New AI radar system aims to cut human error in maritime collisions

Scientists at Texas A&M University have developed an AI-assisted radar system called SMART-SEA (Ship collision avoidance of Machine learning And Radar Technology for Stationary Entities and Avoidance) to help ship captains reduce deadly maritime collisions caused by human error. Unlike fully autonomous navigation systems, SMART-SEA operates with a “human-in-the-loop” approach, providing real-time instructions that combine human expertise with AI precision. The system was created under a contract from the US Department of the Interior and Department of Energy to address the rising incidence of collisions between vessels and stationary structures such as oil rigs. SMART-SEA integrates raw radar imaging with advanced machine learning to detect moving objects even in adverse weather and to classify stationary hazards. It uses computational fluid dynamics models and algorithms trained on historical vessel motions, incorporating seafarer experience gathered through focus groups. The system employs a Modified Velocity Obstacle algorithm combined with an Asymmetric Grey Cloud model to assess collision risks and suggest avoidance maneuvers, all while complying with International Regulations for