creators_name: Metta, Giorgio
creators_name: Fitzpatrick, Paul
editors_name: Prince, Christopher G.
editors_name: Demiris, Yiannis
editors_name: Marom, Yuval
editors_name: Kozima, Hideki
editors_name: Balkenius, Christian
type: confpaper
datestamp: 2003-10-04
lastmod: 2011-03-11 08:55:04
metadata_visibility: show
title: Better Vision Through Manipulation
ispublished: pub
subjects: comp-sci-mach-vis
subjects: comp-sci-art-intel
subjects: comp-sci-robot
full_text_status: public
keywords: manipulation, active vision, motion segmentation, optic flow, visual competence, neuroscience, robotics
abstract: For the purposes of manipulation, we would like to know what parts of the environment are physically coherent ensembles - that is, which parts will move together, and which are more or less independent. It takes a great deal of experience before this judgement can be made from purely visual information. This paper develops active strategies for acquiring that experience through experimental manipulation, using tight correlations between arm motion and optic flow to detect both the arm itself and the boundaries of objects with which it comes into contact. We argue that following causal chains of events out from the robot's body into the environment allows for a very natural developmental progression of visual competence, and relate this idea to results in neuroscience.
date: 2002
date_type: published
volume: 94
publisher: Lund University Cognitive Studies
pagerange: 97-104
refereed: TRUE
citation:   Metta, Giorgio and Fitzpatrick, Paul  (2002) Better Vision Through Manipulation.  [Conference Paper]     
document_url: http://cogprints.org/2520/1/Metta.pdf