135

1 INTRODUCTION

All manner of “water-going” platforms have been by

far the first sophisticated machines developed by

humans. As a key element of exploration, commerce

and war, ships have always involved engineering

solutions to difficult problems and talented humans

to build and operate them. For thousands of years

sailors have placed their trust, and their lives, in

constructions of wood, then steel, in the face of a

challenging ocean. It could be said that the age of

“autonomy” has been slow to come to ships. But this

is changing. Nowadays there are many small and

medium-size unmanned boats in routine-use, paving

the way towards fully autonomous vessels as

ultimate step in this sector. Many institutions,

universities and companies have begun developing

Unmanned Surface Vehicles (USV) aiming to cover a

wide range of applications and services, evolving

rapidly. With growing worldwide interest in

commercial, scientific, and military issues associated

with both open-ocean and shallow waters, there has

been a corresponding growth in demand for the

development of more complex USV with advanced

guidance, navigation, and control (GNC)

functionalities. The development of fully-

autonomous USV is underway aiming to minimize

both human control needs and the effects to the

effective and reliable operation from human errors

[12].

USV are defined as unmanned vehicles which

perform tasks in a wide range of environments

without any human intervention with highly

nonlinear dynamics. Further improvements on USV

technology are expected to bring tremendous

benefits, such a lower development and operation

cost, improved staff safety, extended operational

range, and precision and greater autonomy. Increased

Trends and Challenges in Unmanned Surface Vehicles

(USV): From Survey to Shipping

C. Barrera

, I. Padron

, F.S. Luis

, O. Llinas

& G.N. Marichal

Oceanic Platform of the Canary Islands, Las Palmas, Spain

University of La Laguna, Tenerife, Spain

Technological Center for Marine Sciences, Las Palmas, Spain

ABSTRACT: Autonomy and unmanned systems have evolved significantly in recent decades, becoming a key

routine component for various sectors and domains as an intrinsic sign of their improvement, the ocean not

being an exception. This paper shows the transition from the research concept to the commercial product and

related services for Unmanned Surface Vehicles (USV). Note that it has not always been easy in most cases due

to the limitations of the technology, business, and policy framework. An overview of current trends in USV

technology looking for a baseline to understand the sector where some experiences of the authors are shown in

this work. The analysis presented shows a multidisciplinary approach to the field. USV's capabilities and

applications today include a wide range of operations and services aimed at meeting the specific needs of the

maritime sector. This important consideration for USV has yet to be fully addressed, but progress is being

made.

http://www.transnav.eu

the International Journal

on Marine Navigation

and Safety of Sea Transportation

Volume 15

Number 1

March 2021

DOI: 10.12716/1001.15.01.13

136

flexibility in sophisticated environments and

dangerous mission [4, 7, 67] is also envisaged.

With the inclusion of a more robust, commercially

available and affordable navigation equipment (GPS,

IMU, etc.), wireless telemetry systems, “blue” power

sources and trending intelligent-analytics

technologies (Artificial Intelligence, Machine/Deep

learning, etc.) [47, 51, 52, 57], the applications range

for USV has significantly increased and improved in

key domains and sectors such as scientific research,

environmental missions, ocean exploration, military

uses and other applications (transportation,

communication relays, refueling, unmanned aerial or

unmanned underwater vehicles platform, etc.) [2, 45,

48].

This paper is organized as follows: Section 2

provides an updated overview on USV technology.

Section 3 focus on autonomous vessels as evolution

from USV technology in as ultimate step on maritime

navigation technology [6]. Section 4 provides a

description of the policy framework as key driver for

autonomous maritime navigation and shipping

implementation. Section 5 is addressed to review

intelligent analytics methodologies in path planning

and collision avoidance for USV navigation. Finally,

concluding remarks are drawn in Section 6.

2 USV TECHNOLOGY. DEVELOPMENTS AND

MILESTONES

Through the last two decades, several USV

developments have been undertaken through public

and private initiatives with diverse scope and

purpose [46, 53, 79]. After clearly experimental

beginnings with limited capabilities in terms

autonomy, endurance, payload, power outputs, etc.,

in recent years significant progress has been made in

all USV subsystem components (hull and structural

elements, propulsion and power system, GNC,

telemetry, payloads, data management and ground

station). This enabled USV to become a leading

commercial technology solution in several

applications and services (some on a routine basis)

beyond the military and research [5, 10, 26, 27, 41].

The initial reference on the path to autonomous

ships is technical. The core technologies that enable

unmanned vessels have come about largely due to

developments in other fields [8, 15, 22, 23]. Improved

USV capabilities allow to undertake missions both in

coastal and open-ocean areas for long periods of time

due to a more efficient power and propulsion systems

based in some cases on renewable energy sources

(solar, wind, waves), Fig. 1. State-of-the-art

broadband telemetry systems enable remote real-time

operation and decision-making by the operator. In

parallel with the mechanical and electronic system

architecture improvements for USVs, software

advanced rapidly as well, with special focus on

autonomous navigation methods and techniques in

compliance and contribution to ocean digitalization

and e-navigation framework initiatives.

