Galvanometer Motor Control Based on Reinforcement Learning

Kainan Liu; Xiaoshi Cai; Xiaojun Ban; Jian Zhang

doi:10.1109/ICoIAS56028.2022.9931291

Galvanometer Motor Control Based on Reinforcement Learning

Kainan Liu
, Xiaoshi Cai
, Xiaojun Ban
, Jian Zhang

School of Astronautics

Harbin Institute of Technology
Aerospace Motor Power Division

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

1 Scopus citations

Abstract

In order to address the problem that the control effect of the galvanometer motor is often dependent on the accuracy of the model parameters, this paper proposes a control method that is based on reinforcement learning. With the galvanometer motor in the steady state as the target, a state feedback control method incorporating an online update control strategy that does not depend on model parameters is proposed on the premise of obtaining the system order, and the method able to identify the state feedback coefficient. As suggested by the computer simulation results, the method proposed in this paper is capable of applying stable control on the galvanometer motor, and the iterative results are found consistent with the design results of the LQR method with the model, which ensures the reliability of the method.

Original language	English
Title of host publication	5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	261-266
Number of pages	6
ISBN (Electronic)	9781665498388
DOIs	https://doi.org/10.1109/ICoIAS56028.2022.9931291
State	Published - 2022
Event	5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022 - Dalian, China Duration: 23 Sep 2022 → 25 Sep 2022

Publication series

Name	5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022

Conference

Conference	5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022
Country/Territory	China
City	Dalian
Period	23/09/22 → 25/09/22

Keywords

Galvanometer motor
Policy iteration
Reinforcement learning

Access to Document

10.1109/ICoIAS56028.2022.9931291

Cite this

Liu, K., Cai, X., Ban, X., & Zhang, J. (2022). Galvanometer Motor Control Based on Reinforcement Learning. In 5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022 (pp. 261-266). (5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICoIAS56028.2022.9931291

@inproceedings{dad840f775b347e19c495ba34a0ffc46,

title = "Galvanometer Motor Control Based on Reinforcement Learning",

abstract = "In order to address the problem that the control effect of the galvanometer motor is often dependent on the accuracy of the model parameters, this paper proposes a control method that is based on reinforcement learning. With the galvanometer motor in the steady state as the target, a state feedback control method incorporating an online update control strategy that does not depend on model parameters is proposed on the premise of obtaining the system order, and the method able to identify the state feedback coefficient. As suggested by the computer simulation results, the method proposed in this paper is capable of applying stable control on the galvanometer motor, and the iterative results are found consistent with the design results of the LQR method with the model, which ensures the reliability of the method.",

keywords = "Galvanometer motor, Policy iteration, Reinforcement learning",

author = "Kainan Liu and Xiaoshi Cai and Xiaojun Ban and Jian Zhang",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022 ; Conference date: 23-09-2022 Through 25-09-2022",

year = "2022",

doi = "10.1109/ICoIAS56028.2022.9931291",

language = "英语",

series = "5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "261--266",

booktitle = "5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022",

address = "美国",

}

Liu, K, Cai, X, Ban, X & Zhang, J 2022, Galvanometer Motor Control Based on Reinforcement Learning. in 5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022. 5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022, Institute of Electrical and Electronics Engineers Inc., pp. 261-266, 5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022, Dalian, China, 23/09/22. https://doi.org/10.1109/ICoIAS56028.2022.9931291

Galvanometer Motor Control Based on Reinforcement Learning. / Liu, Kainan; Cai, Xiaoshi; Ban, Xiaojun et al.
5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 261-266 (5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022).

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

TY - GEN

T1 - Galvanometer Motor Control Based on Reinforcement Learning

AU - Liu, Kainan

AU - Cai, Xiaoshi

AU - Ban, Xiaojun

AU - Zhang, Jian

PY - 2022

Y1 - 2022

N2 - In order to address the problem that the control effect of the galvanometer motor is often dependent on the accuracy of the model parameters, this paper proposes a control method that is based on reinforcement learning. With the galvanometer motor in the steady state as the target, a state feedback control method incorporating an online update control strategy that does not depend on model parameters is proposed on the premise of obtaining the system order, and the method able to identify the state feedback coefficient. As suggested by the computer simulation results, the method proposed in this paper is capable of applying stable control on the galvanometer motor, and the iterative results are found consistent with the design results of the LQR method with the model, which ensures the reliability of the method.

AB - In order to address the problem that the control effect of the galvanometer motor is often dependent on the accuracy of the model parameters, this paper proposes a control method that is based on reinforcement learning. With the galvanometer motor in the steady state as the target, a state feedback control method incorporating an online update control strategy that does not depend on model parameters is proposed on the premise of obtaining the system order, and the method able to identify the state feedback coefficient. As suggested by the computer simulation results, the method proposed in this paper is capable of applying stable control on the galvanometer motor, and the iterative results are found consistent with the design results of the LQR method with the model, which ensures the reliability of the method.

KW - Galvanometer motor

KW - Policy iteration

KW - Reinforcement learning

UR - https://www.scopus.com/pages/publications/85142415943

U2 - 10.1109/ICoIAS56028.2022.9931291

DO - 10.1109/ICoIAS56028.2022.9931291

M3 - 会议稿件

AN - SCOPUS:85142415943

T3 - 5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022

SP - 261

EP - 266

BT - 5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022

Y2 - 23 September 2022 through 25 September 2022

ER -

Galvanometer Motor Control Based on Reinforcement Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this