Abstract
This chapter examines the artificial embryogeny of landscapes intended for use with virtual reality which consist of collections of polygons encoded using L-systems. Artificial Embryogeny is the study of indirect representations. A recent survey that attempts to classify different types of artificial embryogeny appears in [18]. A representation is a way of encoding a model or a solution to a problem for use in computation. For example, an array of n real numbers is a representation of the value of a function in n variables. A representation is indirect if it gives a set of directions for constructing the thing it specifies rather than encoding the object directly. The process of following the directions given in the indirect representation to obtain the final object is called expression. Indirect representations require an interpreter to express them and, because of this, are more difficult to understand at the specification or genetic level. There are number of advantages to indirect representations that more than balance this genetic obscurity in many situations. The most general of these advantages is that the transformation from the indirect specification to the final model or solution can incorporate heuristics and domain knowledge. This permits a search of a genetic space that is far smaller than the space in which the expressed objects reside and has a much higher average quality. Another advantage, showcased in this chapter, is compactness of representation. The indirect representations we evolve in this chapter use a few hundred bytes to specify megabyte-sized collections of polygons.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
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
Ashlock, D., Bryden, K.: Evolutionary control of L-system interpretation. In: Proceedings of the 2004 Congress on Evolutionary Computation, vol. 2, pp. 2273–2279. IEEE Press, Piscataway, NJ (2004)
Ashlock, D., Bryden, K., Gent, S.: Evolutionary control of bracketed L-system interpretation. In: Intelligent Engineering Systems Through Artificial Neural Networks, vol. 14, pp. 271–276 (2004)
Ashlock, D., Bryden, K., Gent, S.: Evolving L-systems to locate edit metric codes. In: C. Dagli et al. (ed.) Smart Engineering System Design: Neural Networks, Fuzzy, Evolutionary Programming, and Artificial Life, vol. 15, pp. 201–209. ASME Press (2005)
Ashlock, D., Bryden, K., Meinert, K., Bryden, K.: Transforming data into music using fractal algorithms. In: Intelligent Engineering Systems Through Artificial Neural Networks, vol. 13, pp. 665–670 (2003)
Ashlock, D., Gent, S., Bryden, K.: Evolution of L-system for compact virtual landscape generation. In: Proceedings of the 2005 Congress on Evolutionary Computation, vol. 3, pp. 2760–2767. IEEE Press (2005)
Ashlock, D., Kim, E.: The impact of cellular representation on finite state agents for Prisoner’s Dilemma. In: Proceedings of the 2005 Genetic and Evolutionary Computation Conference, pp. 59–66. ACM Press, New York (2005)
Ball, P.: The Self-made Tapestry, Pattern Formation in Nature. Oxford University Press, New York (1999)
Gruau, F.: Genetic synthesis of modular neural networks. In: Proceedings of the Fifth International Conference on Genetic Algorithms, pp. 318–325. Morgan Kaufmann, San Francisco (1993)
Gruau, F., Whitley, D., Pyeatt, L.: A comparison between between cellular encodings and direct codings for genetic neural networks. In: Genetic Programming 1996, pp. 81–89. MIT Press, Cambridge MA (1996)
Hornby, G, Pollack, J.: Body-brain co-evolution using L-systems as a generative encoding. In: L. Spector et al. (ed.) Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2001), pp. 868–875, Morgan Kaufmann, San Francisco, California, USA (2001)
Hornby, G., Pollack, J.: Evolving L-systems to generate virtual creatures. Computers and Graphics 25 (6), 1041–1048 (2001)
Kitano, H.: Designing neural networks using genetic algorithms with graph genetation system. Complex Systems 4, 461–476 (1990)
Lindenmayer, A.: Mathematical models for cellular interaction in development. parts I and II. Journal of Theoretical Biology 16, 280–315 (1968)
Mandelbrot, B.: The fractal geometry of nature. W. H. Freeman and Company, New York (1983)
Miller, G., Todd, P., Hegde, S.: Designing neural networks using genetic algorithms. In: Proceedings of the 3rd International conference on Genetic Algorithms, pp. 379–384. Morgan Kaufmann, San Mateo, CA (1989)
Murray, J.: Mathematical Biology II, Springer-Verlag, New York (2003)
Prusinkiewicz, P., Lindenmayer, A., Hanan, J.: The algorithmic beauty of plants. Springer-Verlag, New York (1990)
Stanley, K., Miikkulainen, R.: A taxonomy for artificial embryology. Artificial Life 9, 93–130 (2003)
Syswerda, G.: A study of reproduction in generational and steady state Genetic Algorithms. In: Foundations of Genetic Algorithms, pp. 94–101. Morgan Kaufmann (1991)
Turing, A.: The chenical basis of morphogenesis. Philosophical Transactions of the Royal Society (B) 237, 37–72 (1952)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Ashlock, D., Gent, S., Bryden, K. (2008). Embryogenesis of Artificial Landscapes. In: Hingston, P.F., Barone, L.C., Michalewicz, Z. (eds) Design by Evolution. Natural Computing Series. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74111-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-540-74111-4_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74109-1
Online ISBN: 978-3-540-74111-4
eBook Packages: Computer ScienceComputer Science (R0)