Neural dynamic optimization for control systems - Part II: Theory

被引：17

作者：

Seong, CY ^{[1
]}

Widrow, B ^{[1
]}

机构：

[1] Stanford Univ, Dept Elect Engn, Informat Syst Lab, Stanford, CA 94305 USA

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS | 2001年 / 31卷 / 04期

基金：

美国国家科学基金会; 美国国家航空航天局;

关键词：

dynamic programming; information time shift operator; learning operator; neural dynamic optimization; neural networks; nonlinear systems; optimal feedback control;

D O I：

10.1109/3477.938255

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The paper presents neural dynamic optimization (NDO) as a method of optimal feedback control for nonlinear multi-input-multi-output (MIMO) systems. The main feature of NDO is that it enables neural networks to approximate the optimal feedback solution whose existence dynamic programming (DP) justifies, thereby reducing the complexities of computation and storage problems of the classical methods such as DR This paper mainly describes the theory of NDO, while the two other companion papers of this topic explain the background for the development of NDO and demonstrate the method with several applications including control of autonomous vehicles and of a robot arm, respectively.

引用

页码：490 / 501

页数：12

共 17 条

[1]

Boyd S., 1991, LINEAR CONTROLLER DE

[2]

Bryson A.E., 1999, Dynamic Optimization

[3]

Franklin G., 1994, Feedback Control of Dynamic Systems

[4]

Franklin G.F., 1998, Digital Control of Dynamics Systems, V3rd ed.

[5]

Isidori A., 1989, NONLINEAR CONTROL SY

[6]

KAILATH T., 1979, Linear systems

[7]

Khalil H. K., 1992, NONLINEAR SYSTEMS

[8]

Lewis FL., 1995, OPTIMAL CONTROL

[9]

Noble B., 1988, APPL LINEAR ALGEBRA

[10] Neural dynamic optimization for control systems - Part III: Applications [J].

Seong, CY ;

Widrow, B .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2001, 31 (04) :502-513

← 1 2 →