Learning to Anticipate the Movements of Intermittently Occluded Objects
Author
Editor
- Christian Balkenius
Summary, in English
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.
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.
Department/s
Publishing year
2008
Language
English
Pages
54-60
Publication/Series
Proceedings of the Eighth International Conference on Epigenetic Robotics
Volume
139
Document type
Conference paper
Publisher
Lund University Cognitive Studies
Topic
- Computer Vision and Robotics (Autonomous Systems)
Conference name
Epigenetic Robotics
Conference date
2008-07-30
Conference place
Brighton, United Kingdom
Status
Published
Project
- From Reactive to Anticipatory Cognitive Embodied Systems
- Ikaros: An infrastructure for system level modelling of the brain
Research group
- Lund University Cognitive Science (LUCS)