Chris Urmson: How a driverless car sees the road

865,908 views ใƒป 2015-06-26

TED


ืื ื ืœื—ืฅ ืคืขืžื™ื™ื ืขืœ ื”ื›ืชื•ื‘ื™ื•ืช ื‘ืื ื’ืœื™ืช ืœืžื˜ื” ื›ื“ื™ ืœื”ืคืขื™ืœ ืืช ื”ืกืจื˜ื•ืŸ.

ืžืชืจื’ื: Ido Dekkers ืžื‘ืงืจ: Tal Dekkers
00:12
So in 1885, Karl Benz invented the automobile.
0
12528
3949
ืื– ื‘ 1885, ืงืืจืœ ื‘ื ืฅ ื”ืžืฆื™ื ืืช ื”ืžื›ื•ื ื™ืช.
00:16
Later that year, he took it out for the first public test drive,
1
16707
3762
ืžืื•ื—ืจ ื™ื•ืชืจ ื‘ืื•ืชื” ืฉื ื”, ื”ื•ื ืœืงื— ืื•ืชื” ืœื ืกื™ืขืช ืžื‘ื—ืŸ ืคื•ืžื‘ื™ืช ืจืืฉื•ื ื”,
00:20
and -- true story -- crashed into a wall.
2
20469
3375
ื• -- ืกื™ืคื•ืจ ืืžื™ืชื™ -- ื”ืชืจืกืง ื‘ืงื™ืจ.
00:24
For the last 130 years,
3
24184
2043
ื‘ืžืฉืš 130 ื”ืฉื ื” ื”ืื—ืจื•ื ื•ืช,
00:26
we've been working around that least reliable part of the car, the driver.
4
26227
4319
ืขื‘ื“ื ื• ืกื‘ื™ื‘ ื”ื—ืœืง ื”ื›ื™ ืคื—ื•ืช ืืžื™ืŸ ืฉืœ ื”ืžื›ื•ื ื™ืช, ื”ื ื”ื’.
00:30
We've made the car stronger.
5
30546
1354
ืขืฉื™ื ื• ืืช ื”ืžื›ื•ื ื™ื•ืช ื—ื–ืงื•ืช ื™ื•ืชืจ.
00:32
We've added seat belts, we've added air bags,
6
32200
2548
ื”ื•ืกืคื ื• ื—ื’ื•ืจื•ืช ื‘ื˜ื™ื—ื•ืช, ื”ื•ืกืคื ื• ื›ืจื™ื•ืช ืื•ื™ืจ,
00:34
and in the last decade, we've actually started trying to make the car smarter
7
34748
3971
ื•ื‘ืขืฉื•ืจ ื”ืื—ืจื•ืŸ, ืœืžืขืฉื” ื”ืชื—ืœื ื• ืœืขืฉื•ืช ืืช ื”ืžื›ื•ื ื™ื•ืช ื—ื›ืžื•ืช ื™ื•ืชืจ
00:38
to fix that bug, the driver.
8
38719
2938
ื›ื“ื™ ืœืชืงืŸ ืืช ื”ื‘ืื’ ื”ื–ื”, ื”ื ื”ื’.
00:41
Now, today I'm going to talk to you a little bit about the difference
9
41657
3261
ืขื›ืฉื™ื•, ื”ื™ื•ื ืื ื™ ืขื•ืžื“ ืœื“ื‘ืจ ืื™ืชื›ื ืžืขื˜ ืขืœ ื”ื”ื‘ื“ืœ
00:44
between patching around the problem with driver assistance systems
10
44918
3808
ื‘ื™ืŸ ื”ื˜ืœืื” ืžืกื‘ื™ื‘ ืœื‘ืขื™ื” ืขื ืžืขืจื›ื•ืช ืžืกื™ื™ืขื•ืช ืœื ื”ื’
00:48
and actually having fully self-driving cars
11
48726
2564
ื•ืœืžืขืฉื” ื›ืฉื™ืฉ ืœื ื• ืžื›ื•ื ื™ื•ืช ื‘ื ื”ื™ื’ื” ืขืฆืžื•ื ื™ืช
00:51
and what they can do for the world.
12
51290
1880
ื•ืžื” ื”ืŸ ื™ื›ื•ืœื•ืช ืœืขืฉื•ืช ื‘ืฉื‘ื™ืœ ื”ืขื•ืœื.
00:53
I'm also going to talk to you a little bit about our car
13
53170
2995
ืื ื™ ื’ื ื”ื•ืœืš ืœื“ื‘ืจ ืื™ืชื›ื ืžืขื˜ ืขืœ ื”ืžื›ื•ื ื™ืช ืฉืœื ื•
00:56
and allow you to see how it sees the world and how it reacts and what it does,
14
56165
3999
ื•ืืืคืฉืจ ืœื›ื ืœืจืื•ืช ืื™ืš ื”ื™ื ืจื•ืื” ืืช ื”ืขื•ืœื ื•ืื™ืš ื”ื™ื ืžื’ื™ื‘ื” ื•ืžื” ื”ื™ื ืขื•ืฉื”,
01:00
but first I'm going to talk a little bit about the problem.
15
60164
3187
ืื‘ืœ ืจืืฉื™ืช ืื ื™ ืื“ื‘ืจ ืžืขื˜ ืขืœ ื”ื‘ืขื™ื”.
01:03
And it's a big problem:
16
63651
1648
ื•ื–ื• ื‘ืขื™ื” ื’ื“ื•ืœื”:
01:05
1.2 million people are killed on the world's roads every year.
17
65299
3089
1.2 ืžืœื™ื•ืŸ ืื ืฉื™ื ื ื”ืจื’ื™ื ืžืกื‘ื™ื‘ ืœืขื•ืœื ื›ืœ ืฉื ื”.
01:08
In America alone, 33,000 people are killed each year.
18
68388
3784
ื‘ืืžืจื™ืงื” ื‘ืœื‘ื“, 33,000 ืื ืฉื™ื ื ื”ืจื’ื™ื ื›ืœ ืฉื ื”.
01:12
To put that in perspective,
19
72172
2028
ื›ื“ื™ ืœืฉื™ื ืืช ื–ื” ื‘ืคืจืกืคืงื˜ื™ื‘ื”,
01:14
that's the same as a 737 falling out of the sky every working day.
20
74200
4797
ื–ื” ืื•ืชื• ื”ื“ื‘ืจ ื›ืžื• ืฉ 737 ื™ืคื•ืœ ืžื”ืฉืžื™ื™ื ื›ืœ ื™ื•ื ืขื‘ื•ื“ื”.
01:19
It's kind of unbelievable.
21
79342
1786
ื–ื” ืกื•ื’ ืฉืœ ืœื ื™ืื•ืžืŸ.
01:21
Cars are sold to us like this,
22
81548
2298
ืžื›ื•ื ื™ื•ืช ื ืžื›ืจื•ืช ืœื ื• ื›ืš,
01:23
but really, this is what driving's like.
23
83846
2717
ืื‘ืœ ื‘ืืžืช, ื ื”ื™ื’ื” ื”ื™ื ื›ืš.
01:26
Right? It's not sunny, it's rainy,
24
86563
2159
ื ื›ื•ืŸ? ื–ื” ืœื ืฉืžืฉื™, ื–ื” ื’ืฉื•ื,
01:28
and you want to do anything other than drive.
25
88722
2488
ื•ืืชื ืจื•ืฆื™ื ืœืขืฉื•ืช ื›ืœ ื“ื‘ืจ ื—ื•ืฅ ืžืœื ื”ื•ื’.
01:31
And the reason why is this:
26
91210
1622
ื•ื”ืกื™ื‘ื” ืœื–ื” ื”ื™ื ื–ื•:
01:32
Traffic is getting worse.
27
92832
1858
ื”ืชื ื•ืขื” ื ืขืฉื™ืช ื’ืจื•ืขื” ื™ื•ืชืจ.
01:34
In America, between 1990 and 2010,
28
94690
3506
ื‘ืืžืจื™ืงื”, ื‘ื™ืŸ 1990 ื• 2010,
01:38
the vehicle miles traveled increased by 38 percent.
29
98196
3504
ื”ืงื™ืœื•ืžื˜ืจื™ื ืฉืžื›ื•ื ื™ื•ืช ื ื•ืกืขื•ืช ื’ื“ืœื• ื‘ 38 ืื—ื•ื–.
01:42
We grew by six percent of roads,
30
102213
2749
ื’ื“ืœื ื• ื‘ืฉืฉ ืื—ื•ื– ื‘ื›ื‘ื™ืฉื™ื,
01:44
so it's not in your brains.
31
104962
1602
ืื– ื–ื” ืœื ื‘ืžื— ืฉืœื›ื.
01:46
Traffic really is substantially worse than it was not very long ago.
32
106564
4276
ื”ืชื ื•ืขื” ื‘ืืžืช ื’ืจื•ืขื” ื‘ื”ืจื‘ื” ืžืฉื”ื™ื ื”ื™ืชื” ืœื ืžื–ืžืŸ.
01:50
And all of this has a very human cost.
33
110840
2409
ื•ืœื›ืœ ื–ื” ื”ื™ื” ืžื—ื™ืจ ืžืื•ื“ ืื ื•ืฉื™.
