setting, the proposed method achieves higher training return and coverage rate than representative baseline algorithms while maintaining a high final target discovery rate and reaching the discovery threshold earlier. Ablation and visualization results further demonstrate the effectiveness and interpretability of the proposed hierarchical guidance mechanism within the considered simulation scenario.

Drones doi: 10.3390/drones10070482

Authors: Nader Alotaibi Wojdan BinSaeedan

In the original publication [...]

Drones doi: 10.3390/drones10070481

Authors: Yuntao Xu Bing Chen Feng Hu Yue Cai Zhuqing Xu

In resource-constrained UAV swarm systems, multimodal sensory data are often affected by complex environmental factors, resulting in modality missing, signal degradation, and asynchrony, which significantly reduce the reliability of multimodal learning and incremental model updates. To address this issue, we propose a Compensatory Collaboration Modality-Balanced Sample Selection framework (CC-MBS), which improves robustness through modality quality modeling and cross-UAV collaborative compensation. Specifically, a modality confidence vector is introduced to quantify modality reliability from missing rate, degradation, and asynchrony. A lightweight collaboration mechanism is designed to exchange low-dimensional confidence information instead of high-dimensional features or model parameters. Based on the compensated confidence, a modality-aware sample selection strategy is further developed to prioritize high-value samples under limited memory. Experimental results in simulated UAV-swarm-inspired benchmark settings show that CC-MBS outperforms representation-based methods such as ShaSpec and its parameter aggregation variants (AVG, PFM, POW) in both modality compensation accuracy and communication–computation efficiency under missing conditions. In addition, it achieves stronger robustness than MBS and training-dynamics-based methods such as EL2N and GraNd in sample selection. These results demonstrate that CC-MBS effectively improves robustness and data efficiency for multimodal incremental learning under incomplete modalities.

Drones doi: 10.3390/drones10070479

Authors: Xiaoyi Liu Yuhan Yin Kunxiao Wu Yetong Zhang Jianyong Zheng Penghao Chen Kangxin Cai Fei Mei

To address the problems of closed-loop task organization, strong corridor constraints, and path failure after local disturbances in unmanned aerial vehicle (UAV) inspection of gas-insulated switchgear (GIS) rooms, this paper proposes a topology-and-corridor-guided bias-suppressed D* (TCG-BS-D*) method for closed-loop three-dimensional (3D) path planning and local replanning. The proposed method constructs a structured guidance model based on the inspection-corridor topology, generates local 3D path segments according to a predetermined inspection sequence, and forms a nominal closed-loop inspection path through bias suppression and path regularization. Meanwhile, for local maintenance blockage and dynamic disturbance scenarios, an alternative local replanning strategy is applied to the affected path segments. Simulation results show that, under the static closed-loop inspection condition, the proposed method achieves a total path length of 700.22 m, a total inspection time of 269.32 s, an average safety clearance of 8.18 m, 37 large-angle turns, a corridor adherence rate of 80.73%, and a task completion rate of 100%, showing superior performance in inspection efficiency, safety margin, trajectory regularity, and corridor consistency. Under the local blockage condition, the replanned path introduces path-length and time increments of 71.29 m and 25.88 s, respectively, while maintaining the minimum safety clearance at 1.52 m and increasing the corridor adherence rate to 83.91%. Under dynamic disturbance conditions, the minimum dynamic safety clearance is improved from −2.71 m to 17.84 m, effectively eliminating the local dynamic collision risk. The results demonstrate that the proposed method can balance closed-loop path-generation efficiency, corridor-structure consistency, safety margin, and adaptability to local disturbances, providing an effective solution for UAV inspection path planning in GIS rooms.

Drones doi: 10.3390/drones10070480

Authors: Chenyang Sun Xingyu He Duo Qi Xiaoyue Ren

Three-dimensional UAV operations require path planning methods that can jointly maintain route efficiency, threat avoidance, and trajectory smoothness under spatially distributed and time-varying constraints. To address this problem, this paper develops an integrated Dual-Layer Adaptive T-perturbation and Opposition-based Multi-Objective Particle Swarm Optimization framework, termed DATO-MOPSO, for 3D UAV path planning in complex threat environments. The method integrates a dual-layer adaptive inertia-weight and velocity-regulation mechanism with symmetric T-perturbation, an elite quasi-opposition-based learning strategy for diversity recovery and feasible local exploitation, and an archive-driven simulated annealing rule for stagnation-aware personal-best updating. A three-objective model minimizing path length, threat exposure, and path smoothness is established, and comparative experiments against MOPSO, ZAMOPSO, NSGA-II, and SPEA2 are conducted in both static and dynamic environments, together with statistical and ablation analyses. In the static scenario, DATO-MOPSO achieved the highest mean HV and stable repeated-run performance, but its IGD was comparable to ZAMOPSO with higher computational cost. In the dynamic scenario, DATO-MOPSO showed its main advantage, achieving the highest mean HV and the lowest mean IGD with statistically significant HV and IGD improvements over all baselines. Overall, DATO-MOPSO is most advantageous in time-varying complex threat environments, whereas its static-scenario advantages are accompanied by higher computational cost.

Drones doi: 10.3390/drones10070478

Authors: Kunlin Han Yiming Liu Ziming Xiong Jiafeng Hu Hao Lu Minqian Sun Tongxin Zhang

The escalating security risks associated with unauthorized unmanned aerial vehicles (UAVs) in advancing smart cities necessitate the development of robust active countermeasures. This work presents a novel approach centered on a UAV-borne flexible net system and provides a rigorous investigation into its complex nonlinear dynamics. This study establishes a lumped-mass, semi-spring–damper dynamic model of the flexible capture net, characterizing its key dynamic properties, including deployment performance, aerodynamic attitude, and the high-impact phenomena of collision and entanglement with the target UAV. To verify the reliability of the proposed method, numerical simulations are combined with field tests for systematic validation. Comparative analysis reveals excellent quantitative agreement, with over 80% conformity in the net’s spatial configuration between simulated and experimental results. This paper illuminates the fundamental principles governing energy dissipation and transient tension dynamics pre- and post-capture. This study provides preliminary evidence for the feasibility of the proposed method and identifies key directions for future investigation. The findings offer guidance for the design and optimization of future systems intended to neutralize low, slow, and small (LSS) aerial threats.

Drones doi: 10.3390/drones10070477

Authors: Youyao Gao Tongchang Liu Huan Jin

This paper studies large-scale last-mile delivery using a heterogeneous fleet of trucks, onboard drones in a hybrid truck–drone mode, and independent drones. Orders are first screened by a feasibility check; feasible orders are then assigned to one of the three modes by a delivery mode selection policy and routed using mode-specific planning algorithms. The delivery mode selection policy is trained with Proximal Policy Optimization (PPO), warm-started by behaviour cloning from heuristic decisions. For route planning, we use a five-step procedure for the hybrid mode and simple depot round trips for independent drones. Experiments on Solomon VRPTW benchmarks and extended instances (100/200/400 customers; R/C/RC distributions) show lower total cost than representative heuristic baselines and metaheuristics, with practical runtime. Sensitivity analysis over fleet sizes further indicates competitive performance across a range of truck and drone configurations, especially for medium and large fleets.

Drones doi: 10.3390/drones10070476

Authors: Didem Cicek Murat Simsek Burak Kantarci

Truck–drone collaborative delivery (TDCD) refers to a coordinated logistics paradigm in which drones are deployed from delivery trucks to serve nearby customers, enabling parallelized last-mile operations. Much of the existing TDCD literature relies on synthetic datasets and manufacturer-declared drone specifications, which may overestimate performance in real-world operations. This study develops an empirically informed, route-based Mixed-Integer Linear Programming (MILP) framework that integrates empirically derived drone performance models with constrained fleet allocation decisions. Using delivery routes from the Amazon Last Mile Routing Dataset (2021), we consider three electric trucks departing from a common depot, each equipped with drones drawn from a shared fleet of 10 units. Drone flight time and energy consumption are modeled using regression functions calibrated with real flight test data from a DJI Matrice 100 platform, capturing observed variations due to payload and operational conditions. The optimization jointly determines truck stop selection, customer assignments, and drone allocation while minimizing a weighted combination of route makespan, total energy consumption, and fleet size under operational and energy constraints. The results indicate that coordinated truck–drone delivery can achieve substantial reductions in both delivery completion time and energy consumption relative to conventional truck-only delivery. These findings demonstrate the effectiveness of coordinated truck–drone operations under realistic constraints and highlight the importance of data-driven modeling and fleet-level resource allocation in improving last-mile delivery performance.

Drones doi: 10.3390/drones10060475

Authors: Maria Căldărar Tiberius-Florian Frigioescu Mădălin Dombrovschi Gabriel-Petre Badea Laurențiu Ceatră Flavia-Elena Blaga Răzvan Roman

The development of low-emission and reliable propulsion systems is essential for extending the operational capability of unmanned aerial vehicles (UAVs). Although aviation decarbonization is widely recognized as an important objective, it must be considered within the broader context of limited renewable-energy availability. Recent system-level analyses of transportation decarbonization have shown that the allocation of renewable electricity and sustainable fuels should prioritize sectors where direct electrification is most efficient, while hard-to-electrify sectors require alternative pathways. Aviation is one of the most difficult transport sectors to electrify because of strict energy-density requirements, especially for long-endurance airborne platforms. Therefore, sustainable liquid fuels and hybrid propulsion systems should not be considered universal replacements for electrification, but rather complementary solutions for applications where batteries alone cannot provide the required endurance, payload capacity or operational flexibility. In this context, the present study focuses on alcohol–kerosene blends for hybrid UAV power systems, where liquid-fuel energy density and partial emission reduction remain relevant engineering requirements. This work provides one of the first systematic experimental evaluations of ethanol–, butanol– and octanol–kerosene blends in a micro-turboprop engine operating as part of a hybrid UAV power-generation architecture. Unlike previous studies focused mainly on micro-turbojet thrust response, the present work evaluates the coupled influence of alcohol chain length and blending ratio on exhaust gas temperature, gaseous emissions, electrical output and operational stability under multi-load conditions representative of UAV operation. Jet-A and nine alcohol–kerosene blends containing 10%, 20% and 30% ethanol, butanol or octanol by volume were tested over four operating regimes, from idle to 2500 W electrical load. The results show that ethanol blends provided the strongest CO reduction, with E30 reducing CO by 24.9% relative to Jet-A under R3, while E10 offered the most balanced behavior across the full operating range. Higher ethanol fractions improved CO suppression but introduced NOx and low-load stability penalties. Octanol blends, particularly O20, exhibited the most kerosene-like and stable response, supporting reliable power delivery with reduced operational variability. Butanol blends showed intermediate behavior without providing a dominant advantage. A multi-criteria evaluation combining emissions, EGT behavior, relative performance, operational stability and cost identified E10 as the best overall compromise for hybrid UAV use. The study demonstrates that alcohol chain length produces nonlinear system-level effects in hybrid micro-turboprop architectures and provides an experimental basis for fuel selection in low-emission UAV power systems.

Drones doi: 10.3390/drones10060474

Authors: Hexing Zheng Haitao Gu Tianzhu Gao

The detection and localization of large underwater targets are important for maritime security, marine resource exploration, and underwater situational awareness, while the increasing acoustic stealth of underwater vehicles has limited conventional acoustic methods. This review provides a systematic overview of non-acoustic detection and localization technologies for large underwater targets, with emphasis on their relevance to unmanned aerial, surface, and underwater platforms. Wake-based detection, magnetic anomaly detection (MAD), and gravity anomaly detection (GAD) are reviewed as three representative non-acoustic routes. A bibliometric analysis is first conducted to summarize research trends, major contributors, and emerging hotspots. Wake-based methods are discussed in terms of wake signatures, modeling approaches, sensing platforms, and localization potential. MAD is analyzed from the perspectives of magnetic dipole modeling, target-based detection, noise-based detection, artificial intelligence (AI)-based detection, and magnetic localization. GAD is discussed with respect to physical feasibility, gravity-gradient target modeling, inversion methods, and engineering constraints. The review shows that wake-based methods are suitable for wide-area search and trajectory inference, MAD is relatively mature for short-range confirmation and localization, and GAD remains promising but less mature. Future research should focus on onboard sensors, platform stability, weak-signal extraction, background suppression, quantitative evaluation metrics, multi-source fusion, autonomous mission planning, and multi-platform collaboration.

