Smart Technologies for Unmanned Surface Vessels: On the Path Towards Full Automation

Mårten Lager

Smart Technologies for Unmanned Surface Vessels: On the Path Towards Full Automation

Bidragets översatta titel : Smart teknologi för obemannade ytfartyg: På vägen mot full automation

Mårten Lager

Forskningsoutput: Avhandling › Licentiatavhandling

1711 Nedladdningar (Pure)

Sammanfattning

Precis som för bilindustrin, investeras stora belopp på att skapa obemannade fartyg. De huvudsakliga fördelarna är att säkerheten förväntas förbättras, vinsterna
kommer att öka, samt att utsläppen kommer att minska. Helt autonoma fraktfartyg förväntas kunna korsa Atlanten helt obemannat innan år 2030, och fram tills
dess förväntas tekniken gradvis förbättra säkerheten och ersätta arbetsuppgifter
som idag utförs av människor. Även för obemannade fartyg förväntas människor
utföra viktiga arbetsuppgifter, men då genom att färrstyra olika system.
I denna licentiatavhandling presenteras metoder för att förbättra två olika
byggblock som är viktiga för autonoma fartyg; ett positioneringssystem som inte
är GPS-beroende, och ett verktyg för färrövervakning av obemannat fartyg med
begränsad dataöverföringskapacitet.
Positioneringssystemet använder sig av en teknik som kallas Partikelfilter. Partikelfiltret jämför uppmätt djup och magnetism med kända kartor, och kan med
hjälp av sannolikhetsberäkning estimera var fartyget befinner sig. Till sin hjälp
används tusentals positionsuppskattningar (partiklar) som sprids på kartan, vilket
bildar ett partikelmoln. Om fartyget t.ex. mäter ett djup på 10 m, men kartan
säger att det ska vara 20 m djupt där partikeln är placerad, är det osannolikt att
partikeln är placerad på rätt ställe, vilket leder till att partikeln tas bort, till förmån
för partiklar som är bättre placerade. Efter varje iteration, kommer partikelmolnet
att uppdateras, och därmed följa fartygets korrekta position.
Systemet för färrövervakning av obemannat fartyg tar emot position från det
färrövervakade fartyget, samt information om detekterade objekt i omgivningen. Denna information, tillsammans med känd kartinformation, används för
att skapa en 3D-värld och ett användargränssnitt, där man kan övervaka fartyget
i den virtuella världen. Genom att bygga upp redan känd omgivning från kartor,
behöver inte lika mycket data överföras. En användarstudie i en simulerad värld
har visat att användargränssnittet i 3D ger mindre olyckor och bättre överblick
jämfört med ett traditionellt användargränssnitt.

Bidragets översatta titel	Smart teknologi för obemannade ytfartyg: På vägen mot full automation
Originalspråk	engelska
Kvalifikation	Licentiat
Tilldelande institution	Institutionen för datavetenskap
Handledare	Malec, Jacek, handledare Topp, Elin A., Biträdande handledare
Tilldelningsdatum	2019 feb. 4
Utgivningsort	Lund
Utgåva	1
ISBN (tryckt)	978-91-7753-960-5
ISBN (elektroniskt)	978-91-7753-961-2
Status	Published - 2019 feb. 4

Ämnesklassifikation (UKÄ)

Datorgrafik och datorseende

Fria nyckelord

Virtual reality
human interaction
Positioning
Navigation
Unmanned Surface Vessel
Autonomous system
Teleoperation

Tillgång till dokument

Lic_Marten_Lund_FinalPublicerad version, 18,4 MB

Digital Cognitive Companion for Marine Vessels
Lager, M. (PI), Malec, J. (Handledare) & Topp, E. A. (Handledare)
2016/01/01 → 2020/10/01
Projekt: Avhandling

Citera det här

@phdthesis{a0b87d254f644108ab4b44d15923a9f4,

title = "Smart Technologies for Unmanned Surface Vessels: On the Path Towards Full Automation",

abstract = "As for the automotive industry, large efforts are being made by industry andacademia to create autonomous ships. Te solutions for this is very technologyintense, as many building blocks, often relying on AI technology, need to worktogether to create a complete system that is safe and reliable to use. Even whenthe ships are fully unmanned, humans are still foreseen to guide the ships whenunknown situations arise. Tis will be done through teleoperation systems.In this thesis, methods are presented to enhance the capability of two building blocks that are important for autonomous ships; a positioning system, and asystem for remote supervision.Te positioning system has been constructed to not rely on GPS (Global Positioning System), as this system can be jammed or be spoofed. Instead, it usesBayesian calculations to compare the bottom depth and magnetic field measurements with known sea charts and magnetic field maps, in order to estimate theposition. State-of-the-art techniques for this method normally use low-accuracynavigation sensors and high-resolution maps. Te problem is that there are hardlyany high-resolution maps available in the world, hence we present a method of theopposite; namely using high-accuracy navigation sensors and low-resolution maps(normal sea charts). Te results from a 20h test-run gave a mean position error of10.2m, which would in most cases be accurate enough for navigation purpose.In the second building block, we investigated, how 3D and VR approachescould support the remote operation of unmanned ships with a low bandwidthconnection, by comparing respective GUIs with a Baseline GUI following the currently applied interfaces in such contexts. Our findings show, that both the 3Dand VR approaches outperform the traditional approach significantly. We foundthe 3D GUI and VR GUI users to be better at reacting to potentially dangeroussituations compared to the Baseline GUI users, and they could keep track of thesurroundings more accurately.",

