Abstract
Humanoid whole-body teleoperation translates human motion into stable robot behavior in real time. Existing systems typically rely on online motion retargeting to bridge human--robot morphological differences, but this process adds latency and can produce physically infeasible targets. Meanwhile, diverse, noisy, and partial human-motion observations often fall outside the training distribution, potentially causing unstable robot behavior. We propose a retargeting-free policy that maps raw human motion directly to robot joint commands in a single forward pass, eliminating online kinematic adaptation. To improve robustness, we learn a codebook of full-body motion primitives that projects out-of-distribution observations onto plausible motion prototypes and recovers full-body motion from partial inputs. Experiments on a Unitree~G1 in simulation and on hardware, using virtual reality, optical mocap, text-to-motion generation, and monocular video inputs, show that our method outperforms baselines in latency and robustness.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Xu, X., Yu, J., Chen, X., Qian, S., Ma, Z., Liu, L., Shi, L., & Zhang, H. (2026). Beyond Retargeting: Low-Latency and Robust Humanoid Whole-Body Teleoperation with Learned Atomic Motion Primitives. https://omanscience.com/en/articles/beyond-retargeting-low-latency-and-robust-humanoid-whole-body-teleoperation-with-learned-atomic-motion-primitives
MLA 9
Xu, Xiayan, et al. "Beyond Retargeting: Low-Latency and Robust Humanoid Whole-Body Teleoperation with Learned Atomic Motion Primitives." https://omanscience.com/en/articles/beyond-retargeting-low-latency-and-robust-humanoid-whole-body-teleoperation-with-learned-atomic-motion-primitives.
Chicago (author–date)
Xu, Xiayan, Jiyu Yu, Xingzhou Chen, Siyi Qian, Zongyu Ma, Lilu Liu, Ling Shi, and Haodong Zhang. 2026. "Beyond Retargeting: Low-Latency and Robust Humanoid Whole-Body Teleoperation with Learned Atomic Motion Primitives." https://omanscience.com/en/articles/beyond-retargeting-low-latency-and-robust-humanoid-whole-body-teleoperation-with-learned-atomic-motion-primitives.
Harvard
Xu, X., Yu, J., Chen, X., Qian, S., Ma, Z., Liu, L., Shi, L. and Zhang, H. (2026) 'Beyond Retargeting: Low-Latency and Robust Humanoid Whole-Body Teleoperation with Learned Atomic Motion Primitives', Available at: https://omanscience.com/en/articles/beyond-retargeting-low-latency-and-robust-humanoid-whole-body-teleoperation-with-learned-atomic-motion-primitives.
Vancouver
Xu X, Yu J, Chen X, Qian S, Ma Z, Liu L, et al. Beyond Retargeting: Low-Latency and Robust Humanoid Whole-Body Teleoperation with Learned Atomic Motion Primitives. https://omanscience.com/en/articles/beyond-retargeting-low-latency-and-robust-humanoid-whole-body-teleoperation-with-learned-atomic-motion-primitives
IEEE
X. Xu, J. Yu, X. Chen, S. Qian, Z. Ma, L. Liu, L. Shi, and H. Zhang, "Beyond Retargeting: Low-Latency and Robust Humanoid Whole-Body Teleoperation with Learned Atomic Motion Primitives," https://omanscience.com/en/articles/beyond-retargeting-low-latency-and-robust-humanoid-whole-body-teleoperation-with-learned-atomic-motion-primitives.