Figure 1. Wave Glider ASV starting a mission conducted by

PLOCAN

While small USV developments are usually

deployed within sight of the operator there are many

others that go further. Considering hull dimension

and propulsion system as classification factors,

several flag-ship developments through last decade

have been released, highlighting Sailbuoy [21] tested

as pre-commercial solution at Oceanic Platform of the

Canary Islands (PLOCAN) open-ocean observatory in

2012; Wave Glider [17, 30] robust enough to complete

a crossing of the Pacific Ocean from California to

Australia or successfully accomplish routing transects

across the Macaronesia region by PLOCAN;

AutoNaut [36] performed trials at PLOCAN testy-site

waters for marine mammal monitoring, see Fig. 2; C.-

Enduro; the Saildrone [86] able to perform long-range

missions such circumnavigate the Antarctica and

ATL2MED [71] being PLOCAN an active member in

the second one providing its test-site facilities for

launching and initial field validations; DriX [34] with

specific applications on survey-services for industry;

Mayflower [50] expecting to sail between Plymouth-

Cape Cod (MA, USA); Sphyrna [72] that focusses on

passive acoustic monitoring applications; Data

Explorer; XOCEAN XO-450 [82] for energy and

seabed mapping commercial survey services; SeaTrac;

Submaran-S10 [58] as hybrid concept able to both sail

the ocean surface and glide the water-column as

underwater vehicle.

All of them are fully or partially powered by

endless ocean-energy sources. In parallel, half-way to

autonomous ship concept, developments such Sea-

KIT [73]; Ocean Infinity [59] have also been released

for specific seabed-mapping and survey-services in

industry applications at ocean-basin level worldwide.

These developments, many of them already

commercial, demonstrated that specialty USV could

withstand the harsh ocean environment for extended

periods and their software and systems were reliable

enough for extended voyages and missions.

Figure 2. AutoNaut ASV trials at PLOCAN test-site

facilities

137

3 AUTONOMOUS VESSELS: THE ULTIMATE

STEP TOWARDS SHIPPING 4.0

IMPLEMENTATION

The current global trend on autonomy developments

in mobility seems to be widely yet accepted by the

maritime community, primarily due to budgetary

issues. Up to date, autonomous and remotely

operated platforms at sea have been mainly used as

carriers of sensors and other measuring devices

mainly addressed to oceanography, hydrography and

off-shore applications in nearshore, controlled test-

site areas or outside shipping routes. However,

nowadays we are facing a step further towards a new

paradigm associated with cyber-physical systems, big

data and autonomy as part of Shipping 4.0 and

Digital Ocean international trends and strategies.

Efforts in transport cost reduction, the global need of

minimize emissions and the demand for improving

safety at sea are three base reasons on why

autonomous shipping is under consideration and

early stages of implementation [9, 54, 65, 66].

Under these premises, the development and future

implementation of vessels as MASS (Maritime

Autonomous Surface Ship) will represent an inflexion

point for the paradigm shift in the industry and

maritime shipping system as a whole [39, 61, 80, 81].

Therefore, for a successful and smooth settlement of

MASS as well as the relevant infrastructures in the

maritime sector, key aspects related to autonomous

shipping and their impact on technology, regulation

and societal aspects should be envisaged [1, 28, 29].

From the purely technology perspective, ships

should be built with enhanced control capabilities,

broadband telemetry, graphic interfaces, complex

sensor payloads, etc. in order to be operated by

means of remote land-based or off-shore services [40].

However, the technology replacing manning needs to

re-shape the crew in terms of safety, efficiency and

environmental protection. On the industry side,

MASS is expected to change shipbuilding and

equipment, as well as shipping protocols and port

infrastructures. Industries related to high specialized

technology base sectors such autonomy and

automation, unmanned operations, big data, artificial

intelligence, machine learning, enterprise-grade

connectivity and analytics will be essential.

In what refers to global trends of autonomous

vessels development, in the past decade several

international projects with large investment have

been (and still) conducted with Scandinavian

companies and research institutions playing a leading

role. Rolls Royce [69], Kongsberg, DNV GL,

Norwegian University of Science and Technology

(NTNU), among others, are fully involved with

ambitious plans to develop a new generation of all-

electric and autonomous container ships by 2022,

according to projects listed in Table 1. In the same

direction, other research institutions and companies

are developing complementary and competing

concepts to support unmanned shipping operations,

coupled with specific infrastructures and services,

including autonomous ports, high bandwidth

telemetry, etc.

