analiza aiqbench
This research addresses a critical gap in humanoid robotics by adapting general human motion data for wheeled-humanoid systems, which lack leg joints but require coupled locomotion and manipulation. The authors propose a novel pipeline that redistributes lower-body movement into base steering and torso posture while preserving arm geometry for tasks like bending and squatting. By training a specific policy in Isaac Lab, the study demonstrates a functional bridge from human motion datasets to physically executable behaviors on platforms like the Galaxea R1 Pro.
Morphology-Aware Human Motion Retargeting for Wheeled-Humanoid Loco-Manipulation
arXiv:2609.11357v1 Announce Type: new 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.
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.
Robotics (cs.RO)
arXiv:2609.11357 [cs.RO]
(or arXiv:2609.11357v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.11357 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 287 cuvinte
Subiecte conexe
GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors
arXiv · 4 iun. 2026
Human2Humanoid: Physics-Aware Cross-Morphology Motion Retargeting for Humanoid Robots
arXiv · 3 iun. 2026
VICAR: Video Imitation with Contact-Aware Retargeting for Humanoid Interactive Skills
arXiv · 12 oct. 2026
DexWeave: Learning Dexterous Humanoid Loco-Manipulation from Human Demonstrations
arXiv · 29 sept. 2026