Title :
A deadbeat trajectory controller for nonlinear systems via neural network: a robot case study
Author :
Güzelkaya, Müde ; Kurtulan, Salman ; Goren, Leyla
Author_Institution :
Istanbul Tech. Univ., Turkey
fDate :
6/15/1905 12:00:00 AM
Abstract :
A method for trajectory control of nonlinear systems is presented. Nonlinear feedback is used in order to obtain a linear model, and the nonlinearities and uncertainties remain are modelled by a multilayer neural network. The tracking error between the nonlinear system output and a desired trajectory is attempted to be removed by a deadbeat controller. The algorithm is applied to the trajectory control of a robot arm.
Keywords :
digital control; feedback; neural nets; nonlinear control systems; position control; robots; algorithm; deadbeat controller; deadbeat trajectory controller; digital control; feedback; linear model; multilayer; neural network; nonlinear systems; position control; robot; tracking error; Control systems; Error correction; Multi-layer neural network; Neural networks; Neurofeedback; Nonlinear control systems; Nonlinear systems; Robots; Trajectory; Uncertainty;
Conference_Titel :
Industrial Electronics, 1993. Conference Proceedings, ISIE'93 - Budapest., IEEE International Symposium on
Conference_Location :
Budapest, Hungary
Print_ISBN :
0-7803-1227-9
DOI :
10.1109/ISIE.1993.268746
