On the dynamics of active categorisation of different objects shape through tactile sensors

Elio Tuci, Gianluca Massera, Stefano Nolfi

Research output: Chapter in Book/Report/Conference proceedingConference Proceeding (Non-Journal item)

143 Downloads (Pure)

Abstract

Active perception refers to a theoretical approach to thestudy of perception grounded on the idea that perceiving is a way ofacting, rather than a process whereby the brain constructs an internalrepresentation of the world. In this paper, we complement previousstudies by illustrating the operational principles of an active categorisationprocess in which a neuro-controlled anthropomorphic robotic arm,equipped with coarse-grained tactile sensors, is required to perceptuallycategorise spherical and ellipsoid objects.
Original languageEnglish
Title of host publicationAdvances in Artificial Life. Darwin Meets von Neumann
Subtitle of host publication10th European Conference, ECAL 2009, Budapest, Hungary, September 13-16, 2009, Revised Selected Papers, Part I
EditorsGeorge Kampis, István Karsai, Eörs Szathmáry
PublisherSpringer Nature
Pages124-131
ISBN (Electronic)978-3-642-21283-3
ISBN (Print)978-3-642-21282-6
DOIs
Publication statusPublished - 10 Sept 2009
Event10th European Conference, ECAL - Budapest, Hungary
Duration: 13 Sept 200916 Sept 2009

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
ISSN (Print)0302-9743

Conference

Conference10th European Conference, ECAL
Country/TerritoryHungary
CityBudapest
Period13 Sept 200916 Sept 2009

Keywords

  • Active perception
  • categorisation
  • evolutionary robotics

Fingerprint

Dive into the research topics of 'On the dynamics of active categorisation of different objects shape through tactile sensors'. Together they form a unique fingerprint.

Cite this