• DocumentCode
    2791886
  • Title

    A cognitive model with growing structure and its application to learning to control the inverted pendulum

  • Author

    Shao-bai, Zhang ; Xiao-gang, Ruan ; Xie-feng, Cheng ; Zhi-quan, Feng

  • Author_Institution
    Coll. of Comput., Nanjing Univ. of Posts & Telecommun., Nanjing, China
  • fYear
    2009
  • fDate
    17-19 June 2009
  • Firstpage
    4361
  • Lastpage
    4364
  • Abstract
    A growing cognitive model of motor balance skill, which simulates the manners of human beings and animals in motor balance skill learning, is constructed. A neuro-controller based on the model is proposed to balance an inverted pendulum. The cognitive model, whose architecture is similar to the reflex arc of the biologic nerve, adopts a growing algorithm from reference to growing cell structures in order to perform the pattern classification in the nerve center. This growing mechanism is able to be evolved through the continuous growing of the new nerve cell. And reinforcement Hebbian synaptic modification is used as the self-learning method in the cognitive model to make the neurons in difference fields to respond to the different stimulus in the best way. The experimental results are shown that the growing cognitive model can interact autonomously with the environment and develop the motor balance skill by the growing manners of neural system itself.
  • Keywords
    neurocontrollers; nonlinear control systems; pendulums; cognitive model; growing cell structures; growing structure; inverted pendulum; motor balance skill; neuro-controller; pattern classification; reinforcement Hebbian synaptic modification; self-learning method; Animal structures; Biological information theory; Biological system modeling; Cells (biology); Control systems; Humans; Neural networks; Neurons; Pattern classification; Telecommunication control; Cognitive model; Growing Cell Structures; Inverted Pendulum;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Control and Decision Conference, 2009. CCDC '09. Chinese
  • Conference_Location
    Guilin
  • Print_ISBN
    978-1-4244-2722-2
  • Electronic_ISBN
    978-1-4244-2723-9
  • Type

    conf

  • DOI
    10.1109/CCDC.2009.5192401
  • Filename
    5192401