Search Results (54)

Traditional target-oriented task allocation and path planning methods often struggle to balance real-time responsiveness to dynamic task alterations with multi-UAV cooperative operations in complex urban environments under meteorological disturbances. To address these challenges, this paper proposes a dynamic path planning method for low-altitude Unmanned Aerial Vehicles (UAVs) tailored for urban inspection missions. Integrating an improved Discrete Particle Swarm Optimization (DPSO) algorithm with a decoupled Soft Actor–Critic (SAC) and B-spline smoothing framework, the proposed approach optimizes upper-level task allocation and lower-level trajectory planning within a 3D joint meteorological-obstacle feasible region. For task scheduling, an improved DPSO algorithm embedded with a spatial topology guidance mechanism dynamically coordinates task flows governed by Poisson processes. effectively addressing the spatial blindness and fragmented route assignments typical of conventional discrete optimization. Concurrently, local trajectory replanning executes receding-horizon spatial exploration via SAC deep reinforcement learning, followed by B-spline refinement to strictly enforce UAV kinematic limits, systematically bridging continuous-space exploration with low-level flight compliance to overcome the kinematic infeasibility common in pure learning-based models. Validated through extensive Monte Carlo comparative simulations (N = 50) and further verified by a high-fidelity AirSim dynamic physics engine, the results demonstrate that: (1) The improved DPSO constrains the average response latency for high-priority emergency tasks to within 40 s even under 50 concurrent dynamic tasks. (2) The lower-level replanning achieves an average execution time of 3.60 ± 0.18 s and a path success rate of 95.8 ± 1.2%, in numerical tests, while maintaining a 96.2% kinematic feasibility rate under realistic rigid-body inertia and aerodynamic drag. While the current 3.60 s latency presents a potential bottleneck for millisecond-level dynamic emergency reactions, the developed framework offers a highly effective and safe closed-loop dynamic scheduling solution that lays a rigorous computational foundation for low-altitude urban inspections. Full article

Unmanned aerial vehicles (UAVs) have become essential cyber-physical platforms for applications such as surveillance, infrastructure inspection, emergency response, and intelligent transportation. However, their tight coupling among sensing, communication, control, actuation, and swarm coordination also exposes them to sophisticated cyber-physical attacks that are difficult to detect using conventional intrusion detection systems. Existing machine learning, deep learning, graph-based, and federated intrusion detection approaches generally rely on statistical feature representations or temporal patterns, providing limited capability to model causal dependencies among interacting UAV subsystems and to generalize across heterogeneous operating environments. To address these limitations, this paper proposes Fed-CGIDS-UAV, a federated causal graph learning framework for cross-domain intrusion detection in cyber-physical UAV networks. The proposed framework models each telemetry window as a typed causal graph in which nodes represent navigation, sensing, communication, control, actuation, and swarm states, while directed edges capture stable operational dependencies. Intrusions are detected by identifying violations of these learned causal relationships, and the framework provides interpretable node-edge explanations to support root-cause analysis. Furthermore, federated learning enables collaborative model training across distributed UAV clients without sharing raw telemetry, thereby preserving data privacy while improving robustness under heterogeneous operating conditions. The proposed framework was implemented and experimentally evaluated in a controlled simulation environment covering four UAV operating domains and six representative attack classes. All experiments were repeated over five independent runs using different random seeds, and the reported results correspond to the measured average performance. The proposed framework was implemented using Python 3.12 (Python Software Foundation, Wilmington, DE, USA) and PyTorch 2.3 (Meta Platforms, Menlo Park, CA, USA). UAV flight data were generated using Microsoft AirSim 1.9.1 (Microsoft Corporation, Redmond, WA, USA), integrated with PX4 Autopilot v1.14 (Dronecode Foundation, San Francisco, CA, USA) and Gazebo Sim 11 (Open Source Robotics Foundation, Mountain View, CA, USA). Within this simulation-based evaluation, Fed-CGIDS-UAV achieved an accuracy of 0.968, an F1-score of 0.956, and an internal–external stability gap (IESG) of 0.028, outperforming conventional machine learning, deep learning, graph-based, and centralized causal baselines while maintaining competitive computational latency. Although these results demonstrate the effectiveness of the proposed framework under controlled simulation conditions, validation using real-flight UAV telemetry remains an important direction for future research. These results demonstrate that integrating causal graph learning with federated optimization provides an effective and interpretable solution for privacy-preserving intrusion detection in heterogeneous cyber-physical UAV environments. Full article

