In recent years, USVs have become popular in applications such as remote sensing, surveillance, coast patrolling and navigation support for unmanned underwater vehicles (UUVs).
Ideally, USVs need to operate without human intervention, but even with the most advanced navigation, guidance and control systems, the vehicles still require an obstacle detection and avoidance system to be fully autonomous.
‘At the moment, anti-collision systems are lacking in USVs,’ said project leader, Dr Wasif Naeem, ‘It’s standard in aviation, but there is no such thing in marine right now and that’s what we are trying to push forward.’
As part of the two-year project, the team at Queen’s will consider a range of parameters including ship dynamics, environmental conditions and marine collision regulations to develop a vision-based obstacle detection algorithm.
This algorithm will be used alongside a laser range finder and conventional pan-and-tilt mounted camera to detect possible collisions and help determine the best course of action.
‘One problem we’re likely to find is the rate of false alarms,’ said Naeem. ‘Any object that creates a reflection could be classed as an obstacle. There is no easy solution to this but that’s one of the issues we’re hoping to tackle with the EPSRC funding.’
As well as USVs, Naeem hopes to extend the application to manned vehicles. According to Queen’s, more than 60 per cent of casualties at sea are caused by collisions, with human error a major contributing factor.
‘We will look at how this could be applied to bigger vessels, such as oil tankers,’ he said. By the end of the project in September 2012 Naeem hopes to demonstrate a working prototype.
BAE’s Talisman unmanned underwater vehicle aims to automate the work of clearing waters of dangerous mines to protect divers from harm. Click here to read more.
Five ways to prepare for your first day
If I may add my own personal Tip No. 6 it goes something like this: From time to time a more senior member of staff will start explaining something...