In order to guarantee that the autonomous cars of the future will be smart enough to handle the tough Australian road conditions, researchers from the Queensland University of Technology will take an artificial intelligence (AI) system on a road trip of southeast Queensland.
As reported, the project involves a driver taking an electric Renault fitted with high tech sensors and computers on a 1,200 kilometre road trip that includes a wide range of road and driving conditions.
The project is part of the Cooperative and Highly Automated Driving (CHAD) Pilot run, in partnership with the Queensland Department of Transport, and a consortium on improving Australia’s transport systems.
The AI will serve as the ultimate backseat driver during the trip. It will watch the team as they drive and determine if it could perform the same as a human driver in all conditions.
The big problem being faced by autonomous vehicles right now is that they do not drive as well as humans in all possible conditions.
Minister for Transport and Main Roads Mark Bailey said understanding AI technology was an important step towards getting automated cars on Queensland roads.
This road trip will help gain a better understanding of the future infrastructure needs.
Professor Milford, who is leading the team, shared that current autonomous car systems either refused to go into autonomous mode or hand control back to a human driver, when faced with some of the road conditions dealt by Australian drivers daily.
This research project will look at how the AI system of an autonomous vehicle copes with Australian road conditions in four main areas.
These areas are lane markings, traffic lights, street signs, and how to determine a vehicle’s exact position despite errors that occur with GPS systems in highly built-up urban areas or poor reception areas such as tunnels.
Past studies and initial experiments showed that autonomous cars could have difficulties on rural roads, which often lacked lane markings on the side or even a centre line.
Early testing of the system had already revealed how a paint spill on the road from the back of a truck could confuse a self-driving AI system into wrongly identifying it as a lane marking.
The 1,200 km testing will be spread over three months. The research team will assess the car’s AI data each day to analyse how it responded to the road conditions, lane markings and road signs.
Robotics and AI are ultimately about enhancing human life in some way.
The primary goal of the research is to determine 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 humans take for granted.
Safety is an obvious off-shoot, but not the focus of this particular study.
Importance is given to understanding how AI performs as well as the potential improvements to both the technology and physical infrastructure as the autonomous car revolution unfolds.
To add, this pilot project is part of the Queensland Government’s wider Cooperative and Automated Vehicle Initiative (CAVI).
Expected to run for 12 months, the Pilot will assess the degree to which modern sensors and AI techniques used on autonomous vehicles can interpret and understand signage and road markings to inform future development and investment in infrastructure.
The team will be out on roads, day and night, and in all weather conditions to guarantee that the AI is put to the ‘real world’ test.
