Aurora CEO Chris Urmson on what's next for self-driving cars

Aurora CEO Chris Urmson stops by to discuss the future of self-driving cars with The Verge's Nilay Patel and Andrew Hawkins. They explore how the industry has evolved over the years, and how long it will take before self-driving cars are commonly used on the road. Learn more about your ad choices. Visit podcastchoices.com/adchoices

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Speaker 00

  This episode is brought to you by On Investing, an original podcast from Charles Schwab. Each week, hosts Lizanne Saunders, Schwab's Chief Investment Strategist, and Colin Martin, Head of Fixed Income Research and Strategy for the Schwab Center for Financial Research, bring you fresh insights on what's happening in the markets and why, and what the implications might be for your portfolio. Join Colin and Lizanne as they explore questions like, how do you evaluate corporate bonds that look interesting? And what sectors are on the move right now? Download the latest episode and subscribe at schwab.com/oninvesting or wherever you get your podcasts.

• 0:45Speaker 01

  When it comes to your business, you want cards and tools you can trust. Amex Corporate helps put you in control, set custom spend parameters to help fit your business needs, and quickly issue unlimited corporate cash back cards, all backed by best-in-class fraud protection and the powerful backing of American Express. Get started at go.amex slash Amex Corporate. Terms apply.

• 1:12Nilay Patel?

  Hey, everybody. It's Eli from the Vergecast. On this week's interview episode, I sat down with Andy Hawkins, once again, our senior transportation reporter. We talked to Aurora CEO Chris Urmson. Aurora is a new self-driving car startup. They're really focused on the software package, on the cars themselves. But Chris is a really interesting guy. He used to be at Waymo, which is Google's self-driving division. He was at Carnegie Mellon, which is a hotbed of self-driving research talent. So he talked about the industry, why it's so crazy, why all the people are suing each other, why the talent keeps leaving from one company to another, how hard it is to develop a self-driving car. We talked about the first line of code they sat down and wrote at Aurora. It's probably not what you think, and it's way more complicated than I expected. We also talked about whether it's going to happen.

• 1:56Nilay Patel?

  This is the first question I ask every self-driving car person that comes on the show. Is this going to happen? They all say yes, because they all run the companies. Their timelines are different, and the way they think it's going to happen is usually widely divergent. So, super interesting conversation with Chris Urmson, CEO and co-founder of Aurora.

• 2:16Nilay Patel?

  All right, we're here with Chris Urmson. He's a co-founder and CEO of Aurora, which is a self-driving car company. Welcome, Chris.

• 2:22Speaker 03

  Thanks for having me.

• 2:23Nilay Patel?

  I'm joined again by Andy Hawkins, two weeks in a row, Andy. Hello. Yes, I'm taking over the Vergecast. A person who understands what's going on in transportation, our senior transportation reporter, Andy Hawkins. So, Chris, you now work at Aurora, which is like a self-driving car tech company. Give us your history. You were at Google before?

• 2:39Speaker 03

  Yeah, so I've been working in self-driving cars for roughly the last 15 years. So, I was at Carnegie Mellon as a grad student, then on the faculty. And there, I took part in the DARPA Grand Challenges, which were these kind of robot races the Defense Department put on. And then, back in 2009, went to Google, helped found the self-driving car program there that's now called Waymo, led engineering, and ultimately ran that program for a number of years. And then, back in 2016, left and spent a few months trying to figure out what to do. And in that time, realized it was a chance to accelerate this technology coming to market through pulling together a great team, and then working in partnership with the rest of the transportation infrastructure, and founded Aurora with Drew and Sterling. And, you know, we've been off to the races for the last two years.

• 3:23Nilay Patel?

  I want to get into self-driving cars.

• 3:25Speaker 03

  Sure.

• 3:25Nilay Patel?

  My interest is actually the technology. But I just want to take one step back. It seems like the market for people who know how to make cars drive themselves is crazy, right? Like, and you named some of the biggest players. There was Carnegie Mellon, half of that team went to Uber, then he went to Google, which sued, like, right? Like, there's like, there's all these people.

• 3:48Speaker 03

  Yeah.

• 3:48Nilay Patel?

  Why, why is this industry as fluid, as contentious as it seems, at least from my perspective on the outside?

• 3:55Speaker 03

  I think there's a couple of reasons. One is, it's a new industry. And I think anytime you have a new industry, there's a lot of dynamic, right? There's a, there's a lot of, you know, flowers blooming, and, you know, mixing and whatnot. I think the other is that the technology is really great for capturing people's imaginations. Right, we've, we've all, well, almost all of us, probably everybody who listens to this is ridden in a car. And, you know.

• 4:18Nilay Patel?

  A long-running joke on the Verchassas is we make people pull over in their cars to tweet at us.

• 4:22Speaker 03

  Excellent. So, yeah, so they don't even need to pull over anymore.

• 4:26Nilay Patel?

  I have a vested interest in these cars driving themselves, yeah.

• 4:28Speaker 03

  Yeah, totally. And, and I think that, that most of us had the experience, you know, there's times when we've really enjoyed driving a car. And then there's a lot of times that's kind of sucked. And so the fact that we get to work on something that can transform the way people, you know, get around, the way our goods get around. I think that captures people's imagination. And I think that the opportunity here, both to make the road safer, to, um, to make it more efficient, to give better access to people. And ultimately to build a heck of a business, uh, I think is, is compelling.

• 4:58Nilay Patel?

  So you were, you were at three places. Obviously, the university is a research-oriented place. You're at Google, which is a very commercially-oriented place, and we almost got cars in the road now.

• 5:07Speaker 03

  Yeah.

• 5:07Nilay Patel?

  What is, what does Aurora fit?