Table 1. Flagship projects to develop autonomous vessels

_______________________________________________

Project Name (Period) Main Partner Institutions

_______________________________________________

MUNIN (2012-215) 8 EU research and industry

ReVOLT (2014-2018) DNV GL, NTNU

AAWA (2015-2018) Rolls Royce, DNV GL

YARA BIRKELAND KM, YARA, NTNU, DNV GL

(2017-2020)

AUTOSHIP (2019-2022) CIAOTECH, KM, SINTEF, BV

_______________________________________________

MUNIN, ReVOLT [18], AAWA have paved the

way for Yara Birkeland project [70, 85]. Yara and

Kongsberg have partnered to develop the world’s

first fully electric container vessel, starting in 2017

working towards remote operation by 2019 and is

scheduled to go fully autonomous in 2021.

Therefore, despite the rapid development of

science and technology in the maritime industry,

autonomous vessels indisputably need to be subject

to the international regulations necessary for the

vessels to operate safely across nations and even the

seabed areas beyond national jurisdiction. Some

regulatory aspects of manned vessels may be

compatible with unmanned vessels, such as certain

clauses of the International Safety Management (ISM)

Code. However, there is a need for specific

international regulations taking into account the

characteristics of unmanned vessels as well.

4 POLICY FRAMEWORK AS KEY DRIVER FOR

AUTONOMOUS MARITIME NAVIGATION

AND SHIPPING IMPLEMENTATION

While technology and market push are required for

any innovation to take hold, regulation aspects

become a major consideration. This is especially right

in the case of autonomous vessels, where certain key

developments can be noted as advancing the field.

During the period of roughly 2000-2010 early

work on software and algorithms to enable

unmanned vessels to adhere to the COLREGs

(Convention on the International Regulations for

Preventing Collisions at Sea) began. The ASTM

Committee launch, designed to develop technical

standards for unmanned maritime vehicles, including

a sub-committee for regulatory issues. This catalyzed

further policy developments. The Association for

Unmanned Systems International (AUVSI) began to

engage the issue through their Maritime Advocacy

Committee in 2011. A particular focus was informing

and engaging the U.S. Navigation Safety Advisory

Council (NAVSAC). This body informs the U.S. Coast

Guard, the relevant regulator for U.S. Waters.

Through a series of meetings this work eventually

resulted, in late 2012, in a resolution offering advice

on both technology solutions, such as use of the

automated identification system (AIS) and policy

steps, such as amendments to certain COLREGs [37].

The UK’s industry group, Maritime UK, launched

an effort to develop voluntary best practices for

unmanned vessels, though they referred to them as

maritime autonomous systems (MAS). The first

version of the UK Industry Code of Practice focused

mainly on technical aspects such as design and

construction of MAS [25, 49]. The UK Maritime

138

Autonomous Systems Regulatory Working Group

(MASRWG) released this first document in 2017.

While the guidance in the first version of the code

was for design, construction, and operation, it was

heavily focused on design and manufacture. Seeing

significant growth in the autonomous systems the

MASRWG updated the Code of Practice to increase

focus on the USV operations, with firstly guidance on

skills, training and platform’s registration.

A multidisciplinary group of Spanish research

centers, companies and public agencies, under the

coordination of DGMM (General Directorate of

Marine Merchant) are joining forces since late 2020 in

order to setup a working group on autonomous

maritime navigation. Its main goal is to setup the

right national framework to develop and operate

USV and autonomous ships that currently are under

development [56, 78]. PLOCAN is one of the active

partners providing both test-site capabilities and the

ownership of the first autonomous boat flagged in

Spain [24].

Figure 3. UTEK unmanned boat tested at PLOCAN test-site

While these previous efforts were regional in

focus the ultimate regulator responsible for the

COLREGs is the International Maritime Organization

(IMO). In 2017, following a proposal by a number of

Member States, IMO's Maritime Safety Committee

(MSC) agreed to include the issue on its agenda. This

led to yet another name for the technology, marine

autonomous surface ships (MASS). IMO agreed to

start with a scoping exercise to determine how the

safe, secure and environmentally sound operation of

MASS might be introduced in IMO policies and rules

[31–33].

Subsequently, in 2019 the MSC approved interim

guidelines for MASS trials. These were intended to

guide the ongoing developments and early

demonstrations on larger MASS eyeing commercial

scale vessels. The guidelines said that trials should be

conducted to provide at least the same degree of

safety, security and protection of the environment as

provided by the relevant existing regulations for

manned vessels. They addressed risk mitigation

practices and MASS operator qualifications. Notably

the guidelines also suggested that appropriate steps

to ensure cyber risk management.

The next step in the IMO process is to complete

their scoping exercise. This will evaluate IMO rules

and policies for applicability to MASS operations,

taking into account human, technology and

operational factors. Of particular interest to the

technology community the IMO will employ four

“degrees” of autonomy for the scoping exercise

(Table 2). The IMO anticipates completing this work

in 2021.

Table 2. MASS Levels of Control according to IMO in the

frame of a regulatory scoping exercise from 2018.

