by Craig Reynolds
Robust behavioral control programs for a simulated 2d vehicle can be constructed by artificial evolution. Corridor following serves here as an example of a behavior to be obtained through evolution. A controller's fitness is judged by its ability to steer its vehicle along a collision free path through a simple corridor environment. The controller's inputs are noisy range sensors and its output is a noisy steering mechanism. Evolution determines the quantity and placement of sensors. Noise in fitness tests discourages brittle strategies and leads to the evolution of robust, noise-tolerant controllers. Genetic Programming is used to model evolution, the controllers are represented as deterministic computer programs.
Keywords: evolution of behavior, obstacle avoidance, steering, genetic programming, genetic algorithms.
Reynolds, C. W. (1994) Evolution of Corridor Following Behavior in a Noisy World, in From Animals to Animats 3: Proceedings of the Third International Conference on Simulation of Adaptive Behavior (SAB94), D. Cliff, P. Husbands, J-A Meyer, and S. Wilson, Editors, ISBN 0-262-53122-4, MIT Press, Cambridge, Massachusetts, pages 402-410.
Full article available online:
PDF (0.24 MB)
Postscript (compressed, 0.70 MB)
Send comments to Craig Reynolds
Last update: June 11, 2000