发表机构
Gachon University（嘉泉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对移动底座人形机器人，提出任务条件化分配与部署适配框架，将人体动作重定向到底座、升降和手臂，并在仿真与实体上验证。
AI 中文摘要
人体视频提供了可扩展的机器人演示来源，然而大多数从人体到人形机器人的重定向方法假设机器人具有类似人类的运动学特性的腿式结构。这一假设对于配备轮式底座、垂直升降机构和两只手臂的移动底座人形机器人并不成立。人体行走必须通过底座运动来表达，而躯干弯曲可能需要升降机构和手臂的协调运动。我们通过一个任务条件化框架来解决这一不匹配问题，该框架在机器人特定实现之前，将重建的人体运动分配给底座、升降机构和手臂的职责。该分配器保留人体衍生的路径，稳定航向，在需要时分离转弯和平移，重新定时命令以满足底座限制，并修复升降机构和手臂轨迹。随后，一个部署适配器利用静止底座检测、死区和变化率滤波、时间一致的播放缩放以及独立的线性和角增益，将参考转换为50 Hz的命令。我们通过人体衍生的任务空间比较、无策略的仿真回放以及在物理机器人上的定性执行来评估生成的参考。
英文摘要
Human video offers a scalable source of robot demonstrations, yet most human-to-humanoid retargeting methods assume a legged robot with human-like kinematics. This assumption does not hold for mobile-base humanoids equipped with a wheeled base, vertical lift, and two arms. Human walking must be expressed through base motion, while torso bending may require coordinated lift and arm motion. We address this mismatch with a task-conditioned framework that assigns reconstructed human motion to base, lift, and arm responsibilities before robot-specific realization. The allocator preserves the human-derived path, stabilizes heading, separates turn and translation when needed, retimes commands to satisfy base limits, and repairs lift and arm trajectories. A deployment adapter then converts the reference to 50 Hz commands using stationary-base detection, deadband and slew-rate filtering, time-consistent playback scaling, and separate linear and angular gains. We evaluate the resulting references with human-derived task-space comparisons, policy-free simulation replay, and a qualitative execution on a physical robot.
Comments8 pages, 4 figures
