Drones

24 pages, 639 KB

Open AccessArticle

Human Machine Autonomy in Medical and Humanitarian Logistics in Remote and Infrastructure-Poor Settings

by Martha R. Grabowski, Gwendolyn Morgan, James McGarvey, Steve Roberts, Robert Squire, Sebastian Ibanez, Selmer Bringsjord and Aaron Rowen

Drones 2025, 9(12), 841; https://doi.org/10.3390/drones9120841 (registering DOI) - 5 Dec 2025

Abstract

Human–autonomy teams (HATs) incorporating uncrewed aerial systems (UASs) play critical roles in a variety of safety-critical systems. Increased autonomy in HATs in beyond visual line of sight (BVLOS) UAS operations introduces new mission, safety, and logistics system performance challenges, and highlights the scarcity [...] Read more.

Human–autonomy teams (HATs) incorporating uncrewed aerial systems (UASs) play critical roles in a variety of safety-critical systems. Increased autonomy in HATs in beyond visual line of sight (BVLOS) UAS operations introduces new mission, safety, and logistics system performance challenges, and highlights the scarcity of in situ empirical research examining UAS and operator performance and operator situation awareness in HATs with embedded autonomy, particularly in remote and infrastructure-poor settings. This work addresses this research gap and examines the challenges and contributions of HATs employing various levels of autonomy in remote humanitarian logistics delivery systems, using initial empirical data from an on-going study in a resource-constrained environment. The preliminary results suggest the importance of considering human and technology performance and perceptions in HATs together, particularly in infrastructure-poor settings such as the Arctic, where leveraging limited resources is critical and the force multiplication effects of HATs may have significant impact. Full article

(This article belongs to the Special Issue Recent Advances in Healthcare Applications of Drones)

► Show Figures

Figure 1

57 pages, 6092 KB

Open AccessReview

Development Stages of Quadrotors from Past to Present: A Review

by Mehmet Karahan

Drones 2025, 9(12), 840; https://doi.org/10.3390/drones9120840 (registering DOI) - 5 Dec 2025

Abstract

Quadrotors have been under development for over a century. The first quadrotors were large, heavy, and difficult to control aircraft operated by a single pilot. The first quadrotors remained in the prototype stage due to accidents, budget cuts, and failure to meet military [...] Read more.

Quadrotors have been under development for over a century. The first quadrotors were large, heavy, and difficult to control aircraft operated by a single pilot. The first quadrotors remained in the prototype stage due to accidents, budget cuts, and failure to meet military standards. Production of manned quadrotors ceased in the 1980s. Since the 2010s, manned quadrotors have been used as air taxis, achieving greater success. The development of quadrotor unmanned aerial vehicles (UAVs) began in the 1990s. Their small size, low cost, and ease of control have made them advantageous. Advances in hardware and software technologies have expanded the use of quadrotor UAVs. Today, quadrotor UAVs are used in various fields, including surveillance, aerial photography, search and rescue, firefighting, first aid, cargo transportation, agricultural spraying, mapping, mineral exploration, and counterterrorism. This review examines the development of manned quadrotors and quadrotor UAVs in detail from the past to the present. First, the major manned quadrotors developed are described in detail, along with their technical specifications and photographs. Graphs are provided showing the weight, powerplant, flight duration, and passenger capacity of manned quadrotors. Second, the main quadrotor UAV models entering mass production are discussed, presenting their development processes, technical specifications, areas of use, and photographs. Graphs are presented showing the weight, battery capacity, flight duration, and camera resolution of quadrotor UAVs. Unlike studies focusing solely on the recent past, this review provides a broad overview of the development of quadrotors from their inception to the present. Full article

(This article belongs to the Section Drone Design and Development)

25 pages, 1643 KB

Open AccessArticle

A Quality Evaluation Method for Drone Swarm Command and Control Networks Based on Complex Network

by Zijun Zhao, Shitao Chen, Le Ru, Gang Hu and Wenfei Wang

Drones 2025, 9(12), 839; https://doi.org/10.3390/drones9120839 (registering DOI) - 4 Dec 2025

Abstract

To address the issues of structural diversity, modeling complexity, and the lack of evaluation methods in drone swarm command and control (C2) networks, this paper proposes a complex network-based quality evaluation method for drone swarm C2 networks from a network topology perspective. First, [...] Read more.

