Drones, Volume 9, Issue 5 (May 2025) – 66 articles

Early detection of cotton diseases is critical for safeguarding crop yield and minimizing agrochemical usage. However, most state-of-the-art systems rely on multispectral or hyperspectral sensors, which are costly and inaccessible to smallholder farmers. This paper introduces CottoNet, a lightweight and efficient deep learning framework for detecting early-stage cotton diseases using only RGB images captured by unmanned aerial vehicles (UAVs). The proposed model integrates an EfficientNetV2-S backbone with a Dual-Attention Feature Pyramid Network (DA-FPN) and a novel Early Symptom Emphasis Module (ESEM) to enhance sensitivity to subtle visual cues such as chlorosis, minor lesions, and texture irregularities. A custom-labeled dataset was collected from cotton fields in Uzbekistan to evaluate the model under realistic agricultural conditions. CottoNet achieved a mean average precision (mAP@50) of 89.7%, an F1 score of 88.2%, and an early detection accuracy (EDA) of 91.5%, outperforming existing lightweight models while maintaining real-time inference speed on embedded devices. The results demonstrate that CottoNet offers a scalable, accurate, and field-ready solution for precision agriculture in resource-limited settings. Full article

This study proposes an unmanned combat aerial vehicle (UCAV)-oriented hierarchical reinforcement learning framework to address the temporal abstraction challenge in autonomous within-visual-range air combat (WVRAC) for UCAVs. The incorporation of maximum-entropy objectives within the MEOL framework facilitates the optimization of both autonomous low-level tactical discovery and high-level option selection. At the low level, three tactical policies (angle, snapshot, and energy tactics) are designed with reward functions informed by expert knowledge, while the high-level policy dynamically terminates current tactics and selects new ones through sparse reward learning, thus overcoming the limitations of fixed-duration tactical execution. Furthermore, a novel automatic curriculum generation mechanism based on Wasserstein Generative Adversarial Networks (WGANs) is introduced to enhance training efficiency and adaptability to diverse initial combat conditions. Extensive experiments conducted in UCAV air combat simulations have shown that MEOL not only achieves significantly better win rates than other policies when training against rule-based opponents, but also that MEOC achieves superior results in tests against tactical intra-option policies as well as other option learning policies. The framework facilitates dynamic termination and switching of tactics, thereby addressing the limitations of fixed-duration hierarchical methods. Ablation studies confirm the effectiveness of WGAN-based curricula in accelerating policy convergence. Additionally, the visual analysis of UCAVs’ flight logs validates the learned hierarchical decision-making process, showcasing the interplay between tactical selection and manoeuvring execution. This research provides novel methodologies combining hierarchical reinforcement learning with tactical domain knowledge for the autonomous decision-making of UCAVs in complex air combat scenarios. Full article

This review explores the evolution and current state of aerial drones’ use in geophysical mining applications. Aerial drones have transformed many fields by offering high-resolution and cost-effective data acquisition. In geophysics, drones equipped with advanced sensors such as magnetometers, ground-penetrating radar, electromagnetic induction, and gamma-ray spectrometry have enabled more precise and rapid subsurface investigations, reducing operational costs and improving safety in mining exploration and monitoring. Over the last decade, advances in drone navigation, sensor integration, and data processing have improved the accuracy and applicability of geophysical surveys in mining. This review provides a historical overview and examines the latest developments in aerial drones, sensing technologies, data acquisition strategies, and processing methodologies. It analyses 59 studies spanning 66 drone-based geophysical applications and 63 geophysical method entries, published between 2005 and 2025. Multirotor drones are the most common, used in 72.73% of cases, followed by fixed-wing drones (12.12%), unmanned helicopters (9.09%), hybrid VTOL designs (3.03%), airships (1.52%), and one unspecified platform (1.52%). In terms of geophysical methods, magnetometry was the most frequently used technique, applied in thirty-nine studies, followed by gamma-ray spectrometry (eighteen studies), electromagnetic surveys (five studies), and ground-penetrating radar (one study). The findings show how drone-based geophysical techniques enhance resource exploration, safety, and sustainability in mining. Full article

