Human motions convert to wheeled humanoid robot walking and manipulating
Morphology-Aware Human Motion Retargeting for Wheeled-Humanoid Loco-Manipulation
Robotics
Summary
Robots that move and use their arms like humans usually have legs, but some have wheels instead. Moving the way a person walks and uses their arms onto a wheeled robot is hard because wheels can’t copy legs. The authors created a complete process that changes human motion data so a wheeled humanoid robot can do walking and arm tasks physically, not just as a cartoon. This helps the robot understand how to move wheels and bend its body like a person would walk and manipulate things.
What this means in practice
- •For robotics developers: Create wheeled humanoid robots that can replicate human walking and manipulation motions using real motion capture data.
- •For industrial automation teams: Program wheeled humanoid robots for complex tasks requiring both movement and manipulation in environments where legged robots are less practical.
Authors
Chenbo Xia, Chao Ye
Abstract
Human-to-humanoid retargeting has largely been studied on legged platforms, while comparatively few wheeled-humanoid systems support coupled locomotion and manipulation from general human motion. Building on GMR's configurable general-motion retargeting and BeyondMimic's physically simulated R1 Pro learning framework, we present a reproducible pipeline that converts multi-dataset SMPLX motion into executable loco-manipulation behavior for the Galaxea R1 Pro wheeled humanoid. The robot has a planar three-wheel base, a serial torso, and two arms but no leg joints, so human lower-body motion must be redistributed across base motion and torso posture without sacrificing manipulation-relevant arm geometry. Our pipeline combines canonical body-shape preprocessing, planar-base normalization, morphology-aware differential inverse kinematics, shoulder-rooted hierarchical arm retargeting, and continuous torso substitution for bending and squatting. A reference-twist-driven planning layer then decodes planar base motion into continuous three-wheel steering and rolling commands subject to hysteresis, kinematic continuity, acceleration, and actuator-rate limits. Finally, a 21-dimensional BaseDecode policy is trained in Isaac Lab with directional joint-limit scaling, focused upper-body tracking, and a staged wheel-contact reward. The resulting system provides a complete bridge from human motion data to physically trackable wheeled-humanoid loco-manipulation rather than a visualization-only retargeter; quantitative policy comparisons remain scheduled for a later revision.