• 5:09Speaker 03

  So Aurora, you know, we're a startup. You know, our mission is to deliver the benefits of self-driving technology safely, quickly, and broadly. We think about it as building the driver. So we don't want to build the car. We have a tremendous amount of respect for those people. We don't want to go build Uber or Lyft or UPS. We have an incredible amount of respect for how hard that is. We just want to build this capability to get the vehicle from one place to another and then work with partners to have a go and serve people.

• 5:34Nilay Patel?

  So you, you want to be one of the many, many suppliers of the automotive industry?

• 5:38Speaker 03

  Well, we don't think there'll be many, many people who can do this, right? We, we think actually building the driver is really hard. And we imagine ultimately this, you know, what's now probably a hundred companies working in this space will, will probably consolidate down to a handful. And we expect to be one of those.

• 5:52Nilay Patel?

  Why do you, is, is that a technology reason you think it's going to consolidate? Is it a capital reason? Is it?

• 5:58Speaker 03

  Yes, it's, it's all of them, right? I, I think it's really hard. It's a very complicated problem. It's one of the more complicated engineering problems where, you know, if not the most complicated engineering problem we're trying to solve right now. The number of people who have deep experience in it is relatively small. You, you know, you talked about the fluidity and kind of keep moving around. Well, the way you you win is kind of pull those people together and have them work towards a common goal, and that's what we're we're trying to do at Aurora. And then ultimately, I think the the technology, once we start to get it actually really deployed and serving people, right, you know, people talk about there being self-driving cars today, but there aren't.

• 6:32Nilay Patel?

  Yeah.

• 6:32Speaker 03

  They're not really out there yet. Once we start to really see commercial scale happening, there'll be, you know, there'll be evidence that the system works well and is serving people well, and so that'll start to kind of build a bit of a flywheel, I expect.

• 6:44Nilay Patel?

  So let me ask you, you actually said you were debating this over the weekend, but this is the question I ask every person who comes on our show and talks about self-driving cars is, is this gonna happen? Is this real?

• 6:54Speaker 03

  Yes, yes, it's gonna happen.

• 6:56Nilay Patel?

  Okay. On what timeframe?

• 6:58Speaker 03

  I think you're gonna see small-scale deployments in the next five years, and then it's gonna phase in over, you know, the next thirty, fifty years.

• 7:06Nilay Patel?

  And do you think the the model is the same as, you know, we had the CEO of Ford Mobility in here, and he's like, we're gonna do level two, and then everyone's gonna be comfortable, and we're gonna, we're gonna skip level three, because that'll make people crash their cars, and we're gonna... Do you think it's that stages of adaptive cruise control's get better, or are you taking the steering wheel out right away?

• 7:25Speaker 03

  So we're not taking the steering wheel out necessarily right away, but no, I don't think it's a continuum, all right? I think that this level-two driver assistance capability, I think that's great, right? That's, that's making people's lives a little bit better, but it's very different than self-driving capability, right? Driverless vehicles. And that's what Aurora, we're focused on, because we we look at all the the big players in the automotive space, and they know how to do driver assistance, and it's really a problem of, is the product compelling enough that the consumer wants to buy it for the, you know, the the price they can sell it at? When we think about driverless vehicles or self-driving vehicles as, you know, the level four and five from the SAE standard.

• 8:09Speaker 03

  That's where we see a transformation. That's where you can sleep in the car. That's where the vehicle can be deployed as part of a transportation service and, you know, give you a ride, then give me a ride. And we can share the benefit of that together. And I think that's where the economics swing. And that's where we see the biggest social good for the, you know, for cities like New York and San Francisco.

• 8:30Speaker 04

  Will they be personally owned vehicles, do you think? Will they be part of a commercial fleet? What do you think is going to be sort of the breakdown there?

• 8:38Speaker 03

  So I expect this will come to market first as part of a fleet. I think that the, just the economics again, that's where it makes sense. If you could imagine, you know, let's say we're a few years down the road and the kit for the self-driving capability, I don't know, it's $20,000 worth of stuff, let's imagine. That's really, that's really a premium to pay on top of the price of a car. Whereas if that car is out and actually, you know, contributing commerce, right, it's people are paying to get rides in it, or people are paying that vehicle to go and deliver goods, then the economics suddenly make a ton of sense. And $20,000 sounds really cheap. And so I'm pretty convinced that's the way it comes to market first. And the good news is, I think that's the way that

• 9:22Speaker 03

  we get the social good. Because if this really comes to market as an expensive feature that, you know, rich kids use to go send out to run errands, you know, I joke about fetching ice cream for them, right? That's just going to create more traffic and that's not really helping anyone, I don't think.

• 9:39Speaker 04

  It's like the zombie car phenomenon that I've heard spoken of.

• 9:42Speaker 03

  Yeah, I hadn't heard of that.

• 9:43Speaker 04

  Just empty cars. You ever heard of that one? Just empty cars, pile in the streets, fetching ice cream and Uber Eats deliveries for people.

• 9:49Speaker 03

  Geez, yeah, let's, let's not do that.

• 9:52Speaker 04

  Well, so some of the recent news around Aurora was that you guys just received a very significant investment from Amazon, over half a billion dollars. What do you think Amazon's interest is in Aurora? Where's, where are the sort of the overlap here?

• 10:07Speaker 03

  Presumably they told you. Well, I think you'd have to talk with the Amazon guys about what they're thinking. But let me tell you what we think about it. So we see Amazon as this incredible company that has both world-leading capability in cloud, which is an important technology for us as we're building what we're doing. And then on top of that, they're just an immense logistics company. And Aurora's in the business of building drivers. And so we think ultimately that'll be a way that we collaborate.

• 10:38Nilay Patel?

  When you say, you said earlier, you can sleep in the car.

• 10:42Speaker 03

  Yeah.

• 10:43Nilay Patel?

  Is that your North Star? Is there just a picture on the wall of your office of somebody asleep in the front seat of a car?

