Abstract
This paper introduces experiments of visual attention and learning of a mobile robot. The recurrent neural network (RNN) learns the sequence of events encountered during navigation incrementally as episodic memories so that the RNN can make prediction based on such sequences in the future. The visual module has two task processes to execute, namely object recognition and wall-following. Attention between these two tasks is switched by means of the top-down prediction made by the RNN. The strength of the top-down prediction acting on the vision processes is modulated dynamically using the measurement of learning status of the RNN. Our experimental results showed that the robot adapts to the environment in the course of dynamical interactions between its learning, attention and behavioral functions.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
J.J. Hopfield and D.W. Tank. Neural computation of decision in optimization problems. Biological Cybernetics, Vol. 52, pp. 141–152, 1985.
M.I. Jordan and D.E. Rumelhart. Forward models: supervised learning with a distal teacher. Cognitive Science, Vol. 16, pp. 307–354, 1992.
T. Kohonen. Self-organized formation of topographically correct feature maps. Biological Cybernetics, Vol. 43, pp. 59–69, 1982.
L.R. Squire, N.J. Cohen, and L. Nadel. The medial temporal region and memory consolidation: A new hypothesis. In H. Weingartner and E. Parker, editors, Memory consolidation, pp. 185–210. Erlbaum, Hillsdale, N.J., 1984.
J. Tani. Model-Based Learning for Mobile Robot Navigation from the Dynamical Systems Perspective. IEEE Trans. System, Man and Cybernetics Part B. Special issue on learning autonomous robots, Vol. 26, No. 3, pp. 421–436, 1996.
J. Tani, J. Yamamoto, and H. Nishi. Dynamical Interactions between Learning, Visual Attention, and Behavior. In P. Husbands and I. Harvey, editors, Proc. of the Fourth European Conf. of Artificial Life (ECAL'97). Cambridge, MA: MIT press, 1997.
L.G. Ungerleider and M. Mishkin. Two cortical visual systems. In D.G. Ingle, M.A. Goodale, and R.J. Mansfield, editors, Analysis of Visual Behavior. Cambridge, MA: MIT Press, 1982.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tani, J. (1997). Visual attention and learning of a cognitive robot. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020235
Download citation
DOI: https://doi.org/10.1007/BFb0020235
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive