Learning fine motion by using the Hierarchical Extended Kohonen Map

  • Cristina Versino
  • Luca Maria Gambardella
Oral Presentations: Applications Applications in Robotics
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1112)


A Hierarchical Extended Kohonen Map (HEKM) learns to associate actions to perceptions under the supervision of a planner: they cooperate to solve path finding problems. We argue for the utility of using the hierarchical version of the KM instead of the “flat” KM. We measure the benefits of cooperative learning due to the interaction of neighboring neurons in the HEKM. We highlight a beneficial side-effect obtained by transferring motion skill from the planner to the HEKM, namely, smoothness of motion.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Clearwater, S.H., Hogg, T., Huberman, B.A. (1992) Cooperative Problem Solving. In Huberman, B.A., Editor, Computation: The Micro and the Macro View., World Scientific.Google Scholar
  2. 2.
    Fritzke, B. (1995) A Growing Neural Gas Network Learns Topologies. In Tesauro, G., Touretzky, D.S., Leen, T.K., Editors, Advances in Neural Information Processing Systems 7, MIT Press, Cambridge MA, pp. 625–632.Google Scholar
  3. 3.
    Gambardella, L.M., Versino, C. (1994) Learning High-Level Navigation Strategies from Sensor Information and Planner Experience. Proc. PerAc94, From Perception to Action Conference, Lausanne, Switzerland, September 7–9, pp. 428–431.Google Scholar
  4. 4.
    Heikkonen, J., Koikkalainen, P., Oja, E. (1993) Motion Behavior Learning by Self-Organization. Proc. ICANN93, International Conference on Artificial Neural Networks, Amsterdam, The Netherlands, September 13–16, pp.262–267.Google Scholar
  5. 5.
    Heikkonen, J., Millán, J. del R., Cuesta, E. (1995) Incremental Learning from Basic Reflexes in an Autonomous Mobile Robot. Proc. EANN95, International Conference on Engineering Applications of Neural Networks, Otaniemi, Espoo, Finland, August 21–23, pp. 119–126.Google Scholar
  6. 6.
    Knobbe, A.J., Kok, J.N., Overmars, M.H. (1995) Robot Motion Planning in Unknown Environments Using Neural Networks. Proc. ICANN95, International Conference on Artificial Neural Networks, Paris, France, October 9–13, pp. 375–380.Google Scholar
  7. 7.
    Millán, J. del R. (1995) Reinforcement Learning of Goal-Directed Obstacle-Avoiding Reaction Strategies in an Autonomous Mobile Robot. Robotics and Autonomous Systems, 15(3), pp. 275–299.Google Scholar
  8. 8.
    Ritter, H., Martinetz, T., Schulten, K. (1992) Neural Computation and Self-Organizing Maps. An Introduction. Addison-Wesley Publishing Comp.Google Scholar
  9. 9.
    Versino, C., Gambardella, L.M. (1995) Learning Fine Motion in Robotics by Using Hierarchical Neural Networks. IDSIA-5-1995 Technical Report.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Cristina Versino
    • 1
  • Luca Maria Gambardella
    • 1
  1. 1.IDSIALuganoSwitzerland

Personalised recommendations