aiqbench analysis
Human2Humanoid addresses the critical challenge of transferring human motion to humanoid robots without requiring paired datasets, leveraging a CycleGAN-based architecture with physics-aware constraints to ensure physical plausibility. By normalizing end-effector trajectories and accounting for skeletal topology differences, the framework successfully retargets movements to the Unitree G1 robot with high fidelity and improved controllability. This approach significantly advances imitation learning and teleoperation by bridging the domain gap between human and robotic embodiments under unpaired data conditions.
Human2Humanoid: Physics-Aware Cross-Morphology Motion Retargeting for Humanoid Robots
arXiv:2606.03476v1 Announce Type: new Abstract: Retargeting human motion to humanoid robots is critical for teleoperation, imitation learning and human-robot interaction. However, it remains challenging because of substantial morphological discrepancies between humans and robots, including differences in skeletal topology, limb proportions and degrees of freedom, as well as the scarcity of paired motion data. This paper presents Human2Humanoid, an unsupervised motion retargeting framework that transfers human motions to humanoid robot behaviors with high fidelity. To bridge the domain gap under unpaired data, we adopt a CycleGAN-based architecture equipped with a skeleton-aware graph convolutional network to capture topology-dependent motion features. To address cross-domain scale mismatches, we introduce a morphology-invariant end-effector consistency loss that aligns normalized end-effector trajectories to preserve motion semantics across embodiments. To improve physical plausibility and reduce contact artifacts, we impose explicit physics-aware feasibility constraints to encourage reproduction of the contact patterns in the source motion. Experimental results show that the proposed method successfully retargets human motion to the Unitree G1 humanoid robot without paired data, and outperforms existing methods in both downstream controllability and physical feasibility.
Abstract:Retargeting human motion to humanoid robots is critical for teleoperation, imitation learning and human-robot interaction. However, it remains challenging because of substantial morphological discrepancies between humans and robots, including differences in skeletal topology, limb proportions and degrees of freedom, as well as the scarcity of paired motion data. This paper presents Human2Humanoid, an unsupervised motion retargeting framework that transfers human motions to humanoid robot behaviors with high fidelity. To bridge the domain gap under unpaired data, we adopt a CycleGAN-based architecture equipped with a skeleton-aware graph convolutional network to capture topology-dependent motion features. To address cross-domain scale mismatches, we introduce a morphology-invariant end-effector consistency loss that aligns normalized end-effector trajectories to preserve motion semantics across embodiments. To improve physical plausibility and reduce contact artifacts, we impose explicit physics-aware feasibility constraints to encourage reproduction of the contact patterns in the source motion. Experimental results show that the proposed method successfully retargets human motion to the Unitree G1 humanoid robot without paired data, and outperforms existing methods in both downstream controllability and physical feasibility.
Robotics (cs.RO)
arXiv:2606.03476 [cs.RO]
(or arXiv:2606.03476v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.03476 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.
Full text under the publisher's open licence · 265 words
Related coverage
BeyondRetarget: Learning Executable Humanoid Motions Directly from Monocular Video
arXiv · Sep 25, 2026
Proprioceptive-visual correspondence enables self-other distinction in humanoid robots
arXiv · Jun 12, 2026
Morphology-Aware Human Motion Retargeting for Wheeled-Humanoid Loco-Manipulation
arXiv · Sep 11, 2026
GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors
arXiv · Jun 4, 2026