To address the issues of structural diversity, modeling complexity, and the lack of evaluation methods in drone swarm command and control (C2) networks, this paper proposes a complex network-based quality evaluation method for drone swarm C2 networks from a network topology perspective. First, by analyzing the structure of the drone swarm C2 system, three hierarchical C2 network models are constructed, which are based on the Leader–Follower architecture, BA scale-free network, and ER random network, respectively. Subsequently, a drone swarm network quality evaluation indicator, system integrating network connectivity, load status, and transmission efficiency is established, along with an evaluation model that considers both static and dynamic characteristics. Finally, an analysis is conducted using networks of the same scale but different C2 structures. The evaluation results demonstrate that this method can effectively distinguish the performance of networks with different structures and exhibits good applicability under both random and targeted attack scenarios. Under static scenarios, distributed C2 networks exhibit the highest quality values, while centralized networks demonstrate the lowest. In random attack scenarios, the Leader–Follower structure achieves the highest network quality among the three hierarchical architectures, outperforming BA and ER network structures by 117% and 25%. In targeted attack scenarios, the ER network structure achieves the highest network quality, surpassing Leader–Follower and BA network structures by 66% and 17%. It provides a quantitative reference for the design and optimisation of the drone swarm C2 system structure. Full article

(This article belongs to the Section Artificial Intelligence in Drones (AID))

► Show Figures

Figure 1

20 pages, 3503 KB

Open AccessArticle

Vibration Fatigue Assessment of UAV Wing Pylons Based on the PSD Method

by Lijun Sui, Youchao Sun and Haonan Sun

Drones 2025, 9(12), 838; https://doi.org/10.3390/drones9120838 - 4 Dec 2025

Abstract

(1) Background: The structural integrity of key components in unmanned aerial vehicle (UAV) mission systems is crucial for achieving performance goals. The installation environment of military and civilian UAV wing pylons is very complex, as they are subject to various complex vibration excitations. [...] Read more.

(1) Background: The structural integrity of key components in unmanned aerial vehicle (UAV) mission systems is crucial for achieving performance goals. The installation environment of military and civilian UAV wing pylons is very complex, as they are subject to various complex vibration excitations. Therefore, it is necessary to conduct vibration fatigue analysis on the wing pylons of UAVs to ensure structural integrity and safe operation. (2) Method: This study is based on the experience of vibration fatigue design for military and civilian aircraft, and flight test data of HH-100 UAV, a specific wing pylon for UAV, was taken as the research object, and the vibration evaluation modeling method was studied. A vibration fatigue assessment model for wing pylons was established, and relevant fatigue failure and strain data were collected through experimental data to validate the vibration fatigue analysis model. A fatigue analysis model was used to conduct fatigue analysis on the design details of the wing pylon structure under multi-source dynamic loads and to determine the structural vibration fatigue characteristics. (3) Result: Based on the finite element method and using the power spectral density (PSD) of the load spectrum, analyses and calculations were carried out to obtain the stress distribution of the connecting structure under vibration and impact loads. Based on this, the fatigue weaknesses of the structure have been clearly identified. Subsequently, dynamic fatigue analysis was conducted to calculate the fatigue life of the structure. Using Miner’s damage accumulation theory and considering the uncertainty of calculations or the sensitivity of results to geometric simplification and PSD spectra, the nominal fatigue life of the pylon structure was obtained through conversion. (4) Conclusions: Using a fatigue analysis model validated through experiments, a comprehensive damage accumulation evaluation was conducted on the fatigue life of the wing pylon under external multi-source dynamic loads, and the vibration fatigue life of the wing pylon was obtained, which meets the design requirements of UAVs. Full article

► Show Figures

Figure 1

35 pages, 2620 KB

Open AccessArticle

Overlapping Coalition Formation for Resource Allocation in Post-Disaster Rescue UAV Swarms

by Wenxin Li, Yongxin Feng, Fan Zhou, Konstantin Igorevich Kostromitin, Jian Wang and Peiying Zhang

Drones 2025, 9(12), 837; https://doi.org/10.3390/drones9120837 - 4 Dec 2025

Abstract

Unmanned aerial vehicle (UAV) swarms, equipped for distributed sensing and rapid response, can form coalitions to undertake complex missions such as post-disaster relief, communication support, and payload delivery. However, typical coalition formation methods assign each UAV to a single task, limiting cross-task resource [...] Read more.

Unmanned aerial vehicle (UAV) swarms, equipped for distributed sensing and rapid response, can form coalitions to undertake complex missions such as post-disaster relief, communication support, and payload delivery. However, typical coalition formation methods assign each UAV to a single task, limiting cross-task resource sharing. To address this, we investigate overlapping coalition formation (OCF) for UAV swarms, where a single UAV is permitted to participate in multiple coalitions, enabling resource reuse and reducing idleness. We formulate OCF as a multi-objective combinatorial optimization problem that jointly balances task fulfillment ratio, coalition synchronization deviation, and operational cost, while explicitly accounting for inter-coalition resource contention and execution precedence. Specifically, we first construct a hypergraph representation of UAVs and tasks and employ a hypergraph attention network to capture their high-order interactions. Next, we propose a structure-aware hierarchical value decomposition method for policy learning, which progressively aggregates individual- and coalition-level information, models member complementarity and inter-coalition cooperative–competitive relations, and generates a global value estimate that is sensitive to changes in coalition structure. Furthermore, we integrate Monte Carlo Tree Search, utilizing the learned value as a heuristic to efficiently explore the feasible region, and close the loop with candidate-structure demonstration replay and policy distillation, enabling search to refine the learned policy. In multi-scale rescue simulations, the proposed approach improves task utility by up to 11.4% over the best-performing baseline and increases energy efficiency by more than 228% compared to a non-overlapping coalition variant. Full article

