qRRT: Quality-Biased Incremental RRT for Optimal Motion Planning in Non-Holonomic Systems

TL;DR

This paper introduces qRRT, a novel sampling-based motion planning algorithm that combines incremental RRT with reinforcement learning to learn workspace costs, enabling asymptotically optimal solutions for non-holonomic systems without known cost functions.

Contribution

It proposes a new framework integrating RRT and reinforcement learning to learn workspace costs and bias the search for optimal motion planning in non-holonomic systems.

Findings

Demonstrates asymptotic optimality of the proposed method.

Shows improved planning efficiency over traditional RRT.

Validates effectiveness through multiple experiments.

Abstract

This paper presents a sampling-based method for optimal motion planning in non-holonomic systems in the absence of known cost functions. It uses the principle of learning through experience to deduce the cost-to-go of regions within the workspace. This cost information is used to bias an incremental graph-based search algorithm that produces solution trajectories. Iterative improvement of cost information and search biasing produces solutions that are proven to be asymptotically optimal. The proposed framework builds on incremental Rapidly-exploring Random Trees (RRT) for random sampling-based search and Reinforcement Learning (RL) to learn workspace costs. A series of experiments were performed to evaluate and demonstrate the performance of the proposed method.