Skip to main content

A small number of self-driving cars on the road could solve some traffic woes

Self-driving cars experiment demonstrates dramatic improvements in traffic flow
If you’re of the opinion that the traffic problems associated with human drivers will only cease when the majority of vehicles on the road are autonomous, think again!

According to a recent study carried out at the University of Illinois at Urbana-Champaign, having just 5 percent of cars on the road be autonomous vehicles could eliminate stop-and-go waves of traffic — and all the accident risk and fuel inefficiency that comes with it.

“We wondered what would happen if we tried to use the emerging connected and automated vehicle technologies at low penetration rates to influence the overall traffic flow,” Daniel Work, the assistant professor who served as lead researcher on the project, told Digital Trends. “We started by picking a very helpful experimental setup, inspired by experiments conducted by the Mathematical Society of Traffic Flow — famous in the transportation engineering community because it showed experimentally that ‘phantom’ traffic jams can be created entirely by human driving behavior. Based on those tests, we began to think about the possibility of an automated vehicle that could cancel the stop-and-go wave.”

Traffic Jam without bottleneck - experimental evidence

In field experiments conducted in Tucson, Arizona, a single autonomous vehicle circled a track continuously along with more than 20 human-driven cars. While humans naturally create the dreaded phenomenon of stop-and-go traffic, researchers discovered that controlling the pace of the autonomous car had a major impact on overall traffic flow. The results of their experiment not only made traffic flow better, but also reduced overall fuel consumption by up to 40 percent.

“It is important to clarify that a single AV on a real roadway would only have local benefits in the lane of travel in the 20-car neighborhood behind the vehicle,” Work said. “To be effective, one needs a small number distributed in the flow in order to prevent the waves from re-appearing after the AV has passed through the roadway section. Lane changes are another area of interest [where] we need further modeling and testing, since they act as a trigger for stop-and-go waves, but also free up gaps in the departure lane that can be used to dampen waves. We will need to address this in our future work before we are ready to claim victory over phantom traffic jams.”

Still, it’s promising to know that all of us are likely to benefit from self-driving cars — and not just the rich few who will initially be able to afford them.

As Work points out, such effects can also come from adaptive cruise control (ACC) and cooperative adaptive cruise control (CACC) systems. “We don’t necessarily need a fully self-driving car to make this work,” he noted.

Editors' Recommendations

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Apple’s rumored car could cost the same as a Tesla Model S
Apple Car rendering from Vanarama.

Rumors have been swirling around for years regarding Apple’s plans for an electric, self-driving car.

The latest report, which arrived on Tuesday via a usually reliable source, suggests Apple has scaled back its plan for an autonomous car, with some elements yet to be agreed upon.

Read more
Ford and VW close down Argo AI autonomous car unit
An Argo AI autonomous car on the road.

Autonomous-car specialist Argo AI is closing down after Ford and Volkswagen, Argo's main backers, ended support for the Pittsburgh-based company.

First reported by TechCrunch and later confirmed by the two auto giants, some of the 2,000 workers at Argo will transfer to Ford and Volkswagen, while others without an offer will receive a severance package. Argo’s technology is also set to end up in the possession of the two companies, though at this stage it’s not clear how it might be shared.

Read more
Tesla hopes full self-driving beta will be out globally by the end of 2022
Beta of Tesla's FSD in a car.

At the Tesla AI Day 2022 event, the electric car maker revealed some key statistics about the Full Self Driving (FSD) tech that is currently still in the beta testing phase. The company divulged that the number of FSD beta testers has gone up from 2,000 last year to roughly 1,60,000 users in 2022, despite a few regulatory hiccups and incidents that raised questions about its safety.

Tesla still hasn’t provided a timeline for when the FSD package will formally exit the beta phase, but it doesn’t seem too far off. In a TED interview this year, Musk claimed that the FSD system, which now costs $15,000, will most likely be out by the end of 2022 for all customers. There are also plans for a global rollout by the end of this year, pending regulatory approval, of course.

Read more