Intelligent Streets: Roads, Bridges and the AI-Ready Right-of-Way
Turning roadway data into safer, more resilient and better-performing infrastructure.
Event Summary
Roads, bridges, sidewalks, signs, signals, markings, streetlights and right-of-way assets generate enormous amounts of spatial and operational information. Yet many agencies still struggle to maintain a complete, current view of asset condition and performance.
This session explores how imagery, mobile mapping, LiDAR, drones, pavement systems, sensors, connected-vehicle information and field observations can create a continuously updated roadway intelligence environment.
Speakers will examine AI-assisted asset extraction, automated condition assessment, pavement deterioration forecasting, crash-pattern analysis, maintenance prioritization and right-of-way coordination.
Key Takeaways
Attendees will learn:
- 01
How to build a comprehensive roadway and right-of-way asset inventory.
- 02
Where AI-assisted image and LiDAR analysis can reduce manual inspection.
- 03
How to combine condition, safety, traffic and equity data when prioritizing projects.
- 04
How predictive models can support pavement and bridge maintenance planning.
- 05
How to coordinate permits, utilities, closures and construction geographically.
- 06
How roadway data can support autonomous and connected transportation.
- 07
How to communicate infrastructure priorities more clearly to residents and elected officials.
Resource Guide
Roadway & Right-of-Way Intelligence Guide
How to build a continuously updated roadway inventory and use imagery, LiDAR and AI to prioritize pavement, safety and ROW work.
Data you should have on hand
- Centerline and pavement segment network with surface type
- Pavement condition index history and treatment records
- Bridge and structure inspection reports
- Signs, signals, markings, streetlights and sidewalk inventories
- Crash data with location and severity
- Recent imagery, mobile mapping or LiDAR collections
- Permits, closures, utility cuts and construction schedules
Readiness checklist
- Roadway network is linear-referenced and version controlled
- Collection cadence is defined for imagery and condition data
- AI-extracted features are reviewed under a documented QA process
- Safety, condition, traffic and equity factors are combined in one score
- ROW permits are geospatially visible to every department
Questions to ask internally
- How current is our pavement condition data, honestly?
- Where does manual inspection consume the most staff time?
- Can we show residents why one street was chosen over another?
- Who reconciles conflicting projects on the same block?
Next 90 days
- Run one AI-assisted extraction pilot on existing imagery
- Publish a public-facing paving priority map
- Stand up a shared ROW coordination view for utilities and permits
Metrics to track
- Network-level PCI trend
- Inspection hours saved per mile
- % of ROW permits visible on the map
Attend this event