Kinodynamic Motion Retargeting for Humanoid Locomotion via Multi-Contact Whole-Body Trajectory Optimization

2026-03-10

AI Summary

This work addresses the physical inconsistencies—such as foot sliding and ground penetration—that commonly arise in traditional motion retargeting methods relying solely on kinematic data, which degrade downstream imitation learning performance. The authors formulate humanoid motion retargeting as a multi-contact full-body trajectory optimization problem, jointly optimizing dynamic consistency and complex foot-ground contact patterns for the first time. By integrating motion capture and ground reaction force (GRF) measurements, the approach explicitly enforces rigid-body dynamics constraints and contact complementarity conditions, while automatically detecting heel-toe contact events. The resulting reference trajectories exhibit significantly improved dynamic feasibility and smoothness, accurately reproduce the original GRF profiles, and consequently accelerate convergence of downstream control policies while enhancing walking stability.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Computer Vision: Motion & Tracking
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

We present the KinoDynamic Motion Retargeting (KDMR) framework, a novel approach for humanoid locomotion that models the retargeting process as a multi-contact, whole-body trajectory optimization problem. Conventional kinematics-based retargeting methods rely solely on spatial motion capture (MoCap) data, inevitably introducing physically inconsistent artifacts, such as foot sliding and ground penetration, that severely degrade the performance of downstream imitation learning policies. To bridge this gap, KDMR extends beyond pure kinematics by explicitly enforcing rigid-body dynamics and contact complementarity constraints. Further, by integrating ground reaction force (GRF) measurements alongside MoCap data, our method automatically detects heel-toe contact events to accurately replicate complex human-like contact patterns. We evaluate KDMR against the state-of-the-art baseline, GMR, across three key dimensions: 1) the dynamic feasibility and smoothness of the retargeted motions, 2) the accuracy of GRF tracking compared to raw source data, and 3) the training efficiency and final performance of downstream control policies trained via the BeyondMimic framework. Experimental results demonstrate that KDMR significantly outperforms purely kinematic methods, yielding dynamically viable reference trajectories that accelerate policy convergence and enhance overall locomotion stability. Our end-to-end pipeline will be open-sourced upon publication.

Problem

• kinodynamic motion retargeting
• humanoid locomotion
• physical inconsistency
• foot sliding
• ground penetration

Innovation

• kinodynamic retargeting
• multi-contact optimization
• whole-body trajectory optimization
• ground reaction force
• humanoid locomotion