Study: Autonomous Vehicles Can Boost Traffic Flow by 35 Percent

author: Michael Cheng   

A new study published by the University of Cambridge suggests that self-driving vehicles can improve traffic flow by a whopping 35 percent. The solutions implemented by the researchers leveraged communication between autonomous cars on a miniature test track.

Presented at the International Conference on Robotics and Automation (ICRA) in Canada, the study provides insights on how driverless vehicles can work together to mitigate various road conditions – including the presence of an aggressive human-controlled driver. The units on the track communicated with each other via a connected network. Such findings contribute to the development of autonomous cars and establishes their use cases in real-world scenarios.

Cooperative Driving

In order to monitor the driverless cars, researchers from the University of Cambridge equipped the compact units with motion-capture sensors and a Raspberry Pi. The vehicles were programmed with adaptive algorithms to promote cooperation on the test track. Another set of algorithms were used to detect driving activities at the front of cars. Such measures helped reduce bottlenecks on the track.

With such solutions in place, the autonomous cars would change lanes based on available space and the motion of surrounding vehicles. During the trials, when a vehicle stopped at an inner lane, it would notify other cars in the outer lanes. The signal advised the surrounding driverless cars to slow down, making way for vehicles in the inner lane wanting to pass the stopped vehicle.

This movement is more seamless than stop-and-go driving actions frequently implemented by human drivers on public roads. Furthermore, congestion was regularly avoided as the vehicles in the outer lanes prioritized the passing of autonomous cars slowing down in the inner lane.

"Our design allows for a wide range of practical, low-cost experiments to be carried out on autonomous cars," said Dr. Amanda Prorok from Cambridge's Department of Computer Science and Technology.

"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."

Going back to responding to aggressive, human-controlled drivers on the road, the study showed that cooperative driving can improve traffic flow by an additional 10 percent – even when some cars are not working together.

Creating Communication Standards

In cases wherein the vehicles weren't cooperating with each other on the test track, traffic-like conditions persisted. Upon encountering a stopped car, the approaching vehicle slowed down and would only shift lanes after the area was clear. This action is similarly tied to the way vehicles become congested during peak periods.

Researchers have only started to dive into the positive effects that autonomous vehicles have on congested roads. Moving forward, individuals who participated in the study believe creating a standard for effective communication between driverless cars is essential to streamlined cooperation. Such guidelines would ensure data is shared across all types of self-driving vehicles.

"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 Nicholas Hyldmar, co-author and undergraduate student at Downing College.

Michael Cheng

Michael Cheng is a legal editor and technical writer with publications for Blackberry ISHN Magazine Houzz and Payment Week. He specializes in technology business and digesting hard data. Outside of work Michael likes to train for marathons spend time with his daughter and explore new places.