In recent years, UAVs have faced increasingly severe and diversified missile threats. To address the challenge that reinforcement learning-based missile evasion algorithms struggle to adapt to various unknown missile types, we introduce a risk-sensitive PPO algorithm and propose a training framework incorporating multi-head attention mechanisms and dual-population adversarial training. The multi-head attention mechanism enables the policy network to extract latent features such as missile guidance laws from state sequences, while the dual-population adversarial approach ensures policy diversity and robustness. Compared to conventional self-play methods and GRU-based evasion strategies, our method demonstrates superior training efficiency and generates evasion policies with better adaptability to different missile types. Full article

Wireless power transfer (WPT) systems are critical for enabling safe and efficient charging of inspection drones in flammable oilfield environments, yet existing solutions struggle with multi-target compatibility and reactive power losses. This study proposes a novel frequency-regulated LCC-S topology that achieves both constant current (CC) and constant voltage (CV) charging modes for heterogeneous drones using a single hardware configuration. By dynamically adjusting the operating frequency, the system minimizes the input impedance angle (θ < 10°) while maintaining load-independent CC and CV outputs, thereby reducing reactive power by 92% and ensuring spark-free operation in explosive atmospheres. Experimental validation with two distinct oilfield inspection drones demonstrates seamless mode transitions, zero-phase-angle (ZPA) resonance, and peak efficiencies of 92.57% and 91.12%, respectively. The universal design eliminates the need for complex alignment mechanisms, offering a scalable solution for multi-drone fleets in energy, agriculture, and disaster response applications. Full article

This paper presents a strategy for collision detection and recovery control of drones using an onboard Inertial Measurement Unit (IMU). The collision detection algorithm compares the expected response of the drone with the measurements from the IMU to identify and characterize collisions. The recovery controller implements a gain scheduling approach, adjusting its parameters based on the characteristics of the collision and the drone’s attitude. Simulations were conducted to compare the proposed collision detection strategy with a popular detection method with fixed thresholds, and the simulation results showed that the proposed approach outperformed the existing method in terms of detection accuracy. Furthermore, the proposed collision detection and recovery control approaches were tested with physical experiments using a custom-built drone. The experimental results confirmed that the proposed collision detection algorithm was able to distinguish between actual collisions and aggressive flight maneuvers, and the recovery controller can recover the drone within 0.8 s. Full article

Unmanned aerial vehicle (UAV) self-localization in complex environments is critical when global navigation satellite systems (GNSSs) are unreliable. Existing datasets, often limited to low-altitude urban scenes, hinder generalization. This study introduces Multi-UAV, a novel dataset with 17.4 k high-resolution UAV–satellite image pairs from diverse terrains (urban, rural, mountainous, farmland, coastal) and altitudes across China, enhancing cross-view geolocalization research. We propose a lightweight value reduction pyramid transformer (VRPT) for efficient feature extraction and a residual feature pyramid network (RFPN) for multi-scale feature fusion. Using meter-level accuracy (MA@K) and relative distance score (RDS), VRPT achieves robust, high-precision localization across varied terrains, offering significant potential for resource-constrained UAV deployment. Full article

This paper presents a neural network-based path planning method for fixed-wing UAVs under terminal roll-angle constraints. The nonlinear optimal path planning problem is first formulated as an optimal control problem. The necessary conditions derived from Pontryagin’s Maximum Principle are then established to convert extremal trajectories as the solutions of a parameterized system. Additionally, a sufficient condition is presented to guarantee that the obtained solution is at least locally optimal. By simply propagating the parameterized system, a training dataset comprising at least locally optimal trajectories can be constructed. A neural network is then trained to generate the nonlinear optimal control command in real time. Finally, numerical examples demonstrate that the proposed method robustly ensures the generation of optimal trajectories in real time while satisfying the prescribed terminal roll-angle constraint. Full article

Unmanned aerial vehicle (UAV) swarms are widely applied in various fields, including military and civilian domains. However, due to the scarcity of spectrum resources, UAV swarm clustering technology has emerged as an effective method for achieving spectrum sharing among UAV swarms. This paper introduces a distributed heterogeneous multi-agent deep reinforcement learning algorithm, named HMDRL-UC, which is specifically designed to address the cluster-based spectrum sharing problem in heterogeneous UAV swarms. Heterogeneous UAV swarms consist of two types of UAVs: cluster head (CH) and cluster member (CM). Each UAV is equipped with an intelligent agent to execute the deep reinforcement learning (DRL) algorithm. Correspondingly, the HMDRL-UC consists of two parts: multi-agent proximal policy optimization for cluster head (MAPPO-H) and independent proximal policy optimization for cluster member (IPPO-M). The MAPPO-H enables the CHs to decide cluster selection and moving position, while CMs utilize IPPO-M to cluster autonomously under the condition of certain partial channel distribution information (CDI). Adequate experimental evidence has confirmed that the HMDRL-UC algorithm proposed in this paper is not only capable of managing dynamic drone swarm scenarios in the presence of partial CDI, but also has a clear advantage over the other existing three algorithms in terms of average throughput, intra-cluster communication delay, and minimum signal-to-noise ratio (SNR). Full article