(This article belongs to the Topic Advanced Technologies and Applications for Unmanned Systems)

► Show Figures

Figure 1

21 pages, 5801 KB

Open AccessArticle

A Gaussian Process-Based Funnel MPC for Docking Control of Unmanned Underwater Vehicles by Learning Residual Dynamics

by Jie Liu, Shaowen Hao, Yimin Chen, Jiarun Wang and Jian Gao

Drones 2025, 9(12), 836; https://doi.org/10.3390/drones9120836 - 3 Dec 2025

Abstract

This paper presents a Gaussian Process (GP)-based Funnel Model Predictive Control (MPC) for docking control of unmanned underwater vehicles (UUVs). The control method employs a Gaussian Process regression to learn the residual dynamics, which compensates for the unmodeled dynamics to improve prediction accuracy. [...] Read more.

This paper presents a Gaussian Process (GP)-based Funnel Model Predictive Control (MPC) for docking control of unmanned underwater vehicles (UUVs). The control method employs a Gaussian Process regression to learn the residual dynamics, which compensates for the unmodeled dynamics to improve prediction accuracy. Furthermore, a distance-adaptive performance funnel is designed to satisfy the field of view (FOV) constraints of sensors during the terminal guidance phase. The funnel imposes time-varying constraints on the UUV to ensure that the docking station remains observable. This funnel constraint is integrated into the cost function of the MPC, which systematically enforces safety without the computational complexity of traditional invariant sets. Comparative simulations validate the framework’s reliability under external disturbances, demonstrating superior tracking precision against conventional MPC benchmarks. Full article

(This article belongs to the Section Unmanned Surface and Underwater Drones)

► Show Figures

Figure 1

32 pages, 845 KB

Open AccessArticle

Flight Loads Evaluation and Airworthiness Compliance for the V-Tail of a Medium-Altitude Long-Endurance Unmanned Platform

by Pierluigi Della Vecchia, Vincenzo Cusati and Claudio Mirabella

Drones 2025, 9(12), 835; https://doi.org/10.3390/drones9120835 - 2 Dec 2025

Abstract

This work addresses the critical need for documentation and validation of structural flight loads for Medium-Altitude Long-Endurance (MALE) Unmanned Aerial Systems (UAS). Despite the increasing prevalence of these aircraft, the industrial and research landscape still exhibits a significant data gap regarding loads under [...] Read more.

This work addresses the critical need for documentation and validation of structural flight loads for Medium-Altitude Long-Endurance (MALE) Unmanned Aerial Systems (UAS). Despite the increasing prevalence of these aircraft, the industrial and research landscape still exhibits a significant data gap regarding loads under extreme operating conditions, particularly for unconventional geometric configurations. This study presents a rigorous and comprehensive load analysis for the certification of a fixed-wing MALE UAS, which is distinguished by its unique V-Tail configuration, characteristic of platforms such as the Elbit Hermes series. The entire investigation was conducted in strict adherence to the requirements of the NATO airworthiness standard STANAG 4671, aiming to precisely define the aerodynamic behavior and structural integrity of the airframe under an exhaustive set of critical flight conditions. The implemented methodology relies on the use of high-fidelity Computational Fluid Dynamics (CFD) data, derived from RANS simulations to create a complete aerodynamic database. This advanced approach is crucial for the accurate modeling of forces and moments, especially those generated by the coupled control surfaces, known as the ruddervators of the V-Tail. The results obtained include the precise derivation of the operational envelope, which defines the maximum load factors for both maneuver and atmospheric gust conditions. A detailed analysis of balancing and specific loads on the control surfaces was performed, leading to the definition of structural load distributions essential for subsequent stress analysis. Notably, the analysis identified the Unchecked Pitch-Up maneuver performed at the maximum load factor as the dimensioning design condition, particularly for the empennage structure. This work not only provides fundamental data for demonstrating compliance with applicable airworthiness criteria but also establishes a robust and repeatable methodology for the evaluation of flight loads in structurally complex UAS configurations. Full article

(This article belongs to the Section Drone Design and Development)

► Show Figures

Figure 1

34 pages, 15573 KB

Open AccessArticle

A Learning-Based Measurement Validation Approach for Cooperative Multi-UAV Navigation Using Kalman Filtering

by Kenan Can Taşan and Ahmet Akbulut

Drones 2025, 9(12), 834; https://doi.org/10.3390/drones9120834 - 2 Dec 2025

Abstract

Reliable navigation in cooperative unmanned aerial vehicle (UAV) networks requires adaptively managing measurement degradations within Kalman-filter-based estimation frameworks. This paper introduces a learning-based Kalman approach for real-time detection of degraded measurements in mesh-network-based multi-UAV navigation. The method incorporates a data-driven pre-filtering module that [...] Read more.

