看到达，触觉抓取：学习拟人机械手的盲抓取反射
See to Reach, Feel to Grasp: Learning A Blind Grasp Reflex for Anthropomorphic Robotic Hands
浏览论文内容
中文总结 AI 辅助
本研究提出模块化灵巧抓取架构，仅凭手部本体感觉实现盲抓取，分离手臂运动与接触控制，学习稳定抓取分数，仿真与硬件实验验证鲁棒性，遵循“看到达，触觉抓取”原则。
中文摘要 AI 辅助
在这项工作中，我们研究仅使用本体感觉的机械手是否能在没有视觉观察的情况下抓取各种物体。我们提出了一种模块化的灵巧抓取架构，将全局手臂运动与局部接触控制分离。一个独立控制的手臂引导手朝向物体，而强化学习策略仅使用手部本体感觉反馈来抓取并稳定物体。我们称之为“盲抓取反射”：在没有图像、物体姿态或几何观察的情况下进行抓取。一个学习到的稳定抓取分数决定物体何时被牢固握住，从而使手臂能够开始抓取后操作。这种分离使抓取成为一种可重用的手级技能，可以与独立设计的手臂控制器结合，用于各种操作任务。在仿真和硬件上的实验证明了在不同物体上的鲁棒盲抓取以及与多种手臂控制器的无缝组合。此外，尽管从未观察接触几何，学习到的抓取分数与基于物理的独立抓取稳定性度量紧密对齐。所得到的方法遵循一个简单的原则：看到达，触觉抓取。项目页面：此 https URL。
英文摘要
In this work we study if a robotic hand using proprioception alone can grasp diverse objects with no visual observation. We present a modular dexterous grasping architecture that separates global arm motion from local contact control. An independently controlled arm guides the hand toward the object, while a reinforcement learning policy grasps and stabilizes it using only hand proprioceptive feedback. We call this \textit{a blind grasp reflex}: grasping without images, object poses, or geometric observations. A learned stable-grasp score determines when the object is securely held, allowing the arm to begin post-grasp manipulation. This separation makes grasping a reusable hand-level skill that can be combined with independently designed arm controllers for various manipulation tasks. Experiments in simulation and on hardware demonstrate robust blind grasping across diverse objects and seamless composition with a range of arm controllers. Moreover, despite never observing contact geometry, the learned grasp score closely aligns with an independent physics-based measure of grasp stability. The resulting approach follows a simple principle: see to reach, feel to grasp. Project page: https://blindgraspreflex.github.io.
发表机构
- Massachusetts Institute of Technology（麻省理工学院）
- Seoul National University（首尔大学）
- Yonsei University（延世大学）
机构由 AI 辅助整理，请以论文原文为准。
