CLOT: Closed-Loop Global Motion Tracking for Whole-Body Humanoid Teleoperation

Tengjie Zhu1,2,*, Guanyu Cai1,*, Zhaohui Yang1,*, Guanzhu Ren1, Haohui Xie1, Junsong Wu1, Zirui Wang2, Jingbo Wang2, Xiaokang Yang1, Yao Mu1,2,†, Yichao Yan1,†

1Shanghai Jiao Tong University     2Shanghai AI Laboratory
*Authors with equal contribution, †Corresponding author
arXiv Video Code(Coming soon) Data(Coming soon)

Abstract


Long-horizon whole-body humanoid teleoperation remains challenging due to accumulated global pose drift, particularly on full-sized humanoids. Although recent learning-based tracking methods enable agile and coordinated motions, they typically operate in the robot's local frame and neglect global pose feedback, leading to drift and instability during extended execution. In this work, we present CLOT, a real-time wholebody humanoid teleoperation system that achieves closed-loop global motion tracking via high-frequency localization feedback. CLOT synchronizes operator and robot poses in a closed loop, enabling drift-free human-to-humanoid mimicry over long time horizons. However, directly imposing global tracking rewards in reinforcement learning, often results in aggressive and brittle corrections. To address this, we propose a data-driven randomization strategy that decouples observation trajectories from reward evaluation, enabling smooth and stable global corrections. We further regularize the policy with an adversarial motion prior to suppress unnatural behaviors. To support CLOT, we collect 20 hours of carefully curated human motion data for training the humanoid teleoperation policy. We design a transformer-based policy and train it for over 1300 GPU hours. The policy is deployed on a full-sized humanoid with 31 DoF (excluding hands). Both simulation and real-world experiments verify high-dynamic motion, high-precision tracking, and strong robustness in sim-to-real humanoid teleoperation. Motion data, demos and code can be found in our website.

Video

Whole-Body Tracking Demos

Robustness Demos

Long-Horizon Loco-Manipulation Demos

Long-Term Stability Demos

BibTeX

@misc{zhu2026clotclosedloopglobalmotion,
      title={CLOT: Closed-Loop Global Motion Tracking for Whole-Body Humanoid Teleoperation}, 
      author={Tengjie Zhu and Guanyu Cai and Yang Zhaohui and Guanzhu Ren and Haohui Xie and ZiRui Wang and Junsong Wu and Jingbo Wang and Xiaokang Yang and Yao Mu and Yichao Yan and Yichao Yan},
      year={2026},
      eprint={2602.15060},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2602.15060}, 
}