TII’s new transformative approach to National Road Network (NRN) condition data collection
Colleagues in Network Management have implemented a data-driven, AI-enabled asset intelligence approach that transforms how road pavement infrastructure condition is collected, analysed, and managed across both the national road and active travel networks. It has been a game changer for TII asset managers, engineers, and decision-makers responsible for maintaining national roads and active travel infrastructure, as well as the travelling public — including motorists, cyclists, and pedestrians — who rely on safe, high-quality infrastructure.
What problem did they solve?
TII manages a €31 billion national road network (5,300+ km) and a rapidly expanding active travel network (greenways and cycleways). Before this project, the asset condition was primarily assessed through periodic machine surveys (e.g. RSP, LCMS, SCRIM) and manual inspections. These inspections that were typically undertaken on multi-year cycles, resulting in delayed identification of defects and limited ability to monitor deterioration between survey.
The solution combines five key elements:
1. Scalable, Low-Cost Data Collection
They introduced the use of smartphone and camera-based data collection (e.g. GoPro, mobile apps) alongside traditional surveys to capture georeferenced video and imagery across the network at scale. This approach significantly increases coverage while reducing reliance on expensive specialist survey vehicles.
2. AI and Computer Vision Analytics
Using AI-powered platforms, captured data is processed automatically to:
- Detect defects (e.g. cracking, potholes, surface deterioration)
- Classify asset condition
- Generate standardised condition scores (0–100 index)
This replaces manual interpretation with consistent, objective, and repeatable outputs.
3. Integration of Multiple Data Sources
The solution integrates:
- AI video analytics
- Traditional machine survey data
- LiDAR surveys (e.g. Xenobike for active travel assets)
This creates a single, unified dataset across all asset types, improving comparability and decision-making.
4. Cloud-Based Platforms and Decision Tools
All data is processed and visualised through:
- GIS-based platforms (e.g. ArcGIS)
- Web-based dashboards and reporting tools
5. Connected Vehicle Data
Road Roughness Data (IRI) from NIRA Dynamics Volkswagen Database provides near real-time condition monitoring of Road Roughness Data.
3. Integration of Multiple Data Sources
The solution integrates:
- AI video analytics
- Traditional machine survey data
- LiDAR surveys (e.g. Xenobike for active travel assets)
This creates a single, unified dataset across all asset types, improving comparability and decision-making.
4. Cloud-Based Platforms and Decision Tools
All data is processed and visualised through:
- GIS-based platforms (e.g. ArcGIS)
- Web-based dashboards and reporting tools
5. Connected Vehicle Data
Road Roughness Data (IRI) from NIRA Dynamics Volkswagen Database provides near real-time condition monitoring of Road Roughness Data.
What are the benefits?
- Near real-time access to asset condition data
- Easy visualisation of defects and trends
- Exportable data for lifecycle planning and investment decisions
Resulting Transformation
Together, these elements shift TII from periodic, inspection-led asset management to continuous, data-driven and AI-enabled asset intelligence. This provides network-wide visibility, improves efficiency, and supports proactive and predictive maintenance strategies.
This project has been shortlisted as a finalist under the category of Infrastructure, Assets & Built Environment Digitisation in the Ireland eGovernment Awards.