发表机构
Inria, Département d’Informatique de l’École Normale Supérieure, PSL Research University; Stanford University（法国国家信息与自动化研究所，巴黎高等师范学校计算机科学系，巴黎文理研究大学; 斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出OTRetarget，利用熵正则化最优传输联合重定向机器人与多物体运动，在OMOMO上交互Jaccard达87%，并成功迁移至物理人形机器人。
AI 中文摘要
将人类运动迁移到人形机器人上，需要在保持与环境交互的同时，将演示运动适配到机器人形态。这对于移动操作任务尤其具有挑战性，因为尽管身体比例不同，与地面和被操作物体的接触必须保持一致。然而，仅骨骼运动并不能完全描述这些交互，而固定物体轨迹限制了对新形态的适配。在本文中，我们提出OTRetarget，一种统一的方法，用于从人类演示中联合重定向机器人和多物体运动。我们的方法通过符号距离、最近表面点和相对方向来表示表面交互，并使用熵正则化最优传输将这些量在人类、机器人和物体几何之间进行传递。我们将得到的交互目标纳入一个约束逆运动学公式中，该公式在保持接触与运动风格之间取得平衡，并在每一帧联合优化机器人和物体的位姿。该公式无需重新缩放场景或演示即可适应机器人-物体和物体-物体交互。我们在OMOMO上验证了所提出的方法，其机器人-物体交互Jaccard得分为87%，深度误差为8.7毫米，而OmniRetarget分别为28%和29.3毫米。最后，我们展示了使用在重定向参考上通过强化学习训练的全身策略，将运动迁移到物理G1人形机器人上，包括双手将箱子从桌上拿起并放置到桌上的动作。
英文摘要
Transferring human motion to humanoid robots requires adapting the demonstrated motion to the robot morphology while preserving interactions with the environment. This is particularly challenging for loco-manipulation tasks, where contacts with the ground and manipulated objects must remain consistent despite differences in body proportions. Yet, skeletal motion alone does not fully describe these interactions, and fixing object trajectories limits the adaptation to a new embodiment. In this paper, we introduce OTR ETARGET, a unified approach to jointly retarget robot and multi-object motion from human demonstrations. Our approach represents surface interactions through signed distances, closest surface points, and relative directions, and uses entropic optimal transport to transfer these quantities across human, robot, and object geometries. We incorporate the resulting interaction targets into a constrained inverse kinematics formulation that balances contact preservation with motion style and jointly optimizes robot and object poses at each frame. This formulation accommodates robot-object and object-object interactions without rescaling the scene or the demonstration. We validate the proposed approach on OMOMO, where it achieves a robot- object interaction Jaccard score of 87% and a depth error of 8.7 mm, compared with 28% and 29.3 mm for OmniRetarget. Finally, we demonstrate transfer to a physical G1 humanoid using whole-body policies trained with reinforcement learning on the retargeted references, across motions including two-handed box pick-and-place onto a table.
Comments9 pages
