Particle swarm optimization with orientation angle-based grouping for practical unmanned surface vehicle path planning

This paper presents a practical and efficient path planning algorithm based on the architecture of conventional particle swarm optimization (PSO) for a self-developed unmanned surface vehicle to complete tasks of water quality detection and sampling. A preprocessing orientation angle-based grouping strategy appropriately enhances computing efficiency and adaptability to the distribution feature of planned points. Meanwhile, mutation is introduced in the initialization phase to improve the global search ability of the PSO. Multiparticle competition is added to maintain population diversity during late iterations. After stringing all the subdomain paths together, a simplified 4-opt is employed for further improvement and convergence acceleration. Computational simulations show that the proposed algorithm is superior to three of our previous algorithms and comparable with several existing algorithms from other reports. The path-planning algorithm is also integrated into the vehicle's navigation, guidance, and control system with satisfactory feasibility.

Automated summary

This paper introduces a practical and efficient path planning algorithm based on PSO for a self-developed unmanned surface vehicle. Through a series of optimization measures, the algorithm enhances computing efficiency and global search ability, showing superior performance in computational simulations and successful integration into the vehicle system.