Drones, Volume 8, Issue 6 (June 2024) – 53 articles

In this paper, the predefined-time platoon control for multiple uncertain unmanned aerial vehicles (UAVs) under range-limited communication and external disturbance constraints is considered. A novel control scheme, which can guarantee communication connectivity, collision avoidance, and the predefined convergence time simultaneously, is proposed. To achieve disturbance robustness, an observer-based distributed control law is firstly proposed with a time-varying gain. Then, a radial basis function neural network (RBFNN) with an adaptive tuning law is applied to approximate uncertainties of the system. Under the time and error transformation techniques, uniformly ultimate boundedness (UUB) stability of the closed-loop system is guaranteed within predefined convergence time. Compared with the existing results, the proposed method allows the system to have UUB within any predefined time without depending on the initial conditions or system parameters. Finally, simulation results are presented to verify the derived theorem. Full article

In the event of a sudden natural disaster, the damaged communication infrastructure cannot provide a necessary network service for vehicles. Unfortunately, this is the critical moment when the occupants of trapped vehicles need to urgently use the vehicular network’s emergency service. How to efficiently connect the trapped vehicle to the base station is the challenge facing the emergency vehicular network. To address this challenge, this study proposes a UAV-assisted multi-objective and multi-hop ad hoc network (UMMVN) that can be used as an emergency vehicular network. Firstly, it presents an integrated design of a search system to find a trapped vehicle, the communication relay, and the networking, which significantly decreases the UAV’s networking time cost. Secondly, it presents a multi-objective search for a trapped vehicle and navigates UAVs along multiple paths to different objectives. Thirdly, it presents an optimal branching node strategy that allows the adequate use of the overlapping paths to multiple targets, which decreases the networking cost within the limited communication and searching range. The numerical experiments illustrate that the UMMVN performs better than other state-of-the-art networking methods. Full article

Crafting an edge-based real-time object detector for unmanned aerial vehicle (UAV) aerial images is challenging because of the limited computational resources and the small size of detected objects. Existing lightweight object detectors often prioritize speed over detecting extremely small targets. To better balance this trade-off, this paper proposes an efficient and low-complexity object detector for edge computing platforms deployed on UAVs, termed EUAVDet (Edge-based UAV Object Detector). Specifically, an efficient feature downsampling module and a novel multi-kernel aggregation block are first introduced into the backbone network to retain more feature details and capture richer spatial information. Subsequently, an improved feature pyramid network with a faster ghost module is incorporated into the neck network to fuse multi-scale features with fewer parameters. Experimental evaluations on the VisDrone, SeaDronesSeeV2, and UAVDT datasets demonstrate the effectiveness and plug-and-play capability of our proposed modules. Compared with the state-of-the-art YOLOv8 detector, the proposed EUAVDet achieves better performance in nearly all the metrics, including parameters, FLOPs, mAP, and FPS. The smallest version of EUAVDet (EUAVDet-n) contains only 1.34 M parameters and achieves over 20 fps on the Jetson Nano. Our algorithm strikes a better balance between detection accuracy and inference speed, making it suitable for edge-based UAV applications. Full article

This paper puts forward a coordinated formation control scheme for multiple fixed-wing unmanned aerial vehicle (UAV) systems with external nonlinear disturbances including not only the drag force and uncertain lateral force, but also the drag, lift, and lateral forces caused by wake vortices. A novel distributed finite-time extended state observer is designed to estimate both the unmeasurable states and uncertain external nonlinear disturbances of each fixed-wing UAV. In particular, an event-triggered mechanism is employed to reduce the burden of communication networks among multiple fixed-wing UAVs. Meanwhile, an inter-trigger output predictor, replacing the classic zero-order holder, is adopted to obtain cooperative errors between two consecutive triggering moments. Furthermore, a composite distributed controller is proposed to mitigate uncertain disturbances, enabling the coordinated formation flying of multiple fixed-wing UAVs.Finally, two illustrative simulation scenarios are discussed to verify the performance of the presented coordinated formation control scheme. Full article

