Object-Centric Kinodynamic Planning for Nonprehensile Robot Rearrangement Manipulation

TL;DR

This paper introduces an object-centric planning framework for nonprehensile robot rearrangement tasks, improving efficiency and intuitiveness over traditional robot-centric methods, validated through extensive simulation and real-world experiments.

Contribution

It presents a unified object-centric planning approach for large-scale, physics-intensive rearrangement problems, addressing modeling inaccuracies and uncertainties.

Findings

More intuitive robot actions generated

Significant efficiency improvements over baselines

Validated on both simulation and physical robot

Abstract

Nonprehensile actions such as pushing are crucial for addressing multi-object rearrangement problems. Many traditional methods generate robot-centric actions, which differ from intuitive human strategies and are typically inefficient. To this end, we adopt an object-centric planning paradigm and propose a unified framework for addressing a range of large-scale, physics-intensive nonprehensile rearrangement problems challenged by modeling inaccuracies and real-world uncertainties. By assuming each object can actively move without being driven by robot interactions, our planner first computes desired object motions, which are then realized through robot actions generated online via a closed-loop pushing strategy. Through extensive experiments and in comparison with state-of-the-art baselines in both simulation and on a physical robot, we show that our object-centric planning framework can generate more intuitive and task-effective robot actions with significantly improved efficiency. In addition, we propose a benchmarking protocol to standardize and facilitate future research in nonprehensile rearrangement.