IEEE Spectrum reports that pilot tests in Pittsburgh of AI controlled street lights has shown "impressive results." Composed of decentralised street lights capable of making their own decisions, the system is capable of working in unison informing each other of changing traffic patterns. Reportedly, the test pilot showed a reduction of travel time by 25%, idling by 40%, and emissions by 21%. The city is looking in expanding the system further.
Conventional traffic lights have preprogrammed timing that’s updated every few years. But as traffic patterns evolve, the systems can fall out of date much more quickly than that. The Surtrac system instead relies on computerized traffic lights coordinating closely with each other. Radar sensors and cameras at each light detect traffic. Sophisticated AI algorithms use that data to build a timing plan “that moves all the vehicles it knows about through the intersection in the most efficient way possible,” Smith says. The computer also sends the data to traffic intersections downstream so they can plan ahead.