Material Recognition using Tactile Sensing

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Identification of the material from which an object is made is of signifi cant value for effective robotic grasping and manipulation. Characteristics of the material can be retrieved using different sensory modalities: vision based, tactile based or sound based. Compressibility, surface texture and thermal properties can each be retrieved from physical contact with an object using tactile sensors. This paper presents a method for collecting data using a biomimetic fingertip in contact with various materials and then using these data to classify the materials both individually and into groups of their type. Following acquisition of data, principal component analysis (PCA) is used to extract features. These features are used to train seven different class ers and hybrid structures of these classi ers for comparison. For all materials, the arti cial systems were evaluated against each other, compared with human performance and were all found to outperform human participants' average performance. These results highlighted the sensitive nature of the BioTAC sensors and pave the way for research that requires a sensitive and accurate approach such as vital signs monitoring using robotic systems.
LanguageEnglish
Pages94-111
JournalExpert Systems with Applications
Volume94
Early online date28 Oct 2017
DOIs
Publication statusPublished - 15 Mar 2018

Fingerprint

Robotics
Sensors
Biomimetics
Compressibility
Principal component analysis
Thermodynamic properties
Textures
Acoustic waves
Monitoring

Keywords

  • Tactile Sensing
  • Signal Processing
  • Neural Networks
  • Artificial Intelligence
  • Classification
  • Material classification

Cite this

@article{a463a99ef76646f68106c7f2598c8e71,
title = "Material Recognition using Tactile Sensing",
abstract = "Identification of the material from which an object is made is of signifi cant value for effective robotic grasping and manipulation. Characteristics of the material can be retrieved using different sensory modalities: vision based, tactile based or sound based. Compressibility, surface texture and thermal properties can each be retrieved from physical contact with an object using tactile sensors. This paper presents a method for collecting data using a biomimetic fingertip in contact with various materials and then using these data to classify the materials both individually and into groups of their type. Following acquisition of data, principal component analysis (PCA) is used to extract features. These features are used to train seven different class ers and hybrid structures of these classi ers for comparison. For all materials, the arti cial systems were evaluated against each other, compared with human performance and were all found to outperform human participants' average performance. These results highlighted the sensitive nature of the BioTAC sensors and pave the way for research that requires a sensitive and accurate approach such as vital signs monitoring using robotic systems.",
keywords = "Tactile Sensing, Signal Processing, Neural Networks, Artificial Intelligence, Classification, Material classification",
author = "Emmett Kerr and T.Martin McGinnity and SA Coleman",
year = "2018",
month = "3",
day = "15",
doi = "10.1016/j.eswa.2017.10.045",
language = "English",
volume = "94",
pages = "94--111",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier",

}

Material Recognition using Tactile Sensing. / Kerr, Emmett; McGinnity, T.Martin; Coleman, SA.

In: Expert Systems with Applications, Vol. 94, 15.03.2018, p. 94-111.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Material Recognition using Tactile Sensing

AU - Kerr, Emmett

AU - McGinnity, T.Martin

AU - Coleman, SA

PY - 2018/3/15

Y1 - 2018/3/15

N2 - Identification of the material from which an object is made is of signifi cant value for effective robotic grasping and manipulation. Characteristics of the material can be retrieved using different sensory modalities: vision based, tactile based or sound based. Compressibility, surface texture and thermal properties can each be retrieved from physical contact with an object using tactile sensors. This paper presents a method for collecting data using a biomimetic fingertip in contact with various materials and then using these data to classify the materials both individually and into groups of their type. Following acquisition of data, principal component analysis (PCA) is used to extract features. These features are used to train seven different class ers and hybrid structures of these classi ers for comparison. For all materials, the arti cial systems were evaluated against each other, compared with human performance and were all found to outperform human participants' average performance. These results highlighted the sensitive nature of the BioTAC sensors and pave the way for research that requires a sensitive and accurate approach such as vital signs monitoring using robotic systems.

AB - Identification of the material from which an object is made is of signifi cant value for effective robotic grasping and manipulation. Characteristics of the material can be retrieved using different sensory modalities: vision based, tactile based or sound based. Compressibility, surface texture and thermal properties can each be retrieved from physical contact with an object using tactile sensors. This paper presents a method for collecting data using a biomimetic fingertip in contact with various materials and then using these data to classify the materials both individually and into groups of their type. Following acquisition of data, principal component analysis (PCA) is used to extract features. These features are used to train seven different class ers and hybrid structures of these classi ers for comparison. For all materials, the arti cial systems were evaluated against each other, compared with human performance and were all found to outperform human participants' average performance. These results highlighted the sensitive nature of the BioTAC sensors and pave the way for research that requires a sensitive and accurate approach such as vital signs monitoring using robotic systems.

KW - Tactile Sensing

KW - Signal Processing

KW - Neural Networks

KW - Artificial Intelligence

KW - Classification

KW - Material classification

U2 - 10.1016/j.eswa.2017.10.045

DO - 10.1016/j.eswa.2017.10.045

M3 - Article

VL - 94

SP - 94

EP - 111

JO - Expert Systems with Applications

T2 - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -