1
00:00:15,356 --> 00:00:22,036
Speaker 1: Pushkin. In two thousand and three, Chris Armsen was a

2
00:00:22,076 --> 00:00:25,836
Speaker 1: grad student at Carnegie Mellon University and he was working

3
00:00:25,836 --> 00:00:29,476
Speaker 1: on a research project in Chile in the Ata Kama Desert.

4
00:00:29,836 --> 00:00:33,196
Speaker 2: Beautiful place, very desolate, the closest thing we have to

5
00:00:33,236 --> 00:00:36,156
Speaker 2: Mars in many ways on Earth, which is why you

6
00:00:36,196 --> 00:00:38,996
Speaker 2: were there. We were building a robot to go look

7
00:00:39,036 --> 00:00:41,556
Speaker 2: for signs of life, and I was developing the navigation

8
00:00:41,636 --> 00:00:45,076
Speaker 2: system for it, and my PhD advisor came down and said, Hey,

9
00:00:45,116 --> 00:00:47,436
Speaker 2: the Defense Departments has this competition. They want to build

10
00:00:47,436 --> 00:00:50,076
Speaker 2: a robot to drive fifty miles an hour across the

11
00:00:50,116 --> 00:00:52,596
Speaker 2: desert between Los Angeles Las Vegas. And I thought that

12
00:00:52,676 --> 00:00:56,956
Speaker 2: just sounded awesome. So we bought a Humvy and we

13
00:00:57,036 --> 00:00:59,196
Speaker 2: cut the top of it, put a big electronics box

14
00:00:59,236 --> 00:01:01,756
Speaker 2: in a lot of computers. All of the stuff that's

15
00:01:01,796 --> 00:01:04,756
Speaker 2: in a self driving car today. The high performs computing,

16
00:01:05,356 --> 00:01:09,396
Speaker 2: the lasers, the radars, the cameras, the hd map apps

17
00:01:09,436 --> 00:01:11,716
Speaker 2: were part of this. It's kind of the first time

18
00:01:11,716 --> 00:01:15,676
Speaker 2: when all this stuff came together into a vehicle, and

19
00:01:15,716 --> 00:01:18,876
Speaker 2: then we developed it for six or nine months, and

20
00:01:18,876 --> 00:01:21,596
Speaker 2: then we tried to compete with it. The first darper challenge.

21
00:01:22,516 --> 00:01:25,716
Speaker 2: The team I was a technical director for we actually

22
00:01:25,716 --> 00:01:28,876
Speaker 2: had the highest performing thing there. It was supposed to

23
00:01:28,916 --> 00:01:30,876
Speaker 2: go one hundred and twenty six miles across the desert.

24
00:01:31,036 --> 00:01:35,236
Speaker 2: It ended up going about seven when it got hung

25
00:01:35,316 --> 00:01:38,196
Speaker 2: up on a berm and almost literally burst into flames.

26
00:01:38,876 --> 00:01:41,596
Speaker 1: And you, I mean, nobody won. But if anybody won,

27
00:01:41,676 --> 00:01:43,956
Speaker 1: you won, right, that was more than nobody. That was

28
00:01:43,996 --> 00:01:46,156
Speaker 1: farther than Yeah. The key thing is nobody won.

29
00:01:46,396 --> 00:01:48,796
Speaker 2: If you imagine a marathon where you're supposed to go

30
00:01:48,836 --> 00:01:50,996
Speaker 2: twenty six miles and the best runner went too right,

31
00:01:51,036 --> 00:01:52,516
Speaker 2: it's yes.

32
00:01:52,436 --> 00:01:55,956
Speaker 1: Yes, fair, and then burst into flames and then burst

33
00:01:55,996 --> 00:01:56,516
Speaker 1: into flames.

34
00:01:56,556 --> 00:02:02,996
Speaker 2: Yeah.

35
00:02:03,036 --> 00:02:05,276
Speaker 1: I'm Jacob Goldstein, and this is What's your problem? The

36
00:02:05,316 --> 00:02:07,076
Speaker 1: show where I talk to people who are trying to

37
00:02:07,116 --> 00:02:11,556
Speaker 1: make technological progress. My guest today is Chris Ermson. He's

38
00:02:11,596 --> 00:02:14,636
Speaker 1: the co founder and CEO of Aurora, a company that's

39
00:02:14,636 --> 00:02:18,396
Speaker 1: trying to bring autonomous driving to commercial trucks. As you

40
00:02:18,476 --> 00:02:21,636
Speaker 1: just heard, Chris started working on autonomous vehicles more than

41
00:02:21,716 --> 00:02:25,756
Speaker 1: twenty years ago, and in fact, his career traces the

42
00:02:25,956 --> 00:02:29,596
Speaker 1: really the entire modern arc of self driving cars, from

43
00:02:29,596 --> 00:02:33,196
Speaker 1: that first DARPA challenge to a top job at Google's

44
00:02:33,196 --> 00:02:36,276
Speaker 1: self driving car project, the project that later became Waimo

45
00:02:36,756 --> 00:02:40,236
Speaker 1: to founding Aurora, the company where he works now. We

46
00:02:40,276 --> 00:02:42,556
Speaker 1: talked a lot about the problems Chris is trying to

47
00:02:42,596 --> 00:02:45,956
Speaker 1: solve in autonomous trucking, and we also talked about the

48
00:02:45,996 --> 00:02:49,556
Speaker 1: future of autonomous driving more generally. But before we got

49
00:02:49,596 --> 00:02:52,036
Speaker 1: to that, we talked about the earlier work he did,

50
00:02:52,396 --> 00:02:55,196
Speaker 1: work that really helped get the field, the broader field,

51
00:02:55,276 --> 00:02:57,756
Speaker 1: to where it is today. So we'll pick up the

52
00:02:57,796 --> 00:03:01,316
Speaker 1: interview back in two thousand and four at that moment

53
00:03:01,396 --> 00:03:05,516
Speaker 1: when his team's autonomous car had failed and almost burst

54
00:03:05,516 --> 00:03:06,116
Speaker 1: into flames.

55
00:03:06,476 --> 00:03:09,596
Speaker 2: It was crushing, yeah, right, Like, you know, on the

56
00:03:09,636 --> 00:03:12,716
Speaker 2: one hand, it was called a Grand challenge, right because

57
00:03:13,076 --> 00:03:14,396
Speaker 2: you know, a lot of people didn't think it could

58
00:03:14,436 --> 00:03:17,356
Speaker 2: be solved. It was impossible. Because on the one hand,

59
00:03:17,356 --> 00:03:20,516
Speaker 2: it's kind of like, okay, it was really hard. On

60
00:03:20,556 --> 00:03:23,396
Speaker 2: the other hand, you've you know, we're sleeping on the

61
00:03:23,436 --> 00:03:25,356
Speaker 2: floor in the lab, in the you know, in this

62
00:03:25,396 --> 00:03:28,716
Speaker 2: garage in the middle of the desert for weeks and

63
00:03:28,756 --> 00:03:30,356
Speaker 2: months trying to get this thing to go, and then

64
00:03:30,356 --> 00:03:32,756
Speaker 2: you launch it out there and you have this this

65
00:03:32,836 --> 00:03:35,756
Speaker 2: epic moment where you're watching this thing that you've built,

66
00:03:35,836 --> 00:03:37,716
Speaker 2: tear out across the desert and you can just see

67
00:03:37,716 --> 00:03:41,596
Speaker 2: the top of it, and these helicopters that the military

68
00:03:41,676 --> 00:03:43,436
Speaker 2: is using to track them as they're out in the

69
00:03:43,476 --> 00:03:47,196
Speaker 2: desert doing this, and then you hear you know, it's

70
00:03:47,196 --> 00:03:48,916
Speaker 2: supposed to one hundred and twenty miles, and they're like, oh,

71
00:03:48,916 --> 00:03:52,516
Speaker 2: it's stuck. And then you hear like billowing smoke and

72
00:03:52,556 --> 00:03:55,756
Speaker 2: broken and poor thing comes back looking very sad, and

73
00:03:56,236 --> 00:03:59,076
Speaker 2: you know, it was crushing. But at the same time,

74
00:04:00,276 --> 00:04:02,756
Speaker 2: we did set records. Right, if you look at the

75
00:04:02,836 --> 00:04:04,876
Speaker 2: kind of the product of the speed and the distance

76
00:04:04,916 --> 00:04:07,036
Speaker 2: it went, this was an order of magnitude better than

77
00:04:07,076 --> 00:04:10,276
Speaker 2: anyone had done before, and so it was a big step.

78
00:04:10,356 --> 00:04:12,636
Speaker 2: And I think that was partly what encouraged the Defense

79
00:04:12,636 --> 00:04:15,156
Speaker 2: Department to say, hey, come back again and try it

80
00:04:15,156 --> 00:04:15,556
Speaker 2: in a year.

81
00:04:17,196 --> 00:04:19,716
Speaker 1: And then you did, and then you did it again

82
00:04:19,836 --> 00:04:21,476
Speaker 1: and again. And what year do we go to? Is

83
00:04:21,516 --> 00:04:23,996
Speaker 1: it two thousand and seven? Is that at the next

84
00:04:23,996 --> 00:04:24,596
Speaker 1: big moment?

85
00:04:24,836 --> 00:04:26,796
Speaker 2: Yeah? Two thousand and five was another one of these

86
00:04:26,796 --> 00:04:30,116
Speaker 2: in the desert. Two thousand and seven they did what

87
00:04:30,116 --> 00:04:32,676
Speaker 2: they called the Urban Challenge. So two thousand and five

88
00:04:32,676 --> 00:04:34,836
Speaker 2: we're able to drive it around the desert not hit

89
00:04:34,876 --> 00:04:37,636
Speaker 2: things too much. Two thousand and seven, they say, okay,

90
00:04:37,676 --> 00:04:39,556
Speaker 2: that's great, but now let's stay on the right side

91
00:04:39,556 --> 00:04:41,756
Speaker 2: of the road. Let's move in kind of pseudo urban

92
00:04:41,876 --> 00:04:46,516
Speaker 2: environments and show that that can work. And that was

93
00:04:46,556 --> 00:04:48,956
Speaker 2: the last of Grand challenges, because that year we actually

94
00:04:49,116 --> 00:04:51,676
Speaker 2: accomplished it. We drove sixty miles around this air base

95
00:04:51,756 --> 00:04:54,276
Speaker 2: and interacted with traffic. They hired a bunch of stunt

96
00:04:54,316 --> 00:04:56,236
Speaker 2: drivers out of Hollywood to come and drive cars around

97
00:04:56,276 --> 00:05:00,356
Speaker 2: these robots to make traffic for them, and it was

98
00:05:00,356 --> 00:05:03,316
Speaker 2: a heck of a day. And then the Defense Department,

99
00:05:03,396 --> 00:05:06,756
Speaker 2: or at least darpas said, you know, effectively, problem solved.

100
00:05:07,836 --> 00:05:09,676
Speaker 2: We've got this close enough. Now hand it off to

101
00:05:09,756 --> 00:05:11,636
Speaker 2: industry or whoever to take it from here.

102
00:05:12,516 --> 00:05:14,356
Speaker 1: And how did how did your car do?

103
00:05:14,436 --> 00:05:17,116
Speaker 2: In two thousand and seven, we won, which was nice.

104
00:05:17,156 --> 00:05:17,916
Speaker 2: It was a good change.

105
00:05:18,436 --> 00:05:21,796
Speaker 1: So you know, we went and did it catch on fire?