Drones doi: 10.3390/drones10060473

Authors: Chengyuan Pang Zongpu Li Le Ru Fan Sun Jiaxu Chen

In the task planning of heterogeneous unmanned aerial vehicle formations, problems such as dynamic topological instability and sparse Pareto front exist, which affect the robustness of the planning. To address this, this paper proposes a cooperative task planning method based on multi-objective dolphin echolocation optimization driving. Firstly, a differentiated dynamic model of heterogeneous unmanned aerial vehicles covering different configurations such as rotors and fixed wings is constructed, and a dynamic communication topology model is established based on time-varying graph theory to quantify transmission delay and link stability. Then, a multi-objective optimization model is designed with task completion, energy balance, and time cost as the core, Bayesian networks are introduced to construct a dynamic threat field, and risk assessment and real-time response are achieved in complex environments. Based on this, a multi-objective dolphin echo optimization algorithm is adopted to solve the model, and its echo beam focusing search and adaptive weight allocation mechanism are utilized to effectively improve the convergence and distribution of the Pareto solution set. Finally, a “decision execution” hierarchical collaborative control architecture is constructed, utilizing the decision layer to output a global planning scheme and the execution layer to achieve rolling optimization and precise tracking of instructions through distributed model predictive control. The simulation test results show that this method can maintain high task completion, energy balance, and communication stability in different formation sizes and complex environments significantly better than traditional algorithms. When the formation size is between 20 and 60 sorties, the hypervolume (HV) index of this method is superior to that of the comparison method. In cases of sudden obstacles and complex electromagnetic interference scenarios, the average energy consumption of a single unmanned aerial vehicle after applying this method is maintained at 150–250 Wh, and the transmission delay is stable at 50–200 ms. The experimental results verify that this method has good planning robustness and collaborative real-time performance.

Drones doi: 10.3390/drones10060472

Authors: Ehsan Kouchaki Miguel Angel de Frutos Carro Jose Ramiro Martinez-de Dios Anibal Ollero

Despite the large amount of successful existing methods and frameworks for planning sets of multiple unmanned aerial systems (UASs), there is still a lack of coordination frameworks that are capable of coping with real-world operational conditions. This paper presents U-Plan, an integrated management framework for the coordination of multi-UAS missions. U-Plan is designed to plan, schedule, monitor, and replan a heterogeneous set of UASs to complete point of interest (PoI) visiting missions while ensuring that all the generated trajectories are safe, feasible, and compliant with the required PoIs’ arrival times, UAS kinematics and energy constraints, and the existing 3D no-fly zones (NFZs). U-Plan is designed as a practical tool for strongly dynamic missions and is built upon three core components: (1) an NFZ-aware route computation method that explicitly accounts for NFZs prior to vehicle routing problem (VRP) optimization, resulting in shorter NFZ-safe routes; (2) a trajectory smoothing module that ensures the generation of kinematically feasible trajectories for fixed-wing UASs; and (3) a mission supervision module for real-time monitoring and replanning in case of changes in the UAS, mission, wind speed, or airspace restrictions. To validate the proposed architecture, we conducted rigorous experiments utilizing the VECTOR-SIL autopilot and Visionair Ground Control Station to realistically replicate the behavior of certified fixed-wing autopilots under various weather conditions using the exact same hardware and flight control software that runs onboard the physical drones. The validation shows U-Plan’s capacity to efficiently satisfy complex mission requirements with strong scalability. Due to its high computational efficiency, U-Plan enables online mission replanning, allowing UAS fleets to seamlessly adapt to changes that are typical of real-world operational scenarios.

Drones doi: 10.3390/drones10060471

Authors: Yapeng Wang Xirui Xu Shenglong Yang Fei Wang

Spatially explicit water-quality information is critical for precision management in pond aquaculture but point sampling alone cannot capture pond-to-pond heterogeneity in multi-unit farms. This single-date, single-farm study re-evaluated the potential of UAV hyperspectral imagery for water-quality screening in inland aquaculture ponds in Shanghai, China, using site-matched extraction from a 138-band orthomosaic (450–998 nm, Cubert S185) acquired during a single UAV survey on 24 August 2023 and matched with 23 GPS-registered sampling sites. Eight water-quality parameters were analyzed: chemical oxygen demand (COD), total phosphorus (TP), total nitrogen (TN), ammonium (NH4+ ), nitrite (NO2−), nephelometric turbidity unit (NTU), chlorophyll-a (Chla), and total suspended solids (TSS). Raw single-band correlations were modest (r= 0.236–0.417), but two-band difference spectral indices (DSI), normalized spectral indices (NSI), and ratio spectral indices (RSI) substantially improved sensitivity, with r reaching 0.558–0.928. Quadratic inversion models were calibrated on the full dataset and assessed using three validation layers: two-fold cross-validation, nested leave-one-pond-out (LOPO) validation with within-fold predictor reselection, and extraction-window sensitivity tests. Bootstrap 95% confidence intervals for calibration (Cal) R2 characterize small-sample uncertainty (n = 23). Three parameters satisfied all three defensibility criteria (Cal R2 > 0.5, CV R2 > 0.2, and LOPO R2 > 0.2): NH4+ (Cal R2 = 0.836 [0.61, 0.94]; LOPO R2 = 0.420), COD (0.607 [0.34, 0.82]; 0.328), and NTU (0.862 [0.77, 0.96]; 0.204). TP, TN, NO2−, TSS, and Chla showed overfit behavior under nested holdout and were demoted to exploratory products. A TreeSHAP analysis confirmed that band-to-band contrast carried more explanatory power than raw reflectance magnitude. Extraction-sensitivity tests further demonstrated that positional uncertainty (±2-pixel offset: ΔCV R2= 0.23–0.41) exceeded averaging-window sensitivity (3 × 3→10 × 10: ΔCV R2 ≤ 0.11), identifying geolocation control as the dominant robustness constraint. This single-date, single-farm reanalysis suggests that UAV hyperspectral imagery may support exploratory pond-scale screening of NH4+, COD, and NTU. However, robust quantitative inversion and broader transferability remain unverified and will require denser sampling, improved geolocation control, pond-edge masking, multi-site observations, and multi-temporal calibration.

Drones doi: 10.3390/drones10060470

Authors: Yufeng Li Erming Tian Xiaofeng Chen Huiyan Han Xinya Zhang

Complex urban scenarios impose high demands on the environmental perception capabilities of unmanned systems, which serve as a prerequisite for executing autonomous missions such as disaster response, infrastructure inspection, and smart city operations. UAVs, leveraging their high mobility, can provide accurate prior maps and wide-area aerial observation for unmanned ground vehicles. However, their long-range perception accuracy is limited. Conversely, UGVs can achieve high-precision environmental perception along their navigation paths using prior maps, but suffer from a constrained field of view. The collaboration between the two platforms complements their respective strengths, thereby enhancing 3D object perception and mapping accuracy in complex scenarios. To address the aforementioned challenges, this study proposes a cross-platform feature fusion method for 3D object perception and an incremental map updating approach for UAVs and UGVs. First, a dynamic SLAM method that integrates an optimized YOLOv8 with ORB-SLAM3 is employed to mitigate map blurring caused by dynamic noise, providing prior map information for UGVs. Second, a multimodal fusion perception model is constructed for UGVs, utilizing attention mechanisms to achieve deep fusion of multimodal Bird’s-Eye-View (BEV) features. This overcomes issues such as diminishing complementarity between modalities and weak temporal feature associations. Finally, an air ground fusion model based on a cross-attention mechanism is developed to fuse aerial view features with ground-based fused BEV features across platforms, yielding a unified feature representation for 3D object detection and generating a fused high-precision map. Experimental results demonstrate that under complex occlusion scenarios in a simulated dataset, the proposed collaborative perception system improves the mean Average Precision (mAP) by 12.7% and 15.7% compared to using a single UAV or a single UGV, respectively, while increasing the map accuracy F1-score by 0.21. This study provides technical support for achieving real-time and accurate air ground collaborative perception in complex dynamic environments.

Drones doi: 10.3390/drones10060468

Authors: Guoquan Xiao Ruijie Rao Yuanming Chen Xiaobin Hong

Autonomous navigation of unmanned surface vehicles (USVs) in complex obstacle scenarios remains challenging due to redundant perception inputs, unstable value estimation, and inefficient policy convergence. To address these problems, this paper proposes LDA-D3QN, an improved deep reinforcement learning method for USV autonomous navigation. The proposed method constructs a compact navigation state representation by combining target-related information with local obstacle features, allowing the agent to retain key decision-making information while reducing unnecessary environmental redundancy. Based on this representation, an enhanced value-learning framework is developed to improve the stability of navigation decisions in cluttered environments. Moreover, a reward-guided and staged training strategy is introduced to help the agent gradually adapt to increasingly complex navigation tasks. The proposed method was evaluated on a Unity–ROS–MATLAB integrated simulation platform. Experimental results show that LDA-D3QN achieves superior overall navigation performance compared with several representative reinforcement learning algorithms. Specifically, the proposed method achieves a final training success rate of 91.4%, outperforming PPO (82.3%), Dueling DQN (78.5%), Double DQN (79.8%), and Rainbow DQN (86.5%). Additional tests in complex multi-obstacle and multi-target scenarios further demonstrate that the learned policy can generate safe, stable, and effective navigation behaviors. Preliminary validation using real-USV sensor data also confirms the feasibility of the LiDAR and GPS data processing procedures, providing a basis for future closed-loop autonomous navigation experiments and multi-sensor fusion deployment.

Drones doi: 10.3390/drones10060469

Authors: Yunkai Qiu Tianyu Yang Yuanhong Liu

Planning a low-detectability route for a fixed-wing UAV in mountainous environments with radar-based sensing constraints remains highly challenging. Conventional approaches struggle to simultaneously ensure both path quality and operational safety. To address this problem, this paper proposes a two-layer planning framework in which a Risk-A* algorithm provides a global reference route, while a model predictive control (MPC) scheme performs online receding-horizon trajectory optimization. The proposed method combines prior radar-platform information with time-varying detection-risk cues to generate terrain-masked and detection-feasible trajectories. In this study, the framework is instantiated and evaluated on a representative fixed-wing medium-altitude long-endurance (MALE) UAV, where “medium-altitude” denotes the platform class rather than the flight altitude maintained during the low-altitude flight segment. As a result, the UAV can complete the entire flight while reducing the detection-risk metric and overall planning cost. Simulation results on two DEM-based mountainous terrain zones, with one nominal start-goal pair specified in each terrain zone and 50 repeated executions conducted for each scenario, demonstrate that the Risk-A*-MPC framework may yield slightly longer paths and flight times; however, it consistently satisfies the no detection-threshold-exceedance requirement under the tested conditions. In the two main terrain-zone scenarios, the recorded maximum MPC solve time was 0.812 s, which remained below the 3 s control update period and supports the real-time executability of the online MPC layer on the tested computational platform.

Drones doi: 10.3390/drones10060467

Authors: Gengsong Li Yi Liu Qibin Zheng Kun Liu

Efficient cooperative task allocation is essential for multiple unmanned aerial vehicles (UAVs) performing complex missions. However, diverse dynamic events in real-world scenarios require rapid response through dynamic task allocation (DTA). Although evolutionary algorithms have been widely adopted for DTA, existing methods often fail to maintain consistency between allocation decisions and actual operational states, consider only limited classes of dynamic events, and still leave room for performance improvement. This paper formulates multi-UAV DTA as a dynamic multi-objective optimization problem (DMOP) that jointly minimizes the residual target value and mission makespan, incorporating a state inheritance mechanism and a comprehensive set of dynamic events covering multiple facets of disruptions in observation task scenarios. To solve this DMOP, a multi-swarm dynamic crow search algorithm for task allocation (MDCSATA) is proposed, which integrates five strategies: violation-tolerant multi-swarm co-evolution for feasibility and diversity; objective-oriented heuristic initialization to accelerate convergence; an adaptive position update for better exploration and exploitation; stagnation and elite guided perturbation for intensified local exploitation; and an event-aware change response for rapid adaptation to dynamic events. Experiments on three constructed scenarios against seven state-of-the-art algorithms show that MDCSATA achieves superior performance on the evaluation metrics with acceptable runtime. It obtains the best MHV and MIGD in all scenarios, improving MHV by at least 0.93% and reducing MIGD by at least 12.92% across scenarios. These results confirm its effectiveness for DTA.

