盲态灵巧性：仅通过本体感知实现人形机器人全身操作
Blind Dexterity: Whole-Body Humanoid Manipulation via Pure Proprioception
浏览论文内容
中文总结 AI 辅助
该研究提出仅用关节编码器本体感知的策略，让Unitree G1人形机器人完成抗推行走、接球等盲态全身操作，证明其可作为灵巧操作与交互式感知的实用基础。
中文摘要 AI 辅助
我们展示了Unitree G1人形机器人仅利用机载本体感知（不使用摄像头、标记点、力扭矩或触觉传感器）实现的盲态全身操作技能。尽管感知方式极简，训练出的策略在性质迥异的任务中展现出惊人能力：无IMU反馈的抗推双足行走、用脚主动接住足球、寻找并通过把手提起行李箱、安装随机放置的滑板。我们认为这些能力源于一个被低估的关键信号：关节编码器读数在有意顺应接触下的变化方式，有效形成了全身触觉通道。通过生成富含接触的运动，训练出的策略主动探测环境；因此，任务相关的物体状态（如位姿）可从短期本体感知历史中越来越多地被解码。我们使用与策略同步训练但完全独立的紧凑任务特定状态估计器来提取该信息；其预测误差在接触后迅速降低。我们的结果表明，基于关节编码器的本体感知，结合顺应式驱动（目前已在商用机器人和低成本电机上广泛应用），已成为全身灵巧操作和交互式感知的强大实用基础，因此是叠加更丰富感知的自然基础。
英文摘要
We present blind, whole-body manipulation skills on a Unitree G1 humanoid using only onboard proprioception, without cameras, markers, force-torque, or tactile sensors. Despite this minimal sensing, the trained policies exhibit surprising capability across qualitatively different tasks: push-resilient bipedal walking without IMU feedback, active soccer ball trapping with a foot, seeking and lifting a suitcase by its handle, and mounting a randomly positioned skateboard. We argue that these capabilities arise from a key underappreciated signal: the way the joint encoder readouts evolve under purposeful compliant contact, effectively forming a whole-body tactile channel. By generating contact-rich motions, the trained policies actively probe the environment; as a result, task-relevant object state (e.g., pose) becomes increasingly decodable from short proprioceptive histories. We expose this information using compact task-specific state estimators trained alongside, but fully separately from, the policies; their prediction errors decrease rapidly after informative contact. Our results indicate that joint encoder-based proprioception, combined with compliant actuation (now widely available on commercial robots and low-cost motors) is already a strong, practical substrate for whole-body dexterous manipulation and interactive perception, and therefore a natural foundation on which richer sensing can be layered.
发表机构
- TU Darmstadt（达姆施塔特工业大学）
- German Research Center for AI (DFKI)（德国人工智能研究中心）
- Tongji University（同济大学）
- Shanghai Research Institute for Autonomous Intelligent Systems（上海自主智能系统研究院）
- Robotics Institute Germany（德国机器人研究所）
机构由 AI 辅助整理，请以论文原文为准。
