creators_name: Olsson, Lars
creators_name: Nehaniv, Chrystopher L.
creators_name: Polani, Daniel
editors_name: Berthouze, Luc
editors_name: Kaplan, Frédéric
editors_name: Kozima, Hideki
editors_name: Yano, Hiroyuki
editors_name: Konczak, Jürgen
editors_name: Metta, Giorgio
editors_name: Nadel, Jacqueline
editors_name: Sandini, Giulio
editors_name: Stojanov, Georgi
editors_name: Balkenius, Christian
type: confpaper
datestamp: 2006-07-23
lastmod: 2011-03-11 08:56:29
metadata_visibility: show
title: Discovering Motion Flow by
Temporal-Informational Correlations in Sensors
ispublished: pub
subjects: comp-sci-stat-model
subjects: comp-sci-mach-learn
subjects: comp-sci-robot
full_text_status: public
keywords: motion flow, information distance, sensor correlation, sensor adaptation, AIBO robot, RobotCub
abstract: A method is presented for adapting the sensors
of a robot to its current environment and
to learn motion flow detection by observing
the informational relations between sensors
and actuators. Examples are shown where
the robot learns to detect motion flow from
sensor data generated by its own movement.
date: 2005
date_type: published
volume: 123
publisher: Lund University Cognitive Studies
pagerange: 117-120
refereed: TRUE
citation:   Olsson, Lars and Nehaniv, Chrystopher L. and Polani, Daniel  (2005) Discovering Motion Flow by Temporal-Informational Correlations in Sensors.  [Conference Paper]     
document_url: http://cogprints.org/4983/1/olsson.pdf