Drones doi: 10.3390/drones10060466

Authors: Yuxuan Ji Linya Liu Yong Wang Xi Vincent Wang Lihui Wang

Existing truck–drone collaborative routing models predominantly assume fixed flight speeds, overlooking the non-linear coupling among speed, payload, and energy consumption, which limits urban delivery efficiency. To bridge this gap, this paper proposes the multiple flying sidekick traveling salesman problem with variable drone speed (mFSTSP-VDS). Formulating drone cruising speed as a continuous variable under strict non-linear energy constraints, we design a hybrid algorithm (ALNS-SA-VND) to jointly optimize routing, task allocation, and speed. Empirical analysis of Wuhan’s road network demonstrates the VDS strategy’s robustness. Specifically, VDS reduces the system makespan by up to 17.5% compared to rigid maximum-speed strategies, with consistent stability across varying load scenarios. By adaptively trading permissible battery capacity for temporal synchronization, VDS effectively mitigates unnecessary truck waiting times at rendezvous nodes. This study quantitatively validates the impact of sortie-specific speed adaptation on time efficiency, providing an exploratory theoretical baseline for tactical-level planning in smart logistics networks.

Drones doi: 10.3390/drones10060465

Authors: Min Zhang Song Gao Chaobo Chen Qingmin Liu Kai Cao Tianli Ma

This paper proposes a dual-loop layered control mechanism for the dynamic trajectory tracking of non-holonomic unmanned ground vehicles (UGVs). The proposed scheme enhances steady-state precision while guaranteeing parameter convergence under specified trajectory constraints. To tackle the underactuated constraints of Unmanned Ground Vehicles, the control mechanism is structured into kinematic and dynamic loops. Specifically, a kinematic controller is first synthesized to serve as a virtual control law, generating desired velocity commands. Subsequently, a layered adaptive control strategy based on the Immersion and Invariance technique is developed for the dynamic loop. This strategy integrates a parameter estimation layer, which utilizes tailored tuning functions to ensure the exponential convergence of estimation errors under the condition that the reference trajectory is not persistently vertical. A controller design layer is then responsible for uncertainty compensation. By decoupling parameter adaptation from control law synthesis, the proposed mechanism circumvents the structural limitations of the certainty equivalence principle. Theoretical analysis confirms that the proposed design achieves almost-global asymptotic tracking. Simulation results demonstrate that the mechanism resolves the imprecise parameter convergence inherent in traditional adaptive schemes, eliminates steady-state pose fluctuations during time-varying trajectory tracking, and achieves asymptotic convergence of tracking errors.

Drones doi: 10.3390/drones10060464

Authors: Yuan Chen Yong Zhang Yiheng Wang

A novel hybrid ISSA-GWO (Improved Sparrow Search Algorithm–Grey Wolf Optimizer) is proposed for the path planning of Unmanned Wing-in-Ground-Effect Craft (UWIGC), integrating ground-effect constraints and island-reef environments into a unified optimization framework. Leveraging its exceptional ultra-low-altitude flight capability and high economic efficiency, the UWIGC offers unique advantages in maritime missions such as island patrol and rapid replenishment. However, its path planning faces the dual challenge of precise obstacle avoidance and ultra-low-altitude maintenance, due to the obstacle distribution in island regions and the altitude window constraints inherent to ground-effect flight. To address this, the proposed method integrates the swarm intelligence of the Sparrow Search Algorithm and employs a self-destruction mechanism to escape local optima. Furthermore, it combines the hierarchical guidance of the Grey Wolf Optimizer to enhance convergence accuracy. The algorithm incorporates ground-effect maintenance constraints and an island-reef threat model, and it smooths the final path using cubic B-spline curves. Simulation results demonstrate that the proposed algorithm outperforms the standard Sparrow Search Algorithm, Grey Wolf Optimizer, and Particle Swarm Optimization in terms of convergence speed, optimization accuracy, and obstacle avoidance success rate. It is capable of generating a feasible, safe, and smooth path, thereby supporting the autonomous navigation of UWIGC in island reef waters.

Drones doi: 10.3390/drones10060463

Authors: Emilia-Georgiana Prisăcariu Oana Dumitrescu

Future planetary exploration missions are expected to employ increasingly sophisticated aerial, ground, and hybrid robotic systems that must interact directly with extraterrestrial regolith during landing, takeoff, mobility, anchoring, sampling, and subsurface investigation activities. Consequently, understanding the mechanical behavior of lunar and Martian regolith is essential for the design and reliable operation of autonomous exploration platforms. This review examines drone–regolith interaction from a system-level perspective by integrating knowledge of regolith mechanical properties with findings from penetration mechanics, anchoring technologies, mobility studies, numerical modelling, and in situ mission observations. Key differences between lunar and Martian regolith are identified, highlighting the predominantly friction-driven behavior of lunar soils and the combined frictional–cohesive response frequently observed in Martian regolith. Lessons learned from planetary missions, particularly the Apollo and Mars InSight programs, demonstrate how system–soil mismatch can significantly affect penetration, stabilization, and surface-operation performance. The review further discusses the implications of regolith mechanics for landing stability, rotor–surface interaction, anchoring efficiency, subsurface access, and future drone-assisted exploration concepts. Finally, current challenges in experimental validation and numerical modelling are assessed, emphasizing the need for integrated approaches that combine soil mechanics, robotic system design, and environmental constraints to enable reliable autonomous operations on the Moon and Mars.

Drones doi: 10.3390/drones10060462

Authors: Mădălin Dombrovschi Daniel-Eugeniu Crunțeanu

Next-generation unmanned aerial vehicles require compact propulsion systems capable of providing efficient vertical lift, rapid thrust vectoring, and improved maneuverability. Cyclorotors represent a promising alternative to conventional propellers, but their aerodynamic behavior is governed by highly unsteady blade–wake interactions, making performance prediction challenging. This study investigates a four-bladed cyclorotor equipped with NACA 0012 airfoils using transient computational fluid dynamics simulations and a calibrated semi-analytical blade-element model. The numerical analysis was performed over a rotational-speed range of 368–2305 rpm and for several pitch-amplitude configurations, including 5°, 7.5°, 10°, 12.5° and 15°. The results showed that the favorable pitch amplitude decreases with increasing rotational speed, shifting from larger amplitudes at low RPM to approximately 5° at higher RPM values. The semi-analytical model reproduced the main CFD trends for lift, drag, moment, and power, providing a reduced-order tool for preliminary cyclorotor performance estimation. The comparison confirmed that pitch-amplitude selection strongly influences aerodynamic loading and efficiency and should therefore be adapted to the operating regime. The proposed CFD-based methodology, supported by semi-analytical modelling, provides a useful framework for the aerodynamic characterization and early-stage optimization of cyclorotor propulsion systems for UAV applications.

Drones doi: 10.3390/drones10060461

Authors: Shihab Hasan Tarek Sheltami Ashraf Mahmoud

Urban Unmanned Aerial Vehicle (UAV) logistics operations are frequently constrained by the intersection of limited battery endurance and dynamic ground traffic. When mobile depots are delayed by congestion, onboard drone fleets experience extended idling periods, leading to constrained sortie generation and reduced asset utilization. To address this bottleneck, this paper introduces a traffic-predictive multi-UAV dispatch framework for deterministic day-ahead planning under modeled urban operating conditions. By coupling a count-derived macroscopic speed surrogate learned using XGBoost with a Particle Swarm Optimization (PSO)–Mixed-Integer Linear Programming (MILP) optimization architecture, the framework synchronizes mobile depot trajectories with forecasted low-congestion windows and pre-allocates endurance-feasible parallel aerial sorties. Controlled computational experiments across 30 synthetic routing instances demonstrate the potential value of this approach within the stated modeling assumptions. Compared to baseline clustered deployments, the traffic-aware framework raises mean fleet utilization from 0.43 to 0.63—a 46.2% relative improvement driven by temporal compression of the mission window rather than an absolute increase in flight hours. Furthermore, the proposed framework reduces total mission completion time by 69.87% relative to the conventional truck-only baseline, while achieving a 29.58% incremental gain over static speed drone deployments. These findings suggest that incorporating predictive ground traffic information into day-ahead UAV scheduling can improve modeled fleet efficiency; however, field validation with measured route-level speeds, real delivery demand, and operational constraints remains necessary before deployment-level claims can be made.

Drones doi: 10.3390/drones10060460

Authors: Chengyan Ji Xiye Guo Yuqiu Tang Xiaohe Han Yuhang Song

In complex low-altitude environments, unmanned aerial vehicles (UAVs) require reliable positioning, yet Global Navigation Satellite System (GNSS) signals are vulnerable to occlusion and interference. Pseudolite-augmented cooperative localization, which combines ground base-station signals with inter-UAV relative observations, can complement GNSS in such environments. However, two practical issues remain in real-world deployment: UAV-to-base-station (U-B) and UAV-to-UAV (U-U) observations have markedly different error statistics that a unified noise adjustment cannot handle, and the conservative covariance estimates produced by Covariance Intersection (CI) fusion bias the innovation-based adaptive noise estimation in distributed architectures. To address these issues, this paper proposes a Distributed Group Covariance Compensation Adaptive Kalman Filter (DGCC-AKF) for collaborative enhancement of UAV regional localization. DGCC-AKF establishes a group adaptive mechanism that independently adjusts the noise covariance matrices of U-B and U-U observations, enabling observation-type-level adaptive weighting that suppresses anomalous U-B or U-U measurements at the group level. In addition, a bounded covariance compensation factor is incorporated to alleviate the CI-induced conservatism in the adaptive noise estimation. The proposed method is evaluated on a 2800 km2 semi-physical testbed based on the Ground-based High-precision Local Positioning System (GH-LPS) pseudolite network using measured U-B observations and high-dynamic (>300 km/h) flight trajectories collected from a fixed-wing platform across three independent flight sessions. Results demonstrate that under observation fault periods, the proposed method improves 3D positioning accuracy by up to about 75% over single-UAV extended Kalman filter (EKF). Compared with two advanced algorithms in this field, variational Bayesian adaptive Kalman filter (VBAKF) and maximum correntropy criterion Kalman filter (MCC-EKF), it is the only scheme that remains accurate and stable across all UAVs and fault types. The framework provides a practical step toward field deployment for resilient multi-UAV cooperative navigation in pseudolite-augmented GNSS-denied regions.

Drones doi: 10.3390/drones10060459

Authors: Wei Tang Qilong Li Yueping Peng Hexiang Hao Wenchao Kang Xuekai Zhang Liming Hou Hongyan Lu

Drone-to-drone (D2D) detection is a critical yet underexplored task in low-altitude intelligent perception, where UAV targets are often small, weakly textured, motion-affected, and disturbed by complex backgrounds and environmental changes. Existing cross-domain detection datasets mainly focus on ground objects or single-factor shifts, making them insufficient for evaluating D2D detection under coupled real-world variations. To address this gap, we present TriCross-D2D, an RGB air-to-air UAV detection dataset and benchmark with three explicit domain shifts: scene, viewpoint, and weather. Built from real flight videos and controlled synthetic fog, TriCross-D2D contains 13 RGB video sequences, 23,403 raw frames, 7045 benchmark images, and 9771 annotated UAV instances. It provides a fixed split of 4045 Source_train images, 2000 Target_train images, and 1000 Target_val images, supporting both unsupervised domain adaptation (UDA) and semi-supervised domain adaptation (SSDA). The dataset is dominated by small objects, with extremely tiny, tiny, and small targets accounting for 73.8% of all instances. Benchmark results show that existing cross-domain detectors still perform limitedly on TriCross-D2D, especially under stricter localization and recall metrics. Single-factor analysis further reveals that the coupled scene–viewpoint–weather protocol is more challenging than isolated shifts, with viewpoint variation producing a particularly strong domain gap. As an exploratory enhanced baseline, SCOPE-DA-RTDETR improves DA-RTDETR from 28.63/13.12/22.39 to 29.94/13.71/23.40 in AP50/AP50–95/AR, showing consistent but modest gains. These findings demonstrate that TriCross-D2D provides a challenging and discriminative benchmark for cross-domain D2D small-object detection.

