论文/arXiv 2610.04238·25 天前

人形机器人拉人力车：耦合轮式负载下的全身运动

提出人形机器人拉人力车全身控制框架，以教师-学生蒸馏和强化学习，在对比实验与硬件上验证重载运输。

AI 整理

• 硬件零部件
• 本体 SDK 与控制

宇树 G1

原文链接：Humanoid Rickshaw Pulling: Whole-Body Locomotion under Coupled Wheeled Loads（arXiv 2610.04238 · 发布日期：2026-10-03）

Humanoid Rickshaw Pulling: Whole-Body Locomotion under Coupled Wheeled Loads

提出人形机器人拉人力车全身控制框架，以教师-学生蒸馏和强化学习，在对比实验与硬件上验证重载运输。

核心要点

• 拉被动轮式车辆可搬运更重载荷，但需在未知耦合力下保持上身接触、平衡和抓握。
• 框架跟踪车辆运动；特权教师利用车辆状态、作用力和载荷属性，蒸馏给历史条件学生并微调。
• 相较 No History 和 Only History，策略实现更准确跟踪，并降低车辆振荡、躯干倾斜和驱动成本。
• 硬件上单一策略可完成起步、持续拉行、转弯和停止，适用于刚性载荷与人类乘客。

验证范围与局限：验证包括 Unitree G1 拉人力车的硬件实验，最高加载人力车质量为 115 kg，且未进行负载特定再调参。

英文摘要 (Abstract)

Humanoid robots could transport payloads substantially heavier than themselves by pulling passive wheeled vehicles instead of carrying the load. This capability, however, creates a coupled locomotion problem: the robot must maintain persistent upper-body contact while adapting to unknown, configuration-dependent forces arising from the payload, vehicle, and terrain. We present a whole-body control framework for humanoid rickshaw pulling that tracks commanded vehicle motion while preserving balance and stable grasps under uncertain load dynamics. During training, a privileged teacher exploits vehicle states, interaction forces, and load properties. Its actions and latent are distilled into a history-conditioned student that implicitly infers coupled dynamics from proprioceptive responses, followed by reinforcement-learning fine-tuning. Comparisons with \emph{No History} and \emph{Only History} baselines show that the resulting policy achieves accurate vehicle tracking while reducing vehicle oscillation, torso tilt, and actuation cost. Behavioral analysis shows that Unitree G1 propels the rickshaw and generates gait-synchronized whole-body reactions that stabilize its lateral and roll motions. Moreover, pulling redistributes joint effort and yields a lower robot-normalized cost-of-transport proxy than unloaded walking over most tested load--speed conditions. On hardware, a single policy performs starting, sustained pulling, turning, and stopping with both rigid payloads and human passengers, handling a loaded rickshaw mass of up to 115~kg without load-specific retuning. These results demonstrate robust heavy-load transportation through coordinated and persistent humanoid--vehicle interaction.

作者：Yangzhi Yang, Xiansheng Lin, Zhaoming Xie, Xiaobin Xiong

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.04238：Humanoid Rickshaw Pulling: Whole-Body Locomotion under Coupled Wheeled Loads访问 2026-10-21