GelSphere: An Omnidirectional Rolling Vision-Based Tactile Sensor for Online 3D Reconstruction and Normal Force Estimation

TL;DR

GelSphere is a novel spherical tactile sensor that enables omnidirectional rolling and real-time surface reconstruction, overcoming limitations of traditional vision-based tactile sensors in local sensing and damage resistance.

Contribution

The paper introduces GelSphere, a spherical design with internal steel balls allowing omnidirectional rolling and continuous surface scanning, with real-time image streaming and reconstruction.

Findings

Maintains high geometric fidelity during multi-directional rolling

Achieves accurate online 3D surface reconstruction

Demonstrates robust tactile image fusion performance

Abstract

We present GelSphere, a spherical vision-based tactile sensor designed for real-time continuous surface scanning. Unlike traditional vision-based tactile sensors that can only sense locally and are damaged when slid across surfaces, and cylindrical tactile sensors that can only roll along a fixed direction, our design enables omnidirectional rolling on surfaces. We accomplish this through our novel sensing system design, which has steel balls inside the sensor, forming a bearing layer between the gel and the rigid housing that allows rolling motion in all axes. The sensor streams tactile images through Wi-Fi, with online large-surface reconstruction capabilities. We present quantitative results for both reconstruction accuracy and image fusion performance. The results show that our sensor maintains geometric fidelity and high reconstruction accuracy even under multi-directional rolling, enabling uninterrupted surface scanning.