Unmanned aerial vehicles (UAVs) have revolutionized fields such as monitoring, cargo delivery, precision farming, and emergency response, demonstrating remarkable flexibility and operational effectiveness. A fundamental aspect of UAV autonomy lies in route optimization, which determines efficient paths while considering factors like mission goals, safety, and power consumption. This article presents an extensive overview of methodologies for UAV route planning, including deterministic models, stochastic sampling techniques, biologically inspired methods, and integrated algorithmic frameworks. The discussion extends to their performance in various operational contexts, including stationary, moving, and three-dimensional settings. Innovative methods utilizing artificial intelligence, particularly machine learning and neural networks, are emphasized for their promise in facilitating adaptive responses to intricate, evolving environments. Furthermore, strategies focused on reducing energy usage and enabling coordinated operations among multiple drones are analyzed, addressing issues such as prolonged operation, distribution of assignments, and navigation around obstacles. Although notable advancements have been achieved, challenges like high computational demands and the need for immediate responsiveness persist. By consolidating the latest progress, this survey provides meaningful perspectives and guidance for the ongoing evolution of UAV route planning solutions. Full article

In recent years, rapid progress in autonomous driving has been achieved through advances in sensing, control, and earning. However, as the complexity of traffic scenarios increases, ensuring safe interaction among vehicles remains a formidable challenge. Recent works combining artificial potential fields (APFs) with game-theoretic methods have shown promise in modeling vehicle interactions and avoiding collisions. However, these approaches often suffer from overly conservative decisions or fail to capture the nonlinear dynamics of real-world driving. To address these imitations, we propose a novel framework that integrates mean field game (MFG) theory with model predictive control (MPC) and quadratic programming (QP). Our approach everages the aggregate behavior of surrounding vehicles to predict interactive effects and embeds these predictions into an MPC-QP scheme for real-time control. Simulation results in complex driving scenarios demonstrate that our method achieves multiple autonomous driving tasks while ensuring collision-free operation. Furthermore, the proposed framework outperforms popular game-based benchmarks in terms of achieving driving tasks and producing fewer collisions. Full article

The distributed electric tilt-rotor Unmanned Aerial Vehicle (UAV) combines the vertical take-off and landing (VTOL) capability of helicopters with the high-speed cruise performance of fixed-wing aircraft, offering a transformative solution for Urban Air Mobility (UAM). However, aerodynamic interference between rotors is a new challenge to improving their flight efficiency, especially the dynamic interactions during the transition phase of non-parallel tandem dual-rotor systems, which require in-depth investigation. This study focuses on the aerodynamic performance evolution of the tilt-rotor system during asynchronous transition processes, with an emphasis on quantifying the influence of rotor tilt angles. A customized experimental platform was developed to investigate a counter-rotating dual-rotor model with fixed axial separation. Key performance metrics, including thrust, torque, and power, were systematically measured at various tilt angles (0–90°) and rotational speeds (1500–3500 RPM). The aerodynamic coupling mechanisms between the front and rear rotor disks were analyzed. The experimental results indicate that the relative tilt angle of the dual rotors significantly affects aerodynamic interference between the rotors. In the forward tilt mode, the thrust of the aft rotor recovers when the tilt angle reaches 45°, while in the aft tilt mode, it requires a tilt angle of 75°. By optimizing the tilt configuration, the aerodynamic performance loss of the aft rotor due to rotor-to-rotor aerodynamic interference can be effectively mitigated. This study provides important insights for the aerodynamic performance optimization and transition control strategies of the distributed electric tilt-rotor UAV. Full article

