# CoDance：从视频学习反应式柔顺人类-人形机器人互动

> 原文链接：https://robotics.hellobike.com/papers/2026-10-04-2610-05324
> 频道：papers | 更新日期：2026-10-04 | 标签：arxiv, cs.RO
> 核心摘要：CoDance从双人舞视频学习反应式柔顺人形互动，并在仿真与物理人形机器人上验证双手接触舞蹈。

# CoDance：从视频学习反应式柔顺人类-人形机器人互动

::: v-pre
> 原文链接：[CoDance: Learning Reactive and Compliant Human-Humanoid Interaction from Video](https://arxiv.org/abs/2610.05324)（arXiv 2610.05324 · 发布日期：2026-10-04）

**CoDance: Learning Reactive and Compliant Human-Humanoid Interaction from Video**

CoDance从双人舞视频学习反应式柔顺人形互动，并在仿真与物理人形机器人上验证双手接触舞蹈。

## 核心要点

- 人形机器人需在连续身体接触中协调人的运动、响应交互力并保持稳定自然。
- 从单段双人舞视频重定向为机器人参考与移动伙伴，并用多连杆柔顺增强生成力感知训练数据。
- 仿真中策略随伙伴变化调整步伐，并复现增强示范中约80%的腕部位移。
- 实机上实现与人类伙伴持续双手舞蹈，包含前进和后退间的反复转换。

**验证范围与局限**：验证范围为仿真和一台物理人形机器人上的双手接触双人舞任务。

## 英文摘要 (Abstract)

Partnered human-humanoid interaction couples locomotion with continuous physical contact. A humanoid needs to coordinate with a person's motion while responding to interaction forces and maintaining stable and natural movement. We present CoDance, a framework for learning reactive and compliant human-humanoid interaction from video. We study partnered dancing as a challenging instantiation, where a humanoid coordinates its footsteps with a moving partner and maintains continuous two-hand contact. Given a single video of two human dancers, CoDance retargets their motions into a robot reference and a moving partner. We introduce a multi-link compliance augmentation that transforms the kinematic demonstration into force-aware training data by adapting the robot reference under structured forces at both hands. Policies trained on this data follow the observed partner while preserving the demonstrated locomotion style and responding compliantly to physical interaction. In simulation, the policies adapt their footsteps to changes in the partner and reproduce approximately 80% of the wrist displacement encoded by the augmented demonstrations. On a physical humanoid, CoDance enables sustained two-hand dancing with a human partner including repeated transitions between forward and backward motions.

作者：Zhuoqun Chen, Shucheng Jia, Boyuan Chen
:::

## 原始参考来源 (Sources)

- [arXiv 2610.05324：CoDance: Learning Reactive and Compliant Human-Humanoid Interaction from Video](https://arxiv.org/abs/2610.05324)