Autonomous Ships 2022

Abstracts

AIS will become a Maritime IoT network – Sternula will make It global with satellites

L Moltsen, Sternula ApS

AIS has been tracking ships for more than 20 years. Now AIS 2.0 (also known as VDES) is about to be deployed in coast radio networks and satellites. AIS 2.0 has been given new radio spectrum which allows for new open data channels that can be used for a range of digital services, such as distribution of weather forecasts, preventive monitoring of engines. Sternula is Denmark’s first satellite operator and will be offering global AIS 2.0 connectivity via satellite.

Regulating Autonomous Shipping- A Case Study

B Soyer, Institute of International Shipping and Trade Law, Swansea University

Various companies and organisations have been working for some time to develop Maritime Autonomous Surface Ships (MASSs) that can be used in commercial shipping. As it is often the case with emerging technologies, there is a risk that such technological developments might well be ahead of the current legal and regulatory framework and that adjustments in the regulatory sense will need to be made within a short period of time. The primary objective of this paper is to highlight the regulatory and legal challenges that need to be addressed so that MASSs can operate within UK territorial waters without complication. It is envisaged that it will be within the remit of different regulatory bodies to deal with the legal and regulatory challenges ahead. For example, the Marine and Coastguard Agency (MCA) is expected to provide regulatory solutions to issues concerning safety and technological requirements of MASSs. Port and harbour authorities need to specify the conditions that a MASS should comply with to gain access into areas that come under their jurisdiction. As part of this paper, it is intended to consider legislative changes that are needed to clarify matters concerning liability (collusion liability and product liability), limitation of liability, salvage, cargo claims and arrest of MASSs as well as to deal with criminal law issues that might emerge.

Maritime Autonomy and Remote Operations – Development of Regulations

R Taylor, Maritime & Coastguard Agency

Progress is being made at a great pace to support and enable the use of autonomous vessels with the appropriate regulation in the UK and internationally. Building on the work of MARLab, the Maritime and Coastguard Agency are now updating regulations to enable the safe operation of smaller under 24m MASS in the UK and have started to develop the regulatory framework required for all MASS to operate safely in UK waters. The Maritime and Coastguard Agency has developed a leading team, the Maritime Future Technologies team, who are at the forefront of researching and instigating change for future MASS in maritime.
The MCA will give insight into the regulatory updates and how they will support autonomous vessels in the UK and present our latest thinking on how the MCA will facilitate and support industry in the future. With key developments planned over the next six months, presenting at the conference will gives us the opportunity to explore with industry key areas or issues highlighted in the development of new regulatory frameworks. These developments and push for change in domestic legislation continue to put the UK in a leading position amongst regulators across the world.

Towards autonomy – A view from the bridge

C Balls, Cayman Islands Ship Register

This paper will show that the role of a lookout as an essential part of proper bridge watchkeeping has existed for a long time but has been evolving over that time and will continue to as autonomy develops.
It will include a brief study of historical records of the evolving role of a lookout including personal experience. From persons stationed at mastheads to the now more common sitting in a fully enclosed wheelhouse. As technology developed such as binoculars, radar etc. so some people have opposed it, but eventually the technology has become the norm. Also mention will be made of the trend to regulatory exemptions and equivalences including such items as CCTV to augment visual information to watch-keepers.
It will include an overview and analysis of the principal regulatory requirements for lookout and watchkeeping for example; COLREGS – Rule 5 ” Every vessel shall at all times maintain a proper look-out by sight and hearing as well as by all available means appropriate to the prevailing circumstances and conditions so as to make a full appraisal of the situation and risk of collision”. Regulation 22 of SOLAS V, specifies bridge visibility requirements, STCW- Section A-VIII/2 covers watchkeeping arrangements and principles to be observed – technically applies only to seafarers serving on board seagoing ships which is interesting especially when considering shore based control centres for ships.
The more widespread introduction of unmanned vessels will in many ways be evolutionary rather than revolutionary.