Drones doi: 10.3390/drones10060456

Authors: Liruizhi Jia Jiazhan Gao Zuolong Li Heng Shi Jihong Zhu

UAV remote sensing provides centimetre-level imagery for fine-grained cotton growth monitoring, yet existing segmentation models face three challenges: cotton fields exhibit a pronounced row and column structure that standard convolutions struggle to capture; conventional decoders fuse features statically, suppressing fine boundary cues; and the pixel-level class distribution is severely imbalanced. We present DCA-DeepLab, built on DeepLabv3+ with three task-specific components: a Dual-Coordinate Attention Gating (DCAG) module that decouples horizontal and vertical dependencies to encode row and column structures; a Multi-Scale Attention-Guided Modulated Feature Merging (MSAM-MFM) module that reweights semantic and detail features at each location; and an adaptive pixel-level modulated focal loss (APMFL), which focuses training on hard, minority-class pixels. We construct a cotton growth dataset of 11,745 UAV patches with four semantic classes. On this dataset and the public LoveDA benchmark, DCA-DeepLab attained the highest mIoU among the compared methods (51.74% and 51.71%), exceeding the strongest cotton baseline by 1.10 percentage points. Relative to DeepLabv3+, the Vigorous and Sparse minority-class IoUs improved by 3.51 and 1.91 percentage points, respectively, and Vigorous recall rose from 51.85% to 60.04%, with only 3.9% more parameters. These results show that encoding directional structure and adaptively balancing class contributions benefits fine-grained UAV crop segmentation.

Drones doi: 10.3390/drones10060457

Authors: Bowen Xu Peinan He Xu Wang Yixiao Zhang Yuanjie Zhao

Accurate Unmanned Aerial Vehicle (UAV) position estimation is the cornerstone of urban low-altitude safety management systems. Time Difference of Arrival (TDOA) and Remote Identification (Remote ID) are widely used surveillance technologies with complementary characteristics. TDOA provides high-rate updates but suffers from geometry-induced horizontal–vertical anisotropy and multipath effects, while Remote ID supplies absolute state information yet struggles with intermittent sampling and packet loss. Existing fusion schemes typically address these issues in isolation: sequential filtering manages asynchrony but assumes Gaussian noise, robust estimators suppress outliers at the cost of discarding valid data, and coupled-filter architectures allow vertical anomalies to contaminate horizontal estimates through the Kalman gain cross-coupling. No prior framework jointly handles structural TDOA altitude jumps, stochastic Remote ID timing jitter, and the geometric anisotropy between estimation subspaces within a single coherent pipeline. To bridge this gap, we propose a Hybrid Conditional Kalman Filter (HCKF) framework comprising three integrated modules. First, a kinematics-based temporal alignment module maps asynchronous measurements onto a uniform timeline and predicts missing samples, resolving cross-modal time mismatches. Second, a measurement quality evaluation mechanism detects TDOA altitude steps via robust two-layer stratification and scores Remote ID timing irregularity through a confidence mapping, converting these anomalies into dynamic covariance adjustments and weight caps without discarding observations. Third, a Subspace-Decoupled Fusion strategy exploits the physical insight that TDOA horizontal precision derives from hyperbolic intersection geometry, whereas its vertical estimates suffer from weak observability due to near-coplanar ground-station deployment. By applying entropy-guided weighting in the horizontal plane and a conditional Remote ID-dominant rule in the vertical axis, this design prevents cross-dimensional error propagation. The framework was validated using three real-world flight missions at distinct altitudes (255 m, 345 m, and 440 m) totaling 13.51 km of flight distance, with RTK serving as ground truth. HCKF reduces the Root Mean Square Error by over 40% relative to single-source baselines (95% bootstrap confidence interval: [35.2%, 48.7%]), and paired Wilcoxon signed-rank tests confirm statistically significant improvement (p<0.01) over standard EKF, Covariance Intersection, and Iterative CI across all three tracks.

Drones doi: 10.3390/drones10060458

Authors: Yuze Liu Changming Xu Kewen Xiao Yuhua Wu Ziyu Li

City-scale unmanned aerial vehicle vision-and-language navigation (UAV-VLN) requires accurate upstream target localization from an overhead map, onboard observation, and language description. Existing VLM-based methods often treat road names, landmarks, and spatial relations as raw text, leaving the model to search a large map and implicitly infer geometric constraints. This paper proposes GPOD, an inference-time candidate-prior interface for the upstream target-localization stage in city-scale UAV-VLN. GPOD converts language anchors, spatial relations, target-category cues, static map objects, and vehicle detections into ranked candidate priors through branch-specific candidate generation, thereby reformulating unconstrained full-map coordinate regression as candidate-prior-conditioned coordinate prediction. The static branch aligns language constraints with map-object geometries, while the dynamic branch uses YOLOv8l-VisDrone with Slicing Aided Hyper Inference (SAHI) to construct detection-conditioned vehicle candidates. In the GPOD-VLM setting, ranked candidates are injected as structured spatial prompts and the base VLM predicts the final continuous coordinates; GPOD-Direct is a candidate-direct diagnostic variant that directly uses candidate centers without VLM coordinate regression. On the CityNav localization protocol, GPOD improves FlightGPT Overall SR@20m from 15.23% to 25.61% and consistently reduces Mean Navigation Error (Mean NE) across splits and backbones. On Val-Unseen, GPOD-Direct (Top-1) reaches 32.59% SR@20m, showing that ranked candidate priors provide strong discrete localization signals. These results show that inference-time candidate priors can reduce city-scale search ambiguity without updating the base VLM parameters, while also revealing a candidate-utilization gap in the current prompt-based continuous coordinate-regression interface.

Drones doi: 10.3390/drones10060455

Authors: Sujunjie Sun Cong Cao Yan Lyu Xueyong Xu Renzhi Huang Yuhang Xu Shenquan Tang Chenchen Fu Weiwei Wu

UAV clusters operating in harsh environments must maintain connectivity under sudden node failures and dynamic traffic demands. Existing studies often address maintenance and routing separately, which leads to unnecessary reorganization overhead and forwarding bottlenecks around gateway nodes. To overcome these limitations, we propose a unified UAV Cluster Maintenance and Routing System (UCMR) that combines a firefly-inspired clustering method, a DQN–GCN-based medium-level interference recovery strategy (DGMR), and load-aware routing over forwarding neighbors. The maintenance component improves backbone repair by integrating global topology features with local observations, while the routing component exploits edge and node features to distribute forwarding pressure beyond gateway nodes. Extensive experiments demonstrate that UCMR outperforms representative benchmark methods in terms of average end-to-end delay and packet delivery ratio.

Drones doi: 10.3390/drones10060454

Authors: Jing He Rui Li Chunlei Pang Peiran Li Chenhao Zhao

Synthetic aperture radar (SAR) can acquire navigation data to correct inertial navigation system (INS) errors even under global navigation satellite system (GNSS)-denied conditions. However, when unmanned aerial vehicles (UAVs) may deactivate the SAR system to maintain radio silence, or the SAR sensor may be subjected to transient interference, the INS/SAR integrated navigation system transitions to degraded scenarios without SAR navigation data. Furthermore, the irregular sampling characteristics of SAR navigation data pose significant challenges to the localization performance of the INS/SAR integrated navigation system. In order to address the above challenges faced by UAVs, we propose a liquid time-constant (LTC) network-enhanced INS/SAR integrated localization method. The method adopts a loosely coupled integration strategy with training and prediction modes. During training, an LTC-assisted localization prediction network (LTC-ALPN) is designed to model input–output relationships using prior flight data while explicitly accounting for the non-uniform temporal sampling characteristics of SAR measurements. In prediction mode, the trained LTC-ALPN forecasts missing SAR navigation information, which is subsequently fused with INS outputs via a Kalman filter to maintain high-precision positioning during SAR outages. Experimental results demonstrate that, compared to pure INS localization in degraded scenarios, the proposed method reduces northward error MAE and RMSE by approximately 92.8% and 93.9% and eastward error MAE and RMSE by 54.1% and 67.1%. Against suboptimal network baselines, further improvements of 50.8%/38.1% (north) and 17.1%/16.7% (east) in MAE/RMSE were achieved.

Drones doi: 10.3390/drones10060453

Authors: Lanbo Wu Chen Wei

This paper is concerned with cooperative multi-UAV navigation in a planar obstacle environment. A hierarchical embodied swarm framework with leader, subleader, and follower roles is proposed. At the high level, a passable-corridor-driven decision layer is developed to perform split–merge reconfiguration and navigate/encircle mode switching. At the low level, a multi-term force synthesis controller is constructed for formation maintenance, inter-agent collision avoidance, obstacle avoidance, and sub-swarm cohesion. To accommodate both rule-based and local large language model (LLM) decisions, a feasibility projection operator is introduced so that only kinematically admissible structural actions are executed. In addition, a LiDAR-based obstacle-repulsion term and an occlusion-attenuated attraction mechanism are incorporated to improve navigation safety in cluttered environments. A Lyapunov analysis of the smooth controller core further certifies that, for a known (possibly time-varying) cruise velocity compensated by feedforward, the formation tracking error is uniformly bounded by the initial energy. Finally, multi-seed numerical simulations verify the proposed framework in standard, ablated, and complex scenarios. In the hardest alternating-gate scenario, the LLM-assisted variant raises mission success from 0.000 to 0.100, increases the goal-reaching ratio from 0.025 to 0.125, and reduces the mean terminal error from 44.738m to 39.851m, showing the value of semantic high-level reconfiguration under tight passage constraints.

Drones doi: 10.3390/drones10060452

Authors: Ilya Mashkov Angelika Kochetkova Valerii Serpiva Grigoriy Yashin Pavel Golikov

This study investigates offline trajectory planning strategies for multi-UAV missions in complex 3D environments, with the aim of systematically comparing classical, hybrid, and reinforcement learning-based approaches under unified evaluation conditions. Two simulation scenarios were considered: an uneven terrain environment with elevation-induced constraints and a planar obstacle-rich environment. The evaluated planners include graph-based (A*), sampling-based (RRT, RRT*), gradient-based (APF), a hybrid APF B-RRT* method, and a DQN-based reinforcement learning planner with spatial attention and reward shaping. Performance was assessed using geometric, safety, energetic, and computational metrics. The results show that A* consistently produces the shortest and most stable trajectories with low energy consumption but at increased computational cost in high-resolution environments. Sampling-based planners exhibit higher variability and planning time, while APF achieves computational efficiency but may violate safety margins. The hybrid planner provides improved robustness across scenarios. The reinforcement learning planner demonstrates consistent safety compliance and strong inter-UAV separation in both environments, also with longer trajectories and higher energy usage. Overall, the study highlights trade-offs between determinism, scalability, safety, and adaptability across planning paradigms.

Drones doi: 10.3390/drones10060451

Authors: Andrew Manu Jeff Dacosta Osei Thomas Lawler

Unmanned aerial vehicle (UAV)-based remote sensing combined with artificial intelligence (AI) has emerged as a key enabler of climate-smart agriculture (CSA). However, the extent to which these technologies operationalize CSA’s three pillars, productivity, adaptation, and mitigation, remains unevenly assessed. This study presents a PRISMA-guided systematic review of 59 peer-reviewed studies examining UAV–AI applications in agricultural systems. The synthesis categorizes platform configurations, sensor modalities, analytical architectures, geographic distribution, and data integration strategies, and evaluates their alignment with CSA objectives. Results indicate that productivity-oriented applications, including yield estimation, biomass mapping, and nutrient assessment, are the most mature, while adaptation-focused stress detection is also well established. In contrast, mitigation-oriented applications, such as carbon quantification and greenhouse gas monitoring, remain comparatively underrepresented. The analysis further reveals a growing convergence toward multimodal sensing and cross-scale data integration linking UAV observations with satellite and environmental datasets. However, substantial variability in validation approaches and dataset representativeness limits generalizability and scalability. Advancing UAV–AI contributions to CSA therefore requires methodological standardization, interoperable data governance, and strengthened institutional capacity. Collectively, the findings position UAV–AI systems as emerging components of climate-smart agricultural intelligence infrastructure rather than isolated monitoring tools.

