Drivers are always searching for the fastest route–whether they are traveling home on a busy Friday afternoon or rushing to the airport for an early-morning flight. Now Tele Atlas, a Boston-based company that provides digital maps and navigational content, has integrated new trafficking software into its map database so that drivers can find the most optimal route based on speed rather than distance–for any stretch of road at any hour of any day of the week.
“It’s like having an experienced cab driver with you all the time who knows which roads to avoid to find the most time-saving route,” says Jerry Kim, director of global dynamic content at Tele Atlas.
The software was developed by Inrix, a startup based in Kirkland, WA, that provides real-time and predictive traffic information. The software determines the average speed of roadways across the United States based on two years of historical traffic-speed data collected from commercial fleet vehicles; it uses real-time global positioning software and road sensors from the department of transportation. These billions of data points are then run through proprietary software to create a table of historical traffic patterns based on the hour of the day and the day of the week.
The table contains 168 attributes–24 hours for each of the seven days in a week–and each of the attributes has an average speed that is linked to a road segment, which is identified by a traffic messaging code. The traffic messaging code is embedded into Tele Atlas’s maps. When drivers input their starting position and their end position, their navigational device creates a routing algorithm that pulls the traffic messaging codes and then looks up these codes in the data table to identify the average speed of the roadways. This speed is applied to the algorithm, and a color-coded display–in green, yellow, red, or black–of the road segments appears on the device’s screen. For instance, the color green indicates a wide-open road, whereas black indicates stop-and-go traffic. Drivers can also view the highways of an entire city to determine which typically move the fastest. (Click here for an animation of traffic flow).
View an animation of traffic flow in California.
“I can tell you that at 3 P.M. on Friday on a certain stretch of road in Detroit, traffic is typically flowing at 35 miles per hour–and we have done that for almost a million miles of road across the country,” says Bryan Mistele, the founder and CEO of Inrix. By integrating this information into its map database, Tele Atlas enables drivers, who want to do things like estimate their time of arrival, to get a much more accurate answer than what is available now.
Currently, map databases combine the location of roadways with their posted speed limits to estimate the time it will take a driver to get from point A to point B. So, if a driver looks up directions from her house to the airport using an in-car navigation device or portable navigation system, the system would use the posted speed limits. Depending on the time of day and where the driver lives, that information could be grossly inaccurate, explains Mistele. The new software gauges how fast each segment of road is flowing based on the time of day and the day of the week, providing a more precise estimation.
The only comparable product on the market today is developed by LandSonar, a San Francisco-based company. Its software is also based on historical traffic data that is integrated with digital maps. The company recently partnered with TrafficCast to launch an updated version with more data and real-time content, but its product remains limited to only 450,000 miles of roadway for three days of the week.
Tele Atlas’s product also offers real-time updates. But this real-time coverage is limited to about 94 cities right now. It will be most efficient when used with the historical traffic-speed information, says Mistele.
A new version of the Tele Atlas software will be released every quarter, or every time the company offers a new map database. The software will be constantly upgraded, incorporating the changing traffic patterns and giving drivers a more robust, efficient navigation experience.
Meta has built a massive new language AI—and it’s giving it away for free
Facebook’s parent company is inviting researchers to pore over and pick apart the flaws in its version of GPT-3
The gene-edited pig heart given to a dying patient was infected with a pig virus
The first transplant of a genetically-modified pig heart into a human may have ended prematurely because of a well-known—and avoidable—risk.
Saudi Arabia plans to spend $1 billion a year discovering treatments to slow aging
The oil kingdom fears that its population is aging at an accelerated rate and hopes to test drugs to reverse the problem. First up might be the diabetes drug metformin.
Yann LeCun has a bold new vision for the future of AI
One of the godfathers of deep learning pulls together old ideas to sketch out a fresh path for AI, but raises as many questions as he answers.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.