Multi-UAV cooperative maneuver decision-making for pursuit-evasion using improved MADRL

Multi-UAV cooperative maneuver decision-making for pursuit-evasion using improved MADRL

Blog Article

Aiming at the problem of multi-UAV pursuit-evasion confrontation, a UAV cooperative maneuver method based on an improved multi-agent deep reinforcement learning (MADRL) is proposed.In this method, an improved CommNet network based on a communication Tennis Balls mechanism is introduced into a deep reinforcement learning algorithm to solve the multi-agent problem.A layer of gated recurrent unit (GRU) is added to the actor-network structure to remember historical environmental states.

Subsequently, another GRU is designed as a communication channel in the CommNet core network layer to refine communication information between UAVs.Finally, the simulation results of the algorithm in two sets of scenarios are given, and the Ball - Softballs results show that the method has good effectiveness and applicability.