Researchers at the Massachusetts Institute of Technology (MIT) have devised an algorithm that predicts when an oncoming car is likely to run a red light. The team has been able to determine which cars were potential ‘violators’, based on parameters such as the vehicle’s deceleration and its distance from a light. The algorithm was tested using an extensive set of traffic data collected at a busy intersection in Christianburg, Virginia, that was heavily monitored as part of a safety-prediction project sponsored by the USDOT, which had outfitted the intersection with a number of instruments that tracked vehicle speed and location, as well as when lights turned red. The researchers applied their algorithm to data from more than 15,000 approaching vehicles at the intersection, and found that it was able to correctly identify red-light violators 85% of the time; an improvement of 15 to 20% over existing algorithms.
The team was able to predict, within two seconds, whether a car would run a red light and also managed to find a ‘sweet spot’ period of one to two seconds in advance of a potential collision, when the algorithm had the highest accuracy and when a non-violating driver may still have enough time to react. Jonathan How, the MIT professor in charge of the project says ‘connected vehicles’ using vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2I) communication systems may be able to use such algorithms to help drivers anticipate and avoid potential accidents. According to the National Highway Traffic Safety Administration (NHTSA), more than 700 deaths were due to drivers running red lights in 2008.
December 1, 2011
Jul 22, 2016 10:54
Louisiana activates ramp meters on US 90 B in New Orleans
Jul 22, 2016 10:52
KPMG report shows UK insurers unprepared for driverless vehicles
Jul 22, 2016 10:50
Oxbotica launches ground-breaking autonomous vehicle software
Jul 22, 2016 10:47
TomTom expands City traffic information portal to another 25 cities
Jul 21, 2016 10:49
Purchase of Willow Run a major step toward American Center for Mobility