SoftMimic: Learning Compliant Whole-body Control from Examples

TL;DR

SoftMimic is a novel framework that enables humanoid robots to learn compliant, safe, and adaptable whole-body control policies from example motions, improving interaction safety and robustness.

Contribution

It introduces a reinforcement learning approach that emphasizes compliant responses over rigid tracking, using augmented datasets for safer, more adaptable robot control.

Findings

Robots respond safely to external forces during experiments.

SoftMimic generalizes from a single motion clip to varied tasks.

Demonstrates effective real-world interaction and disturbance absorption.

Abstract

We introduce SoftMimic, a framework for learning compliant whole-body control policies for humanoid robots from example motions. Imitating human motions with reinforcement learning allows humanoids to quickly learn new skills, but existing methods incentivize stiff control that aggressively corrects deviations from a reference motion, leading to brittle and unsafe behavior when the robot encounters unexpected contacts. In contrast, SoftMimic enables robots to respond compliantly to external forces while maintaining balance and posture. Our approach leverages an inverse kinematics solver to generate an augmented dataset of feasible compliant motions, which we use to train a reinforcement learning policy. By rewarding the policy for matching compliant responses rather than rigidly tracking the reference motion, SoftMimic learns to absorb disturbances and generalize to varied tasks from a single motion clip. We validate our method through simulations and real-world experiments, demonstrating safe and effective interaction with the environment.