SEA.AI on the Route du Rhum – Offering artificial vision abroad
by SEA.AI Nov 3 08:13 UTC
New boat Malizia – Seaexplorer © Antoine Auriol | Malizia Team
“To finish first, you must first finish” is an age-old adage in offshore racing. This has never been more critical than in this new era of flying racing yachts fitted with far more vital foils, but also more vulnerable. It is also true that a high-speed collision with any object on a foiling yacht can not only damage the yacht, but also injure its skipper.
This is why, this year, on the Route du Rhum – Destination Guadeloupe, a solo offshore race from St Malo to Guadeloupe, SEA.AI equips 50% of the boats in the Ultim and IMOCA classes plus Philippe Poupon’s FLO.
Formerly called OSCAR, SEA.AI was designed by Franco-German Raphaël Biancale. Prior to focusing on this project, Biancale’s career focused on R&D in the areas of intelligent automotive systems and automotive software. The inspiration for SEA.AI came when he was on an offshore passage at night and in poor visibility. Relatively new to sailing, he was struck by the glaring lack of driver assistance systems in the marine world of the type he was developing for cars. To help remedy this, he created OSCAR, now SEA.AI, combining optical sensor technology with artificial intelligence to not only detect, but also identify, objects in the water that could pose a threat. collision for a ship.
Now fully launched on the market, SEA.AI fills a gap in a yacht’s collision avoidance arsenal, alongside radar – which works well for larger objects – and AIS – which identifies suitably equipped vessels. SEA.AI’s specialty is to constantly detect, 24/7, night and day, objects in the water that are smaller than those visible on radar, but which could nevertheless be capable of seriously damaging a boat. and injure his crew. These objects can be logs, containers, buoys, large sea life, small vessels such as a local fishing boat, icebergs, etc. On fully crewed vessels, SEA.AI is also very useful for man overboard incidents, especially at night.
hardware and database
SEA.AI comprises a compact and lightweight vision unit mounted at the top of the mast and a processing unit located at the bottom. The first embeds a set of cameras capable of capturing daytime optical images, in high resolution and even in low light, and thermal images 24 hours a day. These images are then transmitted to the processing unit where SEA.AI’s algorithm compares the images with its massive and ever-expanding database to determine whether or not something in the water ahead poses a threat of collision.
Since the system’s inception in 2018, the SEA.AI collision threat database has grown steadily. To help market the product, Biancale created BSB Marine with Gaëtan Gouerou, former general manager of IMOCA and co-creator of the famous Chantier CDK. . Well connected in the world of French professional sailing, Gouerou was able to surround himself with several skippers and key technicians such as the winners of the Vendée Globe Vincent Riou, François Gabart and Armel Le Cléac’h who contributed to the development of the notebook system loads. Meanwhile, competitors in several of France’s biggest offshore events, including the Vendée Globe, have been recording data to help build SEA.AI’s database.
Competitors carrying SEA.AI gear on the Route du Rhum will continue to contribute to this learning process, helping to improve SEA.AI and ultimately make the sea a safer place for all sea users. , whether they use the sea for pleasure, sport or commerce. purposes.
Given how catastrophic a collision between a high-speed sailboat and something in the water can be, the majority of top Route du Rhum teams all carry SEA.AI as an additional device to ensure they reach Guadeloupe with boat and skipper. in one piece and free of any collision damage. The race will also provide other valuable data and insight into how best to use technology.
Vendée Globe skipper Romain Attanasio is a typical SEA.AI user in the IMOCA class. He’s been using the system on his IMOCA Fortinet-Best Western for three years: “It’s always on – like having an extra crew on watch, except for the crew, it’s often difficult to constantly look ahead as there is so much water . But SEA.AI is up there, always on the lookout. Frankly, I couldn’t live without it. The biggest risk in racing at sea is collisions, so the most important thing is to anticipate. I honestly think SEA.AI should be on every boat.”
Attanasio remembers that in the Azimut Challenge, he avoided two trawlers just 50 meters away, thanks to the SEA.AI alarm, not having spotted them on AIS. On the Vendée Globe in the Strait of the Mayor shortly after rounding Cape Horn, the same alarm alerted him to the presence of a small sailboat which he had not spotted. “There are many times that SEA.AI has worked for me. During the day I monitor but at night I respond more on SEA.AI to look like it’s rarely wrong.”
As each day passes and SEA.AI’s image database continues to be updated, the AI’s ability to detect and identify threats is continuously refined and improved. Currently, the SEA.AI Competition 640 equipment used on the racing yachts of the Route du Rhum makes it possible to accurately identify relatively small elements such as a buoy or a person up to 150 m ahead. In the coming years, its cameras will certainly be improved with higher resolution models to extend the range with which SEA.AI can identify objects. The new, larger and heavier model, the SEA.AI Sentry, designed for commercial vessels or motorboats, can already identify similar objects up to 700 m ahead.
AIS targets can already be overlaid on radar screens or fed into routing software, so it seems likely that the ability to overlay threats detected by SEA.AI could be used in the same way, in the future.
But for future single-handed offshore races like the Route du Rhum and the Vendée Globe, there’s also the potentially very useful prospect of SEA.AI sending critical information to a sailboat’s autopilot. Thus, in the event of identification of an object ahead and if the skipper did not react in time, the autopilot could decide to go around it. A step closer to the well-established automatic emergency braking system in the automotive industry and another milestone on the way to autonomous sea navigation.
For more information, visit sea.ai.