UAV path planning in complex urban environments faces significant challenges due to dense obstacles, narrow corridors, and stringent safety requirements. To address these issues, this paper proposes LLSOA, a modified Seagull Optimization Algorithm that integrates Latin Hypercube Sampling (LHS) for population initialization and Lévy Flight for global search. The key innovation lies in the problem-driven design: LHS ensures uniform coverage in dense urban maps, while Lévy Flight helps escape local optima. Compared with four state-of-the-art swarm intelligence algorithms (DBO, GWO, PIO, and PSO) across four urban scenarios, LLSOA achieves the best comprehensive fitness. Considering multiple constraints including path length, curvature, collision avoidance, and obstacle-avoidance logic, the trajectories generated by LLSOA show competitive overall performance, with no unsafe points recorded in the test scenarios and the best fitness values among the compared algorithms, albeit with a slight trade-off in path length. High-fidelity AirSim simulations with GPS/IMU noise further demonstrate that the planned trajectories remain within engineering acceptable limits. Compared with the noise-free baseline, the maximum trajectory deviation increases by 2.3% and the average deviation increases by 2.8% under high GPS/IMU noise. The main contributions are: (1) a problem-driven LLSOA that combines LHS and Lévy Flight, specifically tailored to dense urban environments; (2) theoretical analysis and simulation verification demonstrating its feasibility for multi-constraint path planning under the tested conditions; (3) high-fidelity (UE+AirSim) validation showing that the generated trajectories retain stability even under realistic sensor noise. Full article

Offline action prediction does not by itself guarantee reliable closed-loop flight for unmanned aerial vehicle (UAV) vision-language-action (VLA) models. We study a controlled AirSim Blocks waypoint task using 100 expert episodes and 3385 RGB-D, instruction, state, and action records. Checkpoints are selected only on val-seen data, after which val-unseen is evaluated once. A 132,840-parameter policy reaches $0.9278\pm 0.0019$ final-test action accuracy across three training seeds, yet raw VLA control fails in closed loop. We therefore embed its action proposals in progress-aware hybrid execution with explicit recovery and near-goal precision. The strongest checkpoint reaches 59/60 goals, but crossing three independently trained checkpoints with three target seeds yields a more conservative 147/180 successes (81.7%) with zero recorded collisions and marked checkpoint sensitivity. Substantial overrides and fallback-tagged steps further show that the reported closed-loop outcomes are properties of the hybrid system, not of the learned policy alone. These findings are restricted to the controlled AirSim Blocks benchmark and do not demonstrate real-UAV deployment, sim-to-real transfer, or field robustness. Full article

Testing advanced driver assistance systems (ADAS) under rare or safety-critical conditions is impractical at full scale: track campaigns are expensive, time-intensive, and cannot easily reproduce low-probability events. Scaled cyber–physical testbeds offer a more accessible path by coupling miniature vehicle platforms with virtual simulation environments, but the field has no unified review that covers co-simulation architectures, indoor localization, and ground truth strategies in a single treatment. This paper addresses that gap with a PRISMA 2020-compliant systematic review of 92 primary sources selected from 984 records identified across IEEE Xplore and Scopus. Three topic areas are examined: real-time co-simulation architectures built on AirSim, CARLA, Gazebo, and LGSVL, compared for ROS 2 integration, synchronisation model, and edge hardware suitability; three indoor localization methods, namely AprilTag fiducial tracking, Visual Simultaneous Localization and Mapping (VSLAM), and Ultra-Wideband (UWB) radio positioning, evaluated against shared accuracy, latency, infrastructure, and robustness criteria; and existing ground truth strategies for indoor localization benchmarking. A consistent finding across the corpus is that no controlled cross-method localization comparison exists for scaled testbeds. To address this, we introduce the Programmable Ground Truth Reference System (PGTRS), which renders spatial references on a programmable LED floor panel at a pixel pitch of approximately 3.9 mm, targeting sub-centimetre ground truth accuracy without dedicated motion-capture infrastructure. The concept is demonstrated within a 1:14 scale Digital Driving Twin (DDT) testbed built at the University of Applied Sciences Wildau at a hardware cost of approximately €6576. Design guidelines and open research challenges are discussed. Full article

