Representing Robot-Environment Interactions by Dynamical Features of Neuro-controllers

  • Martin Hülse
  • Keyan Zahedi
  • Frank Pasemann
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2684)


This article presents a method, which enables an autonomous mobile robot to create an internal representation of the external world. The elements of this internal representation are the dynamical features of a neuro-controller and their time regime during the interaction of the robot with its environment. As an examples of this method the behavior of a Khepera robot is studied, which is controlled by a recurrent neural network. This controller has been evolved to solve an obstacle avoidance task. Analytical investigations show that this recurrent controller has four behavior relevant attractors, which can be directly related to the following environmental categories: free space, obstacle left/right, and deadlock situation. Temporal sequences of those attractors, which occur during a run of the robot are used to characterize the robot-environment interaction. To represent the temporal sequences a technique, called macro-action maps, is applied. Experiments indicate that macro-action maps allow to built up more complex environmental categories and enable an autonomous mobile robot to solve navigation tasks.


Mobile Robot Output Unit Sharp Corner Successor Node Autonomous Mobile Robot 
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.
    Angeline, P.J., Saunders, G.B., Pollack, J.B.: An Evolutionary Algorithm that Evolves Recurrent Neural Networks. IEEE Transactions on Neural Networks 5, 54–65 (1994)CrossRefGoogle Scholar
  2. 2.
    Arbib, M.A., Erdi, P., Szentagothai, J.: Neural Organization: Structure, Function, and Dynamics. MIT Press, Cambridge (1998)Google Scholar
  3. 3.
    Bajcsy, R.: Active Perception. In: Proceedings of the IEEE, vol. 76, pp. 996–1005 (1988)Google Scholar
  4. 4.
    Ballad, D.H.: Animate vision. Artificial Intelligence 48, 57–86 (1991)CrossRefGoogle Scholar
  5. 5.
    Beer, R.: A dynamical systems perspective on agent-environment interaction. Artificial Intelligence 72(1), 173–215 (1995)CrossRefGoogle Scholar
  6. 6.
    Bickhard, M.H., Treveen, L.: Foundational Issues in Artificial Intelligence and Cognitive Science. Elsevier Scientific, Amsterdam (1995)Google Scholar
  7. 7.
    Braitenberg, V.: Vehicles: Experiments in Synthetic Psychology. MIT Press, Cambridge (1984)Google Scholar
  8. 8.
    Harnard, S.: The symbold grouding problem. Physica D 42, 335–346 (1990)CrossRefGoogle Scholar
  9. 9.
    Hülse, M., Pasemann, F.: Dynamical neural schmitt trigger for robot control. In: Dorronsoro, J.R. (ed.) ICANN 2002. LNCS, vol. 2415, pp. 783–788. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  10. 10.
    Hülse, M.: Implementation of homing behavior based on a recurrent neuro-controller and macro-action maps, MPEG video 12.12 (2002),
  11. 11.
    Krichmar, J.L., Edelman, G.M.: Machine Psychology: Autonomous Behavior, Perceptual Categorization, and Conditioning in a Brain-Based Device. Cerebral Cortex 12, 818–830 (2002)CrossRefGoogle Scholar
  12. 12.
    Matarić, M.J.: Navigating With a Rat Brain: A Neurobiologically-Inspired Model for Robot Spatial Representation. In: Proceedings of the International Conference on Simulation of Adaptive Behavior: From Animals to Animats, vol. 3, pp. 282–290 (1994)Google Scholar
  13. 13.
    Metta, G., Fitzpatrick, P.: Better Vision Through Manipulation. In: Prince, C.G., Demiris, Y., Marom, Y., Kozima, H., Balkenius, C. (eds.) Proceedings of the Second International Workshop on Epigenetic Robotics: Modeling Cognitive Developement in Robotic Systems. Lund University Cognitive Studies, vol. 94, pp. 97–104 (2002)Google Scholar
  14. 14.
    Michel, O.: Khepera Simulator Package version 2.0: Freeware mobile robot simulator written at the University of Nice Sophia-Antipolis by Oliver Michel. Downloadable from the World Wide, Web at
  15. 15.
    Möller, R.: Perception Through Anticipation - A Behavior-Based Approach to Visual Perception. In: Riegler, A., von Stein, A., Peschl, M. (eds.) Understanding Representation in the Cognitive Sciences. Plenum Press, New York (1999)Google Scholar
  16. 16.
    Mondada, F., Franzi, E., Ienne, P.: Mobile robots miniaturization: a tool for investigation in Control Algorithms. In: Proceedings of ISER 1993, Kyoto (October 1993)Google Scholar
  17. 17.
    Mondada, F., Floreano, D.: Evolution of neural control structures: Some experiments on mobile robots. Robotics and Autonomous Systems 16, 183–195 (1995)CrossRefGoogle Scholar
  18. 18.
    Nolfi, S., Floreano, D.: Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines. MIT Press, Cambridge (2000)Google Scholar
  19. 19.
    Nolfi, S., Marocco, D.: Active Perception: A Sensorimotor Account of Object Categorization. In: Proceedings of the 7th International Conference on Simulation of Adaptive Behavior: From Animals to Animats, vol. 7, pp. 266–271 (2002)Google Scholar
  20. 20.
    Pasemann, F.: Dynamics of a single model neuron. International Journal of Bifurcation and Chaos 2, 271–278 (1993)CrossRefMathSciNetGoogle Scholar
  21. 21.
    Pasemann, F.: Neuromodules: A dynamical systems approach to brain modelling. In: Herrmann, H., Pöppel, E., Wolf, D. (eds.) Supercomputing in Brain Research - From Tomography to Neural Networks, pp. 331–347. World Scientific, Singapore (1995)Google Scholar
  22. 22.
    Pasemann, F.: Characteristics of periodic attractors in neural ring networks. Neural Networks 8, 421–429 (1995)CrossRefGoogle Scholar
  23. 23.
    Pasemann, F., Steinmetz, U., Hülse, M., Lara, B.: Robot control and the evolution of modular neurodynamics. Theory in Biosciences 120, 311–326 (2001)Google Scholar
  24. 24.
    Tani, J.: An Interpretation of the “Self” From the Dynamical Systems Perspective: A Constructivist Approach. Journal of Consciousness Studies 5(5-6) (1998)Google Scholar
  25. 25.
    Tani, J., Sugita, Y.: On the Dynamics of Robot Exploration Learning. In: Floreano, D., Mondada, F. (eds.) ECAL 1999. LNCS, vol. 1674, pp. 279–288. Springer, Heidelberg (1999)Google Scholar
  26. 26.
    Wolpert, D.M., Ghahramani, Z., Flanagan, J.R.: Perspectives and problems in motor learning. Trends in Cognitive Science 5(11), 487–494 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Martin Hülse
    • 1
  • Keyan Zahedi
    • 1
  • Frank Pasemann
    • 1
  1. 1.Fraunhofer Institute for Autonomous Intelligent Systems (AIS)Sankt AugustinGermany

Personalised recommendations