RoboDuet: Learning a Cooperative Policy for Whole-body Legged Loco-Manipulation

TL;DR

RoboDuet introduces a dual-policy framework for quadruped robots that enables effective whole-body loco-manipulation, achieving significant success rate improvements and zero-shot transfer capabilities in complex tasks.

Contribution

This work presents a novel two-policy approach for simultaneous locomotion and manipulation in quadruped robots, supporting zero-shot transfer and large-range pose tracking.

Findings

23% success rate improvement over baseline

Supports zero-shot transfer across similar robots

Enables large-range 6D pose tracking for manipulation

Abstract

Fully leveraging the loco-manipulation capabilities of a quadruped robot equipped with a robotic arm is non-trivial, as it requires controlling all degrees of freedom (DoFs) of the quadruped robot to achieve effective whole-body coordination. In this letter, we propose a novel framework RoboDuet, which employs two collaborative policies to realize locomotion and manipulation simultaneously, achieving whole-body control through mutual interactions. Beyond enabling large-range 6D pose tracking for manipulation, we find that the two-policy framework supports zero-shot transfer across quadruped robots with similar morphology and physical dimensions in the real world. Our experiments demonstrate that RoboDuet achieves a 23% improvement in success rate over the baseline in challenging loco-manipulation tasks employing whole-body control. To support further research, we provide open-source code and additional videos on our website: locomanip-duet.github.io.