How Waymo's Driverless Strategy Compares to Tesla's

追加: 2026-05-10

[00:00:00]There is the obvious, which is the driver, the software that runs the car.

[00:00:03]But there are two other very important pieces of the tech stack.

[00:00:07]One, of course, is the simulator, which is this virtual environment where you can test the car before you deploy it on the roads.

[00:00:14]And then there is a critique, which is a piece of software that's able to detect suboptimal performance in the simulator or in the real world, because then you can hone in on those suburb suboptimal cities and then improve the driver and then verify that those fixes have indeed worked in the simulator.

[00:00:34]So it's really the driver, the simulator and the critique is that triad it in our tech stack that allows us to scale. You have the full stack when it comes to autonomous vehicles. That's right, Waymo.

[00:00:47]That's right. But some of your competitors are going for a very different approach. They're kind of the brain only approach, the end to end machine learning approach without as much hardware, without necessarily those three different components.

[00:00:59]That's right. What gives you conviction that your approach that the Waymo approach ends up winning out?

[00:01:05]Our tech stack not focuses not just on the driver, but also ensuring that all of the plans the driver generates its journey, of course, so it generates plans, but you have to make sure that those plans that it generates are safe.

[00:01:20]And so you need to build in safety checks in real time so you can make sure the driver is prioritizing safety. And so it's the driver of the simulator and the critique on board components that prioritize safety, which is an onboard validation or an independent validation layer to ensure the driver does the right thing. And when you look at all of that, that's what it takes to drive, because there will be some who say that Waymo is winning the present, but Wayve AI, Tesla, maybe others end up winning the future. I think for us, what we have seen is that the the system allows us to learn fast and learn the right solutions to some of these problems.

[00:02:07]Recall we talk about this Waymo flywheel inside the company, which is this continuous learning loop where we take all of the experience of everything and every additional mile of experience, whether it's on the real road or in a simulator. And we take all of those learnings, we discover, we learn, we train our models, we simulate them, we validated that, we deploy it, and then we collect more miles, which is more experience. And it's that it's that continuous learning loop, that flywheel that we build around these three crucial components that allows us to scale. Do you think ultimately the two approaches converge, those pursuing the the end to end machine learning approach end up putting some light out, some radar onto their systems to have that that backup when it comes to safety, as you start to pare back some of the hardware to meet those those cost differentials to the two to the two systems start to converge at some point. I can't predict the future, but I think so. Right.

[00:03:10]Because, you know, in the end, we're all solving the same problem.

[00:03:14]You know, we want to drive safely and we want to have good solutions to the challenges that we face all along along the way.

[00:03:22]If Tesla cracks L4 fully autonomous and then they ship across that fleet that they have, how much of a competitive challenge would that be?

[00:03:31]We're always looking at competitors, and Tesla is a formidable competitor.

[00:03:35]And so, you know, I think competition is good.

[00:03:39]But if there is that breakthrough moment, we'd be right there with it.