AustraliaFinance and insurance2026 – ongoingRoyal Automobile Club of Victoria
RoughSense road-defect detection pilot
RACV's AI-equipped patrol van recorded more than 300 road defects during a 2-month pilot
Problem
Road managers needed earlier information about deteriorating road surfaces to support maintenance planning. RACV members had raised concerns about potholes and road conditions.
Approach
RMIT equipped an RACV roadside-assistance van with RoughSense, combining AI with video, GPS and vehicle-movement data. The van collected observations along its normal Mornington Peninsula routes, while its driver manually flagged defects for validation. RMIT led system development and evaluation with industry partners.
Results
Takeaway
Routine patrol routes provided repeated observations of road deterioration. The reported defect count did not establish detection accuracy or maintenance savings.
Categories
- Industry
- Finance and insurance
- Business function
- Production and quality
- Innovation type
- Product and service innovation
- AI technology
- Computer visionPredictive analytics and ML
- Adoption
- Partner co-development
- Evidence
- Company's own claim
Sources
Source summaries
RACV reported the pilot's defect count and road coverage. It described driver validation and said evaluation would continue until January 2027.
Full details are in the original sources.
