Robot path planning using improved particle swarm optimization

Abstract

To get an optimal smooth path for a micro soccer robot, a novel path planning approach using improved particle swarm optimization is proposed with a path description by string of Ferguson splines. The path planning is then equivalent to optimization of parameters of particular cubic Ferguson splines. The improved Particle Swarm Optimization with Velocity Mutation(VMPSO)is introduced to optimize the path for its fast convergence and global search character. Experimental results prove the rationality and great practical value of the proposed algorithm, which can get convergence within 80 iterations, with a collision-avoiding smooth optimal path being planned fleetly.