Reliable navigation in cooperative unmanned aerial vehicle (UAV) networks requires adaptively managing measurement degradations within Kalman-filter-based estimation frameworks. This paper introduces a learning-based Kalman approach for real-time detection of degraded measurements in mesh-network-based multi-UAV navigation. The method incorporates a data-driven pre-filtering module that assesses measurement reliability prior to the Kalman update, thereby improving the robustness of the estimation process under communication-induced degradations. Within this approach, four measurement fault detection strategies—Innovation Filter (IF), Deep Q-Network (DQN), Multi-Layer Perceptron (MLP), and Long Short-Term Memory (LSTM)—were implemented and comparatively evaluated through Monte Carlo simulations combining inertial sensors, time-of-arrival, and Doppler-based inter-agent observations. Additional statistical analyses, including ±1σ error bars and a Wilcoxon rank-sum test, were conducted to verify the significance of the performance differences among the methods. The results show that the proposed approach significantly enhances navigation reliability, particularly under degraded or intermittent GNSS and communication conditions. The MLP-based configuration achieved the best balance between fault-detection accuracy and overall filter consistency. These findings confirm the effectiveness of learning-augmented Kalman filtering architectures for robust and scalable cooperative UAV navigation. Full article

(This article belongs to the Section Artificial Intelligence in Drones (AID))

► Show Figures

Figure 1

21 pages, 4950 KB

Open AccessArticle

Enhanced UAV-Dot for UAV Crowd Localization: Adaptive Gaussian Heat Map and Attention Mechanism to Address Scale/Low-Light Challenges

by Min Zhang, Fei Zhao and Yan Zhang

Drones 2025, 9(12), 833; https://doi.org/10.3390/drones9120833 - 1 Dec 2025

Abstract

In public safety scenarios, such as large-scale event security and urban crowd management, unmanned aerial vehicles (UAVs) serve as a vital tool for crowd localization, offering high mobility and broad coverage. However, UAV-based overhead localization faces challenges, including significant target scale variations due [...] Read more.

In public safety scenarios, such as large-scale event security and urban crowd management, unmanned aerial vehicles (UAVs) serve as a vital tool for crowd localization, offering high mobility and broad coverage. However, UAV-based overhead localization faces challenges, including significant target scale variations due to altitude changes and poor feature visibility in low-light conditions. To overcome these issues, this study enhances the UAV-Dot framework by introducing a scale prediction branch for adaptive Gaussian heatmap adjustment, embedding a CBAM attention module in the U-Net encoder to strengthen feature extraction in dim environments and optimizing post-processing via dynamic thresholding and DBSCAN clustering. Experiments on the DroneCrowd dataset show that the improved model increases parameters by only 0.36% during training and 0.29% during testing yet achieves 53.38% L-mAP—outperforming the original UAV-Dot by 2.38% and STNNet by 12.93%. The model also delivers consistent gains of approximately 2% in L-AP@10, L-AP@15, and L-AP@20. Full article

► Show Figures

Figure 1

21 pages, 6125 KB

Open AccessArticle

An Online Human-Aware Behavior Planning Method for Nondeterministic UAV System Under Probabilistic Model Checking

by Jiancheng Zhu, Peng Wang, Yong Peng and Quanjun Yin

Drones 2025, 9(12), 832; https://doi.org/10.3390/drones9120832 - 1 Dec 2025

Abstract

This paper proposes an online human-aware behavior planning method to enable Unmanned Aerial Vehicles (UAVs) to dynamically satisfy high-level linear temporal logic (LTL) task descriptions from human collaborators. The proposed method has the potential to be applied to the industrial human–UAV collaboration. The [...] Read more.

This paper proposes an online human-aware behavior planning method to enable Unmanned Aerial Vehicles (UAVs) to dynamically satisfy high-level linear temporal logic (LTL) task descriptions from human collaborators. The proposed method has the potential to be applied to the industrial human–UAV collaboration. The specific process is as follows. Firstly, the global high-level task of the UAV is described using the formal language of LTL, which can usually be issued by human collaborators in natural language. Secondly, the task description is transformed into a deterministic Rabin automaton, and then the state values of the automaton are given by the distance from the accepted states. Thirdly, the Markov decision process is used to construct the probabilistic behavior model of the UAV offline. Based on this model, a finite state automaton in the finite horizon is dynamically constructed online, and the Cartesian product system within the horizon is constructed, in which the expected arrival states within the horizon are set by the minimum state values. Finally, aiming at maximizing the reachability probability of the expected states, the value iterative algorithm is introduced to solve the optimal behavior plan online within the finite horizon. After it, an infinite horizon planning and execution algorithm is formed. Experiments and analysis show that the results of the online behavior planning are consistent with the task logic at the semantic level, indicating the correctness of the proposed method. Moreover, the proposed method can effectively alleviate the state explosion caused by the global probabilistic model checking and improve the efficiency of plan generation. Full article

