Chris Urmson: Self-Driving Cars at Aurora, Google, CMU, and DARPA

Chris Urmson was the CTO of the Google Self-Driving Car team, a key engineer and leader behind the Carnegie Mellon autonomous vehicle entries in the DARPA grand challenges and the winner of the DARPA urban challenge. Today he is the CEO of Aurora Innovation, an autonomous vehicle software company he started with Sterling Anderson, who was the former director of Tesla Autopilot, and Drew Bagnell, Uber’s former autonomy and perception lead. This conversation is part of the Artificial Intelligence podcast. If you would like to get more information about this podcast go to https://lexfridman.com/ai or connect with @lexfridman on Twitter https://twitter.com/lexfridman, LinkedIn https://www.linkedin.com/in/lexfridman/, Facebook https://www.facebook.com/lexfridman, Medium https://medium.com/@lexfridman, or YouTube https://www.youtube.com/lexfridman where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on iTunes or support it on Patreon https://www.patreon.com/lexfridman.

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

• 0:00Lex Fridman?

  The following is a conversation with Chris Armsen. He was a CTO of the Google self-driving car team, a key engineer and leader behind the Carnegie Mellon University autonomous vehicle entries in the DARPA Grand Challenges and the winner of the DARPA Urban Challenge. Today, he's the CEO of Aurora Innovation, an autonomous vehicle software company he started with Sterling Anderson, who was the former director of Tesla Autopilot, and Drew Bagnell, Uber's former autonomy and perception lead. Chris is one of the top roboticists and autonomous vehicle experts in the world and a longtime voice of reason in a space that is shrouded in both mystery and hype. He both acknowledges the incredible challenges involved in solving the problem of autonomous

• 0:45Lex Fridman?

  driving and is working hard to solve it. This is the Artificial Intelligence Podcast. If you enjoy it, subscribe on YouTube, give it five stars on iTunes, support it on Patreon, or simply connect with me on Twitter at @LexFriedman, spelled F-R-I-D-M-A-N. And now, here's my conversation with Chris Armsen.

• 1:25Lex Fridman?

  You were part of both the DARPA Grand Challenge and the DARPA Urban Challenge teams at CMU with Red Whitaker. What technical or philosophical things have you learned from these races?

• 1:38Speaker 01

  I think the high-order bit was that it could be done. I think that was the thing that was incredible about the, first, the Grand Challenges, that I remember, you know, I was a grad student at Carnegie Mellon, and there we, it was kind of this dichotomy of...

• 2:01Speaker 01

  It seemed really hard, so that would be cool and interesting. But, you know, at the time, we were the only robotics institute around. And so, you know, if we went into it and fell on our faces, that would be embarrassing. So I think, you know, just having the will to go do it, to try to do this thing that at the time was marked as, you know, darn near impossible. And then after a couple of tries, be able to actually make it happen. I think that was, you know, that was really exciting.

• 2:28Lex Fridman?

  But at which point did you believe it was possible? Did you, from the very beginning, did you personally? Because you're one of the lead engineer, you actually had to do a lot of the work.

• 2:38Speaker 01

  Yeah, I was the technical director there and did a lot of the work, along with a bunch of other really good people. Did I believe it could be done? Yeah, of course. Right? Like, why would you go do something you thought was impossible, completely impossible? We thought it was going to be hard. We didn't know how we're going to be able to do it. We didn't know if we'd be able to do it the first time. Turns out we couldn't. That, yeah, I guess you have to. I think there's a certain benefit to naivete, right? That if you don't know how hard something really is, you try different things and, you know, it gives you an opportunity that others who are, you know, wiser, maybe don't have.

• 3:20Lex Fridman?

  What were the biggest pain points? Mechanical, sensors, hardware, software, algorithms for mapping, localization, just general perception control, like hardware, software, first of all?

• 3:31Speaker 01

  I think that's the joy of this field, is that it's all hard. And that you have to be good at each part of it. So for the first, for the urban challenges, if I look back at it from today, it should be easy today. That, you know, it was a static world. There weren't other actors moving through it, is what that means. It was out in the desert, so you get really good GPS.

• 4:03Speaker 01

  You know, so that that went and you know, we could map it roughly. And so in retrospect, now it's, you know, it's it's within the realm of things we could do back then.

• 4:14Speaker 01

  Just actually getting the vehicle and the, you know, there's a bunch of engineering work to get the vehicle so that we could control it and drive it. That's, you know, that's still a pain today, but it was even more so back then. And then the uncertainty of exactly what they wanted us to do was was part of the challenge as well.

