Electrical engineers in Queensland are currently developing a new technology which will equip autonomous underground mining vehicles to help workers navigate in poor lighting, through dust or with a blurred camera.
The new technology is set to improve mine safety and to improve tracking of mobile mining assets which operate in a maze of tunnels underground. The difficult terrains make it impossible to use GPS. Wireless sensor networks are also less reliable due to interference from the rock mass and lack of access points.
The development of the new technology is being led by Professor Michael Milford and his engineering team from the Australian Centre for Robotic Vision at the Queensland University of Technology (QUT).
The technology utilises vehicle-mounted cameras to track the vehicle’s location in tunnels to within a metre.
Currently, at stage 1 in its development, the project uses mathematics and biologically-inspired algorithms.
“We have developed a positioning system that uses cameras rather than lasers, based on more than a decade of research in biologically-inspired navigation technology,” said Prof. Milford.
Prof. Milford said conditions at mine sites are challenging and their initial experiments didn’t work very well when tested onsite.
“We had to add some additional intelligence to the technology, to deal with the challenging environment,” he said.
“We developed a system which could intelligently evaluate the usefulness of the images coming in from the camera, and disregard ones that were blurry, dusty, or that were washed out from incoming vehicle lights.”