Abstract

This work presents a low-cost soft fingertip sensor for recognition of texture roughness. This sensor is designed with a soft rounded shape made of silicone rubber. An array of flexible piezo vibration elements, embedded in the sensor, measures vibrations while interacting with an object surface. The sensor is mounted on a robot arm for data collection with sliding exploratory procedures. The soft fingertip sensor is validated with roughness recognition of eight artificial textures using five different sliding directions (horizontal, vertical, left diagonal, right diagonal, square). The sensor uses four machine learning methods (KNN, SVM, ANN, CNN) for recognition and comparison processes. The tactile sensor can recognise textures with accuracies from 90.60% to 100% for different sliding directions and computational methods, where the horizontal sliding with SVM and KNN methods achieved the highest performance. This tactile sensor has the potential to extract surface properties for autonomous object exploration, recognition and manipulation tasks.

Original languageEnglish
Pages (from-to)1-4
Number of pages4
JournalIEEE Sensors Letters
Volume8
Issue number7
Early online date5 Jun 2024
DOIs
Publication statusPublished - 1 Jul 2024

Data Availability Statement

Data created in this research work is openly available from the University of Bath Research Data Archive at https://doi.org/10.15125/BATH-01351.

Keywords

  • Data collection
  • Manipulators
  • Robot sensing systems
  • Rough surfaces
  • Sensors
  • Surface roughness
  • Tactile sensors
  • Vibrations
  • machine learning
  • texture roughness recognition
  • vibration sensing

ASJC Scopus subject areas

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this