VICAR：面向人形机器人交互技能的接触感知重定向视频模仿
VICAR: Video Imitation with Contact-Aware Retargeting for Humanoid Interactive Skills
AI总结：
该研究提出VICAR框架，从第三人称人类视频学习人形机器人交互技能，通过接触感知重定向保留关键运动信息，经10类技能验证后成功部署到硬件，为机器人模仿学习提供新方案。
摘要：
第三人称人类视频为人形机器人的运动操作任务提供了一种可扩展的替代方案，可替代特定任务的奖励工程、遥操作和手动编写的演示。近期的视频到人形机器人系统已表明，可从非结构化视频中提取嘈杂的人类运动、物体轨迹和接触信息，并将其优化为可部署的技能。然而，在接触丰富的模仿任务中仍存在关键缺口：该任务通常由世界坐标系下的接触定义，其姿态、时间和速度必须在实体不匹配和运行时场景变化中保持有效。为此，我们提出VICAR（Video Imitation with Contact-Aware Retargeting，面向人形机器人交互技能的接触感知重定向视频模仿），这是一种从第三人称人类视频中学习人形机器人交互技能的流程。该系统首先恢复人类运动，从单目视频中重建与任务相关的障碍物，然后将运动重定向到人形机器人，同时保留全局接触姿态、运动速度和碰撞间隙。与仅消除穿透或保留局部交互几何的重定向方法不同，我们的公式将用户指定的接触姿态和碰撞间隙表示为高优先级拉格朗日惩罚项，并优化整个运动以在接触丰富的过渡中保持平滑。生成的运动用于训练接触条件的运动生成器，其输入包括可移动接触点，支持运行时适应新的接触位置。我们在10种不同的第三人称视频技能上演示了该框架，包括6种乒乓球发球、3种物体拾取任务和爬梯子，并将学习到的技能部署到硬件上。这些结果表明，保留接触的重定向是实现人形机器人通过观察人类学习有用交互行为的实用一步。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
