# OTRetarget：通过最优传输进行机器人与物体运动联合重定向

> 原文链接：https://robotics.hellobike.com/papers/2026-09-29-2609-36602
> 频道：papers | 更新日期：2026-09-29 | 标签：arxiv, cs.RO
> 核心摘要：该方法面向人类示范到人形机器人的运动迁移，用熵正则最优传输联合重定向机器人与多物体运动，并在OMOMO和真实G1上验证。

# OTRetarget：通过最优传输进行机器人与物体运动联合重定向

::: v-pre
> 原文链接：[OTRetarget: Joint Robot and Object Motion Retargeting via Optimal Transport](https://arxiv.org/abs/2609.36602)（arXiv 2609.36602 · 发布日期：2026-09-29）

**OTRetarget: Joint Robot and Object Motion Retargeting via Optimal Transport**

该方法面向人类示范到人形机器人的运动迁移，用熵正则最优传输联合重定向机器人与多物体运动，并在OMOMO和真实G1上验证。

## 核心要点

- 针对移动操作中机器人形态差异导致地面与物体接触难以保持的问题。
- 用有符号距离、最近表面点和相对方向表示表面交互，并通过熵正则最优传输跨几何体迁移。
- 将交互目标纳入约束逆运动学，逐帧联合优化机器人与物体位姿，兼顾接触保持和运动风格。
- 在OMOMO上机器人-物体交互Jaccard达87%、深度误差8.7 mm，并优于OmniRetarget；还演示了真实G1迁移。

**验证范围与局限**：验证包括OMOMO和真实G1人形机器人，真实演示涵盖双手搬箱放到桌上等动作。

## 英文摘要 (Abstract)

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.

作者：Guillaume Besset, Erwann Carn, Timothée Carecchio, Valentin Tordjman--Levavasseur, Fabian Schramm, Yann Dubois de Mont-Marin, Justin Carpentier, Ajay Suresha Sathya
:::

## 原始参考来源 (Sources)

- [arXiv 2609.36602：OTRetarget: Joint Robot and Object Motion Retargeting via Optimal Transport](https://arxiv.org/abs/2609.36602)