► Show Figures

Figure 1

24 pages, 10999 KB

Open AccessArticle

CE-Bi-RRT*: Enhanced Bidirectional RRT* with Cooperative Expansion Strategy for Autonomous Drone Navigation

by Guangjun Gao, Jijian Lu and Weiyuan Guan

Drones 2025, 9(12), 831; https://doi.org/10.3390/drones9120831 - 30 Nov 2025

Abstract

Path planning is a critical capability for unmanned aerial vehicles (UAVs) operating in complex 2D environments such as agricultural fields or indoor facilities—scenarios where flight altitude is often constrained and safe, smooth trajectories are essential. While the sampling-based Bidirectional RRT* (BI-RRT*) algorithm offers [...] Read more.

Path planning is a critical capability for unmanned aerial vehicles (UAVs) operating in complex 2D environments such as agricultural fields or indoor facilities—scenarios where flight altitude is often constrained and safe, smooth trajectories are essential. While the sampling-based Bidirectional RRT* (BI-RRT*) algorithm offers asymptotic optimality and improved computational efficiency, it frequently generates paths that lack the curvature continuity, obstacle clearance, and low turning angles required for stable drone flight. To address these limitations, this paper proposes a bi-directional rapid exploration random tree algorithm based on cooperative expansion strategy (CE-BI-RRT*) specifically designed for UAVs path planning in cluttered 2D settings. In terms of expansion, for different environments, the algorithm successively tests the direct expansion strategy, the intelligent deflection strategy and the improved artificial potential field method, as these strategies can quickly guide the two trees to the target while avoiding obstacles. In terms of ChooseParent and Rewire, the path length, path smoothness and safety distance are comprehensively considered in the path cost function, and a rotation strategy is applied to make the path away from obstacles after rewiring, so as to realize the gradual optimization of the path. The final path is further refined using a cubic Bezier curve optimization technique to ensure smooth transitions and continuous curvature. Evaluation results confirm its search performance when benchmarked against mainstream randomized motion planning algorithms. Full article

► Show Figures

Figure 1

20 pages, 6710 KB

Open AccessArticle

A Phenotyping Perception Mechanism of Fusing Spatial and Channel Reconstruction Convolution Employing Maize-Breeding UAV Visual Images

by Huanzhe Wang, Jian Chen, Xiqing Wang and Shuaisong Zhang

Drones 2025, 9(12), 830; https://doi.org/10.3390/drones9120830 - 30 Nov 2025

Abstract

As precision agriculture advances, UAV-based aerial image object detection has emerged as a pivotal technology for maize-phenotyping perception operations. Complex backgrounds reduce the model’s performance in extracting features of maize tassels, while sacrificing model computation complexity to improve feature expression is detrimental to [...] Read more.

As precision agriculture advances, UAV-based aerial image object detection has emerged as a pivotal technology for maize-phenotyping perception operations. Complex backgrounds reduce the model’s performance in extracting features of maize tassels, while sacrificing model computation complexity to improve feature expression is detrimental to deployment on UAVs. To achieve a balance between the model size and deploy ability, an enhanced model incorporating spatial-channel convolution is proposed. First, a maize-breeding UAV was built, and the collection of maize tassel image data was realized. Second, Spatial and Channel Reconstruction Convolution (SCConv) was integrated into the neck network of the YOLOv8 baseline model, reducing the model computation complexity while maintaining the detection accuracy. Finally, the constructed maize tassel dataset and public Maize Tasseling Stage (MTS) dataset were used for the training and evaluation of the enhanced model. The results showed that the enhanced model achieved a precision of 92.2%, recall of 84.3%, and mAP@0.5 of 91.7%, with 7.3 G floating-point operations (FLOPs) and a model size of 5.16 MB. Compared with the original model, the enhanced model exhibited respective increases of 3.2%, 3.4%, and 3.4% in precision, recall, and mAP@0.5, along with respective reductions of 0.8 G FLOPs in computation complexity and 0.79 MB in model size. Compared with YOLOv10n, the precision, recall, and mAP@0.5 of the enhanced model are increased by 1.8%, 3.1%, and 2.9%, respectively, and the model computation is reduced by 0.3 G FLOPs, and the model size is reduced by 0.42 MB. The improved model is accurate, performs better on UAV aerial images in complex scenarios, and provides a methodological basis for deployment. It also supports maize tassel detection and holds potential for application in maize breeding. Full article

(This article belongs to the Special Issue Advances of UAV in Precision Agriculture—2nd Edition)

► Show Figures

Figure 1

19 pages, 3750 KB

Open AccessArticle

Autonomous UAV-Based Volcanic Gas Monitoring: A Simulation-Validated Case Study in Santorini

by Theodoros Karachalios and Theofanis Orphanoudakis

Drones 2025, 9(12), 829; https://doi.org/10.3390/drones9120829 - 29 Nov 2025

Abstract

Unmanned Aerial Vehicles (UAVs) can deliver rapid, spatially resolved measurements of volcanic gases that often precede eruptions, yet most deployments remain manual or preplanned and are slow to react to seismic unrest. In the present work, we present a simulation-validated design of an [...] Read more.

