A reinforced learning control using iterative error compensation for uncertain dynamical systems

Authors:
Kuei-Shu Hsu;Wen-Shyong Yu;Ming-In Ho
Affiliations:
Department of Automation Engineering, Kao Yuan Institute of Technology, Kaohsiung, Taiwan;Department of Electrical Engineering, Tatung University, Taipei, Taiwan;Department of Mechanical Engineering, China Institute of Technology, Taipei, Taiwan
Venue:
International Journal of Computer Mathematics
Year:
2008

Citing 3
Cited 0

Experiments with reinforcement learning in problems with continuous state and action spaces

Adaptive Behavior
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Iterative Learning Control for Deterministic Systems

Iterative Learning Control for Deterministic Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper investigates a learning control using iterative error compensation for uncertain systems to enhance the precision of a high speed, computer-controlled machining process. It is specially useful in mass-produced parts produced by a high-speed machine tool system. This method uses an iterative learning technique which adopts machine commands and cutting errors experienced from previous manoeuvres as references for compensation actions in the current manoeuvre. Non-repetitive disturbances and nonlinear dynamics of the cutting processes and servo systems of the machine which greatly affect the convergence of the learning control systems were studied in this research. State feedback and output feedback methods were used for controller design. Stability and performance of learning control systems designed via the proposed method were verified by simulations on a single degree of freedom servo positioning system.