无需机器人即可学习人形机器人全身操作技能。
Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations
- 用便携设备采集人类全身动作，实现无机器人的数据收集。
- 在5种任务中达成70%未见环境成功率，效率是遥操作3倍。
- 适合想快速部署人形机器人操作能力的研究者与开发者。
当前人形机器人全身操作方法主要依赖遥操作或视觉模拟到现实的强化学习，受限于硬件物流和复杂的奖励设计，导致自主技能有限且多局限于受控环境。本文提出人形操作接口（HuMI），一种便携高效的框架，可在多种环境中学习多样化的全身操作任务。HuMI通过便携硬件捕捉丰富的全身运动，实现机器人自由的数据采集，驱动分层学习流程，将人类动作转化为灵巧且可行的人形技能。在5项全身任务——包括跪姿、蹲姿、投掷、行走和双臂操作——上的大量实验表明，与遥操作相比，HuMI的数据采集效率提升3倍，并在未见过的环境中达到70%的成功率。
原文摘要 · Abstract (English)
Current approaches for humanoid whole-body manipulation, primarily relying on teleoperation or visual sim-to-real reinforcement learning, are hindered by hardware logistics and complex reward engineering. Consequently, demonstrated autonomous skills remain limited and are typically restricted to controlled environments. In this paper, we present the Humanoid Manipulation Interface (HuMI), a portable and efficient framework for learning diverse whole-body manipulation tasks across various environments. HuMI enables robot-free data collection by capturing rich whole-body motion using portable hardware. This data drives a hierarchical learning pipeline that translates human motions into dexterous and feasible humanoid skills. Extensive experiments across five whole-body tasks--including kneeling, squatting, tossing, walking, and bimanual manipulation--demonstrate that HuMI achieves a 3x increase in data collection efficiency compared to teleoperation and attains a 70% success rate in unseen environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。