Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions

The field of automatic collision avoidance for surface vessels has been an active field of research in recent years, aiming for the decision support of officers in conventional vessels, or for the creation of autonomous vessel controllers. In this paper, the multi-ship control problem is addressed u...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Myron Papadimitrakis, Marios Stogiannos, Haralambos Sarimveis, Alex Alexandridis
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	autonomous vessels collision avoidance model predictive control radial basis function networks trajectory optimization Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/4646ade1a6ef43978960564136dc8ff2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4646ade1a6ef43978960564136dc8ff2
record_format	dspace
spelling	oai:doaj.org-article:4646ade1a6ef43978960564136dc8ff22021-11-11T19:00:28ZMulti-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions10.3390/s212169591424-8220https://doaj.org/article/4646ade1a6ef43978960564136dc8ff22021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/6959https://doaj.org/toc/1424-8220The field of automatic collision avoidance for surface vessels has been an active field of research in recent years, aiming for the decision support of officers in conventional vessels, or for the creation of autonomous vessel controllers. In this paper, the multi-ship control problem is addressed using a model predictive controller (MPC) that makes use of obstacle ship trajectory prediction models built on the RBF framework and is trained on real AIS data sourced from an open-source database. The usage of such sophisticated trajectory prediction models enables the controller to correctly infer the existence of a collision risk and apply evasive control actions in a timely manner, thus accounting for the slow dynamics of a large vessel, such as container ships, and enhancing the cooperation between controlled vessels. The proposed method is evaluated on a real-life case from the Miami port area, and its generated trajectories are assessed in terms of safety, economy, and COLREG compliance by comparison with an identical MPC controller utilizing straight-line predictions for the obstacle vessel.Myron PapadimitrakisMarios StogiannosHaralambos SarimveisAlex AlexandridisMDPI AGarticleautonomous vesselscollision avoidancemodel predictive controlradial basis function networkstrajectory optimizationChemical technologyTP1-1185ENSensors, Vol 21, Iss 6959, p 6959 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	autonomous vessels collision avoidance model predictive control radial basis function networks trajectory optimization Chemical technology TP1-1185
spellingShingle	autonomous vessels collision avoidance model predictive control radial basis function networks trajectory optimization Chemical technology TP1-1185 Myron Papadimitrakis Marios Stogiannos Haralambos Sarimveis Alex Alexandridis Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions
description	The field of automatic collision avoidance for surface vessels has been an active field of research in recent years, aiming for the decision support of officers in conventional vessels, or for the creation of autonomous vessel controllers. In this paper, the multi-ship control problem is addressed using a model predictive controller (MPC) that makes use of obstacle ship trajectory prediction models built on the RBF framework and is trained on real AIS data sourced from an open-source database. The usage of such sophisticated trajectory prediction models enables the controller to correctly infer the existence of a collision risk and apply evasive control actions in a timely manner, thus accounting for the slow dynamics of a large vessel, such as container ships, and enhancing the cooperation between controlled vessels. The proposed method is evaluated on a real-life case from the Miami port area, and its generated trajectories are assessed in terms of safety, economy, and COLREG compliance by comparison with an identical MPC controller utilizing straight-line predictions for the obstacle vessel.
format	article
author	Myron Papadimitrakis Marios Stogiannos Haralambos Sarimveis Alex Alexandridis
author_facet	Myron Papadimitrakis Marios Stogiannos Haralambos Sarimveis Alex Alexandridis
author_sort	Myron Papadimitrakis
title	Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions
title_short	Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions
title_full	Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions
title_fullStr	Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions
title_full_unstemmed	Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions
title_sort	multi-ship control and collision avoidance using mpc and rbf-based trajectory predictions
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/4646ade1a6ef43978960564136dc8ff2
work_keys_str_mv	AT myronpapadimitrakis multishipcontrolandcollisionavoidanceusingmpcandrbfbasedtrajectorypredictions AT mariosstogiannos multishipcontrolandcollisionavoidanceusingmpcandrbfbasedtrajectorypredictions AT haralambossarimveis multishipcontrolandcollisionavoidanceusingmpcandrbfbasedtrajectorypredictions AT alexalexandridis multishipcontrolandcollisionavoidanceusingmpcandrbfbasedtrajectorypredictions
_version_	1718431641648496640

Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions

Ejemplares similares