title: Discovering Motion Flow by Temporal-Informational Correlations in Sensors
creator: Olsson, Lars
creator: Nehaniv, Chrystopher L.
creator: Polani, Daniel
subject: Statistical Models
subject: Machine Learning
subject: Robotics
description: 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.
publisher: Lund University Cognitive Studies
contributor: Berthouze, Luc
contributor: Kaplan, Frédéric
contributor: Kozima, Hideki
contributor: Yano, Hiroyuki
contributor: Konczak, Jürgen
contributor: Metta, Giorgio
contributor: Nadel, Jacqueline
contributor: Sandini, Giulio
contributor: Stojanov, Georgi
contributor: Balkenius, Christian
date: 2005
type: Conference Paper
type: PeerReviewed
format: application/pdf
identifier: http://cogprints.org/4983/1/olsson.pdf
identifier:   Olsson, Lars and Nehaniv, Chrystopher L. and Polani, Daniel  (2005) Discovering Motion Flow by Temporal-Informational Correlations in Sensors.  [Conference Paper]     
relation: http://cogprints.org/4983/