Under review
TL;DR: We propose a tactile-reactive controller that refines grasps without object models or precise poses, improving grasp stability on a 15-DoF arm–hand system.
Real-time demos
Vision-only grasping systems are fundamentally constrained by calibration errors, sensor noise, and grasp-pose prediction inaccuracies, leading to unavoidable contact uncertainty in the final stage of grasping. High‑bandwidth tactile feedback, when paired with a well‑designed tactile‑reactive controller, can significantly improve robustness in the presence of perception errors. This paper contributes to controller design by proposing a purely tactile-feedback grasp-adjustment algorithm. The proposed controller requires neither prior knowledge of the object’s geometry nor an accurate grasp pose, and is capable of refining a grasp even when starting from a crude, imprecise initial configuration and uncertain contact points. Through simulation studies and real‑world experiments on a 15‑DoF arm–hand system (featuring an 8‑DoF hand) equipped with fingertip tactile sensors operating at 200 Hz, we demonstrate that our tactile-reactive grasping framework effectively improves grasp stability.
Projected Gradient Descent
Cross-Finger Gradient Descent
Projected Gradient Descent
Cross-Finger Gradient Descent
Projected Gradient Descent
Cross-Finger Gradient Descent
Vanilla (No Reflex)
Projected Gradient Descent
Cross-Finger Gradient Descent
Vanilla (No Reflex)
Projected Gradient Descent
Cross-Finger Gradient Descent
Vanilla (No Reflex)
Projected Gradient Descent
Cross-Finger Gradient Descent
Videos of our reflexive grasping algorithms.
@misc{lee2025highbandwidthtactilereactivecontrolgrasp,
title={High-Bandwidth Tactile-Reactive Control for Grasp Adjustment},
author={Yonghyeon Lee and Tzu-Yuan Lin and Alexander Alexiev and Sangbae Kim},
year={2025},
eprint={2509.15876},
archivePrefix={arXiv},
primaryClass={cs.RO},
url={https://arxiv.org/abs/2509.15876},
}