• 10:49Speaker 03

  No, that's not really our North Star, right? Our North Star is the company's mission, which is to deliver the benefits of self-driving technology safely, quickly, and broadly. And so we really, I think a lot of our people think about the 1.3 million people that die globally on the world's roads, right? And that is one of the leading causes of death, or if not the leading cause of death for people under 29. That's incredible, right? This is the thing where we can bring technology to bear to address it. And then we think about the accessibility of transportation, both for folks that can't, don't have the privilege of driving like you or I do, and allowing them to get around with the same kind of flexibility and freedom we have. And then we think ultimately about the ability of this technology to come to market and to

• 11:34Speaker 03

  serve across socioeconomic boundaries. That New York has an incredible public transportation system, right? I used it this morning to get here. You're shaking your head, but I think compared to a lot of places in America, it's pretty incredible.

• 11:46Nilay Patel?

  Yeah. There's people who live here.

• 11:49Speaker 03

  Fair enough.

• 11:50Nilay Patel?

  It's a C+.

• 11:51Speaker 03

  C+, fair enough. Well, I think that means that everywhere else in the country, it's an F-. So I think that this technology can actually come to market in a way where it's augmenting public transportation, where we can actually provide the level of service, a much better level of service at a much lower cost ultimately.

• 12:07Nilay Patel?

  It's funny, I love hearing new startup founders talk about not doing the technology for the technology's sake. When you talk about, okay, we're going to make transportation more inclusive, okay, we're going to make the car safer, how does that actually factor into the technology decisions?

• 12:21Speaker 03

  Well, we look at it as, some parts of it as table stakes, that we're actually, the status quo today is broken. Yeah, we've had two 737 MAX 8 crashes. It turns out if you annualize, you know, you take the 40,000 people that die every year on America's roads, that's the equivalent of four of those planes crashing a week. So we have this fundamental problem in the transportation system that we have. So we look at that and say, that's pretty profound. We think about the amount of value that can be created by addressing that, both to society,

• 13:02Speaker 03

  but also when we, you know, we do kind of in a very cold way, look at the business. And we say, we don't have an opportunity to go, we don't think we add value to driver assistance work. Companies are doing that well already. Where we do think we add value is the insights we have and the understanding we have about self-driving capability. And that means we can go build a business in that space. And it's pretty much green field because the technology doesn't exist. And if we can go and tap into the three trillion miles that are driven everywhere in the US and make, you know, cents per mile, that's an incredible business.

• 13:40Nilay Patel?

  Yeah.

• 13:40Speaker 03

  So, yes, our company's mission is, honestly, you know, I've been doing this for 15 years. I've been doing it since before it was sexy. Right? We're bought into all the social good things. But if you look at the, you know, our ability to go raise capital, we have some very smart folks who care about the economic outcome here and they're pretty, you know, making a pretty big bet with us.

• 14:04Nilay Patel?

  So you're not making like a LiDAR versus vision decision based on the bigger stuff? You're making your own kind of independent decisions and you're saying the other stuff is going to come along for the ride because this is just so much better?

• 14:17Speaker 03

  Well, we make a LiDAR versus vision versus whatever. And actually, we don't think of it versus, we think it's a combination of them.

• 14:25Nilay Patel?

  Yeah, that was my next question.

• 14:26Speaker 03

  Right? Because, because that's what you have to do to solve the problem. You know, people. We won't be able to bring this technology to market if it isn't safer than what we have today. And so this is one of those places where kind of the the the business interest and the social interest, I think, are really well aligned.

• 14:45Nilay Patel?

  Okay, so let's do the nerdy stuff.

• 14:47Speaker 03

  Sure, let's do it.

• 14:47Nilay Patel?

  I was trying to lead to it and you you beat me to the punch.

• 14:49Speaker 03

  Oh, I'm sorry.

• 14:50Nilay Patel?

  No, it's great. That's how it's supposed to go. Everyone else is supposed to be smarter than me.

• 14:53Speaker 04

  Why why else are people listening to this anyways? They want the nerdy stuff.

• 14:56Nilay Patel?

  Yeah, they're here for it. So describe your technology. Like, there's a lot of competing ways to do this.

• 15:01Speaker 03

  Yeah.

• 15:02Nilay Patel?

  It seems, at least from this conversation so far, you think the incremental improvement of driver assistance is not the way to go there. It's handled.

• 15:08Speaker 03

  Not gonna get there.

• 15:09Nilay Patel?

  You don't you don't think it's gonna get there.

• 15:10Speaker 03

  Yeah.

• 15:11Nilay Patel?

  What is how does your system work?

• 15:13Speaker 03

  So so our system, you know, we we talk about it as version 2.0 of the self-driving car technology. So we were able to bring together founders and team that have spent a lot of time building this technology. So our VP of Software Engineering used to lead SpaceX's software team. So these are the guys who land and launch rockets, right? That's pretty cool. One of the co-founders of Ross works at Aurora. And this is the big robot operating system which a bunch of people use. So so we we've taken that experience and we've said, okay, what what are the insights we have now about how to solve the problem? So one of them is that, yes, you know, deep learning is important. Machine learning generally is super important. But folks who kind of forget about all of the classic kind of algorithmic work that's been done, you know, things like

• 15:58Speaker 03

  common filtering and all the the probabilistic state estimation work that's that's happened in the past. Maybe you could get a machine learned system to approximate that. But it turns out if you actually understand the models, you can do it really well and you you know, you you can do it much more efficiently. So at Aurora, the the philosophy is, let's go bring the best of the deep learning world. Let's go bring the best of kind of that that engineered world together to solve the problem. And based on the experience we have, we can kind of figure out where to apply that. Yeah, one of the the examples we talk about is how we deploy machine learning in our motion planning system. So machine learning is great because it can pick up on on feature vectors and whatnot that our engineers maybe don't intuit. The challenge is, you don't know exactly.

