We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
基 基 于多智能体深度强化学习的无人机路径规划.
- Authors
司鹏搏; 吴兵; 杨睿哲; 李萌; 孙艳华
- Abstract
To solve the path planning problem of multi-unmanned aerial vehicle ( UAV) in complex environment, a multi-agent deep reinforcement learning UAV path planning framework was proposed. First, the path planning problem was modeled as a partially observable Markov decision process, and then, it was extended to multi-agent by using the proximal strategy optimization algorithm. Specifically, the multi-UAV barrier-free path planning was achieved by designing the UAV's state observation space, action space and reward function. Moreover, to adapt to the limited computing resource conditions of UAVs, a network pruning-based multi-agent proximal policy optimization (NP-MAPPO) algorithm was proposed, which improved the training efficiency. Simulations verify the effectiveness of the proposed multi-UAV path planning framework under various parameter configurations and the superiority of NP- MAPPO algorithm in training time.
- Subjects
PARTIALLY observable Markov decision processes; REINFORCEMENT learning; OPTIMIZATION algorithms; FUNCTION spaces; MARKOV processes; DRONE aircraft
- Publication
Journal of Beijing University of Technology, 2023, Vol 49, Issue 4, p449
- ISSN
0254-0037
- Publication type
Article