Hit enter to search or ESC to close

From Plymouth to Plymouth: Mayflower 400 to Sail Into a New World of Autonomous Technology

When the Mayflower left Plymouth, UK in September 1620, she was equipped with little more than a ship’s compass, the wind in her sails, and the hopes and dreams of the Pilgrims risking it all for a life in the New World.

400 years later, that crossing is being recreated by a new Mayflower. But while the original ship’s Captain Christopher Jones steered a triple-masted, wooden ship with canvas sails and roughly 130 people onboard, Mayflower 400 is an aluminum and composite-hulled trimaran with solar panels and electric power. Crucially, she’s captained not by a human, but by the artificial intelligence of IBM’s AI Captain, tasked with making the first fully autonomous transatlantic crossing, from Plymouth, UK to Plymouth, Massachusetts.

The 1620 voyage took 66 days, with the 30 or so crew members and 102 passengers facing unimaginable living conditions, violent weather, and seas so rough that for days on end, there was no choice but to drift in waters too choppy for sailing.

The Mayflower Autonomous Ship at sea in April 2021. Photo courtesy of Getty Images.
The Mayflower Autonomous Ship at sea in April of 2021. Photo courtesy of Getty Images.

When she makes her crossing in early 2022, the Mayflower Autonomous Ship (MAS) will take on equally brutal weather and choppy waters, but she’ll be equipped with the latest in solar power, electric propulsion, machine learning and AI. And she’ll make the 3,125 mile crossing in two to three weeks instead of 10.

Clearly, Mayflower 400 won’t seek to establish a new colony, but as an autonomous research ship, she’s been designed to establish a new era of ocean research and autonomous vessel technology.

“Go to Plymouth”

With storms if you’re lucky, and hurricanes if you’re not, the Atlantic crossing is brutal—and that’s why the team behind the MAS project knew the Mayflower 400 had to be something special.

She’s the brainchild of Brett Phaneuf, a submarine builder and expert in robotics and underwater systems, and co-director of MAS, who cautiously describes it as a moonshot project, and he’s open about the influence of space exploration. “It’s no accident that she looks like a spaceship, with a payload bay like the space shuttle. Space was the inspiration.

Brett Phaneuf, Co-Director of the Mayflower Autonomous Ship Project. Reprint Courtesy of IBM Corporation ©.
Brett Phaneuf, Co-Director of the Mayflower Autonomous Ship Project. Reprint Courtesy of IBM Corporation ©.

“Our goal is to get to a point where you can say, “Go to Plymouth, Massachusetts,” and the ship just does it, dynamically, moment by moment, planning its own path,” explains Phaneuf.

That’s not unlike designing an autonomous vehicle to navigate to a destination—indeed, there are similarities between autonomous vehicles and autonomous vessels, notably when operating in a harbor. “In a port, there’s traffic and congestion, and for good reason there are rules and regulations.” 

The differences, he explains, lie in vehicle speed, reaction time, and interaction with other vehicles and humans. “In a port, you’re operating amongst other vessels, but the humans in the vicinity are very well-protected, and there are far fewer of them than a car needs to deal with on, say, a downtown city street.”

Just like autonomous vehicles, Mayflower 400 uses a sensor suite, in this case made up of six cameras, precision GPS, radar, and lidar. “We use lidar in harbors for close quarters maneuvering, but not when we’re out at sea for a trans-Atlantic crossing. We also have a very sophisticated computer vision system trained to detect, recognize, classify, and predict the movement of everything around it,” says Phaneuf. “It recognizes a navigation buoy, a ship at anchor, what a sailboat or an aircraft carrier will do, and how they behave differently, and then references all that against shipping rules and regulations.”

The 50-ft long (15 meter) Mayflower 400 is also equipped with an echo sounder for bathymetry (measuring water depth), an acoustic current Doppler profiler to measure tide movement, anemometers for wind, a night vision system, thermal systems, and electronic chart data. “And we get unbelievable weather data from The Weather Company.”

Ship ahoy!

Phaneuf says he’s often asked what would happen if an autonomous ship were to have an incident involving another vessel, and he’s keen to underline the near-impossibility of a surprise encounter with another ship out at sea. “That isn’t a reason for not going to sea,” he states, emphatically. “I’m going to see it visually from a great distance away, on radar literally miles away, and on AIS from hundreds of miles away.” AIS is the automatic information system used by international shipping vessel traffic services to track and monitor vessel movements.

By contrast, says Phaneuf, the risk of hitting a random object at sea is unavoidable. “A log drifting 1,000 miles offshore is the same color and temperature as the ocean, and we won’t see it in the waves. The same goes for a container just below the surface.” According to Bloomberg, the number of shipping containers lost to the oceans is rising sharply, with over 3,000 falling overboard in 2020 alone—and the floating container hazard is the same for a human as for an AI captain. “Ships with human captains at the wheel hit containers,” he notes. “At least if Mayflower hits one, nobody gets hurt.”

Also unavoidable are the risks of piracy and sabotage, adds Phaneuf. “If someone wants to spend their time chasing down my autonomous boat, to disable its cameras and tow it somewhere, it’s extremely redundant. And we’ll know where it is.” While at sea, Mayflower 400 is monitored continuously by remote operators, who are ready to take over if required—whenever connectivity is available.

Testing the waters

With no-one onboard, and no new colony to establish, Mayflower 400 is a pure research ship. En route, she’ll carry out a wide range of tasks, such as collecting data on oxygen, carbon dioxide, phytoplankton, chlorophyll, fluorometry (essentially, the study of light), conductivity, and temperature.

Cross-section view of the Mayflower Autonomous Ship. Reprint Courtesy of IBM Corporation ©.
A cross-section view of the Mayflower Autonomous Ship. Reprint Courtesy of IBM Corporation ©.

