In the previous attempts to design such an algorithm, the targets where like Cars with IR sensors, cameras and connectivities to avoid collation and accidents, but still we humans have always been a wild card for all these protective technologies.
Now this new algorithm designed is different in this way, it analyzes several parameters like deceleration of the vehicle, distance from the traffic signals and when red signal is turned on. It captures the vehicles's motion in 3-D in less than 5 milliseconds (As in MIT NEWS). Using this data, it is able to determine which cars are driven by potential violators, those likely to run a red signal, and which drivers were obeying all the traffic rules.
“The challenge is, you don’t want to be overly pessimistic,” How says. “If you’re too pessimistic, you start reporting there’s a problem when there really isn’t, and then very rapidly, the human’s going to push a button that turns this thing off.”
John Dolan, a principal systems scientist at Carnegie Mellon University’s Robotics Institute, points out that such algorithms will ultimately need to evaluate a wide variety of intersections. While the MIT team looked at just one intersection, Dolan says its results are encouraging.
“[They] use real driving data … to make more nuanced judgments about whether an approaching vehicle will comply with the intersection rules,” says Dolan, who develops algorithms to aid defensive driving. “These methods are more computationally expensive, but give more accurate results.”
The researchers are now investigating ways to design a closed-loop system — to give drivers a recommendation of what to do in response to a potential accident — and are also planning to adapt the existing algorithm to air traffic control, to predict the behavior of aircraft.
As in MIT NEWS