Advertisement

Evolutionary Approaches to Neural Control of Rolling, Walking, Swimming and Flying Animats or Robots

  • Jean-Arcady Meyer
  • Stéphane Doncieux
  • David Filliat
  • Agnès Guillot
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 109)

Abstract

This article describes past and current research efforts in evolutionary robotics that have been carried out at the AnimatLab, Paris. Such approaches entail using an artificial selection process to automatically generate developmental programs for neural networks that control rolling, walking, swimming and flying animats or robots. Basically, they complement the underlying evolutionary process with a developmental procedure — in order to hopefully reduce the size of the genotypic space that is explored — and they occasionally call on an incremental approach, in order to capitalize upon solutions to simpler problems so as to devise solutions to more complex problems. This article successively outlines the historical background of our research, the evolutionary paradigm on which it relies, and the various results obtained so far. It also discusses the potentialities and limitations of the approach and indicates directions for future work.

Keywords

Mobile Robot Developmental Program Sensory Cell Artificial Life Incremental Approach 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Beer R, Gallagher J (1992) Evolving dynamical neural networks for adaptive behavior. Adaptive Behavior 1 (1): 91 - 122CrossRefGoogle Scholar
  2. Bongard JC, Paul C (2001) Making Evolution an Offer it Can’t Refuse: Morphology and the Extradimensional Bypass. To appear in Proceedings of the 6 European Conference on Artificial Life (ECAL2001). Springer VerlagGoogle Scholar
  3. Boers E, Kuiper H (1992) Biological Metaphors and the Design of Modular Artificial Neural Networks. Master’s Thesis. Department of Computer Science and Experimental and Theoretical Psychology. Leiden UniversityGoogle Scholar
  4. Brooks RA (1986) A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation 2: 14 - 23MathSciNetCrossRefGoogle Scholar
  5. Cangelosi A, Parisi D, Nolfi S (1994) Cell division and migration in a ’genotype’ for neural networks. Network 5: 497 - 515MATHCrossRefGoogle Scholar
  6. Chavas J, Corne C, Horvai P, Kodjabachian J, Meyer JA (1998) Incremental evolution of neural controllers for robust obstacle-avoidance in Khepera. In: Husbands P, Meyer J A (eds) Proceedings of The First European Workshop on Evolutionary Robotics - EvoRobot’98. Springer Verlag, pp 224 - 244Google Scholar
  7. Cliff D, Harvey I, Husbands P (1993) Explorations in evolutionaryrobotics. Adaptive Behavior 20 ): 73 - 110CrossRefGoogle Scholar
  8. Conrad M (1990) The geometry of evolution. Biosystems 24: 61 - 81CrossRefGoogle Scholar
  9. Cliff D, Miller GF (1996) Co-evolution of pursuit and evasion II: Simulation methods and results. In: P Maes P, Mataric MJ, Meyer JA, Pollack JB, Wilson SW (eds) (1996) Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior: From Animals to Animats 4. The MIT Press/Bradford Books, Cambridge, MA, pp 506 - 515Google Scholar
  10. Cruse H, Brunn DE, Bartling C, Dean J, Dreifert M, Kindermann T, Schmitz J (1995) Walking: A complex behavior controlled by simple networks. Adaptive Behavior 3 (4): 385 - 418CrossRefGoogle Scholar
  11. Dellaert F, Beer R (1994) Toward an evolvable model of development for autonomous agent synthesis. In: Brooks RA, Maes P (eds) Proceedings of the Fourth International Workshop on Artificial Life. The MIT Press/Bradford Books, Cambridge, MA, pp 393 - 401Google Scholar
  12. Doncieux S (1999) Evolution d’architectures de contrôle pour robots volants. In: DrogoulGoogle Scholar
  13. A, Meyer JA (eds) Intelligence artificielle située. Hermès, Paris, pp 109-127Google Scholar
  14. Doncieux S (2001) Evolution d’Architectures de Contrôle pour Animats Volants. MémoireGoogle Scholar
