Interactive evolution of equations for procedural models

This paper describes how the evolutionary mechanisms of variation and selection can be used to “evolve” complex equations used by procedural models for computer graphics and animation. An interactive process between the user and the computer allows the user to guide evolving equations by observing results and providing aesthetic information at each step of the process. The computer automatically generates random mutations of equations and combinations between equations to create new generations of results. This repeated interaction between user and computer allows the user to search hyperspaces of posible equations without being required to design the equations by hand or even understand them. Three examples of these techniques have been implemented and are described: procedurally generated pictures and textures, three-dimensional shapes represented by parametric equations, and two-dimensional dynamical systems described by sets of differential equations. It is proposed that these methods have potential as powerful tools for exploring procedural models and achieving flexible complexity with a minimum of user input and knowledge of details.

[1]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[2]  Douglas B. Lenat,et al.  Why AM and EURISKO Appear to Work , 1984, Artif. Intell..

[3]  Guy L. Steele,et al.  Common Lisp the Language , 1984 .

[4]  John J. Grefenstette,et al.  Genetic algorithms and their applications , 1987 .

[5]  W. Daniel Hillis,et al.  The connection machine , 1985 .

[6]  Ken Perlin,et al.  [Computer Graphics]: Three-Dimensional Graphics and Realism , 2022 .

[7]  Darwyn R. Peachey,et al.  Solid texturing of complex surfaces , 1985, SIGGRAPH.

[8]  R. Dawkins The Blind Watchmaker , 1986 .

[9]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[10]  J. P. Lewis,et al.  Algorithms for solid noise synthesis , 1989, SIGGRAPH.

[11]  John R. Koza,et al.  Genetic programming: a paradigm for genetically breeding populations of computer programs to solve problems , 1990 .

[12]  Karl Sims,et al.  Artificial evolution for computer graphics , 1991, SIGGRAPH.

[13]  Andrew Witkin,et al.  Reaction-diffusion textures , 1991, SIGGRAPH.

[14]  Greg Turk,et al.  Generating textures on arbitrary surfaces using reaction-diffusion , 1991, SIGGRAPH.

[15]  Michael Haggerty Virtual reality dominates siggraph [selective update] , 1991, IEEE Computer Graphics and Applications.

[16]  Sam Kwong,et al.  Genetic algorithms and their applications , 1996, IEEE Signal Process. Mag..