See to Reach, Feel to Grasp: Learning A Blind Grasp Reflex for Anthropomorphic Robotic Hands

2026-09-25

AI Summary

This study addresses the challenge of stable grasping of diverse objects by robotic manipulators relying solely on proprioception in the absence of visual observations. To overcome this limitation, the work proposes a modular control architecture that decouples arm motion from contact control. It introduces the principle of “look to reach, feel to grasp,” leveraging reinforcement learning to achieve blind grasping reflexes and enabling the transfer of grasping skills without requiring geometric information. By integrating an independent arm controller with a physical stability scoring mechanism, the proposed approach demonstrates robust cross-object grasping capabilities in both simulation and real-world hardware. Ultimately, this research establishes a novel paradigm for dexterous manipulation under visually deprived conditions.

Abstract

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.

Problem

• blind grasping
• proprioception
• anthropomorphic robotic hands
• dexterous manipulation
• grasp stability

Innovation

• Blind Grasp Reflex
• Proprioception
• Reinforcement Learning
• Modular Architecture
• Dexterous Grasping