• 4:33Lex Fridman?

  Right. You didn't actually know the track heading in. You knew approximately, but you know, didn't actually know the route, the route that is going to be taken.

• 4:39Speaker 01

  That's right. We didn't know the route and we didn't even really, the way the rules have been described, you had to kind of guess. So if you think back to that challenge, the idea was to, that the government would give us, the DARPA would give us a set of waypoints and kind of the width that you had to stay within between the line that went between, you know, each of those waypoints. And so the the most devious thing they could have done is set, you know, a kilometer wide corridor across, you know, a field of scrub brush and rocks and said, you know, go figure it out. Fortunately, it really, it turned into basically driving along a set of trails, which is much more relevant to to the application they were looking for.

• 5:25Speaker 01

  But no, it was, it was a hell of a thing back in the day.

• 5:28Lex Fridman?

  So the legend, Red, was kind of leading that effort in terms of just broadly speaking. So you're a leader now. What have you learned from Red about leadership?

• 5:41Speaker 01

  I think there's a couple of things. One is, you know, go and try those really hard things. That's where there is an incredible opportunity. I think the other big one, though, is to see people for who they can be, not who they are. It's one of the things that I actually, one of the deepest lessons I learned from Red was that he would look at, you know, undergraduates or graduate students and empower them to be leaders, to, to, you know, have responsibility, to do great things. That I think. Another person might look at them and think, oh, well, that's just, you know, an undergraduate student. What could they know?

• 6:24Speaker 01

  And so I think that, that, you know, kind of trust but verify, have confidence in what people can become, I think, is a really powerful thing.

• 6:32Lex Fridman?

  So through that, let's just like fast forward through the history. Can you maybe talk through the technical evolution of autonomous vehicle systems from the first two grand challenges to the urban challenge to today?

• 6:47Speaker 01

  Sure.

• 6:47Lex Fridman?

  Are there major shifts in your mind, or is it the same kind of technology just made more robust?

• 6:53Speaker 01

  I think there's been some big, big steps. So the, for the grand challenge, the real technology that unlocked that was HD mapping. Prior to that, a lot of the off-road robotics work had been done without any real prior model of what the vehicle was going to encounter. And so that innovation, that the fact that we could get, you know, decimeter resolution models was really a big deal. And that allowed us to, to kind of bound the complexity of the driving problem the

• 7:35Speaker 01

  vehicle had and allowed it to operate at speed because we could assume things about the environment that it was going to encounter. So that was a, that was one of the, that was the big step there. For the urban challenge, you know, one of the big technological innovations there was the multi-beam LiDAR. And be able to generate high-resolution, you know, mid to long-range 3D models the world and use that for, you know, for understanding the world around the vehicle. And that was really a, you know, kind of a game-changing technology.

• 8:15Speaker 01

  In parallel with that, we saw a bunch of other technologies that had been kind of converging, half their day in the sun. So Bayesian estimation had been, you know, SLAM had been a big field in robotics. You know, you would go to a conference, you know, a couple of years before that and every paper would effectively have SLAM somewhere in it. And so seeing that, you know, that Bayesian estimation techniques, you know, play out on a very visible stage, you know, I thought that was, that was pretty exciting to see.

• 8:53Lex Fridman?

  And mostly SLAM was done based on LiDAR at that time?

• 8:57Speaker 01

  Uh, well, yeah, and in fact, we weren't really doing SLAM per se, you know, in real time because we had a model ahead of time, we had a roadmap, but we were doing localization. And we're using, you know, the LiDAR or the cameras, depending on, you know, who exactly was doing it, to localize to a model of the world. And I thought that was, that was a big step from kind of naively trusting GPS INS before that. And again, like lots of work had been going on in this field. Certainly this was not doing anything particularly innovative in SLAM or in localization, but it was seeing that technology necessary in a real application on a big stage, I thought was very cool.

• 9:39Lex Fridman?

  So for the urban challenge, there was already maps constructed offline?

• 9:42Speaker 01

  Yes.

• 9:43Lex Fridman?

  In general, okay. And did people do that, did individual teams do it individually? So they had their own different approaches there? Or did everybody kind of share that information, at least intuitively?

• 9:59Speaker 01

  So DARPA gave all the teams a model of the world, a, you know, a map, and then...

