Advertisement

Recurrent Neural Networks in a Mobile Robot Navigation Task

  • Branko Šter

Abstract

Recurrent neural networks are applied to the forward modeling of the sensory-motor flow of a miniature mobile robot. It is shown that the robot is able to predict the sensory flow a few steps ahead, which suffices for simple environments. The proposed method requires mainly topological information (little geometrical information is used), simplifying the problem considerably.

Keywords

Mobile Robot Recurrent Neural Network Obstacle Avoidance Sensory Output Sensory Flow 
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. [1]
    R. A. Brooks, “Intelligence without representation” Artificial Intelligence, vol. 47, pp. 262–276, 1991.CrossRefGoogle Scholar
  2. [2]
    J. Tani, “Model-Based Learning for Mobile Robot Navigation from the Dynamical Systems Perspective” IEEE Transactions on Systems, Man, and Cybernetics — Part B:Cybernetics, vol. 26, no. 3, pp. 421–436, 1996.CrossRefGoogle Scholar
  3. [3]
    M. J. Mataric, “Integration of representation Into Goal-Driven Behavior-Based Robots”, IEEE Transactions on Robotics and Automation, vol. 8, no. 3, pp. 304–312, 1992.CrossRefGoogle Scholar
  4. [4]
    R. J. Williams and D. Zipser. “A Learning Algorithm for Continually Running Fully Recurrent Neural Networks”, Neural Computation, vol. 1, pp. 270–280, 1989.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Wien 2001

Authors and Affiliations

  • Branko Šter
    • 1
  1. 1.Faculty of Computer and Information ScienceUniversity of LjubljanaSlovenia

Personalised recommendations