Why Look at It at All?: Vision-Free Multifingered Blind Grasping Using Uniaxial Fingertip Force Sensing

TL;DR

This paper presents a vision-free, minimal-sensing approach for reliable multifingered robotic grasping using only uniaxial force feedback and proprioception, validated on real hardware with high success rates.

Contribution

It introduces a novel training pipeline combining reinforcement learning and distillation to enable robust grasping with minimal sensing modalities.

Findings

Achieved 98.3% grasp success rate on real hardware.

Demonstrated robustness to out-of-distribution objects.

Reduced sensing complexity while maintaining high performance.

Abstract

Grasping under limited sensing remains a fundamental challenge for real-world robotic manipulation, as vision and high-resolution tactile sensors often introduce cost, fragility, and integration complexity. This work demonstrates that reliable multifingered grasping can be achieved under extremely minimal sensing by relying solely on uniaxial fingertip force feedback and joint proprioception, without vision or multi-axis/tactile sensing. To enable such blind grasping, we employ an efficient teacher-student training pipeline in which a reinforcement-learned teacher exploits privileged simulation-only observations to generate demonstrations for distilling a transformer-based student policy operating under partial observation. The student policy is trained to act using only sensing modalities available at real-world deployment. We validate the proposed approach on real hardware across 18 objects, including both in-distribution and out-of-distribution cases, achieving a 98.3~$\%$ overall grasp success rate. These results demonstrate strong robustness and generalization beyond the simulation training distribution, while significantly reducing sensing requirements for real-world grasping systems.