Collaborative task allocation for multiple unmanned ground vehicles (UGVs) is a constrained combinatorial optimization problem in which symmetric vehicle resources must be coordinated with asymmetric task requirements. In delivery and inspection scenarios, homogeneous vehicles operate under identical rules, whereas task points differ in spatial distribution, demand, service time, and time window requirements. These asymmetries make compact, temporally feasible, and workload-balanced routing difficult. SACWDO-PSO is developed as a discrete particle swarm optimization framework that integrates Clarke–Wright savings initialization, adaptive parameter control, and simulated annealing local search. The savings strategy improves initial swarm quality, adaptive control adjusts exploration and exploitation during the search, and simulated annealing refines local route structures. The method is evaluated on Solomon VRPTW benchmark data under a soft time window penalty objective and insimulation scenarios developed using Unreal Engine 4.27 integrated with Microsoft AirSim 1.8.1. SACWDO-PSO obtains lower objective values and fewer time window violations than the compared swarm-intelligence baselines on most benchmark instances, while Wilcoxon signed-rank tests indicate statistically significant improvements over PSO, DPSO, and GA. Full article

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

We propose KoSim-GL, a large-scale vision-based geo-localization dataset for drone positioning in GPS-denied environments. Geo-localization estimates a drone’s location by matching drone-view imagery against a geo-referenced satellite image database, offering a reliable alternative to GPS under conditions such as signal jamming, spoofing, or degradation in dense urban canyons. Although this task is challenging due to the domain gap between drone-view and satellite-view imagery, existing benchmarks are built predominantly around urban environments in the United States and China, leaving South Korea largely unrepresented, despite its distinctive landscape in which mountainous terrain coexists with dense high-rise districts and low-rise residential neighborhoods. To address this gap, we introduce KoSim-GL, constructed from drone-view images captured via an AirSim- and ROS-based flight simulator and satellite images collected through the Google Maps Tile API, covering the urban area of Daejeon, South Korea. Its key feature is a multi-view configuration that simultaneously captures five views, one nadir and four oblique, at each flight position across altitudes from 100 m to 600 m, enabling robust localization even in feature-sparse environments where nadir-only matching is prone to fail. In total, KoSim-GL comprises 2,450,315 drone images and 1704 satellite images. We further provide systematic comparisons against five existing benchmarks and baseline evaluations of ten representative geo-localization models under single- and multi-view settings. Experimental results show that the multi-view configuration substantially improves localization performance; for example, FSRA improves Recall@1 from 44.08% (single-view) to 65.37% (multi-view), a gain of 21.29 percentage points. The dataset is publicly available. Full article