• 16:43Speaker 03

  What the bounds of its behavior are going to be, particularly in situations that you may not have encountered. And so the way we address that Aurora is we actually encode invariance, which are effectively rules that the system has to maintain as it's operating. So, an easy example of this is, we force the vehicle to always keep enough distance, enough time, really, between it and the vehicle in front, such that if the front vehicle hits the brakes as hard as it can, we can sense that, react to it, and avoid a collision. And so that invariant is coded and wrapped around the machine learned system that is then, within that set of constraints, saying, okay, given all of the infinite ways we could

• 17:27Speaker 03

  have turned the steering wheel, or pressed the brake pedal and a gas pedal, what feels most natural? What behaves in a way that is a reasonable approximation of the way a human would drive?

• 17:38Speaker 04

  So do you have to recognize the vehicle in front? So if you're in front of like a delivery truck versus a Ferrari, you know the Ferrari's gonna stop faster?

• 17:45Speaker 03

  We don't, actually. We kind of make a pessimistic assumption about what might happen.

• 17:52Speaker 04

  An unmaintained Ferrari?

• 17:53Speaker 03

  Yeah.

• 17:54Speaker 04

  Worn out?

• 17:55Speaker 03

  Well, actually, it's kind of the other, right? Is that we assume that the package truck has super brakes, because that's actually the more difficult thing, right? If it slows down more slowly, we've got more time to brake for it.

• 18:07Speaker 04

  I've been told from folks in this industry that prediction is a very hard, sort of hard nut to crack in all of this. Could you talk a little bit about how you guys are approaching that?

• 18:18Speaker 03

  Yeah, so, when we think about the stack for self-driving vehicles, right, it starts with, you've got the sensors observing the energy in the world, you then got the system that's estimating the state right now, and then you're trying to figure out, how's the world gonna evolve over the next five to 10 seconds? And then the motion planning system uses that to figure out how it moves through the world. And so- We are using human driving experience to kind of build an implicit model of what the world will do over the next five to 10 seconds. And then the combination, really, it's what's interesting about one of the things we're doing at Aurora is we're actually closing the loop around both motion planning and perception and, you know, also through that prediction.

• 19:02Speaker 03

  And what's kind of cool about this is the way that I've seen this done in the past is machine learning was primarily applied to the perception system. And the perception team would go off and they'd kind of learn as good a model as they could. They would spit that out and it would have some kind of noise and issues with it. And then the motion planning team would say, okay, we're going to go implement a feature set and we'll use that model. So they go churn away at it and they deal with whatever the noise characteristics are. Then the perception team says, hey, we just spent the last three months, we've just kicked out a new model. And so then it hands off to the motion planning team again and they're like, oh, that's great. I'm glad it's so much better, but now we have to go and re-tune everything again. And so they kind of get stuck, you know, being swung around by the perception folks.

• 19:45Speaker 03

  The way we're engineering the system at Aurora, and this is back to this kind of V2 idea, is to close the loop around both so that as soon as the perception guys have done whatever magic they've done, you know, the motion planning team can then basically overnight incorporate that information, that new model into their way of doing business.

• 20:03Nilay Patel?

  Why is that not possible in other places?

• 20:05Speaker 03

  Because it's not obvious how to do it. Right? So this is one of the things that Drew Bagnell, one of our co-founders, brings. So he's, you know, he and I have known each other for the last 20 years. We went to grad school together at Carnegie Mellon and he's one of the world's experts in machine learning applied to robotics, applied in particular to motion planning. And so this is kind of a big chunk of what his career has been is how does he, how do you smartly apply machine learning to that? And so that experience kind of shines through. And for me, Drew and I had never really worked together in the past. And so, you know, I had a great bunch of people I worked with at Google and we did some very cool stuff. And since working together with Drew, what's been great is there's a few things where,

• 20:49Speaker 03

  you know, he said, you know, we're going to solve this problem like this. You know, my intuition is like, no, Drew, you're crazy. That's a terrible idea. But, you know, that the, but, okay, let's give it a go. And then we do, and it turns out he's right. Give me a natural example. Well, in particular, this, this kind of model for closing the loop around, around motion planning is kind of hard to get into the details of it. But it was not obvious to me that, you know, investing the energy we did upfront was the right answer. My instinct is, let's go out, let's get something on the road, let's try it and, you know, iterate. And his was, no, let's, let's actually take a moment and think here. And, you know, architect a system so over time, as we get more data, it will automatically improve.

• 21:32Speaker 03

  And, you know, I'm like, okay, that's a great idea, but how do we do it? And, you know, he came up with an approach with the team and, and that's, that's rolled out and that's exciting to see.

• 21:39Nilay Patel?

  Want to take a quick break for an ad? We'll be right back.

• 21:48Speaker 00

  Ask yourself, what are your best people spending their time on right now? Expense reports, receipt chasing, month end close that takes weeks. You become what you spend on, and that's not what you're building toward. Brex is the intelligent finance platform that eliminates that work before it starts. AI agents that handle the manual stuff automatically so your team can spend their time on what actually compounds. It's time to get Brex AF. Learn more at brex.com/AF.

• 22:24Speaker 05

  Your heart can tell you a lot about your health. Apple Watch Series 12 measures your heart rate every five seconds with the most accurate heart rate sensing and wearable. So your vitals app, now with heart rate variability, can tell you when something is off. And your readiness score can let you know when to rest and when to push. Hear the story in every heartbeat with Apple Watch Series 12. The features described are for wellness purposes only and not for medical use. iPhone 11 or later required. Based on Apple conducted study of heart rate accuracy, August 2026. Visit apple.com slash Apple Watch Series 12.

• 22:55Nilay Patel?

  Okay, we're back with Aurora CEO, Chris Urmson.

