Reinforcement-Learning-Based Multi-UAV Cooperative Search for Moving Targets in 3D Scenarios

• Published in: Drones (Basel) 2024-08, Vol.8 (8), p.378
• Main Authors: Liu, Yifei, Li, Xiaoshuai, Wang, Jian, Wei, Feiyu, Yang, Junan
• Format: Article
• Language: English
• Subjects: Ablation; Adaptability; Algorithms; Altitude; Collaboration; Collision avoidance; Cooperation; cooperative target search; Decision making; Deep learning; Design; Drone aircraft; Efficiency; Flexibility; Heuristic; High altitude; Low altitude; Machine learning; Moving targets; multi-UAV; Multiagent systems; Neural networks; Optimization; Optimization algorithms; Path planning; Regional development; reinforcement learning; Reinforcement learning (Machine learning); Search algorithms; Search methods; Submarines; Target detection; Target masking; Uncertainty; Unmanned aerial vehicles
• ISSN: 2504-446X; 2504-446X
• DOI: 10.3390/drones8080378

Most existing multi-UAV collaborative search methods only consider scenarios of two-dimensional path planning or static target search. To be close to the practical scenario, this paper proposes a path planning method based on an action-mask-based multi-agent proximal policy optimization (AM-MAPPO) algorithm for multiple UAVs searching for moving targets in three-dimensional (3D) environments. In particular, a multi-UAV high–low altitude collaborative search architecture is introduced that not only takes into account the extensive detection range of high-altitude UAVs but also leverages the benefit of the superior detection quality of low-altitude UAVs. The optimization objective of the search task is to minimize the uncertainty of the search area while maximizing the number of captured moving targets. The path planning problem for moving target search in a 3D environment is formulated and addressed using the AM-MAPPO algorithm. The proposed method incorporates a state representation mechanism based on field-of-view encoding to handle dynamic changes in neural network input dimensions and develops a rule-based target capture mechanism and an action-mask-based collision avoidance mechanism to enhance the AM-MAPPO algorithm’s convergence speed. Experimental results demonstrate that the proposed algorithm significantly reduces regional uncertainty and increases the number of captured moving targets compared to other deep reinforcement learning methods. Ablation studies further indicate that the proposed action mask mechanism, target capture mechanism, and collision avoidance mechanism of the AM-MAPPO algorithm can improve the algorithm’s effectiveness, target capture capability, and UAVs’ safety, respectively.