Street sweeping vehicles in regional NSW and the south-west of Sydney are using dashboard-mounted cameras linked to a machine-learning program to assist councils better maintain local roads.
Designed and built in NSW by Deloitte, Asset AI software will highlight and eventually predict critical safety issues like damaged signage, faded line markings, potholes and rutting, and escalate them based on severity and safety risk to council maintenance planners.
As it develops over time, the artificial intelligence software will draw on weather data and learn to predict issues like potholes or cracks before they even form.
The NSW Government is backing the next phase of the Asset AI pilot project as preventative road maintenance can slash costs for councils by reducing the reliance on time-consuming and costly road audits while also extending the lifespan of asphalt and bitumen roads through timely intervention.
Traditionally, councils carry out road audits every 3 to 5 years, but Asset AI has the potential to deliver a snapshot of the condition of the NSW local road network every fortnight in future.
Canterbury-Bankstown and Griffith have been chosen for the trial to ensure the platform meets the needs of both regional NSW and metropolitan areas. An earlier phase of the pilot used Transport for NSW vehicles.
Based on the success of data capture in Griffith and Canterbury-Bankstown, the technology could be rolled out to more councils from 2024.
Asset AI received a $2.9 million funding co-contribution through the NSW Government's Smart Places Acceleration Program, a special reservation under the Digital Restart Fund.
Other councils that have expressed interest in being involved in the development of Asset AI as it progresses include Georges River, Blayney, Central Coast, Liverpool, Wingecarribee, Warren Shire, Liverpool Plains, Tamworth, Wollongong, Murray River, and Shoalhaven.
Minister for Roads John Graham:
"Keeping roads safe and in good condition are some of the biggest challenges for local councils. This platform will help cut costs, accelerate maintenance and prioritise safety.
"The data to fuel the machine-learning will be gathered from Canterbury-Bankstown and Griffith so that we are sure the software meets the needs of regional and metropolitan councils in NSW.
"One of the most exciting aspects is that the system will begin to draw on weather data and learn to predict issues like potholes or cracks before they form and help councils prioritise repairs based on potential future risk.
"This will keep NSW at the forefront of technology-led solutions to what are some of the most essential services for all communities. No one wants to see potholes on the roads and this could be part of seeing fewer of them in future."
Minister for Regional Transport and Roads Jenny Aitchison:
"Regional councils have large sprawling road networks that are built differently to city roads and can be particularly challenging to audit and maintain.
"Last year's extreme rainfall highlighted the battle regional councils face tracking and prioritising work in the wake of natural disasters. With this platform they can get a snapshot within a day of what has been impacted, as well as a recommendation of where to send crews first."
David Elliott, CEO of Institute of Public Works Engineering Australia NSW & ACT:
"We are excited to be at the forefront of this transformative project. The introduction of Asset AI represents a massive leap forward in how we manage and maintain our roads in NSW.
"This initiative will significantly reduce the time and cost associated with traditional road audits, freeing up valuable resources for councils across the state. It's a game-changer for the way road maintenance will be approached."
Bilal El-Hayek, Canterbury-Bankstown Council Mayor:
"City of Canterbury Bankstown is pleased to be the first metropolitan Council involved in the initial trial and council will now install cameras on its street sweepers. This new technology will help inform the program of works to manage the conditions of the road network more effectively."
Find out more about Asset AI
