Study: V2V Autonomous Cars Smooth Traffic Flow

A fleet of driverless cars working together can improve overall traffic flow by 35% under certain conditions, according to researchers at the University of Cambridge in the U.K.

The team programed 16 miniature robotic cars to drive on a two-lane track, then observed how traffic flow changed when one of the cars stopped. The results were presented at this week’s International Conference on Robotics and Automation in Montreal.

Under normal conditions, cars behind the stopped vehicle were forced to stop or slow down and wait for a gap in the traffic. This caused a line to form that hindered overall traffic.

When the cars communicated, the stopped car sent a signal to all the other vehicles. Nearby trailing cars in the other lane slowed down slightly so that otherwise blocked cars could quickly pass the stopped car without any vehicles slowing significantly.

Traffic flow was improved by as much as 45% under the cooperative system when one of the vehicles was remotely controlled and driven more aggressively. By communicating with each other, the other vehicles were able to avoid the aggressive driver without having to stop.

During the tests, the vehicles communicated via wi-fi. The vehicles used artificial intelligence and algorithms to determine when they should change lanes, based on surrounding traffic flow and safety. A separate algorithm allowed cars to travel in tighter packs at higher speeds.

The researchers plan to test the system in more complex scenarios such as roads with more lanes, intersections and a wider range of vehicle types. The team also calls for greater standardization among carmakers as vehicle-to-vehicle and vehicle-to-infrastructure systems are launched.

Watch a video demonstration of the Cambridge tests HERE.