Home › Shipping News › New AI System Could Prevent Vessel Collisions By Reducing Dependence On Ship Captain

New AI System Could Prevent Vessel Collisions By Reducing Dependence On Ship Captain

Add Marine Insight on Google

Add Marine Insight on Google
Image for representation purposes only.

Researchers at Texas A&M University have created an intelligent AI system that can help prevent accidents and collisions at sea.

Named ‘Ship Collision Avoidance of Machine learning And Radar Technology for Stationary Entities and Avoidance’, or SMART-SEA, the platform works to decrease the dependence on ship captains.

The project team was led by Dr Mirjam Fürth, an assistant professor of ocean engineering, who was awarded a contract by the US Department of the Interior (DOI) and the US Department of Energy (DOE) through the Ocean Energy Safety Institute (OESI).

It is not completely an autonomous system, rather it provides ‘a human-in-the-loop’, who gives real-time instructions based on maritime traffic, weather and other factors.

This makes navigation safer and easier for the crew, transiting crucial or dangerous waterways by providing additional information and instructions.

Collisions between vessels and accidents like ships hitting stationary structures like rigs or lighthouses are becoming common, and most are caused by human error. This AI system will help eliminate that, stated the project team.

Massive vessels have a lot of forward momentum that their stopping distances are measured in miles rather than metres.

They also turn very slowly, meaning that any collision has to factor in this slow movement while also adjusting for sensor time lags, ocean current impacts and several other factors.

The AI system has been developed keeping all the above-mentioned factors in mind and is extremely accurate.

The research team also said that the system combines raw radar imaging data with machine learning, enabling it to identify moving objects even in bad weather with limited visibility.

The machine learning algorithm detects stationary objects as well from a large distance.

The system uses computational fluid dynamics models and machine learning, which have been previously trained on vessel motions, the team added.

The system does all of this while complying with International Regulations for Preventing Collisions at Sea (COLREGs).

 

Disclaimer :
The information on this website is for general purposes only. While efforts are made to ensure accuracy, we make no warranties of any kind regarding completeness, reliability, or suitability. Any reliance you place on such information is at your own risk. We are not liable for any loss or damage arising from the use of this website.

Disclaimer :
The information on this website is for general purposes only. While efforts are made to ensure accuracy, we make no warranties of any kind regarding completeness, reliability, or suitability. Any reliance you place on such information is at your own risk. We are not liable for any loss or damage arising from the use of this website.

Subscribe To Our Daily Newsletter

    By subscribing, you agree to our Privacy Policy  you can unsubscribe anytime.

    BE THE FIRST TO COMMENT

    Leave a Reply

    Your email address will not be published. Required fields are marked *