A look at how Google builds accurate maps with ‘Ground Truth’ data
Google’s map offerings build in the human intelligence on the front end, and that’s what allows its computers to tell you the best route from San Francisco to Boston.
In an exclusive story by the Senior Editor at The Atlantic, Alexis C. Madrigal, Google for the first time gives us a look at “Ground Truth”. It is a project described by Madrigal as a secretive, complex internal map that contains data, such as “no-left-turns and freeway on-ramps, speed limits and traffic conditions,” necessary to help users navigate through Google Maps:
I was slated to meet with Gupta and the engineering ringleader on his team, former NASA engineer Michael Weiss-Malik, who’d spent his 20 percent time working on Google Mars, and Nick Volmar, an “operator” who actually massages map data.
“So you want to make a map,” Weiss-Malik tells me as we sit down in front of a massive monitor. “There are a couple of steps. You acquire data through partners. You do a bunch of engineering on that data to get it into the right format and conflate it with other sources of data, and then you do a bunch of operations, which is what this tool is about, to hand massage the data. And out the other end pops something that is higher quality than the sum of its parts.”
Describing Ground Truth to be an elaborate internal Map Maker of sorts, perhaps the most interesting aspect of the story is just how much human input goes into making the Google Maps experience accurate. In the story, Madrigal noted the Ground Truth Geo team aims to address most of the fixable problems reported by users (thousands daily) within minutes:
Expand
Expanding
Close