Real-time cooperative control of quadrotor swarms in cluttered environments requires balancing formation maintenance, obstacle avoidance, inter-UAV safety, and per-step computational cost. This paper proposes a multilayer perceptron (MLP) surrogate for high-level objective-weight selection in a modified multi-objective pigeon-inspired optimization (modified MPIO) distributed controller. The proposed MLP surrogate learns the state-to-weight mapping of the online search and directly predicts the two-dimensional objective-weight vector, while the original flocking, gap-based obstacle-avoidance, and command generation rules are retained unchanged. The surrogate is trained from teacher-generated weight labels using randomized scenes, DAgger-based state aggregation, and risk-weighted supervision. On a fixed closed-loop benchmark, the proposed controller increases the true collision free rate from 48.00% to 86.89% and the safe success rate from 38.67% to 74.22% relative to modified MPIO, while reducing the mean per-step decision latency for the whole swarm from 8494.70 ms to 0.92 ms. The improvement is most pronounced in safety-related and runtime metrics, while the formation-related gain is comparatively modest. Ablation results show that the final benchmark performance is not explained by DAgger or risk weighting alone, and that the medium-sized surrogate provides the best safety-latency tradeoff among the tested network architectures. A qualitative AirSim case study further indicates that the same high-level surrogate controller can be executed in a higher-fidelity asynchronous multirotor simulator. Full article

The integration of artificial intelligence (AI), particularly deep reinforcement learning (DRL), promises to enhance the autonomy and adaptability of drones in complex environments. This research explores the implementation of a cooperative counter-drone swarm solution using multi-agent DRL, such as Multi-Agent Proximal Policy Optimization (MAPPO), and the aim is to enhance public security. In this paper, an open-source simulation platform, AirSim, is utilized to train and test the proposed method. A centralized critic architecture within a multi-agent reinforcement learning (MARL) framework using Proximal Policy Optimization (PPO) is implemented. A PettingZoo–Ray RLlib integration provides scalable multi-agent training using shared policies to encourage collaboration. A centralized critic is trained by observing the joint state and action space of all drone agents, while drone agents execute decentralized policies during deployment. We observed that increasing the number of cooperative drones improves performance, achieving a 66.7% increase in episode reward, a 42% improvement in team success rate, and a 65% reduction in geofence violations compared to the two-drone configuration. The proposed framework provides a scalable foundation for real-world cooperative counter-unmanned aerial system (C-UAS) operations using deep reinforcement learning. Full article

Aerial docking is a crucial capability for extending the autonomy and functionality of uncrewed aerial vehicles (UAVs), yet practical and robust docking mechanisms remain underdeveloped. Mid-air recovery also enables flexible multi-UAV cooperation across diverse mission scenarios. To address the core challenge of achieving reliable and precise airborne rendezvous, this paper proposes a control-driven approach supported by a complementary mechanical design. A Nonlinear Model Predictive Control (NMPC) framework is developed for the follower UAV, incorporating a velocity-penalty strategy to ensure the smooth and accurate tracking of the leader UAV based on GNSS guidance during the rendezvous phase. In the terminal docking stage, alignment accuracy is further enhanced through vision-based pose estimation using an ArUco marker array mounted on the leader UAV. Building on these algorithmic components, an improved active V-shaped docking mechanism is introduced to compensate for the follower UAV’s pitch angle during engagement, providing robustness against residual alignment errors. The feasibility and performance of the proposed system are validated through static ground docking experiments of the mechanical module and AirSim dynamic simulations evaluating the autonomous docking controller. Full article

A single drone collects data, but a fleet builds a complete picture, and this is the primary objective of this study. To address this goal, a swarm-based drone system has been designed in which multiple drones follow one another to collect data from diverse perspectives. Such a strategy demonstrates strong potential for use in critical fields such as search and rescue operations. This study introduces the first unified framework that integrates autonomous formation control, real-time object detection, and multi-source data fusion within a single operational UAV-swarm system. A high-fidelity simulation environment was built using Unreal Engine with the AirSim plugin, featuring a lightweight QR code tracking algorithm for inter-drone coordination. The drones were employed to detect vehicles from various angles in real time. Two types of experiments were conducted: the first used a pretrained YOLO model, and the second used a custom-trained YOLOv8-nano model, which outperformed the baseline by achieving an average detection confidence of 90%. Finally, the results from multiple drones were fused using various techniques including temporal, probabilistic, and geometric fusion methods to produce more reliable and robust detection results. Full article

