Cerebellar Augmented Joint Control for a Humanoid Robot

  • Damien Kee
  • Gordon Wyeth
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3276)


The joints of a humanoid robot experience disturbances of markedly different magnitudes during the course of a walking gait. Consequently, simple feedback control techniques poorly track desired joint trajectories. This paper explores the addition of a control system inspired by the architecture of the cerebellum to improve system response. This system learns to compensate the changes in load that occur during a cycle of motion. The joint compensation scheme, called Trajectory Error Learning, augments the existing feedback control loop on a humanoid robot. The results from tests on the GuRoo platform show an improvement in system response for the system when augmented with the cerebellar compensator.


Position Error Humanoid Robot Joint Position Zero Moment Point Receptive Unit 
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.
    Collins, D.: Cerebellar Modeling Techniques for Mobile Robot Control in a Delayed Sensory Environment, PhD Dissertation, University of Queensland (2003)Google Scholar
  2. 2.
    Barto, A.: Learning to reach via corrective movements. Self-Learning Robots III Brainstyle Robotics, 6/1 (1999)Google Scholar
  3. 3.
    Collins, D., Wyeth, G.: Fast and accurate mobile robot control using a cerebellar model in a sensory delayed environment. Intelligent Robots and Systems, 233–238 (2000)Google Scholar
  4. 4.
    Fagg, Sitkoff, N., Barto, A., Houk, J.: A model of Cerebellar Learning for Control of Arm Movements Using Muscle Synergies. In: Computational Intelligence in Robotics and Automation, pp. 6–12 (1997)Google Scholar
  5. 5.
    Kee, D., Wyeth, G., Hood, A., Drury, A.: GuRoo: Autonomous Humanoid Platform for Walking Gait Research. Autonomous Minirobots for Research and Edutainment (2003)Google Scholar
  6. 6.
    McMillan, S.: Computational Dynamics for Robotic Systems on Land and Underwater, PhD Dissertation, Ohio State University (1995)Google Scholar
  7. 7.
    Albus, J.S.: A Theory of Cerebellar Function Mathematical Biosciences, vol. 10, pp. 25–61 (1971)Google Scholar
  8. 8.
    Roberts, J., Wyeth, G., Kee, D.: Generation of humanoid control parameters using a GA. In: ACRA 2003 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Damien Kee
    • 1
  • Gordon Wyeth
    • 1
  1. 1.School of Information Technology and Electrical EngineeringUniversity of QueenslandAustralia

Personalised recommendations