Unmanned Aerial Vehicles (UAVs) can deliver rapid, spatially resolved measurements of volcanic gases that often precede eruptions, yet most deployments remain manual or preplanned and are slow to react to seismic unrest. In the present work, we present a simulation-validated design of an earthquake-triggered, autonomous workflow for early detection of CO₂ anomalies, demonstrated through a conceptual case study focused on the Santorini caldera. The system ingests real-time seismic alerts, generates missions automatically, and executes a two-stage sensing strategy: a fast scan to build a coarse CO₂ heatmap followed by targeted high-precision sampling at emerging hotspots. Mission planning includes wind-and terrain-aware flight profiles, geofenced safety envelopes and a facility-location approach to landing-site placement; in a Santorini case study, we provide a ring of candidate launch/landing zones with wind-contingent usage, illustrate adaptive replanning driven by heatmap uncertainty and outline calibration and quality-control steps for robust CO₂ mapping. The proposed methodology offers an operational blueprint that links seismic triggers to actionable, georeferenced gas information and can be transferred to other island or caldera volcanoes. Full article

(This article belongs to the Special Issue Unmanned Aerial Vehicles for Enhanced Emergency Response)

► Show Figures

Figure 1

19 pages, 806 KB

Open AccessArticle

DPAD: Distribution-Driven Perturbation-Adaptive Defense for UAV Time-Series Regression Under Hybrid Adversarial Attacks

by Bo Xu, Zhiqiang Liu, Zhongjun Dong, Kaiqi Huang, Xiaopeng Huang, Haolin Zhu, Jun Wei, Yong Li, Yangbai Zhang and Xiuping Li

Drones 2025, 9(12), 828; https://doi.org/10.3390/drones9120828 - 28 Nov 2025

Abstract

Time-series regression models are essential components in unmanned aerial vehicles (UAVs) for accurate trajectory and state prediction. Nevertheless, they are still vulnerable to hybrid adversarial attacks, which can lead to a compromised mission performance and cause huge economic loss. For this challenge, we [...] Read more.

Time-series regression models are essential components in unmanned aerial vehicles (UAVs) for accurate trajectory and state prediction. Nevertheless, they are still vulnerable to hybrid adversarial attacks, which can lead to a compromised mission performance and cause huge economic loss. For this challenge, we propose the Distribution-driven Perturbation-Adaptive Defense (DPAD) framework. DPAD improves perturbation detection with Gaussian Mixture Model (GMM)-based feature augmentation that raises the accuracy of perturbation strength prediction, increasing from 0.685 to 0.943

R^{2}

, and dynamically chooses a suitable defense sub-model or the original model for adaptive correction. The experiments on UAV_Delivery show that DPAD significantly enhances robustness by achieving about 80% reduction in prediction errors under hybrid attacks while maintaining high accuracy on clean samples with an inference speed of 2.744 ms per sample. The proposed framework can scale up an effective solution to defend UAV time-series regression models against complex adversarial scenarios. Full article

(This article belongs to the Special Issue Recent Developments in Artificial Intelligence and Interdisciplinary Research for UAV Application)

► Show Figures

Figure 1

25 pages, 8947 KB

Open AccessArticle

Advancing Real-Time Aerial Wildfire Detection Through Plume Recognition and Knowledge Distillation

by Pirunthan Keerthinathan, Juan Sandino, Sutharsan Mahendren, Anuraj Uthayasooriyan, Julian Galvez, Grant Hamilton and Felipe Gonzalez

Drones 2025, 9(12), 827; https://doi.org/10.3390/drones9120827 - 28 Nov 2025

Abstract

Uncrewed aerial systems (UAS)-based remote sensing and artificial intelligence (AI) analysis enable real-time wildfire or bushfire detection, facilitating early response to minimize damage and protect lives and property. However, their effectiveness is limited by three issues: distinguishing smoke from fog, the high cost [...] Read more.

