The Royal Navy’s Route Survey and Tasking Analysis (RSTA) project aims to deliver an automated capability for detecting and rendering harmless underwater mines in UK waters by 2022. Currently, a fleet of mine-hunter ships use sonar to detect anomalies on the seabed, but the AI-enabled submersibles to be developed by BAE Systems Applied Intelligence and British geospatial data company Envitia are expected to work in a fleet to scan objects, identify threats and make decisions about what action to take much faster.
Based in West Sussex, Envitia is prime contractor on the project. The company, active in the UK and the US, was established in 1989. It works primarily in the defence sector, and specialises in using open-source solutions to apply AI and machine learning to complex geospatial data problems.
“AI is set to play a key role in the future of the service,” commented Admiral Sir Philip Jones, First Sea Lord. “As modern warfare becomes ever faster, and ever more data driven, our greatest assets will be the ability to cut through the deluge of information to think and act decisively.”
The project builds on Envitia’s previous work on the programme to develop the NELSON common data platform, which are designed to deliver access to Royal Navy data at sea and onshore. The company will also deliver geospatial services into NELSON, to ensure that RSTA has accurate and up-to-date maritime data for each mission.
“Envitia has a strong heritage with maritime data,” commented CEO Nabil Lodey . “This project demonstrates the successful journey Envitia has been on since last year, working with our customers to utilise authoritative data to aid mission planning through to post-mission analysis. This application has the potential to transform mine surveying and increase the efficiency of the Navy mine-hunting capability, and we are proud to be leading the way.”
RSTA is part of a wider mine countermeasures and hydrographic capability programme. The goal of the project is to task a fleet of autonomous vehicles to analyse mission conditions using machine learning to improve its success rate.
Nanogenerator consumes CO2 to generate electricity
Whoopee, they've solved how to keep a light on but not a lot else.