UK-based autonomous systems provider ASV Global is leading a new £1.2 million research project in partnership with compatriot BMT to enhance safety and reliability of autonomous navigation, through the use of deep learning machine vision systems trained with simulated and real-world data.
Partly funded by Innovate UK, the UK’s innovation agency, this project aims to enhance situational awareness enabling the USV to operate in extreme and congested marine environments. Improved situational awareness concerns both the autonomy onboard and the remote human supervisor.
The Synthetic Imagery training for Machine Vision in Extreme Environments (SIMVEE) project will build upon ASV’s autonomous collision avoidance and path planning strategy, while it will use BMT’s REMBRANDT simulator to train and validate ASV Global’s vision algorithms to detect and classify objects at sea.
The combination of real world and simulated data to train deep learning algorithms is expected to improve the reliability of the existing system extending safe operations into complex environments “with a wide range of objects to detect, classify and avoid.”
Richard Daltry, R&D Director at ASV Global said:
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.
Phil Thompson, Managing Director at BMT comments:
This research will play a pivotal role in helping to accelerate the wider adoption of unmanned systems and increase trust in their feasibility by mariners around the world.
UK has earlier reveled plans to be at the forefront of maritime technology that will result in safer and more efficient shipping.
