Evolving virtual creatures
Karl Sims · ACM SIGGRAPH Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH) · 1994
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 build by design. 1
Cited by 988 works. doi:10.1145/192161.192167
Authors
References
- Genetic algorithms in search, optimization, and machine learning
- Adaptation in Natural and Artificial Systems
- Genetic Algorithms in Search
- Genetic Programming: On the Programming of Computers by Means of Natural Selection
- The Blind Watchmaker
- Robot Dynamics Algorithms
- Artificial evolution for computer graphics
- Plants, fractals, and formal languages
- Designing Neural Networks Using Genetic Algorithms with Graph Generation System
- A Representation for the Adaptive Generation of Simple Sequential Programs