Skip to Content
Uncategorized

Beat the Jam

Traffic

The trouble with traffic reports is they’re real-time at best: By the time you hear about the mess, you may well be sitting in it. It’s often too late for you to change your route, much less decide to take the train or stay at home.

But transportation researchers at MIT and the University of Texas at Austin think they can predict where congestion will strike 30 minutes in advance. Two traffic forecasting programs (DynaMIT and DYNASMART-X) are being tested in Irvine, Calif., and neighboring Anaheim, where highways and secondary roads are equipped with embedded magnetic sensors that detect passing vehicles and their speed. Historical and real-time data from the sensors fuel the prediction programs.

DynaMIT tries to predict the behavior of each vehicle. If traffic is light, the computer assumes cars will accelerate; if it’s heavy, the computer predicts lane changes and heavy braking. The software simulates thousands of driver choices every few seconds, and predicts when these choices will converge to create a traffic jam, says Moshe Ben-Akiva, head of MIT’s Intelligent Transportation Systems lab, which created DynaMIT. The University of Texas’ DYNASMART-X is similar, but can make traffic predictions in smaller regions within a larger traffic system.

If testing goes well over the next two years, researchers may begin announcing the forecasts to the public. In anticipation of the system’s catch-22-drivers who hear the forecast may render it moot by changing routes–researchers equipped the programs with a loop that predicts this effect and continually adjusts the forecast.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.