• 10:07Speaker 01

  You know, one of the things that we had to figure out back then was, and it's still one of these things that trips people up today, is actually the coordinate system. So you get a latitude, longitude, and you know, to so many decimal places, you don't really care about kind of the ellipsoid of the earth that's being used. But when you want to get to 10 centimeter or centimeter resolution, you care whether the coordinate system is, you know, NAD 83, or WGS 84, or, you know, these are different ways to describe both the kind of non-sphericalness of the earth, but also, kind of, in, I think, I can't remember which one, the tectonic shifts that are happening and how to transform,

• 10:51Speaker 01

  you know, the global datum as a function of that. So you're getting a map and then actually matching it to reality to centimeter resolution, that was kind of interesting and fun back then.

• 11:00Lex Fridman?

  So how much work was the perception doing there? So how, how much were you relying on localization based on maps without using perception to register to the maps? And how, I guess the question is, how advanced was perception at that point?

• 11:15Speaker 01

  Yeah. It's certainly behind where we are today, right? We're more than a decade since the urban challenge. But the core of it was there. That we were tracking vehicles, we had to do that at 100-plus meter range because we had to merge with other traffic. We were using, you know, again, Bayesian estimates for state of these vehicles. We had to deal with a bunch of the problems that you think of today, of predicting what that, where that vehicle's going to be a few seconds into the future. We had to deal with the fact that there were multiple hypotheses for that because a vehicle at an intersection might be going right, or it might be going straight, or it might be making a left turn.

• 11:57Speaker 01

  And we had to deal with the challenge of the fact that our behavior was going to impact the behavior of that other operator. And, you know, we did a lot of that in relatively naive ways, but it kind of worked.

• 12:11Lex Fridman?

  Still had to have some kind of solution. And so where does that, 10 years later, where does that take us today? From that artificial city construction to real cities to the urban environment?

• 12:23Speaker 01

  Yeah, I think the biggest thing is that the, you know, the actors are truly unpredictable.

• 12:31Speaker 01

  That most of the time, you know, the drivers on the road, the other road users are out there behaving well, but every once in a while they're not. The variety of of other vehicles is, you know, you have all of them.

• 12:48Lex Fridman?

  In terms of behavior, in terms of perception, or both?

• 12:52Speaker 01

  Both. That we have, you know, back then, we didn't have to deal with cyclists, we didn't have to deal with pedestrians, didn't have to deal with traffic lights. You know, the scale over which that you have to operate is now, you know, is much larger than, you know, the airbase that we were thinking about back then.

• 13:08Lex Fridman?

  So what, easy question. What do you think is the hardest part about driving?

• 13:15Speaker 01

  Easy question.

• 13:16Lex Fridman?

  Yeah. No, I'm joking. I'm sure nothing really jumps out at you as one thing, but in the jump from the urban challenge to the real world, is there something that's a particular, you foresee a very serious, difficult challenge?

• 13:34Speaker 01

  I think the most fundamental difference is that we're doing it for real. That in that environment, it was both a limited complexity environment because certain actors weren't there, because, you know, the roads were maintained, there were barriers keeping people separate from from robots at the time. And it only had to work for 60 miles, which, looking at it from, you know, 2006, it had to work for 60 miles.

• 14:03Lex Fridman?

  Yeah.

• 14:04Speaker 01

  Right? Looking at it from now, you know, we want things that will go and drive for, you know, half a, half a million miles. And, you know, it's just a, it's a different game.

• 14:16Lex Fridman?

  So how important, you said LiDAR came into the game early on, and it's really the primary driver of autonomous vehicles today as a sensor. So how important is the role of LiDAR in the sensor suite in the near term?

• 14:30Speaker 01

  So I think it's, I think it's essential. You know, I believe, but I also believe that cameras are essential and I believe the radar is essential. I think that you, you really need to use the composition of data from, from these different sensors if you want the thing to, to really be robust.

• 14:48Lex Fridman?

  The question I want to ask, let's see if we can untangle it, is what are your thoughts on the Elon Musk provocative statement that LiDAR is a crutch? That is a kind of, I guess, growing pains and that much of the perception task can be done with cameras?

• 15:08Speaker 01

  So I think it is undeniable that people walk around without, you know, lasers in their foreheads and they can get into vehicles and drive them. And, and so there's an existence proof that you can drive using, you know, passive vision. No doubt, can't argue with that.

• 15:28Lex Fridman?

  In terms of sensors, yeah.

