雷神:面向在高度密集接触环境中实现人类水平的全身反应
Thor: Towards Human-Inspired Whole-Body Reactions for Intense Contact-Rich Environments
AI总结:
研究旨在使人形机器人在高度密集接触环境中实现人类水平全身反应。提出雷神框架,基于力分析设计奖励函数,引入解耦强化学习架构。部署在宇树G1上,大幅超越基线,提升了人形机器人力量交互能力。
摘要:
人形机器人在服务、工业和救援应用中有巨大潜力,在这类应用中机器人须在与环境进行激烈、大量接触互动时保持全身稳定。然而,使人形机器人在这种条件下产生类人适应性反应仍是重大挑战。为此,我们提出雷神,一个用于在高度密集接触环境中实现人类水平全身反应的人形机器人框架。基于机器人的力分析,设计了力自适应躯干倾斜(FAT2)奖励函数,以鼓励人形机器人在力交互任务中展现类人反应。为缓解人形机器人控制的高维挑战,雷神引入一种强化学习架构,解耦上半身、腰部和下半身,各组件共享全身全局观测并联合更新参数。最后,将雷神部署在宇树G1上,它在力交互任务中大幅超越基线。具体而言,机器人向后移动时达到167.7N的峰值拉力(约为G1体重的48%),向前移动时为145.5N,与最佳基线相比分别提高了68.9%和74.7%。此外,雷神能够拉动载重货架(130N)并用一只手打开防火门(60N)。这些结果凸显了雷神在增强人形机器人力量交互能力方面的有效性。
英文摘要:
Maintaining whole-body stability and motion tracking under large interaction forces remains challenging for humanoids. We present Thor, a reinforcement learning framework for forceful humanoid loco-manipulation. Thor jointly trains lower-body, waist, and upper-body policies with shared whole-body observations and body-specific rewards to coordinate locomotion and force adaptation, waist posture regulation, and upper-body motion tracking. We further introduce a force-adaptive torso-tilt (FAT2) objective that derives a load-dependent horizontal center-of-mass offset reference from quasi-static moment balance. Capacity-matched simulation blations show that the three-policy architecture improves tracking under large external force disturbances, while real-world ablations demonstrate that FAT2 increases peak pulling capability. On the Unitree G1, Thor achieves mean peak dual-hand pulling forces of 167.7 N and 145.5 N during backward and forward locomotion, exceeding the best-performing baseline by 68.9% and 74.7%, respectively. Real-world demonstrations include opening a fire door with one hand using approximately 60 N of pulling force and towing a 1.7-ton passenger car.
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。