Multi-UAV Distributed Collaborative Path Planning Based on NTVPPSO

Multi-UAV cooperative path planning (MUCPP) is one of the core issues of UAV swarms. When the number of UAVs is large or the mission is complex, problems such as poor scalability and slow convergence will be faced. This paper proposes a multi-UAV distributed hierarchical collaborative path planning method based on an improved particle swarm optimization algorithm. In order to speed up the convergence and ensure the global optimality of the results, a coefficient nonlinear time-varying parallel particle swarm optimization algorithm (NTVPPSO) is designed in this method. This algorithm splits the population into multiple sub-populations. Each particle in the sub-population is updated in parallel using non-linear time-varying coefficients, and information is exchanged between the sub-populations. In order to enhance scalability, a distributed framework with a two-layer structure is designed. First, each UAV plans its own path to determine the collaborative goal. Then the collaborative path planning of multiple UAVs is completed sequentially based on heuristic priorities. The simulation results show that the proposed method can converge quickly and the collaborative path tends to be optimal, and is a feasible distributed solution to the MUCPP problem.