Waymo co-CEO Dmitri Dolgov recently gave a very interesting, 49-minute-long presentation at a Y Combinator event. A few days ago, I covered some of his comments from the beginning of the presentation. Getting further into it, this next topic had to be highlighted. In the video above, 16 minutes in, Dolgov gets into why the company uses cameras, radar, and lidar for its self-driving vehicles. “There’s been a looooongstanding debate about what kind of sensors do you actually need for autonomous driving. Naturally, more sensors means higher performance, but also means higher complexity,” he noted. “So, humans can drive with just eyes, so there’s that proof of existence. And if the goal were just to approximately match human performance, or to build an assist product, that’s a very reasonable way to go. However, if you are targeting full autonomy, and you’re targeting superhuman — strongly superhuman performance — you find that weak sensing just leads to a safety curve that flattens out way too early. So, at Waymo, we’ve taken an approach where we use multiple sensing modalities. We use cameras, lidars, and radars — and they all complement each other. Cameras give you high resolution and color, but they’re passive and the degrade in darkness and glare. Lidar gives you a direct measurement of the 3D structure of the world, uh, around you. And radar is very good at punching through environmental conditions and weather like fog or rain or snow. And it can directly measure velocity using Doppler. “Lidar and radar are active sensors. So that means they see just as well in pitch darkness — for example, when driving into a blinding sunset.” He goes on, offering more details and nuance. Overall, though, the point is clear — Waymo is throwing the gauntlet down right in front of Tesla’s foot and saying that Tesla’s system will never be as good as Waymo’s. I’m sure that claim will piss off many people who are big fans of Tesla, and “Full Self Driving” in particular.