01:53
So if you take the average commute time in America, which is about 50 minutes,
34
113529
3948
ืื– ืื ืชืงื—ื• ืืช ื–ืžืŸ ื”ื ืกื™ืขื” ื”ืžืžื•ืฆืข ื‘ืืžืจื™ืงื”, ืฉื”ื•ื ื‘ืขืจืš 50 ื“ืงื•ืช,
01:57
you multiply that by the 120 million workers we have,
35
117477
3649
ืืชื ืžื›ืคื™ืœื™ื ืืช ื–ื” ื‘ 120 ืžื™ืœื™ื•ืŸ ืขื•ื‘ื“ื™ื ืฉื™ืฉ ืœื ื•,
02:01
that turns out to be about six billion minutes
36
121126
2225
ื•ื–ื” ื™ื•ืฆื ื‘ืขืจืš ืฉืฉ ืžื™ืœื™ืืจื“ ื“ืงื•ืช
02:03
wasted in commuting every day.
37
123351
2026
ืฉืžื‘ื•ื–ื‘ื–ื•ืช ื›ืœ ื™ื•ื ื‘ื ืกื™ืขื”.
02:05
Now, that's a big number, so let's put it in perspective.
38
125377
2827
ืขื›ืฉื™ื•, ื–ื” ืžืกืคืจ ื’ื“ื•ืœ, ืื– ื‘ื•ืื• ื ืฉื™ื ืื•ืชื• ื‘ืคืจืกืคืงื˜ื™ื‘ื”.
02:08
You take that six billion minutes
39
128204
1774
ืืชื ืœื•ืงื—ื™ื ืืช ืฉืฉ ืžื™ืœื™ืืจื“ ื”ื“ืงื•ืช ื”ืืœื•
02:09
and you divide it by the average life expectancy of a person,
40
129978
3784
ื•ืืชื ืžื—ืœืงื™ื ื‘ืื•ืจืš ื”ื—ื™ื™ื ื”ืžืžื•ืฆืข ืฉืœ ืื“ื,
02:13
that turns out to be 162 lifetimes
41
133762
3135
ื–ื” ื™ื•ืฆื 162 ื—ื™ื™ื
02:16
spent every day, wasted,
42
136897
2925
ืžื‘ื•ื–ื‘ื–ื™ื ื›ืœ ื™ื•ื, ืžื‘ื•ื–ื‘ื–ื™ื,
02:19
just getting from A to B.
43
139822
2044
ืคืฉื•ื˜ ืœื”ื’ื™ืข ืž A ืœ B.
02:21
It's unbelievable.
44
141866
1730
ื–ื” ืœื ื™ืื•ืžืŸ.
02:23
And then, there are those of us who don't have the privilege
45
143596
2844
ื•ืื–, ื™ืฉ ืืช ืืœื” ืžืื™ืชื ื• ืฉืื™ืŸ ืœื”ื ืืช ื”ื–ื›ื•ืช
02:26
of sitting in traffic.
46
146440
1672
ืœืฉื‘ืช ื‘ืชื ื•ืขื”.
02:28
So this is Steve.
47
148112
1578
ืื– ื–ื” ืกื˜ื™ื‘.
02:29
He's an incredibly capable guy,
48
149690
1765
ื”ื•ื ื‘ื—ื•ืจ ืžื•ื›ืฉืจ ืžืื•ื“,
02:31
but he just happens to be blind,
49
151455
2516
ืื‘ืœ ื”ื•ื ืคืฉื•ื˜ ื‘ืžืงืจื” ืขื™ื•ื•ืจ,
02:33
and that means instead of a 30-minute drive to work in the morning,
50
153971
3217
ื•ื–ื” ืื•ืžืจ ืฉื‘ืžืงื•ื ื ืกื™ืขื” ืฉืœ 30 ื“ืงื•ืช ืœืขื‘ื•ื“ื” ื‘ื‘ื•ืงืจ,
02:37
it's a two-hour ordeal of piecing together bits of public transit
51
157188
3979
ื–ื” ืขื ื™ื™ืŸ ืฉืœ ืฉืขืชื™ื™ื ืฉืœ ืœื”ืจื›ื™ื‘ ื—ืœืงื™ื ืฉืœ ืชื—ื‘ื•ืจื” ืฆื™ื‘ื•ืจื™ืช
02:41
or asking friends and family for a ride.
52
161167
2385
ืื• ืœื‘ืงืฉ ืžื—ื‘ืจื™ื ื•ืžืฉืคื—ื” ื˜ืจืžืค.
02:43
He doesn't have that same freedom that you and I have to get around.
53
163552
3669
ืื™ืŸ ืœื• ืืช ืื•ืชื” ื—ืจื•ืช ื›ืžื•ื ื• ืœื”ืกืชื•ื‘ื‘.
02:47
We should do something about that.
54
167221
2460
ืื ื—ื ื• ืฆืจื™ื›ื™ื ืœืขืฉื•ืช ืžืฉื”ื• ื‘ื ื•ื’ืข ืœื–ื”.
02:49
Now, conventional wisdom would say
55
169891
1757
ืขื›ืฉื™ื•, ื”ื—ื•ื›ืžื” ื”ืจื’ื™ืœื” ื”ื™ืชื” ืื•ืžืจืช
02:51
that we'll just take these driver assistance systems
56
171648
2492
ื•ืื ื—ื ื• ืคืฉื•ื˜ ื ื™ืงื— ืืช ืžืขืจื›ื•ืช ื”ืขื–ืจื” ืœื ื”ื™ื’ื” ื”ืืœื•
02:54
and we'll kind of push them and incrementally improve them,
57
174140
3750
ื•ืกื•ื’ ืฉืœ ื ื“ื—ื•ืฃ ืื•ืชืŸ ื•ื ืฉืคืจ ืื•ืชืŸ ื‘ืฉืœื‘ื™ื,
02:57
and over time, they'll turn into self-driving cars.
58
177890
2542
ื•ื‘ืžืฉืš ื”ื–ืžืŸ, ื”ืŸ ื™ื”ืคื›ื• ืœืžื›ื•ื ื™ื•ืช ืฉื ื•ื”ื’ื•ืช ื‘ืขืฆืžืŸ.
03:00
Well, I'm here to tell you that's like me saying
59
180432
2409
ื•ื‘ื›ืŸ, ืื ื™ ืคื” ื›ื“ื™ ืœื”ื’ื™ื“ ืœื›ื ื•ื›ืžื• ืฉืื ื™ ืื•ืžืจ
03:02
that if I work really hard at jumping, one day I'll be able to fly.
60
182841
4057
ืฉืื ืื ื™ ืืขื‘ื•ื“ ืžืžืฉ ืงืฉื” ืขืœ ืงืคื™ืฆื”, ื™ื•ื ืื—ื“ ืื ื™ ืื•ื›ืœ ืœืขื•ืฃ.
03:06
We actually need to do something a little different.
61
186898
2728
ืื ื—ื ื• ืœืžืขืฉื” ืฆืจื™ื›ื™ื ืœืขืฉื•ืช ืžืฉื”ื• ืžืขื˜ ืฉื•ื ื”.
03:09
And so I'm going to talk to you about three different ways
62
189626
2711
ื•ืื ื™ ืขื•ืžื“ ืœื“ื‘ืจ ืื™ืชื›ื ืขืœ ืฉืœื•ืฉ ื“ืจื›ื™ื ืฉื•ื ื•ืช
03:12
that self-driving systems are different than driver assistance systems.
63
192337
3346
ืฉืžืขืจื›ื•ืช ื ื”ื™ื’ื” ืขืฆืžื™ืช ืฉื•ื ื•ืช ืžืžืขืจื›ื•ืช ืกื™ื•ืข ืœื ื”ื™ื’ื”.
03:15
And I'm going to start with some of our own experience.
64
195683
2651
ื•ืื ื™ ืขื•ืžื“ ืœื”ืชื—ื™ืœ ืขื ื›ืžื” ืžื”ื ืกื™ื•ื ื•ืช ืฉืœื ื•.
03:18
So back in 2013,
65
198334
2253
ืื– ื‘ 2013,
03:20
we had the first test of a self-driving car
66
200587
2663
ื”ื™ื” ืœื ื• ืืช ื”ื ืกื™ื•ืŸ ื”ืจืืฉื•ืŸ ืฉืžื›ื•ื ื™ืช ื ื”ื™ื’ื” ืขืฆืžื™ืช
03:23
where we let regular people use it.
67
203250
2027
ื‘ื• ื ืชื ื• ืœืื ืฉื™ื ืจื’ื™ืœื™ื ืœื”ืฉืชืžืฉ ื‘ื”.
03:25
Well, almost regular -- they were 100 Googlers,
68
205277
2202
ื•ื‘ื›ืŸ, ื›ืžืขื˜ ืจื’ื™ืœื™ื -- ื”ื ื”ื™ื• 100 ืขื•ื‘ื“ื™ ื’ื•ื’ืœ,
03:27
but they weren't working on the project.
69
207479
2003
ืื‘ืœ ื”ื ืœื ืขื‘ื“ื• ืขืœ ื”ืคืจื•ื™ื™ืงื˜.
03:29
And we gave them the car and we allowed them to use it in their daily lives.
70
209482
3621
ื•ื ืชื ื• ืœื”ื ืืช ื”ืžื›ื•ื ื™ืช ื•ืืคืฉืจื ื• ืœื”ื ืœื”ืฉืชืžืฉ ื‘ื” ื‘ื—ื™ื™ื ื”ื™ื•ื ื™ื•ืžื™ื™ื.
03:33
But unlike a real self-driving car, this one had a big asterisk with it:
71
213103
3719
ืื‘ืœ ื‘ื ื™ื’ื•ื“ ืœืžื›ื•ื ื™ืช ื ื”ื™ื’ื” ืขืฆืžื™ืช, ืœื–ื• ื”ื™ืชื” ื’ื ื›ื•ื›ื‘ื™ืช ื’ื“ื•ืœื”:
03:36
They had to pay attention,
72
216822
1504
ื”ื ื”ื™ื• ืฆืจื™ื›ื™ื ืœืฉื™ื ืœื‘,
03:38
because this was an experimental vehicle.
