Abstract
The methodology of artificial evolution based on the traditional fitness function is argued to be inadequate for constructing the entities with behaviors novel to their designers. Evolutionary emergence via natural selection(without an explicit fitness function) is a promising way. This paper primarily considers the question of what to evolve, and focuses on the principles of developmental modularity based on neural networks. The connection weight values of this neural network are encoded as genes, and the fitness individuals are determined using a genetic algorithm. In paper we has created and described an artificial world containing autonomous organisms for developing and testing some novel ideas. Experimental results through simulation have demonstrated that the developmental system is well suited to long-term incremental evolution. Novel emergent strategies are identified both from an observer’s perspective and in terms of their neural mechanisms.
Partial funding provided by the Internatioanl Centre for Theoretical Physics, Trieste, Italy
Chapter PDF
Similar content being viewed by others
References
Zaera N., Cliff D., and Bruten J.(1996). Evolving collective behaviours in synthetic fish. Proceedings of SAB96, MIT Press Bradford Books, 635–644.
Ray, T. S.(1991). An approach to the synthesis of life. In Langton, C.; Taylor, C.; Farmer, J.; and Rasmussen, S. eds., Artificial Life II, 371–408. Redwood City, CA: Addison-Wesley.
Yaeger, L.(1993).Computational genetics, physiology, metabolism, neuralsystems, learning, vision, and behavior or polyworld: Life in a new context. In Langton, C. G., ed., Artificial Life III, 263–298.
Malrey Lee (2003). Evolution of behaviors in autonomous robot using artificial neural network and genetic algorithm. International Journal of Information Sciences, Vol.155, Issue 1–2, pp.43–60.
Harvey, I.(1993). Evolutionary robotics and SAGA: the case for hill crawling and tournament selection. In Langton, C. G., ed., Artificial Life III.
Koza, J. R.(1992). Genetic Programming. Cambridge, MA: MIT Press/Bradford Books.
Gruau, F.(1996). Artificial cellular development in optimization and compilation. Technical Report, Psychology Department, Stanford University, Palo Alto, CA.
Lindenmayer, A.(1968). Mathematical models for cellular interaction in development. Journal of Theoretical Biology (Parts I and II), 18: 280–315.
Kitano, H. (1990). Designing neural networks using genetic algorithms with graph generation system. Complex Systems, 4: 461–476.
Boers, E. J. and Kuiper, H.(1992). Biological metaphors and the design of modular artificial neural networks. Master’s thesis, Departments of Computer Science and Experimental Psychology, Leiden University.
Yang, J. A. and Wang, H. Y.(2002). Research on combined behavior method for evolutionary robot based on neural network. Journal of Shanghai Jiao Tong University, Vol.36, Sup.pp.89–95.
Wang, H. Y. and Yang, J. A.(2000). Research on evolutionary robot behavior using developmental network, Acta Electronica Sinica, 28(12): 41–45.
Wang, H. Y., Yang, J. A. and Jiang, P.(2000). Research on evolutionary robot behavior using developmental network [J]. Journal of Computer & Development, 37(12): 1457–1465.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer Science + Business Media, Inc.
About this chapter
Cite this chapter
Yang, J., Zhuang, Y., Wang, H. (2004). Evolutionary Robot Behaviors Based on Natural Selection and Neural Network. In: Bramer, M., Devedzic, V. (eds) Artificial Intelligence Applications and Innovations. AIAI 2004. IFIP International Federation for Information Processing, vol 154. Springer, Boston, MA. https://doi.org/10.1007/1-4020-8151-0_6
Download citation
DOI: https://doi.org/10.1007/1-4020-8151-0_6
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4020-8150-7
Online ISBN: 978-1-4020-8151-4
eBook Packages: Springer Book Archive