Distributed Cooperative Guidance Law for UAV Swarm Based on Reinforcement Learning

We propose a distributed cooperative guidance law for UAV swarms based on the multi-agent deep deterministic policy gradient (MADDPG) algorithm. Specifically, we propose a cooperative guidance law based on sliding surface and use an improved MADDPG algorithm to intelligently design the parameters of the proposed guidance law. The improved MADDPG algorithm includes a communication module based on multi-head attention network and a mixer network. Simulation experiments show that the cooperative guidance law can effectively achieve the cooperative guidance and collaboration of UAV swarms.