UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Evolving fractal gene regulatory networks for robot control

Bentley, PJ; (2003) Evolving fractal gene regulatory networks for robot control. In: Banzhaf, W and Christaller, T and Dittrich, P and Kim, JT and Ziegler, J, (eds.) ADVANCES IN ARTIFICIAL LIFE, PROCEEDINGS. (pp. 753 - 762). SPRINGER-VERLAG BERLIN

Full text not available from this repository.

Abstract

Fractal proteins are a new evolvable method of mapping genotype to phenotype through a developmental process, where genes are expressed into proteins comprised of subsets of the Mandelbrot Set. The resulting network of gene and protein interactions can be designed by evolution to produce specific patterns, that in turn can be used to solve problems. Here the use of fractal gene regulatory networks for learning a robot path through a series of obstacles is described. The results indicate the ability of this system to learn regularities in solutions and automatically create and use modules.

Type:Proceedings paper
Title:Evolving fractal gene regulatory networks for robot control
Event:7th European Conference on Artificial Life
Location:DORTMUND, GERMANY
Dates:2003-09-14 - 2003-09-17
ISBN:3-540-20057-6
UCL classification:UCL > School of BEAMS > Faculty of Engineering Science > Computer Science

Archive Staff Only: edit this record