Imagine if every car on the road acted like a tiny inspector, spotting potholes and cracks automatically. This system uses smartphone-like sensors and AI to map road damage in real-time. It turns ordinary driving data into a digital map that tells city managers exactly where the road needs fixing.
Traditional road inspection is expensive, infrequent, and relies on manual surveys. This leads to delayed repairs, increased vehicle damage, and safety risks for the public.
An EGNSS-compliant sensor device and local hub prototype, paired with an AI-driven software platform for detecting and mapping road anomalies.
If you are a city council dealing with expensive manual road inspections — this project developed a low-cost sensor and AI software that automates the detection and georeferencing of pavement anomalies. This allows for continuous monitoring of transport infrastructure to ensure public safety.
If you are a fleet operator dealing with vehicle wear and tear from poor road conditions — this project developed EGNSS-compliant sensor devices that can be used for participatory sensing. This enables the collection of crowd-sourced data to identify hazardous road sections.
If you are a software vendor dealing with static or outdated infrastructure maps — this project developed an open-architecture software solution using machine learning and machine vision. This can be integrated into GIS-based pavement management systems for real-time updates.
Based on available project data, the project specifically focuses on developing 'low-cost' sensor technologies and software to make road assessment more affordable than traditional methods.
Yes, the software architecture is being developed with scalability and modularity as key aspects, and the use of participatory sensing (crowd-sourcing) allows for wide-scale data collection.
Based on available project data, the software is described as an 'open-architecture' solution, though specific licensing terms are not detailed in the provided text.
The system is designed to integrate with GIS-based pavement management systems (PMS) through the development of APIs and a digital platform.
The project runs from 2024-01-01 to 2026-12-31, aiming for a market-ready TRL 8-9 status by the end of the period.
The consortium is heavily weighted toward commercial application, with a 62% industry ratio comprising 8 industrial partners (including 5 SMEs). This strong industrial presence, combined with 2 universities and 3 other entities across 7 countries, suggests a high priority on market viability and practical deployment rather than purely academic research.
University of Cyprus
Contact us to connect with the PAVE-SCAN consortium for early adoption of their road-sensing prototypes.
