The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지

A study on the stabilization control of an inverted pendulum system using CMAC-based decoder

CMAC 디코더를 이용한 도립 진자 시스템의 안정화 제어에 관한 연구

  • 박현규 (부산정보대학 정보통신계열) ;
  • 이현도 (통일중공업㈜) ;
  • 한창훈 (동아대학교 전자공학과) ;
  • 안기형 (부산정보대학 정보통신계열) ;
  • 최부귀 (동아대학교 전자공학과)
  • Published : 1998.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presetns an adaptive critic self-learning control system with cerebellar model articulation controller (CMAC)-based decoder integrated with the associative search element (ASE) and adatpive critic element(ACE)- based scheme. The tast of the system is to balance a pole that is hinged to a movable cart by applying forces to the cart's base. The problem is that error feedback information is limited. This problem can be sloved when some adaptive control devices are involved. The ASE incorporates prediction information for reinforrcement from a critic to produce evaluative information for the plant. The CMAC-based decoder interprets one state to a set of patways into the ASE/ACE. These signals correspond to te current state and its possible preceding action states. The CMAC's information interpolation improves the learning speed. And design inverted pendulum hardware system to show control capability with neural network.

Keywords

References

  1. Dynamics of physical system R.H. Cannon
  2. System dynamics Katsuhiko Ogata
  3. Digital control systems Rolf Isermann
  4. Computer and Elec. Eng. v.5 Computer control of double inverted pendulum K. Furuta;T. Okutani;H. Some
  5. Robotica v.6 Design and simulation of control systems of an inverted pendulum Qing Feng;Kazuo Yamafuki
  6. IEEE Journal of Robotics and Automat v.RA-3 Sensor-based control of robotics manipulator using a general learning algorithm W.T. Miller
  7. IEEE Control Systems Magazine v.9 Learning To Control An Inverted Pendulum Using Neural Networks C.W. Anderson
  8. Biology Cybernetics v.43 Synthesis of Nonlinear Control Surfaces by a Layered Associative Search Network A.G. Barto;C.W. Anderson;R.S. Sutton
  9. IEEE Transactions on Systems, Man, and Cybernetics, SMX-13 Neuron-like Adaptive Elements That Can Solve Difficult Learning Control Problems A.G. Barto;R.S. Sutton;C.W. Anderson
  10. Biology Cybernetics v.42 Landmark learning : An illustration of associative search A.G. Barto;R.S. Sutton
  11. Biology cybernetics v.40 Associative Search Network : A Reinforcement Learning Associative Memory A.G. Barto;R.S. Sutton
  12. Journal of Dynamics Systems, Measurement, and Control A New Approach to Manipulator control:The Cerebellar Medel Articulation Controller(CMAC) Albus, J.S.
  13. Journal of Dynamic Systems, Measurement and control Data Storage in the Cerebellar Medel Articulation controller(CMAC) Albus, J.S.
  14. Machine Intelligence v.2 BOXES : An experiment in adaptive control D. Michie;R. A. Chambers
  15. IEEE Control Systmes Magazine v.10 A comparison between CMAC neural Network Control and two traditinal Adaptive control system L.G. Kraft;D.P. Campagna