SIMIC

The trial, 99 per cent of the time under auto pilot, was performed by cargo ship Suzaku, a 749-gross ton vessel chosen for the project by the DFFAS consortium, comprising 30 Japanese companies and led by NYK group company - Japan Marine Science (JMS) and MTI.

The vessel was powered by Orca AI in partnership with the Designing the Future of Full Autonomous Ships (DFFAS) and the Nippon Foundation, said the report.

During the trial, the vessel automatically performed 107 collision avoidance maneuvers on the outbound voyage alone, with the programme director at the consortium suggesting that the system avoided a total of 400 to 500 ships. The voyage, which started from Tokyo Bay - one of the most congested routes in the world - sailed towards the Port of Tsumatsusaka in the Ise Bay.

Orca AI's algorithms were trained on data collected over a year from Suzaku to identify targets in the complex Japanese shorelines environment. The information from the cameras reflected to the fleet operations centre in Tokyo - hundreds of kilometres away.

Yarden Gross, co-founder and CEO of Orca AI, said, "We are honoured to collaborate with the DFFAS consortium led by NYK to drive automation and autonomous capabilities in commercial ships in some of the most congested waters in the world.

"The world's first commercial autonomous voyage is a significant milestone in this journey and we expect to see big shipping companies implementing advanced AI and computer vision technologies to materialise the autonomous shipping vision," said the company.