UUV 3D Path Planning Based on PSO-ACO Fusion Algorithm

In order to solve the problems of difficult convergence and local optimal solution of ant colony optimization (ACO) algorithm, and low convergence accuracy of particle swarm optimization (PSO) algorithm, a particle swarm optimization ant colony optimization (PSO-ACO) fusion algorithm is proposed to deal with the three-dimensional (3D) path planning problem of unmanned underwater vehicle (UUV). In this algorithm: based on the idea of spatial stratification, a 3D grid model is established to build underwater environment model; PSO algorithm is used to pre search the path and quickly obtain the solution, which is used as the initial pheromone increment of ACO algorithm; the pheromone global updating method of ACO algorithm is improved: an adjusting factor is added to the pheromone global update equation to accelerate the convergence speed of ACO algorithm; the state transition equation of ACO algorithm is also improved, so that the algorithm has a greater probability to select the point with the largest weighted product of pheromone and heuristic information as the next path point. Experimental results show that the fusion algorithm effectively improves the global search ability and shortens the search time.

I. Introduction

China has a long coastline and is rich in marine resources, but the complex seabed environment has great restrictions on human underwater operations. Therefore, unmanned underwater vehicle has become an important tool for mining marine resources. At present, the path planning of unmanned underwater vehicle is still an important topic. The effect of many algorithms in path planning is not satisfactory, and it is difficult to get good results.