An autonomous ship manoeuvring itself for nearly 804 km distance in the ocean with an Artificial Intelligence (AI) system is a groundbreaking technology in the history of shipping.
It seems the most obvious place for autonomous navigation to happen – the wide-open oceans. Artificial Intelligence (AI)-autonomous powered vessels are making waves. In mid-May, the 750-ton Japanese cargo ship, Suzaka, became the “world’s first” autonomous commercial cargo ship to successfully complete an over 800-kilometre voyage in the congested waters of Tokyo Bay, travelling without human intervention for 99% of the trip. It successfully dodged hundreds of ships, and manoeuvred, congested Japanese ports and coasts, that at times rivalled the worst of Mumbai road traffic.
Powered by Deep Learning
The vessel was powered by Orca AI, whose software helped the ship avoid hundreds of collisions autonomously. Founded in 2018, the Israeli technology company, Orca AI provides intelligent navigation solutions, that helps prevent collisions and save lives. It claims to ensure safety in waterways and deep waters by reducing human-caused errors through intelligent automated vessels.
Orca AI’s algorithms were powered by AI and deep learning and were trained on data collected from Suzaka for over a year prior to the voyage. This helped the software identify targets in the complex Japanese shoreline environment. The real-time data from the autonomous cargo ship’s cameras were monitored at the fleet operations centre in Tokyo hundreds of kilometres away.
A glitch hits another vessel
Meanwhile, another ship the research vessel, Mayflower Autonomous Ship ran into technical challenges in its second attempt to become the largest crewless vessel to navigate across the Atlantic. A mechanical issue doomed the first attempt to cross the Atlantic in June 2021. The Mayflower had completed 11% of its crossing on the first trip when three days out power levels and speed fell.
Measuring 50 feet in length and weighing five tons, the craft was developed at a cost of more than $1 million in a research partnership involving the University of Plymouth, IBM, autonomous vessel specialists MSubs, and charity ProMare. Taking more than four years to develop, the goal of the project was to collect ocean research data during the crossing and demonstrate the emerging capabilities of AI to navigate vessels.
AI ranks & responds to collision potential
Orca AI technology is a combination of high resolution and thermal cameras to detect hidden objects under the sea, continuous data monitoring using an AI model to rank every passing ship according to its collision potential, and responding proactively to avoid hitting each other. Its systems also monitor shallow waters to avoid grounding. The company claims that its technology helps the captain and his navigation crew get an accurate view of the environment in real-time, and make “life-altering decisions.”
The future of fully autonomous ships
Headquartered in Israel, Orca AI looks to bridge sea-bound ships to the shore with 24/7 insights to ensure shipping companies keep their cargo safe and efficient at all times while providing the technology to bring autonomous cargo ships to reality. Orca AI in last September, signed a partnership with Nippon Yusen Kabushiki Kaisha (NYK Line) to test its safety system for autonomous ships. Orca AI’s Automatic Ship Target Recognition System had been installed on an NYK ship as a research trial to support the advancement of autonomous sea travel. Together, these two companies are Designing the Future of Full Autonomous Ships (DFFAS).
Proving sceptics wrong
Even as recently as 2018, the shipping industry was sceptical of autonomous ships. In February that year, the then CEO of Maersk, Soren Skou, told Bloomberg that autonomous containerships without humans on board are unlikely to operate in his lifetime. In an interview about how the company would drive efficiency, the world’s biggest container shipping company leader said there was little to gain by reducing the size of crews on containerships. During the interview, Skou said: “Even if the technology advances, I don’t expect we will be allowed to sail around with 400-meter long container ships, weighing 200,000 tonnes without any human beings on board. “I don’t think it will be a driver of efficiency, not in my time.”
AI operating as a human watchkeeper
Nevertheless, it now seems that the future of cargo vessels will be autonomous. During Suzaka’s over 800 km voyage, the autonomous cargo ship performed 107 collision avoidance manoeuvres without the help of a human. The program director suggests that Suzaka avoided between 400-500 other vessels on the water during its outbound trip alone. According to Orca AI, its safety navigation system was set up on the cargo ship to operate as a “human watchkeeper,” providing real-time detection, tracking, classification, and range estimation on eighteen onboard cameras, combined to provide a 360° view, day and night.
(Abhijit Roy is a technology explainer and business journalist. He has worked with Strait Times of Singapore, Business Today, Economic Times and The Telegraph. Also worked with PwC, IBM, Wipro, Ericsson.)
(Disclaimer: The views expressed in the article above are those of the author’s and do not necessarily represent or reflect the views of Autofintechs.com. Unless otherwise noted, the author is writing in his/her personal capacity. They are not intended and should not be thought to represent official ideas, attitudes, or policies of any agency or institution.)