Symbols and Dynamics in Embodied Cognition: Revisiting a Robot Experiment

  • Jun Tani
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2684)


This paper introduces novel analyses that clarify why the dynamical systems approach is essential for studies of embodied cognition by revisiting author’s prior robot experiment studies. Firstly, we argue that the symbol grounding problems as well as the “situatedness” problems should be the consequences of lacking a shared metric space for the interactions between the higher cognitive levels based on symbol systems and the lower sensory-motor levels based on analog dynamical systems. In our prior studies it was proposed to employ recurrent neural networks (RNNs) as adaptive dynamical systems for implementing the top-down cognitive processes by which it is expected that dense interactions can be made between the cognitive and the sensory-motor levels. Our mobile robot experiments in prior works showed that the acquired internal models embedded in the RNN is naturally situated to the physical environment by means of entrainment between the RNN and the environmental dynamics. In the current study, further analysis was conducted on the dynamical structures obtained in the experiments, which turned out to clarify the essential differences between the conventional symbol systems and its equivalence realized in the adaptive dynamical systems.


Sensory Input Recurrent Neural Network Global Attractor Motor Program Symbol System 
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.
    Beer, R.: A dynamical systems perspective on agent-environment interaction. Artificial Intelligence 72, 173–215 (1995)CrossRefGoogle Scholar
  2. 2.
    Crutchfield, J.: Inferring statistical complexity. Phys Rev Lett 63, 105–108 (1989)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Elman, J.: Finding structure in time. Cognitive Science 14, 179–211 (1990)CrossRefGoogle Scholar
  4. 4.
    Gunji, Y., Konno, N.: Artificial Life with Autonomously Emerging Boundaries. App. Math. Computation 43, 271–298 (1991)zbMATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Harnad, S.: The symbol grounding problem. Physica D 42, 335–346 (1990)CrossRefGoogle Scholar
  6. 6.
    Jordan, M., Rumelhart, D.: Forward models: supervised learning with a distal teacher. Cognitive Science 16, 307–354 (1992)CrossRefGoogle Scholar
  7. 7.
    Kolen, J.: Exploring the computational capabilities of recurrent neural networks. PhD thesis, The Ohio State University (1994)Google Scholar
  8. 8.
    Kuipers, B.: A qualitative approach to robot exploration and map learning. In: AAAI Workshop Spatial Reasoning and Multi-Sensor Fusion, Chicago, pp. 774–779 (1987)Google Scholar
  9. 9.
    Mataric, M.: Integration of representation into goal-driven behavior-based robot. IEEE Trans. Robotics and Automation 8, 304–312 (1992)CrossRefGoogle Scholar
  10. 10.
    Matsuno, K.: Physical Basis of Biology. CRC Press, Boca Raton (1989)Google Scholar
  11. 11.
    Maturana, H., Varela, F.: Autopoiesis and cognition: the realization of the living. D. Riedel Publishing, Boston (1980)Google Scholar
  12. 12.
    Pollack, J.: The induction of dynamical recognizers. Machine Learning 7, 227–252 (1991)Google Scholar
  13. 13.
    Rumelhart, D., Hinton, G., Williams, R.: Learning internal representations by error propagation. In: Rumelhart, D., Mclelland, J. (eds.) Parallel Distributed Processing. MIT Press, Cambridge (1986)Google Scholar
  14. 14.
    Tani, J.: Model-Based Learning for Mobile Robot Navigation from the Dynamical Systems Perspective. IEEE Trans. on SMC (B) 26, 421–436 (1996)Google Scholar
  15. 15.
    Tani, J.: An interpretation of the ”self” from the dynamical systems perspective: a constructivist approach. Journal of Consciousness Studies 5, 516–542 (1998)Google Scholar
  16. 16.
    Tani, J.: Learning to generate articulated behavior through the bottom-Up and the top-down interaction processes. Neural Networks 16, 11–23 (2003)CrossRefGoogle Scholar
  17. 17.
    Tani, J., Fukumura, N.: Embedding a Grammatical Description in Deterministic Chaos: an Experiment in Recurrent Neural Learning. Biological Cybernetics 72, 365–370 (1995)CrossRefGoogle Scholar
  18. 18.
    Tani, J., Ito, M.: Self-organization of behavior primitives as multiple attractor dynamics by the forwarding forward model network. Trans On IEEE SMC-B (2003) (in print)Google Scholar
  19. 19.
    Tani, J., Nolfi, S.: Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems. Neural Networks 12, 1131–1141 (1999)CrossRefGoogle Scholar
  20. 20.
    Tani, J., Yamamoto, J.: On the dynamics of robot exploration learning. Cognitive Systems Research 3, 459–470 (2002)CrossRefGoogle Scholar
  21. 21.
    Tsuda, I.: Toward an interpretation of dynamic neural activity in terms of chaotic dynamical systems. Behavioral and Brain Sciences 24:5, 793–848 (2001)CrossRefGoogle Scholar
  22. 22.
    Wiggins, S.: Introduction to Applied Nonlinear Dynamical Systems and Chaos. Springer, New York (1990)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Jun Tani
    • 1
  1. 1.Brain Science InstituteRIKENSaitamaJapan

Personalised recommendations