Stein Variational Probabilistic Roadmaps

TL;DR

This paper introduces Stein Variational Probabilistic Roadmaps (SV-PRM), a novel sampling-based motion planning method that uses particle-based Variational Inference to efficiently generate probabilistically-safe planning graphs in uncertain environments.

Contribution

The paper presents SV-PRM, a new approach that leverages Stein Variational Inference for improved sampling efficiency and robustness in probabilistic motion planning under uncertainty.

Findings

SV-PRM outperforms traditional sampling methods in efficiency.

The approach effectively handles partial observability and environment uncertainty.

Demonstrated success on real-world robotics problems.

Abstract

Efficient and reliable generation of global path plans are necessary for safe execution and deployment of autonomous systems. In order to generate planning graphs which adequately resolve the topology of a given environment, many sampling-based motion planners resort to coarse, heuristically-driven strategies which often fail to generalize to new and varied surroundings. Further, many of these approaches are not designed to contend with partial-observability. We posit that such uncertainty in environment geometry can, in fact, help drive the sampling process in generating feasible, and probabilistically-safe planning graphs. We propose a method for Probabilistic Roadmaps which relies on particle-based Variational Inference to efficiently cover the posterior distribution over feasible regions in configuration space. Our approach, Stein Variational Probabilistic Roadmap (SV-PRM), results in sample-efficient generation of planning-graphs and large improvements over traditional sampling approaches. We demonstrate the approach on a variety of challenging planning problems, including real-world probabilistic occupancy maps and high-dof manipulation problems common in robotics.