论文/arXiv 2610.13079·19 天前

VICAR：用于人形机器人交互技能的接触感知重定向视频模仿

VICAR从第三人称人类视频恢复运动与障碍，接触感知重定向后训练生成器，并在多种技能硬件部署验证。

AI 整理

• 硬件零部件
• 数据与采集

原文链接：VICAR: Video Imitation with Contact-Aware Retargeting for Humanoid Interactive Skills（arXiv 2610.13079 · 发布日期：2026-10-09）

VICAR: Video Imitation with Contact-Aware Retargeting for Humanoid Interactive Skills

VICAR从第三人称人类视频恢复运动与障碍，接触感知重定向后训练生成器，并在多种技能硬件部署验证。

核心要点

• 接触丰富模仿需让世界坐标接触的位姿、时序和速度跨形体差异与场景变化保真。
• 系统从单目视频恢复人体运动、重建任务相关障碍，并将动作重定向到人形机器人。
• 方法以高优先级拉格朗日惩罚保持接触位姿和碰撞间隙，并优化接触过渡平滑性。
• 在十个第三人称视频技能上演示，包括乒乓发球、拾取和爬梯，并部署到硬件。

验证范围与局限：验证范围为十个第三人称视频技能及硬件部署。

英文摘要 (Abstract)

Third-person human videos offer a scalable alternative to task-specific reward engineering, teleoperation, and manually scripted demonstrations for humanoid loco-manipulation. Recent video-to-humanoid systems have shown that noisy human motion, object trajectories, and contacts can be extracted from unstructured videos and refined into deployable skills. However, a key gap remains for contact-rich imitation: the task is often defined by world-frame contacts whose poses, timing, and speed must survive embodiment mismatch and runtime scene changes. Towards this, we present VICAR (Video Imitation with Contact-Aware Retargeting), a pipeline for learning humanoid interactive skills from third-person human videos. The system first recovers human motion, reconstructs task-relevant obstacles from monocular video, and then retargets the motion to a humanoid while preserving global contact poses, motion speed, and collision clearance. Unlike retargeting methods that only remove penetration or preserve local interaction geometry, our formulation represents user-specified contact poses and collision clearance as high-priority Lagrangian penalty terms and optimizes the full motion to remain smooth through contact-rich transitions. The resulting motions are used to train a contact-conditioned motion generator whose inputs include movable contact points enabling runtime adaptation to new contact positions. We demonstrate the framework on ten diverse third-person video skills, including six table-tennis serves, three object-pickup tasks, and ladder climbing, and deploy the learned skills on hardware. These results suggest that contact-preserving retargeting is a practical step toward humanoids that learn useful interactive behavior by watching humans.

作者：Dvij Kalaria, Bike Zhang, S. Shankar Sastry

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.13079：VICAR: Video Imitation with Contact-Aware Retargeting for Humanoid Interactive Skills访问 2026-10-21