
How Do Machines Map the World? A Conversation With Geospatial Legend Brian McClendon
An autonomous vehicle can have the greatest lidar and cameras in the world, but how does it “understand” what it’s looking at? Robotaxis and delivery bots alike need a source of ground truth that lets them comprehend the state of the world. Properly equipped, an AV can ideally enter a new space for the first time, and instead of having to figure it out the way a human would, it can pull up a rich history of how that location has looked over the years.
Building that knowledge is complicated, requiring constant scanning of real world locations. But what if folks had been serendipitously scanning their streets and cities all along? That’s the premise behind Niantic Spatial, borne out of the company that popularized the hit mobile Pokémon Go, which sent millions of people into their neighborhoods, smartphones in hand.
For the latest episode of The Courier, I caught up with Brian McClendon, Niantic Spatial’s CTO. Beyond visual positioning systems for bots and cars, Brian has an incredibly rich history across the geospatial industry, having previously spearheaded iconic efforts like Google Maps, Google Earth, Keyhole and SGI. Listen in for a fascinating conversation about the future of mapping and location intelligence!
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.thecurbivore.com
Flere episoder fra "The Courier"



Gå ikke glip af nogen episoder af “The Courier” - abonnér på podcasten med gratisapp GetPodcast.