SWOT analysis of leading safety indicators for collision avoidance of Maritime Autonomous Surface Ships

J Nasur and K Wróbel, Gdynia Maritime University

Timely and reliably detecting a close-quarters situation at sea is vital to the safety of navigation. With the development of Maritime Autonomous Surface Ships (MASS), successful collision avoidance will depend to a lesser extent on humans, but rather on computers and implemented algorithms. However, the risk of collision is nowadays evaluated by humans, based on their experience, training, within a context of relevant collision regulations, adopting various safety indicators, being often subjective. The latter include: Bow Crossing Range (BCR) and Closest Point of Approach (CPA) – commonly used in seagoing practice – and recently proposed Last Time to Take Action (LTTA) or Minimum Distance To Collision (MDTC).
However for the indicators to be applicable for MASS ensuring its safe and efficient navigation, the following generic SMART requirements appropriate for leading safety indicators shall be met: Specific, Measurable, Attainable, Relevant, and Time-based.
This study aims to define and analyze a set of SMART-type leading safety indicators suitable for MASS, along with their feasibility, benefits, and disadvantages, as well as reference values. To this end a comprehensive literature study has been performed, including scientific literature, as well as reports, working papers, government documents, white papers and evaluations. Additionally the experts’ knowledge is elicited from sea going personnel. Finally, the obtained findings from those two sources of knowledge are collated using SWOT analysis and the results are formulated.
These can allow for a better managerial insight into the subject of MASS collision avoidance and safety of navigation in general.

Manning the unmanned ship: Is safe manning legislation a bottleneck in the development of autonomous ships?

S Eriksen, SIMAC

Legislation is often mentioned as a barrier to the development of autonomous and/or unmanned ships. Fully unmanned operation may not be possible within the current rules, but it is not so clear whether the laws on safe manning of ships is currently a bottleneck in a gradual reduction of crew sizes. This paper examines this issue through the analysis of data on safe manning and actual manning for 210 cargo and passenger ships. It is found that most vessels have an actual manning which is significantly higher than the minimum manning required by law. Both safe and actual crew sizes are, as expected, found to increase with increasing ship size but so is the difference between safe and actual manning. The reason why ships operate with a larger crew than required by law is found to be caused by the technical and operational needs of the vessels. Maritime law may not at present allow for completely unmanned operation of commercial cargo ships. If the assumption that the reduction in crew size will happen gradually is accepted, however, legislation on safe manning is not a bottleneck in the development of autonomous and unmanned ships.

The Armada Fleet: Technical Update ahead of initial operations

D Hook, Ocean Infinity

Ocean Infinity’s Armada fleet will revolutionise offshore operations, providing uncrewed and low-emission alternatives to conventional marine solutions.
With 17 custom-designed hybrid-powered robotic ships ranging from 21-78m in length, Ocean Infinity’s new Armada Fleet is being designed and built to be remotely-operated. This will cover both navigational and payload operations.
The fleet is currently in build and the first ships will begin operations in 2022. This paper will give an update of the vessels, payload, control, communications and remote operations architecture. The presentation will discuss lessons learned and the design freedom associated with lean and uncrewed vessels.
The fleet includes both aluminium and steel vessels, under and over 24m in length with varying levels of complexity such as DP2 systems. The systems for remote monitoring and predictive maintenance are focussed on efficiency and could benefit more conventional operations.
Remotely operated and uncrewed vessels will be a huge part of the future of our industry, and we look forward to engaging with colleagues, partners and stakeholders to show the progress we’ve made.

Highly Autonomous Warship Technologies

J Rigby, BMT

Highly Autonomous Warship Technologies: Underpinning Safe, Secure and Cost-effective lean-crewed warships. Embracing the future of maritime autonomy this paper explores the core enabling technologies that will facilitate lean crewing on warships. There are many ethical and practical constraints that currently make a completely unmanned surface combatant unfeasible; therefore the near future solutions may utilise highly autonomous vessels alongside smaller unmanned counterparts to create an optimal force structure. In this thought leadership piece, BMT breaks down the challenges of autonomy in warship design into seven core development areas and creates a vision for how a warship in 2040 could operate.

