Even when they are on roads equipped with advanced traffic-data-collection and advisory systems, drivers know that a fender bender can turn the morning rush hour into an endless wait. Transportation researchers at the National University of Singapore say that although they can’t prevent crashes or rubbernecking, they’ll soon have a better way to disperse traffic and avoid jams: computers will identify the best response and change electronic highway signs to suggest alternate routes, for instance. The Singapore project is just one of several traffic-prediction efforts that, by 2004, could be saving drivers’ time in cities such as Tokyo, Los Angeles, Houston, and Stockholm, where “intelligent highway” infrastructures are already in place.
In these and many other cities, cameras, magnetic loops in roadbeds, and even signal patterns from drivers’ cell phones provide analysts with raw data on traffic speed and density. But today’s systems for utilizing those data have two big shortcomings: When gridlock sets in, the responsibility for interpreting the data and recommending responses falls to human traffic managers, who sometimes err. Furthermore, their recommendations offer no look ahead. “Without good predictions, you cannot come up with good traffic management,” says Henry Lieu, a transportation engineer at the Federal Highway Administration’s research labs in McLean, VA.
The Singapore system aims to provide traffic predictions early enough for drivers to act on them. In the aftermath of an accident, the system analyzes traffic conditions in the surrounding area to determine which response-lane closures, light cycle adjustments, or driver advisories-will restore order fastest. The problem is so complex that most computers can’t keep up, but the Singapore team has developed efficient algorithms and data-mining strategies that generate predictions and select the best response within seconds. “The system will pick the highest-performance strategy, so you can implement that traffic control strategy on the real traffic network,” says Der-Horng Lee, a civil engineer who led the project at the National University of Singapore. His country expects to deploy the system on its 300 kilometers of expressways by August 2005, he says.
A similar traffic-prediction system under development at MIT incorporates feedback-the response of drivers to announcements of anticipated points of congestion. Traffic centers in Los Angeles and McLean plan to implement the program in 2004. Such systems will add intelligence to the roadways-although researchers still haven’t figured out how to add any to drivers.
Geoffrey Hinton tells us why he’s now scared of the tech he helped build
“I have suddenly switched my views on whether these things are going to be more intelligent than us.”
ChatGPT is going to change education, not destroy it
The narrative around cheating students doesn’t tell the whole story. Meet the teachers who think generative AI could actually make learning better.
Meet the people who use Notion to plan their whole lives
The workplace tool’s appeal extends far beyond organizing work projects. Many users find it’s just as useful for managing their free time.
Learning to code isn’t enough
Historically, learn-to-code efforts have provided opportunities for the few, but new efforts are aiming to be inclusive.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.