Learning Speed-Adaptive Walking Agent Using Imitation Learning with Physics-Informed Simulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chiu, Yi-Hung, Lee, Ung Hee, Song, Changseob, Hu, Manaen, Kang, Inseung
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916508948496384
author Chiu, Yi-Hung
Lee, Ung Hee
Song, Changseob
Hu, Manaen
Kang, Inseung
author_facet Chiu, Yi-Hung
Lee, Ung Hee
Song, Changseob
Hu, Manaen
Kang, Inseung
contents Virtual models of human gait, or digital twins, offer a promising solution for studying mobility without the need for labor-intensive data collection. However, challenges such as the sim-to-real gap and limited adaptability to diverse walking conditions persist. To address these, we developed and validated a framework to create a skeletal humanoid agent capable of adapting to varying walking speeds while maintaining biomechanically realistic motions. The framework combines a synthetic data generator, which produces biomechanically plausible gait kinematics from open-source biomechanics data, and a training system that uses adversarial imitation learning to train the agent's walking policy. We conducted comprehensive analyses comparing the agent's kinematics, synthetic data, and the original biomechanics dataset. The agent achieved a root mean square error of 5.24 +- 0.09 degrees at varying speeds compared to ground-truth kinematics data, demonstrating its adaptability. This work represents a significant step toward developing a digital twin of human locomotion, with potential applications in biomechanics research, exoskeleton design, and rehabilitation.
format Preprint
id arxiv_https___arxiv_org_abs_2412_03949
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Speed-Adaptive Walking Agent Using Imitation Learning with Physics-Informed Simulation
Chiu, Yi-Hung
Lee, Ung Hee
Song, Changseob
Hu, Manaen
Kang, Inseung
Robotics
Machine Learning
Virtual models of human gait, or digital twins, offer a promising solution for studying mobility without the need for labor-intensive data collection. However, challenges such as the sim-to-real gap and limited adaptability to diverse walking conditions persist. To address these, we developed and validated a framework to create a skeletal humanoid agent capable of adapting to varying walking speeds while maintaining biomechanically realistic motions. The framework combines a synthetic data generator, which produces biomechanically plausible gait kinematics from open-source biomechanics data, and a training system that uses adversarial imitation learning to train the agent's walking policy. We conducted comprehensive analyses comparing the agent's kinematics, synthetic data, and the original biomechanics dataset. The agent achieved a root mean square error of 5.24 +- 0.09 degrees at varying speeds compared to ground-truth kinematics data, demonstrating its adaptability. This work represents a significant step toward developing a digital twin of human locomotion, with potential applications in biomechanics research, exoskeleton design, and rehabilitation.
title Learning Speed-Adaptive Walking Agent Using Imitation Learning with Physics-Informed Simulation
topic Robotics
Machine Learning
url https://arxiv.org/abs/2412.03949