Expectation-based selective attention for visual monitoring and control of a robot vehicle - Robotics Institute Carnegie Mellon University

Expectation-based selective attention for visual monitoring and control of a robot vehicle

Shumeet Baluja and Dean Pomerleau
Journal Article, Robotics and Autonomous Systems: Special Issue: Robot Learning: The New Wave, Vol. 22, No. 3, pp. 329 - 344, December, 1997

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.

BibTeX

@article{Baluja-1997-14536,
author = {Shumeet Baluja and Dean Pomerleau},
title = {Expectation-based selective attention for visual monitoring and control of a robot vehicle},
journal = {Robotics and Autonomous Systems: Special Issue: Robot Learning: The New Wave},
year = {1997},
month = {December},
volume = {22},
number = {3},
pages = {329 - 344},
}