Multi-objective particle swarm optimization with multi-mode collaboration based on reinforcement learning for path planning of unmanned air vehicles

In order to solve the multiple unmanned aerial vehicles (UAVs) collaborative path planning problem under complex environments with multiple constraints, the multi-objective particle swarm optimization algorithm with multi-mode collaboration based on reinforcement learning (MCMOPSO-RL) is proposed in this paper to find optimal paths and handle constraints simultaneously. Reinforcement learning (RL) is applied to enable the proposed algorithm to choose the suitable position updated mode to achieve the high performance. Multi-mode collaboration strategy is developed to update the particle positions, where three modes are designed to balance the population diversity and the convergence speed, including the exploration, exploitation modes, and the hybrid update mode. Experimental results show that MCMOPSO-RL can solve the path planning problem for multiple UAVs more efficiently and robustly than other algorithms.