Frontend
Imitation Learning from Human Motion Alone Does Not Guarantee Biomechanically Plausible Gait Kinetics
arXiv cs.RO0 views
arXiv:2603.12408v4 Announce Type: replace Abstract: Imitation learning (IL) via motion data is increasingly used in robotics and character animation, yet its ability to be applied to human biomechanics to estimate physiologically plausible joint moments without explicit kinetic information remains unclear. In this study, we examined whether motion imitation alone can estimate reasonable biological joint moments in human walking. We compared motion-only IL (MOIL) against a kinetics-aware IL (KAIL) framework, which incorporates additional ground reaction forces (GRFs) and center of pressure (CoP) in imitation rewards. A progressive kinetic reward shaping approach was used to examine the contribution of each kinetic term. Experiments were conducted using walking data from two non-disabled participants at three speeds (0.9, 1.2, and 1.5 m/s). While both MOIL and KAIL achieved comparable kinematic tracking accuracy, KAIL produced kinetics more closely aligned with biomechanical values across participants and walking speeds, reducing the root mean square errors (RMSEs) of vertical GRF and CoP by 40% and 48%, and of hip, knee, and ankle moments by 19%, 18%, and 35%, respectively, relative to MOIL. These findings highlight a fundamental limitation of MOIL approaches, as their failure to accurately estimate human-like gait kinetics may lead to erroneous interpretations of gait biomechanics and adversely affect downstream applications such as wearable robot design and the diagnosis of pathological gait.
Source:https://arxiv.org/abs/2603.12408PreviousReal-Time QP Solvers: A Concise Review and Practical Guide Towards Legged RobotsNextAERR-Nav: Adaptive Exploration-Recovery-Reminiscing Strategy for Zero-Shot Object Navigation
Related posts
Projection-Retraction MPPI: Exact Command-Space Constraint-Manifold Control for Manipulators
0arXiv cs.RO
CSS-only Dropdown with Native HTML
0dev.to CSS
The page that collapses: transforms on the real DOM instead of a screenshot
0dev.to CSS
Neon Snake: Building a Serverless CI/CD Pipeline on AWS with S3, Lambda, SSM & EC2
0dev.to AWS
Control S3 Costs by Tracking Requests and Data Transfer
0dev.to AWS
Expiring Untagged ECR Images Deletes the Digest an ECS Service Still Runs, and New Tasks Fail to Pull
0dev.to AWS