Knowledge

In this webinar, Adrienne Mannov from Aarhus University and Peter Aske Svendsen from NFA presented their research on autonomous shipping as this relates to seafaring and technology, based on their 2019 report, “Transport 2040: Autonomous ships: A new paradigm for Norwegian shipping - Technology and transformation”.

The event was organized in collaboration with MARLOG

The purpose of this project is therefore to develop a software tool that can implement an automated intelligent registration (artificial intelligence) of the catch of cod on board the vessel. The project can both support the ongoing camera projects, but also functions as a forward-looking method where the concept of this approach is that the camera focuses on the catch and can be implemented without human supervision. This has a number of potential advantages, including that human supervision is avoided, the number of cameras can probably be reduced to just one (although possibly a stereo camera), labor resources are saved by automated monitoring, it will be possible to reduce the amount of data, fishermen can target selective fishing based on the information obtained, increased precision in relation to possible legal
use of the observations and overall it will reduce costs. The project supports the monitoring that has been initiated in the Kattegat, but should also be seen as a future development, including internationally, where the focus is on building monitoring/surveillance around the use of images as documentation of the catch. An extremely important element of the project is to create a high-quality dataset that can be used internationally to improve algorithms and intensify research.

Highly reliable situation awareness is a main driver to enhance safety via autonomous technology in the marine industry. Groundings, ship collisions and collisions with bridges illustrate the need for enhanced safety. Authority for a computer to suggest actions or to take command, would be able to avoid some accidents where human misjudgement was a core reason. Autonomous situation awareness need be conducted with extreme confidence to let a computer algorithm take command. The anticipation of how a situation can develop is by far the most difficult step in situation awareness, and anticipation is the subject of this article. The IMO International Regulations for Preventing Collisions
at Sea (COLREGS), describe the regulatory behaviours of marine vessels relative to each other, and correct interpretation of situations is instrumental to safe navigation. Based on a breakdown of COLREGS rules, this article presents a framework to represent manoeuvring behaviours that are expected when all vessels obey the rules. The article shows how nested finite automata can segregate situation assessment from decision making and provide a testable and repeatable algorithm. The suggested method makes it possible to anticipate own ship and other vessels’ manoeuvring in a multi-vessel scenario. The framework is validated using scenarios from a full-mission simulator.

Highly reliable situation awareness is a main driver to enhance safety via autonomous technology in the marine industry. Groundings, ship collisions and collisions with bridges illustrate the need for enhanced safety. Authority for a computer to suggest actions or to take command, would be able to avoid some accidents where human misjudgement was a core reason. Autonomous situation awareness need be conducted with extreme confidence to let a computer algorithm take command. The anticipation of how a situation can develop is by far the most difficult step in situation awareness, and anticipation is the subject of this article. The IMO International Regulations for Preventing Collisions
at Sea (COLREGS), describe the regulatory behaviours of marine vessels relative to each other, and correct interpretation of situations is instrumental to safe navigation. Based on a breakdown of COLREGS rules, this article presents a framework to represent manoeuvring behaviours that are expected when all vessels obey the rules. The article shows how nested finite automata can segregate situation assessment from decision making and provide a testable and repeatable algorithm. The suggested method makes it possible to anticipate own ship and other vessels’ manoeuvring in a multi-vessel scenario. The framework is validated using scenarios from a full-mission simulator.

Background: Autonomous ships have the potential to increase operational efficiency and reduce carbon footprints through technology and innovation. However, there is no comprehensive literature review of all the different types of papers related to autonomous ships, especially with regard to their integration with ports. This paper takes a systematic review approach to extract and summarize the main topics related to autonomous ships in the fields of container shipping and port management. Methods: A machine learning method is used to extract the main topics from more than 2000 journal publications indexed in WoS and Scopus. Results: The research findings highlight key issues related to technology, cybersecurity, data governance, regulations, and legal frameworks, providing a different perspective compared to human manual reviews of papers. Conclusions: Our search results confirm several recommendations. First, from a technological perspective, it is advised to increase support for the research and development of autonomous underwater vehicles and unmanned aerial vehicles, establish safety standards, mandate testing of wave model evaluation systems, and promote international standardization. Second, from a cyber–physical systems perspective, efforts should be made to strengthen logistics and supply chains for autonomous ships, establish data governance protocols, enforce strict control over IoT device data, and strengthen cybersecurity measures. Third, from an environmental perspective, measures should be implemented to address the environmental impact of autonomous ships. This can be achieved by promoting international agreements from a global societal standpoint and clarifying the legal framework regarding liability in the event of accidents.

This PhD theis focuses on identifying the opportunities and challenges that on-board maintenance and practical operation of vessels poses in the development of autonomous ships. Inspired by the rapid development of autonomous vehicles considerable effort and interest is now invested in the development of autonomous ships. So far however, most of the research has focused on the legal aspect of unmanned vessels and on developing a system enabling a vessel to operate within the maritime collision regulation without human interaction. Specifically, the theisi looks into three research questions: (1) How is autonomous technology going to affect the workload required for operating and maintaining modern cargo vessels? (2) How is autonomous technology going to affect the operational patterns of the vessels? And (3) How is autonomous technology going to affect the reliability and utilization rate of the vessels?

The study is planned in cooperation between Svendborg International Maritime Academy (SIMAC) and University of Southern Denmark.

