Kinodynamic Rapidly-exploring Random Forest for Rearrangement-Based Nonprehensile Manipulation

TL;DR

This paper introduces a forest-based kinodynamic planning framework for rearrangement-based nonprehensile manipulation, enabling efficient, robust, and adaptive manipulation in complex, uncertain environments by combining local and global search strategies.

Contribution

It presents a novel kinodynamic planning approach that integrates local rearrangement and global action optimization using a forest-based search, improving efficiency and robustness.

Findings

Significantly improves planning efficiency.

Enhances manipulation effectiveness.

Robust against physical uncertainties.

Abstract

Rearrangement-based nonprehensile manipulation still remains as a challenging problem due to the high-dimensional problem space and the complex physical uncertainties it entails. We formulate this class of problems as a coupled problem of local rearrangement and global action optimization by incorporating free-space transit motions between constrained rearranging actions. We propose a forest-based kinodynamic planning framework to concurrently search in multiple problem regions, so as to enable global exploration of the most task-relevant subspaces, while facilitating effective switches between local rearranging actions. By interleaving dynamic horizon planning and action execution, our framework can adaptively handle real-world uncertainties. With extensive experiments, we show that our framework significantly improves the planning efficiency and manipulation effectiveness while being robust against various uncertainties.