A Multi-modal Approach to Continuous Material Identification through Tactile Sensing

Augusto Gomez Eguiluz, Ignacio Rano, SA Coleman, Martin McGinnity

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Tactile sensing has recently been used in robotics for object identification, grasping, and material recognition. Most material recognition approaches use vibration information from a tactile exploration, typically above one second long, to identify the material. This work proposes a tactile multi- modal (vibration and thermal) material identification approach based on recursive Bayesian estimation. Through the frequency response of the vibration induced by the material and thermal features, like an estimate of the thermal power loss of the finger, we show that it is possible to identify materials in less than half a second. Moreover, a comparison between the use of vibration only and multi-modal identification shows that both recognition time and classification errors are reduced by adding thermal information.
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages6
Publication statusAccepted/In press - 1 Jul 2016
EventIEEE/RSJ International Conference on intelligent Robots and Systems, 2016 - Daejeon, Korea
Duration: 1 Jul 2016 → …

Conference

ConferenceIEEE/RSJ International Conference on intelligent Robots and Systems, 2016
Period1/07/16 → …

Fingerprint

Frequency response
Identification (control systems)
Robotics
Hot Temperature

Keywords

  • Robotics
  • Tactile Sensing
  • Material identification

Cite this

Gomez Eguiluz, A., Rano, I., Coleman, SA., & McGinnity, M. (Accepted/In press). A Multi-modal Approach to Continuous Material Identification through Tactile Sensing. In Unknown Host Publication
@inproceedings{759b18cb6d6c4494b7995fddd653665a,
title = "A Multi-modal Approach to Continuous Material Identification through Tactile Sensing",
abstract = "Tactile sensing has recently been used in robotics for object identification, grasping, and material recognition. Most material recognition approaches use vibration information from a tactile exploration, typically above one second long, to identify the material. This work proposes a tactile multi- modal (vibration and thermal) material identification approach based on recursive Bayesian estimation. Through the frequency response of the vibration induced by the material and thermal features, like an estimate of the thermal power loss of the finger, we show that it is possible to identify materials in less than half a second. Moreover, a comparison between the use of vibration only and multi-modal identification shows that both recognition time and classification errors are reduced by adding thermal information.",
keywords = "Robotics, Tactile Sensing, Material identification",
author = "{Gomez Eguiluz}, Augusto and Ignacio Rano and SA Coleman and Martin McGinnity",
year = "2016",
month = "7",
day = "1",
language = "English",
booktitle = "Unknown Host Publication",

}

Gomez Eguiluz, A, Rano, I, Coleman, SA & McGinnity, M 2016, A Multi-modal Approach to Continuous Material Identification through Tactile Sensing. in Unknown Host Publication. IEEE/RSJ International Conference on intelligent Robots and Systems, 2016, 1/07/16.

A Multi-modal Approach to Continuous Material Identification through Tactile Sensing. / Gomez Eguiluz, Augusto; Rano, Ignacio; Coleman, SA; McGinnity, Martin.

Unknown Host Publication. 2016.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A Multi-modal Approach to Continuous Material Identification through Tactile Sensing

AU - Gomez Eguiluz, Augusto

AU - Rano, Ignacio

AU - Coleman, SA

AU - McGinnity, Martin

PY - 2016/7/1

Y1 - 2016/7/1

N2 - Tactile sensing has recently been used in robotics for object identification, grasping, and material recognition. Most material recognition approaches use vibration information from a tactile exploration, typically above one second long, to identify the material. This work proposes a tactile multi- modal (vibration and thermal) material identification approach based on recursive Bayesian estimation. Through the frequency response of the vibration induced by the material and thermal features, like an estimate of the thermal power loss of the finger, we show that it is possible to identify materials in less than half a second. Moreover, a comparison between the use of vibration only and multi-modal identification shows that both recognition time and classification errors are reduced by adding thermal information.

AB - Tactile sensing has recently been used in robotics for object identification, grasping, and material recognition. Most material recognition approaches use vibration information from a tactile exploration, typically above one second long, to identify the material. This work proposes a tactile multi- modal (vibration and thermal) material identification approach based on recursive Bayesian estimation. Through the frequency response of the vibration induced by the material and thermal features, like an estimate of the thermal power loss of the finger, we show that it is possible to identify materials in less than half a second. Moreover, a comparison between the use of vibration only and multi-modal identification shows that both recognition time and classification errors are reduced by adding thermal information.

KW - Robotics

KW - Tactile Sensing

KW - Material identification

M3 - Conference contribution

BT - Unknown Host Publication

ER -