DocumentCode :
2428242
Title :
Real-time control of an inverted pendulum system using complementary neural network and optimal techniques
Author :
Nelson, John ; Kraft, L. Gordon
Author_Institution :
Dept. of Electr. & Comput. Eng., New Hampshire Univ., Durham, NH, USA
Volume :
3
fYear :
1994
fDate :
29 June-1 July 1994
Firstpage :
2553
Abstract :
Inverted pendulum is a simple, inherently unstable system which exhibits the fundamental characteristics of balance. This paper explores the control of a robotic pole-balancing system using complementary optimal and neural network techniques. A full state feedback linear regulator type optimal controller was developed from the approximate system model. When applied to the real physical system, this controller produced a relatively large limit cycle, due primarily to unmodelled system nonlinearities. The CMAC neural network was then introduced into the controller to learn any nonlinearities, reject residual noise, and, as a result, shrink the system limit cycle.
Keywords :
cerebellar model arithmetic computers; intelligent control; limit cycles; neurocontrollers; nonlinear control systems; optimal control; real-time systems; robots; state feedback; CMAC neural network; inverted pendulum system; limit cycle; optimal controller; real-time control; residual noise rejection; robotic pole-balancing system; state feedback; system nonlinearities; Control nonlinearities; Control systems; Limit-cycles; Neural networks; Nonlinear control systems; Optimal control; Real time systems; Regulators; Robot control; State feedback;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
American Control Conference, 1994
Print_ISBN :
0-7803-1783-1
Type :
conf
DOI :
10.1109/ACC.1994.735019
Filename :
735019
Link To Document :
بازگشت