Relevant Region Exploration On General Cost-maps For Sampling-Based Motion Planning
This work addresses a specific bottleneck in motion planning for robotics by improving sampling efficiency, but it appears incremental as it builds on existing Informed Sampling methods.
The paper tackles the problem of inefficient exploration in asymptotically optimal sampling-based motion planners by proposing an algorithm that samples from a 'Relevant Region', a subset of the Informed Set, to accelerate convergence. Benchmarking tests in uniform and general cost-space settings demonstrate its efficacy, though no concrete numbers are provided.
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.