HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos

TL;DR

HumanX is a comprehensive framework that converts human videos into generalizable, real-world interaction skills for humanoid robots, enabling scalable, task-agnostic learning of complex interactive behaviors without task-specific rewards.

Contribution

It introduces a novel full-stack approach combining data synthesis and imitation learning to transfer human video demonstrations into versatile robot skills.

Findings

Achieves over 8 times higher generalization success than prior methods.

Successfully transfers 10 diverse skills to a physical humanoid robot.

Learns complex maneuvers and interactive tasks from single video demonstrations.

Abstract

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.