I-CTRL: Imitation to Control Humanoid Robots Through Constrained Reinforcement Learning

TL;DR

This paper introduces I-CTRL, a reinforcement learning framework that improves humanoid robot motion imitation by ensuring physical feasibility and visual fidelity through constrained refinement and an automatic priority scheduler.

Contribution

It presents a novel bounded residual reinforcement learning approach with a unified policy and motion dataset management for diverse humanoid robots.

Findings

Effective motion imitation across five robots

Enhanced physical realism in robot motions

Unified RL policy for diverse motions

Abstract

Humanoid robots have the potential to mimic human motions with high visual fidelity, yet translating these motions into practical, physical execution remains a significant challenge. Existing techniques in the graphics community often prioritize visual fidelity over physics-based feasibility, posing a significant challenge for deploying bipedal systems in practical applications. This paper addresses these issues through bounded residual reinforcement learning to produce physics-based high-quality motion imitation onto legged humanoid robots that enhance motion resemblance while successfully following the reference human trajectory. Our framework, Imitation to Control Humanoid Robots Through Bounded Residual Reinforcement Learning (I-CTRL), reformulates motion imitation as a constrained refinement over non-physics-based retargeted motions. I-CTRL excels in motion imitation with simple and unique rewards that generalize across five robots. Moreover, our framework introduces an automatic priority scheduler to manage large-scale motion datasets when efficiently training a unified RL policy across diverse motions. The proposed approach signifies a crucial step forward in advancing the control of bipedal robots, emphasizing the importance of aligning visual and physical realism for successful motion imitation.