Driverless cars cooperate to speed up traffic

A fleet of self-driving cars that effectively communicate with one another via Wi-Fi can improve traffic flow by 35%, a study has found.

Researchers from the University of Cambridge programmed 16 miniature robotic cars to drive on a multilane track and observed how the traffic flow changed when one of the cars stopped.

They found that when the cars were not driving cooperatively, a queue quickly formed behind the stopped car as other vehicles waited for a gap in the traffic. However, when the cars were communicating with each other, as soon as one car stopped in the inner lane, it sent a signal to all the other cars. Those in immediate proximity of the stopped car slowed down slightly to allow cars in the inner lane to pass quickly.

The autonomous cars also had the ability to avoid an aggressive human driver, therefore improving safety.

"Autonomous cars could fix a lot of different problems associated with driving in cities, but there needs to be a way for them to work together," said co-author and undergraduate student Michael He, who designed the algorithms.

"If different automotive manufacturers are all developing their own autonomous cars with their own software, those cars all need to communicate with each other effectively," said co-author and undergraduate student Nicholas Hyldmar, who designed much of the hardware.

In the study, the researchers adapted vehicles with motion capture sensors and a Raspberry Pi, so they could communicate via Wi-Fi. They then adapted a lane-changing algorithm for autonomous cars to work with a fleet of cars, which allows them to be packed more closely when changing lanes and adds a safety constraint to prevent crashes when speeds are low. A second algorithm allowed the cars to detect a projected car in front of it and make space.

Cooperative driving improved traffic flow by 35% over egocentric driving, and this increased to 45% for aggressive driving.

According to the researchers, the results can be used to study how autonomous cars can communicate with each other, and with cars controlled by human drivers, on real roads in the future. They plan to use the fleet to test multicar systems in more complex scenarios including roads with more lanes, intersections and a wider range of vehicle types.

The results were presented at the International Conference on Robotics and Automation (ICRA) in Montreal.

This is an edited version of an article published by the University of Cambridge under a Creative Commons Attribution 4.0 International License.

Image credit: ©stock.adobe.com/au/carloscastilla