Paper Info
Title
Expectation-based selective attention for visual monitoring and control of a robot vehicle
Abstract
Reliable vision-based control of an autonomous vehicle requires the ability to focus attention on the important features in an input scene. Previous work with an autonomous lane following system, ALVINN (Pomerleau, 1993), has yielded good results in uncluttered conditions. This paper presents an artificial neural network based learning approach for handling difficult scenes which will confuse the ALVINN system. This work presents a mechanism for achieving task-specific focus of attention by exploiting temporal coherence. A saliency map, which is based upon a computed expectation of the contents of the inputs in the next time step, indicates which regions of the input retina are important for performing the task. The saliency map can be used to accentuate the features which are important for the task, and de-emphasize those which are not.
Year
DOI
Venue
1997
10.1016/S0921-8890(97)00046-8
ROBOTICS AND AUTONOMOUS SYSTEMS
Keywords
Field
DocType
expectation-based selective attention,Autonomous navigation,temporal coherence,saliency map,artificial neural networks
Computer vision,Computer science,Simulation,Image processing,Coherence (physics),Selective attention,Autonomous system (mathematics),Artificial intelligence,Artificial neural network,Robot,Visual monitoring,Robotics
Journal
Volume
Issue
ISSN
22
3-4
0921-8890
Citations 
PageRank 
References 
28
80.99
7
Authors
2
Name
Order
Citations
PageRank
Shumeet Baluja14053728.83
Dean Pomerleau21039283.23