Mayflower 400 will also sample water to examine particulate matter, notably plastics. A holographic microscope will count and classify the plankton flowing through an imaging cell in real-time, using a sophisticated AI system. Hypertaste, a digital tongue originally developed by IBM to detect forged brandies and wines, has been repurposed to enable oceanographers to characterize sea water. And hydrophones will monitor and analyze whale song. “At the moment, our focus is on chemistry, biology, and climate. Later we’ll be working on seafloor mapping,” says Phaneuf.

A technological sea change

Despite centuries of seafaring, evolutions in maritime shipping have been incremental. Just as in the automotive industry, full autonomy will be the next big sea change, and Mayflower 400 joins a number of autonomous projects making waves around the world. In response, the International Maritime Organization (IMO), the UN agency in charge of shipping regulations, is racing to “ensure that the regulatory framework for Maritime Autonomous Surface Ships (MASS) keeps pace with technological developments that are rapidly evolving.” 

In Norway, Kongsberg Maritime is working with shipbuilder Vard and fertiliser manufacturer Yara International on a fully autonomous, electric container ship for port-to-port coastal shipping. Fully utilized, Yara Birkeland could replace 40,000 diesel truck journeys annually from the fertiliser company’s delivery schedule.

In the Port of Rotterdam, Netherlands, Finland’s Wärtsilä is the largest partner in an EU-funded zero emission port project called MAGPIE (sMArt Green Ports as Integrated Efficient multimodal hubs). Wärtsilä aims to develop a commercially viable autonomous intra-port inter-terminal container shuttle to solve a container transport capacity bottleneck.

In Japan, the Nippon Foundation, a Tokyo-headquartered public interest foundation focused on marine and shipping activities, has called for crewless shipping in practical use by 2025, and for 50% of the country’s local fleet to be crewless by 2040. To that end, it is backing shipping company NYK’s efforts to sail an autonomous cargo ship 236 miles (380km) from Tokyo Bay to Ise, as part of a wider project called Designing the Future of Full Autonomous Ship (DFFAS).

Navigating the calmer, yet equally congested waters of Amsterdam’s canals is Roboat III, a 13ft autonomous electric boat developed by MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) in partnership with the Amsterdam Institute for Advanced Metropolitan Solutions. Roboat can operate as a taxi or delivery vessel, navigating traffic and bridges with a 360-degree sensor suite of GPS, lidar, and cameras.

Crewless cargo ships on the horizon?

Safety and operating costs are often cited as the benefits of autonomous technology. When you consider that 90% of international trade by weight is moved by sea, any savings on transportation methods can be significant. Add to that the human cost of shipping; at the mercy of extreme weather conditions, life at sea can be brutal for crew members, and long ocean voyages mean extensive periods away from home and dry land.

Nonetheless, Phaneuf remains unconvinced about crewless cargo shipping. “I don’t think fully autonomous container ships at sea are in our future. The human crew on that ship is such a small proportion of the cost of the total vessel and the cargo value, that on cost alone, it doesn’t make sense to remove them.”

All aboard! 

Similarities between Mayflower 400 and Mayflower 1620 are few and far between. Yet, like the original crossing, today’s Mayflower has been delayed by a technical fault—in June 2021, she was forced to turn back after 450 nautical miles, due to what Phaneuf described as “just a minor mechanical issue on a part you’d find on any boat. The AI systems worked perfectly though.” 

In April 2022—or sooner if weather conditions allow—Mayflower 400 will again leave Plymouth for Plymouth. But aside from the crossing itself, and the first-of-its-kind sense of adventure, perhaps the two ships’ only other similarity will be the absence of latrines.

Choose your lane

How Autonomous Vehicles Distinguish Between Bicycles and People Who Ride Them

How Autonomous Vehicles Distinguish Between Bikes and People

When it comes to how autonomous vehicles see the world, humans come first, literally. Autonomous vehicles (AVs), like the kind operated by Pittsburgh-based Argo AI, use Machine Learning to detect and classify the objects in their surroundings, identifying people...
Why The League of American Bicyclists is optimistic about autonomous vehicles

Why a Leading Cycling Advocacy Group Is Optimistic About Autonomous Vehicles

As autonomous vehicle use grows, AV companies and the League of American Bicyclists are collaborating on how to ensure cyclists and motorists can share the roads safely, even if the “motorist” is artificial intelligence software. As part of the...

Self-Driving Is Arriving Right On Time. Just Like Ice Cream Did

Seven years ago, I was a self-driving skeptic. Not of the technology. Of all the “experts” promising autonomous vehicles would be everywhere by 2020. You didn’t need to be Nostradamus to know that was ridiculous. All you needed was...
Illustration of a futuristic parking deck turned into a mixed-use space, with AVs driving by

How Autonomous Vehicles Could Help Transform Parking Lots

Researchers say it’s likely that autonomous vehicles (AVs) can help reduce the need for parking lots, opening more room for grass and trees and other elements of nature. It may not seem like it when you’re circling the block...
An illustration of an Argo autonomous vehicle in teal against a backdrop of buildings, a bicyclist, and research papers

7 Big Breakthroughs From Argo Research at CVPR 2022

The 2022 Conference on Computer Vision and Pattern Recognition (CVPR 2022) is nearly here. Thousands of computer scientists, software engineers, and researchers from around the globe will gather in New Orleans to review and discuss their latest work in...

Researchers Predict the Future With Lidar Data

Researchers at Carnegie Mellon University’s Argo AI Center for Autonomous Vehicle Research, a private-public partnership funded by Argo for advancing the autonomous-vehicle (AV) field, say they have come up with a way to use lidar data to visualize not...

Must Reads