实际环境中多无人车协同路径规划模型研究

地面无人车的集群作战运用是当前人工智能与作战指挥交叉领域的热点研究问题。针对实际环境中多无人车无法满足动态威胁条件下的协同路径规划问题，采用全局路径规划算法A-star与局部路径规划算法RL相结合的思路，从感知到行为决策全交互协同的角度开展多无人车协同路径规划模型研究，设计协同作战态势威胁算法、状态与动作空间、奖励函数、势力范围函数；设计协同作战编队构型策略生成及打击路径动态优化子模型，完成基于自主学习的多无人车协同路径规划控制模型构建与求解。结果表明：该路径规划模型可有效应对复杂城市环境下多无人车协同路径规划任务需求。

Research on Cooperative Path Planning Model of Multiple Unmanned Vehicles in Real Environment

The cluster combat application of unmanned ground vehicles(UVS) is a hot research issue of the intersection of artificial intelligence and battle command. Aiming at the cooperative path planning multiple unmanned vehicles not meeting the dynamic threat condition requirement, by combining the global path planning algorithm A-STAR with the local path planning algorithm RL, from the perspective of perception to behavioral decision making, the cooperative path planning model of multiple unmanned vehicles is studied. The cooperative combat situation threat algorithm, state and action space, reward function and sphere of influence function are designed, the sub-models of formation configuration strategy generation and dynamic optimization of strike path are carried out, and the cooperative path planning control model of multiple unmanned vehicles based on autonomous learning is constructed and solved. An application example shows that the proposed path planning model can effectively cope with the requirements of multi-unmanned vehicle collaborative path planning task in complex urban environment,and has important theoretical research and practical application value.