Title :
Learning control of an inverted pendulum using a neural network
Author :
Ishida, Tsutomu ; Shiokawa, Naofuai ; Nagado, Tsutomu ; Ganeko, Shinichi
Author_Institution :
Dept. of Electron. & Inf. Eng., Ryukyus Univ., Okinawa, Japan
fDate :
28 Oct-1 Nov 1991
Abstract :
The authors interpret the teaching signal in the backpropagation algorithm proposed for a system controller. They stabilized an actual inverted pendulum using a neural network with a backpropagation algorithm. The problems in using a neural network as a system controller are discussed
Keywords :
control system analysis; learning systems; neural nets; stability; backpropagation; control system analysis; inverted pendulum; learning systems; neural network; stability; teaching signal; Algorithm design and analysis; Control systems; Convergence; Error correction; National electric code; Neural networks; Rails; Sampling methods; Shape; Signal generators;
Conference_Titel :
Industrial Electronics, Control and Instrumentation, 1991. Proceedings. IECON '91., 1991 International Conference on
Conference_Location :
Kobe
Print_ISBN :
0-87942-688-8
DOI :
10.1109/IECON.1991.239063