• 23:00Nilay Patel?

  Let me ask you a really, this is gonna be a dumb question.

• 23:02Speaker 03

  I have my doubts.

• 23:05Nilay Patel?

  Well, it's a good show that I put on.

• 23:09Nilay Patel?

  You start a company.

• 23:10Speaker 03

  Yep.

• 23:11Nilay Patel?

  You're a self-driving car engineer, you've been doing it for fifteen years.

• 23:14Speaker 03

  Yep.

• 23:14Nilay Patel?

  Call your friend, "Hey, we've never worked together, it's great being in school with you, let's start this company together." You call some other friend. You're all in a room, you're in the conference room.

• 23:20Speaker 03

  Yep.

• 23:21Nilay Patel?

  What is the first line of code that you write?

• 23:25Speaker 03

  What was the first line of code we wrote?

• 23:29Speaker 03

  You know what it was, actually? So, I think the first place we started was building the... This sounds really boring, but it was the representation for the position of the vehicle. So, a vehicle, once moving through space, it's got XYZ, roll, pitch, yaw, and some speeds. And this is another one of these places where it's actually kind of one of these geek-out math things. So, historically, you would use XYZ and a rotation matrix, but rotation matrix has got some problems where you kind of have these singularities in the representation, and things don't behave well. So, you say, "Okay, we're gonna go use quaternions instead, because that's a much better representation." And that, again, has some problems.

• 24:13Nilay Patel?

  Can you say that word, "quaternions"?

• 24:15Speaker 03

  Sorry, "quaternions." It's a four-dimensional vector that you use to represent rotation.

• 24:20Nilay Patel?

  This is what we're here for.

• 24:21Speaker 03

  Yeah, this is...

• 24:22Nilay Patel?

  This is my heart's sin.

• 24:23Speaker 03

  Sorry, okay. You want me to say it more slowly?

• 24:26Nilay Patel?

  Yes, please.

• 24:27Speaker 03

  Quaternion.

• 24:28Nilay Patel?

  Quaternion.

• 24:31Speaker 03

  And so, that's kind of the hotness for a while. And it turns out that there's these even cooler stuff called Lie groups. And one of our engineers, Ethan, it turns out if you go to ethaneed.com, it is basically the world's repository of information about Lie groups and Lie mathematics. And it turns out this is one of these very, really interesting ways to represent transformations through space that have none of the problems of rotation matrices or quaternions. And yet, I've been doing this for a very long time and had never done it before, never used it. And so, as we got started, this was like, this is the right way to represent, this is the mathematically beautiful, correct way to do it.

• 25:14Speaker 03

  And so that's what we started with. And from there, we built out the local state estimation. So integrating the inertial system and the GPS to figure out, the wheel encoders figure out how the vehicle's moving. And then the global localization. So this is where is the vehicle in the world to a really high degree of accuracy. So, or high degree of precision. Ten centimeters, you know, tenth of a degree kind of resolution.

• 25:38Nilay Patel?

  So you build that stuff. It sounds like that's a big, a big leap of intuition and logic to get to where you are.

• 25:45Speaker 03

  That was pretty cool. Yeah.

• 25:45Nilay Patel?

  Yeah. And then you're like, well, we need a map. We're just gonna call Here Maps and we're just gonna buy a map and stick it on the map.

• 25:50Speaker 03

  Yeah, we thought about that. And, and in fact, when we founded the company, you know, Drew and I said, we've built maps in the past. We've done a lot of this.

• 25:57Nilay Patel?

  I mean, you're at Google. I mean, it's like you have access and you just don't think of the phone, right?

• 26:01Speaker 03

  Well, we, you know, even at Google, we, we built custom maps for the self-driving car project.

• 26:05Nilay Patel?

  I bet the maps team was like, dudes, come on.

• 26:10Speaker 03

  There was, there was a little bit of that every once in a while. But, but, you know, in our defense, you know, the, the maps guys had to produce maps that were being used by a billion people. And, you know, we had like six self-driving cars.

• 26:23Nilay Patel?

  Yeah.

• 26:24Speaker 03

  And so, you know, if you're the maps team, what are you gonna build? You're gonna fix the six self-driving car problem? Or are you gonna fix the problem that's

• 26:30Nilay Patel?

  Yeah.

• 26:31Speaker 03

  irking a billion people? So, anyway, different products.

• 26:35Nilay Patel?

  Yeah.

• 26:35Speaker 03

  Um, and so we started the company and, you know, Drew and I were like, and I think Sterling as well, were like, we are not gonna build maps. There are a bunch of companies out there doing this. We will use their maps. And then as we, we dug into it, and we came to the conclusion that that was the wrong answer. One is that the maps that we were able to get, they were really built by taking maps that were intended for people and kind of plus-plus-ing them, right? Just making, you know, higher resolution. And what we realized is that the maps that you need for a self-driving car are different, right? And you have different properties that you're looking for. You need, you do need very high precision in these maps. And what you want is you want to be able to

• 27:19Speaker 03

  update them frequently because it, you know, it turns out if my My navigation map is a little bit out of date, you know, I kind of roll with it. If the map of the self-driving car is out of date, well, we have to be able to roll with it, but, you know, what we really want is it to be not out of date, be able to update it very quickly. And so we, we came to the realization that the other, the other map systems that were out there didn't meet the requirements for self-driving vehicles. So we said, okay, well, you know, we'll, we'll actually take this on and, and start to build that as well. And now we, we think that's actually one of the strategic advantages we'll have is, is a really interesting representation of, of the world for these vehicles.

