Networked RoadSafe Technology
Reliably Predict Potential Accidents
Ford has developed a new concept to help identify places on the road where there is a high risk of accidents and report them to local authorities. This enables them to take appropriate measures for greater road safety if necessary.
Called »RoadSafe«, Ford's technology uses an intelligent algorithm to collect anonymized data from sources such as connected vehicles, road sensors and traffic news. The idea is to identify where traffic accidents are most likely to occur. This information can then be displayed on a map that identifies risks and could also be used in the future to warn drivers of dangerous hotspots.
Making roads safer for all
The networked RoadSafe tool is the result of four years of research. This included a 20-month government-funded project carried out by Ford with Oxfordshire County Council, Loughborough University and AI sensor specialist Vivacity Labs. Transport for London and Innovate UK were also involved.
The starting point was an analysis of Greater London to highlight traffic hotspots and identify potential hazards. Over the last 15 months, the project has been extended to Oxfordshire, with a total of more than 200 cars and commercial vehicles taking part.
The data collected allowed the team to develop a special map that identifies road sections of particular concern. This map is composed of different layers of data, including known past accidents and a risk prediction algorithm for each road segment. Colors are used to rate the likelihood of accidents, with red representing the highest risk and yellow the lowest. A more in-depth video on Road Safe can be seen here.
Using sensors to detect near-accidents
To collect the data, the vehicles participating in the trials record different driving events such as braking, steering and accelerating. Roadside sensors from Vivacity, meanwhile, track the movements of various road users. The sensors use machine learning algorithms to detect near misses and analyze movement patterns of vulnerable road users such as cyclists and pedestrians. Data used in this process is anonymized, increasing road safety without compromising privacy.
The combination of vehicle and sensor data can help identify a variety of hazards. These include places where vehicles pass too close to cyclists or an inconveniently located bus stop that causes congestion, as well as poorly designed traffic circles and intersections that cause confusion and near-misses.
In the future, such technology could also benefit passengers traveling in autonomous vehicles. Combining the vehicle's onboard sensors with a digital hazard map could help them anticipate critical situations even earlier and adjust route management accordingly.
