Relevant Region Exploration On General Cost-maps For Sampling-Based Motion Planning

TL;DR

This paper introduces a novel sampling strategy called Relevant Region sampling for sampling-based motion planning, which improves convergence speed by focusing exploration on more promising regions using cost-to-come information, reducing reliance on heuristics.

Contribution

It proposes a new sampling method that targets the Relevant Region, a subset of the Informed Set, enhancing exploration efficiency in motion planning.

Findings

Relevant Region sampling outperforms traditional Informed Sampling in benchmarks.

The method reduces dependence on heuristics for cost estimation.

Experiments show faster convergence in general cost-space settings.

Abstract

Asymptotically optimal sampling-based planners require an intelligent exploration strategy to accelerate convergence. After an initial solution is found, a necessary condition for improvement is to generate new samples in the so-called "Informed Set". However, Informed Sampling can be ineffective in focusing search if the chosen heuristic fails to provide a good estimate of the solution cost. This work proposes an algorithm to sample the "Relevant Region" instead, which is a subset of the Informed Set. The Relevant Region utilizes cost-to-come information from the planner's tree structure, reduces dependence on the heuristic, and further focuses the search. Benchmarking tests in uniform and general cost-space settings demonstrate the efficacy of Relevant Region sampling.