73
218326
2633
ืžืคื ื™ ืฉื–ื” ื”ื™ื” ืจื›ื‘ ื ืกื™ื•ื ื™.
03:40
We tested it a lot, but it could still fail.
74
220959
3525
ื‘ื“ืงื ื• ื”ืจื‘ื”, ืื‘ืœ ื–ื” ืขื“ื™ื™ืŸ ื”ื™ื” ื™ื›ื•ืœ ืœื”ื›ืฉืœ.
03:44
And so we gave them two hours of training,
75
224484
2059
ื•ื›ืš ื ืชื ื• ืœื”ื ื”ื“ืจื›ื” ืฉืœ ืฉืขืชื™ื™ื,
03:46
we put them in the car, we let them use it,
76
226543
2092
ืฉืžื ื• ืื•ืชื ื‘ืžื›ื•ื ื™ืช, ื ืชื ื• ืœื”ื ืœื”ืฉืชืžืฉ ื‘ื”,
03:48
and what we heard back was something awesome,
77
228635
2127
ื•ืžื” ืฉืฉืžืขื ื• ื—ื–ืจื” ื”ื™ื” ืžืฉื”ื• ืžื“ื”ื™ื,
03:50
as someone trying to bring a product into the world.
78
230762
2524
ื›ืžื™ืฉื”ื• ืฉืžื ืกื” ืœื”ื‘ื™ื ืžื•ืฆืจ ืœืขื•ืœื.
03:53
Every one of them told us they loved it.
79
233286
1925
ื›ืœ ืื—ื“ ืžื”ื ืืžืจ ืœื ื• ืฉื”ื ืื”ื‘ื• ืืช ื–ื”.
03:55
In fact, we had a Porsche driver who came in and told us on the first day,
80
235211
3566
ืœืžืขืฉื”, ื”ื™ื” ืœื ื• ื ื”ื’ ืคื•ืจืฉื” ืฉื‘ื ื•ืืžืจ ืœื ื• ื‘ื™ื•ื ื”ืจืืฉื•ืŸ,
03:58
"This is completely stupid. What are we thinking?"
81
238777
2663
"ื–ื” ื˜ื™ืคืฉื™ ืœื’ืžืจื™. ืžื” ืืชื ื—ื•ืฉื‘ื™ื?"
04:01
But at the end of it, he said, "Not only should I have it,
82
241850
2840
ืื‘ืœ ื‘ืกื•ืฃ ืฉืœ ื–ื”, ื”ื•ื ืืžืจ, "ืœื ืจืง ืฉืื ื™ ืฆืจื™ืš ืฉืชื”ื™ื” ืœื™ ื›ื–ื•,
04:04
everyone else should have it, because people are terrible drivers."
83
244690
3175
ืœื›ื•ืœื ืฆืจื™ื›ื” ืœื”ื™ื•ืช ืื—ืช, ืžืคื ื™ ืฉืื ืฉื™ื ื”ื ื ื”ื’ื™ื ื ื•ืจืื™ื™ื."
04:09
So this was music to our ears,
84
249135
1735
ืื– ื–ื• ื”ื™ืชื” ืžื•ื–ื™ืงื” ืœืื•ื–ื ื™ื ื•.
04:10
but then we started to look at what the people inside the car were doing,
85
250870
3803
ืื‘ืœ ื›ืฉื”ืชื—ืœื ื• ืœื”ื‘ื™ื˜ ื‘ืžื” ื”ืื ืฉื™ื ื‘ืชื•ืš ื”ืžื›ื•ื ื™ืช ืขืฉื•,
04:14
and this was eye-opening.
86
254673
1579
ื•ื–ื” ื”ื™ื” ืคื•ืงื— ืขื™ื ื™ื™ื.
04:16
Now, my favorite story is this gentleman
87
256252
2438
ืขื›ืฉื™ื•, ื”ืกื™ืคื•ืจ ื”ืื”ื•ื‘ ืขืœื™ ื”ื•ื ื”ื‘ื—ื•ืจ ื”ื–ื”
04:18
who looks down at his phone and realizes the battery is low,
88
258690
3829
ืฉื”ื‘ื™ื˜ ืœืžื˜ื” ืœื˜ืœืคื•ืŸ ืฉืœื• ื•ื”ื‘ื™ืŸ ืฉื”ื‘ื˜ืจื™ื” ื—ืœืฉื”,
04:22
so he turns around like this in the car and digs around in his backpack,
89
262519
4548
ืื– ื”ื•ื ืžืกืชื•ื‘ื‘ ื›ืš ื‘ืชื•ืš ื”ืžื›ื•ื ื™ืช ื•ื—ื•ืคืจ ื‘ืชื™ืง ืฉืœื•,
04:27
pulls out his laptop,
90
267067
2153
ืžื•ืฆื™ื ืืช ื”ืœืคื˜ื•ืค,
04:29
puts it on the seat,
91
269220
1567
ืฉื ืื•ืชื• ืขืœ ื”ืžื•ืฉื‘,
04:30
goes in the back again,
92
270787
1764
ื—ื•ื–ืจ ืื—ื•ืจื” ืฉื•ื‘,
04:32
digs around, pulls out the charging cable for his phone,
93
272551
3367
ืžื—ืคืฉ, ืฉื•ืœืฃ ืืช ื›ื‘ืœ ื”ื˜ืขื™ื ื” ืฉืœ ื”ื˜ืœืคื•ืŸ,
04:35
futzes around, puts it into the laptop, puts it on the phone.
94
275918
3367
ืžืฉื—ืง, ืฉื ืื•ืชื• ื‘ืชื•ืš ื”ืœืคื˜ื•ืค, ืฉื ืื•ืชื• ื‘ื˜ืœืคื•ืŸ.
04:39
Sure enough, the phone is charging.
95
279285
2043
ื•ื”ื ื” ื”ื˜ืœืคื•ืŸ ื ื˜ืขืŸ.
04:41
All the time he's been doing 65 miles per hour down the freeway.
96
281328
3994
ื›ืœ ื”ื–ืžืŸ ื”ื–ื” ื”ื•ื ื ื•ืกืข 100 ืงืž"ืฉ ื‘ื›ื‘ื™ืฉ ื”ืžื”ื™ืจ.
04:45
Right? Unbelievable.
97
285322
2484
ื ื›ื•ืŸ? ืœื ื™ืื•ืžืŸ.
04:47
So we thought about this and we said, it's kind of obvious, right?
98
287806
3121
ืื– ื—ืฉื‘ื ื• ืขืœ ื–ื” ื•ืืžืจื ื•, ื–ื” ืกื•ื’ ืฉืœ ืžื•ื‘ืŸ, ื ื›ื•ืŸ?
04:50
The better the technology gets,
99
290927
2263
ื›ื›ืœ ืฉื”ื˜ื›ื ื•ืœื•ื’ื™ื•ืช ืžืฉืชืคืจื•ืช,
04:53
the less reliable the driver is going to get.
100
293190
2121
ื”ื ื”ื’ ื ืขืฉื” ืคื—ื•ืช ืืžื™ืŸ.
04:55
So by just making the cars incrementally smarter,
101
295311
2396
ืื– ืขืœ ื™ื“ื™ ื”ืคื™ื›ืช ื”ืžื›ื•ื ื™ืช ืœื—ื›ืžื” ื™ื•ืชืจ ื‘ืฉืœื‘ื™ื,
04:57
we're probably not going to see the wins we really need.
102
297707
2902
ืื ื—ื ื• ื›ื ืจืื” ืœื ื ืจืื” ืืช ื”ื™ืชืจื•ื ื•ืช ืฉืื ื—ื ื• ื‘ืืžืช ืฆืจื™ื›ื™ื.
05:00
Let me talk about something a little technical for a moment here.
103
300609
3901
ืชื ื• ืœื™ ืœื“ื‘ืจ ืขืœ ืžืฉื”ื• ืžืขื˜ ื™ื•ืชืจ ื˜ื›ื ื™ ืœืจื’ืข ืคื”.
05:04
So we're looking at this graph, and along the bottom
104
304510
2438
ืื– ืื ื—ื ื• ืžืกืชื›ืœื™ื ืขืœ ื”ื’ืจืฃ ื”ื–ื”, ื•ื‘ืชื—ืชื™ืช
05:06
is how often does the car apply the brakes when it shouldn't.
105
306948
3051
ื–ื• ื”ืชื›ื™ืคื•ืช ื‘ื” ื”ืžื›ื•ื ื™ืช ืžืคืขื™ืœื” ืืช ื”ื‘ืœืžื™ื ื›ืฉื”ื™ื ืœื ืฆืจื™ื›ื”.
05:09
You can ignore most of that axis,
106
309999
1621
ืืชื ื™ื›ื•ืœื™ื ืœื”ืชืขืœื ืžืจื•ื‘ ื”ืฆื™ืจ ื”ื–ื”,
05:11
because if you're driving around town, and the car starts stopping randomly,
107
311620
3719
ืžืคื ื™ ืฉืื ืืชื ื ื•ื”ื’ื™ื ื‘ืขื™ืจ, ื•ื”ืžื›ื•ื ื™ืช ืžืชื—ื™ืœื” ืœืขืฆื•ืจ ื‘ืืงืจืื™ื•ืช,
05:15
you're never going to buy that car.
108
315339
1701
ืืชื ืœืขื•ืœื ืœื ืชืงื ื• ืืช ื”ืžื›ื•ื ื™ืช ื”ื–ื•.
