---
abstract: |-
We present experiments in which a group of autonomous mobile robots learn to perform fundamental sensor-motor tasks through a collaborative learning process. Behavioural strategies, i.e. motor responses to sensory stimuli, are encoded by means of genetic strings stored on the individual robots, and adapted through a genetic algorithm (Mitchell, 1998) executed by the entire robot collective: robots communicate their own strings and corresponding fitness to each other, and then execute a genetic algorithm to improve their individual behavioural strategy.
The robots acquired three different sensormotor competences, as well as the ability to select one of two, or one of three behaviours depending on context ("behaviour management"). Results show that fitness indeed increases with increasing learning time, and the analysis of the acquired behavioural strategies demonstrates that they are effective in accomplishing the desired task.
altloc:
- http://www.lucs.lu.se/ftp/pub/LUCS_Studies/LUCS94/Nehmzow.pdf
chapter: ~
commentary: ~
commref: ~
confdates: 'August 10-11, 2002'
conference: 'Second International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems'
confloc: 'Edinburgh, Scotland'
contact_email: ~
creators_id: []
creators_name:
- family: Nehmzow
given: Ulrich
honourific: ''
lineage: ''
date: 2002
date_type: published
datestamp: 2003-10-04
department: ~
dir: disk0/00/00/25/21
edit_lock_since: ~
edit_lock_until: ~
edit_lock_user: ~
editors_id: []
editors_name:
- family: Prince
given: Christopher G.
honourific: ''
lineage: ''
- family: Demiris
given: Yiannis
honourific: ''
lineage: ''
- family: Marom
given: Yuval
honourific: ''
lineage: ''
- family: Kozima
given: Hideki
honourific: ''
lineage: ''
- family: Balkenius
given: Christian
honourific: ''
lineage: ''
eprint_status: archive
eprintid: 2521
fileinfo: /style/images/fileicons/application_pdf.png;/2521/1/Nehmzow.pdf
full_text_status: public
importid: ~
institution: ~
isbn: ~
ispublished: pub
issn: ~
item_issues_comment: []
item_issues_count: 0
item_issues_description: []
item_issues_id: []
item_issues_reported_by: []
item_issues_resolved_by: []
item_issues_status: []
item_issues_timestamp: []
item_issues_type: []
keywords: 'mobile robots, collaborative learning, genetic algorithm, PEGA'
lastmod: 2011-03-11 08:55:04
latitude: ~
longitude: ~
metadata_visibility: show
note: ~
number: ~
pagerange: 115-123
pubdom: TRUE
publication: ~
publisher: Lund University Cognitive Studies
refereed: TRUE
referencetext: ~
relation_type: []
relation_uri: []
reportno: ~
rev_number: 12
series: ~
source: ~
status_changed: 2007-09-12 16:45:29
subjects:
- comp-sci-mach-learn
- comp-sci-art-intel
- comp-sci-robot
succeeds: ~
suggestions: ~
sword_depositor: ~
sword_slug: ~
thesistype: ~
title: 'Physically Embedded Genetic Algorithm Learning in Multi-Robot Scenarios: The PEGA algorithm'
type: confpaper
userid: 3507
volume: 94