106
00:05:22,116 --> 00:05:24,996
Speaker 2: No fire? This time, it just kind of worked. We

107
00:05:25,076 --> 00:05:29,436
Speaker 2: had a little bit of nerves at the very beginning,

108
00:05:29,516 --> 00:05:32,636
Speaker 2: because you know, our system was pretty reliable, robust, it

109
00:05:32,716 --> 00:05:35,476
Speaker 2: worked all the time. We go and bring it out

110
00:05:35,516 --> 00:05:38,116
Speaker 2: to the start line and we can't get it to

111
00:05:38,196 --> 00:05:42,236
Speaker 2: boot properly because it can't see this GPS satellites that

112
00:05:42,236 --> 00:05:46,276
Speaker 2: it needed, and we never had this problem before. We're like,

113
00:05:46,756 --> 00:05:48,756
Speaker 2: you know, frantically trying to figure out what's going on.

114
00:05:48,796 --> 00:05:52,196
Speaker 2: And then we look over and realized that for race

115
00:05:52,276 --> 00:05:56,716
Speaker 2: day they brought a JumboTron and they've set that up

116
00:05:56,836 --> 00:05:59,196
Speaker 2: right where the robots are at the starting place. And

117
00:05:59,276 --> 00:06:01,996
Speaker 2: it turns out they don't really check these mobile jumbotrons

118
00:06:02,036 --> 00:06:05,556
Speaker 2: for like how much interference they're generating, I guess. So

119
00:06:05,596 --> 00:06:07,356
Speaker 2: we had this panic moment we said, you know, can

120
00:06:07,396 --> 00:06:09,556
Speaker 2: you turn off the jumbo tron? And sure enough they

121
00:06:09,556 --> 00:06:13,756
Speaker 2: turn off that and suddenly everything works again. So you know,

122
00:06:13,956 --> 00:06:18,156
Speaker 2: it was it wasn't without its challenges, so so but it.

123
00:06:18,156 --> 00:06:19,916
Speaker 1: Works right, So it works, and it works in a

124
00:06:19,996 --> 00:06:24,476
Speaker 1: like quasi real environment, a pseudo real environment. So I

125
00:06:24,516 --> 00:06:26,676
Speaker 1: mean when you at that moment, when you were thinking

126
00:06:26,716 --> 00:06:31,236
Speaker 1: about the future, the future of self driving cars, how

127
00:06:31,836 --> 00:06:33,116
Speaker 1: did it look to you? What did you think?

128
00:06:33,996 --> 00:06:37,476
Speaker 2: Yeah, I think at that point was starting to believe

129
00:06:37,476 --> 00:06:39,796
Speaker 2: there was a thing that could happen here, right, and

130
00:06:40,036 --> 00:06:44,316
Speaker 2: probably you know, certainly naively thought oh yeah, we've got

131
00:06:44,316 --> 00:06:44,876
Speaker 2: this right.

132
00:06:46,076 --> 00:06:49,716
Speaker 1: This maybe everybody kind of thought that, right, Like.

133
00:06:50,036 --> 00:06:53,676
Speaker 2: Yeah, I think, And that's been part of what's made

134
00:06:53,676 --> 00:06:56,396
Speaker 2: the journey really fun for me. It's just there's just

135
00:06:56,476 --> 00:06:59,516
Speaker 2: so many things to learn, so many new problems to

136
00:06:59,516 --> 00:07:03,036
Speaker 2: overcome along the way of taking something from a it

137
00:07:03,196 --> 00:07:05,996
Speaker 2: worked on this day in a race, to hey, we

138
00:07:06,036 --> 00:07:10,156
Speaker 2: can go do something transformational that will save lives and

139
00:07:10,196 --> 00:07:13,156
Speaker 2: improve the economy and you know, do all these other

140
00:07:13,196 --> 00:07:13,756
Speaker 2: great things.

141
00:07:14,876 --> 00:07:17,996
Speaker 1: It seems like that the distance between it worked in

142
00:07:18,036 --> 00:07:22,276
Speaker 1: a race and we can do something transformational has been longer,

143
00:07:22,636 --> 00:07:24,676
Speaker 1: certainly than a lot of people thought. Then a lot

144
00:07:24,676 --> 00:07:26,676
Speaker 1: of like smart, well informed people.

145
00:07:26,436 --> 00:07:32,276
Speaker 2: Thought, yeah, me among them, right. And you know, it's

146
00:07:32,276 --> 00:07:34,116
Speaker 2: one of these things where I think anyone who sets

147
00:07:34,156 --> 00:07:38,516
Speaker 2: out and does something interest and exciting, often I think

148
00:07:38,556 --> 00:07:40,196
Speaker 2: if they understood how hard it was going to be

149
00:07:40,196 --> 00:07:43,516
Speaker 2: before they started, may not have actually taken the first step.

150
00:07:43,556 --> 00:07:47,156
Speaker 2: And so I feel a little lucky to have not

151
00:07:47,236 --> 00:07:49,636
Speaker 2: understood that, because it's caused me to kind of stick

152
00:07:49,676 --> 00:07:51,956
Speaker 2: with it and really enjoy the journey along the way.

153
00:07:52,436 --> 00:07:55,316
Speaker 1: I mean, entrepreneurs basically always say that thing that you

154
00:07:55,476 --> 00:07:58,156
Speaker 1: just said, but in the case of autonomous driving, I

155
00:07:58,196 --> 00:08:01,756
Speaker 1: really believe it. Right, It seems like extra true. Like

156
00:08:02,076 --> 00:08:04,876
Speaker 1: two thousand and seven was basically like the year the

157
00:08:04,996 --> 00:08:07,636
Speaker 1: iPhone came out, right, like, which is to say, in

158
00:08:08,076 --> 00:08:11,116
Speaker 1: technology long time ago, not to mention that there was

159
00:08:11,196 --> 00:08:14,636
Speaker 1: like no computer vision as we know it today, right,

160
00:08:14,676 --> 00:08:17,556
Speaker 1: which has become important, I mean so much.

161
00:08:18,196 --> 00:08:23,396
Speaker 2: No, it is. You know, the waves of technological evolution

162
00:08:23,436 --> 00:08:26,356
Speaker 2: that we've seen since then are profound, and we've been

163
00:08:26,396 --> 00:08:28,436
Speaker 2: able to kind of surf those as we've been building it.

164
00:08:28,476 --> 00:08:35,716
Speaker 2: And it's been Yeah, it is, it's been a long time.

165
00:08:39,156 --> 00:08:41,036
Speaker 1: So then you go to Google, right, you go to

166
00:08:41,036 --> 00:08:43,196
Speaker 1: Google a couple couple of years after that two thousand

167
00:08:43,236 --> 00:08:46,756
Speaker 1: and nine. So you're at Google from twenty nine to

168
00:08:46,836 --> 00:08:50,276
Speaker 1: twenty sixteen, Right, what do you and the team figure out?

169
00:08:50,356 --> 00:08:52,356
Speaker 1: And then yeah, when do you leave?

170
00:08:52,916 --> 00:08:58,676
Speaker 2: So we get there, and we originally want to show

171
00:08:58,756 --> 00:09:00,156
Speaker 2: that we could go from what we've shown at the

172
00:09:00,236 --> 00:09:04,196
Speaker 2: Darker Challenge to something actually worked on public roads, and

173
00:09:04,276 --> 00:09:07,476
Speaker 2: so we had this challenge of driving one hundred thousand

174
00:09:07,516 --> 00:09:10,836
Speaker 2: miles in public roads and miles of really interesting, challenging

175
00:09:10,876 --> 00:09:13,276
Speaker 2: roads in the Bay Area, things like driving down Highway

176
00:09:13,316 --> 00:09:16,596
Speaker 2: wand from San Francisco to La and across all the

177
00:09:16,636 --> 00:09:19,396
Speaker 2: Bay bridges and things like that, with the idea that

178
00:09:19,436 --> 00:09:22,356
Speaker 2: if we could prove we could do these things, then yeah,

179
00:09:22,396 --> 00:09:25,716
Speaker 2: this technology probably has legs. And it was kind of

180
00:09:25,756 --> 00:09:29,596
Speaker 2: a dread pirate Roberts setup right in that, you know,

181
00:09:29,916 --> 00:09:33,116
Speaker 2: we were told that you've got you know, two years

182
00:09:33,156 --> 00:09:35,836
Speaker 2: to do this, and you know then we'll probably fire

183
00:09:35,876 --> 00:09:38,716
Speaker 2: you the day after, right, and you kind of this

184
00:09:38,876 --> 00:09:41,156
Speaker 2: was kind of with us for the time. And so

185
00:09:41,276 --> 00:09:44,076
Speaker 2: we worked with urgency, and it turns out we did

186
00:09:44,116 --> 00:09:46,836
Speaker 2: in eighteen months, and through that we had some really

187
00:09:46,876 --> 00:09:51,236
Speaker 2: interesting technological evolution. You know, we started to see some

188
00:09:51,276 --> 00:09:55,036
Speaker 2: of the you know, early legs of deep learning started

189
00:09:55,036 --> 00:09:56,196
Speaker 2: to show up in that point.

190
00:09:56,996 --> 00:10:00,556
Speaker 1: During that time, so this is like two thousand and ten,

191
00:10:00,676 --> 00:10:02,396
Speaker 1: twenty eleven, yeah.

192
00:10:02,156 --> 00:10:03,596
Speaker 2: Exactly those times, yep.

193
00:10:03,836 --> 00:10:04,036
Speaker 1: Yeah.

194
00:10:04,956 --> 00:10:10,156
Speaker 2: And then but I think almost more importantly really started

195
00:10:10,236 --> 00:10:12,636
Speaker 2: we really started to understand what this would mean to people.

196
00:10:13,396 --> 00:10:16,156
Speaker 2: Right that we you know, as somebody who had worked

197
00:10:16,156 --> 00:10:19,516
Speaker 2: on this because the technology was cool and initially and

198
00:10:19,676 --> 00:10:22,436
Speaker 2: enjoyed the challenge of it, and seeing the benefit to

199
00:10:22,476 --> 00:10:24,956
Speaker 2: the military as we thought about you know, as we

200
00:10:24,996 --> 00:10:26,556
Speaker 2: started to get into the space and started to talk

201
00:10:26,556 --> 00:10:30,316
Speaker 2: to people in the public sector about the number of

202
00:10:30,316 --> 00:10:33,316
Speaker 2: lives lost on America's roads, you know, forty plus thousand

203
00:10:33,316 --> 00:10:40,476
Speaker 2: people every year. The challenge that people, whether because they

204
00:10:40,716 --> 00:10:44,276
Speaker 2: have physical limitation to prevent them from driving or because

205
00:10:44,316 --> 00:10:46,956
Speaker 2: they've aged out no longer feel comfortable driving, the implications

206
00:10:46,956 --> 00:10:50,396
Speaker 2: that has for the quality of life, and how we

207
00:10:50,476 --> 00:10:54,076
Speaker 2: can make that better for folks, you know, the accessibility

208
00:10:54,116 --> 00:10:57,956
Speaker 2: that we could bring to transportation that's kind of lost

209
00:10:57,996 --> 00:10:59,876
Speaker 2: with the public trans system we have in the US.

