multi-UAV System Research Articles

Aerial Surveillance Leveraging Delaunay Triangulation and Multiple-UAV Imaging Systems

In aerial surveillance systems, achieving optimal object detection precision is of paramount importance for effective monitoring and reconnaissance. This article presents a novel approach to enhance object detection accuracy through the integration of Delaunay triangulation with multi-unmanned aerial vehicle (UAV) systems. The methodology involves positioning multiple UAVs at pre-specified locations using the Delaunay triangulation algorithm with performance of O (n log n). This is compared with the conventional single UAV approach at a near distance. Our findings reveal that the collaborative efforts of multiple UAVs, guided by Delaunay triangulation, significantly improves object detection accuracy, especially when compared to a single UAV operating in close proximity. This research employs advanced image processing techniques to identify objects in the area under surveillance. Results indicate a substantial enhancement in the collective surveillance capabilities of the multi-UAV system, demonstrating its efficacy in unconstrained scenarios. This research not only contributes to the optimization of aerial surveillance operations but also underscores the potential of spatially informed UAV networks for applications demanding heightened object detection accuracy. The integration of Delaunay triangulation with multi-UAV systems emerges as a promising strategy for advancing the capabilities of aerial surveillance in scenarios ranging from security and emergency response to environmental monitoring.

Impact of Uncertain Flight Time on Heterogeneous UAVs’ Task Planning with Temporal Constraints

Heterogeneous multi-UAV systems offer distinct advantages through their complementary and coordinated use of their diverse capabilities. However, this complexity poses significant challenges in task planning, particularly in considering temporal constraints among tasks. As task dependencies evolve from simple linear chains to complex networked associations, uncertainties in flight times can have a substantial impact on the overall schedule. To address these challenges, this study introduces a rapid estimation method that recursively calculates task completion times, derives their probability distributions, and assesses the robustness of the plan. Furthermore, a neighborhood search algorithm guided by dynamic time windows is designed to effectively evaluate the consequences of task insertions, precisely to adjust high-risk tasks, and reduce blindness in enumerative neighborhood exploration. Simulation results demonstrate that the proposed approach effectively accounts for inherent randomness in the problem and exhibits strong adaptability to changes in the problem scale, flight time fluctuations, and variations in time window constraints.

Energy efficient deployment of aerial base stations for mobile users in multi-hop UAV networks

Unmanned aerial vehicles (UAVs) are popularly considered as aerial base stations in a Low-Altitude Platform (LAP) to provide wireless connections to ground users in disaster and digital divide situation. Most of previous studies have investigated energy efficient UAV deployment only for the stationary ground users. Contrarily, we propose an on-line deployment algorithm for ground mobile users (GMUs) who are partially observable in the multi-UAV system. In the framework of Partially Observable Markov Decision Process (POMDP) with large state and action space, we use the Monte Carlo Tree Search (MCTS) algorithm enhanced by the Double Progressive Widening (DPW) and Deep Neural Network (DNN)-based guidance. For online learning of the DNN, simulated samples are used with Proximal Policy Optimization (PPO) that prevents excessive training for a particular belief. From experiment in urban environment, the proposed scheme shows better learning performance than the MCTS with rollout policy and faster convergence than training with environment samples. In addition, it optimizes dual objectives proportionally in a trade-off between energy saving and throughput including prediction error on GMU location.

Multi-Objective Optimization of Dynamic Communication Network for Multi-UAVs System

Multi-Objective Optimization of Dynamic Communication Network for Multi-UAVs System

Design of Alerting System for Beyond Visual Line of Sight Operational Cargo Delivery UAV

