ABSTRACT
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.
Supplemental Material
Available for Download
- 1.Cramer, N.L., "A Representation for the Adaptive Generation of Simple Sequential Programs," Proceedings of the First International Conference on Genetic Algorithms, ed. by J. Grefenstette, 1985, pp.183-187. Google ScholarDigital Library
- 2.Dawkins, R., The Blind Watchmaker, Harlow Longman, 1986.Google Scholar
- 3.Featherstone, R., Robot Dynamics Algorithms, Kluwer Aca-demic Publishers, Norwell, MA, 1987. Google ScholarDigital Library
- 4.de Garis, H., "Genetic Programming: Building Artificial Ner-vous Systems Using Genetically Programmed Neural Network Modules," Proceedings of the 7th International Conference on Machine Learning, 1990, pp.132-139. Google ScholarDigital Library
- 5.Goldberg, D.E., Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, 1989. Google ScholarDigital Library
- 6.Hart, J., "The Object Instancing Paradigm for Linear Fractal Modeling," Graphics Interface, 1992, pp.224-231. Google ScholarDigital Library
- 7.Holland, J.H., Adaptation in Natural and Artificial Systems, Ann Arbor, University of Michigan Press, 1975. Google ScholarDigital Library
- 8.Kitano, H., "Designing neural networks using genetic algo-rithms with graph generation system," Complex Systems, Vol.4, pp.461-476, 1990.Google Scholar
- 9.Koza, J., Genetic Programming: on the Programming of Com-puters by Means of Natural Selection, MIT Press, 1992. Google ScholarDigital Library
- 10.Lindenmayer, A., "Mathematical Models for Cellular Interac-tions in Development, Parts I and II," Journal of Theoretical Biology, Vol.18, 1968, pp.280-315.Google ScholarCross Ref
- 11.McKenna, M., and Zeltzer, D., "Dynamic Simulation of Autonomous Legged Locomotion," Computer Graphics, Vol.24, No.4, July 1990, pp.29-38. Google ScholarDigital Library
- 12.Miller, G., "The Motion Dynamics of Snakes and Worms," Computer Graphics, Vol.22, No.4, July 1988, pp.169-178. Google ScholarDigital Library
- 13.Mjolsness, E., Sharp, D., and Alpert, B., "Scaling, Machine Learning, and Genetic Neural Nets," Advances in Applied Mathematics, Vol.10, pp.137-163, 1989. Google ScholarDigital Library
- 14.Ngo, J.T., and Marks, J., "Spacetime Constraints Revisited," Computer Graphics, Annual Conference Series, 1993, pp.343- 350. Google ScholarDigital Library
- 15.van de Panne, M., and Fiume, E., "Sensor-Actuator Net-works," Computer Graphics, Annual Conference Series, 1993, pp.335-342. Google ScholarDigital Library
- 16.Raibert, M., and Hodgins, J.K., "Animation of Dynamic Legged Locomotion," Computer Graphics, Vol.25, No.4, July 1991, pp.349-358. Google ScholarDigital Library
- 17.Ray, T., "An Approach to the Synthesis of Life," Artificial Life II, ed. by Langton, Taylor, Farmer, & Rasmussen, Addison-Wesley, 1991, pp.371-408.Google Scholar
- 18.Sims, K., "Artificial Evolution for Computer Graphics," Com-puter Graphics, Vol.25, No.4, July 1991, pp.319-328. Google ScholarDigital Library
- 19.Sims, K., "Interactive Evolution of Dynamical Systems," Toward a Practice of Autonomous Systems: Proceedings of the First European Conference on Artificial Life, ed. by Varela, Francisco, & Bourgine, MIT Press, 1992, pp.171-178.Google Scholar
- 20.Smith, A.R., "Plants, Fractals, and Formal Languages," Com-puter Graphics, Vol.18, No.3, July 1984, pp.1-10. Google ScholarDigital Library
- 21.Todd, S., and Latham, W., Evolutionary Art and Computers, London, Academic Press, 1992. Google ScholarDigital Library
- 22.Yaeger, L., "Computational Genetics, Physiology, Metabo-lism, Neural Systems, Learning, Vision, and Behavior or Poly-World: Life in a New Context," Artificial Life III, ed. by C. Langton, Santa Fe Institute Studies in the Sciences of Com-plexity, Proceedings Vol. XVII, Addison-Wesley, 1994, pp.263-298.Google Scholar
Index Terms
- Evolving virtual creatures
Recommendations
Evolving Virtual Creatures
Seminal Graphics Papers: Pushing the Boundaries, Volume 2This 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 ...
Evolving a diversity of virtual creatures through novelty search and local competition
GECCO '11: Proceedings of the 13th annual conference on Genetic and evolutionary computationAn ambitious challenge in artificial life is to craft an evolutionary process that discovers a wide diversity of well-adapted virtual creatures within a single run. Unlike in nature, evolving creatures in virtual worlds tend to converge to a single ...
Evolving virtual creatures revisited
GECCO '07: Proceedings of the 9th annual conference on Genetic and evolutionary computationThirteen years have passed since Karl Sims published his work on evolving virtual creatures. Since then,several novel approaches to neural network evolution and genetic algorithms have been proposed. The aim of our work is to apply recent results in these ...
Comments