210
00:11:00,236 --> 00:11:02,596
Speaker 2: All of this was like, oh wow, there is not

211
00:11:02,716 --> 00:11:05,876
Speaker 2: just it's not just a cool, interesting technology. It's not

212
00:11:05,916 --> 00:11:07,716
Speaker 2: that I get to work with good people. It's not

213
00:11:07,796 --> 00:11:10,436
Speaker 2: just that you know, this could be valuable. It's that, like,

214
00:11:10,476 --> 00:11:14,116
Speaker 2: this is socially really important to do as well. And then,

215
00:11:14,436 --> 00:11:18,196
Speaker 2: you know, the course of the program, we got to

216
00:11:18,236 --> 00:11:20,396
Speaker 2: the point where we launched for the first time a

217
00:11:20,476 --> 00:11:24,276
Speaker 2: vehicle operating on public roads with nobody in it, well,

218
00:11:24,316 --> 00:11:27,236
Speaker 2: actually with somebody at it, with Steve Mahon, who is

219
00:11:27,276 --> 00:11:29,316
Speaker 2: a blind gentleman who'd worked with us on some of

220
00:11:29,316 --> 00:11:31,796
Speaker 2: the early kind of concepts and understanding of this, and

221
00:11:31,836 --> 00:11:34,876
Speaker 2: he took a road to Austin, Texas by himself and

222
00:11:35,236 --> 00:11:41,436
Speaker 2: seeing the emotional impact that had on him of you know,

223
00:11:41,596 --> 00:11:44,796
Speaker 2: once again having the freedom to get from me to

224
00:11:44,836 --> 00:11:47,036
Speaker 2: be without having asked somebody else. It was just like, wow,

225
00:11:47,116 --> 00:11:51,236
Speaker 2: this this actually matters. So that was very cool.

226
00:11:52,676 --> 00:11:56,436
Speaker 1: So so you mentioned the machine learning piece starting to

227
00:11:56,476 --> 00:11:59,116
Speaker 1: come in. It's I think I was looking back at

228
00:11:59,196 --> 00:12:02,196
Speaker 1: I think it's twenty twelve that alex net comes along, right,

229
00:12:02,236 --> 00:12:03,956
Speaker 1: the first thing. I think that's right, kind of big

230
00:12:04,196 --> 00:12:08,396
Speaker 1: computer vision breakthrough. And so it is interesting. I mean

231
00:12:08,436 --> 00:12:10,956
Speaker 1: when I I think as a sort of lay person

232
00:12:11,156 --> 00:12:13,876
Speaker 1: about autonomous cars, now, I think of computer vision as

233
00:12:13,916 --> 00:12:17,236
Speaker 1: like central like, how could you even do it without

234
00:12:17,276 --> 00:12:20,676
Speaker 1: that right, without computers being able to quote unquote understand

235
00:12:20,676 --> 00:12:23,196
Speaker 1: what they see. But this is actually emerging just as

236
00:12:23,196 --> 00:12:26,956
Speaker 1: you're building this car, right, this system, So how like

237
00:12:27,716 --> 00:12:29,676
Speaker 1: tell me about that? Tell me sort of building in

238
00:12:29,756 --> 00:12:33,476
Speaker 1: parallel with this technological enabling wave.

239
00:12:33,996 --> 00:12:36,716
Speaker 2: Yeah, there was a bunch of these things. So Moore's

240
00:12:36,796 --> 00:12:39,276
Speaker 2: law was continued in a march along and the amount

241
00:12:39,276 --> 00:12:42,756
Speaker 2: of computation we had in the vehicles improving the cell

242
00:12:42,756 --> 00:12:46,156
Speaker 2: phone was, believe it or not, was a big boon

243
00:12:46,236 --> 00:12:50,036
Speaker 2: to us because it drove the performance of cameras.

244
00:12:50,596 --> 00:12:54,436
Speaker 1: So, oh, interesting thing about like all those selfies everybody

245
00:12:54,476 --> 00:12:57,636
Speaker 1: just wanting to make better cheaper cameras and the processing

246
00:12:57,716 --> 00:12:59,036
Speaker 1: for images, yeah.

247
00:12:58,876 --> 00:13:01,956
Speaker 2: One hundred, but even just the physical imager itself, right,

248
00:13:02,036 --> 00:13:05,316
Speaker 2: went from you know, a one megapixel three twenty two

249
00:13:05,396 --> 00:13:07,516
Speaker 2: forty camera, which is what if you bought a top

250
00:13:07,596 --> 00:13:11,236
Speaker 2: the line you know, Kodak digital camera back in the day,

251
00:13:11,636 --> 00:13:17,236
Speaker 2: was now my iPhone's got forty eight megapixel, right, and so,

252
00:13:17,516 --> 00:13:22,956
Speaker 2: and the quality and color performance and everything that's improved dramatically.

253
00:13:23,956 --> 00:13:27,276
Speaker 2: And then light ar is another thing that has really

254
00:13:27,836 --> 00:13:31,196
Speaker 2: evolved over the course of the last twenty years, going

255
00:13:31,196 --> 00:13:34,076
Speaker 2: from things where we could get a single point along

256
00:13:34,116 --> 00:13:38,956
Speaker 2: the line to now full three D fields of view

257
00:13:39,276 --> 00:13:43,436
Speaker 2: and allows us to combine the camera data with the

258
00:13:43,476 --> 00:13:46,916
Speaker 2: light our data with the computation. And then the final

259
00:13:46,996 --> 00:13:49,676
Speaker 2: big thing that's moved forward is in the sensing side

260
00:13:49,756 --> 00:13:54,236
Speaker 2: is radar and the automotive radar. The quality that you

261
00:13:54,236 --> 00:13:56,396
Speaker 2: can get out of that, the price point that comes

262
00:13:56,396 --> 00:13:59,516
Speaker 2: in at now, you know, when you combine that set

263
00:13:59,556 --> 00:14:03,276
Speaker 2: of advances, there's orders of magnitude improvement in both the

264
00:14:03,396 --> 00:14:06,156
Speaker 2: quality of data we can consume and the amount of

265
00:14:06,236 --> 00:14:09,756
Speaker 2: data that we can perform computation over that really is

266
00:14:09,876 --> 00:14:12,596
Speaker 2: unlocked our ability to understand the world around these vehicles.

267
00:14:14,156 --> 00:14:21,156
Speaker 1: So you leave in twenty sixteen, like, are people getting

268
00:14:21,236 --> 00:14:21,996
Speaker 1: rides in wherever?

269
00:14:21,996 --> 00:14:22,276
Speaker 2: It was?

270
00:14:22,396 --> 00:14:25,196
Speaker 1: Chandler, Arizona yet at that time? Like, is that is

271
00:14:25,196 --> 00:14:26,516
Speaker 1: it out in the world yet when you leave?

272
00:14:26,556 --> 00:14:29,956
Speaker 2: Okay, No, we've been doing demos and we were doing development.

273
00:14:29,996 --> 00:14:32,036
Speaker 2: I think we had vehicles in Chandler at that time,

274
00:14:32,116 --> 00:14:35,796
Speaker 2: and we're starting to operate, but they were still with

275
00:14:35,916 --> 00:14:38,076
Speaker 2: a person behind the steering wheel, and we were still

276
00:14:38,436 --> 00:14:43,236
Speaker 2: we were building towards what ultimately became the initial channel launch.

277
00:14:44,436 --> 00:14:45,796
Speaker 1: Why'd you leave?

278
00:14:46,116 --> 00:14:49,436
Speaker 2: It was time? You know, I had been there. I

279
00:14:49,476 --> 00:14:54,076
Speaker 2: really valued and left the experience, but at some point

280
00:14:54,156 --> 00:14:56,396
Speaker 2: I kind of lost confidence that we were going to

281
00:14:56,396 --> 00:14:59,116
Speaker 2: make the decisions that we needed to make to be successful.

282
00:14:59,156 --> 00:15:03,756
Speaker 2: And as a person leading the organization that you know,

283
00:15:03,996 --> 00:15:05,956
Speaker 2: Google had been incredibly generous to me, give me this

284
00:15:06,036 --> 00:15:09,156
Speaker 2: incredible opportunity, and if I just didn't believe it, it

285
00:15:09,236 --> 00:15:11,636
Speaker 2: wasn't my place to lead the team. And and so

286
00:15:12,356 --> 00:15:15,156
Speaker 2: you know, I'm a big believer that in business, you

287
00:15:15,156 --> 00:15:17,716
Speaker 2: you know, kind of you have three options. You if

288
00:15:17,716 --> 00:15:19,276
Speaker 2: you see something you don't like, you try and fix it.

289
00:15:19,516 --> 00:15:21,916
Speaker 2: If you can't fix it, you get in line. And

290
00:15:22,156 --> 00:15:23,436
Speaker 2: if you can't get in line, you get out of

291
00:15:23,476 --> 00:15:26,436
Speaker 2: the way, and you know, I did what I could

292
00:15:26,476 --> 00:15:28,396
Speaker 2: to try and you know, kind of move things away

293
00:15:28,396 --> 00:15:30,796
Speaker 2: that I thought they needed to go, and ultimately said,

294
00:15:30,876 --> 00:15:33,756
Speaker 2: you know, this company's been incredibly galous to me. Let

295
00:15:33,756 --> 00:15:36,196
Speaker 2: me get out of the way and let it gets

296
00:15:36,276 --> 00:15:37,116
Speaker 2: on its own path.

297
00:15:38,236 --> 00:15:41,996
Speaker 1: When you say you lost confidence that they were going

298
00:15:42,036 --> 00:15:45,476
Speaker 1: to make the decisions they needed to make, I mean,

299
00:15:46,196 --> 00:15:49,636
Speaker 1: obviously we should evaluate decisions based on the information available

300
00:15:49,636 --> 00:15:52,796
Speaker 1: at the time, but it is the case that you know,

301
00:15:53,356 --> 00:15:55,236
Speaker 1: you can get in Awai Mo in San Francisco in

302
00:15:55,316 --> 00:15:57,796
Speaker 1: one minute and have a beautiful ride right now, Like,

303
00:15:59,196 --> 00:15:59,836
Speaker 1: were you wrong?

304
00:16:00,476 --> 00:16:05,476
Speaker 2: I apparently yes, right, Like you know, like you think,

305
00:16:05,476 --> 00:16:07,436
Speaker 2: there's no way to judge it other than they they've

306
00:16:07,516 --> 00:16:12,596
Speaker 2: ultimately been successful. You know, maybe would have taken a different,

307
00:16:12,596 --> 00:16:16,076
Speaker 2: shorter path, but you know, I think I think it's

308
00:16:16,116 --> 00:16:18,396
Speaker 2: it's yeah. I don't know if you're a parent, but

309
00:16:18,396 --> 00:16:19,836
Speaker 2: one of the things you hope as a parent is

310
00:16:19,876 --> 00:16:25,316
Speaker 2: that you you you embody your kids with things and

311
00:16:25,316 --> 00:16:27,836
Speaker 2: then they go off from the world and succeed. And

312
00:16:27,876 --> 00:16:30,196
Speaker 2: the same is true when you lead teams or build something,

313
00:16:30,316 --> 00:16:31,956
Speaker 2: is that you know you do your part and you

314
00:16:31,996 --> 00:16:34,876
Speaker 2: hope it outlives you and that you know, outperforms what

315
00:16:34,916 --> 00:16:37,716
Speaker 2: you might have hoped for it. And I think it's

316
00:16:37,716 --> 00:16:39,556
Speaker 2: been awesome to see way most succeed.

317
00:16:40,236 --> 00:16:46,396
Speaker 1: So you started in twenty seventeen, right, uh, And as

318
00:16:46,436 --> 00:16:49,116
Speaker 1: I understand it, you didn't start focused on trucks, Like,

319
00:16:49,156 --> 00:16:51,276
Speaker 1: tell me about what you're thinking when you start the company?

