When trucks drive themselves with Chris Urmson of Aurora

0:00Wondery Plus subscribers can listen to How I Built This Early Early and Ad Free right now. Join Wondery Plus in the Wondery app or on Apple Podcasts. listening on audible helps your imagination soar whether you listen to stories motivation expert advice any genre you love you can be inspired to imagine new worlds new possibilities new ways of thinking audible has an incredible selection with over 1 million audiobooks podcasts and audible originals all in one easy app find the genres you love and discover new ones Explore bestsellers, new releases, plus thousands of included audiobooks, podcasts, and originals that members can listen to all they want, with more added all the time.

0:47Enjoy Audible anytime while doing other things. Household chores, exercising, on the road, commuting, you name it. Audible makes it easy to be inspired and entertained as part of your everyday routine, without needing to set aside extra time. There's more to imagine when you listen. Sign up for a free 30-day Audible trial and your first audiobook is free. Visit audible.com slash built. I've stayed in awesome homes on Airbnb in places like Athens and Berlin and Rome, and each time these places have given our family a chance to feel like locals. It's the best way to travel. Picture this. You're spending a cozy evening out of town in a home you booked on Airbnb.

1:32The space is thoughtfully designed, and you think, I bet I could host my own home on Airbnb. Your home might be worth more than you think. Find out how much at Airbnb.com slash host. Your AI agents make your teams more productive, right? But if they aren't connected to the rest of your business, how productive can they really make your teams? Any business can use AI. IBM helps you use AI to change how you do business. Let's create smarter business. IBM. Hello and welcome to How I Built This Lab. I'm Guy Raz. So when you think about self-driving vehicles, you might imagine something like a robo-taxi, a car that can take you to work or school or home from a bar or a restaurant.

2:19In fact, if you live in San Francisco or Phoenix or a few other test markets, You can actually get a ride in a driverless car from a company like Waymo or Cruise. In fact, I've actually ridden in one myself, and they're actually pretty amazing. But there is a whole other industry that will be affected by autonomous vehicles as well, and that's trucking. And it's a huge part of the economy. According to the American Trucking Association, there are about three and a half million truck drivers in the U.S. But even with that many workers, there is still a huge shortage of truck drivers in this country.

2:54And that's a problem that Chris Urmson believes could be solved by autonomous vehicles. Chris's company, Aurora, is building an autonomous driving system that can operate everything from large semi-trucks to passenger cars. Chris has actually been working on autonomous vehicles for his entire professional career. He was a founding member of Google's self-driving car program, which is now Waymo, and it all started as an early fascination with science and robots. You know, as a kid, I was kind of mesmerized by the space program and the shuttle launches and, you know, enjoyed a lot of science fiction and thought robots were neat and built some out of Lego.

3:33And then as I was finishing up my computer engineering degree, I saw this poster of this robot crawling out of a volcano that had been developed by the folks at Carnegie Mellon. And I thought that was just really cool. And my girlfriend, wife now, said, you should apply. And so I did. And I got in and I got to go study robotics for five years or so. And, you know, it's exciting stuff. So you end up at Carnegie Mellon at a very interesting time because it was sort of like the beginning of the autonomous driving revolution. Most people probably were not aware of that at the time. We now know that it was.

4:18And I guess while you were there, you started to get into what would become autonomous vehicles. You started to get interested in this technology. Tell me about when you first started to kind of see this nascent industry emerging. Yeah, and it certainly wasn't then. I remember, so I had been there for a few years, and there'd been a lot of research in automated driving for decades before I got to Carnegie Mellon. And it was kind of in a bit of a lull. And I was down in Chile in the Atacama Desert with a robot that we were using to study ways you could look for signs of life on other planets. And so my PhD advisor, Red Whitaker, came down and told me about this DARPA Grand Challenge, which was this robot race from Los Angeles to Las Vegas across the desert.