keywords = "Virtual reality, human interaction, Positioning, Navigation, Unmanned Surface Vessel, Autonomous system, Teleoperation",

author = "M{\aa}rten Lager",

year = "2019",

month = feb,

day = "4",

language = "English",

isbn = "978-91-7753-960-5",

edition = "1",

type = "Licentiate Thesis",

school = "Department of Computer Science",

}

TY - THES

T1 - Smart Technologies for Unmanned Surface Vessels

T2 - On the Path Towards Full Automation

AU - Lager, Mårten

PY - 2019/2/4

Y1 - 2019/2/4

N2 - As for the automotive industry, large efforts are being made by industry andacademia to create autonomous ships. Te solutions for this is very technologyintense, as many building blocks, often relying on AI technology, need to worktogether to create a complete system that is safe and reliable to use. Even whenthe ships are fully unmanned, humans are still foreseen to guide the ships whenunknown situations arise. Tis will be done through teleoperation systems.In this thesis, methods are presented to enhance the capability of two building blocks that are important for autonomous ships; a positioning system, and asystem for remote supervision.Te positioning system has been constructed to not rely on GPS (Global Positioning System), as this system can be jammed or be spoofed. Instead, it usesBayesian calculations to compare the bottom depth and magnetic field measurements with known sea charts and magnetic field maps, in order to estimate theposition. State-of-the-art techniques for this method normally use low-accuracynavigation sensors and high-resolution maps. Te problem is that there are hardlyany high-resolution maps available in the world, hence we present a method of theopposite; namely using high-accuracy navigation sensors and low-resolution maps(normal sea charts). Te results from a 20h test-run gave a mean position error of10.2m, which would in most cases be accurate enough for navigation purpose.In the second building block, we investigated, how 3D and VR approachescould support the remote operation of unmanned ships with a low bandwidthconnection, by comparing respective GUIs with a Baseline GUI following the currently applied interfaces in such contexts. Our findings show, that both the 3Dand VR approaches outperform the traditional approach significantly. We foundthe 3D GUI and VR GUI users to be better at reacting to potentially dangeroussituations compared to the Baseline GUI users, and they could keep track of thesurroundings more accurately.

AB - As for the automotive industry, large efforts are being made by industry andacademia to create autonomous ships. Te solutions for this is very technologyintense, as many building blocks, often relying on AI technology, need to worktogether to create a complete system that is safe and reliable to use. Even whenthe ships are fully unmanned, humans are still foreseen to guide the ships whenunknown situations arise. Tis will be done through teleoperation systems.In this thesis, methods are presented to enhance the capability of two building blocks that are important for autonomous ships; a positioning system, and asystem for remote supervision.Te positioning system has been constructed to not rely on GPS (Global Positioning System), as this system can be jammed or be spoofed. Instead, it usesBayesian calculations to compare the bottom depth and magnetic field measurements with known sea charts and magnetic field maps, in order to estimate theposition. State-of-the-art techniques for this method normally use low-accuracynavigation sensors and high-resolution maps. Te problem is that there are hardlyany high-resolution maps available in the world, hence we present a method of theopposite; namely using high-accuracy navigation sensors and low-resolution maps(normal sea charts). Te results from a 20h test-run gave a mean position error of10.2m, which would in most cases be accurate enough for navigation purpose.In the second building block, we investigated, how 3D and VR approachescould support the remote operation of unmanned ships with a low bandwidthconnection, by comparing respective GUIs with a Baseline GUI following the currently applied interfaces in such contexts. Our findings show, that both the 3Dand VR approaches outperform the traditional approach significantly. We foundthe 3D GUI and VR GUI users to be better at reacting to potentially dangeroussituations compared to the Baseline GUI users, and they could keep track of thesurroundings more accurately.

KW - Virtual reality

KW - human interaction

KW - Positioning

KW - Navigation

KW - Unmanned Surface Vessel

KW - Autonomous system

KW - Teleoperation

M3 - Licentiate Thesis

SN - 978-91-7753-960-5

CY - Lund

ER -

Smart Technologies for Unmanned Surface Vessels: On the Path Towards Full Automation

Sammanfattning

Ämnesklassifikation (UKÄ)

Fria nyckelord

Tillgång till dokument

Fingeravtryck

Projekt

Digital Cognitive Companion for Marine Vessels

Citera det här