Beyond Retargeting: Low-Latency and Robust Humanoid Whole-Body Teleoperation with Learned Atomic Motion Primitives
Beyond Retargeting: Low-Latency and Robust Humanoid Whole-Body Teleoperation with Learned Atomic Motion Primitives
This paper introduces a retargeting-free policy for humanoid whole-body teleoperation that maps raw human motion directly to robot joint commands in a single forward pass, eliminating online kinematic adaptation. To improve robustness, the authors 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 conducted on a Unitree G1 in both simulation and hardware environments, utilizing virtual reality, optical mocap, text-to-motion generation, and monocular video inputs, demonstrate that the proposed method outperforms existing baselines in terms of latency and robustness.
The authors present a retargeting-free policy for humanoid whole-body teleoperation that maps raw human motion directly to robot joint commands, using learned atomic motion primitives to handle out-of-distribution and partial inputs; experiments on a Unitree G1 in simulation and hardware demonstrate improved latency and robustness compared to baselines.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- TeleoperatedOpen source S2
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
on 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.
Open source S4
arXiv:2610.07891v2 Announce Type: replace 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 outsi
Open source S2
Source：arXiv Robotics — research abstracts · arxiv.org