AI-powered RoughSense system detects 300 road defects in Victoria trial

An artificial intelligence system named ‘RoughSense’ has identified more than 300 road defects during a two-month trial on Victoria’s Mornington Peninsula. Developed by RMIT University in partnership with RACV, the technology was installed in an RACV Emergency Roadside Assistance van to monitor road conditions during regular service routes.

The system utilizes a combination of sensors, GPS tracking, video capture, and vehicle movement data to detect potholes, cracking, and rutting in near real time. Between 21 August and 21 October, the trial covered 1,000 kilometres of road, with the highest concentration of defects recorded along the Frankston–Flinders Road corridor through Tyabb, Hastings, Bittern, and Balnarring.

Researchers noted that the technology can identify subtle changes in road surfaces through repeated passes, allowing for preventative maintenance. This approach aims to help road managers address deteriorating surfaces before they become serious hazards, potentially improving safety and reducing long-term repair costs.