Imagine a ship sailing into port, only with no captain on the bridge and no one in sight on board. In the past, such a ship might have been known as a ghost ship, but in the future it might be our new normal.
European researchers are participating in this drive and designing ships with varying degrees of autonomy. Two ships destined for automation are already sailing through Europe today. The first is a carrier delivering fish feed along the west coast of Norway. The second is an inland cargo barge operating in Flanders, the northern region of Belgium. Both will be adapted for autonomous navigation as part of a project called AUTOSHIP.
“The use cases are very different,” says Jason McFarlane, director of research and innovation at the Norwegian company Kongsberg Maritime, a participant in AUTOSHIP. “One is a short sea route off Norway, which presents significant climatic challenges. The inland route, in turn, requires the ship to operate on a confined waterway, often in areas where navigation is more challenging than in the open sea. “
Three parts
The technology that will make these ships autonomous is made up of three main parts. “First you have the vessel control systems,” McFarlane clarifies. “Second, there is digital connectivity from ship to shore. And you finally have the shore-based systems. “
The first part is what makes the ships navigate autonomously. This includes situational awareness subsystems such as sensors, positioning systems or cameras, and other technologies that enable obstacle detection. The data from these sensors is then pooled, something called sensor fusion, and fed back to the ship’s autonomous navigation system, which makes steering decisions based on it.
It is similar to autonomous cars in terms of scanning the surroundings and detecting obstacles using AI-based computer vision systems. But there are also differences. McFarlane, for example , looks at how each ship of a certain size is tracked by a transponder under a system called the Automatic Identification System (AIS), which potentially provides more information to ships’ autonomous navigation systems than is available to cars. . Ships in the open sea are also slower and have more room to maneuver than cars.
Two systems that Kongsberg Maritime has developed are automatic docking and automatic crossing. “Basically the crew pushes a button and the ship will dock,” McFarlane continues. “A range of sensors, which, for example, know the position or orientation of the ship, interact with our system. That allows the ship to dock without a captain on board. “
For now, the crew is still on the ship and can take action if they see a problem. The automatic system is installed on a passenger and car ferry operating in the Oslofjord and has been used on more than 80% of the trips. However, even when a ship using this technology is unmanned, it would still be connected to a control center on land. Here, humans would remotely monitor the ships and their sensors, and could take control manually.
Costs
McFarlane says there are several reasons to automate shipping. One is to increase the attractiveness of water transport, where labor can often account for a significant proportion of operating costs. Another is to reduce road traffic and reduce emissions. McFarlane points out that a barge, like the one they are testing in Flanders, can carry 300 tonnes of cargo, which would replace 7,500 truck trips per year. According to AUTOSHIP calculations, this would reduce CO2 emissions per km by 90%. According to the expert, automated boats could also navigate more efficiently than if they had human operators, optimizing power and engine speed.
However, full autonomy is not always the first step, and intermediate levels of automation can catch up with us before we go completely unmanned. The NOVIMAR project works as a “platoon” for inland and short sea shipping, where a partially automated ship follows a lead ship with a full crew.
“We do not navigate completely autonomously,” explains Danitsja van Heusden-van Winden, project coordinator at NOVIMAR and innovation manager at the Dutch company Netherlands Maritime Technology. “For now there is always at least one person on the boat.”
In his model, a lead ship establishes a “line” or course along a waterway, which is then mimicked by follower ships. Instead of full autonomy, the follower ships copy the route the lead ship took, keeping it on the desired route, while maintaining its distance from the next ship. It is a concept they want to demonstrate at the end of the year in the Netherlands, and which they have already tested using sixteenth-scale model ships in a laboratory depot in the German city of Duisburg.
Labor shortage
This partial automation could be important to reduce costs and fill labor shortages. Rather than having to operate multiple ships with a full crew, a company could operate a lead ship with a full crew and some follower ships with limited personnel.
“Labor shortages are a known problem in shipping,” says van Heusden-van Winden. “It is difficult to find qualified people.”
In 2016 BIMCO, the world’s largest association of shipping companies, published a study that projected that by 2025 there would be a shortage of 150,000 maritime officers worldwide. Automation, whether full autonomy or a partial system like NOVIMAR, could help fill that gap.
It is also why van Heusden-van Winden argues that NOVIMAR would not profoundly affect the prospects of workers in the shipping industry. “Our technology is not a threat to them,” he says. “It will probably require workers to become more skilled, but it will also mean that their skills and labor will be used more efficiently.”
A social impact study is also part of AUTOSHIP. McFarlane notes that there could be job losses for inland waterway workers and even truck drivers. However, their technology does not always replace workers. In the case of the Norwegian fish feed carrier, the operating company mainly wants to use autonomous systems to improve efficiency, for example by allowing crews to rest just before docking and unloading the ship. At the same time, new jobs could be created, such as retrofitting ships for autonomous operations or controlling them remotely.
“Our ships have a limited form of autonomy,” McFarlane said. “There will always be a control center. It will mean a job change. Instead of people living and working on barges, which sometimes young people no longer want to do, we can switch to office jobs. “
Vallas
However, there are hurdles to overcome before autonomous shipping is implemented. “There are risks of having fewer people on board, which could undermine the business case,” van Heusden-van Winden said. A ship train could be caught in a storm , which could be more dangerous when there is only one person on board rather than a full crew, a problem for which NOVIMAR is currently looking for solutions.
Regulation also remains a key issue. Many jurisdictions require that there be a certain number of people on board a ship, defeating the purpose of automation. Both projects are in contact with regulators. “Some regulations, for example, require ships to have a bridge watch,” McFarlane explained. “But does that mean that a natural person needs to be there? Or can we specify that it doesn’t have to be a person on duty?”
For now, both projects are going full steam ahead. NOVIMAR wants to do a real-life test at the end of 2020. AND AUTOSHIP wants to continue with a demonstration of its own in 2022. After these tests, which include a sea crossing from Norway to Denmark for AUTOSHIP, the ships could start to become more autonomous. , although much depends on how quickly regulatory changes are implemented. So in a few years ghost ships could be a common sight in European waters.
Original article
This article was originally published in Horizon, the EU Research and Innovation Magazine
