Title :
A learning-based non-linear control system with constraint consideration
Author :
Kamarulzaman, Syafiq Fauzi ; Shibuya, Takeshi ; Yasunobu, Seiji
Author_Institution :
Dept. of Intell. Interaction Technol., Univ. of Tsukuba, Tsukuba, Japan
Abstract :
A learning based control system which can consider control-interfering-constraints is proposed. Reinforcement learning is applied into the system to make it possible to learn to control upon achieving its control objective. Constraints could exist whether in the system manipulate-able parameter or even in non-manipulate-able parameters as in a non-linear control system, thus often causes learning failure when these constraints is not considered. Therefore, reinforcement learning is used to arranged substitute targets that can consider any interfering constraints during the learning process. This control system is applied on an inverted pendulum system and its effectiveness is later confirmed through simulations experiments.
Keywords :
constraint handling; failure analysis; learning (artificial intelligence); learning systems; nonlinear control systems; pendulums; control-interfering constraint; inverted pendulum system; learning failure; learning process; learning-based nonlinear control system; reinforcement learning; system manipulate-able parameter; Angular velocity; Attenuation; Control systems; Educational institutions; Force; Learning; Process control; Constraint; Reinforcement Learning; Substitute Target;
Conference_Titel :
SICE Annual Conference (SICE), 2011 Proceedings of
Conference_Location :
Tokyo
Print_ISBN :
978-1-4577-0714-8
