Physics-informed Ground Reaction Dynamics from Human Motion Capture

2025-07-02

AI Summary

This work addresses the challenge of estimating ground reaction forces (GRFs) and full-body dynamics directly from motion capture data alone—without force plates. To this end, we propose a physics-informed deep learning framework that explicitly encodes kinematic-dynamic physical constraints by embedding Euler integration and PD control into the network architecture. High-fidelity simulation is leveraged to generate ground-truth GRFs for supervision, enabling end-to-end training without real force measurements. Evaluated on the GroundLink dataset, our method significantly outperforms purely data-driven baselines in both GRF prediction accuracy and root-joint trajectory reconstruction quality. To our knowledge, this is the first generalizable dynamics modeling approach that eliminates the need for force plates while seamlessly integrating differentiable physics priors with learning-based inference. The implementation is publicly available.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Body dynamics are crucial information for the analysis of human motions in important research fields, ranging from biomechanics, sports science to computer vision and graphics. Modern approaches collect the body dynamics, external reactive force specifically, via force plates, synchronizing with human motion capture data, and learn to estimate the dynamics from a black-box deep learning model. Being specialized devices, force plates can only be installed in laboratory setups, imposing a significant limitation on the learning of human dynamics. To this end, we propose a novel method for estimating human ground reaction dynamics directly from the more reliable motion capture data with physics laws and computational simulation as constrains. We introduce a highly accurate and robust method for computing ground reaction forces from motion capture data using Euler's integration scheme and PD algorithm. The physics-based reactive forces are used to inform the learning model about the physics-informed motion dynamics thus improving the estimation accuracy. The proposed approach was tested on the GroundLink dataset, outperforming the baseline model on: 1) the ground reaction force estimation accuracy compared to the force plates measurement; and 2) our simulated root trajectory precision. The implementation code is available at https://github.com/cuongle1206/Phys-GRD

Problem

• Estimating ground reaction forces without force plates
• Using motion capture data with physics constraints
• Improving accuracy in human dynamics simulation

Innovation

• Physics-based reactive forces from motion capture
• Euler's integration and PD algorithm
• Improved accuracy with physics-informed learning