Drones doi: 10.3390/drones10060450

Authors: Zuocheng Liu Qi Feng Zidong Wang Xiaoguang Gao

Collision avoidance in maritime unmanned aerial vehicle (UAV) operations must satisfy two competing objectives: ensuring reliable safety separation and minimizing unnecessary maneuver commands that increase operator burden and communication overhead. While deep reinforcement learning (DRL) has shown promise in handling high-dimensional encounter states, standard DRL approaches often prioritize safety at the cost of operational suitability, leading to frequent, oscillatory, or unnecessary avoidance commands that erode remote operator trust and consume limited communication bandwidth. To address this challenge, this paper proposes Resource-Aware Intrinsic Surprise Exploration (RAISE), a unified framework that balances collision avoidance performance with command economy. We conceptualize the issuance of avoidance maneuvers as a consumable “virtual resource”, compelling the agent to optimize its intervention budget. RAISE integrates this mechanism into the Soft Actor–Critic (SAC) architecture, augmented by a surprise-based intrinsic reward derived from the ensemble forward dynamics prediction error. This allows the agent to efficiently explore complex encounter scenarios driven by curiosity, while a resource-aware coefficient adaptively suppresses redundant actions when the communication or operational budget is constrained. Furthermore, an adaptive exponential moving average (EMA) scaling mechanism is introduced to stabilize the interplay between intrinsic and extrinsic rewards. Extensive simulations under diverse resource constraints and encounter geometries demonstrate that RAISE outperforms state-of-the-art baselines. It significantly reduces maneuver reversal rates and strengthens command stability without compromising safety margins. Specifically, under resource-constrained settings, RAISE suppresses excessive and unstable advisory behavior by reducing strengthening and reversal commands while maintaining effective collision avoidance; under resource-rich settings, it flexibly enhances safety buffers, demonstrating superior adaptability and operational realism for autonomous maritime UAV systems. Robustness evaluation confirms that RAISE maintains stable performance under sensor noise and wind disturbances.

Drones doi: 10.3390/drones10060449

Authors: Yu Jing Yili Yan Zhao Li Fugui Qi Tao Lei Jianqi Wang Guohua Lu

Infrared and visible image fusion is critical for unmanned aerial vehicle (UAV) wilderness search and rescue. By integrating thermal radiation of the targets and texture details of the scenario, it enables accurate search for the wounded and comprehensive perception of disaster areas, thereby significantly improving emergency rescue efficiency. To alleviate data scarcity, we construct UAV-MSR, an infrared-visible dataset for casualty search, comprising 3889 paired images captured under diverse weather, illumination, and scenarios. Existing Transformer-based fusion methods mainly focus on high-intensity pixels while inadequately modeling low-intensity complementary features, resulting in blurred details and degraded target contrast in fused images. To this end, we propose a novel differential cross-attention Transformer network to address the issue of complementary information loss. Specifically, the encoder integrates convolution operations for local detail extraction and self-attention mechanisms for global context modeling. Then, we design a differential cross-attention guided feature fusion module to enhance the representation and preservation of detailed complementary features. Furthermore, a pixel loss function with a segmentation strategy is employed to improve the saliency of the target, enabling the fused image to facilitate subsequent target detection tasks. Experimental results and ablation studies demonstrate that the proposed method achieves notable performance and generalization ability. In summary, this work delivers a multimodal dataset and an efficient infrared-visible image fusion network to enable comprehensive perception for UAVs in wilderness search and rescue scenarios.

Drones doi: 10.3390/drones10060448

Authors: Wei Wei Xubo Zhao Yongjie Shu Qingkai Meng Mingkai Ding Yunyi Wang Qingdong Yan

As unmanned aerial vehicle (UAV) systems evolve from automated execution toward autonomous decision-making, multirotor UAVs increasingly face complex dynamics, uncertain sensing conditions, and task-level autonomy demands. Reinforcement learning (RL) has emerged as a promising learning-based paradigm for addressing these challenges. Existing surveys on RL-based UAV control predominantly classify methods from an algorithmic or learning-paradigm perspective, while relatively little attention has been paid to the functional roles of RL policies within the control loop. This often leads to an unclear correspondence between algorithmic characteristics and the requirements of different control layers. To address this gap, this review proposes a biomimetic “spinal cord–cerebellum–cerebrum” framework, organizing existing RL studies into low-level dynamic stabilization, mid-level perception–action coordination, and high-level task planning and decision-making. The proposed hierarchy emphasizes the functional role and intervention depth of RL policies within the control architecture, further supporting a layer-wise analysis of sim-to-real challenges. This review aims to provide a structured understanding of the roles of reinforcement learning in hierarchical UAV control and to highlight future research directions toward robust real-world deployment.

Drones doi: 10.3390/drones10060447

Authors: Xuekai Zhang Wenchao Kang Yueping Peng Wei Tang Qilong Li Hexiang Hao Liming Hou Xin Ying

Camouflaged object detection (COD) is important for intelligent UAV monitoring and search-and-rescue operations. However, existing benchmarks focus primarily on natural camouflage, creating a noticeable domain shift for specific applications such as the search and rescue of individuals visually similar to their surroundings due to their clothing. To investigate this shift, we introduce CPD-UAV, a benchmark comprising 1061 high-resolution images with detailed pixel-level annotations across diverse terrains and flight altitudes. Benchmarking of seven state-of-the-art models on this dataset reveals specific challenges. Specifically, the scale variations and “vanishing boundaries” inherent in aerial perspectives can lead to boundary localization inaccuracies. Furthermore, this evaluation observes the deceptive nature of traditional metrics, such as Mean Absolute Error (MAE), when targets occupy small image proportions. To address the degradation of weak target signals during feature integration, we propose a lightweight, plug-and-play component: the Residual Gated Alignment Module (RGAM). RGAM handles scale variations by establishing semantic anchors in deep network layers, mitigating signal dilution and highlighting micro-targets against complex backgrounds. By integrating RGAM into three representative baselines, we demonstrate that the enhanced architectures achieve a competitive performance level. Quantitative results show consistent improvements in structural integrity (structure-measure, Sm) and boundary localization. Ultimately, this work provides a practical data platform and an effective algorithmic solution for advancing aerial monitoring systems.

Drones doi: 10.3390/drones10060446

Authors: Jiawei Tang Tian Chang Haiqi Liu Zhe Yu Dekang Liu Xuhui Ding

This paper investigates joint deployment of unmanned aerial vehicle (UAV)-borne linear-array angle-of-arrival (AOA) sensors for localizing a target UAV in three-dimensional space. Since each sensing UAV carries a lightweight one-dimensional (1-D) AOA array, each measurement provides only one angular constraint, and its information contribution depends jointly on the UAV waypoint and array pointing direction. This leads to a coupled coordinate–orientation design problem that differs from conventional full-AOA deployment. We formulate a Cramér–Rao lower bound (CRLB)-based framework under A- and D-optimality criteria, covering both free-flight and constrained hovering regions. By exploiting the structure of the 1-D AOA Fisher information matrix, we show that, for fixed UAV coordinates, the orientation block can be exactly eliminated through a low-dimensional eigenproblem. The resulting reduced coordinate problem is then solved by a geometry-structured sequential quadratic programming (SQP) method, whose curvature model captures the radial and tangential sensitivities induced by line-of-sight geometry. Numerical simulations further validate the effectiveness of the proposed approach.

Drones doi: 10.3390/drones10060445

Authors: Hadi Fares Ammar Mohanna Bilal Kaddouh

Global Navigation Satellite Systems (GNSS)-denied environments pose significant challenges for autonomous drone navigation, requiring robust visual localization systems capable of real-time performance. Existing approaches either sacrifice accuracy for speed or fail to adapt to varying flight altitudes and orientations, limiting their practical deployment. We present Real-Time Elevation and Orientation-Aware Localization Architecture (REOLA), a visual localization system that combines similarity-driven autonomous window sizing, element-wise correlation-based orientation detection, and reinforcement learning with human feedback (RLHF) enhancement for publicly available satellite imagery. On desktop hardware (i7-10700K + RTX 3070), the REOLA achieved approximately 59 FPS performance with sub-5-m accuracy across diverse flight conditions through intelligent similarity-based matching, combined with efficient MobileNet-V3 embeddings and FAISS similarity search. For embedded deployment on NVIDIA Jetson Orin Nano, the system achieved 22.5 FPS, meeting real-time requirements for autonomous drone localization. The system autonomously selects optimal window sizes corresponding to the current elevation and determines drone orientation through element-wise correlation scoring across discrete rotation angles. Enhanced through RLHF, the REOLA achieved a 97.1% success rate (sub-5-m localization) while processing frames in 17 milliseconds on desktop hardware (44.4 ms on embedded hardware), providing a substantial margin over real-time requirements. The approach demonstrates particular superiority over traditional keypoint-based methods in challenging environments with repetitive patterns such as agricultural fields, rocky mountains, dense forests, and grasslands, where conventional keypoint detection struggles. We explicitly identify featureless sand dune deserts and open-sea or coastal water flights as out of scope, since the reference satellite imagery in those regimes does not contain stable landmarks.

Drones doi: 10.3390/drones10060444

Authors: Yichen Liu Chijun Zhou Lei Shao Yangchao He Xueqian Wang Jikun Ye

Long-horizon trajectory prediction for unmanned aerial vehicles (UAVs) operating in constrained environments remains challenging because of strongly nonlinear dynamics, hidden control effects, and evolving destination-oriented behavior. This challenge is particularly pronounced for highly maneuverable cross-domain unmanned aerial vehicles (CDUAVs), whose glide trajectories are strongly coupled with control and environmental constraints. To address this problem, this paper proposes an intent-aware CNN–Informer framework for accurate long-horizon trajectory prediction. First, a control-affine reformulation of the vehicle dynamics is used to construct physically interpretable DBL control parameters, which reduce the learning difficulty associated with hidden control effects. Second, three continuous intent features—tangential no-fly zone avoidance distance, heading error angle, and relative closing velocity—are introduced to encode destination tendency and avoidance requirements. These features are fused with historical trajectory states and fed into a hybrid CNN–Informer network, where the CNN extracts local maneuver patterns and the Informer captures long-range temporal dependencies. Experiments on a constrained trajectory dataset demonstrate that the proposed method achieves the best performance among all compared models, including SSD-LSTM, Transformer, iTransformer, DLinear, and Informer. Compared with Informer, the proposed approach reduces the average prediction error by 17.2% and significantly improves terminal and maximum prediction errors. These results indicate that the proposed framework provides an effective and physically interpretable solution for long-horizon UAV trajectory prediction in constrained flight scenarios, with potential extensions to behavior-aware forecasting and guidance support in autonomous aerial systems.

Drones doi: 10.3390/drones10060443

Authors: Yuxuan Ji Linya Liu Yong Wang Xi Vincent Wang Lihui Wang

Current urban logistics models often struggle to reconcile diurnal traffic dynamics with rigid spatial–temporal regulations. This decoupling causes “cascading infeasibility,” where traffic delays trigger structural regulatory violations and UAV energy depletion. This study formulates a time-dependent vehicle–UAV joint routing problem that strictly couples time-varying speeds with vehicle-restricted zones and no-fly zones. The mixed-integer program minimizes a composite cost by integrating speed curves, geometric detour models, and coupled energy functions. To solve large-scale instances, we propose a hybrid metaheuristic solver (IHGA-VNS-SL) combining genetic algorithms, variable neighborhood search, simulated annealing, and self-learning. Tested on calibrated Wuhan instances, IHGA-VNS-SL quantitatively outperforms baseline heuristics (GA and ALNS). It achieves a tight 2.31% optimality gap against exact solvers (CPLEX) and up to a 20% cost reduction over ALNS, alongside near-zero tardiness. Results demonstrate that this strict coupling effectively mitigates synchronization failures, confirming the framework’s robustness for megacity distribution.

Drones doi: 10.3390/drones10060442

Authors: Hu Yuan Shengkai Yan Zhuzhi Liu Suli Wang Qiang Wang Gaocheng Chen

To enhance path planning efficiency in unmanned aerial vehicle (UAV) search missions in complex environments, this paper proposes a coverage path planning (CPP) algorithm for a UAV that integrates the deep Q-network (DQN) with the A* algorithm (DQN-A*). In the proposed DQN-A* algorithm, a dual-driven reward mechanism is established, comprising a probability-weighted reward and a step-dependent reward, steering the UAV toward high-probability regions. Furthermore, to handle previously unknown obstacles in real time, the algorithm employs a multi-stage obstacle-identification strategy, enabling the UAV to improve coverage of traversable cells by dynamically adjusting its local path when newly detected obstacles are encountered. A theoretical analysis derives a principled recommended range for the UAV positional identifier based on statistical feature analysis; this range is then validated through extensive simulations. Additionally, Hamiltonian path pre-training is introduced to accelerate convergence. Comparative simulations demonstrate that the proposed DQN-A* algorithm achieves higher area-coverage and target-detection probabilities than benchmark algorithms in environments with unknown obstacles, offering valuable insights for positional encoding in deep reinforcement learning (DRL)-based robotic coverage problems.