05:17
And the vertical axis is how often the car is going to apply the brakes
109
317040
3375
ื•ื”ืฆื™ืจ ื”ืื ื›ื™ ื”ื•ื ื”ืชื›ื™ืคื•ืช ืฉื”ืžื›ื•ื ื™ืช ืขื•ืžื“ืช ืœื”ืคืขื™ืœ ืืช ื”ื‘ืœืžื™ื
05:20
when it's supposed to to help you avoid an accident.
110
320415
3049
ื›ืฉื”ื™ื ืืžื•ืจื” ืœืขื–ื•ืจ ืœื›ื ืœื”ื—ืžืง ืžืชืื•ื ื•ืช.
05:23
Now, if we look at the bottom left corner here,
111
323464
2221
ืขื›ืฉื™ื•, ืื ื ื‘ื™ื˜ ื‘ืชื—ืชื™ืช ืžืฉืžืืœ ืคื”,
05:25
this is your classic car.
112
325685
1845
ื–ื• ื”ืžื›ื•ื ื™ืช ื”ืงืœืืกื™ืช ืฉืœื›ื.
05:27
It doesn't apply the brakes for you, it doesn't do anything goofy,
113
327530
3133
ื”ื™ื ืœื ืœื•ื—ืฆืช ืขืœ ื”ื‘ืœืžื™ื ื‘ืฉื‘ื™ืœื›ื, ื”ื™ื ืœื ืขื•ืฉื” ืžืฉื”ื• ืžื•ื–ืจ,
05:30
but it also doesn't get you out of an accident.
114
330663
2779
ืื‘ืœ ื”ื™ื ืœื ืžื•ืฆื™ืื” ืืชื›ื ืžืชืื•ื ื•ืช.
05:33
Now, if we want to bring a driver assistance system into a car,
115
333442
3018
ืขื›ืฉื™ื•, ืื ืื ื—ื ื• ืจื•ืฆื™ื ืœื”ื‘ื™ื ืžืขืจื›ื•ืช ืกื™ื•ืข ืœื ื”ื’ ืœืžื›ื•ื ื™ืช,
05:36
say with collision mitigation braking,
116
336460
1828
ื ื’ื™ื“ ืขื ืžืขืจื›ืช ื‘ืœื™ืžื” ืœืžื ื™ืขืช ื”ืชื ื’ืฉื•ืช,
05:38
we're going to put some package of technology on there,
117
338288
2612
ืื ื—ื ื• ื ืฉื™ื ื—ื‘ื™ืœืช ื˜ื›ื ื•ืœื•ื’ื™ื” ืฉื,
05:40
and that's this curve, and it's going to have some operating properties,
118
340900
3418
ื•ื–ื• ื”ืขืงื•ืžื” ื”ื–ื•, ื•ื™ื”ื™ื• ืœื” ื›ืžื” ืชื›ื•ื ื•ืช ื”ืคืขืœื”,
05:44
but it's never going to avoid all of the accidents,
119
344318
2490
ืื‘ืœ ื”ื™ื ืœืขื•ืœื ืœื ืชืžื ืข ืžื›ืœ ื”ืชืื•ื ื•ืช,
05:46
because it doesn't have that capability.
120
346808
2059
ืžืคื ื™ ืฉืื™ืŸ ืœื” ืืช ื”ื™ื›ื•ืœืช.
05:48
But we'll pick some place along the curve here,
121
348867
2249
ืื‘ืœ ืื ื—ื ื• ื ื‘ื—ืจ ื›ืžื” ืžืงื•ืžื•ืช ืœืื•ืจืš ื”ืขืงื•ืžื” ืคื”,
05:51
and maybe it avoids half of accidents that the human driver misses,
122
351116
3254
ื•ืื•ืœื™ ื”ื™ื ื ืžื ืขืช ืžื—ืฆื™ ืžื”ืชืื•ื ื•ืช ืฉืื ืฉื™ื ื”ื™ื• ืžืคืกืคืกื™ื,
05:54
and that's amazing, right?
123
354370
1297
ื•ื–ื” ืžื“ื”ื™ื, ื ื›ื•ืŸ?
05:55
We just reduced accidents on our roads by a factor of two.
124
355667
2727
ื›ืจื’ืข ื”ืคื—ืชื ื• ืชืื•ื ื•ืช ืขืœ ื”ื›ื‘ื™ืฉื™ื ืฉืœื ื• ื‘ืคืืงื˜ื•ืจ ืฉืœ ืฉืชื™ื™ื.
05:58
There are now 17,000 less people dying every year in America.
125
358394
3987
ื™ืฉ ืขื›ืฉื™ื• ืคื—ื•ืช 17,000 ืื ืฉื™ื ืžืชื™ื ื›ืœ ืฉื ื” ื‘ืืžืจื™ืงื”.
06:02
But if we want a self-driving car,
126
362381
2020
ืื‘ืœ ืื ืื ื—ื ื• ืจื•ืฆื™ื ืžื›ื•ื ื™ืช ืฉื ื•ื”ื’ืช ื‘ืขืฆืžื”,
06:04
we need a technology curve that looks like this.
127
364401
2307
ืื ื—ื ื• ืฆืจื™ื›ื™ื ืขืงื•ืžืช ื˜ื›ื ื•ืœื•ื’ื™ื” ืฉื ืจืื™ืช ื›ืš.
06:06
We're going to have to put more sensors in the vehicle,
128
366708
2599
ืื ื—ื ื• ื ืฆื˜ืจืš ืœืฉื™ื ื™ื•ืชืจ ื—ื™ื™ืฉื ื™ื ื‘ืจื›ื‘,
06:09
and we'll pick some operating point up here
129
369307
2021
ื•ืื ื—ื ื• ื ื™ืงื— ื›ืžื” ื ืงื•ื“ื•ืช ื”ืคืขืœื” ืคื”
06:11
where it basically never gets into a crash.
130
371328
2019
ืฉื ื”ื™ื ื‘ืขื™ืงืจื•ืŸ ืœืขื•ืœื ืœื ื ื›ื ืกืช ืœืชืื•ื ื”.
06:13
They'll happen, but very low frequency.
131
373347
2443
ื”ืŸ ื™ืชืจื—ืฉื•, ืื‘ืœ ื‘ืชื“ื™ืจื•ืช ื ืžื•ื›ื”.
06:15
Now you and I could look at this and we could argue
132
375790
2461
ืขื›ืฉื™ื• ืื ื™ ื•ืืชื ื™ื›ื•ืœื™ื ืœื”ื‘ื™ื˜ ื‘ื–ื” ื•ื ื•ื›ืœ ืœื˜ืขื•ืŸ
06:18
about whether it's incremental, and I could say something like "80-20 rule,"
133
378251
3605
ืื ื–ื” ืื™ื ืงืจืžื ื˜ืœื™, ื•ืื ื™ ื”ื™ื™ืชื™ ื™ื›ื•ืœ ืœื”ื’ื™ื“ ืžืฉื”ื• ื›ืžื• "ื—ื•ืง 80-20,"
06:21
and it's really hard to move up to that new curve.
134
381856
2568
ื•ื–ื” ื‘ืืžืช ืงืฉื” ืœื ื•ืข ื‘ืžืขืœื” ื”ืขืงื•ืžื” ื”ื–ื•.
06:24
But let's look at it from a different direction for a moment.
135
384424
2934
ืื‘ืœ ื‘ื•ืื• ื ื‘ื™ื˜ ื‘ื–ื” ืžื ืงื•ื“ืช ืžื‘ื˜ ืฉื•ื ื” ืœืจื’ืข.
06:27
So let's look at how often the technology has to do the right thing.
136
387358
3512
ืื– ื‘ื•ืื• ื ืจืื” ืžื” ื”ืชื›ื™ืคื•ืช ืฉื”ื˜ื›ื ื•ืœื•ื’ื™ื” ืฆืจื™ื›ื” ืœืขืฉื•ืช ืืช ื”ื“ื‘ืจ ื”ื ื›ื•ืŸ.
06:30
And so this green dot up here is a driver assistance system.
137
390870
3506
ื•ื›ืš ื”ื ืงื•ื“ื” ื”ื™ืจื•ืงื” ื”ื–ื• ืฉื ืœืžืขืœื” ื–ื• ืžืขืจื›ืช ืกื™ื•ืข ืœื ื”ื’.
06:34
It turns out that human drivers
138
394376
2485
ืžืกืชื‘ืจ ืฉื”ื ื”ื’ื™ื ื”ืื ื•ืฉื™ื™ื
06:36
make mistakes that lead to traffic accidents
139
396861
2647
ืขื•ืฉื™ื ื˜ืขื•ื™ื•ืช ืฉืžื•ื‘ื™ืœื•ืช ืœืชืื•ื ื•ืช ื“ืจื›ื™ื
06:39
about once every 100,000 miles in America.
140
399508
3172
ื‘ืขืจืš ื›ืœ 160,000 ืงื™ืœื•ืžื˜ืจื™ื ื‘ืืžืจื™ืงื”.
06:42
In contrast, a self-driving system is probably making decisions
141
402680
3167
ื‘ื ื™ื’ื•ื“ ืœื–ื”, ืžื›ื•ื ื™ืช ื ื”ื™ื’ื” ืขืฆืžื™ืช ื›ื ืจืื” ืขื•ืฉื” ื”ื—ืœื˜ื•ืช
06:45
about 10 times per second,
142
405847
3663
ื‘ืขืจืš 10 ืคืขืžื™ื ื‘ืฉื ื™ื”,
06:49
so order of magnitude,
143
409510
1422
ืื– ื›ืžื” ื“ืจื’ื•ืช ื’ื•ื“ืœ,
06:50
that's about 1,000 times per mile.
144
410932
2832
ื–ื” ื‘ืขืจืš 600 ืคืขืžื™ื ื‘ืงื™ืœื•ืžื˜ืจ.
