Applied Intelligence

, Volume 17, Issue 1, pp 11–33 | Cite as

Searching a Scalable Approach to Cerebellar Based Control

  • Jan Peters
  • Patrick van der Smagt


Decades of research into the structure and function of the cerebellum have led to a clear understanding of many of its cells, as well as how learning might take place. Furthermore, there are many theories on what signals the cerebellum operates on, and how it works in concert with other parts of the nervous system. Nevertheless, the application of computational cerebellar models to the control of robot dynamics remains in its infant state. To date, few applications have been realized.

The currently emerging family of light-weight robots (Hirzinger, in Proc. Second ecpd Int. Conference on Advanced Robotics, Intelligent Automation and Active Systems, 1996) poses a new challenge to robot control: due to their complex dynamics traditional methods, depending on a full analysis of the dynamics of the system, are no longer applicable since the joints influence each other dynamics during movement. Can artificial cerebellar models compete here?

robot dynamics robot arm control computational cerebellar models neural networks 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    S. Arimoto and F. Miyazaki, “Stability and robustness of PID feedback control for robot manipulators of sensory capability,” in Proceedings of the First International Symposium on Robotics Research, edited by M. Brady and R.P. Paul, MIT Press: Cambridge MA, pp. 783–801, 1984.Google Scholar
  2. 2.
    C.-P. Chou and B. Hannaford, “Measurement and modeling of McKibben pneumatic artificial muscles,” IEEE Transactions on Robotics and Automation, vol. 12, no. 1, pp. 90–102, ]1996.Google Scholar
  3. 3.
    M. Katayama and M. Kawato, “Learning trajectory and force control of an artificial muscle arm by parallel-hierarchical neural network model,” in Advances in Neural Information Processing Systems, edited by R. Lippmann, J. Moody, and D. Touretzky, Morgan Kaufmann: San Mateo, vol. 3, pp. 436–442, 1991.Google Scholar
  4. 4.
    T. Hesselroth, K. Sarkar, P. van der Smagt, and K. Schulten, “Neural network control of a pneumatic robot arm,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 24, no. 1, pp. 28–38, 1994.Google Scholar
  5. 5.
    P. van der. Smagt, F. Groen, and K. Schulten, “Analysis and control of a rubbertuator arm,” Biological Cybernetics, vol. 75, no. 5, pp. 433–440, 1996.Google Scholar
  6. 6.
    H.A. Talebi, K. Khorasani, and R.V. Patel, “Neural network based control schemes for flexible-link manipulators: Simulations and experiments,” Neural Networks, vol. 11, no. 7/8, pp. 1357–1377, 1998.Google Scholar
  7. 7.
    K.J. Cole and J.H. Abbs, “Kinematic and electromyographic responses to perturbation of a rapid grasp,” Journal of Neurophysioly, vol. 57, pp. 1498–1510, 1987.Google Scholar
  8. 8.
    R.C. Miall, D.J. Weir, D.M.Wolpert, and J.F. Stein, “Is the cerebellum a Smith predictor?” Journal of Motor Behavior, vol. 25, pp. 203–216, 1993.Google Scholar
  9. 9.
    N. Hogan, “Mechanical impedance of single-and multi-articular systems,” in Multiple Muscle Systems: Biomechanics and Movement Organization edited by J.M. Winters and S.L.-Y. Woo, Springer-Verlag: New York, pp. 149–163, 1990.Google Scholar
  10. 10.
    T. Yoshikawa, Foundations of robotics. MIT Press: Cambridge, MA, 1990.Google Scholar
  11. 11.
    J.J. Slotine and W. Li, “On the adaptive control of robot manipulators,” International Journal of Robotics Research, vol. 6, no. 3, pp. 49–59, 1987.Google Scholar
  12. 12.
    C. Ghez and S. Fahn, “The cerebellum,” in Principles of Neural Science, edited by E.R. Kandel and J.H. Schwartz, Elsevier Science Publishing: Amsterdam, pp. 502–522, 1985.Google Scholar
  13. 13.
    M. Ito, The Cerebellum and Neural Control, Raven Press: New York, 1984.Google Scholar
  14. 14.
    J. Dichgans and H.C. Diener, “Clinical evidence for functional compartmentalization of the cerebellum,” in Cerebellar Function, edited by J.R. Bloedel, Springer Verlag: Berlin, pp. 127–147, 1985.Google Scholar
