RTR+C*CS: An effective geometric planner for car-like robots

Abstract

The need for intelligent autonomous vehicles is increasing in industrial and everyday life as well. Path planning among obstacles is one of the challenging problems to be solved to achieve autonomous navigation. In this paper we present a global geometric path planning method for car-like robots, which proved to be effective especially in cluttered environments, containing narrow passages. Navigation in such scenarios usually requires non-obvious manoeuvring with many reversals, which is challenging even for a human driver. We also present a comparative analysis of our method with possible alternatives from the literature to illustrate its effectiveness regarding computation time and path quality.