Remote sensing visual-light spectral (VIS) maps provide stable and rich features for geo-localization. However, it still remains a challenge to make use of VIS map features as localization references at night. To construct a cross-day-and-night localization system for long-duration UAVs, this study proposes a visual–inertial integrated localization system, where the visual component can register both RGB and infrared camera images in one unified VIS map. To deal with the large differences between visible and thermal images, we inspected various visual features and utilized a pre-trained network for cross-domain feature extraction and matching. To obtain an accurate position from visual geo-localization, we demonstrate a localization error compensation algorithm with considerations about the camera attitude, flight height, and terrain height. Finally, the inertial and dual-vision information is fused with a State Transformation Extended Kalman Filter (ST-EKF) to generate long-term, drift-free localization performance. Finally, we conducted actual long-duration flight experiments with altitudes ranging from 700 to 2400 m and flight distances longer than 344.6 km. The experimental results demonstrate that the proposed method’s localization error is less than 50 m in its RMSE. Full article

Servo-free tilt-rotor UAVs decouple position and attitude control without using servos, which cuts structural weight and removes the travel limits of traditional designs. In many applications—such as aerial platform operations and airborne photogrammetry—large attitude changes are required during hover. Conventional control-allocation schemes tend to distribute thrust unevenly, making actuators prone to saturation. To overcome these challenges, we propose a thrust-balancing control-allocation strategy specifically for passive-hinge tilt-rotor octocopters. The presented method integrates min–max optimization with the force decomposition (FD) algorithm, effectively handling actuator saturation while maintaining low computational complexity. Additionally, an offline-trained neural network is employed to replace the online optimization process, enabling the complete controller to operate on the flight control board without relying on an onboard computer. Simulation and experiment results confirm the effectiveness of the proposed strategy, demonstrating enhanced control performance and its practical feasibility for real-world UAV applications. Full article

This paper considers the multiple path planning problem to cover a region of interest using vertical takeoff and landing (VTOL) drones. Drones are used not only to explore unknown areas but also to view areas from the air that are difficult for people to approach by cars, boats, etc. Hence, the coverage path planning for drones should work regardless of whether the drone is inside or outside the region of interest. The proposed algorithm starts by adjusting the region of interest based on the capturing area. Once the region of interest is determined, multiple path plans are created based on the pre-derived rules for generating an optimal path under the general case and the drone’s performance, such as speed, maximum flight time, etc. The aim is to minimize the time to cover the whole region of interest. Hence, the following criteria are applied to determine the appropriateness of the generated paths: (1) whether the start and end points of the path are located as close as possible to the drone’s position, (2) whether the number of generated paths is appropriate, and (3) whether the makespan differences between the paths are small. The performance of the proposed algorithm is verified by numerous simulations. Full article

This study presents a comprehensive methodology for urban traffic monitoring and infrastructure decision making, centered on synchronous, simultaneous aerial data collection through a distributed multi-point UAV deployment. Conducted in the GreenLine district of Astana, Kazakhstan, the research utilized a coordinated fleet of UAVs to capture real-time video footage at 30 critical observation points during peak traffic periods, enabling a network-wide view of traffic dynamics. The collected data were processed to extract key traffic parameters, such as flow rates, vehicle speeds, and delays, which informed the calibration of a detailed traffic simulation model. Based on this model, six infrastructure development scenarios were evaluated using a multi-criteria decision-making framework to identify the most effective intervention strategies. This study introduces a replicable, data-driven approach that links synchronized UAV sensing with simulation-based evaluation, offering a practical decision support tool for improving urban infrastructure performance within the context of smart and rapidly evolving cities. Full article

With the rapid advancement of UAV technology, robust object detection under adverse weather conditions has become critical for enhancing UAVs’ environmental perception. However, object detection in such challenging conditions remains a significant hurdle, and standardized evaluation benchmarks are still lacking. To bridge this gap, we introduce the Adverse Weather Object Detection (AWOD) dataset—a large-scale dataset tailored for object detection in complex maritime environments. The AWOD dataset comprises 20,000 images captured under three representative adverse weather conditions: foggy, flare, and low-light. To address the challenges of scale variation and visual degradation introduced by harsh weather, we propose WRRT-DETR, a weather-robust object detection framework optimized for small objects. Within this framework, we design a gated single-head global–local attention backbone block (GLCE) to fuse local convolutional features with global attention, enhancing small object distinguishability. Additionally, a Frequency–Spatial Feature Augmentation Module (FSAE) is introduced to incorporate frequency-domain information for improved robustness, while an Attention-based Cross-Fusion Module (ACFM) facilitates the integration of multi-scale features. Experimental results demonstrate that WRRT-DETR outperforms SOTA methods on the AWOD dataset, exhibiting superior robustness and detection accuracy in complex weather conditions. Full article

In the context of evolving Smart Cities, the integration of drone technology and distributed computing paradigms presents significant potential for enhancing urban infrastructure and services. This paper proposes a comprehensive approach to optimizing urban delivery logistics through a cloud-based model that employs Ant Colony Optimization (ACO) for planning and Model Predictive Control (MPC) for trajectory tracking within a broader Computing Continuum framework. The proposed system addresses the Capacitated Vehicle Routing Problem (CVRP) by considering both drone capacity constraints and autonomy, using the ACO-based algorithm to efficiently assign delivery destinations while minimizing travel distances. Collision-free paths are computed by using a Visibility Graph (VG) based approach, and MPC controllers enable drones to adapt to dynamic obstacles in real time. Additionally, this work explores how clusters of drones can be deployed as edge devices within the Computing Continuum, seamlessly integrating with IoT sensors and fog computing infrastructure to support various urban applications, such as traffic management, crowd monitoring, and infrastructure inspections. This dual-architecture approach, combining the optimization capabilities of ACO with the flexible, distributed nature of the Computing Continuum, allows for scalable and efficient urban drone deployment. Simulation results validate the effectiveness of the proposed model in enhancing delivery efficiency and collision avoidance while demonstrating the potential of integrating drone technology into Smart City environments for improved data collection and real-time response. Full article

Mobile edge computing (MEC) has become an effective framework for latency-sensitive and computation-intensive applications by deploying computing resources at network edge. The unmanned aerial vehicle (UAV)-assisted MEC leverages UAV mobility and communication advantages to enable services in dynamic environments, where frequent adjustments to flight trajectories and user association are required due to dynamic factors such as time-varying task requirements, user mobility, and communication environment variation. This paper addresses the joint optimization problem of UAV flight trajectory control and user association in dynamic environments, which explicitly incorporates the constraints governed by UAV flight dynamics. The joint problem is formulated as a non-convex optimization formulation that involves continuous–discrete hybrid decision variables. To overcome the inherent complexity of this problem, a novel proximal policy optimization-based dynamic control (PPO-DC) algorithm is developed. This algorithm aims to reduce the weighted combination of delay and energy consumption by dynamically controlling the UAV trajectory and user association. The numerical results validate that the PPO-DC algorithm successfully enables real-time UAV trajectory control under flight dynamics constraints, ensuring feasible and efficient flight trajectory. Compared to the state-of-the-art hybrid-action deep reinforcement learning (DRL) algorithms or metaheuristics, the PPO-DC achieves notable improvements in system performance by simultaneously lowering system delay and energy consumption. Full article

This paper utilizes the distributed model predictive control (DMPC) method to investigate the formation control problem of unmanned aerial vehicles (UAVs) in the obstacle environment and establishes cooperative capability evaluation metrics of the swarm. Based on the DMPC approach, the formation cost function is constructed to adjust the relative positions and velocities of UAVs, ensuring the desired formation. Additionally, to address the obstacle avoidance problem in the formation, the obstacle avoidance function is designed to provide safe formation control in the obstacle environment. To evaluate the cooperative capability of UAVs, we design evaluation metrics from multiple dimensions to reflect the swarm’s cooperative capability. Finally, the simulation results show the effectiveness of the formation control method with obstacle avoidance and the applicability of the swarm’s cooperative capability evaluation metrics. Full article

Due to traditional recovery systems lacking visual perception, it is difficult to monitor UAVs’ real-time status in communication-constrained or GPS-denied environments. This leads to insufficient ability in decision-making and parameter adjustment and increase uncertainty and risk of recovery. Visual inspection technology can make up for the limitations of GPS and communication and improve the autonomy and adaptability of the system. However, the existing RT-DETR algorithm is limited by single-path feature extraction, a simplified fusion mechanism, and high-frequency information loss, which makes it difficult to balance detection accuracy and computational efficiency. Therefore, this paper proposes a lightweight visual detection model based on transformer architecture to further optimize computational efficiency. Firstly, aiming at the performance bottleneck of existing models, the Parallel Backbone is proposed, which captures local features and global semantic information by sharing the initial feature extraction module and the double-branch structure, respectively, and uses the progressive fusion mechanism to realize the adaptive integration of multiscale features so as to balance the accuracy and lightness of target detection. Secondly, an adaptive multiscale feature pyramid network (AMFPN) is designed, which effectively integrates different scales of information through multi-level feature fusion and information transmission mechanism, alleviates the problem of information loss in small-target detection, and improves the detection accuracy in complex backgrounds. Finally, a wavelet frequency–domain-optimized reverse feature fusion mechanism (WT-FORM) is proposed. By using the wavelet transform to decompose the shallow features into multi-frequency bands and combining the weighted calculation and feature compensation strategy, the computational complexity is reduced, and the representation ability of the global context is further enhanced. The experimental results show that the improved model reduces the parameter size and computational load by 43.2% and 58% while maintaining detection accuracy comparable to the original RT-DETR in three datasets. Even in complex environments with low light, occlusion, or small targets, it can provide more accurate detection results. Full article

