The Mayflower’s AI Captain goes to sea

Share this post:

A prototype of the Mayflower’s AI Captain will soon take to the water on a manned vessel – the Plymouth Quest – a research ship owned and operated by the Plymouth Marine Laboratory in the UK.

It will be managed by the Watson-powered ‘AI Captain’, which will enable the Mayflower Autonomous Ship (MAS) to self-navigate across the Atlantic later this year, is to go to sea this month for testing. The trial will take place on a manned research vessel off the coast of Plymouth in the UK.

It will evaluate how the vessel uses onboard cameras, AI and edge computing systems to safely navigate around ships, buoys and other ocean hazards that it is expected to meet during its record-breaking attempt on September 16th, 2020.  This is 400 years after the original Mayflower set sails for ‘The New World’ from Plymouth, when the finalized, fully autonomous Mayflower 2020 set its ‘solar panels’ to cross the Atlantic.

The trials starting now will help further refine the ship’s machine learning models.

Check out the Mayflower’s AI Captain

 Two years of training and a million nautical images

Over the past 2 years, the Mayflower team have been training the ship’s AI models using over a million nautical images collected from cameras in the Plymouth Sound in the UK as well as open-source databases.

To meet the processing demands of the machine learning process, the team used an IBM Power AC922, the same IBM POWER technology behind the world’s smartest AI supercomputers.

Now, using IBM’s computer vision technology PowerAI Vision, the Mayflower’s AI Captain should be able to independently detect and classify ships  (including class, weight, speed cargo type, etc.), buoys and other hazards such as land, breakwaters, lost containers and debris.

Keeping things local

As the Mayflower will not have access to high-bandwidth connectivity throughout its transatlantic voyage, it will use a fully autonomous edge system running on Red Hat Enterprise Linux and IBM’s edge computing solutions, powered by several onboard NVIDIA Xavier devices.

While at sea, the Mayflower will process data locally, increasing the speed of decision making and reducing the amount of data flow and storage on the ship.

The AI Captain can access data such as the navigation and nautical chart server, which provides the current location, speed, course, and route of the ship, as well as attitude sensors for monitoring the sea condition and a fathometer for water depth.

The onboard vehicle management system provides crucial data, such as the battery charge level and power consumption, that can be used to determine the best route around a hazardous patch of ocean, with weather forecasts informing the final decision.

And finally – not less important:  Crucially, the AI Captain communicates vocally with other nearby to convey any change in plans.

Getting there (safely)

As well as following the overall mission objectives to reach Plymouth, Massachusetts in the shortest amount of time, the AI Captain will draw on IBM’s rule management system (Operational Decision Manager – ODM) to follow the International Regulations for Preventing Collisions at Sea (COLREGs) as well as recommendations from the  International Convention for the Safety of Life at Sea (SOLAS).

As the weather is one of the most significant factors impacting the success of the voyage, the AI Captain will use forecast data from The Weather Company to help make navigation decisions.

Taking into account this and other critical situational data such as depth and vessel status, the Mayflower’s AI captain is designed to operate independently in some of the most challenging circumstances. ODM also provides a completely transparent record of its decision-making process, avoiding ‘black box’ scenarios.

Business impact

Sea transport constitutes around 90% of global trade, as it’s the most cost-effective way of transporting goods in bulk. But it is polluting and still costly. The future is electric – also in the shipping industry and we are entering the decade of autonomous ships.

Major ports around the world are currently investing to prepare for the era of autonomous ships so that their docking and supply chain systems are able to automatically integrate with this new class of AI-powered robotic vessels. There is even an opportunity for autonomous ships to traverse canals and inland waterways helping to remove the transportation load from our overburdened roads.

Scientific impact

The development of zero-emission, crewless and autonomous ships will be a major boost to oceanography. Putting a research ship to sea can cost tens of thousands of dollars or pounds a day and is limited by how much time people can spend onboard –a prohibitive factor for many of today’s marine scientific missions.

With this project, we are pioneering a cost-effective and flexible platform for gathering data that will help safeguard the health of the ocean by advancing understanding in key areas such as ocean pollution, global warming, and over-exploitation – while at the same time gathering important experience in autonomous and sustainable sea transport for business purposes.

Do you want to learn more and to follow the Mayflower’s AI captain on the groundbreaking mission?  Explore the Mayflower landing page and its digital treasures on ibm.com

If you have any further questions, please do not hesitate to contact me at andersq@dk.ibm.com