A semi automated model for improving Naval Vessel System Reliability and Maintenance Data Management 

A  A, Daya and I Lazakis, Department of Naval Architecture Ocean and Marine Engineering, University of Strathclyde, Glasgow, UK.

The demanding nature of Naval operational requirements leads to rapid deterioration and decline in the reliability of ships systems and machineries. In most Navies ships built with design life of 25-30 years begin to significantly decline in performance around 7-8 years after joining service.  Consequently, these leads to frequent and often prolonged downtime and huge maintenance cost. The Nigerian Navy like other navies is equally faced with this situation in a challenging manner due to the introduction of new platforms and largely to non-standardised data management. Therefore, a data management approach that is focused on the use of maintenance, repair, and overhaul (MRO) data is proposed. The proposed approach will build on the existing data collection and management practiced in the Nigerian Navy while identifying possible alternatives for both onboard and fleet level maintenance data collection and management. In this regard a platform for a predictive machinery condition monitoring approach based on failure mode and component criticality is proposed. A combination of tools that includes Failure Mode Effect and Criticality analysis, Bayesian Belief Network and Artificial Neural Network prediction were used to implement the proposed model. Therefore, the combination of these three tools was used to identify Mission Critical faults and components of an offshore patrol vessel; based on which suggested solutions were provided for improved maintenance scheduling.

Evolutionary Treaty Interpretation in the context of compliance of MASS operations with UNCLOS and SOLAS

M Sumer, IMO International Maritime Law Institute

From a regulatory standpoint, legal hurdles may arise in particular for the advanced levels of autonomy in Maritime Autonomous Surface Ships (MASS). This may be more problematic in relation to the classification of MASS as ships under the United Nations Convention on the Law of the Sea, 1982 (UNCLOS) and traditional responsibilities of the master which are stipulated in the International Convention for the Safety of Life at Sea, 1974 (SOLAS). Apparently, when this occurs relevant extant standards may need to be amended or interpreted, as well as new provisions may need to be adopted to enable the operation of MASS.
In this context, this paper seeks to present the interrelationship between the law of treaties and the compliance issues of MASS, in particular amendment and interpretation of the current regulatory framework, including the UNCLOS and IMO instruments, particularly SOLAS. Furthermore, it intends to analyse whether an amendment of the existing framework is possible and if so whether it is also practical. Moreover, this paper seeks to find out the appropriate method of interpretation and whether the “evolutionary interpretation” approach can be useful in clarifying the meaning of generic terms such as “ship” and “master”. Finally, this paper will also explore the role of the States in the implementation of shipping regulations, with a view to underscore the importance of the role of the IMO and its Member States in realising the MASS operations.

Application of Risk Analysis Method with System Modeling to Remote Operation of Experimental Ship, Shinpo

M Shiokari, National Maritime Research Institute, National Institute of Maritime, Port and Aviation Technology

As the technological development related to autonomous ship operation is in progress over the world, risk analysis methods for such complicated technologies have been increasingly required. To address this demand, the authors proposed a modeling method for a complicated system including software, which can be used with existing hazard identification methods. The method was applied to a hypothetical autonomous ship and used to identify hazards within the ship.
In this study, we took a step forward and tried to apply the method to a remote operation of a real ship, namely, a small experimental ship, Shinpo. Firstly, a model diagram of the remote operation system was developed, which could express the overall system structure, consisting of human operators, controllers, sensors, actuators, and communication systems. The interactions among the components, such as data exchanges, controls, and feedbacks, were also included in the diagram.
Then, referring to the diagram, focusing on the interactions among the components in addition to equipment failures, the authors identified hazards within the system, such as transmission of inappropriate control command from remote ship control system to onboard ship control system. The causes of the hazard include input error by the human operator, incorrect algorithm of remote ship control system, trouble in communication system, and complicated user-interface to input command. The results show that the proposed method helps analysts to understand the structure of a target system and facilitates hazard identification, and will contribute to improving the safety of autonomous ship systems including remote operation systems.

