Multiple query probabilistic roadmap planning using single query planning primitives

Publication Type:

Conference Paper

Source:

Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003), Ieee, Volume 01, Number October, p.656–661 (2003)

ISBN:

0-7803-7860-1

Abstract:

We propose a combination of techniques that solve multiple queries for motion planning problems with single query planners. Our implementation uses a probabilistic roadmap method (PRM) with bidirectional rapidly exploring random trees (BI-RRT) as the local planner. With small modifications to the standard algorithms, we obtain a multiple query planner, which is significantly faster and more reliable than its component parts. Our method provides a smooth spectrum between the PRM and BI-RRT techniques and obtains the advantages of both. We observed that the performance differences are most notable in planning instances with several rigid nonconvex robots in a scene with narrow passages. Our work is in the spirit of non-uniform sampling and refinement techniques used in earlier work on PRM.