How a Single Self-Driving Car Ends a Traffic Jam

Print Email

Most Americans have little to no interest in self-driving (autonomous) cars. Few currently trust the technology, and even fewer probably trust the promises made by proponents of self-driving cars.

Concerning safety, the conventional wisdom is that until most of the vehicles on the road are autonomous vehicles that can reliably and fully communicate with one another, human drivers will continue to be the main cause of collisions.

The conventional wisdom also doesn’t believe that without a preponderance of self-driving vehicles, humans will continue to drive just erratically enough to continue causing those so-called phantom traffic jams where traffic slows to a crawl for no apparent reason.

A research team at the University of Illinois demonstrated that the conventional wisdom might be wrong yet again. The team simulated a phantom traffic jam by having 20 vehicles drive in a big circle. One of the cars touches its brakes just enough to slow the others without colliding with anyone else.

According to a report in the MIT Technology Review, here’s what happens when the team adds just one self-driving car:

[B]y having an autonomous vehicle control its speed intelligently when a phantom jam starts to propagate, it’s possible to reduce the amount of braking performed further back down the line. The numbers are impressive: the presence of just one autonomous car reduces the standard deviation in speed of all the cars in the jam by around 50 percent, and the number of sharp hits to the brakes is cut from around nine per vehicle for every kilometer traveled to at most 2.5—and sometimes practically zero.

The report includes a video of the circular phantom traffic jam.

Not only does the self-driving car save on brake wear and tear, fuel consumption averaged across all the cars in the traffic flow falls by 40%.