An Adaptive Modular Recurrent Cerebellum-Inspired Controller

  • Kiyan MaheriEmail author
  • Alexander Lenz
  • Martin J. Pearson
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10384)


Animals and robots face the common challenge of interacting with an unstructured environment. While animals excel and thrive in such environments, modern robotics struggles to effectively execute simple tasks. To help improve performance in the face of frequent changes in the mapping between action and outcome (change in context) we propose the Modular-RDC controller, a bio-inspired controller based on the Recurrent Decorrelation Control (RDC) architecture. The proposed controller consists of multiple modules, each containing a forward and inverse model pair. The combined output of all inverse models is used to control the plant, with the contribution of each inverse model determined by a responsibility factor. The controller is able to correctly identify the best module for the current context, enabling a significant reduction of 70.9% in control error for a context-switching plant. It is also shown that the controller results in a degree of generalization in control.


Cerebellum Adaptive control Bio-inspired Modular control Adaptive filter Context switching 


  1. 1.
    Kawato, M.: Internal models for motor control and trajectory planning. Curr. Opin. Neurobiol. 9(6), 718–727 (1999)Google Scholar
  2. 2.
    Wolpert, D.M., Kawato, M.: Multiple paired forward and inverse models for motor control. Neural Networks 11(7), 1317–1329 (1998). doi: 10.1016/S0893-6080(98)00066-5
  3. 3.
    Wolpert, D.M., Chris Miall, R., Kawato, M.: Internal models in the cerebellum. Trends Cogn. Sci. 2(9), 338–347 (1998)Google Scholar
  4. 4.
    Imamizu, H., Kuroda, T., Miyauchi, S., Yoshioka, T., Kawato, M.: Modular organization of internal models of tools in the human cerebellum. Proc. Nat. Acad. Sci. 100(9), 5461–5466 (2003)Google Scholar
  5. 5.
    Ito, M.: Historical review of the significance of the cerebellum and the role of purkinje cells in motor learning. Ann. N. Y. Acad. Sci. 978(1), 273–288 (2002)CrossRefGoogle Scholar
  6. 6.
    Fujita, M.: Adaptive filter model of the cerebellum. Biol. Cybern. 45(3), 195–206 (1982)Google Scholar
  7. 7.
    Porrill, J., Dean, P., Stone, J.V.: Recurrent cerebellar architecture solves the motor-error problem. Proc. Roy. Soc. London-B, 271(1541), 789–796 (2004)Google Scholar
  8. 8.
    Lenz, A., Balakrishnan, T., Pipe, A.G., Melhuish, C.: An adaptive gaze stabilization controller inspired by the vestibulo-ocular reflex. Bioinspiration Biomimetics 3(3), 035001 (2008)Google Scholar
  9. 9.
    Wilson, E.D., Assaf, T., Pearson, M.J., Rossiter, J.M., Anderson, S.R., Porrill, J.: Bioinspired adaptive control for artificial muscles. In: Lepora, N.F., Mura, A., Krapp, H.G., Verschure, P.F.M.J., Prescott, T.J. (eds.) Living Machines 2013. LNCS, vol. 8064, pp. 311–322. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-39802-5_27 CrossRefGoogle Scholar
  10. 10.
    Lenz, A., Anderson, S.R., Pipe, A.G., Melhuish, C., Dean, P., Porrill, J.: Cerebellar-inspired adaptive control of a robot eye actuated by pneumatic artificial muscles. IEEE Trans. Syst. Man Cybern. Part B (Cybernetics) 39(6), 1420–1433 (2009)Google Scholar
  11. 11.
    Narendra, K.S., Balakrishnan, J.: Improving transient response of adaptive control systems using multiple models and switching. IEEE Trans. Autom. Control 39(9), 1861–1866 (1994)Google Scholar
  12. 12.
    Haruno, M., Wolpert, D.M., Kawato, M.: Mosaic model for sensorimotor learning and control. Neural Comput. 13(10), 2201–2220 (2001)Google Scholar
  13. 13.
    Davidson, P.R., Wolpert, D.M.: Internal models underlying grasp can be additively combined. Exp. Brain Res. 155(3), 334–340 (2004)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Kiyan Maheri
    • 1
    Email author
  • Alexander Lenz
    • 1
  • Martin J. Pearson
    • 1
  1. 1.Bristol Robotics LaboratoryBristolUK

Personalised recommendations