AI car on a road trip of SE Queensland
MTA Institute Board Member and Australian Centre for Robotic Vision Chief Investigator, Professor Michael Milford, will lead the team of researchers in a project that could help shape the future of road infrastructure.
QUT researchers will take an Artificial Intelligence (AI) system on a road trip of south-east Queensland to ensure the autonomous cars of the future will be smart enough to handle Australian road conditions, especially on rural roads which can lack lane markings.
The project, announced this week by Queensland Minister for Transport and Main Roads Mark Bailey, is part of the Cooperative and Highly Automated Driving (CHAD) Pilot run in partnership with Queensland Department of Transport and iMOVE Cooperative Research Centre. It involves a driver taking a zero-emissions Renault Zoe electric car fitted with high-tech artificial intelligence (AI) sensors and computers for a three-month, 1,200km Queensland road trip. The journey will map Queensland roads for the cars of the future.
Professor Milford said, “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.
“So, as we drive, AI will watch and determine if it could perform the same as a human driver in all conditions.”
Professor Milford explained 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.
The research project will study how the automated vehicle’s AI system adapts to Australian road conditions in four main areas – lane markings, traffic lights, street signs and overcoming GPS limitations in built-up areas and tunnels.
15 February 2019