Where does the pilot go when the autonomous ship has no bridge? MASS Routing Service and smart Local Information Centres

T Porathe, NTNU, Norwegian University of Science and Technology

The need for pilots with local knowledge of the danger along a specific stretch of the coast has been an essential part of safe navigation for centuries. On their webpage the International Association of Maritime Pilots state that “There is no substitute for the presence of a qualified pilot on the bridge.” At the same time the International Maritime Organization IMO aims to integrate Maritime Autonomous Surface Ships (MASS) in its regulatory framework, some of which might sail unmanned with no provisions for a bridge onboard. This paper aims to discuss the safety problems this could lead to, and to suggest a concept of how this can be handled. The paper concludes with suggesting some concepts for a MASS Routing Service based on an automatic Local Information Centre researched in the current Norwegian project IMAT (Integrated Maritime Autonomous Transport Systems).

Acoustic-Based Machinery Condition Monitoring in Autonomous Ships

N Rajapaksha, Australian Maritime College, University of Tasmania

Conventional ships monitor their machinery condition within the engine room through a human watch system. Also, the integrated sensor systems of the ships provide the live feed of machinery parameters to the engine control room. In the fully autonomous ships, these inputs would be transferred to a shore-based control centre to monitor by a remote operator. However, the physical absence of human sensory inputs given by the engine room watchkeeper raises issues for remote operators in decision making and having awareness of the deteriorating machinery conditions. This paper presents a developed machine learning-based algorithm which can be used to mimic the watchkeepers’ auditory inspection ability to classify the machinery condition. Firstly, a series of experiments was conducted using a three-phase electric motor to collect acoustic signals and used them as the input data to train several machine learning algorithms. These acoustic data were shown Fast Fourier Transform (FFT) magnitudes and Support Vector Machine (SVM) algorithm could provide a greater classification accuracy. Then the experiments were extended using a four-stroke diesel engine to validate the findings and identify which kernel function can generalise the machinery acoustic signal classification. The results have shown an accuracy of over 94% for unseen four-stroke diesel engine data upon selecting the FFT magnitudes and SVM algorithm with a second-order kernel function. Furthermore, it was found that the accuracy of the second-order polynomial kernel function was independent of the microphone used to collect the acoustic data. The findings of this paper are beneficial to mitigate the lack of awareness of engine room machinery abnormalities in future autonomous ships.

Autonomous Control in Shallow and Confined Water

T Van Zwijnsvoorde, Flanders Hydraulics Research

The number of players in the field of autonomous shipping is increasing rapidly, with some efforts already reaching the prototype stage. A key aspect involves developing an algorithm to control the ship in complex navigational environments, such as rivers, channels and ports. In these conditions, the ship is subjected to specific hydrodynamic effects such as shallow water and bank effects, as well as interaction with other waterway users. If these effects are not adequately accounted for, the ship will experience difficulties to control her track, potentially leading to major damages.

Flanders Hydraulics Research, in co-operation with Ghent University, is a leader in the development of ship control algorithms for these challenging navigational conditions. Towing tank experiments as well as numerical models (ship manoeuvring simulators) are used extensively to develop and validate control algorithms for autonomous vessels. In January 2022 a state-of-the-art free running system was inaugurated in the new Towing Tank for Manoeuvres in Shallow Water in Ostend. The position of the ship model (scale model of an autonomous ship) in the tank is continuously updated using lidar and camera input, while the ship is automatically controlled using in-house developed algorithms. All systems are connected through ROS (Robot Operating System).

The flexibility introduced by the ROS environment allows to perform a wide selection of tests which are used to develop and validate autonomous control systems. Track control and path following algorithms, as well as obstacle avoidance methods can be refined for specific navigational applications involving interactions between multiple autonomous ships.