Sample-Based Planning with Volumes in Configuration Space

Abstract

A simple sample-based planning method is presented which approximates connected regions of free space with volumes in Configuration space instead of points. The algorithm produces very sparse trees compared to point-based planning approaches, yet it maintains probabilistic completeness guarantees. The planner is shown to improve performance on a variety of planning problems, by focusing sampling on more challenging regions of a planning problem, including collision boundary areas such as narrow passages.