Mobile Robot Path Planning Based on Improved Particle Swarm optimization

Abstract

According to the characteristics of particle swarm optimization(PSO), this paper studies on utilizing PSO algorithm to solve the path planning problem of mobile robots in polar coordinate system by polar angle. In order to solve the problem of particles falling into local extreme, which comes from the decline of the diversity of particle population in the later stage of searching, a mutation operation method was proposed. It enables particles to perform mutation operation while retaining most of the previous searching experience. So as to increase the diversity of population and make particles escape from local extreme. For the problem of the path points searched by PSO have many redundant path points, a de-redundant algorithm was proposed to remove them and make the path better. By environment modeling, improved algorithm and other methods are used for path planning. The comparison of simulation analysis shows that the improved PSO algorithm has more effective iterations, the planned path length is shorter, and the running time is not increased, which verifies the effectiveness of the method.