Driverless cars can speed up traffic flow by working together, finds research

If you’ve ever found yourself stuck behind a slow-moving vehicle, unable to overtake thanks to a steady stream of cars in the next lane, you’re not alone.

But a team from Cambridge University may have the answer – at least, when it comes to driverless cars. And it involves the vehicles working together to avoid a stream of traffic building up behind a slow-moving or stopped vehicle.

Researchers have shown that a fleet of driverless cars collaborating to keep traffic moving smoothly can improve overall traffic flow by at least 35%.

During the project, researchers 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.

In a scenario that reflected the situation on today’s roads, any cars behind the stopped car had to slow down or stop and await a gap in the traffic. As a result, a queue quickly formed behind the stopped vehicle, slowing down overall traffic flow.

However, when the cars communicated with each other and drove collaboratively, cars in the outer lane would slow down slightly to allow cars in the inner lane to pass by a stopped vehicle in front of them.

Similarly, when an aggressively-driven human-controlled vehicle was added to the track, the other cars were able to give way to avoid the aggressive driver, improving safety, found the researchers.

While many tests involving multiple autonomous vehicles are carried out digitally, the team used scale models of commercially-available vehicles, equipped to communicate with each other via WiFi.

The team believes the research will be useful for studying how autonomous cars can communicate with each other on real roads in the future.


“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 Michael He, an undergraduate student at the university’s St John’s College.

Nicholas Hyldmar, an undergraduate who designed much of the hardware for the experiment, said: “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.”

The two students completed the research project in the lab of Dr Amanda Prorok, from the university’s Department of Computer Science and Technology.

“Our design allows for a wide range of practical, low-cost experiments to be carried out on autonomous cars,” said Prorok.

“For autonomous cars to be safely used on real roads, we need to know how they will interact with each other to improve safety and traffic flow.”

Send me Driverless Weekly