Angular Memory and Supervisory Modules in a Neural Architecture for Navigating NOMAD

  • Catarina Silva
  • Manuel Crisóstomo
  • Bernardete Ribeiro
Conference paper


This paper presents a neural modular architecture for navigating mobile robots. The proposed architecture, based on functional task division, has been shown to be efficient in previous work [1, 2].

The traditional difficulties associated with monolithic neural networks are circumvent by introducing a neural modular architecture, developed for the NOMAD mobile robot. The modularity introduced retrieves all the available information, minimizing the incoherence in the training sets, that arises from conflicting training patterns.

After presenting the modular architecture, two additional modules are introduced: Supervisory and Angular Memory. The combination of all defined modules was first tested in simulation and then with the real robot, providing a solution to the problem of navigating NOMAD mobile robot to an objective in an unknown environment.


Mobile Robot Real Robot Ultrasonic Sensor Modular Architecture Neural Architecture 
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]
    C. Silva, M. Crisostomo, B. Ribeiro, “MONODA: A Keural Modular Architecture for Obstacle Avoidance Without Knowledge of the Environment”, in Proceedings of the 2000 International Joint Conference on Neural Networks, 24–27 July 2000.Google Scholar
  2. [2]
    C. Silva, M. Crisóstomo, B. Ribeiro, “A Modular Learning Architecture for Navigating NOMAD Mobile Robot”, 8th International Conference on Information Processing and Management of Uncertainty in Knowledge Based Systems, 3–7 July 2000.Google Scholar
  3. [3]
    A. Schmidt, Z. Bandar, “A Modular Neural Network Architecture with Additional Generalisation Abilities for Large Input Vectors”, in Proceedings of the ICANNGA97, Springer-Verlag, pp 40–43, April 1997.Google Scholar
  4. [4]
    G. Auda, M. Kamel, “Modular Neural Networks: A Survey”, in International Journal of Neural Systems, Vol. 9, No.2, pp. 129–151, 1999.CrossRefGoogle Scholar
  5. [5]
    A. Sharkey (Ed.), “Combining Artificial Neural Networks”, Springer-Verlag, 1999.Google Scholar
  6. [6]
    S. Haykin, “Neural Networks — a comprehensive foundation”, Prentice Hall, 1999.Google Scholar
  7. [7]
    E. Baum, D. Haussler, “What Size Net Gives Valid Generalization?”, in Neural Computation, vol. 1, pp. 151–160, 1989.CrossRefGoogle Scholar
  8. [8]
    T. Kwok, D. Yeung, “Constructive Algorithms for Structure Learning in Feed Forward Neural Networks for Regression Problems”, in IEEE Transactions on Neural Networks, Vol. 8(3), pp. 630–645, 1997.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Wien 2001

Authors and Affiliations

  • Catarina Silva
    • 1
    • 2
  • Manuel Crisóstomo
  • Bernardete Ribeiro
    • 2
  1. 1.Escola Superior de Tecnologia e Gestão de LeiriaUniversidade de CoimbraCoimbraPortugal
  2. 2.Departamento de Engenharia Informática, Centro de Informática e SistemasUniversidade de CoimbraCoimbraPortugal

Personalised recommendations