• 15:30Speaker 01

  Yeah, in terms of sensors, right? So like, there's, there's an example that, you know, we all go do it, many of us every day. In terms of LiDAR being a crutch, sure. But, but, you know, in the same way that, you know, the combustion engine was a crutch on the path to an electric vehicle, in the same way that, you know, any technology ultimately gets replaced by some superior technology in the future. And really, what, the way that I look at this is that the way we get around on the ground, the way that we use transportation is broken. And that we have, you know, this, this, you know, what was,

• 16:14Speaker 01

  I think the number I saw this morning, 37,000 Americans killed last year on our roads. And that's just not acceptable. And so tech, any technology that we can bring to bear that accelerates the, this techno, you know, self-driving technology coming to market and saving lives is technology we should be using. And it feels just arbitrary to say, well, you know, I'm, I'm not okay with using lasers because that's whatever, but I am okay with using an eight megapixel camera or a 16 megapixel camera. You know, like it's just, these are just bits of technology and we should be taking the best technology from the tool bin that allows us to go. And you know, and solve a problem.

• 16:57Lex Fridman?

  The question I often talk to, well, obviously you do as well to automotive companies. And you know, if there's one word that comes up more often than anything is cost and trying to drive costs down. So while it's it's true that it's a tragic number, the 37,000. The question is, what, and I'm not the one asking this question because I hate this question, but we want to find the cheapest sensor suite that creates a safe vehicle. So in that uncomfortable trade off, do you foresee LiDAR coming down in cost in the future?

• 17:39Lex Fridman?

  Or do you see a day where level four autonomy is possible without LiDAR?

• 17:46Speaker 01

  I see both of those, but it's really a matter of time. And I think really, maybe the I would talk to the question you asked about, you know, the cheapest sensor. I don't think that's actually what you want. What you want is a sensor suite that is economically viable. And then after that, everything is about margin and driving cost out of the system. What you also want is a sensor suite that works.

• 18:10Lex Fridman?

  Right.

• 18:11Speaker 01

  And so it's great to tell a story about how, you know, how it would be better to have a self-driving system with a $50 sensor instead of a, you know, a $500 sensor. But if the $500 sensor makes it work and the $50 sensor doesn't work, you know, who cares? As long as you can actually, you know, have an economic, you know, there's an economic opportunity there. And the economic opportunity is important because that's how you actually have a sustainable business and that's how you can actually see this come to scale and be out in the world. And so when I look at LiDAR.

• 18:52Speaker 01

  I see a technology that has no underlying fundamentally, you know, expense to it, fundamental expense to it. It's, it's going to be more expensive than an imager because, you know, CMOS processes or, or, you know, FAB processes are dramatically more scalable than mechanical processes. But we still should be able to drive cost down substantially on that side. And then I also do think that with the right business model, you can absorb more, you know, certainly more cost on the bill of materials.

• 19:25Lex Fridman?

  Yeah, if the sensor suite works, extra value is provided thereby. You don't need to drive cost down to zero. It's the basic economics. You've talked about your intuition that level two autonomy is problematic because of the human factor of vigilance, decrement, complacency, overtrust and so on, just us being human. We overtrust the system, we start doing even more so partaking in the secondary activities like smartphone and so on. Have your views evolved on this point in either direction? Can you, can you speak to it?

• 20:00Speaker 01

  So, and I want to be really careful because sometimes this gets twisted in a way that's, that I certainly didn't intend. So, active safety systems are a really important technology that we should be pursuing and integrating into vehicles. And there's an opportunity in the near term to reduce accidents, reduce fatalities, and that's, and we should be, we should be pushing on that. Level two systems are systems where the vehicle is controlling two axes. So, you know, braking and braking and throttle slash steering. And I think there are variants of level two systems that are supporting the driver that

• 20:45Speaker 01

  absolutely like we should, we should encourage to be out there. Where I think there's a real challenge is in. The the human factors part around this and the misconception from the public around the capability set that that enables and the trust they should have in it. And that is where I, you know, I kind of, I I am actually incrementally more concerned around level three systems and, you know, how exactly a level two system is marketed and delivered and, you know, how people, how much effort people have put into those human factors. So I still believe several things around this. One is people will overtrust the technology. We've seen over the last few weeks, you know, a spate of people sleeping

• 21:30Speaker 01

  in their Tesla. You know, I watched an episode last night of Trevor Noah talking about this and, you know, him, you know, this is a smart guy who's has a lot of resources at his disposal describing a Tesla as a self-driving car and that why shouldn't people be sleeping in their Tesla? It's like, well, because it's not a self-driving car and it is not intended to be. And, you know, these people will almost certainly, you know, die at some point or or hurt other people. And so we need to really be thoughtful about how that technology

• 22:09Speaker 01

  is described and brought to market. I also think that because of the economic issue, you know, economic challenges we were just talking about, that that technology path will all the these level two driver assistance systems, that technology path will diverge from the technology path that we need to be on to actually deliver truly self-driving vehicles, ones where you can get in it and sleep and have the equivalent or better safety than, you know, a human driver behind the wheel. Because the, again, the economics are very different in those two worlds. And so that leads to, you know, divergent technology.

