发表机构
Westlake Robotics; Westlake University（西湖机器人; 西湖大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出GAE统一学习框架，通过大规模数据集、两阶段训练和延迟补偿机制，实现低延迟、通用的人形全身遥操作，并在仿真和真实机器人上验证了效果。
AI 中文摘要
人形化身将人类的物理存在扩展到身体之外，使人们能够通过远程操作的机器人参与社交、服务和劳动活动。这要求遥操作系统能够实现多样化和动态的全身行为，同时保持响应迅速的人机同步。我们提出了通用动作专家（GAE），一个用于通用、低延迟人形全身遥操作的统一学习框架。为了覆盖多样化的人类行为，GAE从异构来源（包括视频、动画和动作捕捉）构建了一个大规模人类运动数据集，并进行标准化和增强。然后，GAE通过两阶段训练范式解决人类运动中的噪声和具身不匹配问题：一种特权生成器策略首先在仿真中跟踪人类运动参考并生成可行的人形轨迹；一种可部署的执行器策略随后在课程域随机化下学习跟踪这些生成的轨迹。为了实现响应迅速的人机同步，GAE引入了一种延迟条件预期机制，在实时遥操作期间自适应地补偿端到端延迟。在Unitree G1和Westlake O1机器人上的仿真和真实世界实验表明，GAE使人形机器人能够平滑地镜像多样化、敏捷和富有表现力的人类行为。项目网站：此https URL
英文摘要
Humanoid avatars extend human physical presence beyond the body, enabling people to participate in social, service, and labor activities through remotely operated robots. This requires teleoperation systems capable of realizing diverse and dynamic whole-body behaviors while maintaining responsive human-robot synchronization. We present General Action Expert(GAE), a unified learning framework for general-purpose, low-latency humanoid whole-body teleoperation. To cover diverse human behaviors, GAE builds a large-scale human motion dataset from heterogeneous sources, including videos, animations, and motion capture, followed by standardization and augmentation. GAE then addresses the noise and embodiment mismatch in human motions with a two-stage training paradigm: a privileged generator policy first tracks human motion references in simulation and rolls out feasible humanoid trajectories; a deployable executor policy then learns to track these generated trajectories under curriculum domain randomization. For responsive human-robot synchronization, GAE introduces a latency-conditioned anticipation mechanism that adaptively compensates for end-to-end delay during real-time teleoperation. Simulation and real-world experiments on Unitree G1 and Westlake O1 robots demonstrate that GAE enables humanoids to smoothly mirror diverse, agile, and expressive human behaviors. Project website: https://wangyf0928.github.io/gae-wlrobotics/
Comments12 pages, 14 figures
