Your smartphone could soon double up as a pothole detector
Drivers’ smartphones could help in the fight to improve the UK’s road conditions, according to a new study.
Researchers from the University of Birmingham have said that the GPS and motion-sensing technologies in modern phones could be used to help crowdsource information on road quality, allowing maintenance firms to quickly identify areas in need of repair.
They believe that gathering data from drivers via a simple app could help save time and money in maintaining roads as well as improving conditions for motorists.
Dr. Michael Burrow, senior lecturer at the University of Birmingham who co-authored a report into the idea, commented: “The most accurate automated methods of assessing road roughness use vehicles fitted with lasers, but even assessing the roughness of a reasonably sized network can be costly.
“An attractive solution is to use acceleration sensors built into most smartphones - because smartphone ownership and use are widespread, we can foresee an approach where the condition of road networks is assessed using crowdsourced data from these mobile devices.”
The researchers say that the sensors in phones are powerful enough to register the vertical motion caused by road roughness. Matching this accelerometer data with GPS information logged by the phone, an app could then help build up a picture of the general condition of an entire road network and identify trouble spots.
Assessing road conditions is usually an expensive and time-consuming process. According to the report published in the Journal of Infrastructure Systems, the cost of collecting road roughness data in the United States is between $1.4 and $6.2 per kilometre. The researchers believe that crowdsourcing basic data could help reduce these costs around the world.
They also suggest that by identifying the areas most in need of work, a smartphone app could reduce car damage and repair costs, cut travel time and improve fuel efficiency.
Dr Burrow added: “Routine inspection of the condition of a road network could be achieved using low-cost data collection systems on smartphones with similar characteristics inside a fleet of vehicles of similar types, travelling at normal traffic speeds.
“Vertical acceleration data from smartphones could be analysed using machine learning algorithms to enable IRI (International Roughness Index) to be predicted to a similar accuracy as would be expected from a visual inspection, but with improved repeatability and reproducibility.
“A particularly useful application could be the assessment of the condition of low-volume rural road networks in developing countries where the majority of rural roads are constructed from either gravel or earth and where smartphone ownership is surprisingly high.”