ARTIFICIAL INTELLIGENCE BEING PUT TO THE TEST ON QUEENSLAND ROADS
Professor Michael Milford who is a Director on the MTA Institute Board is leading a team to take an electric car fitted with Artificial Intelligence on a three month road trip.
A team of Queensland University of Technology (QUT) researchers, led by Professor Michael Milford, are taking an electric car fitted with Artificial Intelligence (AI) sensors and computers on a three month, 1200km Queensland road trip.
The aim of the research is to ensure that autonomous cars of the future will be smart enough to handle tough Australian road conditions.
“The QUT trial, in partnership with the Palaszczuk Government, is the first step in charting Queensland’s vast and varied road network for new vehicle technologies,” said Mark Bailey, Transport and Main Roads Minister.
“As researchers drive the car across Queensland, onboard sensors will build a virtual map to help refine AI-equipped vehicles to drive safely on our roads.
“It’s early days yet, but Artificial Intelligence technology and smart road infrastructure have potential to transform the way we travel in Queensland and reduce road trauma.
“This is world-leading transport technology research and it’s happening right here in Queensland.”
The road trip is part of the Queensland Government’s Cooperative and Highly Automated Driving (CHAD) Pilot and is supported by the iMOVE Cooperative Research Centre (iMOVE CRC).
Professor Milford, from QUT’s Australian Centre for Robotic Vision (and Board member of the MTA Institute), said the challenge for the current generation of automated vehicles was driving as well as people.
“Engineers at QUT’s Research Engineering Facility have developed a research car platform equipped with a range of state-of-the-art camera and LIDAR sensors used on automated vehicles.
“As we drive, AI will watch and determine if it could perform the same as a human driver in all conditions.”
Professor Milford added that early testing of the system had already revealed how a paint spill on the road could confuse a self-driving AI system into wrongly identifying it as a lane marking.
“Past studies, along with initial experiments conducted by QUT, show how automated cars have difficulties on rural roads which can lack lane markings,” he said.
“A motorist on a rural road knows to stick on the left or imagine there is a line in the middle of the road.
“People will also cross the imaginary line to go around obstacles, it’s quite difficult for an automated vehicle to do this.
“The primary goal of this work is to consider how current advances in robotic vision and machine learning – the backbone of AI – enable the research car platform to see and make sense of everyday road signage and markings that we, as humans, take for granted.”
The upcoming research project will specifically look at how the automated vehicle’s artificial intelligence system adapts to Australian road conditions in four main areas:
- Lane markings
- Traffic lights
- Street signage, and;
- Overcoming the limitations of GPS systems in built-up areas and tunnels for vehicle positioning.