Application of improved PSO in mobile robotic path planning

Abstract

An improved PSO algorithm which is applied to mobile robot path planning is proposed. In this paper, we use the grid method to decompose two-dimensional space of the robot path to build the path space model. Using this method is simple and easy to achieve computer modeling, storing, processing, updating and analyzing. It can make the pairs of particles in the algorithm exchange information by leading crossover operator into the basic particle swarm algorithm in order to make it have the new ability to fly to the search space. Pulling the mutation operator in basic particle swarm algorithm to enhance the PSO algorithm's capacity of getting out of local optimal. Simulation results show that the improved algorithm is simple and effective, more advantage than the basic PSO algorithm.