5:04And he said, we're going to have to make a robot that drives 50 miles an hour across the desert. You know, I was there slow walking behind a robot, hoping it would work out in the middle of this desert down there, and thought that just sounded awesome. And so kind of shifted the focus of the research I was doing, jumped into that with two feet. And originally the mission was about how do we keep our young men and women on the supply lines out of harm's way in conflict. And that seemed like a big deal. And then over the course of three of these Defense Department competitions, the DARPA Grand Challenges, you know, it moved from driving in the desert to driving in mock urban environments.

5:42And by the end of the third one, it was clear that this technology could have a huge impact on America's roadways. Yeah, this first one in 2004, I mean, this was like, you know, sort of right in the middle of the Iraq war and DARPA was sponsoring all these different kinds of technologies, as you say, to kind of develop autonomous vehicles that could protect soldiers from, you know, being in harm's way. That first challenge, 2004, not a single vehicle, like, finished. I think one vehicle managed to go seven miles. Maybe that was yours. That was ours. No, and it was still an amazing day, right? So we stood in the grandstands at this place called Slash X, which is kind of a biker bar out in the middle of the desert.

6:22And that was where we happened to launch from. And I remember standing there, and I was part of the team that launched our robot in the morning. And you see this thing just drive off into the desert. And we happened to have this giant fin on the top of it for some reason. And you could kind of see it over the sagebrush. And as it left and it drove 40 miles an hour off into the desert. And it got, like you said, about seven and a half miles out of what was supposed to be 130 miles, I think. And the poor thing got stuck up on a berm, the wheels spinning. And the wheels were just touching the ground, so they were melting the tires and big plume of smoke coming off of it.

7:00And so it was amazing in one regard to see these things go off. And you had this kind of like sending your child off to school for the first day where it's off in the desert by itself. and then the heartbreak of the fact that you were hoping it would go 130 miles and we went seven. There was a huge leap between what happened in 2004 and 2005. 2005, a bunch of cars finished. You guys came in second to the Stanford team. What happened in that one year to make that leap in technology possible? Yeah, well, I think that what was really exciting about the challenges was that it was an opportunity to focus a bunch of research that was happening broadly and kind of bring it together on one mission, if you will.

7:46And unlike most academic work where the idea is to kind of have the concept and you get the robot to do the thing once and you shoot the video and then it doesn't matter if it ever does it again or if it ever did it before, you've kind of made the point. Here, it was truly a race. And so the thing had to be reliable enough that when you kicked it out the shoot first thing in the morning that it worked the first time and was off on its way. And so there was a lot of neat ideas we put into it. I think this was the first time where you saw the whole conglomeration of what is now a self-driving vehicle.

8:20We had LiDAR radar camera. We had machine learning. We had high-definition maps. All this stuff that is now making vehicles kind of come together in a moment to solve this problem. And it was still a bit surprising that we made as much progress as we did in those years. But there's a lot of people kind of worked very hard, you know, and enjoyed the thrill of making the thing happen. Yeah, I mean, it's so interesting because so many people have gone on to start their own autonomous vehicle companies were part of these challenges. as you, Sebastian Thrun, Kyle Votu started Cruz, Dave Ferguson founded Nuro.

8:59Both of those founders were on our show in the past. What do you think it was about those challenges that just kind of captured the imagination of this cohort of people who you know? You don't know them. Yeah, no. And it's one of the great successes, I think, of government funding, And it's kind of hit that sweet point between out there enough that it wasn't kind of a trivial commercial process, but close enough that there was a next step to be taken beyond it. And it was simple to explain. We were racing across the desert. It was technologically achievable, apparently, but it didn't feel like it on the front end.

9:45And I think there was an element of the competition part that was attractive, right? Like, you know, part of being an entrepreneur is you have to, you know, you have to want to win. You have to have the grit and determination to push through things. And so I think there's some element of kind of the human spirit part of it that enabled it to be as successful as it has been. Going back to that time, was it clear to you that this was the future of travel, of driving? I would love to say yes, but the honest answer is not in 2004, 2005. For me at the time, it started out as this is really cool. This is an amazing technology.