• 22:48Lex Fridman?

  So you you just don't see the economics of gradually increasing from level two and doing so quickly enough to where it doesn't cause safety, critical safety concerns. You believe that that it needs to diverge at this point into different, basically different routes.

• 23:06Speaker 01

  And really, that comes back to what are those L2 and L1 systems doing? And they are driver assistance functions where the the people that are marketing that responsibly are being very clear and putting human factors in place such that the driver is actually responsible for the vehicle and that the technology is there to support the driver. And the safety cases that are built around those are dependent on that driver attention and attentiveness. And at that point, you you can kind of give up to some degree, for economic reasons, you can give up on, say, false negatives. And so and the way to think

• 23:51Speaker 01

  about this is, for a four collision mitigation braking system, if it, half the times the driver missed a vehicle in front of it, it hit the brakes and brought the vehicle to a stop, that would be an incredible, incredible advance in in safety on our roads, right? That would be equivalent to seat belts. But it would mean that if that vehicle wasn't being monitored, it would hit one out of two cars. And so economically, that's a perfectly good solution for a driver assistance system. What you should do at that point, if you can get it to work 50% of the time, is drive the cost out of that so you can get it on as many vehicles as possible. But driving the cost out of it doesn't drive up performance

• 24:33Speaker 01

  on the false negative case. And so you'll continue to not have a technology that could, you know, really be available for for a self driven vehicle.

• 24:41Lex Fridman?

  So clearly, the communication, and this probably applies to all four vehicles as well, the marketing and the communication of what the technology is actually capable of, how hard it is, how easy it is, all that kind of stuff, is highly problematic. So but say, everybody in the world was perfectly communicated and were made to be completely aware of every single technology out there, what they what it's able to do. What's your intuition, and now we're maybe getting into philosophical ground, is it possible to have a Level 2 vehicle where we don't over-trust it?

• 25:20Speaker 01

  I don't think so. If people truly understood the risks and internalized it, then sure, you could do that safely, but that's a world that doesn't exist. That people are going to, if the facts are put in front of them, they're going to then combine that with their experience. And let's say they're using an L2 system and they go up and down the 101 every day, and they do that for a month, and it just worked every day for a month. That's pretty compelling. At that point, even if you know the statistics, you're like, "Well, I don't know, maybe there's something a little funny about those.

• 26:01Speaker 01

  Maybe they're driving to difficult places. I've seen it with my own eyes, it works." And the problem is that that sample size that they have, so it's 30 miles up and down, so 60 miles times 30 days, so 60, 180, 1,800 miles.

• 26:17Speaker 01

  That's a drop in the bucket compared to the, what, 85 million miles between fatalities. And so they don't really have a true estimate based on their personal experience of the real risks, but they're going to trust it anyway, because it's hard not to. It worked for a month. What's going to change?

• 26:34Lex Fridman?

  So even if you start a perfect understanding of the system, your own experience will make it drift. I mean, that's a big concern. Over a year, over two years even, it doesn't have to be months.

• 26:45Speaker 01

  And I think that as this technology moves from,

• 26:51Speaker 01

  what I would say is kind of the more technology savvy ownership group to the mass market, you may be able to have some of those folks who are really familiar with technology, they may be able to internalize it better, and your immunization against this kind of false risk assessment might last longer. But as folks who aren't as savvy about that, read the material and they compare that to their personal experience, I think there, it's going to...

• 27:22Speaker 01

  It's going to move more quickly.

• 27:24Lex Fridman?

  So your work, the program that you've created at Google and now at Aurora, is focused more on the second path of creating full autonomy. So it's such a fascinating. I think it's one of the most interesting AI problems of the century. Right. It's a, I just talked to a lot of people, just regular people, I don't know, my mom, about autonomous vehicles and you begin to grapple with ideas of giving your life control over to a machine is philosophically interesting, is practically interesting. So let's talk about safety. How do you think we demonstrate? You've spoken about metrics in the past.

• 28:04Lex Fridman?

  How do you think we demonstrate to the world that an autonomous vehicle and Aurora system is safe?

• 28:12Speaker 01

  This is one where it's difficult because there isn't a soundbite answer. That we have to show a combination of

• 28:21Speaker 01

  work that was done diligently and thoughtfully. And this is where something like a functional safety process is part of that is like here's, here's the way we did the work. That means that we were very thorough. So, you know, if you believe that we, what we said about this is the way we did it, then you can have some confidence that we were thorough in, in, in the engineering work we put into the system. And then on top of that, the, you know, to kind of demonstrate that we weren't just thorough, we were actually good at what we did.

• 28:51Speaker 01

  There'll be a kind of a collection of evidence in terms of demonstrating that the capabilities work the way we thought they did. You know, statistically and to whatever degree we can, we can demonstrate that both in some combination of simulation, some combination of, of unit testing and decomposition testing. And then some part of it will be on road data.

• 29:14Speaker 01

  And I think the way we're will ultimately convey this to the public is there'll be clearly some conversation with the public about it, but we'll, you know, kind of invoke the kind of the trusted nodes and that we'll spend more time being able to go into more depth with folks like NHTSA and other federal and state regulatory bodies. And kind of, given that they are operating in the public interest and they're trusted, that if we can, you know, show enough work to them that they're convinced, then, you know, I think we're in a, in a pretty good place.

• 29:50Lex Fridman?

  That means you work with people that are essentially experts at safety to try to discuss and show, do you think the answer is probably no, but just in case, do you think there exists a metric? So currently, people have been using number of disengagements.

• 30:03Speaker 01

  Yeah.

• 30:04Lex Fridman?

  And it quickly turns into a marketing scheme to just sort of you alter the experiments you run to adjust. I think you've spoken that you don't like.

• 30:12Speaker 01

  Don't love it. No, in fact, I was on the record telling DMV that I thought this was not a great metric.

• 30:18Lex Fridman?

  Do you think it's possible to create a metric, a number that, that could demonstrate safety outside of fatalities?

• 30:28Speaker 01

  So, so I do. And I think that it won't be just one number. So as we are internally grappling with this, and at some point, we'll be, we'll be able to talk more publicly about it, is how do we think about human performance in different tasks, say, detecting traffic lights or safely making a left turn across traffic? And what do we think the failure rates are for those different capabilities for people? And then demonstrating to ourselves and then ultimately, folks in regulatory role and then ultimately the public, that we have confidence that our system will work better than that. And so these,

• 31:11Speaker 01

  these individual metrics will kind of tell a compelling story ultimately. I do think at the end of the day, what we care about in terms of safety is lives saved and injuries reduced. And then, and then ultimately, you know, kind of casualty dollars. That people aren't having to pay to get their car fixed. And I do think that you can, you know, in aviation, they look at a kind of an event pyramid where, you know, a crash is at the top of that and that's the worst event, obviously. And then there's injuries and, you know, near miss events and whatnot and, and, you know, violation of operating procedures and you kind of build a statistical model

• 31:56Speaker 01

  of, of the relevance of the low severity things, the high severity things. I think that's something where we'll be able to look at as well. Because, you know, an event per 85 million miles is, you know, statistically a difficult thing, even at the scale of the US, to, to, to kind of compare directly.

• 32:15Lex Fridman?

  And that event, the fatality that's connected to an autonomous vehicle is significantly, at least currently magnified in the amount of attention and guess. So that speaks to public perception. I think the most popular topic about autonomous vehicles in the public is the trolley problem formulation, right? Which has, let's not get into that too much, but is misguided in many ways. But it speaks to the fact that people are grappling with this idea of giving control over to a machine. So how do you win the, the hearts and minds of the people that autonomy is something

• 32:59Lex Fridman?

  that could be a part of their lives?

• 33:01Speaker 01

  I think you let them experience it, right? I think it's, I think, I think it's right. I think people should be skeptical. I think people should ask questions. I think they should doubt because this is something new and different. They haven't touched it yet and I think it's perfectly reasonable and, but at the same time, it's clear there's an opportunity to make the road safer. It's clear that we can improve access to mobility. It's clear that we can reduce the cost of mobility. And that once people try that and are, you know, understand that it's safe and are able to use in their daily lives, I think it's one of these things that will, will just be

• 33:43Speaker 01

  obvious. And I've seen this practically in, you know, demonstrations that I've, you know, given where I've had people come in and, you know, they're very skeptical and they get in a vehicle. You know, my favorite one is taking somebody out on the freeway and we're on the 101 driving at 65 miles an hour. And after 10 minutes, they kind of turn and ask, is that all it does? And you're like, it's a self-driving car. I'm not sure exactly what you thought it would do, right? But they, you know, it becomes mundane, which is, which is exactly what you want a technology like this to be, right? We don't really, when I turn the light switch on in here, I don't think about the complexity of, you know,

• 34:26Speaker 01

  the, those electrons, you know, being pushed down a wire from wherever it was and being generated. Like, it's just, it's like, I just get annoyed if it doesn't work, right? And, and what I value is the fact that I can do other things in this space. I can, you know, see my colleagues. I can read stuff on a paper. I can, you know, not be afraid of the dark. And, and I think that's what we want this technology to be like, is it's, it's in the background and people get to have those, those life experiences and do so safely.

• 34:54Lex Fridman?

  So putting this technology in the hands of people speaks to scale of deployment. Right? So what do you think? The, the dreaded question about the future, because nobody can predict the future.

• 35:08Speaker 01

  Yeah.

• 35:09Lex Fridman?

  But just maybe speak poetically about when do you think we'll see a large scale deployment of autonomous vehicles, 10,000, those kinds of numbers?

• 35:22Speaker 01

  We'll see that within 10 years. I'm pretty confident. We

• 35:30Lex Fridman?

  What's an impressive scale? What moment, so you've done the DARPA challenge where there's one vehicle. At which moment does it become, wow, this is serious scale?

• 35:40Speaker 01

  So, so I think the moment it gets serious is when we really do have a driverless vehicle operating on public roads. And that we can do that kind of continuously.

• 35:54Lex Fridman?

  Without a safety driver.

• 35:55Speaker 01

  Without a safety driver in the vehicle. I think at that moment, we've, we've kind of crossed the zero to one threshold. And then it is about, how do we continue to scale that? How do we build the right business models? How do we build the right customer experience around it? So that it is actually, you know, a useful product out in the world. And I think that is really, at that point, it moves from a, you know, what is this kind of mixed science engineering project? Into engineering and commercialization and really starting to deliver on the value that we all see here. And, you know, and actually making that real in the world.

• 36:36Lex Fridman?

  What do you think that deployment looks like? Where, where do we first see the inkling of no safety driver? One or two cars here and there? Is it on the highway? Is it in specific routes in the urban environment?

• 36:49Speaker 01

  I, I think it's going to be urban suburban type environments. You know, with Aurora, when we, we thought about how to tackle this, it was kind of en vogue to think about trucking. As opposed to urban driving and, and, you know, the, again, the human intuition around this is that freeways are easier to drive on. Because everybody's kind of going in the same direction and, you know, lanes are a little wider, et cetera. And I think that that intuition is pretty good, except we don't really care about most of the time. We, we care about all of the time. And when you're driving on a freeway with a truck, say at 70, 70 miles an hour. And you've got 70,000 pound load with you, that's just an incredible amount of kinetic energy.

• 37:35Speaker 01

  And so when that goes wrong, it goes really wrong. And that those challenges that you see occur more rarely, so you don't get to learn as quickly. And they're incrementally more difficult than urban driving, but they're not easier than urban driving. And so I think this happens in moderate speed urban environments because there, if two vehicles crash at 25 miles per hour, it's not good, but probably everybody walks away. And those events where there's the possibility for that occurring happen frequently. So we get to learn more rapidly. We get to do that with lower risk for everyone.

• 38:18Speaker 01

  And then we can deliver value to people that need to get from one place to another. And then, once we've got that solved, then the freeway driving part of this just falls out. But we're able to learn more safely, more quickly in the urban environment.

• 38:30Lex Fridman?

  So 10 years and then scale 20, 30 years. I mean, who knows if a sufficiently compelling experience is created, it could be faster and slower. Do you think there could be breakthroughs? And what kind of breakthroughs might there be that completely change that timeline? Again, not only am I asking to predict the future. I'm asking you to predict breakthroughs that haven't happened yet.

• 38:54Speaker 01

  So what's the, I think another way to ask that was, would be if I could wave a magic wand, what part of the system would I make work today to accelerate it as quick as possible, quickly as possible?

• 39:05Lex Fridman?

  Don't say infrastructure. Please don't say infrastructure.

• 39:10Speaker 01

  No, it's definitely not infrastructure. It's really that perception forecasting capability. So if tomorrow, you could give me a perfect model of what's happened, what is happening and what will happen for the next five seconds around a vehicle on the roadway, that would accelerate things pretty dramatically.

• 39:31Lex Fridman?

  Are you, in terms of staying up at night, are you mostly bothered by cars, pedestrians or cyclists?

• 39:37Speaker 01

  So I worry most about the vulnerable road users about the combination of cyclists and cars, right? Just cyclists and pedestrians, because they're not in armor. You know, the cars, they're bigger, they've got protection for the people, and so the ultimate risk is lower there.

• 39:57Speaker 01

  Whereas a pedestrian or cyclist, they're out on the road and they don't have any protection. And so we need to pay extra attention to that.

• 40:05Lex Fridman?

  Do you think about a very difficult technical challenge of the fact that pedestrians, if you try to protect pedestrians by being careful and slow, they'll take advantage of that. So the game theoretic dance, does that worry you of how, from a technical perspective, how we solve that? Because as humans, the way we solve that is kind of nudge our way through the pedestrians, which doesn't feel, from a technical perspective, as an appropriate algorithm. But do you think about how we solve that problem?

• 40:42Speaker 01

  Yeah, I think there's, I think that was actually, there's two different concepts there. So one is, am I worried that because these vehicles are self-driving, people will kind of step in the road and take advantage of them? And I've heard this, and I don't really believe it, because if I'm driving down the road and somebody steps in front of me, I'm going to stop. Right? Like, even if I'm annoyed, I'm not going to just drive through a person stood in the road.

• 41:11Lex Fridman?

  Right.

• 41:12Speaker 01

  And so I think today, people can take advantage of this, and you do see some people do it. I guess there's an incremental risk, because maybe they have lower confidence that I'm going to see them than they might have for an automated vehicle, and so maybe that shifts it a little bit. But I think people don't want to get hit by cars. And so I think that I'm not that worried about people walking out of the 101 and creating chaos more than they would today.

• 41:40Speaker 01

  Regarding kind of the nudging through a big stream of pedestrians leaving a concert or something, I think that is further down the technology pipeline. I think that you're right, that's tricky. I don't think it's necessarily...

• 41:56Speaker 01

  I think the algorithm people use for this is pretty simple.

• 41:58Lex Fridman?

  Yeah.

• 41:59Speaker 01

  Uh, right. It's kind of just move forward slowly. And if somebody's really close, then stop. And, and I think that that probably can be replicated pretty, pretty easily. Uh, and particularly given that it's, you don't do this at 30 miles an hour, you do it at one. That even in those situations, the risk is relatively minimal. But I, you know, it's not something we're, we're thinking about in any serious way.

• 42:20Lex Fridman?

  And probably the, that's less an algorithm problem, more creating a human experience. So the HCI people that create a visual display that you're pleasantly as a pedestrian nudged out of the way.

• 42:33Speaker 01

  Yes.

• 42:33Lex Fridman?

  That's a, that's a, yeah, that's an experience problem, not an algorithm problem. Who's the main competitor to Aurora today? And how do you outcompete them in the long run?

• 42:44Speaker 01

  So we, we really focus a lot on what we're doing here. I think that, you know, I've said this a few times, that this is a huge, difficult problem. And it's great that a bunch of companies are tackling it because I think it's so important for society that somebody gets there.

• 43:01Speaker 01

  So we, you know, we're, we don't spend a whole lot of time like thinking tactically about who's out there. And, and how do we beat that, that, that person individually? What are we trying to do to, to go faster ultimately? Well, part of it is the leisure team we have has got pretty tremendous experience. And so we kind of understand the landscape and understand where the cul-de-sacs are to some degree. And, you know, we try and avoid those. I think there's a part of it, just this great team we've built. People, this is a technology and a company that people believe in the mission of. And so it allows us to attract just awesome people to go work.

• 43:42Speaker 01

  We've got a culture, I think, that people appreciate that allows them to focus, allows them to really spend time solving problems. Uh, and I think that keeps them energized. Uh, and then we've invested hard, uh, invested heavily in the infrastructure and architectures that we think will ultimately accelerate us. So because of the folks we're able to bring in early on, because of the, the, the great investors we have. You know, we don't spend all of our time doing demos and kind of leaping from one demo to the next. We've been given the freedom to invest in.

• 44:20Speaker 01

  Infrastructure to do machine learning, infrastructure to pull data from our on-road testing, infrastructure to use that to accelerate engineering. And I think that that early investment and continuing investment in those kind of tools will ultimately allow us to accelerate and do something pretty incredible.

• 44:37Lex Fridman?

  Chris, beautifully put. It's a good place to end. Thank you so much for talking today.

• 44:42Speaker 01

  Thank you very much. Really enjoyed it.