Learning to guide random tree planners in high dimensional spaces

In this paper we present the projection and bias heuristic (PBH), a motion planning algorithm that makes use of low-dimensional projections to improve sampling-based planning algorithms. In contrast to other state-of-the-art methods, we do not assume that projections are either random or given by an expert user. Rather, our goal is to learn projections such that planning on them improves the efficiency and the quality of solutions. We present both, a method to learn effective projections and a sampling algorithm that makes use of them. We show that our approach can be easily integrated into popular sampling-based planners. Extensive experiments performed in simulated environments demonstrate that our approach produces paths that are in general shorter than those obtained with state-of-the-art algorithms. Moreover, it generally requires less computation time.