Robot Path Planning Based on Improved Particle Swarm Optimization

Abstract

In order to improve the safety and efficiency of the robot in the process of moving, this paper proposes a new hybrid approach combining two meta-heuristic methods, we used particle swarm optimization (PSO)-based grey wolf optimization (GWO) to solve this problem. In this paper, a chaotic random method is used to generate the initial population. For the traditional particle swarm algorithm, it is easy to fall into the local optimal problem. Inspired by the grey wolf optimizer, a speed classification system is introduced into the traditional particle swarm optimization and the C-GWPSO hybrid algorithm is proposed. Then the robot motion environment model is constructed, the path length and the risk are used to construct the evaluation function. Finally, the proposed approach is implemented in MATLAB working platform, the results show that the improved new algorithm is easy for the robot to find a path with the least cost. This algorithm strengthens the global optimization ability, and has stronger optimization accuracy and ability in path planning.