Wildlife conservationists have historically depended on manual methods for the identification and tracking of avian species, to monitor population dynamics and discern potential threats. Nonetheless, many of these techniques present inherent challenges and time constraints. With the advancement in computer vision techniques, automated bird detection and recognition have become possible. This study aimed to further advance the task of detecting wild birds using computer vision methods with drone footage, as well as entirely automating the process of detection and tracking. However, detecting objects from drone footage presents a significant challenge, due to the elevated altitudes, as well as the dynamic movement of both the drone and the birds. In this study, we developed and introduce a state-of-the-art model titled ORACLE (optimized rigorous advanced cutting-edge model for leveraging protection to ecosystems). ORACLE aims to facilitate robust communication across multiple models, with the goal of data retrieval, rigorously using various computer vision techniques such as object detection and multi-object tracking (MOT). The results of ORACLE’s vision models were evaluated at 91.89% mAP at 50% IoU. Full article

The application of drones to assist with healthcare delivery has grown rapidly over the last decade. This industry is supported by a growing research field, and we have undertaken a systematic review of the published literature. Web-based searches returned 290 relevant manuscripts published between 2010 and 2024. We applied Topic Modelling to this corpus of literature, which examines word association and connectedness within the research papers. The modelling identified two emerging research themes with little connection between them: those who used drones to deliver time-critical medical items and those who used drones to deliver non-time-critical medical items. The former was in response to medical emergencies, while the latter was for enhancing resilience in the healthcare supply chain. The topics within these research themes exhibited notable differences. The delivery of time-critical medical items theme comprised the topics of ‘Emergency Response’, ‘Defibrillator and Organ Delivery’, and ‘Search and Rescue’, whilst non-time-critical delivery researched the topics of ‘Supply Chain Optimisation’ and ‘Cost-Effectiveness’, ‘Overcoming Remoteness’, and ‘Pandemic Response’. Research on ‘Engineering and Design Considerations’ and ‘Ethical and Social Considerations’ cut across both research themes. We undertook further analysis to assess research topic alignment and identify knowledge gaps. We found that efforts are needed to establish a more standardised terminology for better alignment across the two emerging research themes. Future studies should focus on evaluating the impact of drone delivery on patient health using systematic methods. Additionally, exploring the economic viability of drone-based health services and addressing regulatory barriers are crucial for efficient and effective drone deployment in healthcare delivery systems. Full article

Considering the weak resistance to interference and generalization ability of traditional UAV visual landing navigation algorithms, this paper proposes a deep-learning-based approach for airport runway line detection and fusion of visual information with IMU for localization. Firstly, a coarse positioning algorithm based on YOLOX is designed for airport runway localization. To meet the requirements of model accuracy and inference speed for the landing guidance system, regression loss functions, probability prediction loss functions, activation functions, and feature extraction networks are designed. Secondly, a deep-learning-based runway line detection algorithm including feature extraction, classification prediction and segmentation networks is designed. To create an effective detection network, we propose efficient loss function and network evaluation methods Finally, a visual/inertial navigation system is established based on constant deformation for visual localization. The relative positioning results are fused and optimized with Kalman filter algorithms. Simulation and flight experiments demonstrate that the proposed algorithm exhibits significant advantages in terms of localization accuracy, real-time performance, and generalization ability, and can provide accurate positioning information during UAV landing processes. Full article

The achievement of full autonomy in Unmanned Aerial Vehicles (UAVs) is significantly dependent on effective motion planning. Specifically, it is crucial to plan collision-free trajectories for smooth transitions from initial to final configurations. However, finding a solution executable by the actual system adds complexity: the planned motion must be dynamically feasible. This involves meeting rigorous criteria, including vehicle dynamics, input constraints, and state constraints. This work addresses optimal kinodynamic motion planning for UAVs in the presence of obstacles by employing a hybrid technique instead of conventional search-based or direct trajectory optimization approaches. This technique involves precomputing a library of motion primitives by solving several Two-Point-Boundary-Value Problems (TPBVP) offline. This library is then repeatedly used online within a graph-search framework. Moreover, to make the method computationally tractable, continuity between consecutive motion primitives is enforced only on a subset of the state variables. This approach is compared with a state-of-the-art quadrotor-tailored search-based approach, which generates motion primitives online through control input discretization and forward propagation of the dynamic equations of a simplified model. The effectiveness of both methods is assessed through simulations and real-world experiments, demonstrating their ability to generate resolution-complete, resolution-optimal, collision-free, and dynamically feasible trajectories. Finally, a comparative analysis highlights the advantages, disadvantages, and optimal usage scenarios for each approach. Full article