10:26I get to go drive Humvees in the desert and lasers and cameras and computing. It was just exciting and interesting and very cool. And then as I started to learn about the challenges our troops were facing out in the world and how complicated supply lines are, you know, and how vulnerable our troops are while they're operating those vehicles and how much, you know, we lost more people on the supply line than we did on the front line in Iraq. Yeah. And so that became, okay, I get it, this matters. And then the 2007 challenge was a little different, so it was the urban challenge. And here, instead of driving down a trail in the desert, we were driving on a retired air base, so on the road, and we had to be on our side of the road and got to collaborate with General Motors and Continental for the first time.

11:12And starting to talk to them and kind of widening the aperture to start to think about, oh, geez, like this is actually broadly applicable. And there's a chance here to take a real bite out of the 40 some thousand Americans who die on the roads and make it more accessible. It started to really gel and then really became clear to me how important this was and how transformational this will be for society and for the economy and how important it is that we actually see this technology make it to market. All right. So before we sort of go down that rabbit hole too deeply, just give me a sense of why, of how you think self-driving vehicles will make our lives better.

11:55So when I look at self-driving vehicles, first we see the opportunity for safety. 40 ,000 Americans, 1.5 million people killed globally in traffic accidents. It's a pandemic. And it's something we can address. And this is the technology that will address that while continuing to give people the freedom that they expect and want to be able to move through the world easily and freely. I do expect that we will give freedom back to people who have lost the ability or right to move around, whether it's because of illness or injury or age. There's some people who aren't or shouldn't be driving. And in our society, if you can't drive to get somewhere, you become isolated.

12:36And that has devastating social and physical impacts on people. So keeping generations engaged together, I think, is incredibly valuable. And we should be able to level the accessibility of transportation, that cars are only becoming more expensive. by providing ubiquitous, highly efficient, clean, safe transportation, we'll be able to level the social playing field for all of society. We're going to take a quick break, but when we come back, how Chris Urmson helped start Google's secret self-driving vehicle program and why he eventually left that job to found his own self-driving vehicle company, Aurora.

13:16Stay with us. You're listening to How I Built This Lab.

13:23One of the coolest things I did last summer was take my family to Athens, where we saw the Parthenon and the Agora and all those amazing neighborhoods and ancient historical sites. And one of the things that made it so awesome was the home we booked on Airbnb. We literally had a view of the Parthenon from our bedroom window. There was a hot tub on the top floor. We could sit in it overlooking the entire city. And we had a kitchen and access to markets. And we were in walking distance from all of the things you would want to see. It made the trip so, so amazing. And when you take your own vacation, that's actually a great time to host your home on Airbnb.

14:02Your place with your cool art collection and your handy kitchen gadgets. It might just be what someone else needs to feel right at home on their next trip. Plus, your earnings from hosting provide you with another income stream and could even help offset the cost of your next trip. Your home might be worth more than you think. Find out how much at airbnb.com slash host. This show is brought to you by American Express. Running a business means making countless choices every day, some small and some that can change everything. The business owners who thrive are the ones who are ready for whatever comes next.

14:41And having the right support behind those decisions can make all the difference. That's why so many business owners I talk to choose the American Express Business Platinum Card. It's built to help them move quickly and take their business further. And with five times membership rewards points on flights and prepaid hotels booked through Amextravel.com, you can turn any business trip into a chance to earn more and invest in your business's future. Plus, you get a flexible spending limit that changes as your business does, adapting to where you are and where you're headed next. Because when it comes to growing your business, there's truly nothing like Business Platinum.

15:25Not all purchases will be approved. Terms apply. Learn more at go.amex.com. You know, one of the most surprising things about how I built this is just how many pitches we get every year. tens of thousands of businesses reach out hoping to tell their story. Now, while we do try to read most of those pitches, we can't possibly read all, but we choose most of our guests through our own deep research. And that means my team and I spend hundreds of hours digging into companies, what they make, who's behind them, and whether their journey can inspire you. And that's exactly where Claude has become such an incredible thinking partner in my creative process.

