Collaborative path planning of multi-unmanned surface vehicles via multi-stage constrained multi-objective optimization

Abstract

A collaborative path planning algorithm based on a multi-stage constraint processing strategy is proposed for the task of unmanned surface vehicle (USV) cluster operation in complex water environments. The algorithm takes into account the distinct advantages of different USVs, the collaborative task time, and collision avoidance. Firstly, the objectives and constraints of the collaborative path planning problem for the USV cluster are modeled. Next, a path representation method with an adaptive number of waypoints is designed to improve the smoothness of the USV paths. Subsequently, a multi-stage constrained multi-objective optimization (MSCMO) algorithm is proposed to deal with the cooperative time and collision avoidance constraints of the USV cluster through a multi-stage strategy. Finally, eight collaborative operation scenarios for the USV cluster are designed to verify the performance of MSCMO. The simulation results demonstrate that MSCMO outperforms seven state-of-the-art constrained multi-objective algorithms, exhibiting a strong competitive advantage and superior overall performance. MSCMO enables USV clusters to perform collaborative tasks faster, safer, and smoother without violating any maneuvering constraints, while providing a variety of trade-off solutions for decision-makers. The source code is available at https://github.com/Shihong-Yin/MSCMO-MUCP.