外观
论文arXiv 2610.1939314 天前
超越运动学跟踪：在人形机器人全身控制中保留表现性特征
该文针对人形全身控制中表现性特征易丢失的问题，提出带补偿目标与运动感知门控的残差学习，并在仿真和Unitree G1真机八类动作上验证。
宇树 G1原文链接：Beyond Kinematic Tracking: Preserving Expressive Characteristics in Humanoid Whole-Body Control（arXiv 2610.19393 · 发布日期：2026-10-14）
Beyond Kinematic Tracking: Preserving Expressive Characteristics in Humanoid Whole-Body Control
该文针对人形全身控制中表现性特征易丢失的问题，提出带补偿目标与运动感知门控的残差学习，并在仿真和Unitree G1真机八类动作上验证。
核心要点
- 现有全身跟踪器追求位置误差和稳定性，未必保留动作的动态与姿态特征。
- 方法为冻结跟踪器训练运动特定残差策略，并蒸馏为跨类别统一策略。
- 残差补偿面向幅度、能量、身体扩展、身体倾斜和骨盆高度等目标。
- 仿真与Unitree G1真机实验显示，相比基线更好保留动态和姿态特征。
验证范围与局限：验证范围限于仿真和Unitree G1上的八类运动类别。
英文摘要 (Abstract)
Whole-body control plays a crucial role in enabling humanoid robots to execute expressive motions. Faithful execution requires preserving both the intended action and its expressive characteristics. Existing whole-body trackers typically balance joint and keypoint tracking with physical stability across diverse motions, but these objectives do not necessarily prioritize the expressive characteristics of each action. Our analysis shows that lower average positional tracking error does not guarantee better preservation of dynamic and postural motion characteristics. To address this gap, we propose a residual learning framework with compensation objectives targeting amplitude, energy, body expansion, body lean, and pelvis height. To concentrate compensation while limiting interference with the underlying tracking behavior, motion-aware gating allocates correction capacity according to body-part activity, preserving larger correction ranges in more active parts and restricting them elsewhere. For each frozen tracker, we train motion-specific residual policies and distill them into a unified policy shared across motion categories. Simulation and physical experiments on the Unitree G1 across eight motion categories demonstrate superior preservation of dynamic and postural motion characteristics compared with the corresponding baselines.
作者：Lingfan Bao, Hanshang Zhu, Yan Pan, Jincheng Wang, Jingyang Yu, Tianhu Peng, Yiyang Jia, Dimitrios Kanoulas, Chengxu Zhou
来源
本页事实对应的公开页面，以原文为准。