A New Method for Mobile Robot Path Planning based on Particle Swarm Optimization algorithm

Abstract

Particle swarm optimization (PSO) algorithm has been widely applied to the mobile robot path planning problems, but it still has some shortcomings such as high coding dimension and premature convergence. This paper proposes a new PSO algorithm combined with cubic spline functions. Firstly, several path nodes are set up in the environment, and then use the cubic spline functions to interpolate on the path of the starting point, path nodes and target point, thus obtain a full path which formed by connecting all interpolation points. The particle coding is just the coordinates of the path nodes, which significantly reduces the coding dimension of the particle. In order to further improve the efficiency of this algorithm, a new initialization strategy and penalty function based fitness are designed. The proposed method shows excellent performance in computational experiments in terms of solving quality, stability and speed.