Efficient Distributed 4D Spatiotemporal Path Planning for Multi-UAV Systems in Dynamic Environments

• Published in: IEEE transactions on vehicular technology pp. 1 - 16
• Main Authors: Zhao, Lingzhu, Zhang, Xianchao, Fu, Xiaowei, Wang, Yinhao
• Format: Journal Article
• Language: English
• Published: IEEE 2025
• Subjects: 4D spatiotemporal coordination; Autonomous aerial vehicles; Collaboration; Collision avoidance; distributed constraint optimization problem; Lunar Motion Optimizer; multi-UAV; Optimization; Path planning; Real-time systems; Scalability; Spatiotemporal phenomena; Training; Vehicle dynamics
• ISSN: 0018-9545; 1939-9359
• DOI: 10.1109/TVT.2025.3604613

Path planning, a core technology in modern UAV systems, critically influences flight efficiency and mission success. For multi-UAV systems, it requires addressing flight efficiency, obstacle avoidance, and coordination in dynamic environments, presenting significant challenges. In this paper, we propose a distributed collaborative path planning method. Firstly, we develop a hybrid approach combining global optimization with online local replanning to meet spatiotemporal coordination and obstacle avoidance needs. Secondly, we formulate a distributed constraint optimization problem (DCOP) model to enable effective multi-UAV collaboration. Finally, we introduce an innovative Lunar Motion Optimizer (LMO) to compute UAV flight paths, enhanced by an adaptive population size reduction mechanism for improved efficiency. Simulation results demonstrate that the proposed distributed collaborative path planning method effectively generates safe four-dimensional (4D) flight paths for each UAV. LMO outperforms state-of-the-art algorithms in solution quality, stability, and computational efficiency. Benchmark tests further confirm the high scalability of LMO.