_______________________________________________

Level Description

_______________________________________________

1 Ships with automated processes and decision

support

2 Remotely controlled ships with seafarers onboard

3 Remotely controlled ships without seafarers

onboard

4 Fully autonomous ships

_______________________________________________

In Level (1) seafarers are on board to operate and

control shipboard systems and functions. Some

operations may be automated and at times be

unsupervised but with seafarers on board ready to

take control. Level (2) seafarers are available on board

to take control and to operate the shipboard systems

and functions. In level (3) the ship is controlled and

operated from another location. There are no

seafarers on board. Finally, in Level (4) the operating

system of the ship is able to undertake decisions and

determine actions by itself.

One of the biggest challenges in developing the

technology for MASS is to demonstrate that

unmanned systems are at least as safe as a manned

ship system and to provide the Shore Control Centre

(SCC) with adequate situation awareness. In case of

emergency situations such as stranding or evasive

manoeuvring, the ship systems should be remotely

monitored and controlled by the operators of the SCC

receiving crucial information via satellite at short

time intervals (Figure 4). The SCC should also have a

smart alarm system and the ability to switch to the

manual control mode in case of doubt on the

autonomous system [38, 63, 68].

Figure 4. USV - Shore Control Centre (SCC) at PLOCAN

facilities

5 TOWARDS A SAFE JOURNEY ON

AUTONOMOUS MARITIME NAVIGATION

The mission-oriented operating system (MOOS)

enabled surveys for both commercial and scientific

purposes to make good use of USV technology.

MOOS allowed such missions to be executed in a

supervisory control approach. Usually the vessel low-

level control (i.e. rudder actuation and navigation

path planning to pre-set waypoints) is automated

while the overall behaviour is managed by an

operator (Figure 5). This approach is commonly seen

in USV today [11, 19, 77, 84].

139

Figure 5. Graphic interface for USV remote piloting based

on pre-set waypoints with overlapped path planning tools

from multi-source data assimilation.

Autonomous navigation is achieved by training or

programming the instrument with the stored data

about its behavior in various operational scenarios.

The autonomous behavior relies on intelligent

analytics based on machine learning (ML) algorithms.

As a major advance in ML, the deep learning (DL)

approach is becoming a powerful technique for

autonomy. DL methodologies are applied in various

fields in the maritime industry such as detecting

anomalies, ship classification, collision avoidance,

risk detection of cyberattacks, navigation in ports, etc.

[60]. A diverse range of methods are available in the

literature for USV and MASS autonomy and their

applications in maritime navigation.

All learning techniques require small to large

amount of data in sophisticated format as base for

algorithms to generate the working models. Hence

“Data engineering” plays a crucial role in the proper

functioning of these techniques that are used for

autonomous navigation, and particularly in the field

of ship automation. Considering the range of

scenarios under which USV or MASS is exposed to,

the amount of data to be engineered could escalate to

‘Big Data’. Extremely important elements for their

operation are the anti-collision system and the data

fusion method from various sensors detecting

obstacles on a programmed path aiming a reliable

avoidance for a safe operation [55, 83].

Data source and storage are other key components

on which the total process of ship automation is

based. Considering the diverse type of data being

loaded through sensors, experiments, simulation or

calculation could intensify the problem of effective

storage for the later stage of data cleansing and data

transformation. Data engineering is the basis for the

anticipated outcome expected from a model. These

models are necessary in order a USV or MASS to

navigate without pilot assistance.

Autonomous navigation of ship consists of

various sensors to detect the navigating path, the

environmental and vessel properties to determine

safe travel. The successful implementation of

autonomy on vessels would occur with intelligent

decisions in all operational conditions. Many

methods have evolved from remotely operated to

full-autonomous operations in the last three decades.

Table 3 shows traditional methods summarized in

two categories.

Table 3. Summary of traditional methods on autonomous

navigation

_______________________________________________

Classical Methods Reactive Methods

_______________________________________________

RoadMap Building Fuzzy Logic Controller

Neural Network

Cell Decomposition Neuro-Fuzzy

Generic Algorithm

Artificial Potential Field Particle SWARM Optimization

Artificial Immune network

_______________________________________________

Advances in deep learning has made the

approaches towards replicating these complex

situations and autonomous collision avoidance [42,

62, 76] an easily achievable task in support to

COLREGs [3]. A high level of recognition and

situational awareness is necessary when AIS Data is

combined with data from other sources. To develop a

fully autonomous anomaly detection system, it

should be supported with the visuals of vessel

interaction at various environments to take intelligent

decisions, which can be provided by the CNN

algorithm.

Path planning is one of the key parameters in

marine autonomous systems [13, 35, 44, 74, 75]. Its

essence is to avoid obstacles and reach the target

point at optimum distance and time. The effective

path planning includes methods of artificial potential

field, neural network [16, 64], fuzzy logic [14, 20, 43]

and genetic algorithm. Most recent path planning

algorithm, a deep learning approach, adopts a safety

domain around each obstacle that serves to indicate

the risk of collision. The algorithm uses deep

reinforcement learning to reach the local target

position successfully in unknown dynamic

environment. Deep reinforcement learning solves the

problem of dimensionality well and can process

multidimensional inputs.

