State estimation for autonomous surface vehicles based on Echo state networks

Zhouhua Peng; Jun Wang; Dan Wang

doi:10.1007/978-3-319-59072-1_16

State estimation for autonomous surface vehicles based on Echo state networks

Zhouhua Peng^*
, Jun Wang
, Dan Wang

^*Corresponding author for this work

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

This paper investigates the state estimation for autonomous surface vehicles in the presence of unknown dynamics and unmeasured states. The unknown dynamics comes from parametric model uncertainty, unmodelled hydrodynamics, and external disturbances caused by wind, waves and ocean currents. A nonlinear adaptive observer is proposed based on echo state networks, which are used to approximate the unknown dynamics using input-output data. By using the proposed observer, the unmeasured states and unknown dynamics can be simultaneously estimated in real time. The stability of the observer is analyzed via Lyapunov analysis. The proposed observer can be used in various motion control scenario, such as target tracking, trajectory tracking, path following, formation control, and even sideslip angle identification, not only for fully-actuated marine vehicles but also for under-actuated marine vehicles.

Original language	English
Title of host publication	Advances in Neural Networks - ISNN 2017
Subtitle of host publication	14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part I
Editors	Fengyu Cong, Andrew Leung, Qinglai Wei
Publisher	Springer Nature
Pages	127-134
ISBN (Print)	9783319590714
DOIs	https://doi.org/10.1007/978-3-319-59072-1_16
Publication status	Published - 2017
Event	14th International Symposium on Neural Networks (ISNN 2017) - Hokkaido University, Sapporo, Japan Duration: 21 Jun 2017 → 26 Jun 2017

Publication series

Name	Lecture Notes in Computer Science
Volume	LNCS 10261
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	14th International Symposium on Neural Networks (ISNN 2017)
Abbreviated title	ISNN 2017
Place	Japan
City	Sapporo
Period	21/06/17 → 26/06/17

Research Keywords

Echo state network
Fully-actuated marine vehicles
State estimation
Under-actuated marine vehicles
Unknown dynamics

Access Output

10.1007/978-3-319-59072-1_16

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Peng, Z., Wang, J., & Wang, D. (2017). State estimation for autonomous surface vehicles based on Echo state networks. In F. Cong, A. Leung, & Q. Wei (Eds.), Advances in Neural Networks - ISNN 2017: 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part I (pp. 127-134). (Lecture Notes in Computer Science; Vol. LNCS 10261). Springer Nature. https://doi.org/10.1007/978-3-319-59072-1_16

Peng, Zhouhua ; Wang, Jun ; Wang, Dan. / State estimation for autonomous surface vehicles based on Echo state networks. Advances in Neural Networks - ISNN 2017: 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part I. editor / Fengyu Cong ; Andrew Leung ; Qinglai Wei. Springer Nature, 2017. pp. 127-134 (Lecture Notes in Computer Science).

@inproceedings{dd99daf76267419fb20c74efbd50e7d0,

title = "State estimation for autonomous surface vehicles based on Echo state networks",

abstract = "This paper investigates the state estimation for autonomous surface vehicles in the presence of unknown dynamics and unmeasured states. The unknown dynamics comes from parametric model uncertainty, unmodelled hydrodynamics, and external disturbances caused by wind, waves and ocean currents. A nonlinear adaptive observer is proposed based on echo state networks, which are used to approximate the unknown dynamics using input-output data. By using the proposed observer, the unmeasured states and unknown dynamics can be simultaneously estimated in real time. The stability of the observer is analyzed via Lyapunov analysis. The proposed observer can be used in various motion control scenario, such as target tracking, trajectory tracking, path following, formation control, and even sideslip angle identification, not only for fully-actuated marine vehicles but also for under-actuated marine vehicles.",

keywords = "Echo state network, Fully-actuated marine vehicles, State estimation, Under-actuated marine vehicles, Unknown dynamics",

author = "Zhouhua Peng and Jun Wang and Dan Wang",

year = "2017",

doi = "10.1007/978-3-319-59072-1\_16",

language = "English",

isbn = "9783319590714",

series = "Lecture Notes in Computer Science",

publisher = "Springer Nature",

pages = "127--134",

editor = "Fengyu Cong and Andrew Leung and Qinglai Wei",

booktitle = "Advances in Neural Networks - ISNN 2017",

address = "United States",

note = "14th International Symposium on Neural Networks (ISNN 2017), ISNN 2017 ; Conference date: 21-06-2017 Through 26-06-2017",