With the burgeoning impact of artificial intelligence on the traditional UAV industry, the pursuit of autonomous UAV flight has emerged as a focal point of contemporary research. Addressing the imperative for advancing critical technologies in autonomous flight, this paper delves into the realm of UAV flight state recognition and trajectory prediction. Presenting an innovative approach focused on improving the precision of unmanned aerial vehicle (UAV) path forecasting via the identification of flight states, this study demonstrates its efficacy through the implementation of two prediction models. Firstly, UAV flight data acquisition was realized in this paper by the use of multi-sensors. Finally, two models for UAV trajectory prediction were designed based on machine learning methods and classical mathematical prediction methods, respectively, and the results before and after flight pattern recognition are compared. The experimental results show that the prediction error of the UAV trajectory prediction method based on multiple flight modes is smaller than the traditional trajectory prediction method in different flight stages. Full article

The rapid advancement of unmanned aerial vehicle (UAV) technologies has led to an increasing demand for UAV operations in low-altitude, high-density, and complex airspace such as mountains or urban areas. In order to handle complex scenarios and ensure flight safety for UAVs with different flight missions beyond visual line of sight in such environments, a fusion framework of onboard autonomous flight trajectory management and decision-making system using global strategical path planning and local tactical trajectory optimization combination is proposed in this paper. The global strategical path planning is implemented by an enhanced A* algorithm under the multi-constraint of UAV positioning uncertainty and obstacle density to improve the safety and cost-effectiveness. The local tactical trajectory optimization is realized using quadratic programming to ensure smoothness, kinematic feasibility, and obstacle avoidance of the planned trajectory in dynamic environments. Receding-horizon control is used to ensure the flight path and trajectory planning efficiently and seamlessly. To assess the performance of the system, a terrain database and a navigation system are employed for environment and navigation performance simulation. The experimental results confirm that the fusion approach can realize better safety and cost-effectiveness through path planning with kino-dynamic feasible trajectory optimization. Full article

The proliferation of unmanned aerial vehicle (UAV) networks is increasing, driven by their capacity to deliver automated services tailored to the varied demands of numerous smart city applications. Trust, security, and privacy remain paramount in the public domain. Traditional centralized network designs fall short of ensuring device authentication, data integrity, and privacy within the highly dynamic and adaptable environments of UAV networks. Decentralized reputation systems have emerged as a promising solution for enhancing the reliability and trustworthiness of data and communications within these networks while safeguarding UAV security. This paper presents an exhaustive survey of trust and reputation systems, exploring existing frameworks and proposed innovations alongside their inherent challenges. The crucial role of reputation systems is to strengthen trust, security, and privacy throughout these networks, and various strategies can be incorporated to mitigate existing vulnerabilities. As a useful resource for researchers and practitioners seeking to advance the state of the art in UAV network security, we hope this survey will spark further community discussion and stimulate innovative ideas in this burgeoning field. Full article

With the development of computer vision and Unmanned Aerial Vehicles (UAVs) technology, visual object tracking has become an indispensable core technology for UAVs, and it has been widely used in both civil and military fields. Visual object tracking from the UAV perspective experiences interference from various complex conditions such as background clutter, occlusion, and being out of view, which can easily lead to tracking drift. Once tracking drift occurs, it will lead to almost complete failure of the subsequent tracking. Currently, few trackers have been designed to solve the tracking drift problem. Thus, this paper proposes a tracking algorithm based on motion prediction and block search to address the tracking drift problem caused by various complex conditions. Specifically, when the tracker experiences tracking drift, we first use a Kalman filter to predict the motion state of the target, and then use a block search module to relocate the target. In addition, to improve the tracker’s ability to adapt to changes in the target’s appearance and the environment, we propose a dynamic template updating network (DTUN) that allows the tracker to make appropriate template decisions based on various tracking conditions. We also introduce three tracking evaluation metrics: namely, average peak correlation energy, size change ratio, and tracking score. They serve as prior information for tracking status identification in the DTUN and the block prediction module. Extensive experiments and comparisons with many competitive algorithms on five aerial benchmarks, UAV20L, UAV123, UAVDT, DTB70, and VisDrone2018-SOT, demonstrate that our method achieves significant performance improvements. Especially in UAV20L long-term tracking, our method outperforms the baseline in terms of success rate and accuracy by 19.1% and 20.8%, respectively. This demonstrates the superior performance of our method in the task of long-term tracking from the UAV perspective, and we achieve a real-time speed of 43 FPS. Full article

