PhysHSI：迈向真实世界可泛化且自然的人形机器人-场景交互系统
PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System
浏览论文内容
中文总结 AI 辅助
提出PhysHSI系统，通过仿真中的对抗性运动先验策略学习实现自然泛化动作，结合真实部署中LiDAR与相机的粗到细定位模块，在搬运、坐、躺、站四类任务中取得高成功率和自然运动模式。
中文摘要 AI 辅助
部署人形机器人与真实世界环境交互（例如搬运物体或坐在椅子上）需要可泛化的、逼真的动作以及鲁棒的场景感知。尽管先前的方法分别推进了各项能力，但将它们结合在一个统一系统中仍是一项持续的挑战。在本研究中，我们提出了一种物理世界人形机器人-场景交互系统 PhysHSI，使人形机器人能够自主执行多样化的交互任务，同时保持自然和逼真的行为。PhysHSI 包含一个仿真训练流程和一个真实世界部署系统。在仿真中，我们采用基于对抗性运动先验的策略学习，以在多样化场景中模仿自然的人形机器人-场景交互数据，实现泛化和逼真行为。对于真实世界部署，我们引入了一个由粗到细的物体定位模块，结合 LiDAR 和相机输入，以提供连续且鲁棒的场景感知。我们在仿真和真实世界环境中验证了 PhysHSI 在四个代表性交互任务（搬运箱子、坐下、躺下和站立）上的表现，展示了持续的高成功率、跨多样化任务目标的强泛化能力以及自然的运动模式。
英文摘要
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.
