An autonomous ship used AI to cross the Atlantic without a human crew

An autonomous ship used AI to cross the Atlantic without a human crew

Just under 402 years ago, in August 1620, the Mayflower set sail from Southampton, England, bound for America. The three-masted wooden ship with 100-foot-long canvas sails took more than two months to cross the Atlantic. She carried 102 passengers, had a top speed of three knots per hour (about 6 kilometers or 3.7 miles per hour), and required a crew of 30 to operate.

Earlier this month, another Mayflower crossed the Atlantic, but it couldn’t have been more different from its namesake in almost every way. The only similarity was that, well, it was also a ship.

The differences? The new Mayflower, logically called the Mayflower 400, is a 50 foot long trimaran (it is a boat that has a main hull with a smaller hull attached to each side), it can reach 10 knots or 18.5 kilometers per hour, it’s powered by solar-powered electric motors (with diesel for backup if needed), and it required a crew of… zero.

That’s because the ship was navigated by an AI on board. Like a self-driving car, the ship was outfitted with multiple cameras (6 of them) and sensors (45 of them) to feed the AI ​​information about its surroundings and help it make smart navigation decisions, like rerouting around of the places. in bad weather. There is also a radar and GPS on board, as well as altitude and water depth detectors.

The ship and its journey were a collaboration between IBM and a marine research nonprofit called ProMare. Engineers trained the Mayflower 400’s “AI Captain” on petabytes of data; according to an IBM overview of the ship, its decisions are based on if/then rules and machine learning models for pattern recognition, but also go beyond these standards. the algorithm “learns from the results of his decisions, makes predictions about the future, manages risks, and refines his knowledge through experience.” It is also capable of integratesvery far more inputs in real time than a human he is able to.

The training included teaching the algorithm to identify objects in their path, such as cargo ships, fishing boats, or shipping containers floating on water.

However, despite all their training and preparation, the Mayflower 400 finished slightly short of its target.

It sailed from Plymouth, England, on April 29 and was meant to take three weeks to reach Washington, DC, but a mechanical problem ended up derailing it to the Canadian port of Halifax. Details were not specified, but it may have been something similar to what happened during the ship’s first attempted voyage in 2021, when a metal component in the backup generator fractured and solar power alone was not enough to The ship completed its journey. .

However, Mayflower 400 engineers will no doubt move on and may already be planning another voyage for the high-tech autonomous ship. Despite the gaffe, it’s pretty amazing to see how far technology has come since the original Mayflower crossed the Atlantic. It makes you wonder what a similar trip will look like 400 years from now; From hydrogen-powered aircraft to civilian submarines to faster, sleeker AI-powered solar craft, it seems anything is possible.

Image credit: Oliver Dickinson for IBM/ProMare

Leave a Reply

Your email address will not be published.