This study primarily studies the shortest-path planning problem for unmanned aerial vehicle (UAV) formations under uncertain target sequences. In order to enhance the efficiency of collaborative search in drone clusters, a compensation look-ahead algorithm based on optimizing the four-point heading angles is proposed. Building upon the receding-horizon algorithm, this method introduces the heading angles of adjacent points to approximately compensate and decouple the triangular equations of the optimal trajectory, and a general formula for calculating the heading angles is proposed. The simulation data indicate that the model using the compensatory look forward algorithm exhibits a maximum improvement of 12.9% compared to other algorithms. Furthermore, to solve the computational complexity and sample size requirements for optimal solutions in the Dubins multiple traveling salesman model, a path-planning model for multiple UAV formations is introduced based on the Euclidean traveling salesman problem (ETSP) pre-allocation. By pre-allocating sub-goals, the model reduces the computational scale of individual samples while maintaining a constant sample size. The simulation results show an 8.4% and 17.5% improvement in sparse regions for the proposed Euclidean Dubins traveling salesman problem (EDTSP) model for takeoff from different points. Full article

Historic buildings hold significant cultural value and their repair and protection require diverse approaches. With the advent of 3D digitalization, drones have gained significance in heritage studies. This research focuses on applying digital methods for restoring architectural heritage. It utilizes non-contact measurement technology, specifically unmanned aerial vehicles (UAVs), for data collection, creating 3D point cloud models using heritage building information modeling (HBIM), and employing virtual reality (VR) for architectural heritage restoration. Employing the “close + surround” oblique photography technique combined with image matching, computer vision, and other technologies, a detailed and comprehensive 3D model of the real scene can be constructed. It provides crucial data support for subsequent protection research and transformation efforts. Using the case of the Santo Stefano Church in Volterra, Italy, an idealized reconstructed 3D model database was established after data collection to preserve essential resources such as the original spatial data and relationships of architectural sites. Through the analysis of relevant historical data and the implementation of VR, the idealized and original appearance of the case was authentically restored. As a result, in the virtual simulation space, the building’s style was realistically displayed with an immersive experience. This approach not only safeguards cultural heritage but also enhances the city’s image and promotes tourism resources, catering to the diverse needs of tourists. Full article

The increasing frequency and intensity of extreme weather events are accelerating the mechanisms of surface degradation of heritage buildings, and it is therefore appropriate to find automatic techniques to reduce the time and cost of monitoring and to support their planned conservation. A fully automated approach is presented here for the segmentation and classification of the architectural elements that make up one of the façades of Palazzo Pitti. The aim of this analysis is to provide tools for a more detailed assessment of the risk of detachment of parts of the pietraforte sandstone elements. Machine learning techniques were applied for the segmentation and classification of information from a DEM obtained via a photogrammetric drone survey. An unsupervised geometry-based classification of the segmented objects was performed using K-means for identifying the most vulnerable elements according to their shapes. The results were validated through comparing them with those obtained via manual segmentation and classification, as well as with studies carried out by experts in the field. The initial results, which can be integrated with non-geometric information, show the usefulness of drone surveys in the context of automatic monitoring of heritage buildings. Full article

To address collision challenges between multi-UAVs (unmanned aerial vehicles) during obstacle avoidance, a novel formation control method is proposed. Leveraging the concept of APF (artificial potential field), the proposed approach integrates UAV maneuver constraints with a consensus formation control algorithm, optimizing UAV velocities through the particle swarm optimization (PSO) algorithm. The optimal consensus control algorithm is then employed to achieve the optimal convergence rate of the UAV formation. To mitigate the limitations of traditional APF, a collinear force deflection angle is introduced, along with an obstacle avoidance method aimed at preventing UAVs from being trapped in locally optimal solutions. Additionally, an obstacle avoidance algorithm based on virtual force fields between UAVs is designed. Comparative analysis against the basic algorithm demonstrates the effectiveness of the designed optimal consensus algorithm in improving formation convergence performance. Moreover, the improved APF resolves local optimal solution issues, enabling UAVs to effectively navigate around obstacles. Simulation results validate the efficacy of this method in achieving multi-UAV formation control while effectively avoiding obstacles. Full article

Drone-based transportation is emerging as a novel mode in city logistics, featuring first-mile pickup and last-mile instant delivery using drones and truck transshipment. A fundamental challenge involves coordinating merchants, drones, transshipment hubs, trucks, and consumer communities through the hub-and-spoke network (HSN). This study formulated the optimization problem for HSN to minimize logistics costs and loss of orders constrained by service time limits. The ε-constraint model, two evolutionary algorithms based on Non-dominated Sorting Genetic Algorithm II (NSGA-II) using permutation (EAp) and rand key-based (EAr) encoding/decoding schemes were devised to solve the bi-objective mathematical program. Three groups of twelve experiments were conducted using ideal datasets and datasets generated from Shenzhen city to validate the models and algorithms. Relaxing the logistics objective by 10% and subsequently minimizing the loss of orders can significantly reduce average unmet orders by 24.61%; when spokes were beyond 20, the ε-constraint model failed to achieve solutions within an acceptable time. While EAp and EAr demonstrated competence, EAr proved to be more competitive in computation time, hypervolume, spacing metric, and the number of non-dominated solutions on the Pareto fronts. Key parameters influencing the HSN solutions include drone and truck speeds, acceptable delivery times, and the processing and waiting time at hubs. Full article

During continuous spraying operations, the liquid in the pesticide tank gradually decreases, and the flight speed changes as the route is altered. To maintain stable flight, the rotor speed of a multi-rotor unmanned aerial spraying system (UASS) constantly adjusts. To explore the variation law of rotor speed in a multi-rotor UASS under objective operation attributes, based on indoor and outdoor experimental data, this paper constructs a mathematical model of the relationship between rotor speed and thrust. The model fitting parameter (R²) is equal to 0.9996. Through the neural network, the rotor speed prediction model is constructed with the real-time flight speed and the payload of the pesticide tank as the input. The overall correlation coefficient (R²) of the model training set is 0.728, and the correlation coefficients (R²) of the verification set and the test set are 0.719 and 0.726, respectively. Finally, the rotor speed is matched with the load of the whole UASS through thrust conversion. It is known that the single-axis load capacity under full-load state only reaches about 50% of its maximum load capacity, and the load increase is more than 75.83% compared with the no-load state. This study provides a theoretical and methodological reference for accurately predicting the performance characterization results of a power system during actual operation and investigating the dynamic feedback mechanism of a UASS during continuous operation. Full article

High-altitude platform (HAP) drones and satellites collaborate to form a network that provides edge computing services to terrestrial internet of things (IoT) devices, which is considered a promising method. In this network, IoT devices’ tasks can be split into multiple parts and processed by servers at non-terrestrial nodes in different locations, thereby reducing task processing delays. However, splitting tasks and allocating communication and computing resources are important challenges. In this paper, we investigate the task offloading and resource allocation problem in multi-HAP drones and multi-satellite collaborative networks. In particular, we formulate a task splitting and communication and computing resource optimization problem to minimize the total delay of all IoT devices’ tasks. To solve this problem, we first transform and decompose the original problem into two subproblems. We design a task splitting optimization algorithm based on deep reinforcement learning, which can achieve online task offloading decision-making. This algorithm structurally designs the actor network to ensure that output actions are always valid. Furthermore, we utilize convex optimization methods to optimize the resource allocation subproblem. The simulation results show that our algorithm can effectively converge and significantly reduce the total task processing delay when compared with other baseline algorithms. Full article

Detecting and recognizing distress types on road pavement is crucial for selecting the most appropriate methods to repair, maintain, prevent further damage, and ensure the smooth functioning of daily activities. However, this task presents challenges, such as dealing with crowded backgrounds, the presence of multiple distress types in images, and their small sizes. In this study, the YOLOv8 network, a cutting-edge single-stage model, is employed to recognize seven common pavement distress types, including transverse cracks, longitudinal cracks, alligator cracks, oblique cracks, potholes, repairs, and delamination, using a dataset comprising 5796 terrestrial and unmanned aerial images. The network’s optimized architecture and multiple convolutional layers facilitate the extraction of high-level semantic features, enhancing algorithm accuracy, speed, and robustness. By combining high and low semantic features, the network achieves improved accuracy in addressing challenges and distinguishing between different distress types. The implemented Convolutional Neural Network demonstrates a recognition precision of 77%, accuracy of 81%, mAP of 79%, f1-score of 74%, and recall of 75%, underscoring the model’s effectiveness in recognizing various pavement distress forms in both aerial and terrestrial images. These results highlight the model’s satisfactory performance and its potential for effectively recognizing and categorizing pavement distress for efficient infrastructure maintenance and management. Full article

UAV swarm passive positioning technology only requires the reception of electromagnetic signals to achieve the positioning and tracking of radiation sources. It avoids the active positioning strategy that requires active emission of signals and has the advantages of good concealment, long acting distance, and strong anti-interference ability, which has received more and more attention. In this paper, we propose a new UAV swarm formation flight method based on pure azimuth passive positioning. Specifically, we propose a two-circle positioning model, which describes the positional deviation of the receiving UAV using trigonometric functions relative to the target in polar coordinates. Furthermore, we design a two-step adjustment strategy that enables the receiving UAV to reach the target position efficiently. Based on the above design, we constructed an optimized UAV swarm formation scheme. In experiments with UAV numbers of 8 and 20, compared to the representative comparison strategy, the proposed UAV formation scheme reduces the total length of the UAV formation by 34.76% and 55.34%, respectively. It demonstrates the effectiveness of the proposed method in the application of assigning target positions to UAV swarms. Full article

Step-stare imaging systems are widely used in aerospace optical remote sensing. In order to achieve fast scanning of the target region, efficient coverage path planning (CPP) is a key challenge. However, traditional CPP methods are mostly designed for fixed cameras and disregard the irregular shape of the sensor’s projection caused by the step-stare rotational motion. To address this problem, this paper proposes an efficient, seamless CPP method with an adaptive hyperbolic grid. First, we convert the coverage problem in Euclidean space to a tiling problem in spherical space. A spherical approximate tiling method based on a zonal isosceles trapezoid is developed to construct a seamless hyperbolic grid. Then, we present a dual-caliper optimization algorithm to further compress the grid and improve the coverage efficiency. Finally, both boustrophedon and branch-and-bound approaches are utilized to generate rotation paths for different scanning scenarios. Experiments were conducted on a custom dataset consisting of 800 diverse geometric regions (including 2 geometry types and 40 samples for 10 groups). The proposed method demonstrates comparable performance of closed-form path length relative to that of a heuristic optimization method while significantly improving real-time capabilities by a minimum factor of 2464. Furthermore, in comparison to traditional rule-based methods, our approach has been shown to reduce the rotational path length by at least 27.29% and 16.71% in circle and convex polygon groups, respectively, indicating a significant improvement in planning efficiency. Full article

Insulators are key components to ensure the normal operation of power facilities in transmission corridors. Existing insulator identification methods mainly use image data and lack the acquisition of three-dimensional information. This paper proposes an efficient insulator extraction method based on UAV (unmanned aerial vehicle) LiDAR (light detection and ranging) point cloud, using five histogram features: horizontal density (HD), horizontal void (HV), horizontal width (HW), vertical width (VW) and vertical void (VV). Firstly, a voxel-based method is employed to roughly extract power lines and pylons from the original point cloud. Secondly, the VV histogram is used to categorize the pylons into suspension and tension types, and the HD histogram is used to locate the tower crossarm and further refine the roughly extracted powerlines. Then, for the suspension tower, insulators are segmented based on the HV histogram and HD difference histogram. For the tension tower, the HW histogram is used to recognize the jumper conductor (JC) and transmission conductor (TC) from the power line. The HW histogram and VW histogram are used to extract the tension insulator in the TC and suspension insulator in the JC, respectively. Finally, considering the problem of setting a suitable grid width when constructing the feature histogram, an adaptive method of multi-scale histograms is proposed to refine the extraction result. Two 220 kV long transmission lines are used for the validation, and the overall object-based accuracy for suspension and tension towers are 100% and 97.3%, respectively. Compared with the point feature-based method, the mean F1 score of the proposed method improved by 0.3, and the runtime for each tower is within 2 s. Full article

To address the issues of low model accuracy caused by complex ground environments and uneven target scales and high computational complexity in unmanned aerial vehicle (UAV) aerial infrared image target detection, this study proposes a lightweight UAV aerial infrared small target detection algorithm called PHSI-RTDETR. Initially, an improved backbone feature extraction network is designed using the lightweight RPConv-Block module proposed in this paper, which effectively captures small target features, significantly reducing the model complexity and computational burden while improving accuracy. Subsequently, the HiLo attention mechanism is combined with an intra-scale feature interaction module to form an AIFI-HiLo module, which is integrated into a hybrid encoder to enhance the focus of the model on dense targets, reducing the rates of missed and false detections. Moreover, the slimneck-SSFF architecture is introduced as the cross-scale feature fusion architecture of the model, utilizing GSConv and VoVGSCSP modules to enhance adaptability to infrared targets of various scales, producing more semantic information while reducing network computations. Finally, the original GIoU loss is replaced with the Inner-GIoU loss, which uses a scaling factor to control auxiliary bounding boxes to speed up convergence and improve detection accuracy for small targets. The experimental results show that, compared to RT-DETR, PHSI-RTDETR reduces model parameters by 30.55% and floating-point operations by 17.10%. Moreover, detection precision and speed are increased by 3.81% and 13.39%, respectively, and mAP50, impressively, reaches 82.58%, demonstrating the great potential of this model for drone infrared small target detection. Full article

The extraction of UAV building point cloud contour points is the basis for the expression of a three-dimensional lightweight building outline. Previous unmanned aerial vehicle (UAV) building point cloud contour extraction methods have mainly focused on the expression of the roof contour, but did not extract the wall contour. In view of this, an algorithm based on the geometric features of the neighborhood points of the region-growing clustering fusion surface is proposed to extract the boundary points of the UAV building point cloud. Firstly, the region growth plane is fused to obtain a more accurate segmentation plane. Then, the neighboring points are projected onto the neighborhood plane and a vector between the object point and neighborhood point is constructed. Finally, the azimuth of each vector is calculated, and the boundary points of each segmented plane are extracted according to the difference in adjacent azimuths. Experiment results show that the best boundary points can be extracted when the number of adjacent points is 24 and the difference in adjacent azimuths is 120. The proposed method is superior to other methods in the contour extraction of UAV buildings point clouds. Moreover, it can extract not only the building roof contour points, but also the wall contour points, including the window contour points. Full article

The paper studies a game theory model to ensure fairness and improve the communication efficiency in an unmanned aerial vehicle (UAV)-assisted cellular vehicle-to-everything (C-V2X) communication network using Markovian game theory in a federated learning (FL) environment. The UAV and each vehicle in a cluster utilized a strategy-based mechanism to maximize their model completion and transmission probability. We modeled a two-stage zero sum Markovian game with incomplete information to jointly study the utility maximization of the participating vehicles and the UAV in the FL environment. We modeled the aggregating process at the UAV as a mixed strategy game between the UAV and each vehicle. By employing Nash equilibrium, the UAV determined the probability of sufficient updates received from each vehicle. We analyzed and proposed decision-making strategies for several representative interactions involving gross data offloading and federated learning. When multiple vehicles enter a parameter transmission conflict, various strategy combinations are evaluated to decide which vehicles transmit their data to the UAV. The optimal payoff in a transmission window is derived using the Karush–Khun–Tucker (KKT) optimality conditions. We also studied the variation in optimal model parameter transmission probability, average packet delay, UAV transmit power, and the UAV–Vehicle optimal communication probabilities under different conditions. Full article

