Beyond Motion Imitation: Is Human Motion Data Alone Sufficient to Explain Gait Control and Biomechanics?

2026-03-12

AI Summary

This work addresses the challenge that purely kinematics-driven imitation learning often fails to ensure biomechanically plausible gait dynamics, particularly exhibiting physically inconsistent joint torque predictions. To overcome this limitation, the authors integrate foot–ground interaction information—specifically ground reaction forces and center of pressure—as dynamic constraints into a reinforcement learning–based imitation framework, embedding them directly into the reward function. Experimental results demonstrate that this approach significantly improves the agreement between joint torques generated in forward simulation and those computed via inverse dynamics, thereby enhancing both kinematic and dynamic physical realism in gait synthesis. The findings underscore the critical role of incorporating external dynamic cues for accurate biomechanical modeling.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

With the growing interest in motion imitation learning (IL) for human biomechanics and wearable robotics, this study investigates how additional foot-ground interaction measures, used as reward terms, affect human gait kinematics and kinetics estimation within a reinforcement learning-based IL framework. Results indicate that accurate reproduction of forward kinematics alone does not ensure biomechanically plausible joint kinetics. Adding foot-ground contacts and contact forces to the IL reward terms enables the prediction of joint moments in forward walking simulation, which are significantly closer to those computed by inverse dynamics. This finding highlights a fundamental limitation of motion-only IL approaches, which may prioritize kinematics matching over physical consistency. Incorporating kinetic constraints, particularly ground reaction force and center of pressure information, significantly enhances the realism of internal and external kinetics. These findings suggest that, when imitation learning is applied to human-related research domains such as biomechanics and wearable robot co-design, kinetics-based reward shaping is necessary to achieve physically consistent gait representations.

Problem

• motion imitation
• gait biomechanics
• kinetics estimation
• ground reaction force
• reinforcement learning

Innovation

• imitation learning
• reinforcement learning
• gait biomechanics
• ground reaction force
• kinetic consistency