Tech giant IBM expects its autonomous ship artificial intelligence technology to one day be used by commercial and research vessels. The software is able to optimize decision-making by simulating different alternatives and identifying issues that may arise while the vessel is at sea.
View Gallery – 2 images
In early 2022, the unmanned Mayflower Autonomous Ship (MAS) sailed 3,500 miles from Plymouth, UK, to Halifax, Nova Scotia, Canada. The Atlantic crossing took 40 days without a human captain or crew on board.
Because naval companies tend to be slow to respond to new trends, fully autonomous ships may not be available for quite some time — but AI-powered co-pilots could prove useful. Most marine accidents tend to involve human error, so autonomous software may be able to help human captains make critical decisions.
The nonprofit ProMare designed and built the MAS, and IBM supported the project with its artificial intelligence and automation technology. MAS features 6 AI-powered cameras, 15 Edge devices, and has over 30 seconds to feed into an AI Captain to guide decisions.
While the technology looks promising, there are still some glaring issues in Mayflower’s first public beta.
Notably, in the first run in 2021, the AI worked efficiently, but there were mechanical issues such as the exhaust system duct shearing and damaging the generator. As Andy Stanford-Clark, Chief Inventor and CTO of IBM UK, pointed out in a statement to IoT World Today, the problems are only going to grow:
“Second, we had two issues – one was the disconnector failed in the open position, causing the generator to disconnect from the battery pack, so we couldn’t charge the battery. The other, we lost the main navigation computer, which That’s why we ended up going to Halifax. Luckily, we had a spare, but we only had one.”
This type of technology will take more time before any manufacturer or shipping company wants to get on board. However, it is certainly possible that it could be used to help increase the manning of the ship or to help the captain make decisions while in control.
Introduction to MAS and its artificial intelligence and automation capabilities: