Why Robots Need A Different Map (Google Earth Creator & Niantic Spatial CTO)

<p>Niantic Spatial CTO Brian McClendon on how the best engineers solve problems most give up on — from a 4D model of the world to shipping research in months. He built Google Earth and ran Google Maps for over a decade, and he's been there, done that. What he's building now is harder, and it's already live for customers. Along the way: who makes it on his team and who doesn't, and the one piece of advice he'd give every engineer using AI.</p><p><br /></p><p>In this video, we cover:</p><p>- The 4D model of the world: visual positioning, change detection, and treating a pile of photos like a database</p><p>- Gaussian splats and real-to-sim: capturing a room and loading it into Nvidia Isaac to train robots</p><p>- Turning a research idea into a production service in six months</p><p>- What Google Maps taught him about building for robots instead of humans</p><p>- Designing problems AI can self-check, and why token maxing is a waste</p><p><br /></p><p>For engineers and engineering leaders who want to work on problems that don't have a known answer yet — and who want to know what a CTO who's built the definitive product in his field looks for in the people he hires.</p><p>Recorded at the AI4 conference 2026. </p><p><br /></p><p>Timestamps:</p><p>00:00:00 - Google Earth? Been There, Done That<br />00:00:46 - Turning a Research Idea Into Production in 6 Months<br />00:02:37 - How Any Photo Gets Located Within Half a Meter<br />00:06:37 - The Long-Term Goal: A 4D Model of the World<br />00:08:37 - Treating a Pile of Photos Like a Database<br />00:11:58 - What Google Maps Taught Him About Training Robots<br />00:15:22 - Gaussian Splats Explained in Plain Terms<br />00:17:42 - The Unsolved Problem: Scale and Semantic Change<br />00:20:34 - Why Google Earth Is Good Enough<br />00:22:09 - Who Makes It on His Team and Who Doesn't<br />00:23:38 - Designing Problems AI Can Self-Check<br />00:26:03 - The Insights Hidden in the Physical World<br />00:28:18 - Digital Twins, Cities, and Ready Player One<br />00:31:35 - Visual Positioning When GPS Gets Spoofed<br />00:33:24 - Token Maxing Is Bullshit: Advice for Engineers</p><p><br /></p><p>Guest: Brian McClendon, CTO at Niantic Spatial. The engineer behind Google Earth; ran Google Maps for over a decade.</p><p><a href="https://www.linkedin.com/in/brianmcclendon" target="_blank" rel="ugc noopener noreferrer">https://www.linkedin.com/in/brianmcclendon</a></p><p><br /></p><p>#NianticSpatial #GoogleEarth #SoftwareEngineering</p>