Drones doi: 10.3390/drones10060441

Authors: Zhanheng Xie Lei Liu Xiaosong Li

This paper investigates trajectory tracking and collision-avoidance problems for unmanned surface vehicles (USVs) in maritime sports support scenarios. These tasks require accurate tracking, disturbance rejection, safe motion around static and moving obstacles, and predictable transient performance within task-level time constraints. To address these requirements, an adaptive predefined-time sliding mode control (APTSMC) strategy is formulated for the considered CyberShip II-based USV tracking error system. A predefined-time sliding surface and reaching law are used to provide an explicit convergence-time design parameter for the nominal tracking subsystem, while an adaptive compensation mechanism estimates the unknown bound of lumped disturbances without requiring prior knowledge. To support collision avoidance, a velocity-modulated artificial potential field correction is incorporated as a reactive avoidance layer. The modulation term strengthens repulsion when the USV approaches an obstacle and reduces unnecessary deviation when the relative motion is safe. Numerical results in a constructed maritime sports boundary-tracking simulation scenario with multiple static and moving obstacles further demonstrate the potential effectiveness of the integrated framework in balancing tracking accuracy and collision avoidance safety.

Drones doi: 10.3390/drones10060440

Authors: Xingyang Feng Hua Cong Mianhao Qiu

Autonomous navigation on unknown uneven terrain remains a critical challenge for unmanned ground vehicle (UGV) deployed in unstructured environments such as disaster relief, wilderness exploration, and off-road logistics. Existing motion planning methods for such environments suffer from three key limitations: under-utilization of the solution space due to discretized terrain assessment, difficulty in transforming complex terrain safety constraints into optimization-compatible forms, and the inherent trade-off between environmental modeling accuracy and real-time performance. This paper presents a hierarchical motion planning framework that enables safe and fast navigation of UGV on unknown uneven terrain. We first construct a traversability map based on terrain slope, roughness, and sparsity extracted from ground point cloud clusters. Non-traversable points are then transformed via spherical inversion and inverse mapping to generate terrain safety corridors composed of a series of convex polygons. The geometric containment relationship between the vehicle’s convex hull and the corridor is reformulated as continuously differentiable Control Barrier Function (CBF) constraints to ensure driving safety. The front-end employs a kinodynamic Hybrid A* algorithm with a traversability-aware node pruning strategy, while the back-end trajectory optimization embeds the CBF constraints as hard constraints within the optimization loop to guarantee forward invariance of the safety set under the linearized dynamics. The proposed framework achieves full-shape collision avoidance without sacrificing the solution space, while maintaining real-time performance for autonomous navigation on complex terrain.

Drones doi: 10.3390/drones10060439

Authors: Yulong Cao Guhao Zhao Yarong Wu Hao Wang Yu Gong

Cooperative localization for multi-Unmanned Aerial Vehicle (UAV) systems in GPS-degraded environments is often compromised by ideal-communication or uniform-quality assumptions. This paper proposes Quality-Aware Distributed State Estimation (QA-DSE), which combines three operational quality factors—freshness (Age of Information), accuracy (covariance trace), and link reliability (packet loss and channel noise)—into a single multiplicative score qij, modulated by a bounded history-consistency factor based on velocity-propagated self-trajectory continuity. A dual-constraint AND-gate on AoI and covariance trace excludes jointly degraded neighbors, while admitted neighbors are fused through a quality-squared information-matrix update under a stated bounded residual cross-correlation assumption, with an adaptive Covariance-Intersection fallback when the assumption is stressed. Under explicit observability, bounded-noise, bounded-quality, joint-connectivity, and bounded residual cross-correlation assumptions, we establish mean-square bounded error, exponential convergence at a rate inherited from the Kalman update operator, On3+nm per-step complexity, Bounded-Input Bounded-Output (BIBO) stability, soft attenuation of single-axis faults (Theorem 4), and hard exclusion under joint AoI–covariance violation (Theorem 5). Under a Ultra-Wideband (UWB)-style cooperative-observation model, Monte Carlo experiments across five scenarios show 74.08–74.24% position- Root Mean Square Error (RMSE) reductions over Covariance Intersection, with the relative advantage held within 73.04–74.24% as the fleet scales from 3 to 50 UAVs; QA-DSE remains within 8.1% of an idealized no-cooperation single-vehicle Kalman filter, demonstrating graceful degradation rather than improvement above that floor. Per-step Central Processing Unit (CPU) time scales from 0.09 ms (5 UAVs) to 0.31 ms (50 UAVs); embedded validation is left to future work.

Drones doi: 10.3390/drones10060438

Authors: Chengxiang Wang Yongli Li Tianhang Gu Kai Wang Ke Zhang

Aiming at the problem that it is difficult for existing path planning methods to plan UAV paths in real time in complex atmospheric turbulence environments, this work proposes a dynamic path planning method for UAVs based on an improved artificial lemming algorithm. First, using temperature, pressure, and wind vectors from WRF/NWP forecast data, a dynamic turbulence-change environment model in the airspace is constructed. Then, a UAV dynamic path planning model is formulated by comprehensively considering the turbulence change rate and path safety evaluation factors. Next, to address premature convergence of existing algorithms under turbulence influence, a solving method for the UAV dynamic path planning model based on an improved artificial lemming algorithm is developed. Simulation results show that, under the proposed replanning mechanism, the improved algorithm reduces the final fitness by 36.19% and cumulative turbulence exposure by 16.28% on average compared with all competing methods.

Drones doi: 10.3390/drones10060437

Authors: Chao Su Jiayu Yuan Enhui Zheng Wangpin Xu Zhanghua Liu Jianhong Hu

Achieving long-term, continuous, and accurate localization for Unmanned Aerial Vehicles (UAVs) in outdoor GNSS-denied environments where pre-existing reference maps are available is challenging. To this end, this paper proposes a Cross-view Particle Filter Localization (CPFL) framework. Unlike existing particle filter approaches that rely on inertial sensors for state propagation or sparse semantic labels for observation updates, CPFL is a vision-driven solution. This framework introduces specific adaptations into the two core stages of particle filtering: In the motion propagation stage, it achieves visual state transition by calculating a feature-based inter-frame homography mapping to estimate the 2D global relative motion components, eliminating the dependency on inertial priors; in the observation correction stage, a Dual-Granularity Adaptive Gating (DGAG) cross-view network is designed to mitigate perceptual aliasing and generate discriminative absolute position weights for the particles. By fusing these two stages through a filter mechanism, the framework transforms unbounded cumulative drift into bounded absolute localization errors. Furthermore, addressing the measurement deficiencies of traditional single-frame metrics, this paper also proposes a Trajectory Continuity Index (TCI@d) tailored for continuous localization tasks. Experiments on the real-world MAFS dataset confirm that this framework achieves a mean localization error of 5.28 m and a localization success rate of 89.7% under a 10-m threshold. Compared with mainstream vision-only algorithms and IMU-fusion baselines, this framework demonstrates lower mean errors and improved trajectory continuity, validating its effectiveness for long-term robustness.

Drones doi: 10.3390/drones10060436

Authors: Ye Tian Xiaoping Cui Jinyu Qian Weishi Peng Xudan Dong

The surging need for public security risk mitigation has placed stricter demands on the modernization of emergency response capacities. Unmanned aircraft systems (UASs) offer a promising solution for liquid anti-riot agent dispersion, yet the complex interaction between rotor-induced downwash and droplet trajectories makes nozzle layout optimization a significant challenge. To address the prohibitive computational costs of traditional Computational Fluid Dynamics (CFD) and the limitations of single-objective optimization, this study proposes an integrated “simulation–modeling–optimization–decision” framework. First, a linear nozzle layout was identified as superior to the traditional circular arrangement, achieving a 44.8% increase in deposition rate. Subsequently, Optimal Latin Hypercube Sampling (OLHS) and CFD simulations were combined to construct high-precision Kriging surrogate models for three key indicators: deposition rate, uniformity, and coverage rate. The NSGA-II algorithm was then employed to solve the multi-objective trade-off, followed by the entropy-weighted TOPSIS method to identify the optimal engineering solution. Results indicate that nozzle count is the dominant system-level variable under the constant per-nozzle flow-rate condition, showing strong positive correlations with all performance indicators. The identified optimal configuration (6 nozzles with a 1.88 m boom length) achieved a 66.1% increase in deposition rate and an 18.7% increase in coverage rate compared to the original circular layout. Furthermore, the surrogate-based framework improved optimization efficiency to 296% compared to full factorial methods. This study provides a scientific theoretical basis and a highly efficient technical pathway for the structural design of high-performance UAV spray systems.

Drones doi: 10.3390/drones10060435

Authors: Orkan Özcan Semih Sami Akay Yusuf Gedik Esra Erten Okan Özcan

Precise and continuous monitoring of thermal effects are critical for ensuring the structural safety of bridges and preventing potential failures. This study presents a methodology integrating unmanned aerial vehicle (UAV)-based thermal measurements with interferometric synthetic aperture radar (InSAR) satellite data to assess and monitor the thermomechanical response of bridges. A three-dimensional (3D) finite element model (FEM) of a prestressed concrete (PC) bridge was developed and validated using in situ displacement measurements. High-resolution, 3D temperature distributions of bridge elements were obtained daily and seasonally using UAV-based infrared thermography (UAV–IRT). Thermal maps were validated with point temperature measurements on the structure. Simultaneously, long-term wide-area deformation trends were investigated using satellite-based InSAR observations. The thermo-mechanical displacement behavior derived from UAV–IRT measurements was compared with historical InSAR-derived seasonal deformation patterns to develop an integrated multi-source structural monitoring framework. The behavior of the bridge in daily and seasonal temperature cycles was simulated and analyzed by integrating UAV–IRT thermal load data into FEM. Maximum stress levels occurring under the most adverse thermal loading conditions and over a one-year period were calculated, taking into account stress limits. The FEM revealed a maximum vertical displacement of 12.3 mm under extreme thermal loading, with tensile stresses in the deck mid-depth exceeding the 3.5 MPa limit, signaling a potential risk for thermally induced cracking. Integration of UAV–IRT thermal observations and historical InSAR deformation measurements revealed vertical temperature gradients of up to 24 °C during summer conditions and indicated that the observed structural response was predominantly governed by thermo-elastic deformation. UAV-satellite methodology offers a rapid, economical, and comprehensive solution for the structural health monitoring of bridges exposed to thermal effects.

Drones doi: 10.3390/drones10060434

Authors: Qing Cheng Wenwen Wu Ziwei Zhao

Reliable beam management in Unmanned Aerial Vehicle (UAV)-assisted Integrated Sensing and Communication (ISAC) systems needs accurate trajectory prediction and a clear sense of prediction risk. Most existing methods use deterministic future positions or raw uncalibrated uncertainty. Under high mobility and uncertainty, this leads to unreliable beam decisions. We design a control-oriented probabilistic trajectory prediction framework. It uses calibrated trajectory uncertainty as a risk signal for adaptive beam management. The framework first combines motion history and visual context to predict trajectory distributions. Split conformal calibration turns raw Gaussian uncertainty into statistically reliable risk bounds. A codebook-constrained beam management strategy adjusts beamwidth based on the calibrated spatial risk. This balances beamforming gain, coverage robustness, and switching stability. Tests on UAV data show better prediction accuracy than representative probabilistic baselines. The raw uncertainty remains under-calibrated, and conformal calibration is therefore applied to improve its reliability before beam-control decisions. Using the calibrated uncertainty for beam control improves communication coverage and cuts outages and severe misalignment in high-risk situations. Calibrated predictive uncertainty can serve as an actionable control variable for robust beam management in dynamic UAV-assisted ISAC environments.