  15. de stage de DEA IARFA. Université Pierre et Marie Curie.Google Scholar
  16. Eggenberger E (1996) Cell-cell interactions as a control tool of developmental processes for evolutionary robotics, In: Maes P, Mataric MJ, Meyer JA, Pollack JB, Wilson SW (eds) Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior: From Animals to Animats 4, The MIT Press/Bradford Books, Cambridge, MA, pp 440 - 448Google Scholar
  17. Eggenberger, P (1997) Evolving Morphologies of Simulated 3D Organisms Based on Differentiable Gene Expression. In Proceedings of the Fourth European Conference on Artificial Life. Husbands and Harvey (eds). 205-213. MIT PressGoogle Scholar
  18. Ekeberg O (1993) A combined neuronal and mechanical model of swimming. Biological Cybernetics 69: 363 - 374MATHGoogle Scholar
  19. Filliat D, Kodjabachian J, Meyer JA (1999a) Evolution of neural controllers for locomotion and obstacle-avoidance in a 6-legged robot. Connection Science 11: 223 - 240CrossRefGoogle Scholar
  20. Filliat D, Kodjabachian J, Meyer JA (1999b) Incremental evolution of neural controllers for navigation in a 6-legged robot. In: Sugisaka M, Tanaka H (eds) Proceedings of the Fourth International Symposium on Artificial Life and Robotics. Oita University Press, Beppu, Oita, Japan, pp 753 - 760.Google Scholar
  21. Goldberg D E (1989) Genetic Algorithms in search, optimization and machine learning. Addison-Wesley, Reading, MAGoogle Scholar
  22. Gruau F (1994) Automatic definition of modular neural networks. Adaptive Behavior 3 (2): 151 - 183CrossRefGoogle Scholar
  23. Gruau F (1996) Artificial cellular development in optimization and compilation. In: Sanchez E, Tomassini M (eds) Evolvable Hardware’95. Lecture Notes in Computer Science, Springer Verlag, pp 48 - 75CrossRefGoogle Scholar
  24. Gruau F, Quatramaran K (1997) Cellular Encoding for Interactive Evolutionary Robotics. In: Husbands P, Harvey I (eds) Fourth European Conference on Artificial Life. The MIT Press/Bradford Books, Cambridge, MA, pp 368 - 377Google Scholar
  25. Harvey, I (1992) Species Adaptation Genetic Algorithms: The Basis for a Continuing SAGA. In Proceedings of the First European Conference on Artificial Life. Varela and Bourgine (eds). The MIT Press Cambridge, MA, pp 346 - 354Google Scholar
  26. Harvey I, Husbands P, Cliff D (1994) Seeing the light: Artificial evolution, real vision. In: Cliff D, Husbands P, Meyer JA, Wilson SW (eds) Proceedings of the Third International Conference on Simulation of Adaptive Behavior: From Animals to Animats 3. The MIT Press/Bradford Book, Cambridge, MA, pp 392 - 401Google Scholar
  27. Husbands P, Harvey I., Cliff D, Miller G (1994) The use of genetic algorithms for the development of sensorimotor control systems. In: Nicoud J, Gaussier P (eds) From Perception to Action. Proceedings of the PerAc’94 Conference. IEEE Computer Society Press, Los Alamitos, CA, pp 110 - 121CrossRefGoogle Scholar
  28. Ijspeert AJ, Kodjabachian J (1999) Evolution and development of a central pattern generator for the swimming of a lamprey. Artificial Life 5 (3): 247 - 269CrossRefGoogle Scholar
  29. Jakobi N (1997a) Half-baked, ad-hoc and noisy: Minimal simulations for evolutionary robotics. In: Husbands P, Harvey I (eds) Fourth European Conference on Artificial Life. The MIT Press/Bradford Books, Cambridge, MA, pp 348 - 357Google Scholar
  30. Jakobi N (1997b) Evolutionary robotics and the radical envelope of noise hypothesis. Adaptive Behavior 6 (2): 325 - 367CrossRefGoogle Scholar
  31. Jakobi N (1998) Running across the reality gap: octopod locomotion evolved in minimal simulation. In: Husbands P, Meyer JA (eds) Proceedings of The First European Workshop on Evolutionary Robotics: EvoRobot’98. Springer Verlag, pp 39 - 58Google Scholar
  32. Kodjabachian J, Meyer, JA (1995) Evolution and development of control architectures in animats. Robotics and Autonomous Systems 16: 161 - 182CrossRefGoogle Scholar