Self-supervised monocular depth estimation from oblique UAV videos is crucial for enabling autonomous navigation and large-scale mapping. However, existing self-supervised monocular depth estimation methods face key challenges in UAV oblique video scenarios: depth discontinuity from geometric distortion under complex viewing angles, and spatial ambiguity in weakly textured regions. These challenges highlight the need for models that combine global reasoning with geometric awareness. Accordingly, we propose RMTDepth, a self-supervised monocular depth estimation framework for UAV imagery. RMTDepth integrates an enhanced Retentive Vision Transformer (RMT) backbone, introducing explicit spatial priors via a Manhattan distance-driven spatial decay matrix for efficient long-range geometric modeling, and embeds a neural window fully-connected CRF (NeW CRFs) module in the decoder to refine depth edges by optimizing pairwise relationships within local windows. To mitigate noise in COLMAP-generated depth for real-world UAV datasets, we constructed a high-fidelity UE4/AirSim simulation environment, which generated a large-scale precise depth dataset (UAV SIM Dataset) to validate robustness. Comprehensive experiments against seven state-of-the-art methods across UAVID Germany, UAVID China, and UAV SIM datasets demonstrate that our model achieves SOTA performance in most scenarios. Full article

In vision-guided autonomous robots, object detectors play a crucial role in perceiving the environment for path planning and decision-making. However, adaptive adversarial patch attacks undermine the resilience of detector-based systems. Strengthening object detectors against such adaptive attacks enhances the robustness of navigation systems. Existing defenses against patch attacks are primarily designed for stationary scenes and struggle against adaptive patch attacks that vary in scale, position, and orientation in dynamic environments. In this paper, we introduce Ad_YOLO+, an efficient and effective plugin that extends Ad_YOLO to defend against white-box patch-based image attacks. Built on YOLOv5x with an additional patch detection layer, Ad_YOLO+ is trained on a specially crafted adversarial dataset (COCO-Visdrone-2019). Unlike conventional methods that rely on redundant image preprocessing, our approach directly detects adversarial patches and the overlaid objects. Experiments on the adversarial training dataset demonstrate that Ad_YOLO+ improves both provable robustness and clean accuracy. Ad_YOLO+ achieves $85.4\%$ top-1 clean accuracy on the COCO dataset and $74.63\%$ top-1 robust provable accuracy against pixel square patches anywhere on the image for the COCO-VisDrone-2019 dataset. Moreover, under adaptive attacks in AirSim simulations, Ad_YOLO+ reduces the attack success rate, ensuring tracking resilience in both dynamic and static settings. Additionally, it generalizes well to other patch detection weight configurations. Full article

This study presents a high-fidelity digital twin (DT) framework designed to evaluate and improve vertiport operations for Advanced Air Mobility (AAM). By integrating Unreal Engine, AirSim, and Cesium, the framework enables real-time simulation of Unmanned Aerial Vehicles (UAVs), including unmanned electric vertical take-off and landing (eVTOL) operations under nominal and disrupted conditions, such as adverse weather and engine failures. The DT supports interactive visualisation and risk-free analysis of decision-making protocols, vertiport layouts, and UAV handling strategies across multi-scenarios. To validate system realism, mixed-reality experiments involving physical UAVs, acting as surrogates for eVTOL platforms, demonstrate consistency between simulations and real-world flight behaviours. These UAV-based tests confirm the applicability of the DT environment to AAM. Intelligent algorithms detect Final Approach and Take-Off (FATO) areas and adjust flight paths for seamless take-off and landing. Live environmental data are incorporated for dynamic risk assessment and operational adjustment. A structured capacity evaluation method is proposed, modelling constraints including turnaround time, infrastructure limits, charging requirements, and emergency delays. Mitigation strategies, such as ultra-fast charging and reconfiguring the layout, are introduced to restore throughput. This DT provides a scalable, drone-integrated, and data-driven foundation for vertiport optimisation and regulatory planning, supporting safe and resilient integration into the AAM ecosystem. Full article