320
00:16:51,716 --> 00:16:54,316
Speaker 2: Yeah, how you get to trucks? So you know, I

321
00:16:54,356 --> 00:16:57,316
Speaker 2: didn't leave Google to start the company. I left Goog

322
00:16:57,316 --> 00:16:58,796
Speaker 2: because it was time, and I then spent some time

323
00:16:58,796 --> 00:17:00,436
Speaker 2: trying to figure out what to do and kind of

324
00:17:00,436 --> 00:17:03,196
Speaker 2: came to the conclusion that, you know, it was worth

325
00:17:03,316 --> 00:17:05,196
Speaker 2: taking another shot at this and trying to build something.

326
00:17:06,436 --> 00:17:08,996
Speaker 2: And so found two great co founders in Sterling and True,

327
00:17:09,316 --> 00:17:12,156
Speaker 2: and we wanted to build a driver and we wanted

328
00:17:12,156 --> 00:17:15,316
Speaker 2: to apply that driver and passenger cars and trucks and

329
00:17:15,316 --> 00:17:17,956
Speaker 2: wherever it could go. And we thought at the time,

330
00:17:18,396 --> 00:17:20,236
Speaker 2: we didn't see how it's going to be possible to

331
00:17:20,316 --> 00:17:23,716
Speaker 2: do trucking because based on the experience I had and

332
00:17:23,756 --> 00:17:25,316
Speaker 2: others had, we looked at how far you had to

333
00:17:25,316 --> 00:17:27,556
Speaker 2: see down the road to do that safely, and we

334
00:17:27,596 --> 00:17:29,996
Speaker 2: came to the conclusion you just couldn't do that with

335
00:17:30,036 --> 00:17:32,436
Speaker 2: the technology that exists all the time, and you have.

336
00:17:32,436 --> 00:17:34,436
Speaker 1: To see farther just because it takes longer for a

337
00:17:34,436 --> 00:17:35,356
Speaker 1: big truck to stop.

338
00:17:35,396 --> 00:17:38,836
Speaker 2: This is physics. There's just way more kinetic energy. Right,

339
00:17:40,276 --> 00:17:42,396
Speaker 2: They're heavier, and they're moving at seventy miles an hour

340
00:17:42,436 --> 00:17:44,316
Speaker 2: instead of in a city you're moving at fifteen miles

341
00:17:44,316 --> 00:17:46,836
Speaker 2: an hour. So the combination of the speed and the

342
00:17:46,876 --> 00:17:49,516
Speaker 2: way it means that it just takes longer to stop

343
00:17:49,596 --> 00:17:54,276
Speaker 2: farther distance down the road. And then you add to that,

344
00:17:54,636 --> 00:17:56,596
Speaker 2: it's much easier drive around a light vehicle than a

345
00:17:56,596 --> 00:18:00,236
Speaker 2: big truck, so you don't need a special license. They're

346
00:18:00,356 --> 00:18:04,436
Speaker 2: much smaller, you don't need special thing maintenance programs and whatnot.

347
00:18:04,476 --> 00:18:07,476
Speaker 2: And so we're like, okay, let's focus on light vehicles.

348
00:18:07,676 --> 00:18:10,596
Speaker 2: We see there's a real opportunity there. If we can

349
00:18:10,756 --> 00:18:16,036
Speaker 2: crack the can you see far enough problem, then trucking

350
00:18:16,076 --> 00:18:18,716
Speaker 2: to be a great application to go to. Yeah. Yeah uh.

351
00:18:18,876 --> 00:18:20,516
Speaker 2: And so part of what I spent my time doing

352
00:18:20,596 --> 00:18:22,876
Speaker 2: during the first couple of years of the company was looking,

353
00:18:22,916 --> 00:18:25,316
Speaker 2: you know, basically turning over every rock we could with

354
00:18:25,316 --> 00:18:28,236
Speaker 2: with Bart, one of our early team members, to find

355
00:18:28,236 --> 00:18:30,596
Speaker 2: a technology that would allow us to see for far

356
00:18:30,676 --> 00:18:35,196
Speaker 2: enough that we could actually do trucking. And ultimately we

357
00:18:35,236 --> 00:18:38,876
Speaker 2: found that in this little company in Montana called Blackmore

358
00:18:39,796 --> 00:18:42,356
Speaker 2: that had built this really special kind of laser range

359
00:18:42,356 --> 00:18:45,796
Speaker 2: finder that because of the way it did measurements and

360
00:18:46,036 --> 00:18:53,356
Speaker 2: what's called frequency modulated continuous wave it it could see

361
00:18:53,356 --> 00:18:55,596
Speaker 2: basically twice as far as the rest of the light

362
00:18:55,636 --> 00:18:59,116
Speaker 2: our stuff could see. Uh, And so we're like, huh,

363
00:18:59,236 --> 00:19:02,916
Speaker 2: we now we we have some really interesting driving capability.

364
00:19:02,916 --> 00:19:06,796
Speaker 2: We've now got this pseudomagical light our sensor that can

365
00:19:06,836 --> 00:19:10,396
Speaker 2: see far enough trucking for like a really great application

366
00:19:10,476 --> 00:19:11,116
Speaker 2: to go take on.

367
00:19:12,156 --> 00:19:13,436
Speaker 1: Let's talk about a few of the things you had

368
00:19:13,436 --> 00:19:15,516
Speaker 1: to figure out. So you decide you're going to do trucking. Yeah,

369
00:19:15,556 --> 00:19:19,116
Speaker 1: and presumably by trucking, Like I mean, I know where

370
00:19:19,156 --> 00:19:22,556
Speaker 1: you are now, Like, so presumably by trucking. You don't

371
00:19:22,596 --> 00:19:26,276
Speaker 1: mean like the bread truck that goes to the little

372
00:19:26,396 --> 00:19:28,516
Speaker 1: market by my house. You mean the great, big truck

373
00:19:28,556 --> 00:19:29,676
Speaker 1: that goes on the freeway.

374
00:19:30,076 --> 00:19:33,316
Speaker 2: Yeah, that's where we thought there was the biggest opportunity

375
00:19:33,636 --> 00:19:36,876
Speaker 2: was working what we call class eight tractor trailers, big

376
00:19:36,996 --> 00:19:40,196
Speaker 2: you know, semi trucks. You know, they drive a lot

377
00:19:40,196 --> 00:19:43,156
Speaker 2: of miles. We don't have enough people who want to

378
00:19:43,196 --> 00:19:47,796
Speaker 2: do that job, and yet it's absolutely essential to American

379
00:19:47,956 --> 00:19:52,356
Speaker 2: and worldwide way of life, and there's a real need.

380
00:19:53,156 --> 00:19:55,436
Speaker 2: Right as we've dug into it, we realized that there's

381
00:19:55,756 --> 00:19:58,316
Speaker 2: five thousand people killed every year in heavy truck accidents,

382
00:19:58,556 --> 00:20:01,316
Speaker 2: five hundred thousand people injured. And then we can move

383
00:20:01,356 --> 00:20:05,436
Speaker 2: goods more efficiently, which you know is important, particularly in

384
00:20:05,676 --> 00:20:07,956
Speaker 2: the you know, this age of e commerce where people

385
00:20:07,956 --> 00:20:11,676
Speaker 2: expect things next day or you know, be able to

386
00:20:11,996 --> 00:20:15,356
Speaker 2: move those goods efficiently the customers is really valuable.

387
00:20:17,556 --> 00:20:21,556
Speaker 1: Okay, this April, if I've got my dates right, you

388
00:20:21,676 --> 00:20:26,196
Speaker 1: actually have a truck drive for real stuff on the

389
00:20:26,236 --> 00:20:28,676
Speaker 1: freeway without someone behind the wheel, right.

390
00:20:28,876 --> 00:20:31,876
Speaker 2: That's exactly right. It was awesome, right. We've as a

391
00:20:31,916 --> 00:20:34,756
Speaker 2: company been building towards that for almost eight and a

392
00:20:34,756 --> 00:20:38,196
Speaker 2: half years, eight and fourty years, and you know, we

393
00:20:38,356 --> 00:20:42,396
Speaker 2: take doing these things safely, very seriously, and really a

394
00:20:42,436 --> 00:20:44,596
Speaker 2: lot of the last couple of years has been making

395
00:20:44,596 --> 00:20:48,036
Speaker 2: sure we could have confidence that when we let the

396
00:20:48,036 --> 00:20:50,996
Speaker 2: thing go, that it was actually going to be safe.

397
00:20:51,036 --> 00:20:52,476
Speaker 2: And then we got to a point where we're like, yeah,

398
00:20:52,556 --> 00:20:54,556
Speaker 2: this is safe. We can go send this out in

399
00:20:54,596 --> 00:20:57,956
Speaker 2: the daylight and dry weather and have it drive back

400
00:20:57,956 --> 00:21:00,556
Speaker 2: and forth between Dallas and Houston. And I had the

401
00:21:00,596 --> 00:21:05,876
Speaker 2: privilege of right along in the back seat. And it

402
00:21:05,996 --> 00:21:10,116
Speaker 2: was awesome right in that it worked. Incredibly boring, right,

403
00:21:10,156 --> 00:21:11,196
Speaker 2: It turns out it's like it's.

404
00:21:11,356 --> 00:21:14,716
Speaker 1: Wanted to be so boring. You wanted to be very boring.

405
00:21:14,716 --> 00:21:18,396
Speaker 2: But but it just kind of worked. And I went

406
00:21:18,476 --> 00:21:21,476
Speaker 2: down and back that day in the truck and were.

407
00:21:21,276 --> 00:21:23,516
Speaker 1: You hauling stuff at that point? Was it was it?

408
00:21:23,596 --> 00:21:25,396
Speaker 2: We were? We were all the histories.

409
00:21:25,796 --> 00:21:31,796
Speaker 1: Yeah, oh pastries, Okay, pastries both ways, that would be

410
00:21:31,836 --> 00:21:34,236
Speaker 1: a bit. There's some pastries. It just that they want

411
00:21:34,276 --> 00:21:34,356
Speaker 1: to know.

412
00:21:34,996 --> 00:21:37,316
Speaker 2: I think there is a pastry imbalance. I think we

413
00:21:37,596 --> 00:21:39,516
Speaker 2: for the first trip, I think we may have actually

414
00:21:39,716 --> 00:21:41,996
Speaker 2: been empty. But on the way back, I'm pretty sure

415
00:21:41,996 --> 00:21:47,316
Speaker 2: from for whatever reasons, the pastries diffused from Houston to Dallas.

416
00:21:47,516 --> 00:21:50,636
Speaker 1: So then what happens in May and may you put

417
00:21:50,636 --> 00:21:53,636
Speaker 1: a person back behind the wheel, right? Tell me about that.