16:07Claude is the AI for minds that don't stop at good enough, the thinking partner that works with you to explore the things that fascinate you. Whether you're researching late-night curiosity spirals or working through complex creative challenges, Claude extends your thinking to tackle the problems together. For example, imagine I'm about to sit down with a founder of a snack company. I'll want to know what products they've released, how they've evolved, and which competitors they're up against. In the past, it could take hours to track down reliable details. We'd search articles, databases, reports.

16:42Now, Claude can give me a clear answer in seconds, and then I can decide what to dig into further. It doesn't replace my process, but it sharpens it. And that means I can spend more time doing what I love most, focusing on the human stories, the lessons, the decisions, and the struggles behind the businesses you hear on this show. Experience what collaborative thinking feels like at claude.ai.hibt and see why the world's best problem solvers choose Claude as their thinking partner. One more thing before we get back to the show, please make sure to click the follow button on your podcast app so you never miss a new episode of the show.

17:28It's usually just at the top of the app and it's totally free.

17:40Welcome back to How I Built This Lab. I'm Guy Raz, and I'm talking with Chris Urmson, founder of Aurora. All right, so after these DARPA challenges, you were recruited to go work for Google by Sebastian Thrun, who was kind of like one of your rivals during these competitions. He was the head of the Stanford team in these DARPA challenges. and I guess he recruited you to come work at Google on this secret project at the time, which was an autonomous vehicle project. Tell me about, how did they describe it to you at the time? Yeah, so this was 2009 was when I started Google. And so Sebastian and I had been competing in these challenges, but it was a friendly rivalry.

18:25We all kind of got that this, there was a race, but it was about moving this technology forward. And we had talked about doing something together and thought about a couple of different ideas. And eventually, Larry Page had said to Sebastian, you know, why would you do this outside? We, you know, we want to do this at Google. Let's put a team together. And so I was there to help found the team at Google. And it was a very secret project. Nobody knew that we were doing it because they wanted to be able to take a risk and try something out there and see how it went. And it kind of had this Dread Pirate Roberts feeling to it.

19:04When I signed up, they said, we'll give you two years to go do this, and then we'll probably fire you. But it should be fun in the interim. And so my wife and I and our kids moved out from Pittsburgh to the Bay Area. and at the time it was a very difficult decision because I'd just joined the faculty at Carnegie Mellon and that had kind of been my aspiration up to that point. And like, well, you know, when are we going to have a chance to go visit with the crazy people in California and wear Birkenstocks and all that? And, you know, but it felt like a difficult decision and in retrospect it was probably should have been the easiest decision of my life.

19:39Well, as somebody who's wearing Birkenstocks right now, I can say that was probably a good decision because they're great shoes. Exactly. But seriously, so you get to Google and the challenge is what? I mean you were given a challenge to create a fully autonomous vehicle like that can go on the roads. What did they tell you they wanted to accomplish? Yeah. So one of the brilliant things they did was take the DNA of the DARPA challenges and kind of bring it internally. And so we were given two goals, really, to drive 100 ,000 miles on public roads and then to drive 1 ,000 miles of very specific roads that Larry Page and Sergey Brin had kind of picked out as ways to kind of make sure that we had both the breadth and depth of performance.

20:25And from that, we'd be able to figure out, like, is this 50 years away or is it 5 to 10 years away? And thus whether it's worth kind of a company spending resources on it. And so, you know, the 100 ,000 miles was pretty straightforward. We mapped a part of the freeway in the Bay Area here. We had a bunch of cars that just kind of went up and down it. And we learned from that and refined it. And then the other was driving 1 ,000 miles of really interesting roads where we'd have to kind of push the capabilities so we could really understand, like, is this viable? And so it was things like driving around Tiburon.

