Probabilistic roadmaps and hierarchical genetic algorithms for optimal motion planning

Abstract

In this paper we present a motion planning algorithm that combines between Probabilistic Roadmaps (PRM) and Hierarchical Genetic Algorithms (HGA) in order to generate optimal motions for a non holonomic mobile robot. PRM are used to generate a set of paths that will be optimized by HGA, the obtained trajectory leads a non holonomic mobile robot from an initial to a final configuration while maintaining feasibility and no-collision with obstacles.