Generalized Hamilton–Jacobi–Bellman Formulation -Based Neural Network Control of Affine Nonlinear Discrete-Time Systems
Authors:
- Zheng ChenZCZheng Chen
- Sarangapani JagannathanSJSarangapani Jagannathan
- 14 January 2008
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 19 (1) , 90-106
Abstract
In this paper, we consider the use of nonlinear networks towards obtaining nearly optimal solutions to the control of nonlinear discrete-time (DT) systems. The method is based on least squares successive approximation solution of the generalized Hamilton-Jacobi-Bellman (GHJB) equation which appears in optimization problems. Successive approximation using the GHJB has not been applied for nonlinear DT systems. The proposed recursive method solves the GHJB equation in DT on a well-defined region of attraction. The definition of GHJB, pre-Hamiltonian function, HJB equation, and method of updating the control function for the affine nonlinear DT systems under small perturbation assumption are proposed. A neural network (NN) is used to approximate the GHJB solution. It is shown that the result is a closed-loop control based on an NN that has been tuned a priori in offline mode. Numerical examples show that, for the linear DT system, the updated control laws will converge to the optimal control, and for nonlinear DT systems, the updated control laws will converge to the suboptimal control.Keywords
This publication has 16 references indexed in Scilit:
- Approximations to optimal feedback control using a successive wavelet collocation algorithm2004
- The swing up control for the Acrobot based on energy control approach2003
- Nearly optimal HJB solution for constrained input systems using a neural network least-squares approach2003
- State-constrained agile missile control with adaptive-critic-based neural networksIEEE Transactions on Control Systems Technology, 2002
- Neural approximations for infinite-horizon optimal control of nonlinear stochastic systemsIEEE Transactions on Neural Networks, 1998
- Galerkin approximations of the generalized Hamilton-Jacobi-Bellman equationAutomatica, 1997
- Optimal nonlinear, but continuous, feedback control of systems with saturating actuatorsInternational Journal of Control, 1995
- Neural Networks1990
- An Approximation Theory of Optimal Control for Trainable ManipulatorsIEEE Transactions on Systems, Man, and Cybernetics, 1979
- On an iterative technique for Riccati equation computationsIEEE Transactions on Automatic Control, 1968