Could the future of driverless cars be shaped by Raspberry Pi? For undergraduate researchers at the University of Cambridge, the answer is a resounding yes!
A fleet of driverless cars working together to keep traffic moving smoothly can improve overall traffic flow by at least 35 percent, researchers have shown. The researchers, from the University of Cambridge, programmed a small fleet of miniature robotic cars to drive on a multi-lane track and observed how the traffic flow changed when one of the cars stopped.
So long, traffic!
By using Raspberry Pis and onboard sensors to program scale-model versions of commercially available cars, undergraduate researchers have built a fleet of driverless cars that ‘talk to each other’. They did this because they are studying how driverless technology can help reduce traffic incidents on our roads.
The researchers investigated how a car stalled on a multi-lane track affects the buildup of traffic, and how communication between driverless cars can prevent these buildups.
When the cars acted independently of each other, a stalled car caused other vehicles in the same lane to slow or stop in order to merge into the adjacent lane. This soon led to queues forming along the track. But when the cars communicated via Raspberry Pis, they could tell each other about obstacles on the track, and this allowed cars to shift lanes with the cooperation of other road users.
The researchers recently presented their paper on the subject at the International Conference on Robotics and Automation (ICRA 2019) in Montréal, Canada. You can find links to their results, plus more information, on the University of Cambridge blog.