Unmanned Surface Vehicles (USVs) are commonly used as mobile docking stations for Unmanned Aerial Vehicles (UAVs) to ensure sustained operational capabilities. Conventional vision-based techniques based on horizontally-placed fiducial markers for autonomous landing are not only susceptible to interference from lighting and shadows but are also restricted by the limited Field of View (FOV) of the visual system. This study proposes a method that integrates an improved minimum snap trajectory planning algorithm with an event-triggered vision-based technique to achieve autonomous landing on a small USV. The trajectory planning algorithm ensures trajectory smoothness and controls deviations from the target flight path, enabling the UAV to approach the USV despite the visual system’s limited FOV. To avoid direct contact between the UAV and the fiducial marker while mitigating the interference from lighting and shadows on the marker, a landing platform with a vertically placed fiducial marker is designed to separate the UAV landing area from the fiducial marker detection region. Additionally, an event-triggered mechanism is used to limit excessive yaw angle adjustment of the UAV to improve its autonomous landing efficiency and stability. Experiments conducted in both terrestrial and river environments demonstrate that the UAV can successfully perform autonomous landing on a small USV in both stationary and moving scenarios. Full article

This paper establishes an analytical model for component mass, takeoff weight, and performance constraints of distributed electric propulsion (DEP) propeller-driven short takeoff and landing (STOL) unmanned aerial vehicles (UAV), and develops a conceptual design method considering propulsive/aerodynamic coupling effects. The proposed approach was applied to design a 350 kilogram-class DEP UAV with STOL capability, verifying the feasibility and effectiveness of the design method. To investigate the layout design and propulsive/aerodynamic coupling characteristics of DEP UAV, three UAV configurations with different DEP arrangements are formulated and studied, and the results indicate that the flap deflection significantly increases the lift coefficient of the UAV during takeoff, and under the same total thrust and power conditions, the lift-enhancement using DEP arrangement is more significant. In addition, it is necessary to fully consider the propulsive/aerodynamic coupling effects in the conceptual design process, and this is of great significance for the future development of DEP STOL UAV. Full article

Urban wind, and particularly turbulence present in the roughness zone near structures, poses a critical challenge for next-generation drones. Complex flow patterns induced by large buildings produce significant disturbances that the vehicle must reject at low altitudes. Traditional turbulence models, such as the von Kármán model, underestimate these localized effects, compromising flight safety. To address this gap, we integrate high-resolution time and spatially varying urban wind fields from Large Eddy Simulations into a flight dynamics simulation framework using vehicle plant models based on configuration geometry and commonly deployed Ardupilot control laws, enabling a detailed analysis of drone responses in urban environments. Our results reveal that high-risk flight zones can be systematically identified by correlating drone response metrics with the spatial distribution of Turbulent Kinetic Energy (TKE). Notably, maximum g-loads coincide with abrupt TKE transitions, underscoring the critical impact of even short-lived wind fluctuations. By coupling advanced computational fluid dynamics with a real-time vehicle dynamics model, this work establishes a foundational methodology for designing safer and more reliable advanced air mobility platforms in complex urban airspaces. This work distinguishes itself from the existing literature by incorporating an efficient vortex lattice aerodynamic solver that supports arbitrary fixed-wing drone platforms through the simple specification of planform geometry and mass properties, and operating full-flights throughout a time and spatially varying urban wind field. This framework enables a robust assessment of stability and control for a wide range of fixed-wing drone platforms operating in urban environments, with delivery drones serving as a representative and practical use case. Full article

