发表机构
The University of Osaka; The University of Tokyo（大阪大学; 东京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究在带脚轮的被动移动椅上学习人形机器人全向坐姿运动，通过改进站立速度跟踪环境训练策略，实现零样本仿真到真实机器人的迁移，其坐姿策略速度跟踪性能优于站立策略。
AI 中文摘要
配备准直接驱动执行器的人形机器人站立时会持续产生关节扭矩，而坐姿人类在伏案工作时会将体重支撑委托给椅子。作为坐姿运动操作的第一步，我们研究被动移动椅上的全向坐姿运动，该运动要求机器人-椅子系统的骨盆与座椅接触不固定，且存在间歇性的脚-地面推进。我们在标准的站立速度跟踪环境中加入被动椅模型、坐姿状态奖励、仅评论者的椅子观测值以及任务定制的接触设置。该策略无需运动模仿奖励即可学习，其执行器仅使用本体感觉和速度指令，无需接触传感或椅子状态。在随机指令评估中，策略在几乎所有20秒的滚动测试中都能跟踪全向指令，且最佳坐姿策略在速度跟踪性能上优于站立策略。在四个训练随机种子下，对对称正则化（SY）、脚滑正则化（FS）和指令课程（CC）进行2^3全因子比较，结果显示FS降低了总功耗（CoT）但增加了跟踪误差，且部分仅使用FS的策略收敛到平稳局部最优。将FS与SY或CC结合可避免此失败，无需重新调整FS，同时SY在纵向运动中改善了双腿对称性。方向解析分析显示，CoT的顺序为向后<侧向<<向前，向后和侧向运动中存在支撑腿伸展，向前运动中脚跟接触后膝盖弯曲。学习到的策略实现了零样本仿真到真实的迁移，应用于Unitree G1机器人并生成全向坐姿运动。
英文摘要
Humanoid robots with quasi-direct-drive actuators continuously generate joint torque while standing, whereas seated humans delegate weight support to chairs during desk work. As a first step toward seated loco-manipulation, we study omnidirectional seated locomotion on a passive mobile chair, requiring unfixed pelvis-seat contact and intermittent foot-floor propulsion of the robot-chair system. We extend a standard standing velocity-tracking environment with a passive-chair model, seated-state rewards, critic-only chair observations, and task-tailored contact settings. The policy is learned without motion-imitation rewards; its actor uses only proprioception and velocity commands, without contact sensing or chair states. In random-command evaluation, the policies tracked omnidirectional commands through nearly all 20-s rollouts, and the best seated policies could outperform the Standing policy in velocity tracking. Across four training seeds, a $2^3$ full-factorial comparison of symmetry regularization (SY), foot-slip regularization (FS), and command curriculum (CC) showed that FS reduced CoT but increased tracking error and that some FS-only policies converged to stationary local optima. Combining FS with either SY or CC avoided this failure without retuning FS, while SY improved bilateral leg symmetry during longitudinal motion. Direction-resolved analysis showed CoT ordered backward $<$ lateral $\ll$ forward, with planted-leg extension in backward and lateral motion and knee flexion following heel contact in forward motion. The learned policy achieved zero-shot sim-to-real transfer to a Unitree G1 and generated omnidirectional seated locomotion.