  15. 15.
    G. Holmes, “The cerebellum of man,” Brain, vol. 62, pp. 1–30, 1939.Google Scholar
  16. 16.
    M. Glickstein, “Cerebellar agenesis,” Brain, vol. 117, pp. 1209–1212, 1994.Google Scholar
  17. 17.
    M. Fahle and V. Braitenberg, “Some quantitive aspects of cerebellar anatomy as guide to speculation on cerebellar functions,” in Cerebellar Function, edited by J.R.B. et al., Springer Verlag: Berlin, pp. 186–200, 1985.Google Scholar
  18. 18.
    C.R. Noback, The Human Nervous System, 2nd edn., McGraw-Hill: New York, 1981.Google Scholar
  19. 19.
    J.D. Keeler, “A dynamical system view of cerebellar function,” Physica D, vol. 42, pp. 386–410, 1990.Google Scholar
  20. 20.
    G. Chauvet, “Habituation rules for a theory of the cerebellar cortex,” Biological Cybernetics, vol. 55, pp. 201–209, 1986.Google Scholar
  21. 21.
    A.C. Guyton, Structure and Function of the Nervous System, W. B. Saunders Company, 1972.Google Scholar
  22. 22.
    Checkley. The Brain, 1999.Google Scholar
  23. 23.
    D.W. Molavi, Neuroscience Tutorial, 1997.Google Scholar
  24. 24.
    J.C. Eccles, M. Ito, and J. Szentagothai, The Cerebellum as a Neuronal Machine, Springer-Verlag: Berlin, 1967.Google Scholar
  25. 25.
    M. Rosheim, Robot Evolution: The Development of Anthrorobotics, John Wiley and Sons: New York, 1994.Google Scholar
  26. 26.
    M. Vrahas, R. Brand, T. Brown, and J. Andrews, “Contribution of passive tissues to the intersegmental moments of the hip,” Journal of Biomechanics, pp. 357–362, 1990.Google Scholar
  27. 27.
    R. Brand, R. Crowninshield, C. Wittstock, D. Petersen, C. Clark, and F.V. Krieken, “A model of lower extremity muscular anatomy,” Transaction of the ASME, pp. 302–320, 1982.Google Scholar
  28. 28.
    J. Mansour and M. Audu, “The passive elastic moment at the knee and its influence on human gait,” Journal of Biomechanics, pp. 369–373, 1986.Google Scholar
  29. 29.
    P. Weiss, I. Hunter, and R. Kearney, “Human ankle joint stiffness over the full range of muscle activation levels,” Journal of Biomechanics, pp. 539–544, 1988.Google Scholar
  30. 30.
    R. Woittiez, P. Huijing, H. Boom, and R. Rozendal, “A threedimensional muscle model: A quantified relation between form and function of skeletal muscles,” Journal of Morphology, pp. 95–113, 1984.Google Scholar
  31. 31.
    J.H. Abbs and K.J. Cole, “Neural mechanisms of motor equivalence and goal achievment,” in Higher Brain Functions: Recent Explorations of the Brain's Emergent Properties, edited by S.P. Wise, John Wiley & Sons: New York, pp. 15–43, 1987.Google Scholar
  32. 32.
    R. Klinke and S. Silbernagl, Lehrbuch für physiologie, Georg Time Verlag.Google Scholar
  33. 33.
    G. Schmidt, Regelungstechnik 1, Skript der Technischen Universität München.Google Scholar
  34. 34.
    M. Ito, “A new physiological concept on cerebellum,” Rev. Neuol. (Paris), pp. 564–569, 1990.Google Scholar
  35. 35.
    D.Wolpert and M. Kawato, “Multiple paired forward and inverse models for motor control,” Neural Networks, vol. 11, pp. 1317–1329, 1998.Google Scholar
  36. 36.
    D. Wolpert, C. Miall, and M. Kawato, “Internal models in the cerebellum,” Trends in Cognitive Sciences, vol. 2, pp. 338–347, 1998.Google Scholar
  37. 37.
    V. Braitenberg and R.P. Atwood, “Morphological observations on the cerebellar cortex,” Journal of Comparative Neurology, vol. 109, pp. 1–34, 1958.Google Scholar
  38. 38.
    V. Braitenberg, “Functional interpretation of cerebellar histology,” Nature, vol. 190, pp. 539–540, 1961.Google Scholar
  39. 39.
    M.A. Arbib, P. Irdi, and J. Szentagothai, Neural Organization: Structure, Function, and Dynamics, MIT Press: Cambridge, MA, pp. 262–302, 1998.Google Scholar
  40. 40.
    D. Marr, “A theory of cerebellar cortex,” Journal of Physiology, vol. 202, pp. 437–470, 1969.Google Scholar
  41. 41.
    J. Albus, “A theory of cerebellar function,” Mathematical Bioscience, vol. 10, pp. 25–61, 1971.Google Scholar
  42. 42.