418
00:21:54,076 --> 00:21:56,836
Speaker 2: Yeah. We so as a company, we've really focused on

419
00:21:57,196 --> 00:21:59,116
Speaker 2: do what we do best, and what we do best

420
00:21:59,196 --> 00:22:02,556
Speaker 2: is building a safe, capable driving system. The oral driver

421
00:22:03,116 --> 00:22:06,396
Speaker 2: and we worked with other companies like Peterbilt at Pacar

422
00:22:06,596 --> 00:22:11,956
Speaker 2: and Volvo Trucks, and our partners at peter Bolt called

423
00:22:12,036 --> 00:22:14,956
Speaker 2: up and said, hey, we'd like you to have an

424
00:22:14,996 --> 00:22:17,796
Speaker 2: observer in the seat because there's some prototype parts in

425
00:22:18,476 --> 00:22:21,516
Speaker 2: our truck and it matters to us that you put

426
00:22:21,516 --> 00:22:25,356
Speaker 2: an observer in. And so we said, okay, uh, you know,

427
00:22:25,396 --> 00:22:28,236
Speaker 2: we had a conversation. We respect them, and we ultimately

428
00:22:28,236 --> 00:22:30,316
Speaker 2: put the observer in the seat, and we have a

429
00:22:30,356 --> 00:22:33,556
Speaker 2: person sat on board who is sat in the driver's seat,

430
00:22:33,916 --> 00:22:36,476
Speaker 2: but they're an observer and they're really just there because

431
00:22:36,516 --> 00:22:37,916
Speaker 2: our partner asked them to put them there.

432
00:22:38,356 --> 00:22:41,476
Speaker 1: The VIHA presumably they are a license to drive an

433
00:22:41,476 --> 00:22:43,836
Speaker 1: eighteen year It's not just some n week watching them.

434
00:22:43,876 --> 00:22:45,756
Speaker 1: What's going on. That's the truck driver.

435
00:22:45,636 --> 00:22:47,596
Speaker 2: You know. We we we don't want to put anyone

436
00:22:47,596 --> 00:22:49,396
Speaker 2: in place where you know, the high control has to

437
00:22:49,556 --> 00:22:51,596
Speaker 2: debate whether you know, it's just like, okay, let's just

438
00:22:51,636 --> 00:22:54,036
Speaker 2: put a truck driver there. They sit there. If you

439
00:22:54,076 --> 00:22:58,876
Speaker 2: go to YouTube dot com slash or row driver, you

440
00:22:58,876 --> 00:23:01,036
Speaker 2: can see a live video between eight and five o'clock

441
00:23:01,116 --> 00:23:04,316
Speaker 2: every day of our trucks drive down the road and

442
00:23:04,356 --> 00:23:07,196
Speaker 2: you can see that you know, this person sat there

443
00:23:07,276 --> 00:23:10,236
Speaker 2: and sometimes they're twiddling their sums, sometimes they're eating Fredo's,

444
00:23:11,436 --> 00:23:14,116
Speaker 2: you know, just observing.

445
00:23:14,516 --> 00:23:19,076
Speaker 1: I mean, at least from a narrative standpoint, it's a

446
00:23:19,076 --> 00:23:21,316
Speaker 1: bummer to have to put the person back behind the wheel.

447
00:23:21,356 --> 00:23:24,836
Speaker 2: Surely, absolutely, from a narrative standpoint, it's a bummer, right,

448
00:23:24,916 --> 00:23:28,636
Speaker 2: And it creates a nuance that is, you know, certainly

449
00:23:28,636 --> 00:23:29,836
Speaker 2: in today's.

450
00:23:29,436 --> 00:23:30,996
Speaker 1: You don't want a person buy the wheel. It's the

451
00:23:31,036 --> 00:23:33,116
Speaker 1: whole point. It's the whole point. It's you don't want

452
00:23:33,116 --> 00:23:34,356
Speaker 1: a person buy the wheel, right.

453
00:23:34,476 --> 00:23:38,076
Speaker 2: Totally agree. But in terms of the development and delivery

454
00:23:38,076 --> 00:23:40,556
Speaker 2: of what we're building, it just doesn't matter, right, it's

455
00:23:40,556 --> 00:23:41,876
Speaker 2: a complete nothing.

456
00:23:41,956 --> 00:23:44,236
Speaker 1: Well, I mean that's some margin. It matters at some point,

457
00:23:44,316 --> 00:23:46,276
Speaker 1: it matters, right. The whole premise is you can do

458
00:23:46,316 --> 00:23:49,476
Speaker 1: it without a person there, and so like at some point,

459
00:23:49,756 --> 00:23:52,996
Speaker 1: like relatively soon, I would imagine you need to do

460
00:23:53,036 --> 00:23:53,996
Speaker 1: it without a person there.

461
00:23:54,356 --> 00:23:58,316
Speaker 2: That's right, and uh, look forward to doing that soon.

462
00:24:00,956 --> 00:24:14,516
Speaker 3: We'll be back in just a minute.

463
00:24:14,836 --> 00:24:16,996
Speaker 1: Yeah, So where are you now, Like, give me where

464
00:24:16,996 --> 00:24:20,916
Speaker 1: we're basically to the present now after our twenty year journey,

465
00:24:21,156 --> 00:24:24,796
Speaker 1: Like what's like, are you are people paying you to

466
00:24:24,956 --> 00:24:25,556
Speaker 1: haul stuff.

467
00:24:25,916 --> 00:24:29,996
Speaker 2: Yeah, absolutely, So to like today is an incredibly exciting moment.

468
00:24:30,596 --> 00:24:32,796
Speaker 2: So we have a technology that can drive a truck.

469
00:24:32,876 --> 00:24:36,036
Speaker 2: It has the skills necessary to drive on the freeway

470
00:24:36,116 --> 00:24:40,436
Speaker 2: and drive to sites off the freeway in these industrial

471
00:24:40,476 --> 00:24:44,076
Speaker 2: park areas, and it does that safely. And then internally

472
00:24:44,116 --> 00:24:47,156
Speaker 2: we've got the capability say, okay, what are the new

473
00:24:47,196 --> 00:24:50,876
Speaker 2: features we need to make this more useful for our customers.

474
00:24:51,396 --> 00:24:55,516
Speaker 2: And so we launched in April. About three months later

475
00:24:55,956 --> 00:24:57,916
Speaker 2: we were able to show, you know, be able to

476
00:24:57,996 --> 00:25:00,756
Speaker 2: launch the next version that now doesn't just operate day

477
00:25:00,836 --> 00:25:03,956
Speaker 2: in the daytime, but operates at night as well. And

478
00:25:04,036 --> 00:25:06,156
Speaker 2: of the course the rest of this year, it's really

479
00:25:06,196 --> 00:25:09,596
Speaker 2: about taking and building the you know, in enhancing the

480
00:25:09,596 --> 00:25:11,716
Speaker 2: skills that it has to add the few new skills

481
00:25:11,756 --> 00:25:14,236
Speaker 2: it needs to be able to drive between Fort Worth

482
00:25:14,436 --> 00:25:17,796
Speaker 2: and Phoenix and El Paso. And so at that point, just.

483
00:25:17,756 --> 00:25:20,276
Speaker 1: To be clear, the route you have now is Houston Dallas,

484
00:25:20,356 --> 00:25:20,716
Speaker 1: Is that right?

485
00:25:20,716 --> 00:25:23,156
Speaker 2: That's right? I'm sorry, We drive tween thousand Houston and

486
00:25:23,196 --> 00:25:24,596
Speaker 2: by the end of the year we expect to be

487
00:25:24,676 --> 00:25:28,956
Speaker 2: driving between Fort Worth and Phoenix. And what's exciting about

488
00:25:29,036 --> 00:25:31,876
Speaker 2: and fort Worth and El Paso and El Paso and Phoenix.

489
00:25:33,156 --> 00:25:37,036
Speaker 2: And what's exciting about that is fort worth of Phoenix

490
00:25:37,116 --> 00:25:40,716
Speaker 2: is a thousand miles and a person is not able

491
00:25:40,756 --> 00:25:45,236
Speaker 2: to legally drive that in a day, And so we'll

492
00:25:45,236 --> 00:25:48,956
Speaker 2: be able to start doing things that are superhuman in

493
00:25:49,156 --> 00:25:50,236
Speaker 2: more and more dimensions.

494
00:25:50,636 --> 00:25:54,276
Speaker 1: Presumably the value preposition is really long drives, right, Like

495
00:25:55,316 --> 00:25:58,276
Speaker 1: it makes absolutely no sense for whatever one hundred miles

496
00:25:58,356 --> 00:26:00,636
Speaker 1: or something. And the longer it gets, the more the

497
00:26:00,676 --> 00:26:01,636
Speaker 1: economics makes sense.

498
00:26:01,716 --> 00:26:04,276
Speaker 2: Is that right? I mean, that's think it makes sense

499
00:26:04,316 --> 00:26:07,236
Speaker 2: across all different kinds of scales smiles. But I think

500
00:26:07,276 --> 00:26:09,876
Speaker 2: we're the biggest impact we'll ultimately is on these long

501
00:26:09,876 --> 00:26:10,476
Speaker 2: call trips.

502
00:26:11,156 --> 00:26:17,796
Speaker 1: And like, I get the freeway part in Broadway, How

503
00:26:17,796 --> 00:26:20,676
Speaker 1: does the not on the freeway part work? How constrained

504
00:26:20,716 --> 00:26:22,596
Speaker 1: are you as to where you can go when you're

505
00:26:22,636 --> 00:26:23,516
Speaker 1: not on the freeway.

506
00:26:23,796 --> 00:26:26,436
Speaker 2: Yeah, So the capability we're building is to be able

507
00:26:26,476 --> 00:26:32,076
Speaker 2: to drive everywhere. Sure, but like now, so today we

508
00:26:32,716 --> 00:26:36,596
Speaker 2: drive from a place that's off the freeway onto the freeway,

509
00:26:37,036 --> 00:26:39,196
Speaker 2: and then when we get in at the Dallas end

510
00:26:39,196 --> 00:26:41,276
Speaker 2: of the route, and then at the Houston end, we

511
00:26:41,356 --> 00:26:44,156
Speaker 2: drive about five miles from where we get off the

512
00:26:44,196 --> 00:26:48,076
Speaker 2: freeway to our terminal side, and along the way we

513
00:26:48,236 --> 00:26:51,756
Speaker 2: drive past customer locations. So we're making the choice today

514
00:26:51,756 --> 00:26:57,956
Speaker 2: to go to our terminals, but it's relatively straightforward to

515
00:26:57,996 --> 00:26:59,836
Speaker 2: stop and go to a different terminal instead or a

516
00:26:59,876 --> 00:27:00,636
Speaker 2: different See.

517
00:27:01,596 --> 00:27:05,836
Speaker 1: Like, how hard is that off the freeway part, the

518
00:27:05,916 --> 00:27:10,076
Speaker 1: sort of marginal you know, mile when not on the freeway?

519
00:27:11,196 --> 00:27:14,836
Speaker 2: Not, right, would be the short answer. Right, it's you know,

520
00:27:16,356 --> 00:27:18,676
Speaker 2: we've put a lot of for for a lot of time,

521
00:27:18,756 --> 00:27:21,636
Speaker 2: the primary focus what we're building was the freeway part, because,

522
00:27:22,236 --> 00:27:26,156
Speaker 2: as you pointed out, that's where the most kinetic energy is.

523
00:27:26,196 --> 00:27:30,756
Speaker 2: That's where you know, that's where the bad things could happen. Yeah.

524
00:27:30,836 --> 00:27:33,956
Speaker 1: I mean it's also simpler in certain ways, right, Like

525
00:27:34,196 --> 00:27:36,996
Speaker 1: it seems like turning a big truck around or just

526
00:27:37,076 --> 00:27:38,796
Speaker 1: getting a truck around. Like I live in New York

527
00:27:38,836 --> 00:27:41,196
Speaker 1: City and I see eighteen wheelers in New York City,

528
00:27:41,676 --> 00:27:44,836
Speaker 1: and I don't know, maybe that's maybe that's not that

529
00:27:44,916 --> 00:27:47,716
Speaker 1: hard to engineer for autonomy. You tell me it seems hard.