Unmanned and autonomous cargo ships may transform the maritime industry,
but there are issues regarding reliability of machinery which must frst be solved.
This paper examines the efect of voyage length on the reliability of machinery
with redundancy on unmanned ships. The limiting efects of dependent failures on
the improvement of reliability through the use of redundancy is also explored. A
strong relationship between voyage length and probability of independent failures
in systems with redundancy is shown. Increased redundancy can easily counteract
this negative efect of long unmanned voyages on reliability. Dependent failures,
however, are not afected by increased redundancy. The contribution of dependent
failures on the total probability of failure is found to easily exceed the contribution
from independent failures if even a slight proportion of the failures is dependent.
This has serious implications for unmanned ships where the possibility of corrective
maintenance is very limited and the consequences of mechanical failures on, e.g. the
propulsion of the ships can therefore be expected to be more severe than on conventionally manned ships. Redundancy in itself may not be enough to provide the reliability of machinery systems required for unmanned operation and other solutions
must therefore be found.

Unmanned autonomous cargo ships may change the maritime industry, but there are issues regarding reliability and maintenance of machinery equipment that are yet to be solved. This article examines the applicability of the Reliability Centred Maintenance (RCM) method for assessing maintenance needs and reliability issues on unmanned cargo ships. The analysis shows that the RCM method is generally applicable to the examination of reliability and maintenance issues on unmanned ships, but there are also important limitations. The RCM method lacks a systematic process for evaluating the effects of preventive versus corrective maintenance measures. The method also lacks a procedure to ensure that the effect of the length of the unmanned voyage in the development of potential failures in machinery systems is included. Amendments to the RCM method are proposed to address these limitations, and the amended method is used to analyse a machinery system for two operational situations: one where the vessel is conventionally manned and one where it is unmanned. There are minor differences in the probability of failures between manned and unmanned operation, but the major challenge relating to risk and reliability of unmanned cargo ships is the severely restricted possibilities for performing corrective maintenance actions at sea.

This report presents the AEGIS roadmap for automated waterborne transport and is the result of the work related to Task 2.5 Roadmap for waterborne logistics redesign as defined in the AEGIS Grant Agreement. The task was to collect the results of the AEGIS work package 2 and 6, and the AEGIS use cases, to provide a publicly available roadmap for the redesign of more sustainable waterborne transport. Furthermore, the main AEGIS solutions that can be used to realize the redesign were to be identified, and benefits and possible costs were to be described, exemplified by future transport systems, including intercontinental transport. Furthermore, the focus was to be on unitized cargo (ie, containers and ro-ro trailers).

The report is based on the AEGIS use cases and outlines one logistics redesign for short sea shipping where the cargo is containers, and one for inland waterways shipping where the cargo is roro trailers. Intercontinental transport was not studied in detail within the AEGIS project, as it was not in scope. This means that no study investigating the applicability of AEGIS solutions for intercontinental transport has been done, and thus the background for creating a roadmap for intercontinental transport is missing. Instead, intercontinental transport is briefly discussed in a separate section of the report. Furthermore, even though the AEGIS solutions do not target the deep sea leg of intercontinental transport, they are highly applicable to the distribution and consolidation of cargo in the hinterland. For this part of intercontinental transport, the short sea and inland transport roadmaps are directly applicable.

For each of the two segments short sea and inland waterways, the bassline "as-is" scenarios are discussed to provide insight into current challenges and areas with potential for improvements. Then a redesign is introduced, where the AEGIS innovations and concepts are used to gain efficiency benefits and zero emission transport systems. As part of the redesign discussion, the gaps towards realization are also discussed and identified. These are related to immature technology, certain issues that are currently not addressed and need both research and development, and issues related to uptake and investment risk. Next, one roadmap for short sea shipping and one for inland waterways is presented, and discussed in terms of short term, medium term and long term phases and what advancements need to be made (ie, what gaps need to be closed) within each of these periods. Finally, policy support and actions are discussed in terms of what will be required to realize the roadmaps.

The two roadmaps presented in this report include discussions for the short-, medium- and long-term periods. The roadmaps are structured this way to facilitate a discussion around which aspects are mature, and which require more research and has a longer expected horizon to market. The roadmaps are written with the purpose of allowing the implementation of the new transport systems in the short, medium and long term, and a discussion is made around the sustainability of the transport system at each maturity level.

In near coast navigation, buoys and beacons convey essential information about dangers. At night-time, selected buoys send out individual blink-sequences that are marked in sea charts. International regulations require that navigation officer on watch makes visual confirmation of objects and their type in order to navigate safely. With rapid developments of highly automated vessels, this duty needs be carried out by algorithms that detect and locate objects without human intervention. At night-time, this requires algorithms that decode blink sequences and are able to classify from this information. The paper investigates this problem and suggests an algorithm that solves the problem. Convolutional Neural Networks (CNN) with Gated Recurrent Units (GRU) are developed for classification. A dedicated architecture is suggested that includes both temporal and color decoding to obtain unique precision. We demonstrate how networks are trained on synthetically generated data, and the paper shows, on real-world data, how the suggested approach yields 100.0% accurate results on 44 real-world recordings while being robust to inaccuracy in actual blink sequences. Comparison with baseline signal processing and with a recent state-of-the-art 3D CNN model shows that the new blink-sequence classifier outperforms alternative algorithms. A showcase of the results of this work is available in this video: https://youtu.be/KEi8qNnKV2w.