}

Peng, Z, Wang, J & Wang, D 2017, State estimation for autonomous surface vehicles based on Echo state networks. in F Cong, A Leung & Q Wei (eds), Advances in Neural Networks - ISNN 2017: 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part I. Lecture Notes in Computer Science, vol. LNCS 10261, Springer Nature, pp. 127-134, 14th International Symposium on Neural Networks (ISNN 2017), Sapporo, Japan, 21/06/17. https://doi.org/10.1007/978-3-319-59072-1_16

State estimation for autonomous surface vehicles based on Echo state networks. / Peng, Zhouhua; Wang, Jun; Wang, Dan.
Advances in Neural Networks - ISNN 2017: 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part I. ed. / Fengyu Cong; Andrew Leung; Qinglai Wei. Springer Nature, 2017. p. 127-134 (Lecture Notes in Computer Science; Vol. LNCS 10261).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - State estimation for autonomous surface vehicles based on Echo state networks

AU - Peng, Zhouhua

AU - Wang, Jun

AU - Wang, Dan

PY - 2017

Y1 - 2017

N2 - This paper investigates the state estimation for autonomous surface vehicles in the presence of unknown dynamics and unmeasured states. The unknown dynamics comes from parametric model uncertainty, unmodelled hydrodynamics, and external disturbances caused by wind, waves and ocean currents. A nonlinear adaptive observer is proposed based on echo state networks, which are used to approximate the unknown dynamics using input-output data. By using the proposed observer, the unmeasured states and unknown dynamics can be simultaneously estimated in real time. The stability of the observer is analyzed via Lyapunov analysis. The proposed observer can be used in various motion control scenario, such as target tracking, trajectory tracking, path following, formation control, and even sideslip angle identification, not only for fully-actuated marine vehicles but also for under-actuated marine vehicles.

AB - This paper investigates the state estimation for autonomous surface vehicles in the presence of unknown dynamics and unmeasured states. The unknown dynamics comes from parametric model uncertainty, unmodelled hydrodynamics, and external disturbances caused by wind, waves and ocean currents. A nonlinear adaptive observer is proposed based on echo state networks, which are used to approximate the unknown dynamics using input-output data. By using the proposed observer, the unmeasured states and unknown dynamics can be simultaneously estimated in real time. The stability of the observer is analyzed via Lyapunov analysis. The proposed observer can be used in various motion control scenario, such as target tracking, trajectory tracking, path following, formation control, and even sideslip angle identification, not only for fully-actuated marine vehicles but also for under-actuated marine vehicles.

KW - Echo state network

KW - Fully-actuated marine vehicles

KW - State estimation

KW - Under-actuated marine vehicles

KW - Unknown dynamics

UR - https://www.scopus.com/pages/publications/85021637472

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85021637472&origin=recordpage

U2 - 10.1007/978-3-319-59072-1_16

DO - 10.1007/978-3-319-59072-1_16

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9783319590714

T3 - Lecture Notes in Computer Science

SP - 127

EP - 134

BT - Advances in Neural Networks - ISNN 2017

A2 - Cong, Fengyu

A2 - Leung, Andrew

A2 - Wei, Qinglai

PB - Springer Nature

T2 - 14th International Symposium on Neural Networks (ISNN 2017)

Y2 - 21 June 2017 through 26 June 2017

ER -

Peng Z, Wang J, Wang D. State estimation for autonomous surface vehicles based on Echo state networks. In Cong F, Leung A, Wei Q, editors, Advances in Neural Networks - ISNN 2017: 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part I. Springer Nature. 2017. p. 127-134. (Lecture Notes in Computer Science). Epub 2017 May 31. doi: 10.1007/978-3-319-59072-1_16

State estimation for autonomous surface vehicles based on Echo state networks

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this