    M.G. Paulin, “The role of the cerebellum in motor control and perception,” Brain, Behavior, and Evolution, vol. 31, pp. 39–50, 1993.Google Scholar
  43. 43.
    P. van der Smagt and G. Hirzinger, “The cerebellum as computed torque model,” in Fourth International Conference on Knowledge-Based Intelligent Engineering Systems & Allied Technologies, IEEE, pp. 760–763, 2000.Google Scholar
  44. 44.
    M. Ito, M. Sakurai, and P. Tongroach, “Climbing fiber induced depression of both mossy fiber responsiveness and glutamate sensitivity of cerebellar Purkinje cells,” Journal of Physiology, vol. 324, pp. 113–134, 1982.Google Scholar
  45. 45.
    T.V.P. Bliss and G. Collingridge, “A synaptic model of memory: Long-term potentiation in the hippocampus,” Nature, vol. 361, pp. 31–39, 1993.Google Scholar
  46. 46.
    A. Artola and W. Singer, “Long-term depression of excitatory synaptic transmission and its relationship to long-term potentiation,” Trends in Neuroscience, vol. 16, pp. 480–487, 1993.Google Scholar
  47. 47.
    E. De Schutter, “A new functional role for cerebellar long term depression,” Progress in Brain Research, vol. 114, pp. 529–542, 1997.Google Scholar
  48. 48.
    J.I. Simpson, D.R. Wylie, and C.I. De Zeeuw, “On climbing fiber signals and their consequence(s),” Behavioral and Brain Sciences, vol. 19, pp. 384–398, 1996.Google Scholar
  49. 49.
    Ebner and Bloedel, “Neural organization: Structure, function, and dynamics,” pp. 262–302, 1984.Google Scholar
  50. 50.
    M. Kawato and H. Gomi, “A computational model of four regions of the cerebellum based on feedback-error learning,” Biological Cybernetics, vol. 68, pp. 95–103, 1992.Google Scholar
  51. 51.
    P.F.C. Gilbert and W.T. Thach, “Purkinje cell activity during learning,” Brain Research, vol. 128, pp. 309–328, 1977.Google Scholar
  52. 52.
    M. Kawato, “Cerebellum and motor control,” in The Handbook of Brain Theory and Neural Networks, edited by M.A. Arbib, MIT Press: Cambridge, MA, pp. 172–178, 1995.Google Scholar
  53. 53.
    M. Kawato, “Feedback-error-learning neural network for supervised motor learning,” in Neural Networks for Sensory and Motor Systems, edited by R. Eckmiller, Elsevier: Amsterdam, 1990.Google Scholar
  54. 54.
    J.L. Contreras-Vidal, S. Grossberg, and D. Bullock, “A neural model of cerebellar learning for arm movement control: Cortico-spino-cerebellar dynamics,” Learning & Memory, vol. 3, pp. 475–502, 1997.Google Scholar
  55. 55.
    J.C. Houk, “Cooperative control of limb movements by the motor cortex, brainstem, and cerebellum,” in Models of Brain Function, edited by R.M.J. Cotterill, Cambridge University Press: Cambridge, pp. 309–325, 1989.Google Scholar
  56. 56.
    J.C. Houk, J.T. Buckingham, and A.G. Barto, “Models of the cerebellum and motor learning,” Behavioral and Brain Sciences, vol. 19, pp. 368–383, 1996.Google Scholar
  57. 57.
    P. van der Smagt, “Cerebellar control of robot arms,” Connection Science, vol. 10, pp. 301–320, 1998.Google Scholar
  58. 58.
    J.C. Houk, J.T. Buckingham, and A.G. Barto, “Models of the cerebellum and motor learning,” Behavioral and Brain Sciences, vol. 19, no. 3, pp. 368–383, 1996.Google Scholar
  59. 59.
    R. Smith, “Intelligent motion control with an artificial cerebellum,” unpublished doctoral dissertation, University of Auckland, Scalable Approach to Cerebellar Based Control 33 Department of Electrical Engineering, 1999.Google Scholar
  60. 60.
    N. Schweighofer, “atComputational models of the cerebellum in the adaptive control of movements,” unpublished doctoral dissertation, University of Southern California.Google Scholar
  61. 61.
    M. Brown and C. Harris, Neurofuzzy Adaptive Modelling and Control, Prentice Hall: Englewood cliffs, NJ, 1994.Google Scholar
  62. 62.
    W.T. Miller, F.H. Glanz, and L.G. Kraft, “CMAC: An associative neural network alternative to backpropagation,” in Proceedings of the IEEE, Special Issue on Neural Networks, vol. 78, pp. 1561–1567, 1990.Google Scholar
  63. 63.