6 CONCLUSIONS

In this paper, a global vision of the USV sector has

been shown from the experiences of the authors in

PLOCAN. A detailed analysis about the present and

future of this sector has been depicted. An especial

emphasis has been done in showing the

interdisciplinary nature of the field, involving

technological, commercial and politics aspects. In

particular, the new tends in artificial intelligence

field, which represent a big step forward in the

advance of the autonomous navigation. The

technological developments presented include a

multidisciplinary set of state-of-the-art: Sensors and

systems for orientation, navigation, control,

telemetry, propulsion, route planning, as well as

specific tools for supervision and situational

awareness operations, being key the inclusion of the

aforementioned techniques of artificial intelligence.

IMO is developing a global regulatory framework for

MASS implementation in coming years. Because of

that, it becomes necessary at this time to make further

efforts in order to analysis this new sector.

140

REFERENCES

1. Autonomous and Remotely Operated Ships:

http://rules.dnvgl.com.

2. Barrera, C., Morales, T., Moran, R., Caudet, E., Marrero,

R., Cianca, A., Alcaraz, D., Campuzano, F., Fernandes,

C., de Sousa, J.T.B., Rueda, M.J., Llinas, O.: Expanding

operational ocean-observing capabilities with gliders

across the Macaronesia region. Presented at the AGU -

Ocean Sciences Meeting 2020 , San Diego, CA, USA

February 16 (2020).

3. Benjamin, M.R., Curcio, J.A.: COLREGS-based

navigation of autonomous marine vehicles. In: 2004

IEEE/OES Autonomous Underwater Vehicles (IEEE Cat.

No.04CH37578). pp. 32–39 (2004).

https://doi.org/10.1109/AUV.2004.1431190.

4. Bertram, V.: Unmanned surface vehicles-a survey.

Skibsteknisk Selskab, Copenhagen, Denmark. 1, 1–14

(2008).

5. Bibuli, M., Caccia, M., Lapierre, L., Bruzzone, G.:

Guidance of Unmanned Surface Vehicles: Experiments

in Vehicle Following. IEEE Robotics & Automation

Magazine. 19, 3, 92–102 (2012).

https://doi.org/10.1109/MRA.2011.2181784.

6. Bratić, K., Pavić, I., Vukša, S., Stazić, L.: Review of

Autonomous and Remotely Controlled Ships in

Maritime Sector. Trans. Marit. Sci. 8, 2, 253–265 (2019).

https://doi.org/10.7225/toms.v08.n02.011.

7. Breivik, M.: Topics in guided motion control of marine

vehicles. Norwegian University of Science and

Technology (2010).

8. Bremer, R.H., Cleophas, P.L., Fitski, H.J., Keus, D.:

Unmanned surface and underwater vehicles. DTIC

Document, TNO Defence Security and Safety

(Netherlands) (2007).

9. Burmeister, H.-C., Bruhn, W., Rødseth, Ø.J., Porathe, T.:

Autonomous Unmanned Merchant Vessel and its

Contribution towards the e-Navigation Implementation:

The MUNIN Perspective. International Journal of e-

Navigation and Maritime Economy. 1, 1–13 (2014).

https://doi.org/10.1016/j.enavi.2014.12.002.

10. Caccia, M.: Autonomous Surface Craft: prototypes and

basic research issues. In: 2006 14th Mediterranean

Conference on Control and Automation. pp. 1–6 (2006).

https://doi.org/10.1109/MED.2006.328786.

11. Caccia, M., Bibuli, M., Bono, R., Bruzzone, G.: Basic

navigation, guidance and control of an Unmanned

Surface Vehicle. Autonomous Robots. 25, 4, 349–365

(2008). https://doi.org/10.1007/s10514-008-9100-0.

12. Campbell, S., Naeem, W., Irwin, G.W.: A review on

improving the autonomy of unmanned surface vehicles

through intelligent collision avoidance manoeuvres.

Annual Reviews in Control. 36, 2, 267–283 (2012).

https://doi.org/10.1016/j.arcontrol.2012.09.008.

13. Casalino, G., Turetta, A., Simetti, E.: A three-layered

architecture for real time path planning and obstacle

avoidance for surveillance USVs operating in harbour

fields. In: OCEANS 2009-EUROPE. pp. 1–8 (2009).

https://doi.org/10.1109/OCEANSE.2009.5278104.

14. Chen, S.-L., Cheng, H.B.: Modeling and simulation

based on fuzzy neural network for unmanned surface

vehicle. Ship Science & Technology. 32, 11, 134–136

(2010).

15. Cruz, N.A., Alves, J.C.: Autonomous sailboats: An

emerging technology for ocean sampling and

surveillance. In: OCEANS 2008. pp. 1–6 (2008).

https://doi.org/10.1109/OCEANS.2008.5152113.

16. Dai, S., Wang, C., Luo, F.: Identification and Learning

Control of Ocean Surface Ship Using Neural Networks.

