- Machine Learning Used to Reduce Human Error at Sea.
- SMART-SEA Offers Real-Time Manoeuvring Guidance.
- System Keeps Seafarers in Control of Navigation.
Collisions between marine vessels and stationary offshore structures, like oil platforms and abandoned wellheads, are on the rise, leading to expensive consequences that can range from cargo losses to serious risks to human life, reports TAMU.
New Decision-Support System Aims to Reduce Human Error
A team of researchers in ocean engineering at a prominent US university is working on a data-driven system aimed at minimising these collisions. This innovative system, called SMART-SEA, merges raw marine radar imagery with cutting-edge machine-learning techniques to offer seafarers real-time guidance for manoeuvring.
“Many of these collisions are caused by human error,” said Dr. Mirjam Fürth, an assistant professor of ocean engineering. “By using data to provide seafarers with real-time instructions, we hope to reduce marine collisions.”
Built With Insights From Seafarers and Authorities
To make sure the system is practical, the research team engaged with seasoned seafarers through focus groups, including former mariners who are now involved in maritime education. They also collaborated with industry experts, as well as US naval and coast guard authorities. This valuable input helped shape real-world decision-making processes, like when to change course or yield, into actionable advice that’s integrated into the SMART-SEA system.
How SMART-SEA Operates
The system analyses raw radar images using machine-learning tools that can identify and classify stationary structures near a vessel. SMART-SEA then considers the vessel’s manoeuvrability and the operator’s experience level to suggest the safest possible actions. Importantly, SMART-SEA doesn’t take control of the vessel; instead, it provides guidance through a user-friendly dashboard, allowing the seafarer to stay fully in charge of navigation and decision-making.
Testing and Initial Findings
The research team has been testing SMART-SEA on a university-operated research vessel, and early results indicate its potential to significantly lower the risk of collisions.
“I do think SMART-SEA could reduce marine collisions and possibly pave the way for more autonomous vessels,” said Fürth.
Funding and Future Development
Initial funding for the project was provided through a one-year contract supported by US government’s energy and interior agencies. Researchers are now seeking additional funding to expand testing to other vessels and further refine the system.
Due to its relatively low cost, the team believes SMART-SEA could eventually be adapted for recreational vessels, helping to reduce boating accidents as well. “I hope we get to continue this research in the future. I think we just scratched the surface,” said Fürth.
Did you subscribe to our daily Newsletter?
It’s Free Click here to Subscribe!
Source: TAMU
