Put a child in MARIN’s Optimist sailboat and he or she will learn how to sail intuitively, without understanding the details of aerodynamics and hydrodynamics. MARIN’s AI Sail team has successfully demonstrated that a computer can learn to do the same with the help of AI.

Most maritime prediction methods are founded on a model-based approach: Physics-based models are combined in a computational model and validated in model tests and reality. With AI Sail, MARIN wants to demonstrate the possibilities of data-driven methods, where the physics are not explicit in the model but implicit in the data.

In simple terms: If children can learn how to sail an Optimist without knowledge of aerodynamics, hydrodynamics and oceanography, an AI-algorithm should be able to learn the same.

AI Sail, an open-innovation project, has developed AI “sailing agents” (“digital kids”) based on reinforcement learning (RL) with digital twins of the Optimist and MARIN’s Offshore Basin in MARIN’s time domain simulation framework, XMF. MARIN’s model test engineers modified the Optimist with a computer-controlled rudder, sheet and weight control, and checked all necessary communications in the basin.

The AI Sail team comprises a broad mix of MARIN specialists: AI/machine learning, digital twinning/time domain simulations, sailing/wind assist and model testing.

Learn more here.