Object texture recognition by dynamic tactile sensing using active exploration

Alin Drimus, Mikkel Børlum Petersen, Arne Bilberg

Publikation: Konferencebidrag uden forlag/tidsskriftPaperForskningpeer review

Resumé

For both humans and robots, tactile sensing is
important for interaction with the environment: it is the core
sensing used for exploration and manipulation of objects. In
this paper, we present a method for determining object texture
by active exploration with a robotic fingertip equipped with
a dynamic tactile transducer based on polyvinylidene fluoride
(PVDF) piezoelectric film. Different test surfaces are actively
explored and the signal from the sensor is used for feature
extraction, which is subsequently used for classification. A
comparison between the significance of different extracted
features and performance of learning algorithms is done and the
best method is further used to classify objects by their surface
textures with recognition results higher than 90 percent.
OriginalsprogEngelsk
Publikationsdatosep. 2012
Antal sider7
StatusUdgivet - sep. 2012
BegivenhedRo-Man '12: 21st IEEE International Symposium on Robot and Human Interactive Communication - Paris, Frankrig
Varighed: 10. sep. 201213. sep. 2012

Konference

KonferenceRo-Man '12
LandFrankrig
ByParis
Periode10/09/201213/09/2012

Fingeraftryk

Learning algorithms
Transducers
Robotics
Textures
Robots
Sensors

Bibliografisk note

Paper presented at RO-MAN 2012, IEEE International Symposium on Robot and Human Interactive Communication, Sept. 2012, Paris, France

Citer dette

Drimus, A., Børlum Petersen, M., & Bilberg, A. (2012). Object texture recognition by dynamic tactile sensing using active exploration. Paper præsenteret på Ro-Man '12, Paris, Frankrig.
Drimus, Alin ; Børlum Petersen, Mikkel ; Bilberg, Arne. / Object texture recognition by dynamic tactile sensing using active exploration. Paper præsenteret på Ro-Man '12, Paris, Frankrig.7 s.
@conference{2e4477cf38254242b636eb69a46889ae,
title = "Object texture recognition by dynamic tactile sensing using active exploration",
abstract = "For both humans and robots, tactile sensing isimportant for interaction with the environment: it is the coresensing used for exploration and manipulation of objects. Inthis paper, we present a method for determining object textureby active exploration with a robotic fingertip equipped witha dynamic tactile transducer based on polyvinylidene fluoride(PVDF) piezoelectric film. Different test surfaces are activelyexplored and the signal from the sensor is used for featureextraction, which is subsequently used for classification. Acomparison between the significance of different extractedfeatures and performance of learning algorithms is done and thebest method is further used to classify objects by their surfacetextures with recognition results higher than 90 percent.",
keywords = "active exploration, object recognition, piezoelectric sensors",
author = "Alin Drimus and {B{\o}rlum Petersen}, Mikkel and Arne Bilberg",
note = "Paper presented at RO-MAN 2012, IEEE International Symposium on Robot and Human Interactive Communication, Sept. 2012, Paris, France; Ro-Man '12 : 21st IEEE International Symposium on Robot and Human Interactive Communication ; Conference date: 10-09-2012 Through 13-09-2012",
year = "2012",
month = "9",
language = "English",

}

Drimus, A, Børlum Petersen, M & Bilberg, A 2012, 'Object texture recognition by dynamic tactile sensing using active exploration', Paper fremlagt ved Ro-Man '12, Paris, Frankrig, 10/09/2012 - 13/09/2012.

Object texture recognition by dynamic tactile sensing using active exploration. / Drimus, Alin; Børlum Petersen, Mikkel; Bilberg, Arne.

2012. Paper præsenteret på Ro-Man '12, Paris, Frankrig.

Publikation: Konferencebidrag uden forlag/tidsskriftPaperForskningpeer review

TY - CONF

T1 - Object texture recognition by dynamic tactile sensing using active exploration

AU - Drimus, Alin

AU - Børlum Petersen, Mikkel

AU - Bilberg, Arne

N1 - Paper presented at RO-MAN 2012, IEEE International Symposium on Robot and Human Interactive Communication, Sept. 2012, Paris, France

PY - 2012/9

Y1 - 2012/9

N2 - For both humans and robots, tactile sensing isimportant for interaction with the environment: it is the coresensing used for exploration and manipulation of objects. Inthis paper, we present a method for determining object textureby active exploration with a robotic fingertip equipped witha dynamic tactile transducer based on polyvinylidene fluoride(PVDF) piezoelectric film. Different test surfaces are activelyexplored and the signal from the sensor is used for featureextraction, which is subsequently used for classification. Acomparison between the significance of different extractedfeatures and performance of learning algorithms is done and thebest method is further used to classify objects by their surfacetextures with recognition results higher than 90 percent.

AB - For both humans and robots, tactile sensing isimportant for interaction with the environment: it is the coresensing used for exploration and manipulation of objects. Inthis paper, we present a method for determining object textureby active exploration with a robotic fingertip equipped witha dynamic tactile transducer based on polyvinylidene fluoride(PVDF) piezoelectric film. Different test surfaces are activelyexplored and the signal from the sensor is used for featureextraction, which is subsequently used for classification. Acomparison between the significance of different extractedfeatures and performance of learning algorithms is done and thebest method is further used to classify objects by their surfacetextures with recognition results higher than 90 percent.

KW - active exploration

KW - object recognition

KW - piezoelectric sensors

M3 - Paper

ER -

Drimus A, Børlum Petersen M, Bilberg A. Object texture recognition by dynamic tactile sensing using active exploration. 2012. Paper præsenteret på Ro-Man '12, Paris, Frankrig.