Flow Matching Imitation Learning for Multi-Support Manipulation

TL;DR

This paper introduces a novel imitation learning approach using Flow Matching for multi-contact humanoid robot manipulation, enabling complex tasks like pushing and drawer closing with contact support and shared autonomy.

Contribution

It combines Flow Matching with a multi-contact whole-body controller, demonstrating improved imitation learning for contact-rich tasks on humanoid robots.

Findings

Flow Matching outperforms Diffusion and behavior cloning in robotics tasks.

The approach enables a humanoid robot to learn and perform complex contact-rich tasks.

Shared autonomy mode assists teleoperation with automatic contact placement.

Abstract

Humanoid robots could benefit from using their upper bodies for support contacts, enhancing their workspace, stability, and ability to perform contact-rich and pushing tasks. In this paper, we propose a unified approach that combines an optimization-based multi-contact whole-body controller with Flow Matching, a recently introduced method capable of generating multi-modal trajectory distributions for imitation learning. In simulation, we show that Flow Matching is more appropriate for robotics than Diffusion and traditional behavior cloning. On a real full-size humanoid robot (Talos), we demonstrate that our approach can learn a whole-body non-prehensile box-pushing task and that the robot can close dishwasher drawers by adding contacts with its free hand when needed for balance. We also introduce a shared autonomy mode for assisted teleoperation, providing automatic contact placement for tasks not covered in the demonstrations. Full experimental videos are available at: https://hucebot.github.io/flow_multisupport_website/