Evolved Art via Control of Cellular Automata

Daniel Ashlock and Jeffery Tsang.
Submitted to the 2009 Congress on Evolutionary Computation

Abstract PDF eprint

This is the second study exploring the creation of evolved art through evolutionary control of a dynamical system. Here 1-dimensional cellular automata rules are evolved to exhibit slow but persistent growth or to undergo planned senescence. These simple constraints encourage the automata to develop complex and visually pleasing behavior. Isotropic automata with a forced quiescent state are used, with rules evolved using a simple string representation; the fitness landscapes for both fitness functions are found to be quite rugged with many local optima. This is a desirable feature in an evolved art system as it yields a rich variety of outputs for the artist to use as image elements. A parameter study is performed and it is found that optimization of the slow-growth fitness function favors the use of large populations.