ICRA'09 Paper Abstract


Paper FrB10.4

Borji, Ali (Institute for Research in Fundamental Sciences,(IPM)), Nili Ahmadabadi, Majid (University of Tehran), Nadjar Araabi, Babak (University of Tehran)

Learning Sequential Visual Attention Control through Dynamic State Space Discretization

Scheduled for presentation during the Regular Sessions "Visual Navigation - I" (FrB10), Friday, May 15, 2009, 11:30−11:50, Room: 502

2009 IEEE International Conference on Robotics and Automation, May 12 - 17, 2009, Kobe, Japan

This information is tentative and subject to change. Compiled on January 21, 2022

Keywords Visual Navigation, Recognition, Computer Vision for Robotics and Automation


Similar to humans and primates, artificial creatures like robots are limited in terms of allocation of their resources to huge sensory and perceptual information. Serial processing mechanisms used in the design of such creatures demands engineering attentional control mechanisms. In this paper, we present a new algorithm for learning top-down sequential visual attention control for agents acting in interactive environments. Our method is based on the key idea, that attention can be learned best in concert with visual representations through automatic construction and discretization of the visual state space. The tree representing the top-down attention is incrementally refined whenever aliasing occurs by selecting the most appropriate saccadic direction. The proposed approach is evaluated on action-based object recognition and urban navigation tasks, where obtained results support applicability and usefulness of developed saccade movement method for robotics.



Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2022 PaperCept, Inc.
Page generated 2022-01-21  08:47:05 PST  Terms of use