Saturated Output-Feedback Hybrid Reinforcement Learning Controller for Submersible Vehicles Guaranteeing Output Constraints

In this brief, we propose a new neuro-fuzzy reinforcement learning-based control (NFRLC) structure that allows autonomous underwater vehicles (AUVs) to follow a desired trajectory in large-scale complex environments precisely. The accurate tracking control problem is solved by a unique online NFRLC...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Omid Elhaki, Khoshnam Shojaei, Declan Shanahan, Allahyar Montazeri
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Saturation function reinforcement learning prescribed performance high-gain observer interval type-2 fuzzy neural networks multilayer neural networks Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/72c0722e5e6e4738bb62e6cd1c26e1af
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:72c0722e5e6e4738bb62e6cd1c26e1af
record_format	dspace
spelling	oai:doaj.org-article:72c0722e5e6e4738bb62e6cd1c26e1af2021-11-13T00:00:52ZSaturated Output-Feedback Hybrid Reinforcement Learning Controller for Submersible Vehicles Guaranteeing Output Constraints2169-353610.1109/ACCESS.2021.3113080https://doaj.org/article/72c0722e5e6e4738bb62e6cd1c26e1af2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9539163/https://doaj.org/toc/2169-3536In this brief, we propose a new neuro-fuzzy reinforcement learning-based control (NFRLC) structure that allows autonomous underwater vehicles (AUVs) to follow a desired trajectory in large-scale complex environments precisely. The accurate tracking control problem is solved by a unique online NFRLC method designed based on actor-critic (AC) structure. Integrating the NFRLC framework including an adaptive multilayer neural network (MNN) and interval type-2 fuzzy neural network (IT2FNN) with a high-gain observer (HGO), a robust smart observer-based system is set up to estimate the velocities of the AUVs, unknown dynamic parameters containing unmodeled dynamics, nonlinearities, uncertainties and external disturbances. By employing a saturation function in the design procedure and transforming the input limitations into input saturation nonlinearities, the risk of the actuator saturation is effectively reduced together with nonlinear input saturation compensation by the NFRLC strategy. A predefined funnel-shaped performance function is designed to attain certain prescribed output performance. Finally, stability study reveals that the entire closed-loop system signals are semi-globally uniformly ultimately bounded (SGUUB) and can provide prescribed convergence rate for the tracking errors so that the tracking errors approach to the origin evolving inside the funnel-shaped performance bound at the prescribed time.Omid ElhakiKhoshnam ShojaeiDeclan ShanahanAllahyar MontazeriIEEEarticleSaturation functionreinforcement learningprescribed performancehigh-gain observerinterval type-2 fuzzy neural networksmultilayer neural networksElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 136580-136592 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Saturation function reinforcement learning prescribed performance high-gain observer interval type-2 fuzzy neural networks multilayer neural networks Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Saturation function reinforcement learning prescribed performance high-gain observer interval type-2 fuzzy neural networks multilayer neural networks Electrical engineering. Electronics. Nuclear engineering TK1-9971 Omid Elhaki Khoshnam Shojaei Declan Shanahan Allahyar Montazeri Saturated Output-Feedback Hybrid Reinforcement Learning Controller for Submersible Vehicles Guaranteeing Output Constraints
description	In this brief, we propose a new neuro-fuzzy reinforcement learning-based control (NFRLC) structure that allows autonomous underwater vehicles (AUVs) to follow a desired trajectory in large-scale complex environments precisely. The accurate tracking control problem is solved by a unique online NFRLC method designed based on actor-critic (AC) structure. Integrating the NFRLC framework including an adaptive multilayer neural network (MNN) and interval type-2 fuzzy neural network (IT2FNN) with a high-gain observer (HGO), a robust smart observer-based system is set up to estimate the velocities of the AUVs, unknown dynamic parameters containing unmodeled dynamics, nonlinearities, uncertainties and external disturbances. By employing a saturation function in the design procedure and transforming the input limitations into input saturation nonlinearities, the risk of the actuator saturation is effectively reduced together with nonlinear input saturation compensation by the NFRLC strategy. A predefined funnel-shaped performance function is designed to attain certain prescribed output performance. Finally, stability study reveals that the entire closed-loop system signals are semi-globally uniformly ultimately bounded (SGUUB) and can provide prescribed convergence rate for the tracking errors so that the tracking errors approach to the origin evolving inside the funnel-shaped performance bound at the prescribed time.
format	article
author	Omid Elhaki Khoshnam Shojaei Declan Shanahan Allahyar Montazeri
author_facet	Omid Elhaki Khoshnam Shojaei Declan Shanahan Allahyar Montazeri
author_sort	Omid Elhaki
title	Saturated Output-Feedback Hybrid Reinforcement Learning Controller for Submersible Vehicles Guaranteeing Output Constraints
title_short	Saturated Output-Feedback Hybrid Reinforcement Learning Controller for Submersible Vehicles Guaranteeing Output Constraints
title_full	Saturated Output-Feedback Hybrid Reinforcement Learning Controller for Submersible Vehicles Guaranteeing Output Constraints
title_fullStr	Saturated Output-Feedback Hybrid Reinforcement Learning Controller for Submersible Vehicles Guaranteeing Output Constraints
title_full_unstemmed	Saturated Output-Feedback Hybrid Reinforcement Learning Controller for Submersible Vehicles Guaranteeing Output Constraints
title_sort	saturated output-feedback hybrid reinforcement learning controller for submersible vehicles guaranteeing output constraints
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/72c0722e5e6e4738bb62e6cd1c26e1af
work_keys_str_mv	AT omidelhaki saturatedoutputfeedbackhybridreinforcementlearningcontrollerforsubmersiblevehiclesguaranteeingoutputconstraints AT khoshnamshojaei saturatedoutputfeedbackhybridreinforcementlearningcontrollerforsubmersiblevehiclesguaranteeingoutputconstraints AT declanshanahan saturatedoutputfeedbackhybridreinforcementlearningcontrollerforsubmersiblevehiclesguaranteeingoutputconstraints AT allahyarmontazeri saturatedoutputfeedbackhybridreinforcementlearningcontrollerforsubmersiblevehiclesguaranteeingoutputconstraints
_version_	1718430323745751040

Saturated Output-Feedback Hybrid Reinforcement Learning Controller for Submersible Vehicles Guaranteeing Output Constraints

Ejemplares similares