Optimal control for a class of nonlinear systems with state delay based on Adaptive Dynamic Programming with ε-error bound

Xiaofeng Lin; Nuyun Cao; Yuzhang Lin

doi:10.1109/ADPRL.2013.6615005

Optimal control for a class of nonlinear systems with state delay based on Adaptive Dynamic Programming with ε-error bound

Xiaofeng Lin, Nuyun Cao, Yuzhang Lin

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, a finite-horizon ε-optimal control for a class of nonlinear systems with state delay is proposed by Adaptive Dynamic Programming (ADP) algorithm. First of all, the performance index function is defined and the Hamilton-Jacobi-Bellman (HJB) equation is obtained for the problem, the convergence of the iterative algorithm is also presented. Then, ADP algorithm for finite-horizon optimal control is introduced with an ε-error bound so as to get the ε-optimal control, and BP neural network is used to implement ADP algorithm. At last, an example is given to demonstrate the effectiveness of the proposed algorithm.

Original language	English (US)
Title of host publication	Proceedings of the 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
Pages	177-182
Number of pages	6
DOIs	https://doi.org/10.1109/ADPRL.2013.6615005
State	Published - 2013
Event	2013 4th IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013 - Singapore, Singapore Duration: Apr 16 2013 → Apr 19 2013

Publication series

Name	IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL
ISSN (Print)	2325-1824
ISSN (Electronic)	2325-1867

Conference

Conference	2013 4th IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013
Country/Territory	Singapore
City	Singapore
Period	4/16/13 → 4/19/13

Keywords

ε-optimal control
Adaptive Dynamic Programming
finite time
nonlinear systems
state delay

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science Applications
Software

Access to Document

10.1109/ADPRL.2013.6615005

Cite this

Lin, X., Cao, N., & Lin, Y. (2013). Optimal control for a class of nonlinear systems with state delay based on Adaptive Dynamic Programming with ε-error bound. In Proceedings of the 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 (pp. 177-182). Article 6615005 (IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL). https://doi.org/10.1109/ADPRL.2013.6615005

Optimal control for a class of nonlinear systems with state delay based on Adaptive Dynamic Programming with ε-error bound. / Lin, Xiaofeng; Cao, Nuyun; Lin, Yuzhang.
Proceedings of the 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 177-182 6615005 (IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lin, X, Cao, N & Lin, Y 2013, Optimal control for a class of nonlinear systems with state delay based on Adaptive Dynamic Programming with ε-error bound. in Proceedings of the 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013., 6615005, IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL, pp. 177-182, 2013 4th IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013, Singapore, Singapore, 4/16/13. https://doi.org/10.1109/ADPRL.2013.6615005

Lin X, Cao N, Lin Y. Optimal control for a class of nonlinear systems with state delay based on Adaptive Dynamic Programming with ε-error bound. In Proceedings of the 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 177-182. 6615005. (IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL). doi: 10.1109/ADPRL.2013.6615005

Lin, Xiaofeng ; Cao, Nuyun ; Lin, Yuzhang. / Optimal control for a class of nonlinear systems with state delay based on Adaptive Dynamic Programming with ε-error bound. Proceedings of the 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. pp. 177-182 (IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL).

@inproceedings{9d16926b62cf40efb90a7e29c361a52a,

title = "Optimal control for a class of nonlinear systems with state delay based on Adaptive Dynamic Programming with ε-error bound",

abstract = "In this paper, a finite-horizon ε-optimal control for a class of nonlinear systems with state delay is proposed by Adaptive Dynamic Programming (ADP) algorithm. First of all, the performance index function is defined and the Hamilton-Jacobi-Bellman (HJB) equation is obtained for the problem, the convergence of the iterative algorithm is also presented. Then, ADP algorithm for finite-horizon optimal control is introduced with an ε-error bound so as to get the ε-optimal control, and BP neural network is used to implement ADP algorithm. At last, an example is given to demonstrate the effectiveness of the proposed algorithm.",

keywords = "ε-optimal control, Adaptive Dynamic Programming, finite time, nonlinear systems, state delay",

author = "Xiaofeng Lin and Nuyun Cao and Yuzhang Lin",

year = "2013",

doi = "10.1109/ADPRL.2013.6615005",

language = "English (US)",

isbn = "9781467359252",

series = "IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL",

pages = "177--182",

booktitle = "Proceedings of the 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013",

note = "2013 4th IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013 ; Conference date: 16-04-2013 Through 19-04-2013",

}

TY - GEN

T1 - Optimal control for a class of nonlinear systems with state delay based on Adaptive Dynamic Programming with ε-error bound

AU - Lin, Xiaofeng

AU - Cao, Nuyun

AU - Lin, Yuzhang

PY - 2013

Y1 - 2013

N2 - In this paper, a finite-horizon ε-optimal control for a class of nonlinear systems with state delay is proposed by Adaptive Dynamic Programming (ADP) algorithm. First of all, the performance index function is defined and the Hamilton-Jacobi-Bellman (HJB) equation is obtained for the problem, the convergence of the iterative algorithm is also presented. Then, ADP algorithm for finite-horizon optimal control is introduced with an ε-error bound so as to get the ε-optimal control, and BP neural network is used to implement ADP algorithm. At last, an example is given to demonstrate the effectiveness of the proposed algorithm.

AB - In this paper, a finite-horizon ε-optimal control for a class of nonlinear systems with state delay is proposed by Adaptive Dynamic Programming (ADP) algorithm. First of all, the performance index function is defined and the Hamilton-Jacobi-Bellman (HJB) equation is obtained for the problem, the convergence of the iterative algorithm is also presented. Then, ADP algorithm for finite-horizon optimal control is introduced with an ε-error bound so as to get the ε-optimal control, and BP neural network is used to implement ADP algorithm. At last, an example is given to demonstrate the effectiveness of the proposed algorithm.

KW - ε-optimal control

KW - Adaptive Dynamic Programming

KW - finite time

KW - nonlinear systems

KW - state delay

UR - http://www.scopus.com/inward/record.url?scp=84891550216&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891550216&partnerID=8YFLogxK

U2 - 10.1109/ADPRL.2013.6615005

DO - 10.1109/ADPRL.2013.6615005

M3 - Conference contribution

AN - SCOPUS:84891550216

SN - 9781467359252

T3 - IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL

SP - 177

EP - 182

BT - Proceedings of the 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

T2 - 2013 4th IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2013

Y2 - 16 April 2013 through 19 April 2013

ER -

Optimal control for a class of nonlinear systems with state delay based on Adaptive Dynamic Programming with ε-error bound

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this