NYK Testing AI-powered Collision Avoidance System
Japanese shipping company Nippon Yusen Kabushiki Kaisha (NYK) is testing a navigation and collision avoidance system in another step toward autonomous cargo ship operations.
NYK and MTI Co. Ltd. (MTI) have installed Orca AI’s Automatic Ship Target Recognition System onto an NYK Group ship to assess the system's ability to automatically recognize dangerous targets and other vessels that may be overlooked by the human eye, especially at night and in congested waters through vision sensors and thermal cameras, as well as artificial intelligence (AI)-powered algorithms which constantly analyze the environment and alert crew to dangerous situations.
The navigation and collision avoidance system is engineered to help create a new lookout support system for vessels by providing improved visibility in difficult conditions, preventing human error, and helping crews make informed decisions, Orca AI said.
Yarden Gross, CEO, and co-founder of Orca AI, said, “The challenges faced by the maritime industry are numerous and there is a continual need to make shipping safer, to sustain trade and protect the maritime environment. By adopting an Automatic Ship Target Recognition System and embracing technology, we can create a connected maritime industry that is able to protect crew and cargo by identifying risks straight away. We're delighted to be working closely with Nippon Yusen Kabushiki Kaisha in discovering what lies ahead and bringing the industry one step closer to fully autonomous ships.”
According to the company, nearly 4,000 maritime accidents occur annually and are caused by low situational awareness in congested areas, lack of office visibility regarding misses and risk patterns and insufficient data available for handling potential incidents. Currently, in order to avoid dangerous objects and collisions while sailing, navigators use binoculars to visually recognize dangerous objects. Nautical instruments such as radar are also used, and decisions are then made to change course if necessary. Orca’s system will be installed on a trial basis to verify whether the safety of the ship's operation can be improved by automating the task of recognizing dangerous objects.
A camera unit will shoot day and night to automatically recognize ships and targets and measure the distance to them. Information obtained from navigational equipment; including vessel names, distance, and time when the ship is closest to the target, can be superimposed and displayed in an integrated manner to a tablet or touch-panel monitor display.
In addition, the system is epoch-making because it can independently recognize small fishing boats and small markers that are not captured by radar and not equipped with AIS. The system measures the distance to these targets and notifies the person on duty of danger of collision.
Surrounding images taken are analyzed using AI on Orca AI's server, which makes use of machine learning and then remotely updates the onboard software. This mechanism improves performance such as recognition rate through continuing use. In addition to the captured video, navigation instrument information is sent to the server and displayed together with the video data, making it possible to monitor the movement of the ship and check the situation from the land office.
The trial, which began on August 30, will verify detection capability and contribution to lookout work, improve the target detection algorithm through data collection and machine learning and enhance the recognition rate.