• 27:56Speaker 04

  I wanted to ask you about safety. You brought up the fact that 40,000 people die in car crashes every year. And it seems like on some level, as a society, we've sort of internalized that, right? And we've sort of accepted that as sort of the price of driving a car, having access to cars, and sort of the freedom, quote unquote, that comes with driving a car. And I'm just wondering how you sell safety to a public, especially when, you know, we have a very, we have a high tolerance for people killing other people on the roads, but we probably, I would assume, and it's only happened once, but we have a very low tolerance for robots killing people on the road. So how do, what's, how do we sort of bring that sort of into parity, do you think?

• 28:37Speaker 03

  Yeah, so I, I think the, the first is that we, we have to help educate the folks who can figure out what the rules should be, and help them understand the risks so that they can, you know, so, and I'm thinking about folks like NHTSA or the state DOTs, where their job is to, to kind of govern our roadways and kind of manage the, you know, kind of the, the risks there. And so one of the things that I've spent a fair bit of time over the last several years doing is, is engaging with those folks, helping them understand what we perceive as the risks and what we perceive as the opportunities, and, and helping prepare them for this technology, so they can have an independent opinion and, you know, and do the right thing as, as this technology starts to roll out. I think we

• 29:21Speaker 03

  have to help educate the public about, you know, the opportunity here. I think one of the things, though, that's, that's most compelling to me is that the way this technology's come to come to market, the, kind of the safety will come with it. So- Most people, when they go to buy a car, they, you know, they don't really understand the risks of operating a vehicle. They don't really rationally assess that. And they generally don't pay for extra safety features. Because, you know, if you think about it, there's a bunch of incentives against this. So the first is that when you go to the lot, the cars that are there that you can buy are selected by the dealer. And they look at, you know, what are the different features they can put in that car? And where can they

• 30:05Speaker 03

  effectively make the most money? And so they have a choice. They can put a $3,000 stereo system in the car they ordered, and that's got an 80% margin. Or they could put a $3,000 driver assistance system in the car, and that's got a 20% margin. And so like, well, let's get more of the stereos, because, you know, that, we make more money off of that. So there's less options there. And then as the consumer, you know, you get there and you have a choice. Well, I could buy this thing that's got this nice stereo that I use every day and that I enjoy, or I could have this thing that, you know, well, I'm a better-than-average driver, as 80% Americans plus believe. And so this thing that I will, you know, only use on a really crappy day. Which am I going to pick? Well, I'm going

• 30:46Speaker 03

  to pick the one that's on the lot and that has the feature that I enjoy. And so that's a, you know, kind of a long way to get to. There's a reason why these advanced safety features, driver assistance features, aren't more prevalent in vehicles today. It's because the whole system is kind of stacked against them getting there. Whereas, the driverless technology that we're working on, the Level 4 capability, people will use it because it is more convenient, because it's a better way to, for them to kind of get from one place to another. They can use that time however they want. And along with that, they'll get a system that is never drunk, that, you know, doesn't get distracted, that, you know, isn't tired, and that can see 360 degrees around it. And so the safety will come along with those.

• 31:29Speaker 03

  Kind of the convenience benefits of of the technology.

• 31:32Speaker 04

  Can the can the industry absorb another incident like the Uber incident in Arizona? Do you think? Because that was clearly such a setback and it it it seems like it's had an effect on on the public's attitude towards self-driving cars, even though it's like it kind of boggles my mind that they still do like polls and surveys about self-driving cars when 99.9% of people have had no experience with a self-driving car at all. So you're asking people questions about a technology that they've never encountered in the world. So yeah, it's do you think because it seems likely that there's going to be another incident as more cars come on the road and it starts to become, you know, sort of a more sort of hybrid hybrid system of, you know, human-powered cars and robot-powered cars.

• 32:14Speaker 03

  Yeah. And so to answer your question, yes, I I do believe we we can weather that storm. I think we have to be working diligently to to test safely and responsibly on the roads. I think we need to be building technology where we are holding ourselves to a high safety standard. But we also have to remember that the, you know, the perfect really is the enemy of the good here. And that if we could cut traffic deaths in half with this technology, that would be as big an impact as seat belts. But that is still 20,000 people dying, you know, on America's roads. And what's what I think is really compelling here is that this is a technology where the driver will continue to get better and better over

• 32:56Speaker 03

  time. As we deploy the technology, it'll be better than people to to begin with. As we learn more from what's out there, we can then push improvements to that driver that span the fleet and all of the vehicles will get better, right? If if I have a bad event on the road, maybe as I'm out on the road after that, I think about that and I behave a little differently. But you don't learn from it and you don't learn from it. Whereas the whole fleet will learn from that bad experience and get better.

• 33:24Speaker 04

  So I actually, I think about this all the time.

• 33:27Speaker 03

  Yeah.

• 33:28Speaker 04

  Because I have very nerdy thoughts. I'm sure you do, too. Like, it seems like the big increase is when there's widespread vehicle-to-vehicle communication, when all the cars on the road are talking to each other. But right now, like, there's a jerk in a Mustang and like your your system has to just like have code that's like gonna I mean, I'm just think literally thinking of myself as a teenager because I was definitely a jerk in a Mustang.

• 33:52Nilay Patel?

  Like, is that the ramp?

• 33:53Speaker 03

  Literally in a Mustang?

• 33:54Nilay Patel?

  Literally in a Mustang.

• 33:55Speaker 03

  Excellent.

• 33:55Nilay Patel?

  One time I crashed my Mustang into a bank. This is a true story. The bank didn't-

• 33:59Speaker 03

  Intentionally, or like?

• 34:01Nilay Patel?

  It really depends on where you think attention ends and-

• 34:04Speaker 03

  Statute of limitations, I think is probably good here.

• 34:07Nilay Patel?

  Or, I guess, understeer begins.

• 34:10Nilay Patel?

  Is that the ramp? Is that the inflection point when there's like widespread V2V? Or is it your computer's just gonna-

• 34:16Speaker 03

  I, so I, I think our computer has to deal with it, right? Our software has to deal with it. And I think, again, one thing that's compelling to me is that even one self-driving car on the road i- is a safety benefit because that, that will be a, a, you know, a better driver.

