Neural Networks (NN) Using Genetic Algorithms (GA) and Gradient Back-Propagation (GBP) for an Intelligent Obstacle Avoidance Behavior

  • A. Chohra
  • O. Azouaoui
Conference paper


To ensure more autonomy and intelligence with real-time processing capabilities for the obstacle avoidance behavior of Intelligent Autonomous Vehicles (IAV), the use of Neural Networks (NN) is necessary to bring this behavior near to that of humans in the recognition, learning, adaptation, reasoning and decision-making, and action. In this paper, three (03) supervised learning algorithms namely Gradient Back-Propagation (GBP), Genetic Algorithms (GA) and GA-GBP are suggested to train a NN to learn spatial obstacle avoidance situations. A synthesis of the suggested NN/GBP, NN/GA and NN/GA-GBP is presented where their results and performances are discussed. Finally, a Field-Programmable Gate Array (FPGA) architecture, characterized by its high flexibility and compactness, is suggested for the NN implementation.


Genetic Algorithm Obstacle Avoidance Static Obstacle Mobile Robot Navigation Multilayer Feedforward Neural Network 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    O. Azouaoui and A. Chohra, “Evolution, behavior, and intelligence of Autonomous Robotic Systems (ARS),” in Proc. 3 rd Int. IFAC Conf. Intelligent Autonomous Vehicles, Spain, 1998, pp. 139–145.Google Scholar
  2. [2]
    T. Fukuda, F. Arai, and K. Shimojima, “Intelligent robotic system,” in Proc. Int.IMACS IEEE-SMC Multiconf. Computational Engineering in Systems Applications, Lille, France, 1996, pp. 01–10.Google Scholar
  3. [3]
    D.B. Marco, A.J. Healey, and R.B. McGhee, “Autonomous underwater vehicles: Hybrid control of mission and motion,” Autonomous Robots, vol. 3, no. 2/3, pp. 169–186, 1996.CrossRefGoogle Scholar
  4. [4]
    K. Schilling and C. Jungius, “Mobile robots for planetary exploration,” Int. Conf. Intelligent Autonomous Vehicles, Finland, 1995, pp. 110–120.Google Scholar
  5. [5]
    A. Chohra, A. Farah, and C. Benmehrez, “Neural navigation approach for intelligent Autonomous Vehicles (IAV) in partially structured environments,” Int. J. of Applied Intelligence, vol. 8, no. 3, pp. 219–233, May/June 1998.CrossRefGoogle Scholar
  6. [6]
    H. Herbstreith, L. Gmeiner, and P. Preuß, “A target-directed neurally controlled vehicle,” in Proc. Int. IF AC Conf. Artificial Intelligence in Real-Time Control, Delft, The Netherlands, 1992, pp. 67–71.Google Scholar
  7. [7]
    M. Meng and A.C. Kak, “Mobile robot navigation using neural networks and nonmetrical environment models,” IEEE Control Systems, pp. 30–39, October 1993.Google Scholar
  8. [8]
    E. Sorouchyari, “Mobile robot navigation: A neural network approach,” in Proc. Art Coll. Neuro., Eco. Poly., Lausanne, 1989, pp. 159–175.Google Scholar
  9. [9]
    J.A. Anderson, An Introduction to Neural Networks, The MIT Press, Cambridge, MA, London, England, 1995.MATHGoogle Scholar
  10. [10]
    J.A. Freeman and D.M. Skapura, Neural Networks: Algorithms, Applications, and Programming Techniques, Addison-Wesley, 1992.Google Scholar
  11. [11]
    D.E. Goldberg, Algorithmes Génétiques: Exploration, Optimisation et Apprentissage Automatique, Addison-Wesley, France, 1994.Google Scholar
  12. [12]
    T. Khanna, Foundations of Neural Networks, Addison-Wesley, 1990.MATHGoogle Scholar
  13. [13]
    D.W. Patterson, Artificial Neural Networks: Theory and Applications, Prentice-Hall, Simon & Schuster (Asia) Pte Ltd, Singapore, 1996.MATHGoogle Scholar
  14. [14]
    S.T. Welstead, Neural Network and Fuzzy Logic Applications in C/C++, Jhon Wiley & Sons Inc., Toronto, 1994.Google Scholar
  15. [15]
    S. Cherian and W. Troxell, “Intelligent behavior in machines emerging from a collection of interactive control structures,” Computational Intelligence, vol. 11, no. 4, pp. 565–592, November 1995.CrossRefGoogle Scholar
  16. [16]
    S. Thrun and T.M. Mitchell, “Lifelong robot learning,” Robotics and Autonomous Systems, 15, pp. 25–46, 1995.CrossRefGoogle Scholar
  17. [17]
    Y.S. Kim, I.H. Hwang, J.G. Lee, and H. Chung, “Spatial learning of an autonomous mobile robot using model-based approach,” in Proc. Int. Conf Intelligent Autonomous Vehicles, Finland, 1995, pp. 250–255.Google Scholar
  18. [18]
    H. Kitano, “Empirical studies on the speed of convergence of neural network training using genetic algorithms,” in Proc. 8th National Conf. in Artificial Intelligence, Boston MASS, vol. 2, 1990, pp. 789–795.Google Scholar
  19. [19]
    D.J. Montana and L. Davis, “Training feedforward neural networks using genetic algorithms,” in Proc. 11th Int. Joint Conf. on Artificial Intelligence, Morgan Kaufman, San Mateo CA, 1989, pp. 762–767.Google Scholar
  20. [20]
    M. McInerney and A.P. Dhawan, “Use of genetic algorithms with back propagation in training of feed-forward neural networks,” in Proc. Int. IEEE Conf Neural Networks, vol. I, California, 1993, pp. 203–208.CrossRefGoogle Scholar
  21. [21]
    O. Azouaoui, “Neural networks based approach for the manipulators inverse Jacobian problem,” in Proc. ICSC Int. Conf on Neural Computing, Austria, 1998, pp. 966–972.Google Scholar

Copyright information

© Springer-Verlag Tokyo 2002

Authors and Affiliations

  • A. Chohra
    • 1
  • O. Azouaoui
    • 2
  1. 1.Laboratoire de Vision et Robotique (LVR)Ecole Nationale Supérieure d’Ingénieurs (ENSI) de BourgesBourgesFrance
  2. 2.Laboratoire de Robotique et d’Intelligence ArtificielleCDTA — Centre de Développement des Technologies AvancéesAlgeria

Personalised recommendations