530
00:27:47,716 --> 00:27:48,476
Speaker 1: It looks hard.

531
00:27:48,676 --> 00:27:51,716
Speaker 2: Yeah, I think New York City is hard, right, And

532
00:27:51,756 --> 00:27:53,436
Speaker 2: I think there'll be a time where we get to

533
00:27:53,476 --> 00:27:56,676
Speaker 2: that where I'm really focused and we're really focused on

534
00:27:56,756 --> 00:27:58,756
Speaker 2: in the near term is how do we get to

535
00:27:58,756 --> 00:28:02,116
Speaker 2: the place where most freight moves right, And a lot

536
00:28:02,116 --> 00:28:06,836
Speaker 2: of that will go to these industrial parks in regions

537
00:28:06,836 --> 00:28:10,516
Speaker 2: of a city. And the reason why it's hard to

538
00:28:10,596 --> 00:28:13,796
Speaker 2: drive a truck in New York City right, and it's slow.

539
00:28:14,236 --> 00:28:16,476
Speaker 2: And so if you're trying to build a distribution center

540
00:28:16,516 --> 00:28:18,796
Speaker 2: for these Class eight tractors and trailers, you put them

541
00:28:18,796 --> 00:28:21,676
Speaker 2: in places where it's convenient because you're trying to run

542
00:28:21,716 --> 00:28:24,596
Speaker 2: a business, not build a technology showcase.

543
00:28:25,316 --> 00:28:29,996
Speaker 1: So what can you not do now ya?

544
00:28:30,996 --> 00:28:34,756
Speaker 2: So today we can't drive in the rain. Well, in fact,

545
00:28:34,836 --> 00:28:36,876
Speaker 2: that's not actually true. So today we drive in the

546
00:28:36,956 --> 00:28:42,116
Speaker 2: rain really well, but we haven't validated that fully for

547
00:28:42,236 --> 00:28:45,196
Speaker 2: driverless operations. And this is really an important idea, right,

548
00:28:45,276 --> 00:28:47,676
Speaker 2: is if you came down to Texas and got a

549
00:28:47,756 --> 00:28:49,516
Speaker 2: ride in one of our trucks and it was raining out,

550
00:28:50,516 --> 00:28:54,436
Speaker 2: it would work, and you would go, huh, why if

551
00:28:54,436 --> 00:28:56,756
Speaker 2: you guys not launched this, and we would say, yeah,

552
00:28:56,916 --> 00:29:00,636
Speaker 2: it basically works. But that's not good enough. It's not

553
00:29:00,676 --> 00:29:02,596
Speaker 2: good enough that it feels like it works. What we

554
00:29:02,676 --> 00:29:03,516
Speaker 2: want to have done is.

555
00:29:03,476 --> 00:29:07,036
Speaker 1: All basically it makes me nervous with a ten roil truck.

556
00:29:07,076 --> 00:29:09,996
Speaker 2: Exactly and it should right, And so we put a

557
00:29:10,036 --> 00:29:13,356
Speaker 2: lot of effort into making sure that it doesn't just

558
00:29:13,436 --> 00:29:15,956
Speaker 2: seem like it works, but we have conviction that it

559
00:29:15,996 --> 00:29:21,036
Speaker 2: will work right. And you know, as an example, two

560
00:29:21,076 --> 00:29:24,956
Speaker 2: of the last things that we we got checked off

561
00:29:24,996 --> 00:29:30,916
Speaker 2: when we launch, where it's one really high speed motorbikes

562
00:29:31,396 --> 00:29:34,996
Speaker 2: running red lights in the city. So we had done

563
00:29:35,036 --> 00:29:37,956
Speaker 2: a bunch of testing, I think up to let me say,

564
00:29:38,116 --> 00:29:39,796
Speaker 2: I'm gonna say some numbers here. These are probably not

565
00:29:39,836 --> 00:29:42,996
Speaker 2: quite right, but I'll use some numbers, you know, at

566
00:29:43,076 --> 00:29:45,596
Speaker 2: ninety miles an hour, because we figure, you know, ninety

567
00:29:45,636 --> 00:29:48,636
Speaker 2: miles an hour in a surface road, nobody.

568
00:29:48,396 --> 00:29:50,516
Speaker 1: Need the motorcycles going ninety.

569
00:29:50,636 --> 00:29:53,116
Speaker 2: Motorcycles going ninety miles an hour and they're going to

570
00:29:53,196 --> 00:29:55,396
Speaker 2: run a red light in front of us, and we

571
00:29:55,436 --> 00:29:57,476
Speaker 2: want the truck to not hit that motorbike. And then

572
00:29:57,516 --> 00:29:59,516
Speaker 2: we're on the freeway and we see a motorbike doing

573
00:29:59,556 --> 00:30:03,076
Speaker 2: one hundred and fifty miles an hour, and we're like, okay,

574
00:30:03,116 --> 00:30:07,596
Speaker 2: that is let's go make sure that that works right,

575
00:30:07,636 --> 00:30:10,956
Speaker 2: because you know, at some point we just want to

576
00:30:10,996 --> 00:30:12,716
Speaker 2: have comps. And so we went through and we found

577
00:30:12,756 --> 00:30:17,316
Speaker 2: out that when motorbike's going that extremely fast. First, we

578
00:30:18,036 --> 00:30:20,636
Speaker 2: found that our simulation wasn't quite up to snuff to

579
00:30:20,676 --> 00:30:22,196
Speaker 2: deal with that, so we had to go fix that.

580
00:30:23,316 --> 00:30:26,916
Speaker 2: And then we found that our perception system wasn't able

581
00:30:26,996 --> 00:30:28,876
Speaker 2: to quite track it as well as we'd want, so

582
00:30:28,916 --> 00:30:31,356
Speaker 2: we had some things to fix there, and so ultimately

583
00:30:31,436 --> 00:30:33,276
Speaker 2: we got to the point where if you're a motorbike,

584
00:30:33,716 --> 00:30:36,716
Speaker 2: please don't go test this run in a red light

585
00:30:36,716 --> 00:30:38,836
Speaker 2: at one hundred and fifty miles an hour. We're going

586
00:30:38,916 --> 00:30:41,236
Speaker 2: to see you and assuming you know, we can actually

587
00:30:41,236 --> 00:30:42,836
Speaker 2: see you, because there's not a building in the way,

588
00:30:43,356 --> 00:30:46,316
Speaker 2: we're going to stop and you know, not have an

589
00:30:46,316 --> 00:30:46,876
Speaker 2: event with you.

590
00:30:47,396 --> 00:30:50,836
Speaker 1: So is the rain analog of that, like more rain

591
00:30:50,916 --> 00:30:54,316
Speaker 1: than I can imagine and flooding and it's dark or something.

592
00:30:54,396 --> 00:30:57,876
Speaker 1: I mean, yeah, maybe frozen frozen also.

593
00:30:58,156 --> 00:31:01,676
Speaker 2: And so this is this is the answers. We we

594
00:31:01,756 --> 00:31:03,996
Speaker 2: have some good ideas of what these challenges are, and

595
00:31:04,076 --> 00:31:06,036
Speaker 2: so we're in the process of putting place the last

596
00:31:06,036 --> 00:31:08,916
Speaker 2: of the tests that we need to say yeah, across

597
00:31:08,956 --> 00:31:12,556
Speaker 2: the things that might be a problem, we actually handle

598
00:31:12,596 --> 00:31:13,756
Speaker 2: those in a way that's safe.

599
00:31:14,156 --> 00:31:16,196
Speaker 1: Once you got rain, are you good? I mean, I

600
00:31:16,196 --> 00:31:20,756
Speaker 1: guess you have the whole southern US without snow and ice? Right, Well,

601
00:31:20,876 --> 00:31:23,476
Speaker 1: think it not freezes in Texas? Right? Does it freeze in?

602
00:31:23,796 --> 00:31:26,596
Speaker 2: Does we get we get snow in Texas? And but

603
00:31:27,036 --> 00:31:29,916
Speaker 2: the good news is, like the reason why a lot

604
00:31:29,956 --> 00:31:33,676
Speaker 2: of freight moves wrong the sun belt is because trucks

605
00:31:33,796 --> 00:31:36,916
Speaker 2: don't like driving in snow. Right, It's just, you know,

606
00:31:36,996 --> 00:31:39,036
Speaker 2: much like people in general don't like driving in snow.

607
00:31:39,236 --> 00:31:40,796
Speaker 2: But there is snow. But if you've ever been in

608
00:31:40,836 --> 00:31:43,036
Speaker 2: Texas when there's a snowstorm, it basically shuts down.

609
00:31:43,396 --> 00:31:46,076
Speaker 1: Yeah, so you don't you don't have to solve snow.

610
00:31:46,156 --> 00:31:48,036
Speaker 1: You don't have to solve snow for now.

611
00:31:48,076 --> 00:31:50,956
Speaker 2: For now. But we will solve snow, right because all

612
00:31:50,996 --> 00:31:52,916
Speaker 2: of the stuff that works for rain mostly works for snow.

613
00:31:52,956 --> 00:31:55,436
Speaker 1: To me, all of these problems we can stipulate will

614
00:31:55,476 --> 00:31:58,716
Speaker 1: be solved by somebody, right, Yeah, plausibly by you, if

615
00:31:58,716 --> 00:32:01,156
Speaker 1: not you, by somebody else. But like I feel like

616
00:32:01,196 --> 00:32:04,676
Speaker 1: there's some sense of urgency. Like I'll say so interestingly,

617
00:32:04,876 --> 00:32:09,996
Speaker 1: just purely coincidentally, I talked to uh Worris softman?

618
00:32:10,116 --> 00:32:10,916
Speaker 2: Is it softman? Yeah?

619
00:32:10,916 --> 00:32:13,676
Speaker 1: Have his name is Med and so he said, and

620
00:32:13,716 --> 00:32:16,076
Speaker 1: we were not talking about you. This was not a

621
00:32:16,116 --> 00:32:18,036
Speaker 1: dig on you. It was more talking about why he's

622
00:32:18,116 --> 00:32:21,636
Speaker 1: doing what he's doing. He said, I don't think Open

623
00:32:21,676 --> 00:32:25,596
Speaker 1: Road Autonomy is a startup game. Uh. And he basically

624
00:32:25,836 --> 00:32:28,156
Speaker 1: you probably know he thinks, I mean, he basically thinks

625
00:32:28,156 --> 00:32:29,236
Speaker 1: it's too expensive.

626
00:32:29,636 --> 00:32:29,876
Speaker 2: Yeah.

627
00:32:29,956 --> 00:32:32,796
Speaker 1: In short, too expensive and too hard in that way

628
00:32:33,436 --> 00:32:35,756
Speaker 1: for a company that is capital constrained, for a company

629
00:32:35,756 --> 00:32:37,796
Speaker 1: that you know doesn't have a monopoly on search.

630
00:32:37,956 --> 00:32:38,476
Speaker 2: Let's see.

631
00:32:39,156 --> 00:32:40,796
Speaker 1: And so I do feel like in talking to you

632
00:32:40,956 --> 00:32:43,996
Speaker 1: like I, you plausibly may solve them. But there must

633
00:32:44,036 --> 00:32:46,476
Speaker 1: be some clock for you, right, You must have to

634
00:32:46,516 --> 00:32:50,436
Speaker 1: get to a point where you're making money relatively soon.