Drones doi: 10.3390/drones10060433

Authors: Yun Jiang Daochun Li Zi Kan Zhuoer Yao Jinwu Xiang

Wing rock motion observed in low-aspect-ratio flying-wing unmanned aerial vehicles (UAVs) severely degrades maneuverability and flight safety, making effective recovery control a challenging task. This paper proposes an Enhanced Incremental Nonlinear Dynamic Inversion (EINDI) control framework for autonomous wing rock recovery, in which aerodynamic angular rate feedback is introduced into the outer-loop control design, while an INDI scheme is employed in the inner loop. The proposed controller is evaluated using a six-degree-of-freedom (6-DOF) flying-wing UAV model. Recovery performance is assessed for multiple initial conditions distributed along the wing rock trajectory, and the results are compared with those obtained using linear outer-loop control, nonlinear dynamic inversion (NDI) outer-loop control, and a simplified NDI-based outer-loop control strategies. Simulation results demonstrate that the proposed method can achieve successful recovery from arbitrary initial states along the wing rock trajectory. It is found that the required recovery altitude exhibits a negative correlation with the Euclidean distance between the initial and target states. Under nominal conditions, the EINDI controller achieves higher control accuracy and better stability than linear outer-loop control and exhibits performance comparable to NDI-based control. In the presence of aerodynamic model uncertainties, the sideslip suppression capability of linear outer-loop control degrades, while the angle-of-attack tracking performance of NDI-based outer-loop control deteriorates. These results indicate that, although the attitude control loop itself possesses strong inherent robustness, the proposed EINDI framework provides improved control accuracy under model uncertainty, making it well suited for high-maneuverability flight control of flying-wing UAVs.

Drones doi: 10.3390/drones10060432

Authors: Ahraar Shareef Axel von Freyberg Andreas Fischer

Small surface defects on large structures such as wind turbine blades, bridges, and pipelines pose significant safety risks if left undetected. Therefore, a laser triangulation system is designed for contactless surface geometry inspection from a flying drone at a working distance of 2 m. To enable single-shot triangulation measurements in dynamic aerial environments, a single-shot-capable approach is realized by means of a laser and a diffractive optical element for creating a dot-matrix illumination pattern and a camera for image recording. The setup, with 101 × 101 measurement points, is calibrated by using an interferometer as a reference, which shows a sub-pixel resolution capability. As a result, the depth resolution capability for each point amounts to 126 µm, while the lateral resolution capability is determined by the laser spots’ size of 0.6 mm and the spots’ interspacing of 1.75 mm. With the present configuration, unambiguous depth detection is possible for local surface gradients of up to 2.3 times the interspot distance between adjacent measurement points, and the field of view is 17.56 cm × 17.56 cm. Finally, surface defects with lateral sizes on the order of 1 cm and 0.5 cm are currently detectable, as is demonstrated by experimental results from in-flight measurements. Thus, the potential and challenges of single-shot laser triangulation for drone-based inspection in real-world scenarios are presented.

Drones doi: 10.3390/drones10060431

Authors: Fanghui Huang Junbin Lou Dawei Wang Baolei Wang Yixin He

In vehicular ad hoc networks (VANETs), using vehicle platooning can improve traffic efficiency, reduce driving energy consumption, and ease traffic congestion. However, since land-based stations have limited coverage (about 7% of the Earth’s surface), ensuring low-latency communication is challenging. To address this issue, the introduction of solar-powered unmanned aerial vehicles (UAVs) as aerial base stations provides flexible and extensive communication support for vehicle platooning. Additionally, intelligent connected vehicles (ICVs) adopt non-orthogonal multiple access (NOMA) techniques for uplink transmission to further enhance transmission performance. Motivated by the above, this paper investigates the latency optimization problem of UAV-supported vehicle platooning by jointly considering multi-dimensional resource allocation and imperfect channel state information (CSI) affected by mobility. To solve this problem, we propose an iterative optimization approach with polynomial complexity, where the transmitted power and channel allocation are tackled in turn. Then, an analytical framework is developed to analyze the probability that NOMA is superior to OMA, guiding parameter settings for UAV-supported vehicle platooning. Finally, the simulation results show that the proposed latency optimization scheme can achieve lower total and average latencies on the uplink compared to state-of-the-art works and the benchmark scheme using OMA. Moreover, this paper elucidates the convergence, performance gap, and computational complexity associated with the proposed iterative optimization approach. Furthermore, the probability of NOMA outperforming OMA is quantified through Monte Carlo experiments, which validates the correctness of the developed analytical framework.

Drones doi: 10.3390/drones10060430

Authors: Abdullah Tunç Büyüksan Kerem Utku Demir Durdu Hakan Utku Kamer Özgün

Unmanned aerial vehicle (UAV) routing under realistic operational conditions requires simultaneous consideration of distance- and payload-dependent energy consumption, limited battery capacity, and multi-trip mission feasibility—factors that are rarely integrated into a unified, reproducible benchmarking framework. This study proposes an energy-aware, multi-trip UAV routing model for single-warehouse cargo delivery operations, in which total energy consumption is minimized through a second-degree polynomial power function derived from empirical motor thrust–power data of a theoretically designed quadrotor UAV with a maximum payload capacity and a usable battery capacity. Euclidean service locations and loads are generated randomly within a continuous operational domain to reflect spatial uncertainty, and a split-based decoding mechanism enforces battery feasibility constraints throughout the route. Twenty-six heuristic and metaheuristic algorithms sourced from the recent UAV routing literature are implemented within a standardized MATLAB benchmarking environment and evaluated on TSPLIB instances (Berlin52, kroA100), as well as randomly generated instances with different numbers of delivery locations. A refined subset of eight representative algorithms is subjected to comprehensive scalability analysis under both distance- and energy-minimization objectives, separately. The findings provide evidence-based guidelines for algorithm selection across offline planning and real-time UAV routing scenarios, and establish a transparent, reproducible benchmark baseline for energy-constrained single-UAV operations.

Drones doi: 10.3390/drones10060429

Authors: Wenchao Kang Xuekai Zhang Yueping Peng Wei Tang Qilong Li Hexiang Hao Kang Liu Qinghe Chen

In air-to-air counter-UAV scenarios, vision–language tracking for tiny drones still lacks a dedicated benchmark. Unlike traditional UAV tracking or ground-based Anti-UAV settings, air-to-air counter-UAV tracking involves simultaneous motion of both the tracking platform and the target platform. In addition, the target typically appears as a tiny object and is subject to rapid viewpoint changes, fast background transitions, and interference from similar drones, making it difficult to systematically assess the capability boundaries of existing methods. To address this gap, we present the ATA dataset. To the best of our knowledge, ATA is the first vision–language tracking dataset specifically designed for real air-to-air tiny-object UAV countermeasure scenarios. ATA contains 50 real-flight video sequences with 38,094 frames in total, and provides frame-wise bounding box annotations together with video-level English language descriptions. It supports two unified task settings, namely BBox-only and Language-assisted tracking. The dataset covers diverse real-world low-altitude scenarios with complex backgrounds. Notably, the average target area accounts for only 0.03% of the full image, exhibiting pronounced tiny-object characteristics. ATA also captures several key challenges in this setting, including dual-dynamic disturbances, complex background changes, and multi-drone interference. Based on ATA, we establish a benchmark covering both vision-only and vision–language tracking methods, and conduct a systematic evaluation of eight representative recent trackers. Experimental results show that current mainstream methods still perform unsatisfactorily in this scenario, with evident limitations in tiny-object representation, cross-frame association, robustness to complex backgrounds, and interference suppression. Furthermore, we validate a lightweight temporal enhancement module, AFTE, and show that explicitly leveraging adjacent-frame information consistently improves the performance of multiple baseline models. Overall, ATA provides a unified benchmark for vision–language tracking in air-to-air counter-UAV scenarios of tiny drones and highlights temporal modeling as a promising direction for improving tracking performance in this challenging setting.

Drones doi: 10.3390/drones10060427

Authors: Oleg Illiashenko Oleg Ivanchenko Vyacheslav Kharchenko Dmytro Kucher Herman Fesenko Behnam Bazli Pip Trevorrow

Unmanned Aerial Vehicles (UAVs) are increasingly used in complex civil missions that require reliable operation under uncertainty, creating a need for formal methods to assess how artificial intelligence (AI) contributes to mission performance. This study develops and evaluates a unified modelling framework for AI-enabled UAV systems operating in autonomous and automatic modes on small- and medium-class platforms across different operational configurations, including both single-UAV and multi-UAV deployments. The framework combines a structured decomposition of mission tasks—Environmental Sensing and Monitoring, Situational Awareness, Communication and Sensing Interference Resilience, Hazard and Restricted-Zone Avoidance, and Mission Execution and Intervention—with binary set descriptions, Bayesian Networks (BN), and Reliability Block Diagrams (RBD). This integration enables consistent mapping between mission tasks, AI utilisation approaches, and system-level performance characteristics while accounting for environmental disturbances, communication degradation, and mission constraints. The results show that the framework supports scenario-based analytical evaluation of UAV effectiveness and enables assessment of how AI-enabled perception-stage performance influences mission-level success in a civil Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNe) environment. The proposed framework provides a methodological basis for the design, analysis, and future experimental validation of AI-enabled UAV systems for safety-critical civil missions.

Drones doi: 10.3390/drones10060428

Authors: Zhenxing Zhang Liping Hu Dongwei Zhang Rennong Yang Ying Wang Jialiang Zuo

This paper addresses the formation assignment problem for heterogeneous UAV swarms in dynamic mission environments. A constrained optimization model is constructed in which UAV capabilities are divided into shareable and exclusive types; a neighborhood collaboration decay factor captures the locality of capability complementarity; and a Cobb–Douglas production function evaluates position-specific effectiveness under bottleneck constraints. The objective dynamically trades off deployment costs and system risks through threat-adaptive weight adjustment. To solve the model, a Hybrid Adaptive Large Neighborhood Search (HALNS) algorithm is proposed, integrating an adaptive destroy-repair mechanism, a mathematical-programming-based local search, and an incremental re-optimization strategy for rapid dynamic response. Experiments verify that HALNS attains globally optimal solutions on small-scale instances and outperforms mainstream baselines on medium-to-large problems. The collaboration mechanism raises system effectiveness by an average of 34.75% across four mission scenarios. Compared with static re-optimization, the incremental strategy improves dynamic response performance by 58.25% while reducing runtime by up to 56.7%. Sensitivity analyses confirm the robustness of key parameters. This work provides a theoretical and algorithmic foundation for intelligent UAV swarm assignment and reconfiguration.

Drones doi: 10.3390/drones10060426

Authors: Christian Reyner Rhea P. Liem

Fixed-wing unmanned aircraft are widely used for aerial mapping because they can acquire high-resolution data at relatively low cost, but maintaining both energy efficiency and image quality in the presence of wind and flight-performance limits remains challenging. In practice, operators introduce buffer regions and extended waypoints outside the area of interest to cope with deviations during turning, which increases flight distance and energy use; yet, this approach can still degrade image overlap near the boundary. This paper presents a path-planning framework that designs turning maneuvers compatible with bank-angle, stall-margin, and roll-rate constraints while aligning mapping lanes directly with the area of interest. The framework combines analytically structured turn patterns, an energy-based metric that accounts for increased aerodynamic load in banked flight, and a two-stage path-angle selection procedure that uses a fast, simplified model to guide a more detailed optimization. Simulation studies on both idealized and real survey geometries indicate that, within the considered maneuver families and assumptions, the proposed method can reduce the integrated aerodynamic energy metric and improve coverage compliance relative to a conventional path-following approach that relies on overshoot points.

Drones doi: 10.3390/drones10060425

Authors: Ionut Gabriel Stoica Andra Mihaela Predescu Zoltán Ságodi Gábor Antal Péter Hegedűs Zoltán Hornák

Methane (CH4) is a highly potent greenhouse gas whose accurate detection and quantification are essential for climate mitigation and compliance with emerging environmental regulations. Conventional monitoring approaches, including fixed monitoring stations and satellite-based observations, often exhibit limitations in terms of spatial resolution, operational flexibility, and accessibility for localized measurements. This paper presents CH4SCOUT, a modular unmanned aerial vehicle (UAV)-based platform designed for methane detection, environmental monitoring, and georeferenced data acquisition. The proposed system integrates a methane sensing module, environmental sensors, controlled airflow sampling, onboard data acquisition, and wireless communication capabilities within a UAV-compatible architecture. A three-stage signal-conditioning pipeline based on Median filtering, Hampel outlier suppression, and Exponential Moving Average (EMA) smoothing is implemented to improve measurement stability under dynamic flight conditions. Initial real-world validation flights demonstrate stable methane concentration measurements under realistic environmental conditions while maintaining reliable data transmission and telemetry synchronization. Results indicate that low-cost UAV-assisted sensing architectures can provide operationally useful methane measurements when supported by appropriate calibration and deterministic signal conditioning. Future work will focus on advanced plume localization algorithms, autonomous navigation strategies, and enhanced methane emission quantification capabilities.

