Cookies help us deliver the best experience on our website. By using our website, you agree to our use of cookies Dismiss

‘Deep learning’ research on autonomous navigation gets £1.2m funding

BMT, in partnership with ASV Global, is leading a new £1.2 million research project that will focus on applying deep learning machine vision systems, trained with a combination of simulated and real-world data, to support autonomous navigation systems.

{mprestriction ids="1,2"}Part funded by Innovate UK, the UK’s innovation agency, this project aims to improve the situational awareness of USVs (unmanned surface vehicles) to allow them to operate in congested marine environments.

The Synthetic Imagery training for Machine Vision in Extreme Environments (SIMVEE) project will build upon ASV’s existing, COLREG cognisant, autonomous collision avoidance and path planning technology, connected with BMT’s REMBRANDT simulator system to train and validate its algorithms to detect and classify objects at sea.

Utilising data gathered by REMBRANDT as well as real world onboard camera data will allow the team to train the autonomy system with large quantities of data to accelerate the machine learning process.

“This work will provide a significant step in the capability of ASV Global’s ASView autonomous control and navigation system,” said Richard Daltry, R&D director at ASV Global.

“Today we use a remote human supervisor and AIS to classify objects and ensure safe operations. The addition of machine vision that detects and classifies objects extends our COLREG compliant autonomous navigation, enabling operations in limited bandwidth with reduced supervisor workload.”{/mprestriction}

Related items

Joomla SEF URLs by Artio

Login/Register

Register or Login to view even more of our content. Basic registration is free.

Register now

Digital Ship magazine provides the latest information about maritime satellite communications technology, software systems, navigation technology, computer networks, data management and TMSA. It is published ten times a year.

 

Address:
Digital Ship Ltd
Digital Ship - Digital Energy Journal
39-41 North Road
London
N7 9DP
United Kingdom

Copyright © 2019 Digital Ship Ltd. All rights reserved           Cookie Policy         Privacy Policy

x