Microsoft and Ford take a swing at solving Seattle traffic
Dec 11, 2019, 10:26 AM | Updated: 10:26 am
As part of a partnership with Ford, Microsoft is looking to tackle Seattle’s growing issues with traffic.
Report ranks Seattle traffic as fifth worst in nation
Researchers began working in 2018 to address congestion on Seattle streets, using what Ford labeled “new quantum approaches on classical computers” in a recent blog on Medium.
The problem researchers looked to tackle: When thousands of people use the same app to determine the fastest possible route to their destinations, it sends all of them to same streets, causing a bottleneck. With the help of Microsoft, the hope was to find a way to use advanced computing to spread drivers across multiple routes at once.
“What if we could develop a more balanced routing system — one that could consider all the various route requests from drivers and optimize route suggestions so that the number of vehicles sharing the same roads is minimized? That sounds great — and could potentially save everyone time, not to mention aggravation,” Ford’s blog reads.
Without getting too far into the weeds about what makes a quantum computer different than a classic computer, the bottom line is that it processes more information at faster speeds.
Using that technology, the ultimate goal is to provide a “smoother flow of traffic, more efficient commuters, and even reduced pollution.”
In one scenario tested by Microsoft and Ford researchers, 5,000 vehicles requested routes through the Greater Seattle Area. The algorithm took just 20 seconds to come up its “balanced routing suggestions,” providing 10 different route choices to each driver.
Washington drivers ranks among top 10 worst by new study
That produces a 73 percent improvement in congestion over what researchers labeled the more standard “selfish” routing most drivers use now. Commute times also dropped 8 percent. Over a full year, that would save 55,000 hours for drivers in traffic across the 5,000 vehicles in the simulation.
Describing those results as “promising,” Ford and Microsoft plan to further improve the algorithm, and expand the experiment to account for other roadblocks to a speedy commute.
“Will this method still deliver similar results when some streets are known to be closed, if route options aren’t equal for all drivers, or if some drivers decide to not follow suggested routes?” Ford posited. “These and more are all variables we’ll need to test for to ensure balanced routing can truly deliver tangible improvements for cities.”