A Morphogenetic Evolutionary System: Phylogenesis of the POEtic Circuit
This paper describes a new evolutionary mechanism developed specifically for cellular circuits. Called morphogenetic system, it is inspired by the mechanisms of gene expression and cell differentiation found in living organisms. It will be used as the phylogenetic (evolutionary) mechanism in the POEtic project. The POEtic project will deliver an electronic circuit, called the POEtic circuit, with the capability to evolve (Phylogenesis), self-repair and grow (Ontogenesis) and learn (Epigenesis). The morphogenetic system is applied to the generation of patterns and to the evolution of spiking neural networks, with experiments of pattern recognition and obstacle avoidance with robots. Experimental results show that the morphogenetic system outperforms a direct genetic coding in several experiments.
Unable to display preview. Download preview PDF.
- 1.S. Boshy and E. Ruppin. Small is beautiful: Near minimal evolutionary neurocontrolllers obtained with self-organizing compressed encoding. In B. Hallam, D. Floreano, J. Hallam, G. Hayes, and J.-A. Meyer, editors, Proceedings of the SeventhInternational Conference on Simulation of Adaptive Behaviour, pages 345–346,Cambridge, MA, 2002. MIT Press-Bradford Books.Google Scholar
- 2.E. Coen. The art of genes. Oxford University Press, New York, 1999.Google Scholar
- 3.P. Eggenberger. Cell interactions as a control tool of developmental processes for evolutionary robotics. In P. Maes, M. J. Mataric, J.-A. Meyer, J. Pollack, and S. W. Wilson, editors, From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior, pages 440–448, Cambridge, MA, 1996. MIT Press-Bradford Books.Google Scholar
- 4.D. Floreano and F. Mondada. Automatic creation of an autonomous agent: Genetic evolution of a neural-network driven robot. In D. Cli., P. Husbands, J. Meyer, and S. W. Wilson, editors, From Animals to Animats III: Proceedings of the Third International Conference on Simulation of Adaptive Behavior, pages 421–430, Cambridge, MA, 1994. MIT Press-Bradford Books.Google Scholar
- 5.D. Floreano, N. Schoeni, G. Caprari, and J. Blynel. Evolutionary bits’n’spikes. In Artificial Life VIII Proceedings. MIT Press, 2002.Google Scholar
- 7.P. C. Haddow, G. Tufte, and P. van Remortel. Shrinking the Genotype: L-systems for EHW? In Y. Liu, K. Tanaka, M. Iwata, T. Higuchi, and M. Yasunaga, editors, Evolvable Systems: From Biology to Hardware; Proceedings of the Fourth International Conference on Evolvable Systems (ICES 2001), pages 128–139, Berlin, 2001. Springer.Google Scholar
- 8.T. Smith, P. Husbands, and M. O’shea. Not measuring evolvability: Initial investigation of an evolutionary robotics search space. In Congress on Evolutionary Computation 2001, pages9–16. IEEE Press, 2001.Google Scholar
- 9.G. Tempesti, D. Mange, A. Stauffer, and C. Teuscher. The biowall: An electronic tissue for prototyping bio-inspired systems. In A. Stoica, J. Lohn, R. Katz, D. Keymeulen, and R. S. Zebulum, editors, Proceedings of the 2002 NASA/DoD Conference on Evolvable Hardware, pages 221–230. IEEE Computer Society, Los Alamitos, CA, 2002.Google Scholar
- 10.A. M. Tyrrell, E. Sanchez, D. Floreano, G. Tempesti, D. Mange, J.-M. Moreno, J. Rosenberg, and A. Villa. POEtic Tissue: An Integrated Architecture for Bio-Inspired Hardware. In Evolvable Systems: From Biology to Hardware; Proceedings of the Fifth International Conference on Evolvable Systems (ICES 2003), Berlin, 2003. Springer.Google Scholar
- 11.X. Yao. A review of evolutionary artificial neural networks. International Journal of Intelligent Systems, 4:203–222, 1993.Google Scholar