Please use this identifier to cite or link to this item:

Speeding-Up the Learning of Saccade Control

Authors Antonelli, Marco View this author's profile
Durán, Angel J.
Chinellato, Eris
Del Pobil, Angel P.
Issue Date 2013
Source 2nd International Conference on Biomimetic and Biohybrid Systems: Living Machines, LM 2013, London, United Kingdom, 29 July-2 August 2013, Code 98028. Lecture Notes in Computer Science: Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics , v. 8064 LNAI, 2013, p. 12-23
Summary A saccade is a ballistic eye movement that allows the visual system to bring the target in the center of the visual field. For artificial vision systems, as in humanoid robotics, performing such a movement requires to know the intrinsic parameters of the camera. Parameters can be encoded in a bio-inspired fashion by a non-parametric model, that is trained during the movement of the camera. In this work, we propose a novel algorithm to speed-up the learning of saccade control in a goal-directed manner. During training, the algorithm computes the covariance matrix of the transformation and uses it to choose the most informative visual feature to gaze next. Results on a simulated model and on a real setup show that the proposed technique allows for a very efficient learning of goal-oriented saccade control. © 2013 Springer-Verlag Berlin Heidelberg.
ISSN 03029743
ISBN 978-364239801-8
Language English
Format Conference paper
Access View full-text via DOI
View full-text via Scopus