PapersNo Access

TURING PATTERNS IN RD-CNNs FOR THE EMERGENCE OF PERCEPTUAL STATES IN ROVING ROBOTS

Dipartimento di Ingegneria Elettrica Elettronica e dei Sistemi, Università degli Studi di Catania, viale A. Doria 6, 95125 Catania, Italy

Search for more papers by this author

LUIGI FORTUNA

Dipartimento di Ingegneria Elettrica Elettronica e dei Sistemi, Università degli Studi di Catania, viale A. Doria 6, 95125 Catania, Italy

Search for more papers by this author

MATTIA FRASCA

Dipartimento di Ingegneria Elettrica Elettronica e dei Sistemi, Università degli Studi di Catania, viale A. Doria 6, 95125 Catania, Italy

Search for more papers by this author

DAVIDE LOMBARDO

Dipartimento di Ingegneria Elettrica Elettronica e dei Sistemi, Università degli Studi di Catania, viale A. Doria 6, 95125 Catania, Italy

Search for more papers by this author

LUCA PATANÈ

Dipartimento di Ingegneria Elettrica Elettronica e dei Sistemi, Università degli Studi di Catania, viale A. Doria 6, 95125 Catania, Italy

Search for more papers by this author

, and

PAOLO CRUCITTI

Scuola Superiore di Catania, Via S. Paolo 73, 95123 Catania, Italy

Dipartimento di Ingegneria Elettrica Elettronica e dei Sistemi, Università degli Studi di Catania, viale A. Doria 6, 95125 Catania, Italy

Search for more papers by this author

https://doi.org/10.1142/S0218127407017203Cited by:18 (Source: Crossref)

Abstract

Behavior-based robotics considers perception as a holistic process, strongly connected to behavioral needs of the robot. We present a bio-inspired framework for sensing-perception-action, applied to a roving robot in a random foraging task. Perception is here considered as a complex and emergent phenomenon where a huge amount of information coming from sensors is used to form an abstract and concise representation of the environment, useful to take a suitable action or sequence of actions. In this work a model for perceptual representation is formalized by means of RD-CNNs showing Turing patterns. They are used as attractive states for particular set of environmental conditions in order to associate, via a reinforcement learning, a proper action. Learning is also introduced at the afferent stage to shape the environment information according to the particular emerging pattern. The basins of attraction for the Turing patterns are so dynamically tuned by an unsupervised learning in order to form an internal, abstract and plastic representation of the environment, as recorded by the sensors.

Keywords:

References

A. Adamatzkyet al., IEEE Trans. Circuits Syst. I 51, 926 (2004), DOI: 10.1109/TCSI.2004.827654. Crossref, Google Scholar
P. Arena et al. , CNNs and motor maps for bio-inspired collision avoidance in roving robots , Proc. CNNA2004 ( 2004 ) . Google Scholar
P. Arenaet al., IEEE Trans. Syst. Man Cybern. Part B 34, 1823 (2004), DOI: 10.1109/TSMCB.2004.828593. Crossref, Web of Science, Google Scholar
R. C. Arkin , Behaviour Based Robotics ( MIT Press , Cambridge , 1997 ) . Google Scholar
J. Borenstein and Y. Koren, IEEE J. Robot. Automat. 7, 278 (1991), DOI: 10.1109/70.88137. Crossref, Google Scholar
R. Carmonaet al., Bio-inspired analog VLSI design realizes rogrammable complex spatio-temporal dynamics on a single chip, Proc. 2002 Conf. Design Automation and Test in Europe (2002) pp. 362–366, DOI: 10.1109/DATE.2002.998299. Google Scholar
M. Frasca , P. Arena and L. Fortuna , Bio-Inspired Emergent Control Of Locomotion Systems , World Scientific Series on Nonlinear Science Series A 48 ( 2004 ) . Crossref, Google Scholar
W. J. Freeman , How Brains Make Up Their Minds ( Weidenfeld and Nicolson , London , 1999 ) . Google Scholar
W. J. Freeman, Int. J. Bifurcation and Chaos 14, 515 (2004), DOI: 10.1142/S0218127404009405. Link, Web of Science, Google Scholar
L. Goras and L. Chua, IEEE Trans. Circuits Syst.-I 42, (1995). Google Scholar
T. Kohonen, Biol. Cybern. 43, 59 (1972). Crossref, Web of Science, Google Scholar
Y. Koren and J. Borenstein, Potential field methods and their inherent limitation for mobile robot navigation, Proc. IEEE Conf. Robotics and Automation (1991) pp. 1398–1404. Google Scholar
K. Lynch , The Image of the City ( MIT Press , Cambridge , 1960 ) . Google Scholar
G. Manganaro , P. Arena and L. Fortuna , Cellular Neural Networks: Chaos, Complexity and VLSI Processing ( Springer-Verlag , NY , 1999 ) . Crossref, Google Scholar
J. D. Murray , Mathematical Biology I: An Introduction , 3rd edn. ( Springer-Verlag , NY , 2002 ) . Crossref, Google Scholar
U. Neisser , Cognition and Reality: Principles and Implications of Cognitive Psychology ( W. H. Freeman , San Francisco , 1976 ) . Google Scholar
I. I. Pavlov and G. V. Anrep , Conditioned Reflexes ( Oxford University Press , London , 1927 ) . Google Scholar
H. Ritter and K. Schulten, Kohonen's self-organizing maps: Exploring their computational capabilites, Proc. IEEE Int. Conf. Neural Networks1 (1988) pp. 109–116. Google Scholar
Schulten, K. [2002] Theoretical Biophysics of Living Systems, available in http://www.ks.uiuc.edu/Services/Class/PHYS498TBP/spring2002/neuro_book.html . Google Scholar
B. F. Skinner , About Behaviorism ( Alfred Knopf , NY , 1974 ) . Google Scholar
E. L. Thorndike, J. Appl. Psychol. 4, 469 (1920). Google Scholar
A. M. Turing, Phil. Trans. Roy. Soc. Lond. B 237, 37 (1952). Crossref, Web of Science, Google Scholar
P. F. M. J. Verschure and P. Althaus, Cogn. Sci. 27, 561 (2003). Crossref, Web of Science, Google Scholar
P. F. M. J. Verschure, T. Voegtlin and R. J. Douglas, Nature 425, 620 (2003). Crossref, Web of Science, Google Scholar