Learning to Anticipate the Movements of Intermittently Occluded Objects

Johansson, B; Balkenius, C

Learning to Anticipate the Movements of Intermittently Occluded Objects

Johansson, B Balkenius, C

Permalink

Publisher:: LUCS (Lund University Cognitive Sciences)
Publication Type:: Conference Proceeding
Citation:: Proceedings of the Eighth International Conference on Epigenetic Robotics, 2008, pp. 53 - 60
Issue Date:: 2008-01

Closed Access

	Filename	Description	Size
	2009003288OK.pdf		749.91 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Johansson, B	en_US
dc.contributor.author	Balkenius, C	en_US
dc.contributor.editor	Schlesinger, M	en_US
dc.contributor.editor	Berthouze, L	en_US
dc.contributor.editor	Balkenius, C	en_US
dc.date	2008-07-30	en_US
dc.date.issued	2008-01	en_US
dc.identifier.citation	Proceedings of the Eighth International Conference on Epigenetic Robotics, 2008, pp. 53 - 60	en_US
dc.identifier.issn	1101-8453	en_US
dc.identifier.uri	http://hdl.handle.net/10453/12078
dc.description.abstract	A model of event driven anticipatory learning is described and applied to a number of attention situations where one or several visual targets need to be tracked while being intermittently occluded. The model combines covert tracking of multiple targets with overt control of a single attention focus. The implemented system has been applied to both a simple scenario with a car that is occluded in a tunnel and a complex situation with six simulated robots that need to anticipate the movements of each other. The system is shown to learn very quickly to anticipate target movements. The performance is further increased when the simulated robots are allowed to cooperate in the tracking task.	en_US
dc.publisher	LUCS (Lund University Cognitive Sciences)	en_US
dc.relation.ispartof	Proceedings of the Eighth International Conference on Epigenetic Robotics	en_US
dc.relation.ispartof	International Conference on Epigenetic Robotics	en_US
dc.title	Learning to Anticipate the Movements of Intermittently Occluded Objects	en_US
dc.type	Conference Proceeding
utslib.location	Sweden	en_US
utslib.location.activity	Brighton, UK	en_US
utslib.for	170299 Cognitive Sciences Not Elsewhere Classified	en_US
dc.location.activity	Brighton, UK	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.consider-herdc	false	en_US
pubs.place-of-publication	Sweden	en_US
pubs.start-date	2008-07-30	en_US

Abstract:

A model of event driven anticipatory learning is described and applied to a number of attention situations where one or several visual targets need to be tracked while being intermittently occluded. The model combines covert tracking of multiple targets with overt control of a single attention focus. The implemented system has been applied to both a simple scenario with a car that is occluded in a tunnel and a complex situation with six simulated robots that need to anticipate the movements of each other. The system is shown to learn very quickly to anticipate target movements. The performance is further increased when the simulated robots are allowed to cooperate in the tracking task.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/12078