Uncrewed aerial systems (UAS)-based remote sensing and artificial intelligence (AI) analysis enable real-time wildfire or bushfire detection, facilitating early response to minimize damage and protect lives and property. However, their effectiveness is limited by three issues: distinguishing smoke from fog, the high cost of manual annotation, and the computational demands of large models. This study addresses the three key challenges by introducing plume as a new indicator to better distinguish smoke from similar visual elements, and by employing a hybrid annotation method using knowledge distillation (KD) to reduce expert labour and accelerate labelling. Additionally, it leverages lightweight YOLO Nano models trained with pseudo-labels generated from a fine-tuned teacher network to lower computational demands while maintaining high detection accuracy for real-time wildfire monitoring. Controlled pile burns in Canungra, QLD, Australia, were conducted to collect UAS-captured images over deciduous vegetation, which were subsequently augmented with the Flame2 dataset, which contains wildfire images of coniferous vegetation. A Grounding DINO model, fine-tuned using few-shot learning, served as the teacher network to generate pseudo-labels for a significant portion of the Flame2 dataset. These pseudo-labels were then used to train student networks consisting of YOLO Nano architectures, specifically versions 5, 8, and 11 (YOLOv5n, YOLOv8n, YOLOv11n). The experimental results show that YOLOv8n and YOLOv5n achieved an mAP@0.5 of 0.721. Plume detection outperforms smoke indicators (F1: 76.1–85.7% vs. 70%) in fog and wildfire scenarios. These findings underscore the value of incorporating plume as a distinct class and utilizing KD, both of which enhance detection accuracy and scalability, ultimately supporting more reliable and timelier wildfire monitoring and response. Full article

(This article belongs to the Special Issue Rapid Disaster Assessment and Post-Disaster Recovery Using UAV Remote Sensing)

► Show Figures

Figure 1

26 pages, 2005 KB

Open AccessArticle

PLMT-Net: A Physics-Aware Lightweight Network for Multi-Agent Trajectory Prediction in Interactive Driving Scenarios

by Wan Yu, Fuyun Liu, Huiqi Liu, Ming Chen and Liangliang Zhao

Drones 2025, 9(12), 826; https://doi.org/10.3390/drones9120826 - 28 Nov 2025

Abstract

Accurate and efficient multi-agent trajectory prediction remains a core challenge for autonomous driving, particularly in modeling complex interactions while maintaining physical plausibility and computational efficiency. Many existing methods- especially those based on large transformer architectures- tend to overlook physical constraints, leading to unrealistic [...] Read more.

Accurate and efficient multi-agent trajectory prediction remains a core challenge for autonomous driving, particularly in modeling complex interactions while maintaining physical plausibility and computational efficiency. Many existing methods- especially those based on large transformer architectures- tend to overlook physical constraints, leading to unrealistic predictions and high deployment costs. In this work, we propose a lightweight trajectory prediction framework that integrates physical information to enhance interaction modeling and runtime performance. Our method introduces two physically inspired strategies: (1) a constraint-guided mechanism is used to filter irrelevant or distracting neighbors, and (2) a physics-aware attention module is applied to steer attention weights toward physically plausible interactions. The overall architecture adopts a modular and vectorized design, effectively reducing model complexity and inference latency. Experiments on the Argoverse V1 dataset, comparing against multiple existing methods, demonstrate that our approach achieves a favorable balance among accuracy, physical feasibility, and efficiency, running in real time on a commodity desktop GPU. Future work will focus on validating its performance on embedded hardware. Full article

(This article belongs to the Section Innovative Urban Mobility)

► Show Figures

Figure 1

28 pages, 4458 KB

Open AccessArticle

Multi-UAV Cooperative Search in Partially Observable Low-Altitude Environments Based on Deep Reinforcement Learning

by Xiu-Xia Yang, Wen-Qiang Yao, Yi Zhang, Hao Yu and Chao Wang

Drones 2025, 9(12), 825; https://doi.org/10.3390/drones9120825 - 27 Nov 2025

Abstract

Multi-Unmanned Aerial Vehicle (Multi-UAV) cooperative search represents a cutting-edge research direction in the field of unmanned aerial vehicle applications. The use of multi-UAV systems for low-altitude target search and area surveillance has become an effective means of enhancing security capabilities. In practical scenarios, [...] Read more.

Multi-Unmanned Aerial Vehicle (Multi-UAV) cooperative search represents a cutting-edge research direction in the field of unmanned aerial vehicle applications. The use of multi-UAV systems for low-altitude target search and area surveillance has become an effective means of enhancing security capabilities. In practical scenarios, UAVs rely on onboard sensors to acquire environmental information; however, due to the limited perceptual range of these sensors, their observation capabilities are inherently local and constrained. This paper investigates the problem of multi-UAV cooperative search in partially observable low-altitude environments, where each UAV possesses a circular sensing range with a finite radius. Target location information is only obtained when a target enters the field of view of any UAV. The objective is to achieve cooperative search and sustain continuous surveillance while ensuring safety among UAVs and with the environment. To address this challenge, we propose a novel multi-agent deep reinforcement learning (MADRL) algorithm named Normalizing Graph Attention Soft Actor-Critic (NGASAC). This algorithm integrates a normalizing flow (NL) layer and a multi-head graph attention network (MHGAT). The normalizing flow technique maps traditional Gaussian sampling to a more complex action distribution, thereby enhancing the expressiveness and flexibility of the policy. Simultaneously, by constructing a multi-head graph attention network that captures “obstacle–target” relationships, the algorithm improves the UAVs’ ability to learn and reason about complex spatial topologies, leading to significantly better performance in cooperative search and stable surveillance of hidden targets. Simulation results demonstrate that the NGASAC algorithm markedly outperforms baseline methods such as Multi-Agent Soft Actor-Critic (MASAC), Multi-Agent Proximal Policy Optimization (MAPPO), and Multi-Agent Deep Deterministic Policy Gradient (MADDPG) across multiple evaluation metrics, including success rate, task time, and obstacle avoidance capability. Furthermore, it exhibits strong generalization performance and robustness. Full article

