Motor Learning for Manoeuvring Control of a Remotely Operated Vehicle

Adrià Mompo Alepuz; Silvia Tolu; Roberto Galeazzi

doi:10.1016/j.ifacol.2022.10.416

Motor Learning for Manoeuvring Control of a Remotely Operated Vehicle

Adrià Mompo Alepuz, Silvia Tolu, Roberto Galeazzi

Department of Electrical and Photonics Engineering

Research output: Contribution to journal › Conference article › Research › peer-review

97 Downloads (Orbit)

Abstract

The paper investigates the application of a bio-inspired control paradigm encompassing nonlinear function approximation and adaptive learning to design a manoeuvring controller for a remotely operated vehicle. The bio-inspired learning controller is adopted to overcome limitations introduced by unknown nonlinear dynamics as well as by environmental disturbances. The bio-inspired manoeuvring controller is compared against a traditional adaptive controller with respect to tracking performance and control effort. Simulation results show that the bio-inspired controller displays better tracking performance when the structure of the system dynamics is unknown. Further, the paper shows that offline training of the functional approximator helps in delivering a smoother control effort, and that a bio-inspired integral action fulfils the disturbance rejection.

Original language	English
Book series	IFAC Proceedings Volumes (IFAC-PapersOnline)
Volume	55
Issue number	31
Pages (from-to)	104-109
ISSN	1474-6670
DOIs	https://doi.org/10.1016/j.ifacol.2022.10.416
Publication status	Published - 2022
Event	14^th IFAC Conference on Control Applications in Marine Systems, Robotics and Vehicles - Technical University of Denmark, Kongens Lyngby, Denmark Duration: 14 Sept 2022 → 16 Sept 2022 https://www.ifac-cams2022.dk/

Conference

Conference	14^th IFAC Conference on Control Applications in Marine Systems, Robotics and Vehicles
Location	Technical University of Denmark
Country/Territory	Denmark
City	Kongens Lyngby
Period	14/09/2022 → 16/09/2022
Internet address	https://www.ifac-cams2022.dk/

Keywords

Biomimetics in marine robotics
Guidance
Navigation and control (GNC) of unmanned marine vehicles

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.ifacol.2022.10.416

FulltextFinal published version, 1.69 MB

OpenUrl availability

Full text

Cite this

@inproceedings{7e4d6715b10741a18332b0d8b8fdf9ed,

title = "Motor Learning for Manoeuvring Control of a Remotely Operated Vehicle",

abstract = "The paper investigates the application of a bio-inspired control paradigm encompassing nonlinear function approximation and adaptive learning to design a manoeuvring controller for a remotely operated vehicle. The bio-inspired learning controller is adopted to overcome limitations introduced by unknown nonlinear dynamics as well as by environmental disturbances. The bio-inspired manoeuvring controller is compared against a traditional adaptive controller with respect to tracking performance and control effort. Simulation results show that the bio-inspired controller displays better tracking performance when the structure of the system dynamics is unknown. Further, the paper shows that offline training of the functional approximator helps in delivering a smoother control effort, and that a bio-inspired integral action fulfils the disturbance rejection.",

keywords = "Biomimetics in marine robotics, Guidance, Navigation and control (GNC) of unmanned marine vehicles",

author = "{Mompo Alepuz}, Adri{\`a} and Silvia Tolu and Roberto Galeazzi",

year = "2022",

doi = "10.1016/j.ifacol.2022.10.416",

language = "English",

volume = "55",

pages = "104--109",

journal = "IFAC Proceedings Volumes (IFAC-PapersOnline) ",

issn = "1474-6670",

publisher = "International Federation of Automatic Control",

number = "31",

note = "14<sup>th</sup> IFAC Conference on Control Applications in Marine Systems, Robotics and Vehicles, IFAC CAMS 2022 ; Conference date: 14-09-2022 Through 16-09-2022",

url = "https://www.ifac-cams2022.dk/",

}

TY - GEN

T1 - Motor Learning for Manoeuvring Control of a Remotely Operated Vehicle

AU - Mompo Alepuz, Adrià

AU - Tolu, Silvia

AU - Galeazzi, Roberto

PY - 2022

Y1 - 2022

N2 - The paper investigates the application of a bio-inspired control paradigm encompassing nonlinear function approximation and adaptive learning to design a manoeuvring controller for a remotely operated vehicle. The bio-inspired learning controller is adopted to overcome limitations introduced by unknown nonlinear dynamics as well as by environmental disturbances. The bio-inspired manoeuvring controller is compared against a traditional adaptive controller with respect to tracking performance and control effort. Simulation results show that the bio-inspired controller displays better tracking performance when the structure of the system dynamics is unknown. Further, the paper shows that offline training of the functional approximator helps in delivering a smoother control effort, and that a bio-inspired integral action fulfils the disturbance rejection.

AB - The paper investigates the application of a bio-inspired control paradigm encompassing nonlinear function approximation and adaptive learning to design a manoeuvring controller for a remotely operated vehicle. The bio-inspired learning controller is adopted to overcome limitations introduced by unknown nonlinear dynamics as well as by environmental disturbances. The bio-inspired manoeuvring controller is compared against a traditional adaptive controller with respect to tracking performance and control effort. Simulation results show that the bio-inspired controller displays better tracking performance when the structure of the system dynamics is unknown. Further, the paper shows that offline training of the functional approximator helps in delivering a smoother control effort, and that a bio-inspired integral action fulfils the disturbance rejection.

KW - Biomimetics in marine robotics

KW - Guidance

KW - Navigation and control (GNC) of unmanned marine vehicles

U2 - 10.1016/j.ifacol.2022.10.416

DO - 10.1016/j.ifacol.2022.10.416

M3 - Conference article

SN - 1474-6670

VL - 55

SP - 104

EP - 109

JO - IFAC Proceedings Volumes (IFAC-PapersOnline)

JF - IFAC Proceedings Volumes (IFAC-PapersOnline)

IS - 31

T2 - 14<sup>th</sup> IFAC Conference on Control Applications in Marine Systems, Robotics and Vehicles

Y2 - 14 September 2022 through 16 September 2022

ER -

Motor Learning for Manoeuvring Control of a Remotely Operated Vehicle

Abstract

Conference

Keywords

UN SDGs

Access to Document

OpenUrl availability

Fingerprint

Cite this