The large-scale operational study, jointly conducted by Orca AI and leading P&I club NorthStandard, marks the first time that an AI navigation provider and a marine insurer have combined large-scale operational data to quantify the real-world impact of AI on navigation safety.
The study, based on data from a cohort of 139 vessels operating around the world, found that the implementation of Orca AI’s platform resulted in a 52% reduction in high-severity close encounters over a 12-month period, with the first 22% reduction achieved within the first six months.
The study investigated more than 10.8 million nautical miles of voyage and compared the system’s initial adaptation period (first three months after installation) with the stable use phase (10-12 months). The primary safety indicator was the incidence of close encounters of severity, defined using objective parameters such as point of closest approach (CPA), time to point of closest approach (TCPA), COLREG interaction, and traffic density.
The improvements were consistent across the ship’s life, highlighting that AI-enhanced situational awareness can enhance safety performance regardless of traditional bridge systems.
The report found increased compliance with SMS protocols on the high seas, reflecting a visible decline in high-severity close encounters in busy shipping lanes, including the North Sea and Baltic Sea (36%), and the China Sea and Sea of Japan (18%).
In these crowded areas, the analysis also identified a clear shift towards more proactive behavior, reflected in increased usage of the Orca AI platform. In environments with the highest navigational complexity, where bridge teams manage dense traffic, multiple points of contact, and limited decision-making time, crews have become even more dependent on the system.
In such situations, AI decision support plays a key role in enabling safe and timely decision-making. The findings demonstrate that crews are proactively leveraging AI-assisted situational awareness to manage multiple contacts, prioritize risk, and maintain awareness in rapidly evolving situations.
This combination of improved outcomes and increased usage shows that AI is not only effective, but operationally embedded. Taken together, these findings demonstrate that AI is becoming an integral part of bridge operations, supporting more consistent and proactive decision-making in environments where risk is highest and margin for error is lowest.
