title: Better Vision Through Manipulation
creator: Metta, Giorgio
creator: Fitzpatrick, Paul
subject: Machine Vision
subject: Artificial Intelligence
subject: Robotics
description: 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.
publisher: Lund University Cognitive Studies
contributor: Prince, Christopher G.
contributor: Demiris, Yiannis
contributor: Marom, Yuval
contributor: Kozima, Hideki
contributor: Balkenius, Christian
date: 2002
type: Conference Paper
type: PeerReviewed
format: application/pdf
identifier: http://cogprints.org/2520/1/Metta.pdf
identifier:   Metta, Giorgio and Fitzpatrick, Paul  (2002) Better Vision Through Manipulation.  [Conference Paper]     
relation: http://cogprints.org/2520/