A Whole-Body Motion Imitation Framework from Human Data for Full-Size Humanoid Robot

2025-08-01

AI Summary

To address the challenge of simultaneously achieving high motion fidelity and dynamic balance in whole-body imitation for humanoid robots, this paper proposes a unified control framework integrating contact-aware whole-body motion retargeting with nonlinear center-of-mass (CoM) model predictive control (MPC). Methodologically, contact-aware reference trajectories are first generated from human motion data; subsequently, nonlinear CoM MPC jointly optimizes CoM dynamics and support moment trajectories in real time, while a whole-body controller computes closed-loop joint torques. The framework is validated in both simulation and on a full-scale physical humanoid platform. It successfully reproduces complex anthropomorphic behaviors—including walking, turning, and squatting—demonstrating superior motion fidelity, real-time balance robustness, and disturbance rejection compared to baseline approaches. This work establishes a scalable, unified control paradigm for high-dynamic human-to-robot motion transfer.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Motion and Path Planning
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Motion imitation is a pivotal and effective approach for humanoid robots to achieve a more diverse range of complex and expressive movements, making their performances more human-like. However, the significant differences in kinematics and dynamics between humanoid robots and humans present a major challenge in accurately imitating motion while maintaining balance. In this paper, we propose a novel whole-body motion imitation framework for a full-size humanoid robot. The proposed method employs contact-aware whole-body motion retargeting to mimic human motion and provide initial values for reference trajectories, and the non-linear centroidal model predictive controller ensures the motion accuracy while maintaining balance and overcoming external disturbances in real time. The assistance of the whole-body controller allows for more precise torque control. Experiments have been conducted to imitate a variety of human motions both in simulation and in a real-world humanoid robot. These experiments demonstrate the capability of performing with accuracy and adaptability, which validates the effectiveness of our approach.

Problem

• Imitating human motion on humanoid robots accurately
• Maintaining balance during motion imitation
• Overcoming kinematic and dynamic differences between humans and robots

Innovation

• Contact-aware whole-body motion retargeting for human imitation
• Non-linear centroidal model predictive controller for balance
• Whole-body controller for precise torque control