IEEE Transactions on Industrial Informatics. 8, 4, 801–

810 (2012). https://doi.org/10.1109/TII.2012.2205584.

17. Daniel, T., Manley, J., Trenaman, N.: The Wave Glider:

enabling a new approach to persistent ocean

observation and research. Ocean Dynamics. 61, 10,

1509–1520 (2011). https://doi.org/10.1007/s10236-011-

0408-5.

18. DNV GL. – ReVolt: Next Generation Short Sea

Shipping, https://www.dnvgl.com/news/.

19. Do, K.D.: Practical control of underactuated ships.

Ocean Engineering. 37, 13, 1111–1119 (2010).

https://doi.org/10.1016/j.oceaneng.2010.04.007.

20. Du, J., Yang, Y., Wang, D., Guo, C.: A robust adaptive

neural networks controller for maritime dynamic

positioning system. Neurocomputing. 110, 128–136

(2013). https://doi.org/10.1016/j.neucom.2012.11.027.

21. Fer, I., Peddie, D.: Near-surface oceanographic

measurements using the Sail Buoy: test deployment off

Grand Canaria. Christian Michelsen Research AS,

Bergen (2012).

22. Ferreira, H., Almeida, C., Silva, H., Almeida, J.M., Silva,

E., Martins, A.: ROAZ and ROAZ II Autonomous

Surface Vehicle Design and Implementation. Presented

at the International Lifesaving Congress , La Coruna,

Spain (2007).

23. Ferreira, H., Martins, R., Marques, E., Pinto, J., Martins,

A., Almeida, J., Sousa, J., Silva, E.P.: SWORDFISH: an

Autonomous Surface Vehicle for Network Centric

Operations. In: OCEANS 2007 - Europe. pp. 1–6 (2007).

https://doi.org/10.1109/OCEANSE.2007.4302467.

24. First Test Area for Autonomous Ships Opened in

Finland: https://worldmaritimenews.com.

25. First Unmanned Vessel Joins UK Ship Register:

https://worldmaritimenews.com.

26. Fossen, T.I.: Guidance and Control of Ocean Vehicles.

Wiley (1994).

27. Fossen, T.I.: Handbook of Marine Craft Hydrodynamics

and Motion Control. John Wiley & Sons, Ltd (2011).

28. Gu, Y., Goez, J.C., Guajardo, M., Wallace, S.W.:

Autonomous vessels: state of the art and potential

opportunities in logistics. International Transactions in

Operational Research. 28, 4, 1706–1739 (2021).

https://doi.org/10.1111/itor.12785.

29. Guidelines for Autonomous Shipping:

https://www.bureauveritas.jp.

30. Hine, R., Willcox, S., Hine, G., Richardson, T.: The Wave

Glider: A Wave-Powered autonomous marine vehicle.

In: OCEANS 2009. pp. 1–6 (2009).

https://doi.org/10.23919/OCEANS.2009.5422129.

31. IMO: Interim guidelines for MASS trials. , London, UK

(2018).

32. IMO: Regulatory scoping exercise for the use of

maritime autonomous surface ships (MASS). , London,

UK (2018).

33. IMO: Takes First Steps to Address Autonomous Ships,

http://www.imo.org/en/, last accessed 2021/02/02.

34. iXblue-DriX USV: Rethinking the Traditional Model for

Offshore Operations, https://www.hydro-

international.com/content/article/rethinking-the-

traditional-model-for-offshore-operations, last accessed

2021/04/25.

35. Jing, W., Liu, C., Li, T., Rahman, A.B.M.M., Xian, L.,

Wang, X., Wang, Y., Guo, Z., Brenda, G., Tendai, K.W.:

Path Planning and Navigation of Oceanic Autonomous

Sailboats and Vessels: A Survey. Journal of Ocean

University of China. 19, 3, 609–621 (2020).

https://doi.org/10.1007/s11802-020-4144-7.

36. Johnston, P., Poole, M.: Marine surveillance capabilities

of the AutoNaut wave-propelled unmanned surface

vessel (USV). In: OCEANS 2017 - Aberdeen. pp. 1–46

(2017). https://doi.org/10.1109/OCEANSE.2017.8084782.

37. Karlis, T.: Maritime law issues related to the operation

of unmanned autonomous cargo ships. WMU Journal of

Maritime Affairs. 17, 1, 119–128 (2018).

https://doi.org/10.1007/s13437-018-0135-6.

38. Karvonen, H., Martio, J.: Human Factors Issues in

Maritime Autonomous Surface Ship Systems

Development. In: SINTEF Proceedings. SINTEF

Academic Press (2019).

141

39. Kim, M., Joung, T.-H., Jeong, B., Park, H.-S.:

Autonomous shipping and its impact on regulations,

technologies, and industries. null. 4, 2, 17–25 (2020).

https://doi.org/10.1080/25725084.2020.1779427.

40. Komianos, A.: The Autonomous Shipping Era.

Operational, Regulatory, and Quality Challenges.

