Fixed-Final Time Constrained Optimal Control of Nonlinear Systems Using Neural Network HJB Approach

Author

Cheng, Tao ; Lewis, Frank L.

Author_Institution

Autom. & Robotics Res. Inst., Texas Univ., Arlington, TX

fYear

2006

fDate

13-15 Dec. 2006

Firstpage

3016

Lastpage

3021

Abstract

Fixed-final time constrained input optimal control laws using neural networks to solve Hamilton-Jacobi-Bellman (HJB) equations for general affine in the input nonlinear systems are proposed. A neural network is used to approximate the time-varying cost function using the method of least-squares on a pre-defined region and hence solve the HJB. The result is a neural network nearly optimal constrained feedback controller that has time-varying coefficients found by a priori offline tuning. The results of this paper are demonstrated on an example

Keywords

feedback; function approximation; least squares approximations; neurocontrollers; nonlinear control systems; optimal control; time-varying systems; Hamilton-Jacobi-Bellman equations; finite-horizon optimal control; fixed-final time constrained input optimal control laws; input nonlinear systems; least-squares method; neural network HJB approach; neural network control; neural network nearly optimal constrained feedback controller; time-varying cost function; Adaptive control; Control systems; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Nonlinear equations; Nonlinear systems; Optimal control; Time factors; Time varying systems; Constrained input systems; Finite-horizon Optimal control; Hamilton-Jacobi-Bellman; Neural Network control;

fLanguage

English

Publisher

ieee

Conference_Titel

Decision and Control, 2006 45th IEEE Conference on

Conference_Location

San Diego, CA

Print_ISBN

1-4244-0171-2

Type

conf

DOI

10.1109/CDC.2006.377523

Filename

4177174