Plymouth-based Marine AI has begun a research project with the UK Hydrographic Office (UKHO) to teach autonomous vessels to interpret official navigational information traditionally used only by human mariners.
The eight-month programme will refine Marine AI’s GuardianAI system to read and act upon ADMIRALTY Sailing Directions and Radio Navigation Warnings, translating unstructured natural language into machine-readable data for autonomous control.
The project aims to allow Maritime Autonomous Surface Ships (MASS) to make safe, real-time navigational decisions using the same data relied on by professional crews.
Current autonomous systems depend on human operators to interpret text-heavy navigation updates written in non-standard formats. Marine AI says it will retrain its language model to process this data, while supporting AI agents will structure and feed the information into GuardianAI’s tactical engine and human–machine interface.
A live demonstration is planned for spring 2026 in Plymouth using ZeroUSV’s Oceanus12 vessel equipped with GuardianAI. The results are also expected to contribute to the International Hydrographic Organization’s S-100 data framework, which underpins the latest generation of navigation standards.
“Working with Marine AI allows us to push the boundaries of how autonomous systems can use official hydrographic information,” said Mark Casey, Head of Research, Design and Innovation at the UK Hydrographic Office.
“The outcomes will not only support the safety of lives at sea but also feed directly into the development of the IHO’s S-100 framework, ensuring that UKHO data continues to set the global benchmark for safe navigation in both crewed and uncrewed vessels.”
The project forms part of wider UK efforts to develop autonomous shipping, with Plymouth established as a national testbed for MASS operations.