    M. Lang, “A real-time implementation of a neural-network controller for industrial robotics,” unpublished doctoral dissertation, Institute of Aerospace Studies, University of Toronto, 1997.Google Scholar
  64. 64.
    R. Hewes and W. Miller, “Practical demonstration of a learning control system for a five axis industrial robot,” in Proceedings SPIE Intelligent Robots and Computer Vision, vol. 1002, 1988.Google Scholar
  65. 65.
    W. Miller and A. Kun, “Dynamic balance of a biped walking robot,” in Neural Systems for Robotics, edited by P. van der Smagt and O. Omidvar, Academic Press: San Diego, CA, pp. 17–35, 1997.Google Scholar
  66. 66.
    D. Michie and R.A. Chambers, “BOXES: An experiment in adaptive control,” in Machine Intelligence, edited by E. Dale and D. Michie, Oliver and Boyd: Edinburgh, vol. 2, pp. 137–152, 1968.Google Scholar
  67. 67.
    R. Bellman, Dynamic Programming, Princeton University Press: Princeton, NJ, 1957.Google Scholar
  68. 68.
    W.T. Miller and F.H. Glanz, The University of New Hampshire Implementation of the Cerebellar Model Arithmetic Computer CMAC, Internet-Pages.Google Scholar
  69. 69.
    P.C. Parks and J. Militzer, “A comparison of five algorithms for the training of CMAC memories for learning control systems,” Automatica, vol. 28, no. 5, pp. 1027–1035, 1992.Google Scholar
  70. 70.
    L.G. Kraft, “Optimized weight smoothing for CMAC neural networks,” in Dlr Technical Report 515-97-28 edited by P. van der Smagt, pp. 8–10, 1997.Google Scholar
  71. 71.
    J.C. Houk, S.P. Singh, C. Fisher, and A.G. Barto, “An adaptive sensorimotor network simulation inspired by the anatomy and physiology of the cerebellum,” in Neural Networks for Control, edited by W. Miller, R. Sutton, and P.Werbos, MIT Press: Cambridge, MA, pp. 301–348, 1990.Google Scholar
  72. 72.
    A.G. Barto, J.T. Buckingham, and J.C. Houk, “A predictive switching model of cerebellar movement control,” in Advances in Neural Information Processing Systems, vol. 8, edited by D.S. Touretzky, M.C. Mozer, and M.E. Hasselmo, MIT Press: Boston, MA, pp. 138–144, 1995.Google Scholar
  73. 73.
    A.H. Fagg, N. Sitkoff, A.G. Barto, and J.C. Houk, “Cerebellar learning for control of a two-link arm in muscle space,” in Proceedings of IEEE Conference on Robotics and Automation, pp. 6–12, 1996.Google Scholar
  74. 74.
    A.H. Fagg, N. Sitkoff, A.G. Barto, and J.C. Houk, “A model of cerebellar learning for control of arm movements using muscle synergies,” in Proceedings of IEEE Symposium on Computational Intelligence in Robotics and Automation, pp. 2638–2644, 1997.Google Scholar
  75. 75.
    A.H. Fagg, N. Sitkoff, A.G. Barto, and J.C. Houk, “A computational model of cerebellar learning for limb control, in Proceedings of the Spring Meeting on the Neural Control of Movement, 1997.Google Scholar
  76. 76.
    A.H. Fagg, A.G. Barto, and J.C. Houk, “Learning to reach via corrective movements,” Tenth Yale Workshop on Adaptive and Learning Systems, 1998.Google Scholar
  77. 77.
    A.G. Barto, A.H. Fagg, N. Sitkoff, and J.C. Houk, “A cerebellar model of timing and prediction in the control of reaching,” Neural Computation, vol. 11, no. 3, pp. 565–594, 1999.Google Scholar
  78. 78.
    J. Peters and R. Riener, “A real-time model of the human knee for a virtual orthopaedic trainer,” in print.Google Scholar
  79. 79.
    P. van der Smagt, “Benchmarking cerebellar control,” Robotics and Autonomous Systems, vol. 32, pp. 237–251, 2000.Google Scholar
  80. 80.
    G. Hirzinger, “Towards a new robot generation for space, terrestrial, and medical applications,” in Proc. Second ecpd Int. Conference on Advanced Robotics, Intelligent Automation, and Active Systems, 1996.Google Scholar

Copyright information

© Kluwer Academic Publishers 2002

Authors and Affiliations

  • Jan Peters
    • 1
  • Patrick van der Smagt
    • 2
  1. 1.Computational Learning and Motor Control LabUniversity of Southern CaliforniaLos Angeles
  2. 2.Institute of Robotics and MechatronicsGerman Aerospace Center, DLR OberpfaffenhofenWesslingGermany

Personalised recommendations