TransNav, the International Journal on Marine

Navigation and Safety of Sea Transportation. 12, 2, 335–

348 (2018). https://doi.org/10.12716/1001.12.02.15.

41. Lambert, J., Manley, J.: Development of Unmanned

Maritime Vehicle (UMV) Standards, An Evolving

Trend. Sea Technology. 48, 12, (2007).

42. Larson, J., Bruch, M., Ebken, J.: Autonomous navigation

and obstacle avoidance for unmanned surface vehicles.

Presented at the Proc.SPIE May 9 (2006).

https://doi.org/10.1117/12.663798.

43. Lee, S.-M., Kwon, K.-Y., Joh, J.: A Fuzzy Logic for

Autonomous Navigation of Marine Vehicles Satisfying

COLREG Guidelines. International Journal of Control,

Automation, and Systems. 2, 2, 171–181 (2004).

44. Liu, Y., Bucknall, R.: Path planning algorithm for

unmanned surface vehicle formations in a practical

maritime environment. Ocean Engineering. 97, 126–144

(2015). https://doi.org/10.1016/j.oceaneng.2015.01.008.

45. Liu, Z., Zhang, Y., Yu, X., Yuan, C.: Unmanned surface

vehicles: An overview of developments and challenges.

Annual Reviews in Control. 41, 71–93 (2016).

https://doi.org/10.1016/j.arcontrol.2016.04.018.

46. Manley, J.E.: Unmanned surface vehicles, 15 years of

development. In: OCEANS 2008. pp. 1–4 (2008).

https://doi.org/10.1109/OCEANS.2008.5152052.

47. Marichal, G.N., Acosta, L., Moreno, L., Méndez, J.A.,

Rodrigo, J.J., Sigut, M.: Obstacle avoidance for a mobile

robot: A neuro-fuzzy approach. Fuzzy Sets and

Systems. 124, 2, 171–179 (2001).

https://doi.org/10.1016/S0165-0114(00)00095-6.

48. Marichal, G.N., Hernández, A., Rojas, J.A., Melón, E.,

Rodríguez, J.A., Padrón, I.: Sistema Inteligente de apoyo

a maniobras de grandes buques en puertos. Revista

Iberoamericana de Automática e Informática Industrial

RIAI. 13, 3, 304–309 (2016).

https://doi.org/10.1016/j.riai.2016.03.005.

49. Maritime Autonomous Surface Ships UK Code of

Practice: https://www.maritimeuk.org.

50. MARS: Mayflower Autonomous Research Ship. NMIO

Technical Bulletin. 10, 7–8 (2015).

51. Matía, F., Marichal, G.N., Jiménez, E.: Fuzzy Modeling

and Control: Theory and Applications. Atlantis Press,

Paris (2014).

52. Michalski, R.S., Carbonell, J.G., Mitchell, T.M.: Machine

Learning. Springer, Berlin, Heidelberg (1983).

53. Motwani, A.: A survey of uninhabited surface vehicles.

(2012).

54. Munim, Z.H.: Autonomous ships: a review, innovative

applications and future maritime business models. null.

20, 4, 266–279 (2019).

https://doi.org/10.1080/16258312.2019.1631714.

55. Naeem, W., Sutton, R., Xu, T.: An integrated multi-

sensor data fusion algorithm and autopilot

implementation in an uninhabited surface craft. Ocean

Engineering. 39, 43–52 (2012).

https://doi.org/10.1016/j.oceaneng.2011.11.001.

56. NAVANTIA. USV Vendaval:

https://www.innovaspain.com/navantia-barco-

vendaval-ceuta/.

57. Nilsson, N.J.: Principles of Artificial Intelligence.

Springer-Verlag, Berlin Heidelberg (1982).

58. Ocean Aero S10: UST-Magazine. 9, 22–31 (2015).

59. Ocean Infinity: Armada Fleet,

https://oceaninfinity.com/marine-robotics/.

60. Perera, L.P.: Autonomous Ship Navigation Under Deep

Learning and the Challenges in COLREGs. Presented at

the ASME 2018 37th International Conference on Ocean,

Offshore and Arctic Engineering September 25 (2018).

https://doi.org/10.1115/OMAE2018-77672.

61. Poikonen, J., Hyvonen, M., Kolu, A., Jokela, T., Tissari,

J., Paasio, A.: Remote and autonomous ships – The Next

Steps, https://www.rolls-royce.com.

62. Polvara, R., Sharma, S., Wan, J., Manning, A., Sutton, R.:

Obstacle Avoidance Approaches for Autonomous

Navigation of Unmanned Surface Vehicles. Journal of

Navigation. 71, 1, 241–256 (2018).

https://doi.org/10.1017/S0373463317000753.

63. Porathe, T., Prison, J.: Situation awareness in remote

control centres for unmanned ships. Presented at the

Human Factors in Ship Design & Operation , London,

UK (2014).

