State Supervised Steering Function for Sampling-based Kinodynamic Planning

TL;DR

This paper introduces S3F, a learning-based steering function for sampling-based kinodynamic planning, enabling faster and near-optimal solutions compared to traditional NLP methods, with proven probabilistic completeness.

Contribution

The paper presents S3F, a novel learned steering function that significantly accelerates kinodynamic motion planning while maintaining near-optimality and probabilistic completeness.

Findings

S3F produces solutions orders of magnitude faster than NLP solvers.

RRT* with S3F outperforms state-of-the-art methods in solution cost.

The approach is validated on three challenging robot domains.

Abstract

Sampling-based motion planners such as RRT* and BIT*, when applied to kinodynamic motion planning, rely on steering functions to generate time-optimal solutions connecting sampled states. Implementing exact steering functions requires either analytical solutions to the time-optimal control problem, or nonlinear programming (NLP) solvers to solve the boundary value problem given the system's kinodynamic equations. Unfortunately, analytical solutions are unavailable for many real-world domains, and NLP solvers are prohibitively computationally expensive, hence fast and optimal kinodynamic motion planning remains an open problem. We provide a solution to this problem by introducing State Supervised Steering Function (S3F), a novel approach to learn time-optimal steering functions. S3F is able to produce near-optimal solutions to the steering function orders of magnitude faster than its NLP counterpart. Experiments conducted on three challenging robot domains show that RRT* using S3F significantly outperforms state-of-the-art planning approaches on both solution cost and runtime. We further provide a proof of probabilistic completeness of RRT* modified to use S3F.