The development of drones is now crucial to many industries, investors, and governments as they are more cost-effective and efficient in various industries, such as filmmaking, consumer, and tourism. They can also be used in various fields, such as agriculture, meteorology, construction, logistics, and conservation. Beyond Visual Line of Sight (BVLOS) technology enables drone operations to perform missions more accurately as it allows them to be operated in a wider angular range. BVLOS includes the use of advanced technologies and systems to monitor drones and ensure they comply with regulations. As such, BVLOS can be used to optimise marine cargo drone operations. In addition, the Ground Control System (GCS) is used by multi-UAV systems to remotely monitor drone performance. This enables advancements in navigation and autonomous technologies that can be utilised in the maritime sector. However, the operation of cargo delivery UAVs, especially those operated as multi-UAVs, requires a surveillance system supported by a qualified warning system. One of them is a warning system that will appear when the UAV approaches the boundary of the area of operation that has been set at the beginning. The warning system aims to improve safety and security because by warning UAVs approaching or entering restricted or sensitive areas, this system can prevent unauthorised access or accidents, ensuring the safety and security of the area and the UAV itself. In addition, it improves efficiency and reduces costs where the warning system can help UAVs avoid entering prohibited or unauthorised locations, improving efficiency, and reducing costs associated with re-routing or returning to home. For this reason, in this research, the design of a warning system for UAVs approaching the boundary of the operating area is performed and shown through simulation. In this research, a two-level alert system was designed and simulated that is triggered when the UAV approaches the boundary of the specified operation area to enable the operation supervisor to perform safety procedures in response to mitigate potential risks.

Markerless Motion Capture for Humans Through a Multi-UAV System

Markerless Motion Capture for Humans Through a Multi-UAV System

Distributed Finite Memory Online Learning Strategy for Multi-UAV Systems With Neural Networks

Distributed Finite Memory Online Learning Strategy for Multi-UAV Systems With Neural Networks

Optimal Sensing for Tracking Task by Heterogeneous Multi-UAV Systems

Optimal Sensing for Tracking Task by Heterogeneous Multi-UAV Systems

Stitch-Able Split Learning Assisted Multi-UAV Systems

Stitch-Able Split Learning Assisted Multi-UAV Systems

Resilient Human-in-the-Loop Formation-Tracking of Multi-UAV Systems Against Byzantine Attacks

Resilient Human-in-the-Loop Formation-Tracking of Multi-UAV Systems Against Byzantine Attacks

DPPM: Decentralized Exploration Planning for Multi-UAV Systems Using Lightweight Information Structure

DPPM: Decentralized Exploration Planning for Multi-UAV Systems Using Lightweight Information Structure

Resilient Consensus Control of Heterogeneous Multi-UAV Systems With Leader of Unknown Input Against Byzantine Attacks

Resilient Consensus Control of Heterogeneous Multi-UAV Systems With Leader of Unknown Input Against Byzantine Attacks

Cooperative task allocation with simultaneous arrival and resource constraint for multi-UAV using a genetic algorithm

In recent years, the application of multi-UAV cooperation systems has expanded across various domains. Enhancing the coordination performance of multi-UAV systems can be achieved through task allocation methods, typically relying on a hierarchical structure. This paper proposes a novel approach using a modified genetic algorithm (GA) to address the integrated task allocation and path planning problems for multi-UAV attacking multi-target. To create a more realistic mission scenario, multiple constraints, such as resource requirement and simultaneous target arrival, are considered. The modified GA incorporates tailored crossover and mutation operators that ensure compliance with the aforementioned constraints. Furthermore, an unlocking strategy is devised to prevent the occurrence of a chromosome deadlock condition, in which several UAVs become stuck in an infinite waiting state. Through simulation results, the modified GA is demonstrated to effectively delivers feasible solutions to the coupled task allocation and path planning problems, preserving the integrated nature of the optimization process. Monte Carlo simulations are conducted to highlight the superiority of the proposed method in comparison to conventional approaches.

Makespan-Minimizing Heterogeneous Task Allocation under Temporal Constraints

Task allocation is an essential element for determining the capability of multi-UAV systems to perform various tasks. This paper presents a procedure called a “rebalancing algorithm” for generating task-performing routes in heterogeneous multi-UAV systems. The algorithm adopts a greedy-based heuristic approach to find solutions efficiently in dynamically changing environments. A novel variable named “loitering” is introduced to satisfy temporal constraints, resulting in improved performance compared to heuristic algorithms: a sequential greedy algorithm, a genetic algorithm, and simulated annealing. The rebalancing algorithm is divided into two phases to minimize the makespan, i.e., the initial allocation and reallocation phases. Simulation results demonstrate the proposed algorithm’s effectiveness in highly constrained conditions and its suitability for heterogeneous systems. Additionally, the results show a reduction in calculation time and improved performance compared to the heuristic algorithms.

