Dynamic Generation and Switching of Object Handling Behaviors by a Humanoid Robot Using a Recurrent Neural Network Model

  • Kuniaki Noda
  • Masato Ito
  • Yukiko Hoshino
  • Jun Tani
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4095)


The present study describes experiments on a ball handling behavior learning that is realized by a small humanoid robot with a dynamic neural network model, the recurrent neural network with parametric bias (RNNPB). The present experiments show that after the robot learned different types of behaviors through direct human teaching, the robot was able to switch between two types of behaviors based on the ball motion dynamics. We analyzed the parametric bias (PB) space to show that each of the multiple dynamic structures acquired in the RNNPB corresponds with taught multiple behavior patterns and that the behaviors can be switched by adjusting the PB values.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bianco, R., Nolfi, S.: Evolving the neural controller for a robotic arm able to grasp objects on the basis of tactile sensors. Adaptive Behavior 12(1), 37–45 (2004)CrossRefGoogle Scholar
  2. 2.
    Schaal, S., Sternad, D., Atkeson, C.G.: One-handed juggling: A dynamical approach to a rhythmic movement task. Journal of Motor Behavior 28(2), 165–183 (1996)CrossRefGoogle Scholar
  3. 3.
    Wolpert, D.M., Kawato, M.: Multiple paired forward and inverse models for motor control. Neural Networks 11, 1317–1329 (1998)CrossRefGoogle Scholar
  4. 4.
    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
  5. 5.
    Tani, J.: Learning to generate articulated behavior through the bottom-up and the top-down interaction process. Neural Networks 16, 11–23 (2003)CrossRefGoogle Scholar
  6. 6.
    Ito, M., Tani, J.: Generalization in Learning Multiple Temporal Patterns Using RNNPB. In: Pal, N.R., Kasabov, N., Mudi, R.K., Pal, S., Parui, S.K. (eds.) ICONIP 2004. LNCS, vol. 3316, pp. 592–598. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  7. 7.
    Ito, M., Tani, J.: On-line imitative interaction with a humanoid robot using a dynamic neural network model of a mirror system. Adaptive Behavior 12(2), 93–115 (2004)CrossRefGoogle Scholar
  8. 8.
    Beer, R.: A dynamic systems perspective on agent-environment interaction. Artificial Intelligence 72(1), 173–215 (1995)CrossRefGoogle Scholar
  9. 9.
    van Gelder, T.: The dynamical hypothesis in cognitive science. Behavior and Brain Sciences (1998)Google Scholar
  10. 10.
    Jordan, M.: Attractor dynamics and parallelism in a connectionist sequential machine. In: Erlbaum, L. (ed.) Proc. 1986 Cognitive Science Conference, pp. 531–546 (1986)Google Scholar
  11. 11.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by backpropagating errors. Nature 332, 533–536 (1986)CrossRefGoogle Scholar
  12. 12.
    Tani, J., Ito, M.: Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment. IEEE Transactions on System, Man and Cybernetics Part B 33(4), 481–488 (2003)CrossRefGoogle Scholar
  13. 13.
    Sugita, Y., Tani, J.: Learning semantic combinatoriality from the interaction between linguistic and behavioral processes. Adaptive Behavior 13(1), 33–52 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Kuniaki Noda
    • 1
  • Masato Ito
    • 1
  • Yukiko Hoshino
    • 1
  • Jun Tani
    • 2
  1. 1.Sony Intelligence Dynamics Laboratories, Inc.TokyoJapan
  2. 2.Brain Science Institute, RIKENSaitamaJapan

Personalised recommendations