06:53
So if you compare the distance between these two,
145
413764
2485
ืื– ืื ืืชื ืžืฉื•ื•ื™ื ืืช ื”ืžืจื—ืง ื‘ื™ืŸ ืฉื ื™ ืืœื”,
06:56
it's about 10 to the eighth, right?
146
416249
2600
ื–ื” ื‘ืขืจืš 10 ื‘ื—ื–ืงืช ืฉืžื•ื ื”, ื ื›ื•ืŸ?
06:58
Eight orders of magnitude.
147
418849
1765
ืฉืžื•ื ื” ื“ืจื’ื•ืช ื’ื•ื“ืœ.
07:00
That's like comparing how fast I run
148
420614
2809
ื–ื” ื›ืžื• ืœื”ืฉื•ื•ืช ื›ืžื” ืžื”ืจ ืื ื™ ืจืฅ
07:03
to the speed of light.
149
423423
2206
ืœืžื”ื™ืจื•ืช ื”ืื•ืจ.
07:05
It doesn't matter how hard I train, I'm never actually going to get there.
150
425629
3785
ื–ื” ืœื ืžืฉื ื” ื›ืžื” ืื ื™ ืืชืืžืŸ, ืื ื™ ืœืขื•ืœื ืœื ืื’ื™ืข ืœืฉื.
07:09
So there's a pretty big gap there.
151
429414
2438
ืื– ื™ืฉ ืคืขืจ ืžืื•ื“ ื’ื“ื•ืœ ืฉื.
07:11
And then finally, there's how the system can handle uncertainty.
152
431852
3729
ื•ืื– ืœื‘ืกื•ืฃ, ื™ืฉ ืืช ืื™ืš ืฉื”ืžืขืจื›ืช ื™ื›ื•ืœื” ืœื”ืชืžื•ื“ื“ ืขื ื—ื•ืกืจ ื•ื•ื“ืื•ืช.
07:15
So this pedestrian here might be stepping into the road, might not be.
153
435581
3323
ืื– ื”ื•ืœืš ื”ืจื’ืœ ืคื” ืื•ืœื™ ื™ืจื“ ืœื›ื‘ื™ืฉ, ืื•ืœื™ ืœื.
07:18
I can't tell, nor can any of our algorithms,
154
438904
3395
ืื ื™ ืœื ื™ื›ื•ืœ ืœื“ืขืช, ื’ื ืœื ืืฃ ืืœื’ื•ืจื™ืชื ืฉืœื ื•,
07:22
but in the case of a driver assistance system,
155
442310
2284
ืื‘ืœ ื‘ืžืงืจื” ืฉืœ ืžืขืจื›ื•ืช ืกื™ื•ืข ืœื ื”ื’,
07:24
that means it can't take action, because again,
156
444594
2806
ื–ื” ืื•ืžืจ ืฉื”ื™ื ืœื ื™ื›ื•ืœ ืœืคืขื•ืœ, ืžืคื ื™ ืฉืฉื•ื‘,
07:27
if it presses the brakes unexpectedly, that's completely unacceptable.
157
447400
3339
ืื ื”ื™ื ืœื•ื—ืฆืช ืขืœ ื”ื‘ืœืžื™ื ื‘ืื•ืคืŸ ืœื ืฆืคื•ื™, ื–ื” ืœื’ืžืจื™ ืœื ืžืงื•ื‘ืœ.
07:30
Whereas a self-driving system can look at that pedestrian and say,
158
450739
3133
ื‘ืขื•ื“ ืžื›ื•ื ื™ืช ื ื”ื™ื’ื” ืขืฆืžื™ืช ื™ื›ื•ืœื” ืœื”ื‘ื™ื˜ ื‘ื”ื•ืœืš ื”ืจื’ืœ ื•ืœื”ื’ื™ื“,
07:33
I don't know what they're about to do,
159
453872
1890
ืื ื™ ืœื ื™ื•ื“ืขืช ืžื” ื”ื•ื ื™ืขืฉื”,
07:35
slow down, take a better look, and then react appropriately after that.
160
455762
3762
ืื ื™ ืืื˜, ืื‘ื™ื˜ ืฉื•ื‘, ื•ืื– ืื’ื™ื‘ ื‘ื”ืชืื ืœืื—ืจ ืžื›ืŸ.
07:39
So it can be much safer than a driver assistance system can ever be.
161
459524
3702
ืื– ื–ื” ื™ื›ื•ืœ ืœื”ื™ื•ืช ื”ืจื‘ื” ื™ื•ืชืจ ื‘ื˜ื•ื— ืžืžื” ืฉืžืžืขืจื›ืช ืกื™ื•ืข ืœื ื”ื’ ื™ื›ื•ืœื” ืื™ ืคืขื ืœื”ื™ื•ืช.
07:43
So that's enough about the differences between the two.
162
463226
2730
ืื– ืžืกืคื™ืง ืขืœ ื”ื”ื‘ื“ืœื™ื ื‘ื™ื ื”ืŸ.
07:45
Let's spend some time talking about how the car sees the world.
163
465956
3484
ื‘ื•ืื• ื ื‘ืœื” ืงืฆืช ื–ืžืŸ ื‘ืœื“ื‘ืจ ืขืœ ืื™ืš ื”ืžื›ื•ื ื™ืช ืจื•ืื” ืืช ื”ืขื•ืœื.
07:49
So this is our vehicle.
164
469440
1252
ืื– ื–ื” ื”ืจื›ื‘ ืฉืœื ื•.
07:50
It starts by understanding where it is in the world,
165
470692
2438
ื–ื” ืžืชื—ื™ืœ ื‘ื”ื‘ื ื” ื”ื™ื›ืŸ ื”ื•ื ื‘ืขื•ืœื,
07:53
by taking a map and its sensor data and aligning the two,
166
473130
2787
ืขืœ ื™ื“ื™ ืœืงื™ื—ืช ืžืคื” ื•ืืช ื”ืžื™ื“ืข ืžื”ื—ื™ื™ืฉื ื™ื ืฉืœื• ื•ืชืื•ื ื‘ื™ืŸ ื”ืฉื ื™ื™ื,
07:55
and then we layer on top of that what it sees in the moment.
167
475917
2948
ื•ืื– ืื ื—ื ื• ืžืจื‘ื“ื™ื ืžืขืœ ื–ื” ืžื” ืฉื”ื•ื ืจื•ืื” ื‘ืื•ืชื• ืจื’ืข.
07:58
So here, all the purple boxes you can see are other vehicles on the road,
168
478865
3655
ืื– ืคื”, ื›ืœ ื”ืงื•ืคืกืื•ืช ื”ืกื’ื•ืœื•ืช ืฉืืชื ื™ื›ื•ืœื™ื ืœืจืื•ืช ื”ื ืจื›ื‘ื™ื ืื—ืจื™ื ืขืœ ื”ื›ื‘ื™ืฉ,
08:02
and the red thing on the side over there is a cyclist,
169
482520
2528
ื•ื”ื“ื‘ืจ ื”ืื“ื•ื ื‘ืฆื“ ืฉื ื–ื” ืจื•ื›ื‘ ืื•ืคื ื™ื™ื,
08:05
and up in the distance, if you look really closely,
170
485048
2402
ื•ื‘ืžืจื—ืง, ืื ืชื‘ื™ื˜ื• ื”ื™ื˜ื‘,
08:07
you can see some cones.
171
487450
1794
ืืชื ื™ื›ื•ืœื™ื ืœืจืื•ืช ื›ืžื” ื—ืจื•ื˜ื™ื.
08:09
Then we know where the car is in the moment,
172
489244
2773
ืื– ืื ื—ื ื• ื™ื•ื“ืขื™ื ืื™ืคื” ื”ืžื›ื•ื ื™ืช ื‘ืื•ืชื• ืจื’ืข,
08:12
but we have to do better than that: we have to predict what's going to happen.
173
492017
3833
ืื‘ืœ ืื ื—ื ื• ืฆืจื™ื›ื™ื ืœื”ื™ื•ืช ื”ืจื‘ื” ื™ื•ืชืจ ื˜ื•ื‘ื™ื ืžื–ื”: ืื ื—ื ื• ืฆืจื™ื›ื™ื ืœืฆืคื•ืช ืžื” ืขื•ืžื“ ืœืงืจื•ืช.
08:15
So here the pickup truck in top right is about to make a left lane change
174
495850
3488
ืื– ืคื” ื”ื˜ื ื“ืจ ืžื™ืžื™ืŸ ืœืžืขืœื” ืขื•ืžื“ ืœืขืฉื•ืช ืฉื™ื ื•ื™ ื ืชื™ื‘ ืœืฉืžืืœ
08:19
because the road in front of it is closed,
175
499338
2223
ืžืคื ื™ ืฉื”ื›ื‘ื™ืฉ ืœืคื ื™ื• ืกื’ื•ืจ,
08:21
so it needs to get out of the way.
176
501561
1731
ืื– ื”ื•ื ืฆืจื™ืš ืœื–ื•ื– ืžื”ื“ืจืš.
08:23
Knowing that one pickup truck is great,
177
503292
1863
ืœื“ืขืช ืขืœ ื˜ื ื“ืจ ืื—ื“ ื–ื” ืžืขื•ืœื”,
08:25
but we really need to know what everybody's thinking,
178
505155
2479
ืื‘ืœ ื‘ืืžืช ืื ื—ื ื• ืฆืจื™ื›ื™ื ืœื“ืขืช ืžื” ื›ื•ืœื ื—ื•ืฉื‘ื™ื,
08:27
so it becomes quite a complicated problem.
179
507634
2507
ืื– ื–ื” ื ื”ืคืš ืœื‘ืขื™ื” ื“ื™ ืžื•ืจื›ื‘ืช.
