The Application of a Hybrid Algorithm to the Submersible Path-Planning

The premature problem is always being a hot topic in the swarm intelligence research field. PSO could easily fall into local optima because the particles could quickly get closer to the best particle. To this end, this paper proposes a new hybrid PSO named HGC-PSO to solve this problem. The mutation mainly considers the m+1 particles which have the better fitness values. Firstly, we add the Gauss mutation to the current global optimal. Secondly, we use the Cauchy mutation to change the rest of the m+1 particles. The purpose of this method is to increase the population diversity and avoid the PSO fall into local optima. Finally, HGC-PSO is applied to path planning problem in 3D space for robot in this paper. The experiment of results prove that the proposed algorithm has higher convergence speed and precision, besides a path without collision is found.