In many applications, such as atmospheric observation or disaster monitoring, cooperative control of a fleet of UAVs is crucial because it is effective in repeated tasks. In this work, we provide a workable and useful cooperative guiding algorithm for several fixed-wing UAVs to construct a path-following formation with communication delays. The two primary components of our concept are path-following (lateral guidance) and path formation (longitudinal guidance). The former is in charge of ensuring that, in the presence of wind disturbance, the lateral distance between the UAV and its targeted path converges using a well-known vector field technique. In the event of a communication delay, the latter ensures that several fixed-wing UAVs will create a predetermined formation shape. Furthermore, we provide a maximum delay bound that is dependent on the topology and a controller’s gain. Lastly, in order to confirm the viability and advantages of our suggested approach, we construct an effective platform for a hardware-in-the-loop (HIL) test. Full article

As the missions and environments of unmanned aerial vehicles (UAVs) become increasingly complex in both space and time, it is essential to investigate the dynamic task assignment problem of heterogeneous multi-UAVs aiming at ground targets in an uncertain environment. Considering that most of these existing tasking methods are limited to static allocation in a deterministic environment, this paper firstly constructs the fuzzy multiconstraint programming model for heterogeneous multi-UAV dynamic task assignment based on binary interval theory, taking into account the effects of uncertain factors like target location information, mission execution time, and the survival probability of UAVs. Then, the dynamic task allocation strategy is designed, consisting of two components: dynamic time slice setting and the four-dimensional information grey wolf optimization (4DI-GWO) algorithm. The dynamic time slices create the dynamic adjustment of solving frequency and effect, and the 4DI-GWO algorithm is improved by designing the four-dimensional information strategy that expands population diversity and enhances global search capability and other strategies. The numerical analysis shows that the proposed strategy can effectively solve the dynamic task assignment problem of heterogeneous multi-UAVs under an uncertain environment, and the optimization of fitness values demonstrates improvements of 5%~30% in comparison with other optimization algorithms. Full article

Pan–tilt–zoom cameras are commonly used for surveillance applications. Their automation could reduce the workload of human operators and increase the safety of airports by tracking anomalous objects such as drones. Reinforcement learning is an artificial intelligence method that outperforms humans on certain specific tasks. However, there exists a lack of data and benchmarks for pan–tilt–zoom control mechanisms in tracking airborne objects. Here, we show a simulated environment that contains a pan–tilt–zoom camera being used to train and evaluate a reinforcement learning agent. We found that the agent can learn to track the drone in our basic tracking scenario, outperforming a solved scenario benchmark value. The agent is also tested on more complex scenarios, where the drone is occluded behind obstacles. While the agent does not quantitatively outperform the optimal human model, it shows qualitative signs of learning to solve the complex, occluded non-linear trajectory scenario. Given further training, investigation, and different algorithms, we believe a reinforcement learning agent could be used to solve such scenarios consistently. Our results demonstrate how complex drone surveillance tracking scenarios may be solved and fully autonomized by reinforcement learning agents. We hope our environment becomes a starting point for more sophisticated autonomy in control of pan–tilt–zoom cameras tracking of drones and surveilling airspace for anomalous objects. For example, distributed, multi-agent systems of pan–tilt–zoom cameras combined with other sensors could lead towards fully autonomous surveillance, challenging experienced human operators. Full article

Aiming at the cooperative localization problem for the dynamic UAV swarm in an anchor-limited environment, an adaptive Wasserstein filter (AWF) with distance-constrained bare bones self-recovery particles (CBBP) is proposed. Firstly, to suppress the cumulative error from the inertial navigation system (INS), a position-prediction strategy based on transition particles is designed instead of using inertial measurements directly, which ensures that the generated prior particles can better cover the ground truth and provide the uncertainties of nonlinear estimation. Then, to effectively quantify the difference between the observed and the prior data, the Wasserstein measure based on slice segmentation is introduced to update the posterior weights of the particles, which makes the proposed algorithm robust against distance-measurement noise variance under the strongly nonlinear model. In addition, to solve the problem of particle impoverishment caused by traditional resampling, a diversity threshold based on Gini purity is designed, and a fast bare bones particle self-recovery algorithm with distance constraint is proposed to guide the outlier particles to the high-likelihood region, which effectively improves the accuracy and stability of the estimation. Finally, the simulation results show that the proposed algorithm is robust against cumulative error in an anchor-limited environment and achieves more competitive accuracy with fewer particles. Full article