Managing a road network at scale means constantly balancing condition, maintenance, and long-term performance across thousands of kilometres of assets. For the Queensland Department of Transport and Main Roads, traditional approaches to pavement management made it difficult to analyse the network at the level of detail needed to support consistent, data-driven planning.

This session explores how TMR evolved its approach to pavement and asset management through the ADVICE initiative. By introducing more granular analysis of road segments, improved modelling of deterioration and treatment options, and faster scenario testing, asset managers can better understand network condition and plan maintenance with greater accuracy.

The presentation will focus on why the approach needed to change, how it has been applied in practice, and what it has enabled for teams managing the network day-to-day. It offers a grounded look at how AI can support more effective asset management by improving visibility, reducing manual effort, and helping teams plan and prioritise work across large, complex asset bases.

Key Takeaways:

• Increasing the granularity of asset data improves visibility of condition and enables more targeted maintenance planning.
• Faster modelling of deterioration and treatment options supports more effective prioritisation and scheduling of work.
• Applying AI in asset management can reduce manual effort, improve consistency, and strengthen day-to-day planning outcomes.