DocumentCode :
2711133
Title :
Emergence of perceptual states in nonlinear lattices: A new computational model for perception
Author :
Arena, Paolo ; Fiore, Sebastiano De ; Lombardo, Davide ; Patane, Luca
Author_Institution :
Dipt. di Ing. Elettr., Elettron. e dei Sist., Univ. degli Studi di Catania, Catania, Italy
fYear :
2009
fDate :
14-19 June 2009
Firstpage :
191
Lastpage :
198
Abstract :
Insects show the ability to react to certain stimuli with simple reflexes using direct sensory-motor pathways, which can be considered as basic behaviors, while high brain regions provide secondary pathway allowing the emergence of a cognitive behavior which modulates the basic abilities. Taking inspiration from this evidence, a new general purpose perceptual control architecture is briefly presented and experimentally applied to a rover navigating in a cluttered environment. The core of the architecture is constituted by the representation layer, where different stimuli, triggering competitive reflexes, are fused to form a unique abstract picture of the environment. Each representation induces a learnable modulation of the basic behaviors in order to determine the robot overall behavior. The representation is formalized by means of reaction-diffusion nonlinear partial differential equations, under the paradigm of the cellular neural networks (CNNs), whose dynamics converges to steady-state Turing patterns. A suitable unsupervised learning leads to the shaping of the basins of attraction of the Turing patterns that, at the end of the leaning stage, represent a particular behavior modulation. Both simulations and robot experiments are drawn to demonstrate the potentiality and the effectiveness of the approach.
Keywords :
cellular neural nets; cognitive systems; mobile robots; nonlinear differential equations; partial differential equations; path planning; reaction-diffusion systems; unsupervised learning; brain region; cellular neural network; cluttered environment; cognitive behavior; competitive reflexes; nonlinear lattices; perceptual control architecture; perceptual states; reaction-diffusion nonlinear partial differential equation; representation layer; robot behavior; rover navigation; sensory-motor pathway; steady-state Turing pattern; unsupervised learning; Computational modeling; Lattices;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2009. IJCNN 2009. International Joint Conference on
Conference_Location :
Atlanta, GA
ISSN :
1098-7576
Print_ISBN :
978-1-4244-3548-7
Electronic_ISBN :
1098-7576
Type :
conf
DOI :
10.1109/IJCNN.2009.5178872
Filename :
5178872
Link To Document :
بازگشت