HumanX: 向通过人类视频实现敏捷且可推广的人形交互技能迈进
HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos
浏览论文内容
中文总结 AI 辅助
HumanX通过人类视频实现敏捷且可推广的人形交互技能，无需任务特定奖励，展示出高泛化能力。
中文摘要 AI 辅助
使人形机器人执行敏捷且适应性的交互任务长期以来一直是机器人学的核心挑战。当前的方法受到现实交互数据稀缺或需要细致的任务特定奖励工程的限制，这限制了它们的可扩展性。为了缩小这一差距，我们提出了HumanX，一个全栈框架，将人类视频编译成通用的、现实世界的交互技能，无需任务特定的奖励。HumanX集成了两个协同设计的组件：XGen，一个数据生成管道，从视频中合成多样化且物理上合理的机器人交互数据，同时支持可扩展的数据增强；以及XMimic，一个统一的模仿学习框架，学习通用的交互技能。在五个不同的领域——篮球、足球、羽毛球、货物搬运和反应战斗中进行评估，HumanX成功获得了10种不同的技能，并将其零样本转移到物理的Unitree G1人形机器人上。所学的能力包括复杂的动作，如假动作转身Fadeaway跳投，无需任何外部感知，以及交互任务如持续的人机传球序列超过10个连续循环——从单个视频演示中学习。我们的实验表明，HumanX的泛化成功率比先前的方法高8倍，展示了学习多功能、现实世界机器人交互技能的可扩展且任务无关的路径。
英文摘要
Enabling humanoid robots to perform agile and adaptive interactive tasks has long been a core challenge in robotics. Current approaches are bottlenecked by either the scarcity of realistic interaction data or the need for meticulous, task-specific reward engineering, which limits their scalability. To narrow this gap, we present HumanX, a full-stack framework that compiles human video into generalizable, real-world interaction skills for humanoids, without task-specific rewards. HumanX integrates two co-designed components: XGen, a data generation pipeline that synthesizes diverse and physically plausible robot interaction data from video while supporting scalable data augmentation; and XMimic, a unified imitation learning framework that learns generalizable interaction skills. Evaluated across five distinct domains--basketball, football, badminton, cargo pickup, and reactive fighting--HumanX successfully acquires 10 different skills and transfers them zero-shot to a physical Unitree G1 humanoid. The learned capabilities include complex maneuvers such as pump-fake turnaround fadeaway jumpshots without any external perception, as well as interactive tasks like sustained human-robot passing sequences over 10 consecutive cycles--learned from a single video demonstration. Our experiments show that HumanX achieves over 8 times higher generalization success than prior methods, demonstrating a scalable and task-agnostic pathway for learning versatile, real-world robot interactive skills.
