creators_name: Warnett, Lawrence
creators_name: McGonigle, Brendan
editors_name: Prince, Christopher G.
editors_name: Demiris, Yiannis
editors_name: Marom, Yuval
editors_name: Kozima, Hideki
editors_name: Balkenius, Christian
type: confposter
datestamp: 2003-10-04
lastmod: 2011-03-11 08:55:04
metadata_visibility: show
title: Unsupervised navigation using an economy principle
ispublished: pub
subjects: comp-sci-mach-learn
subjects: comp-sci-art-intel
subjects: comp-sci-robot
full_text_status: public
keywords: robot navigation, learning, self-selection, behavioural adaptation
abstract: We describe robot navigation learning based on self-selection of privileged vectors through the environment in accordance with an in built economy metric. This provides the opportunity both for progressive behavioural adaptation, and adaptive derivations, leading, through situated activity, to “representations" of the environment which are both economically attained and inherently meaningful to the agent.
date: 2002
date_type: published
volume: 94
publisher: Lund University Cognitive Studies
pagerange: 159-162
refereed: TRUE
citation:   Warnett, Lawrence and McGonigle, Brendan  (2002) Unsupervised navigation using an economy principle.  [Conference Poster]     
document_url: http://cogprints.org/2529/1/Warnett.pdf