• 34:32Nilay Patel?

  A known good.

• 34:33Speaker 03

  Right, and, and, and that means it's going to create less bad events for other people around it. And as we, as we integrate more of these vehicles onto the road, it'll get, you know, better and better and better. I do think ultimately, you know, V2V is an interesting technology, but it's not one that I think we can kind of hang our hat on and, and, and wait for. So I, I think about my children walking to school in the morning. They don't have transponders on them. I think about, you know-

• 34:57Nilay Patel?

  Well, they have phones, right?

• 34:58Speaker 03

  Well, the younger one does not, right? Uh, older one does, but, um, you know, I don't think you can count on-

• 35:05Nilay Patel?

  That's like a privacy nightmare too.

• 35:07Speaker 03

  Right, and then, you know, if you think about your old Mustang, it's probably still actually out there. It doesn't have a transponder on it.

• 35:13Nilay Patel?

  The kid I sold to, he totaled it.

• 35:14Speaker 03

  But yeah, I'm sorry. Okay, so, so bad example, but, yeah. Sounds like that car had a hard life.

• 35:20Nilay Patel?

  That car was not treated well, uh, by any, by any stretch of the imagination. But I, it, that's, I, that's interesting to me. Like, you're, you're gonna do all this local processing in the car, effectively, and then you're gonna have a cloud infrastructure that improves your fleet. But that's not gonna go talk to Uber's fleet. That's not gonna go talk to Waymo's fleet.

• 35:42Speaker 03

  Well, hopefully, hopefully our fleet, you know, ends up powering Uber and Lyft and, and the other folks. But, you know, we'll, we'll see how that goes, right?

• 35:49Nilay Patel?

  One self-driving company and you're in there. But it's, you're not gonna talk to, like Volvo's gonna get, do something over time, right?

• 35:55Speaker 03

  Yeah, it'll work with us. It'll be great.

• 35:57Nilay Patel?

  Sure. Okay. Well, it's a bold vision. But like, do you like, worry that there's gonna be like resonant, like nightmare effects of like competing cloud fleets?

• 36:06Speaker 03

  No, I actually, that isn't, you know, I, uh, no, that's not one of the, one of my top worries, right? It's, and, and the reason why is there, there kind of is an interoperability standard today, right? And it's, it's the rule of roads, right? It's the, you know, it's a little loose, but the, you know, the DMV for New York State or for California, you know, describes how you're supposed to behave. That kind of bounds the behavior the vehicles can take. And I think at that point, you're in, you know, you're in pretty good shape.

• 36:30Nilay Patel?

  Yeah. It's funny that you said there is an interoperability standard. I was expecting, like a, like a white paper reference.

• 36:36Speaker 03

  Yeah, no.

• 36:36Nilay Patel?

  No, it's actually just the DMV.

• 36:37Speaker 03

  It's the DMV handbook. Yeah.

• 36:39Nilay Patel?

  Yeah, that's amazing.

• 36:40Speaker 03

  Um, but it works, right? You know, today, there's, there's literally millions of, millions of independent agents interoperating on, you know, the roads out there. And they do that through this, this kind of common standard, which is the DMV handbook.

• 36:53Nilay Patel?

  Yeah. When you think about, it's like when Andy writes about Waymo, it's always in terms of miles driven, right? Like, why, why is Waymo ahead? They've got the most miles.

• 37:04Speaker 03

  Yeah.

• 37:04Nilay Patel?

  Is that a metric that you think about as well?

• 37:06Speaker 03

  No, I, you know, and, and obviously I was, I, I was there and it was a really good number that we could, we could use.

• 37:10Nilay Patel?

  You were responsible for a significant portion of those millions.

• 37:14Speaker 03

  Well, I, I was a small part of, of, of, of folks that did all.

• 37:18Nilay Patel?

  You're personally responsible for like 25 miles.

• 37:21Speaker 03

  There was actually a period of time where, um, I did have the most number of miles.

• 37:26Nilay Patel?

  Hey, there's like a leaderboard in the, in the office?

• 37:29Speaker 03

  Well, it wasn't, you know, we didn't actually have a leaderboard up on the wall, but you, you could cut it by, you know, who was driving and, yeah.

• 37:35Nilay Patel?

  All right. So miles driven is not a metric. What's your, what's your metric?

• 37:38Speaker 03

  Uh, so, so we, you know, we, we look internally at a bunch of different performance criteria. So the way we think about developing is we're going to go, uh, we've got a set of features that we need to build that, you know, things like, we need to be able to deal with traffic like controlled intersections. We need to be able to make left turns across traffic. We need to do right turns. We need to deal with pedestrians crossing, jay workers. So we, we have a collection of these features and then what we do is we go build a bunch of simulation tests and we go gather a bunch of, uh, human driven representative data, uh, driving examples, you know, in those kind of environments. And then we, we internally set the goal to be able to, you know, here's the, the N, where N is a, you know, relatively large number of tests that the system needs to be able to pass in simulation. Once we

• 38:22Speaker 03

  do that, then we're, we're excited to go see, uh, to then look at, you know, how's it doing relative to the human driven data and kind of optimizing within that. That's kind of the way we think about future development internally.

• 38:34Speaker 04

  Can you give us a sense of sort of, what's the current status of your, of your test fleet? You have cars in California, you have cars in Pittsburgh.

• 38:41Speaker 03

  Pennsylvania, yeah.

• 38:41Speaker 04

  Right, so what, what are they doing right now?

