DMCA
APES: ATTENTIVELY PERCEIVING ROBOT (2006)
| Venue: | AUTONOMOUS ROBOTS |
| Citations: | 4 - 0 self |
BibTeX
@MISC{Soyer06apes:attentively,
author = {Ç. Soyer and H. I. Bozma and Y. İstefanopulos},
title = {APES: ATTENTIVELY PERCEIVING ROBOT},
year = {2006}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Robot vision systems- inspired by human-like vision- are required to employ mechanisms similar to those that have proven to be crucial in human visual performance. One of these mechanisms is attentive perception. Findings from vision science research suggest that attentive perception requires a multitude of properties: A retina with fovea-periphery distinction, an attention mechanism that can be manipulated both mechanically and internally, an extensive set of visual primitives that enable different representation modes, an integration mechanism that can infer the appropriate visual information in spite of eye, head, body and target motion, and finally memory for guiding eye movements and modeling the environment. In this paper we present an attentively “perceiving” robot called APES. The novelty of this system stems from the fact that it incorporates all of these properties simultaneously. As is explained, original approaches have to be taken to realize each of the properties so that they can be integrated together in an attentive perception framework.
Keyphrases
attentively perceiving robot attentive perception attentive perception framework vision science research appropriate visual information robot vision system integration mechanism human-like vision extensive set eye movement fovea-periphery distinction different representation mode original approach human visual performance target motion attention mechanism visual primitive
