Partial Motion Imitation for Learning Cart Pushing with Legged Manipulators

TL;DR

This paper introduces a partial imitation learning method enabling legged robots to perform stable cart pushing by transferring learned locomotion styles and imitating lower-body motions, validated in simulation environments.

Contribution

The work presents a novel partial imitation learning approach that transfers locomotion skills to cart manipulation, improving stability and accuracy over baselines.

Findings

The learned policy successfully pushes a cart along diverse trajectories.

The method transfers effectively from IsaacLab to MuJoCo environments.

It outperforms several baseline approaches in stability and precision.

Abstract

Loco-manipulation is a key capability for legged robots to perform practical mobile manipulation tasks, such as transporting and pushing objects, in real-world environments. However, learning robust loco-manipulation skills remains challenging due to the difficulty of maintaining stable locomotion while simultaneously performing precise manipulation behaviors. This work proposes a partial imitation learning approach that transfers the locomotion style learned from a locomotion task to cart loco-manipulation. A robust locomotion policy is first trained with extensive domain and terrain randomization, and a loco-manipulation policy is then learned by imitating only lower-body motions using a partial adversarial motion prior. We conduct experiments demonstrating that the learned policy successfully pushes a cart along diverse trajectories in IsaacLab and transfers effectively to MuJoCo. We also compare our method to several baselines and show that the proposed approach achieves more stable and accurate loco-manipulation behaviors.