Active contour following to explore object shape with robot touch

Uriel Martinez-Hernandez, Giorgio Metta, Tony J. Dodd, Tony J. Prescott, Lorenzo Natale, Nathan F. Lepora

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

40 Citations (Scopus)

Abstract

In this work, we present an active tactile perception approach for contour following based on a probabilistic framework. Tactile data were collected using a biomimetic fingertip sensor. We propose a control architecture that implements a perception-action cycle for the exploratory procedure, which allows the fingertip to react to tactile contact whilst regulating the applied contact force. In addition' the fingertip is actively repositioned to an optimal position to ensure accurate perception. The method is trained off-line and then the testing performed on-line based on contour following around several different test shapes. We then implement object recognition based on the extracted shapes. Our active approach is compared with a passive approach, demonstrating that active perception is necessary for successful contour following and hence shape recognition.

Original languageEnglish
Title of host publication2013 World Haptics Conference, WHC 2013
Pages341-346
Number of pages6
DOIs
Publication statusPublished - 2013
Event2013 IEEE World Haptics Conference, WHC 2013 - Daejeon, Korea, Republic of
Duration: 14 Apr 201317 Apr 2013

Conference

Conference2013 IEEE World Haptics Conference, WHC 2013
CountryKorea, Republic of
CityDaejeon
Period14/04/1317/04/13

Keywords

  • active tactile perception
  • contour following
  • naive Bayes classifier
  • perception-action
  • robotic finger
  • tactile exploration

Fingerprint Dive into the research topics of 'Active contour following to explore object shape with robot touch'. Together they form a unique fingerprint.

Cite this