Learning to Anticipate the Movements of Intermittently Occluded Objects
(2008) Epigenetic Robotics 139. p.54-60- 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... (More) - 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. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/1362038
- author
- Johansson, Birger LU and Balkenius, Christian LU
- organization
- publishing date
- 2008
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Proceedings of the Eighth International Conference on Epigenetic Robotics
- editor
- Balkenius, Christian
- volume
- 139
- pages
- 54 - 60
- publisher
- Lund University Cognitive Studies
- conference name
- Epigenetic Robotics
- conference location
- Brighton, United Kingdom
- conference dates
- 2008-07-30
- project
- From Reactive to Anticipatory Cognitive Embodied Systems
- Ikaros: An infrastructure for system level modelling of the brain
- language
- English
- LU publication?
- yes
- id
- eb656005-60b0-4d65-97dc-0e0623365cbf (old id 1362038)
- date added to LUP
- 2016-04-04 11:27:28
- date last changed
- 2019-09-06 02:18:17
@inproceedings{eb656005-60b0-4d65-97dc-0e0623365cbf, abstract = {{A model of event driven anticipatory learning is described and applied to a number of<br/><br> attention situations where one or several visual<br/><br> targets need to be tracked while being<br/><br> intermittently occluded. The model combines<br/><br> covert tracking of multiple targets with overt<br/><br> control of a single attention focus. The implemented<br/><br> system has been applied to both a<br/><br> simple scenario with a car that is occluded in a<br/><br> tunnel and a complex situation with six simulated<br/><br> robots that need to anticipate the movements<br/><br> of each other. The system is shown to<br/><br> learn very quickly to anticipate target movements.<br/><br> The performance is further increased<br/><br> when the simulated robots are allowed to cooperate<br/><br> in the tracking task.}}, author = {{Johansson, Birger and Balkenius, Christian}}, booktitle = {{Proceedings of the Eighth International Conference on Epigenetic Robotics}}, editor = {{Balkenius, Christian}}, language = {{eng}}, pages = {{54--60}}, publisher = {{Lund University Cognitive Studies}}, title = {{Learning to Anticipate the Movements of Intermittently Occluded Objects}}, volume = {{139}}, year = {{2008}}, }