Robotics engineers eyeing the unseen Monday, 22 January 2018

Electrical engineers in Queensland are developing new technology to equip autonomous underground mining vehicles to navigate in poor lighting, through dust or with a blurred camera.

The technology is set to improve mine safety and to better track mobile mining assets which operate in a maze of tunnels underground. The difficult terrain means GPS cannot be used and wireless sensor networks are less reliable due to interference from the rock mass and lack of access points.

Led by Professor Michael Milford and his engineering team from the Australian Centre for Robotic Vision at the Queensland University of Technology, the technology uses vehicle-mounted cameras to track the vehicle’s location in tunnels to within a metre.

Its development, which is at stage one of the project, uses mathematics and biologically-inspired algorithms, according to Milford. Current tracking relies on expensive laser sensors and extra infrastructure to track the location of mobile assets in underground mines.

“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,” Milford explained.

But, he said conditions at mine sites are challenging and the team’s initial experiments didn’t work so well when tested onsite.

“We had to add some additional intelligence to the technology, to deal with the challenging environment,” Milford explained.

“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.”

The QUT engineering team has completed three field trips to Australian mine sites, with the latest enabling the researchers to start testing the second stage of the project – a more precise positioning technology, Milford revealed.

“If you can track the vehicle’s position to within a few centimetres, then you can use that technology to run the vehicle autonomously.”


Image: Mine researchers with Professor Michael Milford in centre. Source: QUT