WSTac: Interactive Surface Perception based on Whisker-Inspired and Self-Illuminated Vision-Based Tactile Sensor

TL;DR

WStac is a novel self-illuminating visual tactile sensor inspired by whiskers, capable of ambient light resistance and performing various tactile tasks using machine learning on whisker contact data.

Contribution

Introduction of WStac, a self-illuminating VBTS with mechanoluminescent whiskers that eliminates the need for external LEDs and enhances ambient light resistance.

Findings

Successfully performs speed regression, directional identification, and texture classification.

Operates effectively under ambient light without additional lighting.

Uses machine learning to interpret whisker contact variations.

Abstract

Modern Visual-Based Tactile Sensors (VBTSs) use cost-effective cameras to track elastomer deformation, but struggle with ambient light interference. Solutions typically involve using internal LEDs and blocking external light, thus adding complexity. Creating a VBTS resistant to ambient light with just a camera and an elastomer remains a challenge. In this work, we introduce WStac, a self-illuminating VBTS comprising a mechanoluminescence (ML) whisker elastomer, camera, and 3D printed parts. The ML whisker elastomer, inspired by the touch sensitivity of vibrissae, offers both light isolation and high ML intensity under stress, thereby removing the necessity for additional LED modules. With the incorporation of machine learning, the sensor effectively utilizes the dynamic contact variations of 25 whiskers to successfully perform tasks like speed regression, directional identification, and texture classification. Videos are available at: https://sites.google.com/view/wstac/.