Drones doi: 10.3390/drones10060424

Authors: Weigang Wen Weicong Zhong Yang Liu Xun Li Huiqing Lan

As unmanned aerial vehicles (UAVs) are increasingly deployed in various fields, their flight safety has become a critical issue. However, limited onboard sensing and computing resources make it difficult to perform intelligent fault monitoring and diagnosis directly on UAVs. To explore an offboard alternative, this paper investigates a drone nest vibration analysis based fault diagnosis framework for a multirotor UAV rotor system using vibration signals measured from a laboratory-scale simulated drone nest. A simplified coupled dynamic model of the UAV–drone nest system is established to analyze the transmission mechanism of rotor fault-induced vibration and to explain the observability of fault-related frequency components under the tested configuration. Considering the weak and attenuated characteristics of the nest-side vibration signals, a multi-domain feature fusion and multi-task learning network is developed to integrate time-domain, frequency-domain, and envelope-spectrum information while jointly learning fault type and rotational speed. Comparative experiments on the constructed quadrotor–drone nest test platform are conducted to validate the feasibility and effectiveness of the proposed method under the tested operating conditions.

Drones doi: 10.3390/drones10060423

Authors: Yan Liu Pengtao Zhang Zheng Fang

This paper addresses the dynamic mission reliability evaluation of unmanned aerial vehicle (UAV) swarms. To handle the inherent complexity of swarm systems and the limitations of existing static evaluation methods, a new approach based on an improved dynamic Bayesian network (DBN) is proposed. A hierarchical hidden state space is constructed on the basis of the DBN, and a nonlinear state transition model is employed to capture the coupling effects among performance indicators as well as the associated degradation patterns. Stage-dependent observation models are then integrated with measurement data, and particle filtering is used to perform online state estimation. Finally, the mission reliability of the UAV swarm is derived from the estimation results. Simulation case studies demonstrate the effectiveness and feasibility of the proposed method.

Drones doi: 10.3390/drones10060422

Authors: Gandrothu Karthik Namburi Rupesh Joel John Rayappa David Amar Raj Claudio Tomazzoli Cristian Randieri

To ensure the reliability and sustained performance of industrial photovoltaic (PV) systems, fault detection frameworks must achieve both high detection accuracy and computational efficiency, particularly for deployment on resource-constrained edge platforms. This work proposes a lightweight and low-latency photovoltaic defect detection framework that integrates DCGAN-based generative augmentation with the proposed GhostViT-YOLOv10n architecture. The augmentation strategy helps address class imbalance, improve representation of rare defects, and enhance generalization capability in electroluminescence (EL) imagery through structured geometric and photometric transformations. The proposed framework integrates lightweight Ghost-based optimization, Cross-Stage Partial Fusion (C2f), Spatial Pyramid Pooling—Fast (SPPF), MobileViT contextual learning, and SimAM-based attention refinement to improve multi-scale feature extraction while maintaining low computational complexity. Experimental evaluation on the PVEL-AD and PV Multi Defect benchmark datasets demonstrates strong detection performance. On the PVEL-AD dataset, the BaseLine achieves a mAP@0.5 of 71.6% with only 2.7 M parameters and 8.4 GFLOPs, while our proposed GhostViT-YOLOv10n framework with DCGAN-enhanced version further improves detection performance to 93.6% mAP@0.5 with only 2.19 M parameters and 6.6 GFLOPs. On the PV Multi Defect dataset, the BaseLine achieves a mAP@0.5 of 74.0% with 2.71 M parameters and 8.4 GFLOPs, and the optimized framework with DCGAN-augmented configuration further improves performance to 95.4% mAP@0.5 with 2.58 M parameters and 7.7 GFLOPs. These results demonstrate the effectiveness of combining lightweight architectural optimization with generative augmentation for improving rare defect representation and multi-scale photovoltaic defect detection. To validate practical deployment feasibility, the optimized framework was deployed on a Raspberry Pi 5 using ONNX Runtime under CPU-only conditions. The deployed model achieved an average inference time of 43.05 ms and a real-time processing speed of 23.23 FPS while maintaining moderate CPU utilization and stable thermal behavior. These deployment results demonstrate the suitability of the proposed framework for lightweight edge-oriented photovoltaic inspection applications without requiring GPU acceleration. All evaluations were conducted exclusively on real test datasets, while synthetic samples were used only during training to improve data diversity and rare defect representation. Overall, the proposed framework provides a balanced solution that combines detection accuracy, computational efficiency, lightweight edge deployment capability, and generative augmentation for practical photovoltaic defect inspection applications with potential suitability for future drone-assisted inspection scenarios.

Drones doi: 10.3390/drones10060421

Authors: Ruihao Guo Wei Zhang Wentao Xu Kerong Ren Xianfeng Zhang Chunyu Wang Bo Cheng Hua Qing

High-velocity multi-projectile impacts from accidental external debris (e.g., uncontained engine debris or runway stones) on the liquid-filled fuel tanks of modern unmanned aerial vehicles (UAVs) induce complex Fluid–Structure Interaction (FSI) and Hydrodynamic Ram (HRAM) effects, resulting in highly complex dynamic response mechanisms. This study combines high-velocity impact tests with Three-Dimensional Digital Image Correlation (3D-DIC) technology and employs FSI finite element simulations based on the Structured Arbitrary Lagrangian–Eulerian (S-ALE) algorithm to thoroughly investigate the dynamic response mechanisms of liquid-filled containers penetrated by dual projectiles under different spatial spacings and temporal intervals. The results indicate that variations in the spatiotemporal parameters of dual projectiles significantly reconstruct the fluid load field: small spacing and short temporal intervals induce strong wave interference and superposition, generating an amplified composite loading effect that causes a sharp increase in target plate impulse and deformation energy. Conversely, small spacing and long temporal intervals trigger a significant “cavity shielding” phenomenon, causing the subsequent projectile to travel through the existing cavity, which massively suppresses the effective generation of its load and energy transfer. Furthermore, fluid displacement induced by cavity intersection generates secondary pressure waves; the petal hole evolution of the rear plate is dictated by the formation of plastic hinge lines, presenting four typical deformation modes—oblique cross, normal cross, asymmetric pentagon, and hexagon—depending on the degree of spatiotemporal coupling. This study reveals the laws governing the enhanced HRAM effect of dual projectiles, providing key theoretical support for the lightweight protection design and crashworthiness evaluation of long-endurance commercial UAV fuel tanks.

Drones doi: 10.3390/drones10060420

Authors: Julian Rothe Nicolas Kessler Martin Henriquez Wehr Annika Hohbach Michael Strohmeier Sergio Montenegro

The rapidly increasing availability of low-cost commercial UAVs poses significant security challenges for critical infrastructure and law enforcement agencies. This paper presents an integrated LiDAR-based detection and vision-based verification system for an autonomous drone-on-drone aerial interception system. To eliminate the threat of possible dangerous target drones, the interception UAVs presented in this paper use a net to capture them safely in the air. The system addresses the critical limitation of ground-based sensors, which provide insufficient precision for reliable net-based capture operations. Moving beyond simulation-only approaches, the core novelty of this work lies in the successful real-world integration of these sensors on a strictly constrained aerial platform in size, weight and power to achieve sub-meter terminal guidance precision. The developed system uses real-time point cloud processing, DBSCAN clustering, and Moving Horizon Estimation tracking for the detection and tracking of the target. Vision-based verification uses a custom-trained YOLO neural network and achieves over 90% detection rates. The evaluation demonstrates a detection accuracy of less than 0.4 m at ranges exceeding 40 m during dynamic interception scenarios using RTK-GNSS ground truth. The dual-sensor approach successfully completed multiple autonomous interception missions with target detection ranges of up to 60 m, validating the capability of the system for safe, autonomous civilian UAV interception.

Drones doi: 10.3390/drones10060419

Authors: Yaozhong Zhang Jingwen Huang Qiming Yang Yi Cao Jiandong Zhang Guoqing Shi

The interception of saturation incursions by Unmanned Aerial Vehicle (UAV) swarms presents critical challenges in multi-agent coordination, including the curse of dimensionality, heterogeneous interaction effects, and multi-scale decision-making requirements. This paper proposes a Hierarchical Multi-scale Mean-Field DDPG (HM-MF-DDPG) framework augmented by graph sampling and aggregation networks to address these challenges. The framework introduces three key innovations: (1) a graph-enhanced weighted mean-field approximation that employs attention mechanisms to dynamically assess the contextual importance of neighboring agents, overcoming the homogeneity limitation of conventional mean-field methods; (2) a hierarchical decision architecture that separates strategic coordination (via graph attention networks) from low-level flight control (via improved gated recurrent units with situational awareness modulation); and (3) a distributed target assignment mechanism formulated as a potential game and solved via parallel auction algorithms, enabling collision-free allocation without central coordination. Extensive simulations in a constructed UAV swarm interception environment demonstrate that the proposed framework achieves a 93% interception success rate with 50 interceptors against 25 intruders, outperforming Deep Deterministic Policy Gradient (DDPG) and Mean-Field DDPG (MF-DDPG) baselines in both convergence speed and task efficiency. The framework exhibits robust generalization across varying No-Fly Zone (NFZ) configurations and swarm scales, providing a scalable solution for cooperative interception under saturation incursions.

Drones doi: 10.3390/drones10060418

Authors: Lei Zuo Ying Wang Jialu Liu Yu Lu Ruiwen Gu

To address the challenges of unbalanced task allocation, high inter-UAV collision risks, and lagging interception guidance in multi-UAV cooperative missions within complex urban low-altitude environments, a cooperative interception strategy integrating load-balanced allocation, k-nearest neighbor (k-NN) cooperative obstacle avoidance, and adaptive predictive guidance is proposed. First, a load-balanced Hungarian algorithm is developed at the task allocation layer. The integration of a multi-dimensional distance-angle threat assessment model and a nonlinear load penalty mechanism resolves the issues of resource idling and target overloading inherent in traditional one-to-one allocation, thereby achieving optimal resource configuration for saturated cooperative interception. Second, at the path planning layer, a cooperative obstacle avoidance algorithm based on k-NN nonlinear repulsion is introduced. By exclusively considering the dynamic repulsive fields of local nearest neighbors alongside scale-adaptive parameter regulation, this approach maintains safe formation spacing while reducing the computational complexity from O(n2) to O(k)(k≪n), significantly enhancing flight robustness in dense airspaces. Finally, at the terminal guidance layer, an adaptive look-ahead guidance model incorporating motion prediction is constructed to mitigate the overshoot and lag defects associated with classical pure pursuit algorithms during the interception of highly maneuverable targets. The implementation of linear extrapolation and dynamic gain regulation facilitates a paradigm shift from “passive pursuit” to “active interception.” Simulation results demonstrate that the proposed algorithm yields substantial improvements in task allocation efficiency, collision risk mitigation, and overall success rates across red-blue UAV swarm confrontation scenarios of varying scales. These findings provide a viable cooperative defense framework against large-scale, highly maneuverable unmanned aerial vehicle (UAV) swarm intrusions.

Drones doi: 10.3390/drones10060417

Authors: Paolo Tripicchio Edwin Paúl Herrera-Alarcón Davide Bagheri Carlo Alberto Avizzano Massimo Satler

This article presents the design, implementation, and experimental validation of an autonomous drone system for search and rescue operations in cluttered GNSS-denied environments. The proposed platform integrates advanced navigation, mapping, and victim-detection capabilities, leveraging a suite of RGB-D cameras and edge-AI computation for real-time perception and decision-making. A key contribution is the integration of an eye-blink-detection pipeline for onboard assessment of the consciousness states of detected victims, enabling the drone to prioritize rescue efforts based on victim alertness. The system employs a modular software architecture with a pipeline that combines a U-Net segmentation network with a MultiScaleLSTM classifier, achieving approximately 97.73% accuracy and a combined inference latency of 6.35 ms on the NVIDIA Jetson Xavier-NX. Experimental results demonstrate the drone’s ability to autonomously explore unknown environments, accurately detect and classify victims, and operate effectively in real-world scenarios. The article also discusses observed challenges, such as computational bottlenecks and false positive detections, and outlines future directions for improving system robustness and autonomy.