64. Praczyk, T.: Neural anti-collision system for

Autonomous Surface Vehicle. Neurocomputing. 149,

559–572 (2015).

https://doi.org/10.1016/j.neucom.2014.08.018.

65. R⊘dseth, Ø.J.: From concept to reality: Unmanned

merchant ship research in Norway. In: 2017 IEEE

Underwater Technology (UT). pp. 1–10 (2017).

https://doi.org/10.1109/UT.2017.7890328.

66. Remote and Autonomous Ship: The next steps. AAWA

67. Roberts, G.N., Sutton, R.: Advances in Unmanned

Marine Vehicles. IET Digital Library (2006).

https://doi.org/10.1049/PBCE069E.

68. Rolls-Royce: Rolls-Royce Opens Autonomous Ship

Research and Development Centre in Finland. , London,

UK (2021).

69. Rolls-Royce and Finferries Demonstrate World’s First

Fully Autonomous Ferry: https://www.rolls-

royce.com/media/press-releases/2018/03-12-2018.

70. Safety4Sea: Yara Birkeland to start sailing during 2021,

https://safety4sea.com/yara-birkeland-to-start-sailing-

during-2021/, last accessed 2021/04/25.

71. Saildrone: ATL2MED international scientific-

technological mission launched – Plataforma Oceánica

de Canarias, https://www.plocan.eu/en/saildrone-

atl2med-international-scientific-technological-mission-

launched/, last accessed 2021/04/25.

72. Sea Proven: Sphyrna 70 - Unmanned Surface Vehicle,

http://www.seaproven.com/nos-realisations/sphyrna/,

last accessed 2021/04/25.

73. SEA-KIT: Complete First ever International Commercial

Unmanned Transit, http://www.oceannews.com.

74. Śmierzchalski, R., Kolendo, P.: Ship Evolutionary

Trajectory Planning Method with Application of

Polynomial Interpolation. In: Weintrit, A. (ed.)

Activities in Navigation. CRC Press, London, UK (2015).

75. Song, R.: Path planning and bi-directional

communication for unmanned surface vehicle. (2014).

76. Statheros, T., Howells, G., Maier, K.M.: Autonomous

Ship Collision Avoidance Navigation Concepts,

Technologies and Techniques. Journal of Navigation.

61, 1, 129–142 (2008).

https://doi.org/10.1017/S037346330700447X.

77. Sutton, R., Sharma, S., Xao, T.: Adaptive navigation

systems for an unmanned surface vehicle. null. 10, 3, 3–

20 (2011).

https://doi.org/10.1080/20464177.2011.11020248.

78. UTEK Unmanned Solutions for Maritime Applications:

https://www.plocan.eu/la-direccion-general-de-la-

marina-mercante-admite-a-tramite-el-primer-

abanderamiento-en-espana-de-una-embarcacion-

autonoma-no-tripulada/.

79. Verfuss, U.K., Aniceto, A.S., Harris, D.V., Gillespie, D.,

Fielding, S., Jiménez, G., Johnston, P., Sinclair, R.R.,

Sivertsen, A., Solbø, S.A., Storvold, R., Biuw, M., Wyatt,

R.: A review of unmanned vehicles for the detection and

monitoring of marine fauna. Marine Pollution Bulletin.

140, 17–29 (2019).

https://doi.org/10.1016/j.marpolbul.2019.01.009.

80. Wright, R.G.: Unmanned and Autonomous Ships : An

Overview of MASS. Routledge (2020).

https://doi.org/10.1201/9780429450655.

142

81. Wróbel, K., Montewka, J., Kujala, P.: Towards the

assessment of potential impact of unmanned vessels on

maritime transportation safety. Reliability Engineering

& System Safety. 165, 155–169 (2017).

https://doi.org/10.1016/j.ress.2017.03.029.

82. XOCEAN XO-450: UST-Magazine. 22, 22–32 (2018).

83. Xu, T., Sutton, R., Sharma, S.: A multi-sensor data fusion

navigation system for an unmanned surface vehicle.

Proceedings of the Institution of Mechanical Engineers,

Part M: Journal of Engineering for the Maritime

Environment. 221, 4, 167–182 (2007).

https://doi.org/10.1243/14750902JEME72.

84. Yan, R., Pang, S., Sun, H., Pang, Y.: Development and

missions of unmanned surface vehicle. Journal of

Marine Science and Application. 9, 4, 451–457 (2010).

https://doi.org/10.1007/s11804-010-1033-2.

85. Yara Birkeland: Rina,

https://www.rina.org.uk/yarabirkeland.html.

86. Zhang, D., Cronin, M.F., Meinig, C., Farrar, J.T., Jenkins,

R., Peacock, D., Keene, J., Sutton, A., Yang, Q.:

Comparing Air-Sea Flux Measurements from a New

Unmanned Surface Vehicle and Proven Platforms

During the SPURS-2 Field Campaign. Oceanography.

32, 2, (2019). https://doi.org/10.5670/oceanog.2019.220.