Evolution and Development of Modular Control Architectures for 1-D Locomotion in Six-Legged Animats
| Autor: | Jérôme Kodjabachian, Jean-Arcady Meyer |
|---|---|
| Přispěvatelé: | Objets et Agents pour Systèmes d'Information et Simulation (OASIS), Laboratoire d'Informatique de Paris 6 (LIP6), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS) |
| Jazyk: | angličtina |
| Rok vydání: | 1998 |
| Předmět: |
Scheme (programming language)
Artificial neural network Computer science business.industry 05 social sciences Robotics 02 engineering and technology Modular design 050105 experimental psychology Human-Computer Interaction Animat Artificial Intelligence Control theory Encoding (memory) Control system 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing 0501 psychology and cognitive sciences [INFO]Computer Science [cs] Artificial intelligence business computer Software computer.programming_language |
| Zdroj: | Connection Science Connection Science, Taylor & Francis, 1998, 10 (3-4), pp.211-237. ⟨10.1080/095400998116413⟩ Connection Science, 1998, 10 (3-4), pp.211-237. ⟨10.1080/095400998116413⟩ |
| ISSN: | 0954-0091 1360-0494 |
| DOI: | 10.1080/095400998116413⟩ |
| Popis: | International audience; An evolutionary approach is used to design neural control architectures for virtual sixlegged animats. Using a geometry-oriented variation of the cellular encoding scheme and syntactic constraints that reduce the size of the genetic search space, the developmental programs of straight locomotion controllers are first evolved. One such controller is then included as the first module in a larger architecture, in which a second neural module is evolved and develops connections to the first one, so as to set locomotion on or offaccording to sustained or instantaneous external control signals. Such an incremental approach should prove useful to the automatic design of relatively complex control architectures that might, in particular, implement some cognitive abilities over and above mere stimulus-response mechanisms. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|