To be able to generate desired movements a robot needs to learn which motor commands move the limb from one position to another. We argue that learning by imitation might be an efficient way to acquire such a function, and investigate favorable properties of the movement used during training in order to maximize the control system’s generalization capabilities. Our control system was trained to imitate one particular movement and then tested to see if it can imitate other movements without further training.


Internal Model Feedback Controller Inverse Model Recurrent Neural Network Motor Command 
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.


  1. 1.
    Belardinelli, A., Pirri, F.: Bottom-up gaze shifts and fixations learning by imitation. IEEE Trans. Syst. Man Cybern. B Cybern. 37(2), 256–271 (2007)CrossRefGoogle Scholar
  2. 2.
    Wood, M.A., Bryson, J.J.: Skill acquisition through program-level imitation in a real-time domain. IEEE Trans. Syst. Man Cybern. B Cybern. 37(2), 1083–4419 (2007)CrossRefGoogle Scholar
  3. 3.
    Meltzoff, A.N., Moore, M.K.: Explaining facial imitation: A theoretical model. Early Development and Parenting 6, 179–192 (1997)CrossRefGoogle Scholar
  4. 4.
    Demiris, Y., Dearden, A.: From motor babbling to hierarchical learning by imitation: a robot developmental pathway. In: Proceedings of the Fifth International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, pp. 31–37 (2005)Google Scholar
  5. 5.
    von Hofsen, C.: An action perspective on motor development. TRENDS in Cognitive Sciences 8(6), 266–272 (2004)CrossRefGoogle Scholar
  6. 6.
    Wolpert, D.M., Miall, R.C., Kawato, M.: Internal models in the cerebellum. Trends in Cognitive Sciences 2(9) (1998)Google Scholar
  7. 7.
    Shadmehr, R., Krakauer, J.W.: A computational neuroanatomy for motor control. Experimental Brain Research 185(3), 359–381 (2008)CrossRefGoogle Scholar
  8. 8.
    Davidson, P.R., Wolpert, D.M.: Widespread access to predictive models in the motor system a short review. Journal of Neural Engineering 2(3), 313–319 (2005)CrossRefGoogle Scholar
  9. 9.
    Kawato, M., Gomi, H.: The cerebellum and vor/okr learning models. TINS 15(11) (1992)Google Scholar
  10. 10.
    Mehta, B., Schaal, S.: Forward models in visuomotor control. Journal of Neuropysiology 88(2), 942–953 (2002)Google Scholar
  11. 11.
    van der Smagt, P., Hirzinger, G.: The cerebellum as computed torque model. In: Howlett, R., Jain, L. (eds.) Fourth International Conference on Knowledge-Based Ingelligent Engineering Systems & Applied Technologies (2000)Google Scholar
  12. 12.
    Jaeger, H.: A tutorial on training recurrent neural networks, covering bppt, rtrl, and the echo state network approach. Techreport, Fraunhofer Institute for AIS (April 2008)Google Scholar
  13. 13.
    Tidemann, A., Öztürk, P.: Self-organizing multiple models for imitation: Teaching a robot to dance the YMCA. In: Okuno, H.G., Ali, M. (eds.) IEA/AIE 2007. LNCS (LNAI), vol. 4570, pp. 291–302. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  14. 14.
    Rolf, M., Steil, J.J., Gienger, M.: Efficient exploration and learning of whole body kinematics. In: IEEE 8th International Conference on Development and Learning (2009)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2010

Authors and Affiliations

  • Rikke Amilde LÄvlid
    • 1
  1. 1.Department of Computer and Information ScienceNorwegian University of Science and TechnologyTrondheimNorway

Personalised recommendations