Three-dimensional collaborative path planning for multiple UCAVs based on improved artificial ecosystem optimizer and reinforcement learning

Abstract

This study proposes a multi-strategy evolutionary artificial ecosystem optimizer based on reinforcement learning (MEAEO-RL) to tackle the collaborative path-planning problem of multiple unmanned combat aerial vehicles (UCAVs) in complex environments with multiple constraints. The objective is to generate optimal candidate paths for each UCAV, ensuring they reach the destination simultaneously while considering time variables and obstacle avoidance. To overcome the limitations of the standard artificial ecosystem optimizer (AEO), such as local optimality and slow convergence, a learning framework inspired by brain-like perception is constructed. This framework enhances swarm agents with greater intelligence by fusing swarm intelligence and human cognitive mechanisms. Meanwhile, a multi-strategy database is implemented within the evolutionary learning framework to replace the single-update method of the AEO during the consumption phase. To reduce the computational complexity of the algorithm, agents in the consumption stage utilize experience accumulation from reinforcement learning to select an effective update strategy for obtaining the latest consumer location. Path-planning simulation experiments are conducted in a series of complex three-dimensional environments, demonstrating the algorithm’s robustness, improved convergence accuracy, and ability to plan collaborative paths for multiple UCAVs while satisfying various constraints.