The amount of battery electrical vehicles (BEVs) carried as cargo on ro-ro ships is increasing. The possibility of thermal runaway in a lithium-ion battery makes BEVs a different fire risk compared to internal combustion engine vehicles (ICEV). One of the challenges that arise is how to detect a thermal runaway early. Current detection systems in ro-ro spaces generally consist of smoke and/or heat detection. To identify potential techniques and challenges for detection of a thermal runaway, as early as possible, tests with batteries and detectors are needed. Tests with one battery cell were performed inside an ISO container (with almost negligible ventilation) as well as in an open room with moderate ventilation (14 air changes per hour). Point-type detectors (two smoke and heat detectors, one CO detector, and one LEL detector), thermal imaging, video analytics, and light detection and ranging (LIDAR) were evaluated in the tests. A total of 14 tests were conducted. The detectors were evaluated in different positions relative to the battery cell and comparative tests with wood-sticks were performed to investigate the detectors’ ability to detect a more conventional source of fire. Based on the results, it can be concluded that early detection of thermal runaway in batteries is possible in principle. However, detection is a matter of circumstances e.g., ventilation, gas/smoke production and the location of the detector(s). The result indicates that detection in a small and confined space is relatively manageable, but detection in a large and open space could be more of a challenge. If the gas/smoke is cooled down it may sink and spread along the floor/deck, instead of rising and spreading along the ceiling. This would be a challenge with current smoke detectors installed in the ceiling. Shielding may be a problem, especially with LIDAR and thermal imaging. Future research should address full-scale tests, and it is recommended to include Optical Gas Imaging (OGI) as a mean of detection.

The Swedish Transport Administration Research and Innovation fund for Maritime research funded the project "Reference data and algorithms to support research and development of smart ships". The project goes by the working name, and is communicated as, Reeds. It responds to a synthesis of a number of different needs identified in previous projects and studies. The background to the project is that in recent years the focus has been on developing algorithms to interpret and act on the physical environment around different types of craft. In order to be able to develop and evaluate these algorithms, it has become clear that open datasets and a fair benchmarking platform are required that allow various developers in industries and researchers to evaluate algorithms. In the road vehicle sector, Kitti, as of 2013, is the largest dataset used as a reference dataset. The dataset in this project contains sensor data from several data collection occasions within a maritime context, from high-precision sensors such as cameras, radar, lidar, and IMU. For marine applications, there has been no similar dataset with anywhere near the same amount of data and time synchronisation between sensors. The reference data and reference algorithms were available periodically during the project through an online service where researchers and developers could upload their algorithms to use the dataset.

In addition to the dataset itself, Reeds adds additional strengths compared to other reference datasets:

-        New approach to comparing algorithms fairly, where new algorithms are always compared on a centralised hardware in a cloud service and re-evaluated when new data is added, i.e. an unbiased algorithm evaluation service.

-        Method that combines NTP and PTP time protocols for synchronisation between the sensors with microsecond accuracy

-        More types and more modern sensors that can be used at a higher level of abstraction and can thus be applied in more areas.

-        Sensor fusion of both onboard and land-side sensors

-        Identify areas of application for navigation and surveillance on land based on the algorithms developed during the project and the use of new sensor types not established in shipping.

-         

The project built up a maritime reference data set that enables the creation of a digital description for the ship's surrounding environment and developed reference algorithms to demonstrate new navigation and monitoring methodology in the area of "enhanced navigation".

"Enhanced navigation" is defined under the project as the use of new technology based on developments in digitisation and autonomous functions, where new navigation methods use sensors both on board and ashore to increase maritime safety and robustness. The project has built a web-based user interface referred to in the report as "Crowsnest" that handles these new sensors and visualises this data in a familiar interface similar to an overlay in ECDIS that is openly available for the public to build on. Which was used for the evaluation and concept development of new user interfaces based on feedback from pilots and VTS operators.

By providing reference datasets and reference algorithms with demonstrations, researchers and companies now have the opportunity to develop algorithms for the intelligent and autonomous ships of the future.

Projektet “Referensdata och algoritmer till stöd för forskning och utveckling av smarta fartyg” har finansierats av Trafikverkets Forsknings - och Innovationsportfölj för sjöfart. Projektet går under arbetsnamnet och kommuniceras som Reeds svarar mot en syntes av ett antal olika behov som identifierats i tidigare projekt och studier. Bakgrunden till projektet är att de senaste åren har fokus lagts på att ta fram algoritmer för att tolka och agera på den fysiska miljön kring olika typer av farkoster. För att kunna utveckla och utvärdera dessa algoritmer har det blivit tydligt att det krävs öppna dataset och en rättvis benchmarkingplattform som tillåter olika utvecklare inom industrier och forskare att utvärdera algoritmer. Inom vägfordonssektorn är Kitti , från 2013, det största datasetet som används som referensdata set. Datasetet i detta projekt innehåller sensordata från flertalet datainsamlingstillfällen i en maritim kontext, från högprecisionssensorer som kameror, radar, lidar, och IMU. För maritima applikationer har det inte funnits något liknande dataset med tillnärmelsevis lika stor datamängd och med tidssynkronisering mellan sensorer. Referensdata och referensalgoritmerna var tillgängliga periodvis under projektet genom en onlinetjänst där forskare och utvecklare kunde ladda upp sina algoritmer för att använda datasetet. 

Utöver själva datasetet tillför Reeds ytterligare styrkor jämfört andra referensdata set:

-        Nytt tillvägagångssätt för att jämföra algoritmer rättvist, där nya algoritmer alltid jämförs på en centraliserad hårdvara i en molntjänst och omvärderas när nya data läggs till, dvs en opartisk tjänst för utvärdering av algoritmer. 

-        Metod som kombinerar NTP och PTP tidsprotokoll för synkronisering mellan sensorerna med mikrosekunds noggrannhet  

-        Fler typer och modernare sensorer som kan användas på en högre abstraktionsnivå, och kan därmed tillämpas inom fler områden. 

-        Sensorfusion av både ombord sensorer och av sensorer på landsidan

-        Identifiera tillämpningsområden för navigation och övervakning i land baserat på algoritmerna som togs fram under projektet och användning av nya sensortyper som ej är etablerade inom sjöfarten

-         

Projektet har etablerat ett maritimt referensdataset som möjliggör att skapa en digital beskrivning av fartygets omgivande miljö samt utvecklade referensalgoritmer för att demonstrera nya navigations- och övervakningsmetoder inom området för “enhanced navigation”.

“Enhanced navigation” definieras inom projektet som användandet av ny teknik för navigation som bygger på utvecklingen inom digitalisering och autonoma funktioner, där nya navigationsmetoder använder sensorer både ombord och iland för att öka sjösäkerheten och robustheten. Projektet har byggt upp ett webbaserat användargränssnitt, “Crowsnest”, som hanterar dessa nya sensorer och visualiserar denna data i ett familjärt gränssnitt, liknande en overlay i ECDIS som finns öppet tillgängligt för allmänheten att bygga vidare på. Detta användes för utvärdering och konceptutveckling av nya användargränssnitt baserat på erfarna lotsar och VTS-operatörers åsikter.Genom att tillhandahålla referensdataset och referensalgoritmer med demonstrationer ges nu forskare och företag möjligheten att utveckla algoritmer för framtidens intelligenta och autonoma fartyg.

The Swedish policy lab for maritime autonomous surface ships, or smart ships, explored three use cases for developing policy in practice. The policies regard smart ships on national waters: one short-term written policy identifying the next shared step for two authorities to position remote navigational assistance as a new service, giving the maritime ecosystem one official position to relate to; one informal policy relying on a mutual trust, where information sharing between an operator of small, unmanned ships and the supervisory authority enables critical competence building; and one evolving policy on the process of certifying autonomous or remote operated functions using non-standardized technology. In conclusion, despite shipping being explicitly regulated internationally we found that there is substantial leeway for national policies regarding smart ships on national waters.

Swedish Shipping Policy Lab

Smart ships, or Maritime Autonomous Surface Ships as they are also known, have a great potential to advance shipping and sustainable development through optimisation of operations and maintenance. In situations that pose a risk to humans or where humans tend to lose their concentration, smart ships can also contribute to increased safety onboard and for the environment. In short, smart ships are suitable for operations that are dirty, dull and dangerous. The Swedish Shipping Policy Lab was an initiative to support on-going projects within smart shipping with policy-developing activities with the ambition to strengthen Swedish competitiveness. The project has actively strived for a systematic approach to how shipowners, technology developers and authorities among others can foster policy development and innovation in relation to smart ships. As an outcome the project has identified three policies related to the investigated cases (see Appendix G for more details): 1. Navigational assistance from land – A shared statement by the Swedish Maritime Administration and the Swedish Transport Agency on the role of navigational assistance from land and the need to further investigate the service before it can be regulated in more detail. 2. The Ljusterö Ferry – Certification of ferries is commonly done in relation to an established and consistent set of technical requirements. For smart ships such as the new road ferries procured for the Ljusterö-connection it is reasonable to complement traditional certification with a safety case to ensure that the ship is seaworthy. 3. Smart maritime drones – Ships less than five meters long that do not carry passengers are excluded from national rules regulating the supervision performed by the Swedish Transport Agency. As long as there is no explicit need to inspect a specific ship, the probability of a supervision is low. If an inspection were to incur, it is necessary to show how the smart ship and its operation complies to applicable regulation in terms of laws and collision avoidance. Despite the maritime sector having a long tradition of international governance there are still no international instruments explicitly for smart ships. A conclusion from the policy lab is that while such work is ongoing, there is room for the flag states and their authorities to develop and operate smart ships in accordance with national policies. Or, to paraphrase, smart ships seem suitable for operations that are dirty, dull, dangerous and domestic.

The Swedish policy lab for maritime autonomous surface ships, or smart ships, explored three use cases for developing policy in practice. The policies regard smart ships on national waters: one short-term written policy identifying the next shared step for two authorities to position remote navigational assistance as a new service, giving the maritime ecosystem one official position to relate to; one informal policy relying on a mutual trust, where information sharing between an operator of small, unmanned ships and the supervisory authority enables critical competence building; and one evolving policy on the process of certifying autonomous or remote operated functions using non-standardized technology. In conclusion, despite shipping being explicitly regulated internationally we found that there is substantial leeway for national policies regarding smart ships on national waters.