In this paper a novel method is presented for robot motion planning with respect to two objectives, the shortest and smoothest path criteria. A Particle Swarm Optimization (PSO) algorithm is employed for global path planning, while the Probabilistic Roadmap method (PRM) is used for obstacle avoidance (local planning). The two objective functions are incorporated in the PSO equations in which the path smoothness is measured by the difference of the angles of the hypothetical lines connecting the robot's two successive positions to its goal. The PSO and PRM are combined by adding good PSO particles as auxiliary nodes to the random nodes generated by the PRM. The proposed algorithm is compared in path length and runtime with the mere PRM method searched by Dijkstra's algorithm, and the results showed that the generated paths are shorter and smoother and are calculated in less time.
展开▼