► Show Figures

Figure 1

24 pages, 2374 KB

Open AccessArticle

NightTrack: Joint Night-Time Image Enhancement and Object Tracking for UAVs

by Xiaomin Huang, Yunpeng Bai, Jiaman Ma, Ying Li, Changjing Shang and Qiang Shen

Drones 2025, 9(12), 824; https://doi.org/10.3390/drones9120824 - 27 Nov 2025

Abstract

UAV-based visual object tracking has recently become a prominent research focus in computer vision. However, most existing trackers are primarily benchmarked under well-illuminated conditions, largely overlooking the challenges that may arise in night-time scenarios. Although attempts exist to restore image brightness via low-light [...] Read more.

UAV-based visual object tracking has recently become a prominent research focus in computer vision. However, most existing trackers are primarily benchmarked under well-illuminated conditions, largely overlooking the challenges that may arise in night-time scenarios. Although attempts exist to restore image brightness via low-light image enhancement before feeding frames to a tracker, such two-stage pipelines often struggle to strike an effective balance between the competing objectives of enhancement and tracking. To address this limitation, this work proposes NightTrack, a unified framework that optimizes both low-light image enhancement and UAV object tracking. While boosting image visibility, NightTrack not only explicitly preserves but also reinforces the discriminative features required for robust tracking. To improve the discriminability of low-light representations, Pyramid Attention Modules (PAMs) are introduced to enhance multi-scale contextual cues. Moreover, by jointly estimating illumination and noise curves, NightTrack mitigates the potential adverse effects of low-light environments, leading to significant gains in precision and robustness. Experimental results on multiple night-time tracking benchmarks demonstrate that NightTrack outperforms state-of-the-art methods in night-time scenes, exhibiting strong promises for further development. Full article

(This article belongs to the Special Issue Recent Developments in Artificial Intelligence and Interdisciplinary Research for UAV Application)

► Show Figures

Figure 1

24 pages, 15285 KB

Open AccessArticle

An Efficient and Accurate UAV State Estimation Method with Multi-LiDAR–IMU–Camera Fusion

by Junfeng Ding, Pei An, Kun Yu, Tao Ma, Bin Fang and Jie Ma

Drones 2025, 9(12), 823; https://doi.org/10.3390/drones9120823 - 27 Nov 2025

Abstract

State estimation plays a vital role in UAV navigation and control. With the continuous decrease in sensor cost and size, UAVs equipped with multiple LiDARs, Inertial Measurement Units (IMUs), and cameras have attracted increasing attention. Such systems can acquire rich environmental and motion [...] Read more.

State estimation plays a vital role in UAV navigation and control. With the continuous decrease in sensor cost and size, UAVs equipped with multiple LiDARs, Inertial Measurement Units (IMUs), and cameras have attracted increasing attention. Such systems can acquire rich environmental and motion information from multiple perspectives, thereby enabling more precise navigation and mapping in complex environments. However, efficiently utilizing multi-sensor data for state estimation remains challenging. There is a complex coupling relationship between IMUs’ bias and UAV state. To address these challenges, this paper proposes an efficient and accurate UAV state estimation method tailored for multi-LiDAR–IMU–camera systems. Specifically, we first construct an efficient distributed state estimation model. It decomposes the multi-LiDAR–IMU–camera system into a series of single LiDAR–IMU–camera subsystems, reformulating the complex coupling problem as an efficient distributed state estimation problem. Then, we derive an accurate feedback function to constrain and optimize the UAV state using estimated subsystem states, thus enhancing overall estimation accuracy. Based on this model, we design an efficient distributed state estimation algorithm with multi-LiDAR-IMU-Camerafusion, termed DLIC. DLIC achieves robust multi-sensor data fusion via shared feature maps, effectively improving both estimation robustness and accuracy. In addition, we design an accelerated image-to-point cloud registration module (A-I2P) to provide reliable visual measurements, further boosting state estimation efficiency. Extensive experiments are conducted on 18 real-world indoor and outdoor scenarios from the public NTU VIRAL dataset. The results demonstrate that DLIC consistently outperforms existing multi-sensor methods across key evaluation metrics, including RMSE, MAE, SD, and SSE. More importantly, our method runs in real time on a resource-constrained embedded device equipped with only an 8-core CPU, while maintaining low memory consumption. Full article

(This article belongs to the Special Issue Advances in Guidance, Navigation, and Control)

► Show Figures

Figure 1

Journal Description

Drones

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI