Interactive Surface Perception based on Whisker-Inspired and Self-Illuminated Vision-Based Tactile Sensor
Author:
Kai Chong Lei*, Kit Wa Sou*, Wang Sing Chan, Jiayi Yan, Siqi Ping, Dengfeng Peng, Wenbo Ding+, Xiao-Ping Zhang
* Kai Chong Lei and Kit Wa Sou contributed equally to this work.
+ Wenbo Ding is the corresponding author.
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.
Keywords:
Visual-Based Tactile Sensor
Mechanoluminescence
Sensor Data Processing
Interactive Perception
Introductory Video (with audio)
6 minutes
Project Highlights
A novel sensor hardware design for VBTS, using only a camera and elastomer, immune to ambient light interference.
Biomimetically-inspired tri-layered whisker array composite elastomer enables ML for dynamic tactile perception in open environments.
A real-time algorithm using a novel feature extraction technique for VBTS, lowering computational cost by reducing complexity.
Qualitative and quantitative results indicate outstanding performance of the WSTac on speed regression, directional identification, and texture classification.
Supplementary Information
ML Whisker array Testing 1
Slide over ML Whisker array with glass rod
ML Whisker array Testing 2
Let the ML Whisker array slide across the desktop
Preliminary Experiments 1
Film stretching test
(Sorta Clear 37 film with ZnS:Cu)
WSTac Demo 1
Human finger interacting with WSTac
WSTac Demo 2
Film stretching test (Sorta Clear 37 film with ZnS:Cu)
arXiv
https://arxiv.org/abs/2308.13241
Bibtex
@article{lei2023wstac,
title={WSTac: Interactive Surface Perception based on Whisker-Inspired and Self-Illuminated Vision-Based Tactile Sensor},
author={Lei, Kai Chong and Sou, Kit Wa and Chan, Wang Sing and Yan, Jiayi and Ping, Siqi and Peng, Dengfeng and Ding, Wenbo and Zhang, Xiao-Ping},
journal={arXiv preprint arXiv:2308.13241},
year={2023}
}