As research on biological unmanned aerial vehicle (UAV) swarm control has blossomed, professionals face increasing time and cognitive pressure in mastering the rapidly growing domain knowledge. Although recent general large language models (LLMs) may augment human cognitive capabilities, they still face significant hallucination and interpretability issues in domain-specific applications. To address these challenges, this study designs and evaluates a domain-specific LLM for the biological UAV swarm control using an enhanced Retrieval-Augmented Generation (RAG) framework. In particular, this study proposes an element-based chunking strategy to build the domain-specific knowledge base and develops novel hybrid retrieval and reranking modules to improve the classical RAG framework. This study also carefully conducts automatic and expert evaluations of our domain-specific LLM, demonstrating the advantages of our model regarding accuracy, relevance, and human alignment. Full article

Unmanned aerial vehicles (UAVs) may encounter actuator faults in diverse flight scenarios, requiring robust fault detection models that can adapt to varying data distributions. To address this challenge, this paper proposes an approach that integrates Domain-Adversarial Neural Networks (DANNs) with a Mixture of Experts (MoE) framework. By employing domain-adversarial learning, the method extracts domain-invariant features, mitigating distribution discrepancies between source and target domains. The MoE architecture dynamically selects specialized expert models based on task-specific data characteristics, improving adaptability to multimodal environments. This integration enhances fault detection accuracy and robustness while maintaining efficiency under constrained computational resources. To validate the proposed model, we conducted flight experiments, demonstrating its superior performance in actuator fault detection compared to conventional deep learning methods. The results highlight the potential of MoE-enhanced domain adaptation for real-time UAV fault detection in dynamic and uncertain environments. Full article

Synergetic transportation schemes are extensively used in package delivery operations, exploiting the best features of different modes. This paper proposes a methodology to solve the mode assignment and routing problem for the case of combined conventional vehicle and unmanned aerial vehicle (CV–UAV) parcel deliveries under uncertainty for next-day operations. This research incorporates ground and air uncertainties: travel times are assumed for conventional vehicles, while UAV paths are affected by weather conditions and restricted flying zones. A nested genetic algorithm is initially used to solve the problem under fixed conditions. Then, a robust optimization approach is employed to propose the best solution that will perform well in a stochastic environment. The framework is applied to a case study of realistic urban–suburban size, and results are discussed. The entire platform is useful for strategic decisions on infrastructure and for operation planning with satisfactory performance and less risk. Full article

With the rapid growth of IoT data and increasing demands for low-latency computation, UAV-assisted mobile edge computing (MEC) offers a flexible solution to overcome the limitations of fixed MEC servers. To better reflect concurrent service scenarios, this paper innovatively develops a multi-channel task modeling method, enabling UAVs to simultaneously select multiple users and offload tasks via separate channels, thereby breaking the constraints of traditional sequential assumptions. To address task conflicts and resource waste caused by sequential service assumptions, this paper proposes a hierarchical reinforcement learning-based trajectory and offloading decision-making framework (H-TAOD) for UAVs with multi-channel parallel processing. The framework decouples UAV trajectory planning and task offloading into two sub-tasks optimized via appropriate reinforcement learning methods. An invalid action masking (IAM) mechanism is introduced to avoid channel conflicts. Simulation results verify the superiority of H-TAOD in reward, delay, and convergence. Full article

This work proposes a power-efficient framework for adaptive video streaming in UAV-assisted wireless networks specially designed for disaster-hit areas where existing base stations are nonfunctional. Delivering high-quality videos requires higher video rates and more resources, which leads to increased power consumption. With the increasing demand of mobile video, efficient bandwidth allocation becomes essential. In shared networks, users with lower bitrates experience poor video quality when high-bitrate users occupy most of the bandwidth, leading to a degraded and unfair user experience. Additionally, frequent video rate switching can significantly impact user experience, making the video rates’ smooth transition essential. The aim of this research is to maximize the overall users’ quality of experience in terms of power-efficient adaptive video streaming by fair distribution and smooth transition of video rates. The joint optimization includes power minimization, efficient resource allocation, i.e., transmit power and bandwidth, and efficient two-dimensional positioning of the UAV while meeting system constraints. The formulated problem is non-convex and difficult to solve with conventional methods. Therefore, to avoid the curse of complexity, the block coordinate descent method, successive convex approximation technique, and efficient iterative algorithm are applied. Extensive simulations are performed to verify the effectiveness of the proposed solution method. The simulation results reveal that the proposed method outperforms 95–97% over equal allocation, 77–89% over random allocation, and 17–40% over joint allocation schemes. Full article