An all-electric Renault Zoe is about to embark on a 1200km road trip in south-east Queensland, equipped with artificial intelligence technology to learn how to best handle Aussie roads and driving conditions.
Queensland University of Technology (QUT) researchers are testing the AI technology to determine if autonomous vehicles will be able to read road markings and signs in Australian conditions in the same way a human driver can.
Led by Professor Michael Milford from the Australian Centre for Robotic Vision, the research team has equipped the electric hatchback with cameras and LIDAR sensors that will allow the Zoe to “see” the roads.
The technology on-board the electric Zoe will assess four main areas, including lane markings, traffic lights, and street signs, and how well the vehicle’s exact position can be determined despite usual errors that occur with GPS systems – particularly in tunnels and built-up urban areas.
“During this trip, you could say AI will become our ultimate back-seat driver,” Professor Milford said in a statement.
“The big problem that faces autonomous vehicles right now is that at the moment they don’t drive as well as humans in all possible conditions.
“We’re targeting how the car might use infrastructure, such as lane markings and street signage, to help it to drive well,” he says.
The project is part of the Cooperative and Highly Automated Driving (CHAD) Pilot run in partnership with Queensland Department of Transport and iMOVE Cooperative Research Centre – a study focussed on determining whether AI can help make Queensland roads safer.
Minister for transport Mark Bailey says he is keen to see the results.
“This road trip will help us gain a better understanding of our future infrastructure needs,” Bailey said in a statement.
While the development of autonomous driving and related tech is often associated with taking the pressure off drivers and hence increasing safety on roads, Milford says safety is not the only benefit.
“Robotics and AI are ultimately about enhancing human life in some way,” Professor Milford said.
“The primary goal of our research is to determine how current advances in robotic vision and machine learning – the backbone of AI – enable our research car platform to see and make sense of everyday road signage and markings that we, as humans, take for granted.
“So, safety is an obvious off-shoot, but not the focus of this particular study. What’s important is understanding how AI performs and potential improvements to both the technology and physical infrastructure as the autonomous car revolution unfolds.”
The CHAD pilot will continue over a 12 month period, with the results being used to inform future infrastructure development in Queensland.
“We’ll be out on the roads day and night and in all weather conditions to be sure AI is put to the ‘real world’ test,” Professor Milford said.