21:02Tiburon is sort of a peninsula in the Bay. It's just north of San Francisco for people who aren't familiar with it. Yeah, I mean it's a tiny, tiny road that just kind of leads to the town and goes around the peninsula and that's it. It's actually – for part of it is one lane for both directions, which is fun. And then there's another road called Page Mill here, which is this windy road that winds out of Palo Alto up to the top of the mountains here. And it's a very popular road for cyclists. I ride there pretty regularly. So, you know, a nice breadth of different types of roads and driving. And so we ultimately completed both the 100 ,000 miles and this 1 ,000 miles of interesting roads within about 18 months of starting.

21:45I mean, at the time, did you feel like it's just a matter of time, just a matter of, you know, maybe a few years before this is normal, this is deployed everywhere, we're going to see this all over the place? Or did you still think it was a long road ahead? No, I think it was clear that both were true, that this was going to happen and that there was a lot of work to be done. And I think in 2012, I said something about working to make sure that we had self-driving vehicles before my son had to get his driver's license. And so we missed that by a little bit. And I didn't miss it by much because my older son still hasn't got his license.

22:20And my younger son just got his license two weeks ago. So, you know, I feel like in the grand scheme of things, that doesn't feel like a terrible estimate in retrospect. Yeah. But, you know, what's exciting is that today, you know, in Phoenix, in San Francisco, in L.A., you're actually able to get a ride in a self-driving vehicle. Yeah. I mean, I've been in one of those vehicles in San Francisco and you see them driving around. And it's still quite amazing to see a vehicle with not a single human inside just driving the streets. And, of course, they're not perfect yet, but it is pretty amazing to see it.

22:59It is. And it's one of these things that will have a profoundly positive impact on society. All right. So you eventually left Google to start your own company. and tell me a little bit about, first of all, what makes Aurora different from your competitors because there are obviously many of your competitors you know, you've known for a long time, who are working on similar types of technology. Yeah, I think when we founded the company, part of the thesis was if we brought the right people together with the right experience and the business model and kind of the collaborative spirit that we could actually have a bigger impact than trying to build something in isolation and be a disruptor, quote unquote.

23:49And so for us, we're focused initially on trucking. We see that as a gigantic, exciting market where long haul truck drivers, they're 10 times more likely to die at work than an average American. And they spend all this time away from home and they don't get to see their kids or their wives or their husbands. And so helping goods move more efficiently, helping that become lower cost over time, we can have a huge impact on while addressing this critical shortage of drivers we have and helping the U.S. economy. And that's good for all of us. And then we've made some really important technological bets.

24:24So one of the core technologies we have at the company is we call it First Light, which is the special LiDAR technology. So LiDAR is using light like radar, and it allows us to see farther than other people can and see how fast things are moving instantly. And so for driving trucks, you have to see a long way down the road. And First Light enables us to do that. And then there's a variety of other exciting ways we've folded machine learning and AI with classical algorithms to make our system really robust and human-like in the way it drives. Can you sort of explain the difference between developing a driver that can handle a semi, a large truck and a driver that is driving a taxi?

25:08Is it a different type of technology that you have to develop for a long haul truck? So if you think about it up front, there's a lot of commonality. And in fact, our technology can drive light vehicles and big trucks, but there's a few big differences. So one is if you're driving at relatively low speeds in a city, then you don't have to look as far ahead because it doesn't take you as long to stop and everything's moving a bit slower. And then if something breaks, you can basically just kind of stop where you are, kind of move a little bit to the right and everybody's kind of moving slowly. So it's not that big a deal.

25:46Whereas if you're driving a truck down the freeway at 65 miles an hour, you have to be looking out 400, 400 plus meters to see what's happening because there's so much momentum and inertia with that thing. And you can't just kind of stop in a freeway lane. You have to be pulling to the edge of the road whenever possible and getting out of the way. And so the way we've architected our system is that it can span from the high-speed stuff and the trucks down to the light vehicles as well. And if you think about a, you know, if you want to become a truck driver, you have to be able to drive a car first, right?