DocumentCode :
3633359
Title :
A conjugate gradient-based BPTT-like optimal control algorithm
Author :
Josip Kasac;Josko Deur;Branko Novakovic;Ilya V. Kolmanovsky
Author_Institution :
Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, HR-10000, Croatia
fYear :
2009
Firstpage :
861
Lastpage :
866
Abstract :
The paper presents a conjugate gradient-based numerical algorithm for optimal control of nonlinear multivariable systems with control and state vectors constraints. The algorithm has a backward-in-time recurrent structure similar to the backpropagation-through-time (BPTT) algorithm. The emphasis is on implementation and testing of various conjugate gradient methods. A vehicle dynamics control example demonstrates that the use of conjugate gradient algorithms leads to substantial reduction of computational time when compared to the standard gradient algorithm with a constant learning rate.
Keywords :
"Optimal control","Backpropagation algorithms","Control systems","Cost function","Vehicle dynamics","Nonlinear control systems","Nonlinear equations","Testing","Gradient methods","Automotive engineering"
Publisher :
ieee
Conference_Titel :
Control Applications, (CCA) & Intelligent Control, (ISIC), 2009 IEEE
ISSN :
1085-1992
Print_ISBN :
978-1-4244-4601-8
Type :
conf
DOI :
10.1109/CCA.2009.5281028
Filename :
5281028
Link To Document :
بازگشت