Material Classification based on Thermal and Surface Texture Properties Evaluated against Human Performance

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

8 Citations (Scopus)

Abstract

Effective robotic grasping and manipulation requires knowledge about the surface properties of an object and the environment in which it is located. Physical contact with materials using tactile sensors can enable the retrieval of detailed information about the material, i.e. compressibility, surface texture and thermal properties. This paper describes a system used to classify a wide range of materials based on their thermal properties and surface texture. Following acquisition of data from a sophisticated tactile sensor, the system uses principal component analysis (PCA) to extract features from the data which are used to train an Artificial Neural Network (ANN) to classify materials, first into groups and then as individual materials. The system is compared with human performance and the results demonstrate that the proposed system performed better than humans by almost 10%.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages444-449
Number of pages6
Publication statusPublished - 10 Dec 2014
Event13th International Conference on Control, Automation, Robotics & Vision - Singapore
Duration: 10 Dec 2014 → …

Conference

Conference13th International Conference on Control, Automation, Robotics & Vision
Period10/12/14 → …

Fingerprint

Textures
Thermodynamic properties
Sensors
Compressibility
Principal component analysis
Surface properties
Robotics
Hot Temperature
Neural networks

Cite this

@inproceedings{98b1d4c53ee646cf9a63886e2661b676,
title = "Material Classification based on Thermal and Surface Texture Properties Evaluated against Human Performance",
abstract = "Effective robotic grasping and manipulation requires knowledge about the surface properties of an object and the environment in which it is located. Physical contact with materials using tactile sensors can enable the retrieval of detailed information about the material, i.e. compressibility, surface texture and thermal properties. This paper describes a system used to classify a wide range of materials based on their thermal properties and surface texture. Following acquisition of data from a sophisticated tactile sensor, the system uses principal component analysis (PCA) to extract features from the data which are used to train an Artificial Neural Network (ANN) to classify materials, first into groups and then as individual materials. The system is compared with human performance and the results demonstrate that the proposed system performed better than humans by almost 10{\%}.",
author = "Emmett Kerr and TM McGinnity and SA Coleman",
year = "2014",
month = "12",
day = "10",
language = "English",
isbn = "978-1-4799-5199-4/14",
pages = "444--449",
booktitle = "Unknown Host Publication",

}

Kerr, E, McGinnity, TM & Coleman, SA 2014, Material Classification based on Thermal and Surface Texture Properties Evaluated against Human Performance. in Unknown Host Publication. pp. 444-449, 13th International Conference on Control, Automation, Robotics & Vision, 10/12/14.

Material Classification based on Thermal and Surface Texture Properties Evaluated against Human Performance. / Kerr, Emmett; McGinnity, TM; Coleman, SA.

Unknown Host Publication. 2014. p. 444-449.

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

TY - GEN

T1 - Material Classification based on Thermal and Surface Texture Properties Evaluated against Human Performance

AU - Kerr, Emmett

AU - McGinnity, TM

AU - Coleman, SA

PY - 2014/12/10

Y1 - 2014/12/10

N2 - Effective robotic grasping and manipulation requires knowledge about the surface properties of an object and the environment in which it is located. Physical contact with materials using tactile sensors can enable the retrieval of detailed information about the material, i.e. compressibility, surface texture and thermal properties. This paper describes a system used to classify a wide range of materials based on their thermal properties and surface texture. Following acquisition of data from a sophisticated tactile sensor, the system uses principal component analysis (PCA) to extract features from the data which are used to train an Artificial Neural Network (ANN) to classify materials, first into groups and then as individual materials. The system is compared with human performance and the results demonstrate that the proposed system performed better than humans by almost 10%.

AB - Effective robotic grasping and manipulation requires knowledge about the surface properties of an object and the environment in which it is located. Physical contact with materials using tactile sensors can enable the retrieval of detailed information about the material, i.e. compressibility, surface texture and thermal properties. This paper describes a system used to classify a wide range of materials based on their thermal properties and surface texture. Following acquisition of data from a sophisticated tactile sensor, the system uses principal component analysis (PCA) to extract features from the data which are used to train an Artificial Neural Network (ANN) to classify materials, first into groups and then as individual materials. The system is compared with human performance and the results demonstrate that the proposed system performed better than humans by almost 10%.

M3 - Conference contribution

SN - 978-1-4799-5199-4/14

SP - 444

EP - 449

BT - Unknown Host Publication

ER -