Evolution and Development of Neural Networks Controlling Locomotion , Gradient-Following , and Obstacle-Avoidance in Artificial Insects

@inproceedings{Kodjabachian1997EvolutionAD,
  title={Evolution and Development of Neural Networks Controlling Locomotion , Gradient-Following , and Obstacle-Avoidance in Artificial Insects},
  author={J{\'e}r{\^o}me Kodjabachian},
  year={1997}
}
This paper describes how the SGOCE paradigm has been used to evolve developmental programs capable of generating neural networks that control the behavior of simulated insects. This paradigm is characterized by an encoding scheme, by an evolutionary algorithm, and by an incremental strategy that are described in turn. The additional use of an insect model equipped with 6 legs and two antennae made it possible to generate control modules that allowed to successively add gradient-following and… CONTINUE READING
39 Citations
47 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 39 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 47 references

Intelligence as Adaptive Behavior: An Experiment in Computational Neuroethology

  • R. Beer
  • Academic Press, San Diego, CA
  • 1990
Highly Influential
7 Excerpts

Similar Papers

Loading similar papers…