Recurrent neural network based tracking control

Zhao Xu; Qing Song; Danwei Wang

doi:10.1109/ICARCV.2010.5707971

Recurrent neural network based tracking control

Zhao Xu, Qing Song, Danwei Wang

Nanyang Technological University

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

Abstract

In this paper, a recurrent neural network (RNN) based robust tracking controller is designed for a class of multiple-input-multiple-output (MIMO) discrete time nonlinear systems. The RNN is used in the closed-loop system to estimate online unknown nonlinear system function. A multivariable robust adaptive gradient-descent training algorithm is developed to train RNN. The proposed neural control system guarantees the stability of the closed-loop system and good tracking performance is achieved.

Original language	English
Title of host publication	11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010
Pages	2454-2459
Number of pages	6
DOIs	https://doi.org/10.1109/ICARCV.2010.5707971
State	Published - 2010
Externally published	Yes
Event	11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010 - Singapore, Singapore Duration: 7 Dec 2010 → 10 Dec 2010

Publication series

Name	11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010

Conference

Conference	11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010
Country/Territory	Singapore
City	Singapore
Period	7/12/10 → 10/12/10

Access to Document

10.1109/ICARCV.2010.5707971

Cite this

@inproceedings{255d1c4bdb3143eea6a0fe1c7ee44da4,

title = "Recurrent neural network based tracking control",

abstract = "In this paper, a recurrent neural network (RNN) based robust tracking controller is designed for a class of multiple-input-multiple-output (MIMO) discrete time nonlinear systems. The RNN is used in the closed-loop system to estimate online unknown nonlinear system function. A multivariable robust adaptive gradient-descent training algorithm is developed to train RNN. The proposed neural control system guarantees the stability of the closed-loop system and good tracking performance is achieved.",

author = "Zhao Xu and Qing Song and Danwei Wang",

year = "2010",

doi = "10.1109/ICARCV.2010.5707971",

language = "英语",

isbn = "9781424478132",

series = "11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010",

pages = "2454--2459",

booktitle = "11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010",

note = "11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010 ; Conference date: 07-12-2010 Through 10-12-2010",

}

Xu, Z, Song, Q & Wang, D 2010, Recurrent neural network based tracking control. in 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010., 5707971, 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010, pp. 2454-2459, 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010, Singapore, Singapore, 7/12/10. https://doi.org/10.1109/ICARCV.2010.5707971

Recurrent neural network based tracking control. / Xu, Zhao; Song, Qing; Wang, Danwei.
11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010. 2010. p. 2454-2459 5707971 (11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010).

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

TY - GEN

T1 - Recurrent neural network based tracking control

AU - Xu, Zhao

AU - Song, Qing

AU - Wang, Danwei

PY - 2010

Y1 - 2010

N2 - In this paper, a recurrent neural network (RNN) based robust tracking controller is designed for a class of multiple-input-multiple-output (MIMO) discrete time nonlinear systems. The RNN is used in the closed-loop system to estimate online unknown nonlinear system function. A multivariable robust adaptive gradient-descent training algorithm is developed to train RNN. The proposed neural control system guarantees the stability of the closed-loop system and good tracking performance is achieved.

AB - In this paper, a recurrent neural network (RNN) based robust tracking controller is designed for a class of multiple-input-multiple-output (MIMO) discrete time nonlinear systems. The RNN is used in the closed-loop system to estimate online unknown nonlinear system function. A multivariable robust adaptive gradient-descent training algorithm is developed to train RNN. The proposed neural control system guarantees the stability of the closed-loop system and good tracking performance is achieved.

UR - http://www.scopus.com/inward/record.url?scp=79952373908&partnerID=8YFLogxK

U2 - 10.1109/ICARCV.2010.5707971

DO - 10.1109/ICARCV.2010.5707971

M3 - 会议稿件

AN - SCOPUS:79952373908

SN - 9781424478132

T3 - 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010

SP - 2454

EP - 2459

BT - 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010

T2 - 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010

Y2 - 7 December 2010 through 10 December 2010

ER -

Recurrent neural network based tracking control

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this