Evolving virtual creatures

This paper describes a novel system for creating virtual creatures that move and behave in simulated three-dimensional physical worlds. The morphologies of creatures and the neural systems for controlling their muscle forces are both generated automatically using genetic algorithms. Different fitness evaluation functions are used to direct simulated evolutions towards specific behaviors such as swimming, walking, jumping, and following. A genetic language is presented that uses nodes and connections as its primitive elements to represent directed graphs, which are used to describe both the morphology and the neural circuitry of these creatures. This genetic language defines a hyperspace containing an indefinite number of possible creatures with behaviors, and when it is searched using optimization techniques, a variety of successful and interesting locomotion strategies emerge, some of which would be difficult to invent or built by design.

[1]  Aristid Lindenmayer,et al.  Mathematical Models for Cellular Interactions in Development , 1968 .

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

[3]  Alvy Ray Smith,et al.  Plants, fractals, and formal languages , 1984, SIGGRAPH.

[4]  Nichael Lynn Cramer,et al.  A Representation for the Adaptive Generation of Simple Sequential Programs , 1985, ICGA.

[5]  Roy Featherstone,et al.  Robot Dynamics Algorithms , 1987 .

[6]  Clive Richards,et al.  The Blind Watchmaker , 1987, Bristol Medico-Chirurgical Journal.

[7]  Gavin S. P. Miller,et al.  The motion dynamics of snakes and worms , 1988, SIGGRAPH.

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

[9]  David H. Sharp,et al.  Scaling, machine learning, and genetic neural nets , 1989 .

[10]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[11]  Hiroaki Kitano,et al.  Designing Neural Networks Using Genetic Algorithms with Graph Generation System , 1990, Complex Syst..

[12]  David Zeltzer,et al.  Dynamic simulation of autonomous legged locomotion , 1990, SIGGRAPH.

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

[14]  Jessica K. Hodgins,et al.  Animation of dynamic legged locomotion , 1991, SIGGRAPH.

[15]  Thomas S. Ray,et al.  An Approach to the Synthesis of Life , 1991 .

[16]  Stephen Todd,et al.  Evolutionary Art and Computers , 1992 .

[17]  F. Varela,et al.  Toward a Practice of Autonomous Systems: Proceedings of the First European Conference on Artificial Life , 1992 .

[18]  John Hart,et al.  The object instancing paradigm for linear fractal modeling , 1992 .

[19]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[20]  Michiel van de Panne,et al.  Sensor-actuator networks , 1993, SIGGRAPH.

[21]  Joe Marks,et al.  Spacetime constraints revisited , 1993, SIGGRAPH.

[22]  Piero Mussio,et al.  Toward a Practice of Autonomous Systems , 1994 .