Tesla Smart Summon & Custom Maps Will Use Crowdsourced Fleet Data
Sign up for daily news updates from CleanTechnica on email. Or follow us on Google News!
Originally published on Teslablog.
Tesla CEO Elon Musk has confirmed on Twitter that the Smart Summon feature in the future will use the GPS points from the maps/navigation data generated by Tesla cars that have previously been at that location in order to further refine this feature. He was responding to the following tweet directed at him by @thirdrowtesla podcast.
Theoretically it should be possible to improve smart summon’s routing algorithms if Tesla had their own database of GPS points and driving data for Teslas in parking lots
then they could just query to get a sense of where the lanes are, as long as Teslas have driven through
— Third Row Tesla Podcast (@thirdrowtesla) April 13, 2020
What this means is that the automaker is already gathering enough data to be able to create its own maps or a routing engine that will help in navigating parking or private spaces much easier for Tesla vehicles, resulting in a smoother Smart Summon experience.
Tesla currently uses Google Maps as the base and to pinpoint the points of interests, but the navigation data and routing engine are provided by another software company named MapBox which has been working on these projects for about a decade now.
In 2018 MapBox acquired the routing engine named “Vallhalla,” which is now part of the core API MapBox provides to users and enterprise clients like Tesla, Facebook, and many more. MapBox claims it gathers data from millions of devices that its application is a part of and that it reaches at least 600 million people a month.
“Our maps learn from every application they’re embedded in. We use real-time data from 600 million MAUs to ship hundreds of thousands of map updates per day so developers can build precise maps that perform across platforms.”
Ira Ehrenpreis, who was the actual owner of the first-ever production Tesla Model 3 and later on gifted his spot to Elon Musk actually sits on the board of both Tesla Inc. (TSLA) and MapBox, so the bond between the companies is strong — but with billions of miles of Autopilot data, Tesla will want to separate itself just like it did when it developed its own self-driving software and ended the partnership with Mobileye.
Seeing some people respond “Why do you need maps? I thought you only needed vision!”
Vision & memory.
You can exit the mall parking lot with vision only, reading signs.
But it might take you longer than if you *remember* how to get out.
Autopilot will have shared memories https://t.co/kYyd1tmKDx
— Third Row Tesla Podcast (@thirdrowtesla) April 13, 2020
Although we have seen a Tesla Model 3 performing Smart Summon in light snowfall that limits the vision of the vehicle, if the car had the opportunity to access information from Tesla’s neural net or GPS data, this would have enhanced its ability to navigate to the owner with much more precision.
Smart Summon along with the Parallel and Perpendicular Autopark are part of the Full Self-Driving (FSD) suite. Although Tesla has deployed these features already, the Silicon Valley automaker keeps on polishing the stuff for free for its 1 million+ vehicles around the world for the cost of nothing extra — yes, via the free over-the-air (OTA) updates.
Featured image: Tesla Model 3 vehicles using Smart Summon in Florida, by Zachary Shahan | CleanTechnica
Chip in a few dollars a month to help support independent cleantech coverage that helps to accelerate the cleantech revolution!
Have a tip for CleanTechnica? Want to advertise? Want to suggest a guest for our CleanTech Talk podcast? Contact us here.
Sign up for our daily newsletter for 15 new cleantech stories a day. Or sign up for our weekly one if daily is too frequent.
CleanTechnica uses affiliate links. See our policy here.
CleanTechnica's Comment Policy
