Stability Analysis of Optimal Adaptive Control Using Value Iteration With Approximation Errors

被引：55

作者：

Heydari, Ali ^{[1
]}

机构：

[1] Southern Methodist Univ, Dept Mech Engn, Dallas, TX 75205 USA

来源：

IEEE TRANSACTIONS ON AUTOMATIC CONTROL | 2018年 / 63卷 / 09期

基金：

美国国家科学基金会;

关键词：

Adaptive dynamic programming; approximation error; stability analysis; value iteration; TIME NONLINEAR-SYSTEMS; CONVERGENCE;

D O I：

10.1109/TAC.2018.2790260

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Effects of the presence of approximation errors are analyzed on the stability of adaptive optimal control using value iteration, initiated from a stabilizing control policy. This analysis includes the system operated using any single/constant resulting control policy and also using an evolving/time-varying control policy. Sufficient conditions on the 'per iteration' approximation errors are obtained for guaranteeing the stability. A feature of the presented results is providing estimations of the region of attraction, under the approximation errors, so that if the initial condition is within this region, the whole trajectory will remain inside the training region, and hence, the function approximation results remain reliable.

引用

页码：3119 / 3126

页数：8

共 18 条

[1] Discrete-time nonlinear HJB solution using approximate dynamic programming: Convergence proof [J].

Al-Tamimi, Asma ;

Lewis, Frank L. ;

Abu-Khalaf, Murad .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2008, 38 (04) :943-949

[2]

[Anonymous], 1996, Neuro-dynamic programming

[3] Value and Policy Iterations in Optimal Control and Adaptive Dynamic Programming [J].

Bertsekas, Dimitri P. .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2017, 28 (03) :500-509

[4] Stability Analysis of Optimal Adaptive Control Under Value Iteration Using a Stabilizing Initial Policy [J].

Heydari, Ali .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (09) :4522-4527

[5] Theoretical and Numerical Analysis of Approximate Dynamic Programming with Approximation Errors [J].

Heydari, Ali .

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS, 2016, 39 (02) :301-311

[6] Revisiting Approximate Dynamic Programming and its Convergence [J].

Heydari, Ali .

IEEE TRANSACTIONS ON CYBERNETICS, 2014, 44 (12) :2733-2743

[7] MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS [J].

HORNIK, K ;

STINCHCOMBE, M ;

WHITE, H .

NEURAL NETWORKS, 1989, 2 (05) :359-366

[8]

Khalil H. K., 2002, Nonlinear systems, P111

[9]

Kirk Donald E., 1970, OPTIMAL CONTROL THEO, P53

[10] Relaxing dynamic programming [J].

Lincoln, Bo ;

Rantzer, Anders .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2006, 51 (08) :1249-1260

← 1 2 →