Evolving Virtual Creatures
Karl Sims · ACM eBooks · 2023
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.
Cited by 28 works. doi:10.1145/3596711.3596785
Authors
References
- Adaptation in Natural and Artificial Systems
- Genetic Programming: On the Programming of Computers by Means of Natural Selection
- Mathematical models for cellular interactions in development I. Filaments with one-sided inputs
- Designing Neural Networks Using Genetic Algorithms with Graph Generation System
- A Representation for the Adaptive Generation of Simple Sequential Programs
- Artificial evolution for computer graphics
- The motion dynamics of snakes and worms
- Plants, fractals, and formal languages
- Evolutionary Art and Computers
- Scaling, machine learning, and genetic neural nets