08:30
And then given that, we can figure out how the car should respond in the moment,
180
510141
4749
ื•ืื– ื‘ื”ืชื—ืฉื‘ ื‘ื–ื”, ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœื”ื‘ื™ืŸ ืื™ืš ื”ืจื›ื‘ ืฆืจื™ืš ืœื”ื’ื™ื‘ ื‘ืื•ืชื• ืจื’ืข,
08:34
so what trajectory it should follow, how quickly it should slow down or speed up.
181
514890
3866
ืื– ื‘ืื™ื–ื” ื›ื™ื•ื•ืŸ ืฆืจื™ืš ืœื ืกื•ืข, ื›ืžื” ืžื”ืจ ื”ื•ื ืฆืจื™ืš ืœื”ืื˜ ืื• ืœื”ืื™ืฅ.
08:38
And then that all turns into just following a path:
182
518756
3065
ื•ืื– ื›ืœ ื–ื” ื”ื•ืคืš ืคืฉื•ื˜ ืœืœืขืงื•ื‘ ืื—ืจื™ ื”ื ืชื™ื‘:
08:41
turning the steering wheel left or right, pressing the brake or gas.
183
521821
3197
ืœืกื•ื‘ื‘ ืืช ื”ื”ื’ื” ืฉืžืืœื” ืื• ื™ืžื™ื ื”, ืœืœื—ื•ืฅ ืขืœ ื”ื‘ืœืžื™ื ืื• ื”ืžืฆืขืจืช.
08:45
It's really just two numbers at the end of the day.
184
525018
2464
ื–ื” ื‘ืืžืช ืจืง ืฉื ื™ ืžืกืคืจื™ื ื‘ืกื•ืฃ ื”ื™ื•ื.
08:47
So how hard can it really be?
185
527482
2241
ืื– ื›ืžื” ืงืฉื” ื–ื” ื™ื›ื•ืœ ืœื”ื™ื•ืช?
08:50
Back when we started in 2009,
186
530433
1952
ื‘ื–ืžืŸ ืฉื”ืชื—ืœื ื• ื‘ 2009,
08:52
this is what our system looked like.
187
532385
1798
ื›ืš ืฆืจื™ื›ื” ื”ืžืขืจื›ืช ืฉืœื ื• ืœื”ืจืื•ืช.
08:54
So you can see our car in the middle and the other boxes on the road,
188
534183
3391
ืื– ืืชื ื™ื›ื•ืœื™ื ืœืจืื•ืช ืืช ื”ืจื›ื‘ ืฉืœื ื• ื‘ืืžืฆืข ื•ื”ืงื•ืคืกืื•ืช ื”ืื—ืจื•ืช ืขืœ ื”ื›ื‘ื™ืฉ,
08:57
driving down the highway.
189
537574
1271
ื ื•ืกืขืช ื‘ื›ื‘ื™ืฉ ื”ืžื”ื™ืจ.
08:58
The car needs to understand where it is and roughly where the other vehicles are.
190
538845
3818
ื”ืจื›ื‘ ืฆืจื™ืš ืœื”ื‘ื™ืŸ ืื™ืคื” ื”ื•ื ื•ื‘ืขืจืš ืื™ืคื” ื”ืจื›ื‘ื™ื ื”ืื—ืจื™ื ื ืžืฆืื™ื.
09:02
It's really a geometric understanding of the world.
191
542663
2429
ื–ื• ื”ื‘ื ื” ื‘ืืžืช ื’ืื•ืžื˜ืจื™ืช ืฉืœ ื”ืขื•ืœื.
09:05
Once we started driving on neighborhood and city streets,
192
545092
2948
ื‘ืจื’ืข ืฉื”ืชื—ืœื ื• ืœื ื”ื•ื’ ื‘ืฉื›ื•ื ื•ืช ื•ืจื—ื•ื‘ื•ืช ืขื™ืจื•ื ื™ื™ื,
09:08
the problem becomes a whole new level of difficulty.
193
548040
2445
ื”ื‘ืขื™ื” ื”ื•ืคื›ืช ืœืจืžื” ื—ื“ืฉื” ืฉืœ ืžื•ืจื›ื‘ื•ืช.
09:10
You see pedestrians crossing in front of us, cars crossing in front of us,
194
550485
3494
ืืชื ืจื•ืื™ื ื”ื•ืœื›ื™ ืจื’ืœ ื—ื•ืฆื™ื ืœืคื ื™ื ื•, ืžื›ื•ื ื™ื•ืช ื—ื•ืฆื•ืช ืœืคื ื™ื ื•,
09:13
going every which way,
195
553979
1811
ื ื•ืกืขื•ืช ืœื›ืœ ื›ื™ื•ื•ืŸ.
09:15
the traffic lights, crosswalks.
196
555790
1527
ื”ืจืžื–ื•ืจื™ื, ืžืขื‘ืจื™ ื”ื—ืฆื™ื”.
09:17
It's an incredibly complicated problem by comparison.
197
557317
2797
ื–ื• ื‘ืขื™ื” ืžื•ืจื›ื‘ืช ื‘ื”ืฉื•ื•ืื”.
09:20
And then once you have that problem solved,
198
560114
2103
ื•ืื– ื‘ืจื’ืข ืฉืคืชืจืชื ืืช ื”ื‘ืขื™ื”,
09:22
the vehicle has to be able to deal with construction.
199
562217
2512
ื”ืจื›ื‘ ื—ื™ื™ื‘ ืœื”ื™ื•ืช ืžืกื•ื’ืœ ืœื”ืชืžื•ื“ื“ ืขื ื‘ื ื™ื”.
09:24
So here are the cones on the left forcing it to drive to the right,
200
564729
3151
ืื– ื”ื ื” ื”ื—ืจื•ื˜ื™ื ืžืฉืžืืœ ืžื›ืจื™ื—ื™ื ืืช ื”ื ื”ื’ื™ื ืœื™ืžื™ืŸ,
09:27
but not just construction in isolation, of course.
201
567880
2402
ืื‘ืœ ืœื ืจืง ื‘ื ื™ื” ืžื‘ื•ื“ื“ืช, ื›ืžื•ื‘ืŸ.
09:30
It has to deal with other people moving through that construction zone as well.
202
570282
3723
ื”ื•ื ืฆืจื™ืš ืœื”ืชืžื•ื“ื“ ื’ื ืขื ืื ืฉื™ื ืื—ืจื™ื ื ืขื™ื ื“ืจืš ืื–ื•ืจ ื”ื‘ื ื™ื”.
09:34
And of course, if anyone's breaking the rules, the police are there
203
574005
3263
ื•ื›ืžื•ื‘ืŸ, ืื ืžื™ืฉื”ื• ืฉื•ื‘ืจ ืืช ื”ื—ื•ืงื™ื, ื”ืžืฉื˜ืจื” ืฉื
09:37
and the car has to understand that that flashing light on the top of the car
204
577268
3622
ื•ื”ืžื›ื•ื ื™ืช ืฆืจื™ื›ื” ืœื”ื‘ื™ืŸ ืฉื”ืื•ืจ ื”ืžื”ื‘ื”ื‘ ืฉืœ ื”ืžื›ื•ื ื™ืช
09:40
means that it's not just a car, it's actually a police officer.
205
580890
3105
ืื•ืžืจ ืฉื–ื” ืœื ืจืง ืจื›ื‘, ื–ื” ืœืžืขืฉื” ืฉื•ื˜ืจ.
09:43
Similarly, the orange box on the side here,
206
583995
2032
ื‘ื“ื•ืžื”, ื”ืงื•ืคืกื” ื”ื›ืชื•ืžื” ื‘ืฆื“ ื”ืจื—ื•ื‘ ืคื”,
09:46
it's a school bus,
207
586027
1109
ื–ื” ืื•ื˜ื•ื‘ื•ืก ื‘ื™ืช ืกืคืจ,
09:47
and we have to treat that differently as well.
208
587136
2520
ื•ืื ื—ื ื• ืฆืจื™ื›ื™ื ืœื˜ืคืœ ื’ื ื‘ื–ื” ื‘ืฉื•ื ื”.
09:50
When we're out on the road, other people have expectations:
209
590576
2793
ื›ืฉืื ื—ื ื• ืขืœ ื”ื›ื‘ื™ืฉ, ืœืื ืฉื™ื ืื—ืจื™ื ื™ืฉ ืฆื™ืคื™ื•ืช:
09:53
So, when a cyclist puts up their arm,
210
593369
1780
ืื–, ื›ืฉืจื•ื›ื‘ ื”ืื•ืคื ื™ื™ื ืžืจื™ื ืืช ื™ื“ื•,
09:55
it means they're expecting the car to yield to them and make room for them
211
595149
3518
ื–ื” ืื•ืžืจ ืฉื”ื ืžืฆืคื™ื ืฉื”ืžื›ื•ื ื™ืช ืชืชืŸ ืœื”ื ืœืขื‘ื•ืจ ื•ืชืคื ื” ืœื”ื ืžืงื•ื
09:58
to make a lane change.
212
598667
2053
ื›ื“ื™ ืœื‘ืฆืข ืฉื™ื ื•ื™ ืžืกืœื•ืœ.
10:01
And when a police officer stood in the road,
213
601030
2173
ื•ื›ืฉื”ืฉื•ื˜ืจ ืขืžื“ ืขืœ ื”ื›ื‘ื™ืฉ,
10:03
our vehicle should understand that this means stop,
214
603203
2740
ื”ืจื›ื‘ ืฉืœื ื• ืฆืจื™ืš ืœื”ื‘ื™ืŸ ืฉื–ื” ืื•ืžืจ ืœืขืฆื•ืจ,
10:05
and when they signal to go, we should continue.