635
00:32:50,556 --> 00:32:52,396
Speaker 2: Is that right? Yeah, Well we've been at the game

636
00:32:52,436 --> 00:32:54,996
Speaker 2: for a while. You know, we went into an eyes

637
00:32:55,036 --> 00:32:58,196
Speaker 2: open right and looked at the you know, having spent

638
00:32:58,236 --> 00:33:00,276
Speaker 2: the time with Waymo, having the history I have, I

639
00:33:00,396 --> 00:33:02,676
Speaker 2: was like, this is not one hundred million dollar problem

640
00:33:02,796 --> 00:33:04,476
Speaker 2: or a ten million dollar problem. This is a multi

641
00:33:04,476 --> 00:33:08,276
Speaker 2: billion dollar problem. And so as we've built Aurora, it's

642
00:33:08,316 --> 00:33:11,676
Speaker 2: been Okay, we need to set ourselves up with the staff,

643
00:33:11,676 --> 00:33:13,996
Speaker 2: we need to set ourselves up with the capital partners,

644
00:33:13,996 --> 00:33:17,916
Speaker 2: we need to set ourselves up with the technology partners

645
00:33:18,596 --> 00:33:20,676
Speaker 2: that allow us to take that run. And I think

646
00:33:20,716 --> 00:33:23,156
Speaker 2: we've been very careful about how we've done that, and

647
00:33:23,156 --> 00:33:25,116
Speaker 2: we've put ourselves in a position to succeed. And I

648
00:33:25,116 --> 00:33:28,356
Speaker 2: agree with with Boris this is you know, I hear

649
00:33:28,396 --> 00:33:30,476
Speaker 2: people throwing out, oh, we're gonna, you know, spend one

650
00:33:30,516 --> 00:33:32,676
Speaker 2: hundred million dollars to do this. I think, you know,

651
00:33:32,916 --> 00:33:38,756
Speaker 2: you haven't even met the ante, right, And so for us,

652
00:33:39,796 --> 00:33:41,796
Speaker 2: we look at say, driving in the rain, we expect

653
00:33:41,796 --> 00:33:44,956
Speaker 2: to be solving that by the end of this year, right,

654
00:33:44,996 --> 00:33:47,916
Speaker 2: And at that point, as you point out, we've basically

655
00:33:47,996 --> 00:33:51,556
Speaker 2: unlocked the Southern freight belt. The amount of truck travel

656
00:33:51,596 --> 00:33:56,796
Speaker 2: that's there is gigantic, and so you know, from now

657
00:33:56,796 --> 00:33:58,956
Speaker 2: where we have a small number of trucks in the road,

658
00:33:59,276 --> 00:34:01,276
Speaker 2: by the end of next year, end of twenty six,

659
00:34:01,356 --> 00:34:04,716
Speaker 2: we expect to have a few hundred trucks on the road,

660
00:34:05,076 --> 00:34:06,796
Speaker 2: and then the year after that we expect to have

661
00:34:06,836 --> 00:34:09,076
Speaker 2: one thousand plus trucks on the road, and then we'll

662
00:34:09,156 --> 00:34:14,116
Speaker 2: built from there. And so it's you know, the conviction

663
00:34:14,156 --> 00:34:16,276
Speaker 2: we're starting to build internally, like yeah, this is just

664
00:34:16,276 --> 00:34:17,956
Speaker 2: just turn over the kind of the way we want it,

665
00:34:17,956 --> 00:34:20,396
Speaker 2: and we expect it is happening now and so it's

666
00:34:20,396 --> 00:34:22,556
Speaker 2: not a hypothetical. It some day we'll solve it. It's like, no,

667
00:34:22,796 --> 00:34:27,316
Speaker 2: we're you know, four or five months kind of time frame. So, well,

668
00:34:27,356 --> 00:34:28,396
Speaker 2: three four months timeframe.

669
00:34:28,836 --> 00:34:29,996
Speaker 1: What's the business model?

670
00:34:31,156 --> 00:34:34,476
Speaker 2: Yeah, so our business model is to work with the

671
00:34:34,516 --> 00:34:37,556
Speaker 2: ecosystem that's there today. So today, if you're a truck

672
00:34:37,596 --> 00:34:39,476
Speaker 2: and company, you buy a truck and then you pay

673
00:34:39,476 --> 00:34:42,436
Speaker 2: somebody to drive that truck for you. Uh, and so

674
00:34:42,996 --> 00:34:45,116
Speaker 2: that's what our company's going to do. You'll if you're

675
00:34:45,996 --> 00:34:48,396
Speaker 2: a company and wants some Automas truck, you're gonna go

676
00:34:48,436 --> 00:34:50,716
Speaker 2: to pac r and peter Bilt, or you're going to

677
00:34:50,756 --> 00:34:52,276
Speaker 2: go in Evolve and say I want to buy a truck,

678
00:34:52,956 --> 00:34:56,996
Speaker 2: and they buy the truck stuff and then it'll roll

679
00:34:57,076 --> 00:34:59,516
Speaker 2: off the line from our partner and it'll have the

680
00:34:59,636 --> 00:35:01,996
Speaker 2: row driver installed on it and you'll pay a subscription

681
00:35:02,156 --> 00:35:04,556
Speaker 2: to Aurora to drive that truck for you.

682
00:35:04,996 --> 00:35:08,916
Speaker 1: I see. Okay, So so you guys get paid by

683
00:35:08,956 --> 00:35:12,036
Speaker 1: the by the mile or by the by the hall

684
00:35:12,196 --> 00:35:12,956
Speaker 1: or something like that.

685
00:35:13,316 --> 00:35:16,476
Speaker 2: Yeah, that's exactly right. You know, it's at the risk

686
00:35:16,516 --> 00:35:19,356
Speaker 2: of at a service as a services you know, it's

687
00:35:19,476 --> 00:35:21,956
Speaker 2: driver as a service. That's the way we were thinking

688
00:35:21,956 --> 00:35:22,636
Speaker 2: about the business.

689
00:35:23,356 --> 00:35:25,356
Speaker 1: And the trucking company is buying the truck, So that's

690
00:35:25,396 --> 00:35:26,876
Speaker 1: good for you. You don't have to When you say

691
00:35:26,916 --> 00:35:28,756
Speaker 1: you'll have a thousand trucks out there, you don't mean

692
00:35:28,796 --> 00:35:30,436
Speaker 1: you're going to own a thousand trucks. You mean you'll

693
00:35:30,476 --> 00:35:33,356
Speaker 1: have essentially a thousand autonomous drivers in trucks that other

694
00:35:33,396 --> 00:35:33,836
Speaker 1: people own.

695
00:35:34,036 --> 00:35:36,876
Speaker 2: That's right, And this is because that's what our customers

696
00:35:36,876 --> 00:35:39,876
Speaker 2: want right that there Also it.

697
00:35:39,916 --> 00:35:42,836
Speaker 1: Seems easier as a business, and I still not have

698
00:35:42,916 --> 00:35:44,596
Speaker 1: to get into the trucking business.

699
00:35:44,916 --> 00:35:47,556
Speaker 2: I agreed again back to the philosophy of we think

700
00:35:47,556 --> 00:35:50,796
Speaker 2: we're really good at building the driver. And I look

701
00:35:50,836 --> 00:35:54,396
Speaker 2: at our partners, whether it's Werner or Hirshbock or Federal Express,

702
00:35:55,276 --> 00:35:57,436
Speaker 2: they know what they're doing. Why don't we help them

703
00:35:57,436 --> 00:36:00,196
Speaker 2: make their business a bit better and work together?

704
00:36:03,676 --> 00:36:06,076
Speaker 1: Can we talk about autonomy a little bit more broadly,

705
00:36:06,196 --> 00:36:08,356
Speaker 1: just since you're at it so long and I'm curious

706
00:36:08,396 --> 00:36:12,516
Speaker 1: what you think, So, like, what do you think are

707
00:36:12,516 --> 00:36:17,396
Speaker 1: the important constraints on autonomous vehicles right now? Sort of

708
00:36:17,436 --> 00:36:21,116
Speaker 1: broadly technologically, you know, in terms of policy.

709
00:36:21,876 --> 00:36:25,716
Speaker 2: I think it's primarily technological right now. Okay, right, And

710
00:36:25,756 --> 00:36:28,196
Speaker 2: I've said that. You know, people for for the better

711
00:36:28,196 --> 00:36:30,676
Speaker 2: part of a decade have been you know, when when

712
00:36:30,676 --> 00:36:34,996
Speaker 2: it's convenient hiding behind you know, regulation or policy. And

713
00:36:35,556 --> 00:36:38,716
Speaker 2: you know, the US policy of regulatory environment is permissive.

714
00:36:38,836 --> 00:36:40,876
Speaker 2: It's one of the things that's allowed innovation to flourish

715
00:36:40,916 --> 00:36:43,956
Speaker 2: in this country, certainly in the automotive space.

716
00:36:44,516 --> 00:36:47,876
Speaker 1: So what are the what are the important technological constraints

717
00:36:47,916 --> 00:36:51,996
Speaker 1: right now? Like, I mean, obviously WEIMO is thriving where

718
00:36:52,036 --> 00:36:55,676
Speaker 1: it's living, but like, also there are no autonomous cars

719
00:36:55,676 --> 00:36:57,956
Speaker 1: where I live and people aren't buying them, and so

720
00:36:58,076 --> 00:37:01,196
Speaker 1: like what's the what's what are the important bottlenecks right now?

721
00:37:01,716 --> 00:37:06,676
Speaker 2: Uh? Execution madwidth? Right? Like, So so at least where

722
00:37:06,676 --> 00:37:10,276
Speaker 2: I sit at a roar today, I don't out and see,

723
00:37:10,436 --> 00:37:12,076
Speaker 2: Oh my gosh, I don't know how we're going to

724
00:37:12,116 --> 00:37:16,116
Speaker 2: solve that. It's hey, we have this many people, we

725
00:37:16,196 --> 00:37:18,436
Speaker 2: have this much leadership band with we just need to

726
00:37:18,436 --> 00:37:20,036
Speaker 2: go execute right.

727
00:37:19,916 --> 00:37:24,196
Speaker 1: Like thinking industry wide and not to be like petty

728
00:37:24,276 --> 00:37:26,756
Speaker 1: or something, but like why aren't autonomous cars everywhere?

729
00:37:26,836 --> 00:37:29,716
Speaker 2: Right? Yeah? Because it's really hard, right, And I think

730
00:37:29,796 --> 00:37:34,156
Speaker 2: the right metaphor for this is commercial aviation, like the

731
00:37:34,156 --> 00:37:36,516
Speaker 2: physics are really in grasp and like you can both

732
00:37:36,556 --> 00:37:40,636
Speaker 2: things together. And yet you know, we basically have two

733
00:37:42,756 --> 00:37:46,916
Speaker 2: commercial aviation manufacturers globally, right, we have Boeing and Airbus.

734
00:37:47,076 --> 00:37:49,956
Speaker 1: Because it's hard to build big jet aircraft.

735
00:37:50,636 --> 00:37:53,156
Speaker 2: It's hard to build them, it's hard to have conviction

736
00:37:53,196 --> 00:37:56,396
Speaker 2: they're going to be safe, it's hard to produce them right.