Imitation Learning of Complex Behaviors for Multiple Drones with Limited Vision

Navigating multiple drones autonomously in complex and unpredictable environments, such as forests, poses a significant challenge typically addressed by wireless communication for coordination. However, this approach falls short in situations with limited central control or blocked communications. Addressing this gap, our paper explores the learning of complex behaviors by multiple drones with limited vision. Drones in a swarm rely on onboard sensors, primarily forward-facing stereo cameras, for environmental perception and neighbor detection. They learn complex maneuvers through the imitation of a privileged expert system, which involves finding the optimal set of neural network parameters to enable the most effective mapping from sensory perception to control commands. The training process adopts the Dagger algorithm, employing the framework of centralized training with decentralized execution. Using this technique, drones rapidly learn complex behaviors, such as avoiding obstacles, coordinating movements, and navigating to specified targets, all in the absence of wireless communication. This paper details the construction of a distributed multi-UAV cooperative motion model under limited vision, emphasizing the autonomy of each drone in achieving coordinated flight and obstacle avoidance. Our methodological approach and experimental results validate the effectiveness of the proposed vision-based end-to-end controller, paving the way for more sophisticated applications of multi-UAV systems in intricate, real-world scenarios.

Hierarchical Decision-Making Framework for Multi-UAV Task Assignment via Enhanced Pigeon-Inspired Optimization

Effective task assignment decisions are paramount for ensuring reliable task execution in multi-UAV systems. However, in the development of feasible plans, challenges stemming from extensive and prolonged task requirements are encountered. This paper establishes a decision-making framework for multiple unmanned aerial vehicles (multi-UAV) based on the well-known pigeon-inspired optimization (PIO) algorithm. By addressing the problem from a hierarchical structural perspective, the initial stage involves minimizing the global objective of the flight distance cost after obtaining the entire task distribution and task requirements, utilizing the global optimization capability of the classical PIO algorithm to allocate feasible task spaces for each UAV. In the second stage, building upon the decisions made in the preceding stage, each UAV is abstracted as an agent maximizing its own task execution benefits. An improved version of the PIO algorithm modified with a sine-cosine search mechanism is proposed, enabling the acquisition of the optimal task execution sequence. Simulation experiments involving two different scales of UAVs validate the effectiveness of the proposed methodology. Moreover, dynamic events such as UAV damage and task changes are considered in the simulation to validate the efficacy of the two-stage framework.

Decentralized Coordination of a Multi-UAV System for Spatial Planar Shape Formations

Motivated by feedback from firefighters in Normandy, this work aims to provide a simple technique for a set of identical drones to collectively describe an arbitrary planar virtual shape in a 3D space in a decentralized manner. The original problem involved surrounding a toxic cloud to monitor its composition and short-term evolution. In the present work, the pattern is described using Fourier descriptors, a convenient mathematical formulation for that purpose. Starting from a reference point, which can be the center of a fire, Fourier descriptors allow for more precise description of a shape as the number of harmonics increases. This pattern needs to be evenly occupied by the fleet of drones under consideration. To optimize the overall view, the drones must be evenly distributed angularly along the shape. The proposed method enables virtual planar shape description, decentralized bearing angle assignment, drone movement from takeoff positions to locations along the shape, and collision avoidance. Furthermore, the method allows for the number of drones to change during the mission. The method has been tested both in simulation, through emulation, and in outdoor experiments with real drones. The obtained results demonstrate that the method is applicable in real-world contexts.