  33. Kodjabachian J, Meyer JA (1998a) Evolution and development of modular control architectures for 1-D locomotion in six-legged animats. Connection Science 10: 211237Google Scholar
  34. Kodjabachian J, Meyer JA (1998b) Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects IEEE Transactions on Neural Networks 9 (5): 796 - 812CrossRefGoogle Scholar
  35. Koza J (1992) Genetic Programming: On the programming of computers by means of natural selection. The MIT Press, Cambridge, MAMATHGoogle Scholar
  36. Koza J (1994) Genetic Programming I I: Automatic discovery of reusable sub-programs. The MIT Press, Cambridge, MAMATHGoogle Scholar
  37. Koza JR, Bennett FH, Andre D, Keane MA (1999). Genetic Programming III. Morgan Kaufmann PublishersGoogle Scholar
  38. Lee WP, Hallam J, Lund HH (1997) Learning complex robot behaviours by evolutionary approaches. In: Brink A, Demiris J (eds) Proceedings of the 6th European Workshop on Learning Robots. Springer, Brighton, pp 42 - 51Google Scholar
  39. McClelland JL, Rumelhart DE (eds) (1996) Parallel Distributed Processing. Vol 1. The MIT Press/Bradford Books, Cambridge, MAGoogle Scholar
  40. Meyer JA (1998) Evolutionary approaches to neural control in mobile robots. In: Proceedings of the IEEE International Conference on Systems and Cybernetics. San Diego, pp 35 - 40Google Scholar
  41. Michel O (1995) An artificial life approach for the synthesis of autonomous agents. In: Alliot J, Lutton E, Ronald E, Schoenauer M, Snyers D (eds) Proceedings of the European Conference on Artificial Evolution. Springer Verlag, pp 220 - 231Google Scholar
  42. Michel O, Collard P (1996) Artificial Neurogenesis: An application to autonomous robotics. In: Radle M G (ed) Proceedings of The 8 International Conference on Tools in Artificial Intelligence IEEE Computer Society Press, Piscataway, NJ, pp 207 - 214Google Scholar
  43. Mondada F, Franzi E, Ienne P (1993) Mobile robot miniaturization: A tool for investigation in control algorithms. In: Yoshikawa T, Miyazaki F (eds) Proceedings of the Third International Symposium on Experimental Robotics. Springer Verlag, Tokyo, pp 501513Google Scholar
  44. Nolfi S, Miglino O, Parisi D (1994) Phenotypic plasticity in evolving neural networks. In: Gaussier P, Nicoud J (eds) From Perception to Action. Proceedings of the PerAc’94 Conference. IEEE Computer Society Press, Los Alamitos, CA, pp 146 - 157CrossRefGoogle Scholar
  45. Rumelhart DE, McClelland JL (eds) (1986) Parallel Distributed Processing. Vol 2. The MIT Press/Bradford Books, Cambridge, MAGoogle Scholar
  46. Shipman, R (1999). Genetic Redundancy: Desirable or Problematic for Evolutionary Adaptation? In Proceedings of the 4th International Conference on Artificial Neural Networks and Genetic Algorithms. 337-344. Springer VerlagGoogle Scholar
  47. Sims K (1994) Evolving virtual creatures. In: Glassner A (ed) Computer Graphics Proceedings: SIGGRAPH’94, Annual Conferences Series, Association for Computing Machinery, New York, pp 15 - 22Google Scholar
  48. Spencer G (1994) Automatic generation of programs for crawling and walking In: Kinnear KE Jr (ed) Advances in Genetic Programming, The MIT Press/Bradford Books, Cambridge, MA, pp 335 - 353Google Scholar
  49. Vaario J (1993) An emergent modeling method for artificial neural networks, Ph.D. thesis, University of TokyoGoogle Scholar
  50. Vaario J, Onitsuka A, Shimohara K (1997) Formation of neural structures. In: Husbands P, Harvey I (eds) Proceedings of the Fourth European Conference on Artificial Life. The MIT Press, Cambridge, MA, pp 214 - 223Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Jean-Arcady Meyer
    • 1
  • Stéphane Doncieux
    • 1
  • David Filliat
    • 1
  • Agnès Guillot
    • 1
  1. 1.AnimatLab — Lip6ParisFrance

Personalised recommendations