PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System
This work addresses the problem of generalizable and lifelike humanoid-scene interaction for robotics deployment, though it appears incremental by combining existing capabilities into a unified system.
The authors tackled the challenge of enabling humanoid robots to perform diverse interaction tasks with real-world environments by developing PhysHSI, a system that achieved high success rates and natural motion patterns in tasks like box carrying and sitting.
Deploying humanoid robots to interact with real-world environments--such as carrying objects or sitting on chairs--requires generalizable, lifelike motions and robust scene perception. Although prior approaches have advanced each capability individually, combining them in a unified system is still an ongoing challenge. In this work, we present a physical-world humanoid-scene interaction system, PhysHSI, that enables humanoids to autonomously perform diverse interaction tasks while maintaining natural and lifelike behaviors. PhysHSI comprises a simulation training pipeline and a real-world deployment system. In simulation, we adopt adversarial motion prior-based policy learning to imitate natural humanoid-scene interaction data across diverse scenarios, achieving both generalization and lifelike behaviors. For real-world deployment, we introduce a coarse-to-fine object localization module that combines LiDAR and camera inputs to provide continuous and robust scene perception. We validate PhysHSI on four representative interactive tasks--box carrying, sitting, lying, and standing up--in both simulation and real-world settings, demonstrating consistently high success rates, strong generalization across diverse task goals, and natural motion patterns.