Meta-heuristic Algorithms in UAV Path Planning Optimization: A Systematic Review (2018–2022)

Unmanned Aerial Vehicles (UAVs), a subset of aerial robots, play crucial roles in various domains, such as disaster management, agriculture, and healthcare. Their application proves invaluable in situations where human intervention poses risks or involves high costs. However, traditional approaches to UAV path planning struggle in efficiently navigating complex and dynamic environments, often resulting in suboptimal routes and extended mission durations. This study seeks to investigate and improve the utilization of meta-heuristic algorithms for optimizing UAV path planning. Toward this aim, we carried out a systematic review of five major databases focusing on the period from 2018 to 2022. Following a rigorous two-stage screening process and a thorough quality appraisal, we selected 68 papers out of the initial 1500 to answer our research questions. Our findings reveal that hybrid algorithms are the dominant choice, surpassing evolutionary, physics-based, and swarm-based algorithms, indicating their superior performance and adaptability. Notably, time optimization takes precedence in mathematical models, reflecting the emphasis on CPU time efficiency. The prevalence of dynamic environmental types underscores the importance of real-time considerations in UAV path planning, with three-dimensional (3D) models receiving the most attention for accuracy in complex trajectories. Additionally, we highlight the trends and focuses of the UAV path planning optimization research community and several challenges in using meta-heuristic algorithms for the optimization of UAV path planning. Finally, our analysis further highlights a dual focus in UAV research, with a significant interest in optimizing single-UAV operations and a growing recognition of the challenges and potential synergies in multi-UAV systems, alongside a prevalent emphasis on single-target mission scenarios, but with a notable subset exploring the complexities of multi-target missions.

Robust Multiagent Reinforcement Learning for UAV Systems: Countering Byzantine Attacks

Multiple unmanned aerial vehicle (multi-UAV) systems have gained significant attention in applications, such as aerial surveillance and search and rescue missions. With the recent development of state-of-the-art multiagent reinforcement learning (MARL) algorithms, it is possible to train multi-UAV systems in collaborative and competitive environments. However, the inherent vulnerabilities of multiagent systems pose significant privacy and security risks when deploying general and conventional MARL algorithms. The presence of even a single Byzantine adversary within the system can severely degrade the learning performance of UAV agents. This work proposes a Byzantine-resilient MARL algorithm that leverages a combination of geometric median consensus and a robust state update model to mitigate, or even eliminate, the influence of Byzantine attacks. To validate its effectiveness and feasibility, the authors include a multi-UAV threat model, provide a guarantee of robustness, and investigate key attack parameters for multiple UAV navigation scenarios. Results from the experiments show that the average rewards during a Byzantine attack increased by up to 60% for the cooperative navigation scenario compared with conventional MARL techniques. The learning rewards generated by the baseline algorithms could not converge during training under these attacks, while the proposed method effectively converged to an optimal solution, proving its viability and correctness.

Quantum Multiagent Actor–Critic Networks for Cooperative Mobile Access in Multi-UAV Systems

This paper proposes a novel algorithm, named quantum multi-agent actor-critic networks (QMACN) for autonomously constructing a robust mobile access system employing multiple unmanned aerial vehicles (UAVs). In the context of facilitating collaboration among multiple unmanned aerial vehicles (UAVs), the application of multi-agent reinforcement learning (MARL) techniques is regarded as a promising approach. These methods enable UAVs to learn collectively, optimizing their actions within a shared environment, ultimately leading to more efficient cooperative behavior. Furthermore, the principles of a quantum computing (QC) are employed in our study to enhance the training process and inference capabilities of the UAVs involved. By leveraging the unique computational advantages of quantum computing, our approach aims to boost the overall effectiveness of the UAV system. However, employing a QC introduces scalability challenges due to the near intermediate-scale quantum (NISQ) limitation associated with qubit usage. The proposed algorithm addresses this issue by implementing a quantum centralized critic, effectively mitigating the constraints imposed by NISQ limitations. Additionally, the advantages of the QMACN with performance improvements in terms of training speed and wireless service quality are verified via various data-intensive evaluations. Furthermore, this paper validates that a noise injection scheme can be used for handling environmental uncertainties in order to realize robust mobile access.