215
605943
3506
ื•ื›ืฉื”ื ืžืื•ืชืชื™ื ืœื”ืžืฉื™ืš, ืื ื—ื ื• ืฆืจื™ื›ื™ื ืœื”ืžืฉื™ืš.
10:09
Now, the way we accomplish this is by sharing data between the vehicles.
216
609449
3761
ืขื›ืฉื™ื•, ื”ื“ืจืš ื‘ื” ืื ื—ื ื• ืžืฉื™ื’ื™ื ืืช ื–ื” ื”ื™ื ืขืœ ื™ื“ื™ ื—ืœื•ืงืช ืžื™ื“ืข ื‘ื™ืŸ ื”ืจื›ื‘ื™ื.
10:13
The first, most crude model of this
217
613210
1696
ื”ืจืืฉื•ืŸ, ืจื•ื‘ ื”ืžื•ื“ืœื™ื ื”ื’ืกื™ื ืฉืœ ื–ื”
10:14
is when one vehicle sees a construction zone,
218
614906
2113
ื”ื ื›ืฉืจื›ื‘ ืื—ื“ ืจื•ืื” ืื–ื•ืจ ื‘ื ื™ื”,
10:17
having another know about it so it can be in the correct lane
219
617019
3062
ื–ื” ืฉื™ืฉ ืžื™ืฉื”ื• ืื—ืจ ืฉื™ื•ื“ืข ืขืœ ื–ื” ื›ืš ืฉื”ื•ื ื™ื•ื›ืœ ืœื”ื™ื•ืช ื‘ื ืชื™ื‘ ื”ื ื›ื•ืŸ
10:20
to avoid some of the difficulty.
220
620081
1570
ื›ื“ื™ ืœื”ืžื ืข ืžื—ืœืง ืžื”ืงื•ืฉื™.
10:21
But we actually have a much deeper understanding of this.
221
621651
2664
ืื‘ืœ ื™ืฉ ืœื ื• ืœืžืขืฉื” ื”ื‘ื ื” ื”ืจื‘ื” ื™ื•ืชืจ ืขืžื•ืงื” ืฉืœ ื–ื”.
10:24
We could take all of the data that the cars have seen over time,
222
624315
3009
ื ื•ื›ืœ ืœืงื—ืช ืืช ื›ืœ ื”ืžื™ื“ืข ื”ื–ื” ืฉื”ืจื›ื‘ ืจืื” ื‘ืžืฉืš ื”ื–ืžืŸ,
10:27
the hundreds of thousands of pedestrians, cyclists,
223
627324
2376
ืžืื•ืช ืืœืคื™ ื”ื•ืœื›ื™ ื”ืจื’ืœ, ื”ืจื•ื›ื‘ื™ื,
10:29
and vehicles that have been out there
224
629700
1787
ื•ื”ืจื›ื‘ื™ื ืฉื”ื™ื• ืฉื
10:31
and understand what they look like
225
631487
1695
ื•ืœื”ื‘ื™ืŸ ืื™ืš ื”ื ื ืจืื™ื
10:33
and use that to infer what other vehicles should look like
226
633182
2831
ื•ืœื”ืฉืชืžืฉ ื‘ื–ื” ื›ื“ื™ ืœื”ืกื™ืง ืื™ืš ืจื›ื‘ื™ื ืื—ืจื™ื ืฆืจื™ื›ื™ื ืœื”ืจืื•ืช
10:36
and other pedestrians should look like.
227
636013
1926
ื•ืื™ืš ื”ื•ืœื›ื™ ืจื’ืœ ืื—ืจื™ื ืฆืจื™ื›ื™ื ืœื”ืจืื•ืช.
10:37
And then, even more importantly, we could take from that a model
228
637939
3021
ื•ืื–, ืืคื™ืœื• ื—ืฉื•ื‘ ื™ื•ืชืจ, ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœืงื—ืช ืžื”ืžื•ื“ืœ ื”ื–ื”
10:40
of how we expect them to move through the world.
229
640960
2330
ืฉืœ ืื™ืš ืœืฆืคื•ืช ืฉื”ื ื™ื ื•ืขื• ื“ืจืš ื”ืขื•ืœื.
10:43
So here the yellow box is a pedestrian crossing in front of us.
230
643290
2963
ืื– ืคื” ื”ืงื•ืคืกื” ื”ืฆื”ื•ื‘ื” ื”ื™ื ื”ื•ืœืš ืจื’ืœ ืฉื—ื•ืฆื” ืžื•ืœื ื•.
10:46
Here the blue box is a cyclist and we anticipate
231
646253
2250
ืคื” ื”ืงื•ืคืกื” ื”ื›ื—ื•ืœื” ื”ื™ื ืจื•ื›ื‘ ืื•ืคื ื™ื™ื ื•ืื ื—ื ื• ืฆื•ืคื™ื
10:48
that they're going to nudge out and around the car to the right.
232
648503
3312
ืฉื”ื ื™ื ื•ืขื• ื”ื—ื•ืฆื” ื•ืžืกื‘ื™ื‘ ืœืžื›ื•ื ื™ืช ืžื™ืžื™ืŸ.
10:52
Here there's a cyclist coming down the road
233
652115
2092
ืคื” ื™ืฉ ืจื•ื›ื‘ ืื•ืคื ื™ื™ื ืฉืžื’ื™ืข ื‘ืžื•ืจื“ ื”ื›ื‘ื™ืฉ
10:54
and we know they're going to continue to drive down the shape of the road.
234
654207
3486
ื•ืื ื—ื ื• ื™ื•ื“ืขื™ื ืฉื”ื ื™ืžืฉื™ื›ื• ืœืจื›ื‘ ื‘ืžื•ืจื“ ื”ื›ื‘ื™ืฉ.
10:57
Here somebody makes a right turn,
235
657693
1867
ืคื” ืžื™ืฉื”ื• ืคื•ื ื” ื™ืžื™ื ื”,
10:59
and in a moment here, somebody's going to make a U-turn in front of us,
236
659560
3360
ื•ื‘ืขื•ื“ ืจื’ืข ืคื”, ืžื™ืฉื”ื• ืขื•ืžื“ ืœืขืฉื•ืช ืคื ื™ื™ืช ืคืจืกื” ืœืคื ื™ื ื•,
11:02
and we can anticipate that behavior and respond safely.
237
662920
2614
ื•ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœืฆืคื•ืช ืืช ื”ื”ืชื ื”ื’ื•ืช ื”ื–ื• ื•ืœื”ื’ื™ื‘ ื‘ื‘ื˜ื—ื”.
11:05
Now, that's all well and good for things that we've seen,
238
665534
2728
ืขื›ืฉื™ื•, ื”ื›ืœ ื˜ื•ื‘ ื•ื™ืคื” ืœื“ื‘ืจื™ื ืฉืจืื™ื ื•,
11:08
but of course, you encounter lots of things that you haven't
239
668262
2865
ืื‘ืœ ื›ืžื•ื‘ืŸ, ืืชื ื ืชืงืœื™ื ื‘ื”ืจื‘ื” ื“ื‘ืจื™ื
11:11
seen in the world before.
240
671127
1231
ืฉืœื ืจืื™ื ื• ื‘ืขื•ืœื ืœืคื ื™ ื›ืŸ.
11:12
And so just a couple of months ago,
241
672358
1741
ื•ื›ืš ืจืง ืœืคื ื™ ื›ืžื” ื—ื•ื“ืฉื™ื,
11:14
our vehicles were driving through Mountain View,
242
674099
2235
ื”ืจื›ื‘ื™ื ืฉืœื ื• ื ืกืขื• ื“ืจืš ืžืื•ื ื˜ืŸ ื•ื•ื™ื•,
11:16
and this is what we encountered.
243
676334
1644
ื•ื–ื” ืžื” ืฉื ืชืงืœื ื• ื‘ื•.
11:17
This is a woman in an electric wheelchair
244
677978
2082
ื–ื• ืื™ืฉื” ื‘ื›ื™ืกื ื’ืœื’ืœื™ื ื—ืฉืžืœื™
11:20
chasing a duck in circles on the road. (Laughter)
245
680060
2617
ืฉืจื•ื“ืคืช ืื—ืจื™ ื‘ืจื•ื•ื– ื‘ืกื™ื‘ื•ื‘ื™ื ืขืœ ื”ื›ื‘ื™ืฉ. (ืฆื—ื•ืง)
11:22
Now it turns out, there is nowhere in the DMV handbook
246
682677
3111
ืขื›ืฉื™ื• ืžืกืชื‘ืจ, ืื™ืŸ ื‘ืฉื•ื ืžืงื•ื ื‘ืกืคืจ ื”ื”ื“ืจื›ื” ืฉืœ ืžืฉืจื“ ื”ืจื™ืฉื•ื™
11:25
that tells you how to deal with that,
247
685788
2245
ืฉืื•ืžืจ ืœื›ื ืื™ืš ืœื”ืชืžื•ื“ื“ ืขื ื–ื”,
11:28
but our vehicles were able to encounter that,
248
688033
2143
ืื‘ืœ ื”ืจื›ื‘ ืฉืœื ื• ื”ื™ื” ืžืกื•ื’ืœ ืœื”ืชืžื•ื“ื“ ืขื ื–ื”,
11:30
slow down, and drive safely.
249
690176
2255
ืœื”ืื˜, ื•ืœื ืกื•ืข ื‘ื‘ื™ื˜ื—ื”.
11:32
Now, we don't have to deal with just ducks.
250
692431
2041
ืขื›ืฉื™ื•, ืื ื—ื ื• ืœื ืฆืจื™ื›ื™ื ืœื”ืชืžื•ื“ื“ ืจืง ืขื ื‘ืจื•ื•ื–ื™ื.
