Abstract
This paper presents a three level architecture for an autonomous agent and its application to the navigation problem in an unknown environment. The architecture is structured in three levels, called, reactive, instinctive and cognitive. The reactive level is based on a feed-forward symbolic neural network. The instinctive level is based on a set of predefined behaviors selected by a fuzzy classifier according to the perceived situation. Finally, the cognitive level is supported by symbolic production rules that determine the global behavior of the agent. In this sense, the three levels are responsible by behaviors of increasing complexity. The main characteristics of the architecture are: heterogeneity, hierarchic assembly, behavior-oriented design and biological plausibility. Some examples are also presented, that show the behavior robustness of the proposed architecture in a simulated environment.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Anderson, T.L., Donath, M.: Animal behavior as a paradigm for developing robot autonomy. In: Maes, P. (ed.) Designing Autonomous Agents, pp. 145–168. Bradford Book, MIT Press (1991)
Arbib, M.A., Liaw, J.-S.: Sensorimotor transformations in the world of frogs and robots. Artificial Intelligence 72, 53–79 (1995)
Beer, R.D., Chiel, H.J., Sterling, L.S.: A biological perpective on agent autonomous design. In: Maes, P. (ed.) Designing Autonomous Agents, pp. 169–186. Bradford Book, MIT Press (1991)
Bittencourt, G.: In the quest of the missing link. In: Proceedings of IJCAI 15, Nagoya, Japan, August 23-29, pp. 310–315. Morgan Kaufmann, San Francisco (1997) ISBN 1-55860-480-4
Brooks, P.A.: Intelligence without representation. Artificial Intelligence (Special Volume Foundations of Artificial Intelligence) 47(1-3), 139–159 (1991)
Durfee, E.H.: The distributed artificial intelligence melting pot. IEEE Transactions on Systems, Man and Cybernetics 21(6), 1301–1306 (1991), Special Issue on Distributed Artificial Intelligence
Fu, L.: Rule generation from neural networks. IEEE Transactions on Systems, Man and Cybernetics 24(8), 1114–1124 (1994)
Hopcroft, J.E., Ullman, J.D.: Introduction to Automata Theory, Languages and Computation. Addison Wesley Publishing Company, Reading (1979)
Inaba, M.: Remote-brained robots. In: Proceedings of IJCAI 15, Nagoya, Japan, August 23-29, pp. 1593–1606. Morgan Kaufmann, San Francisco (1997) ISBN 1-55860-480-4
Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research 4, 237–285 (1996)
Klir, G.J., Folger, T.A.: Fuzzy Sets, Uncertainty, and Information. Prentice Hall, Englewood Cliffs (1988)
Maes, P. (ed.): Designing Autonomous Agents. Bradford Book, MIT Press (1991)
Meystel, A.: Knowledge-based controller for intelligent mobile robots. Drexel University, Philadelphia, PA 19104, USA (1986)
Michel, O.: Khepera Simulator Package version 2.0: Freeware mobile robot simulator. University of Nice Sophia–Antipolis, France (1997)
Motoda, H., Yoshida, K.: Machine learning techniques to make computers easier to use. In: Proceedings of IJCAI 15, Nagoya, Japan, August 23-29, pp. 1622–1631. Morgan Kaufmann, San Francisco (1997) ISBN 1-55860-480-4
Omlin, C.W., Thornber, K.K., Lee Giles, C.: Fuzzy finite-state automata can be deterministically encoded into recurrent neural networks. Technical Report Technical Report CS-TR-3599 and UMIACS 1996-2012, University of Maryland (April 1996)
Rasmussen, S.: Aspects of information, life, reality, and physics. In: Langton, C., Taylor, C., Farmer, J.D., Rasmussen, S. (eds.) Artificial Life II. SFI Studies in the Sciences of Complexity, vol. X. Addison- Wesley, Reading (1991)
Rocha, A.F.: Neural Nets: A Theory for Brains and Machines. In: Rocha, A.F. (ed.) Neural Nets. LNCS (LNAI), vol. 638. Springer, Heidelberg (1992)
de Sá, C.C., Bittencourt, G., Omar, N.: An architecture for a mobile autonomous agent. In: Gelenbe, E., Schmajuk, N. (eds.) Proceedings of the Workshop on Biologically Inspired Autonomous Systems (March 1996)
Sloman, A.: What sort of architecture is required for a uman-like agent? In: Proceedings of AAAI 1996 ( August 1996)
Turner, R.M.: Context-sensitive reasoning for autonomous agents and cooperative distributed problem solving. In: Proceedings of the 1993 IJCAI Workshop on sing Knowledge in Its Context (1993)
Yager, R.R., Filev, D.P. (eds.): Essentials of Fuzzy Modeling and Control. John Wiley & Sons, Inc., Chichester (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
de Sá, C.C., Bittencourt, G., Omar, N. (1998). An Autonomous Agent Architecture and the Locomotion Problem. In: de Oliveira, F.M. (eds) Advances in Artificial Intelligence. SBIA 1998. Lecture Notes in Computer Science(), vol 1515. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10692710_2
Download citation
DOI: https://doi.org/10.1007/10692710_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65190-1
Online ISBN: 978-3-540-49523-9
eBook Packages: Springer Book Archive