GelSphere: An Omnidirectional Rolling Vision-Based Tactile Sensor for Online 3D Reconstruction and Normal Force Estimation
🤖 AI Summary
This work proposes GelSphere, a spherical vision-based tactile sensor designed to overcome the limitations of conventional tactile sensors—namely, restricted local perception, unidirectional rolling capability, and mechanical fragility—which hinder continuous, omnidirectional surface scanning. GelSphere features an innovative internal steel ball-bearing mechanism that enables stable contact and full omnidirectional rolling. Integrated with embedded visual sensing, Wi-Fi-enabled image streaming, and an online image fusion algorithm, it simultaneously achieves high-fidelity 3D surface reconstruction and normal force estimation during large-scale, continuous rolling motion. Experimental results demonstrate that GelSphere maintains geometric accuracy and reconstruction stability across multidirectional movements, substantially surpassing existing tactile sensors in both directional flexibility and durability.
Application Category
📝 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.
Problem
Research questions and friction points this paper is trying to address.
tactile sensor
omnidirectional rolling
surface scanning
3D reconstruction
vision-based sensing
Innovation
Methods, ideas, or system contributions that make the work stand out.
omnidirectional rolling
vision-based tactile sensor
online 3D reconstruction
bearing layer design
normal force estimation
🔎 Similar Papers
No similar papers found.