• 38:45Speaker 03

  Yeah, so, so we have eight vehicles. For us, you know, again, back to the miles, for us it's not about maximizing miles, it's about maximizing kind of learning and data for the fleet. And so every day those vehicles are on the road. What's cool is we, we have three offices today. We're in San Francisco, Palo Alto, and Pittsburgh. And we have cars on the road in all three locations, basically every day. And that gives us a really good diversity of experiences. So San Francisco is a relatively modern city, but high density. You know, Palo Alto is suburban, representative of an awful lot of America's kind of suburban roadscape. And then Pittsburgh is actually a very dense, you know, older city with an older infrastructure.

• 39:28Speaker 03

  And so by having vehicles on the road across that, we're able to build and learn from that, that breadth of experiences and make sure we're not pigeonholing to, you know, super wide, open spaces that never have weather, you know, for example.

• 39:41Speaker 04

  Like Arizona.

• 39:42Speaker 03

  For example.

• 39:44Speaker 04

  So is the idea that a car, one of your cars, or say, any self-driving car company's cars, will need to operate within a certain domain for a certain period of time before it can become commercially operational, essentially, before it can start to do the thing that makes the company money? Or will you get to a point where you can just basically take a car and drop it into any location and have it begin sort of doing that task?

• 40:11Speaker 03

  So for us, we, we're gonna need a map first. So we'd have to go do that chunk of data gathering. And then, I, I don't know, is the, is the honest answer, right? We, we expect that as we get better and better, it'll look more like we can just effectively drop the vehicle into a domain. Because, you know, I think about, you know, me as a driver, that, you know, I might most of, spend most of my time driving in, you know, suburban. Bay Area, but I can also, you know, not particularly well, go drive in Boston.

• 40:45Nilay Patel?

  I wouldn't recommend it.

• 40:46Speaker 03

  Yeah, I don't do that often. And so, right, I think as the technology gets more advanced, it will look more like we can just drop these vehicles in places, but I think early on, there'll be enough lessons and, you know, to get geeky, you know, we'll be expanding the ODD, the Operational Design Domain, for these vehicles over time.

• 41:07Nilay Patel?

  All right, so I want to, we're a little bit over time, so thank you, but I want to kind of wrap up where we began, which is, is this going to happen? Like, and I ask that question again in that way, but more specifically, do you think that the average consumer is going to go out and purchase a car that drives itself for real within 10 years?

• 41:28Speaker 03

  No, I don't think that, I think, again, that this is going to come to market in fleets and transportation services, and I think the economics there are going to be profound, I think the benefits will be profound. Yeah, I think the adoption curve for personal car ownership is further out. It just, the economics makes so much more sense in the other business model that I think that's where the energy is going to get focused.

• 41:51Nilay Patel?

  Yeah. And how long will people have to be in those cars, do you think, in those sort of early stages, monitoring the situation? Because it seems like it's, half of it is sort of a liability issue and the other half is a psychological issue, like.

• 42:05Speaker 03

  Elevator operators.

• 42:06Nilay Patel?

  Yeah, right, you know, like people weren't willing to get onto an elevator without somebody inside of it until they were positive that it was something that they could safely do.

• 42:14Speaker 03

  So I think, when I say within the next five years, you'll see small-scale deployments, that's without other people in the vehicle, where, you know, you'll be able to hail one of these vehicles, get in it, and it'll take you where you're going, or you'll be able to, you know, order something from somebody, it'll show up, you know, vehicle pull up to curb, you walk up, pull your stuff out of it, and then off it goes. And I think that happens in the next five years.

• 42:36Nilay Patel?

  Wow. So where can people keep up with what Aurora is doing, besides Andy's terrific reporting?

• 42:41Speaker 03

  So, so we have a blog post up on Medium, and, you know, we're at www.aurora.tech.

• 42:48Nilay Patel?

  Cool. All right, well, Chris, thank you so much for stopping by, it was a great conversation. I look forward to getting in a self-driving truck that takes me wherever I'm going, powered by Aurora.

• 42:56Speaker 03

  Or a self-driving Mustang.

• 42:58Nilay Patel?

  Literally any technology would have been a superior driver than me. It could have been two robot arms connected to like an Apple LC2, it would have been better than me.

• 43:08Speaker 03

  Breaking bungee cord.

• 43:09Nilay Patel?

  Yeah, awesome. Thanks, Chris.

• 43:10Speaker 03

  Thank you so much.

• 43:11Nilay Patel?

  All right, that was Aurora CEO Chris Urmson. Special thanks to Andy Hawkins, our senior transportation reporter, for helping me out with that. I'm not going to be on the Birchcast this week on Friday. I'm out in LA doing some LA stuff, but Dieter and Paul hold it down. Probably have some special guests in the mix. We'll be back next Tuesday with another interview episode, next Friday with a chat show. Birchcast, keep rolling. Let me know what you think. Tweet at me, I'm at Reckless. Would love to know what you think of the show and who you want me to interview. I live for that feedback. We'll see you soon.

• 43:45Speaker 06

  Support for this show comes from CoreWeave. Everywhere you look, AI is expanding what we thought was possible, and at the center of it all is CoreWeave. Medical research and diagnosis, education, complex visual effects for movies, science and technology breakthroughs. CoreWeave powers AI pioneers around the world with purpose-built tech, building what's never been built before. CoreWeave is the essential cloud for AI. Ready for anything, ready for AI. To learn more about how CoreWeave powers the world's best AI, go to CoreWeave.com/ReadyForAnything.

• 44:25Speaker 06

  Support for this show comes from Canva Enterprise. Design is the face of your brand. It's how you stand out in a noisy world. That's why Canva Enterprise is the all-in-one visual communication platform that lets your organization create, collaborate, and publish high-impact on-brand content at scale. Canva Enterprise was designed to clear up bottlenecks so your teams move faster, stay on brand, and create content that stands above the rest. Whether it's social, presentations, docs, or video, scale your content without scaling your team. Give your team the power to create their best work today with Canva Enterprise. Learn more at Canva.com/Enterprise.