Object texture recognition by dynamic tactile sensing using active exploration

Alin Drimus, Mikkel Børlum Petersen, Arne Bilberg

Research output: Contribution to conference without publisher/journalPaperResearchpeer-review

Abstract

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.
Original languageEnglish
Publication dateSep 2012
Number of pages7
Publication statusPublished - Sep 2012
EventRo-Man '12: 21st IEEE International Symposium on Robot and Human Interactive Communication - Paris, France
Duration: 10. Sep 201213. Sep 2012

Conference

ConferenceRo-Man '12
Country/TerritoryFrance
CityParis
Period10/09/201213/09/2012

Bibliographical note

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

Keywords

  • active exploration
  • object recognition
  • piezoelectric sensors

Fingerprint

Dive into the research topics of 'Object texture recognition by dynamic tactile sensing using active exploration'. Together they form a unique fingerprint.

Cite this