737
00:37:56,436 --> 00:37:58,396
Speaker 2: And when I look at automated driving, I think it's

738
00:37:58,396 --> 00:38:01,356
Speaker 2: in a very similar space in that a lot of

739
00:38:01,396 --> 00:38:03,676
Speaker 2: things have to work well. You have to have the

740
00:38:03,756 --> 00:38:05,996
Speaker 2: discipline to be able to work across all of them,

741
00:38:06,076 --> 00:38:08,836
Speaker 2: make sure they all fit together, and then you have

742
00:38:08,876 --> 00:38:12,236
Speaker 2: to have the processes. And process in Silicon Valley is

743
00:38:12,276 --> 00:38:14,076
Speaker 2: often kind of a four letter word, like you know,

744
00:38:14,076 --> 00:38:16,356
Speaker 2: you've got to move past and break things, but when

745
00:38:16,396 --> 00:38:19,916
Speaker 2: you're building something safety critical, you actually have to get

746
00:38:19,956 --> 00:38:22,836
Speaker 2: that stuff right, and the art is getting it right,

747
00:38:22,956 --> 00:38:24,556
Speaker 2: we'll also be able to do it quickly.

748
00:38:25,556 --> 00:38:30,396
Speaker 1: So so when you think about the spread of autonomy

749
00:38:30,436 --> 00:38:33,876
Speaker 1: from here, again not just within your company, but sort

750
00:38:33,876 --> 00:38:37,156
Speaker 1: of more broadly, like how do you think it'll play out?

751
00:38:37,596 --> 00:38:40,756
Speaker 2: I think it's going to usher incredible new age all right,

752
00:38:40,836 --> 00:38:48,276
Speaker 2: that we should be able to dramatically reduce traffic fatalities.

753
00:38:48,316 --> 00:38:51,476
Speaker 2: The fact that you know, it had been a decade

754
00:38:51,516 --> 00:38:55,876
Speaker 2: without a fatality on civil aviation, and yet we had

755
00:38:55,876 --> 00:38:58,076
Speaker 2: forty thousand people killed on the road every year in

756
00:38:58,076 --> 00:39:01,276
Speaker 2: the US. Like, we can bring a technology to bear

757
00:39:01,316 --> 00:39:03,796
Speaker 2: to help solve this, right, and I think that's profound.

758
00:39:03,796 --> 00:39:06,756
Speaker 2: I think we can have a huge sustainability impact all

759
00:39:06,796 --> 00:39:12,116
Speaker 2: while actually kind of power up the US economy. And

760
00:39:12,196 --> 00:39:14,396
Speaker 2: so for us, you know, we've got this mission right

761
00:39:14,396 --> 00:39:17,556
Speaker 2: now that's focused on trucking, but what we're really building

762
00:39:17,636 --> 00:39:22,236
Speaker 2: is this capability to release safety critical software and systems

763
00:39:22,836 --> 00:39:25,636
Speaker 2: and this ability to understand the world. And so you

764
00:39:25,676 --> 00:39:27,596
Speaker 2: combine those two things, the places we can go with

765
00:39:27,596 --> 00:39:30,516
Speaker 2: that are profound, right, whether it is you know, last

766
00:39:30,556 --> 00:39:34,996
Speaker 2: mile delivery or ride hailing applications, or mining or farming

767
00:39:35,276 --> 00:39:37,436
Speaker 2: or aviation. Like there's it's just going to be a

768
00:39:37,436 --> 00:39:40,396
Speaker 2: lot of fun over the next decade. So yeah, I'm

769
00:39:40,396 --> 00:39:41,036
Speaker 2: psyched for it.

770
00:39:41,756 --> 00:39:45,836
Speaker 1: Next decade sounds fast given the pace so far. I

771
00:39:45,876 --> 00:39:48,476
Speaker 1: was surprised when you said next decade at the end there.

772
00:39:48,676 --> 00:39:52,356
Speaker 2: Yeah, I think that like anything, there's a point where

773
00:39:52,396 --> 00:39:57,916
Speaker 2: you have built a foundational base and then suddenly you're like, oh,

774
00:39:58,356 --> 00:40:00,316
Speaker 2: now I have this power. Now I have the superpower

775
00:40:00,356 --> 00:40:01,276
Speaker 2: to go do these things.

776
00:40:01,676 --> 00:40:04,556
Speaker 1: It's basically the package of hardware plus software at a

777
00:40:04,556 --> 00:40:06,956
Speaker 1: reductive level, and you can sort of put it on

778
00:40:07,036 --> 00:40:09,076
Speaker 1: other things and it'll more or less work.

779
00:40:09,356 --> 00:40:12,956
Speaker 2: More importantly the process and the data and again does

780
00:40:12,996 --> 00:40:14,476
Speaker 2: not sound sexy.

781
00:40:14,756 --> 00:40:17,356
Speaker 1: But the data sounds sexy, Like the more you talk

782
00:40:17,356 --> 00:40:20,076
Speaker 1: to machine learning people, the more sexy data sounds. Right.

783
00:40:20,276 --> 00:40:23,116
Speaker 2: Yeah, And you know, and we joke internally, you know,

784
00:40:23,156 --> 00:40:26,076
Speaker 2: if you if we have three kind of big artifacts,

785
00:40:26,116 --> 00:40:30,076
Speaker 2: being our software, our data, and our process, if you

786
00:40:30,076 --> 00:40:31,876
Speaker 2: held my gun in my head and said delete one

787
00:40:31,916 --> 00:40:37,116
Speaker 2: of them, I'd say delete the software, right, Please do

788
00:40:37,196 --> 00:40:38,316
Speaker 2: not delete our software.

789
00:40:40,116 --> 00:40:46,036
Speaker 1: Yeah, that's really interesting. Yeah, we'll be back in a

790
00:40:46,076 --> 00:40:59,236
Speaker 1: minute with the life around. We're gonna finish with the

791
00:40:59,316 --> 00:41:01,796
Speaker 1: lightning round. I appreciate your time, and we were almost done.

792
00:41:02,156 --> 00:41:03,596
Speaker 2: Cool. Thanks for the conversation.

793
00:41:05,756 --> 00:41:08,276
Speaker 1: So right that your father was a prison warden he was,

794
00:41:08,316 --> 00:41:11,916
Speaker 1: in fact, Yeah, did you learn any management and were

795
00:41:11,956 --> 00:41:13,196
Speaker 1: parenting tips from him?

796
00:41:14,636 --> 00:41:19,756
Speaker 2: Lock them up? Uh? No, absolutely not. You know. One

797
00:41:19,756 --> 00:41:22,796
Speaker 2: of the things that that stuck with me is, you know,

798
00:41:22,796 --> 00:41:25,396
Speaker 2: it's it's a difficult job being a prison warden because

799
00:41:26,076 --> 00:41:28,596
Speaker 2: you have the staff and then you have the inmates

800
00:41:29,276 --> 00:41:34,836
Speaker 2: and right, and and they're often at odds. And one

801
00:41:34,836 --> 00:41:36,236
Speaker 2: of the things he said was, you know, make sure

802
00:41:36,236 --> 00:41:38,996
Speaker 2: you treat everyone with respect. Right that he would, you know,

803
00:41:39,036 --> 00:41:42,196
Speaker 2: these are people who had made a mistake in life,

804
00:41:42,636 --> 00:41:46,196
Speaker 2: you know, and you treat them with respect. Uh. And

805
00:41:46,596 --> 00:41:48,756
Speaker 2: you know, I think that's really powerful and important.

806
00:41:49,916 --> 00:41:51,596
Speaker 1: What's one thing you learned working at Google?

807
00:41:53,076 --> 00:41:56,076
Speaker 2: I think big, right, I think I think that was,

808
00:41:58,396 --> 00:42:01,476
Speaker 2: you know, Larry and Sergey never lacked for vision, and

809
00:42:01,556 --> 00:42:04,756
Speaker 2: I think you can often find yourself constrained by kind

810
00:42:04,796 --> 00:42:07,116
Speaker 2: of your own kind of sense of what's a limit,

811
00:42:07,636 --> 00:42:10,316
Speaker 2: and they just thinking like, no, what, why can't you

812
00:42:10,396 --> 00:42:13,156
Speaker 2: do that? Why can't you do that? Yeah?

813
00:42:13,196 --> 00:42:16,716
Speaker 1: I remember, just as a consumer, just as a as

814
00:42:16,716 --> 00:42:20,556
Speaker 1: an ordinary person in the world, when they started what

815
00:42:20,716 --> 00:42:23,316
Speaker 1: became Google street View, I was like, yeah, surely you

816
00:42:23,356 --> 00:42:27,596
Speaker 1: can't take a picture of every bit of every road

817
00:42:27,716 --> 00:42:31,516
Speaker 1: in America, and actually you can and they did.

818
00:42:31,796 --> 00:42:34,476
Speaker 2: Yeah. Right. Like I think that that sense of like

819
00:42:34,676 --> 00:42:36,636
Speaker 2: you don't need to be intimidated by this, like you

820
00:42:36,676 --> 00:42:38,916
Speaker 2: need to think rationally, you need to figure it out.

821
00:42:39,396 --> 00:42:41,036
Speaker 2: But you know, I think it's a power one of

822
00:42:41,076 --> 00:42:45,876
Speaker 2: my professors at Carnegie Mellon said, dream like an amateur,

823
00:42:46,356 --> 00:42:49,436
Speaker 2: execute like professional, right, And I think that's just a

824
00:42:49,516 --> 00:42:51,036
Speaker 2: really kind of profound sentiment.

825
00:42:52,396 --> 00:42:54,156
Speaker 1: What's one thing your time at Google taught you not

826
00:42:54,276 --> 00:42:54,596
Speaker 1: to do?

827
00:42:55,236 --> 00:43:00,476
Speaker 2: Oh? What it teged me not to do?

828
00:43:02,996 --> 00:43:03,116
Speaker 1: Uh?

829
00:43:03,396 --> 00:43:06,116
Speaker 2: Maybe kind of adjacent that. Like, so when I went

830
00:43:06,156 --> 00:43:07,996
Speaker 2: to Google, I thought I was a pretty good programmer,

831
00:43:08,116 --> 00:43:10,596
Speaker 2: you know, I was, Yeah, Carnie Melon, I'm just good

832
00:43:10,596 --> 00:43:15,116
Speaker 2: at what I did, and I'm not a bad programmer.

833
00:43:15,596 --> 00:43:18,836
Speaker 2: But like, there are truly exceptional people out in the world, right,

834
00:43:18,876 --> 00:43:22,276
Speaker 2: And so I think, you know, maybe don't overestimate yourself

835
00:43:23,676 --> 00:43:27,196
Speaker 2: and kind of again kind of think, kind of think big,

836
00:43:27,236 --> 00:43:28,516
Speaker 2: don't underestimate what's out there.

837
00:43:34,476 --> 00:43:37,436
Speaker 1: Chris Sumson is the co founder and CEO of Aurora.

838
00:43:38,516 --> 00:43:41,836
Speaker 1: Please email us at problem at pushkin dot fm. We

839
00:43:41,916 --> 00:43:45,596
Speaker 1: are always looking for new guests for the show. Today's

840
00:43:45,636 --> 00:43:49,436
Speaker 1: show was produced by Trinamnino and Gabriel Hunter Chang. It

841
00:43:49,596 --> 00:43:53,436
Speaker 1: was edited by Alexander Garretson and engineered by Sarah Burgher.

842
00:43:53,836 --> 00:43:55,996
Speaker 1: I'm Jacob Goldstein and we'll be back next week with

843
00:43:56,036 --> 00:44:09,276
Speaker 1: another episode of What's Your Problem.