How automated vehicles will interact with road infrastructure

This project will focus upon addressing the following research questions:

• How will existing infrastructure (signage, line markings) affect the major operational capabilities (lane keeping, localisation, hazard signage, etc.) and the reliability of an automated vehicle (AV)?
• How will existing built and signed infrastructure affect the accurate (automation enabling to a few centimetres precision) positioning capability of an automated vehicle?
• What types of infrastructure improvements could address shortcomings identified in this study?
• How will the answer to the above three questions change depending on the technology solution deployed on the automated vehicle, with a primary focus on the spectrum of possible range-based (laser, radar) solutions versus primarily vision-based (MobilEye® for example) solutions?

Participants

• Queensland Department of Transport and Main Roads
• Queensland University of Technology (QUT)

Project background

On-road testing will be conducted in urban and rural environments in South-east Queensland, using a custom dataset-gathering-vehicle equipped with automated vehicle sensor technologies.

The project has a particular focus on evaluating new state-of-the-art perception and algorithm technologies (including deep learning) likely to play a critical role in any technology solution. It will also leverage the unique experience and skillset within Australia of staff from the Australian Centre for Robotic Vision.

This iMOVE pilot will establish a methodology, support the collection of the data through high-fidelity vision and range-based sensors, and evaluate this data set. The results will be used by transport agencies – local, state and federal – to inform investment in infrastructure that supports emerging AV technologies. In the future, the data set and results could also be used by others to perform, compare or supplement the evaluation.

QUT will gather the dataset(s) over several thousands of kilometres of mixed urban and rural, on low- and high-speed roads. High fidelity vision and range-based sensor data will be logged and stored in QUT’s high capacity storage drives and uploaded to a central storage location upon return-to-base at the end of each day for analysis. The dataset will be made open source, and available to the research community at later stages of this project.

At the end of the project a report will be published, summarising local asset readiness to host future automated vehicles, with implications for future road infrastructure upgrade strategies.

Project objectives

• prepare for and accelerate the emergence of AV technologies onto Australian roads
• respond to the national call for priority trials and research of transformative transport technologies
• grow governments’ technical and organisational readiness for deployment of AV technologies on Australian roads, with focus on understanding road asset (signs and lines) readiness for AVs
• demonstrate and evaluate AV sensing and recognition technologies in an Australian context to support public awareness and uptake

Update: November 2018

As you can see in the images below, ‘Zoe 1’, the car being used in this project, has had some technology fitted. Click on the thumbnails below to view larger versions of the images.

Update: February 2020

This project has been completed. Click the buttons below to download either the final report, or an information flyer, or for an overview of the project completion, read Autonomous vehicles and Australian roads: Are they ready for each other?