发表机构
The Hong Kong University of Science and Technology; Zhejiang University; Tencent Robotics X; Hunan University（香港科技大学; 浙江大学; 腾讯机器人实验室; 湖南大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出无重定向策略，直接映射人类运动至机器人指令，利用运动原语码本处理分布外观测，在Unitree G1上实现低延迟鲁棒遥操作。
AI 中文摘要
人形全身遥操作将人类运动实时转化为稳定的机器人行为。现有系统通常依赖在线运动重定向来弥合人机形态差异，但该过程会增加延迟并可能产生物理上不可行的目标。同时，多样化、嘈杂且部分缺失的人类运动观测往往超出训练分布，可能导致机器人行为不稳定。我们提出一种无需重定向的策略，通过单次前向传播直接将原始人类运动映射为机器人关节指令，消除在线运动学自适应。为提高鲁棒性，我们学习了一个全身运动原语码本，将分布外观测投影到合理的运动原型上，并从部分输入中恢复全身运动。在仿真和硬件上使用Unitree G1，结合虚拟现实、光学动作捕捉、文本到运动生成和单目视频输入进行的实验表明，我们的方法在延迟和鲁棒性方面优于基线。
英文摘要
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.
