Behaviour Learning by a Reward-Penalty Algorithm : From Gait Learning to Obstacle Avoidance by Neural Networks

  • Isabelle Sarda
  • Anne Johannet
Conference paper


Designing a mobile robot capable to evolve on various floors is a hard, and not yet solved task. Among the numerous ways, the biological inspired researches are attractive. Taking inspiration from such devices, a study on walk learning and obstacle avoiding by neural networks is presented. After a general presentation of the learning method, and its adaptation to neural networks, results on gait learning are described and first simulations on obstacle avoidance are also presented. Finally, a global network performing the two tasks with success is given.


Mobile Robot Obstacle Avoidance Learn Automaton Parallel Iteration Legged Robot 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    R.A. Brooks, “Intelligence Without Representation”. Artificial Intelligence 47, 139 (1991).CrossRefGoogle Scholar
  2. 2.
    R.A. Brooks, “A Robot that Walks:Emergent behaviors from carefully evolved network,”. Neur. Comput. 1 (2): 253 (1989).CrossRefGoogle Scholar
  3. 3.
    A. Frank, “Walkers”. “Encyclopaedia of robotics: application and automation” DGRF R.C. ed. Wiley Interscience, (1988).Google Scholar
  4. 4.
    Vehicles”. V. Braitenberg; MIT Press 1984.Google Scholar
  5. 5.
    A. G. Barto et P. Anandan,.”Pattern Recognition Stochastic Learning Automata”. IEEE Trans. S.M.C. 15: 360 (1985).MathSciNetMATHGoogle Scholar
  6. 6.
    C. Touzet, O. Sarzeaud. “Application d’un algorithme d’apprentissage á la génération de formes locomotrices hexapodes”. Journées de Rochebrune AFCET (1992).Google Scholar
  7. 7.
    D. M. Wilson. “Insect Walking”. Annual Rewiew of Entomology 11: 103–122 (1966).CrossRefGoogle Scholar
  8. 8.
    A. Johannet, I. Sarda. “Gait Learning of an Hexapod Robot: from Simulation to Realization”. Proceedings of the 2nd Japan-France Congress on Mechatronics. Takamatsu, Japan,(1994).Google Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • Isabelle Sarda
    • 1
  • Anne Johannet
    • 1
  1. 1.LGI2P, EMA - EERIEAlès cedexFrance

Personalised recommendations