11:34
Watch this bird fly across in front of us. The car reacts to that.
251
694472
3708
ืฆืคื• ื‘ืฆื™ืคื•ืจ ื”ื–ื” ืขืคื” ืœืคื ื™ื ื•. ื”ืจื›ื‘ ืžื’ื™ื‘ ืœื–ื”.
11:38
Here we're dealing with a cyclist
252
698180
1615
ืคื” ืื ื—ื ื• ืžืชืžื•ื“ื“ื™ื ืขื ืจื•ื›ื‘ ืื•ืคื ื™ื™ื
11:39
that you would never expect to see anywhere other than Mountain View.
253
699795
3290
ืฉืœืขื•ืœื ืœื ืชืฆืคื• ืœืจืื•ืช ื‘ืฉื•ื ืžืงื•ื ื‘ืžืื•ื˜ื™ื™ืŸ ื•ื•ื™ื•.
11:43
And of course, we have to deal with drivers,
254
703085
2068
ื•ื›ืžื•ื‘ืŸ, ืื ื—ื ื• ืฆืจื™ื›ื™ื ืœื”ืชืžื•ื“ื“ ืขื ื ื”ื’ื™ื,
11:45
even the very small ones.
255
705153
3715
ืืคื™ืœื• ื”ืงื˜ื ื™ื ืฉื‘ื”ื.
11:48
Watch to the right as someone jumps out of this truck at us.
256
708868
4131
ืฆืคื• ืžื™ืžื™ืŸ ื›ืฉืžื™ืฉื”ื• ืงื•ืคืฅ ืžื”ื˜ื ื“ืจ ืฉืœื• ืœืคื ื™ื ื•.
11:54
And now, watch the left as the car with the green box decides
257
714460
2929
ื•ืขื›ืฉื™ื•, ืฆืคื• ืžืฉืžืืœ ื›ืฉื”ืžื›ื•ื ื™ืช ืขื ื”ืงื•ืคืกื” ื”ื™ืจื•ืงื” ืžื—ืœื™ื˜ื”
11:57
he needs to make a right turn at the last possible moment.
258
717389
3325
ืฉื”ื™ื ืฆืจื™ื›ื” ืœืขืฉื•ืช ืคื ื™ื” ื™ืžื™ื ื” ื‘ืจื’ืข ื”ืืคืฉืจื™ ื”ืื—ืจื•ืŸ.
12:00
Here, as we make a lane change, the car to our left decides
259
720714
2851
ืคื”, ื›ืฉืื ื—ื ื• ืขื•ืฉื™ื ืฉื™ื ื•ื™ ืžืกืœื•ืœ, ื”ืžื›ื•ื ื™ืช ืžืฉืžืืœื ื• ืžื—ืœื™ื˜ื”
12:03
it wants to as well.
260
723565
3553
ืฉื”ื™ื ื’ื ืจื•ืฆื” ืœืขืฉื•ืช ื–ืืช.
12:07
And here, we watch a car blow through a red light
261
727118
2693
ื•ืคื”, ืื ื—ื ื• ืจื•ืื™ื ืžื›ื•ื ื™ืช ืขื•ื‘ืจืช ื‘ืจืžื–ื•ืจ ืื“ื•ื
12:09
and yield to it.
262
729811
2090
ื•ืœื ืžืชื™ื™ื—ืกืช ืืœื™ื•.
12:11
And similarly, here, a cyclist blowing through that light as well.
263
731901
3854
ื•ื‘ื“ื•ืžื”, ืคื”, ืจื•ื›ื‘ ืื•ืคื ื™ื™ื ื’ื ื”ื•ื ืขื•ื‘ืจ ื‘ืจืžื–ื•ืจ ื”ื”ื•ื ื‘ืื“ื•ื.
12:15
And of course, the vehicle responds safely.
264
735755
2746
ื•ื›ืžื•ื‘ืŸ, ื”ืจื›ื‘ ืžื’ื™ื‘ ื‘ื‘ื˜ื—ื”.
12:18
And of course, we have people who do I don't know what
265
738501
2601
ื•ื›ืžื•ื‘ืŸ, ื™ืฉ ืœื ื• ืื ืฉื™ื ืฉืขื•ืฉื™ื ืื ื™ ืœื ื™ื•ื“ืข ืžื”
12:21
sometimes on the road, like this guy pulling out between two self-driving cars.
266
741102
3823
ืœืคืขืžื™ื ืขืœ ื”ื›ื‘ื™ืฉ, ื›ืžื• ื”ื‘ื—ื•ืจ ื”ื–ื” ืฉื ื•ืกืข ื‘ื™ืŸ ืฉืชื™ ืžื›ื•ื ื™ื•ืช ื ื”ื™ื’ื” ืขืฆืžื™ืช.
12:24
You have to ask, "What are you thinking?"
267
744925
2045
ืืชื ืฆืจื™ื›ื™ื ืœืฉืื•ืœ, "ืžื” ืืชื” ื—ื•ืฉื‘?"
12:26
(Laughter)
268
746970
1212
(ืฆื—ื•ืง)
12:28
Now, I just fire-hosed you with a lot of stuff there,
269
748182
2521
ืขื›ืฉื™ื•, ืื ื™ ืคืฉื•ื˜ ื™ื•ืจื” ืขืœื™ื›ื ืคื” ื”ืจื‘ื” ื“ื‘ืจื™ื,
12:30
so I'm going to break one of these down pretty quickly.
270
750703
2650
ืื– ืื ื™ ืขื•ืžื“ ืœืคืจื˜ ืื—ื“ ืžืืœื” ืžืžืฉ ืžื”ืจ.
12:33
So what we're looking at is the scene with the cyclist again,
271
753353
2940
ืื– ืžื” ืฉืื ื—ื ื• ืžื‘ื™ื˜ื™ื ื‘ื• ื‘ืกืฆื ื” ื”ื–ื• ื”ื ืจื•ื›ื‘ ื”ืื•ืคื ื™ื™ื ืฉื•ื‘,
12:36
and you might notice in the bottom, we can't actually see the cyclist yet,
272
756293
3491
ื•ืืชื ืื•ืœื™ ืชื‘ื—ื™ื ื• ื‘ืชื—ืชื™ืช, ืื ื—ื ื• ืœื ื™ื›ื•ืœื™ื ืœืจืื•ืช ืืช ืจื•ื›ื‘ ื”ืื•ืคื ื™ื™ื ืœืžืขืฉื” ืขื“ื™ื™ืŸ,
12:39
but the car can: it's that little blue box up there,
273
759784
2504
ืื‘ืœ ื”ืžื›ื•ื ื™ืช ื™ื›ื•ืœื”: ื–ื• ื”ืงื•ืคืกื” ื”ื›ื—ื•ืœื” ื”ืงื˜ื ื” ืœืžืขืœื” ืฉื,
12:42
and that comes from the laser data.
274
762288
2081
ื•ื–ื” ืžื’ื™ืข ืžืžื™ื“ืข ื”ืœื™ื–ืจ.
12:44
And that's not actually really easy to understand,
275
764369
2418
ื•ื–ื” ืœืžืขืฉื” ืœื ืงืœ ืœื”ื‘ื™ืŸ,
12:46
so what I'm going to do is I'm going to turn that laser data and look at it,
276
766787
3584
ืื– ืžื” ืฉืื ื™ ืืขืฉื” ื–ื” ืฉืื ื™ ืื”ืคื•ืš ืืช ื”ืžื™ื“ืข ื”ืœื™ื–ืจ ื”ื–ื” ื•ืื‘ื™ื˜ ื‘ื•,
12:50
and if you're really good at looking at laser data, you can see
277
770371
3029
ื•ืื ืืชื ื‘ืืžืช ื˜ื•ื‘ื™ื ื‘ืœื”ื‘ื™ื˜ ื‘ืžื™ื“ืข ืœื™ื™ื–ืจ, ืืชื ื™ื›ื•ืœื™ื ืœืจืื•ืช
12:53
a few dots on the curve there,
278
773400
1487
ื›ืžื” ื ืงื•ื“ื•ืช ืขืœ ื”ืขืงื•ืžื” ืฉื,
12:54
right there, and that blue box is that cyclist.
279
774887
2372
ืžืžืฉ ืฉื, ื•ื”ืงื•ืคืกื” ื”ื›ื—ื•ืœื” ื”ื–ื• ื”ื™ื ืจื•ื›ื‘ ื”ืื•ืคื ื™ื™ื.
12:57
Now as our light is red,
280
777259
1149
ืขื›ืฉื™ื• ื›ืฉื”ืื•ืจ ืฉืœื ื• ืื“ื•ื,
12:58
the cyclist's light has turned yellow already,
281
778408
2192
ื”ืื•ืจ ืฉืœ ืจื•ื›ื‘ ื”ืื•ืคื ื™ื™ื ื”ืคืš ื›ื‘ืจ ืœืฆื”ื•ื‘,
13:00
and if you squint, you can see that in the imagery.
282
780600
2438
ื•ืื ืชืžืฆืžืฆื•, ืืชื ื™ื›ื•ืœื™ื ืœืจืื•ืช ืืช ื–ื” ื‘ืชืžื•ื ื•ืช.
13:03
But the cyclist, we see, is going to proceed through the intersection.
283
783038
3286
ืื‘ืœ ืจื•ื›ื‘ ื”ืื•ืคื ื™ื™ื, ืืชื ืจื•ืื™ื, ืขื•ืžื“ ืœื”ืžืฉื™ืš ื“ืจืš ื”ืฆื•ืžืช.
13:06
Our light has now turned green, his is solidly red,
284
786324
2394
ื”ืื•ืจ ืฉืœื ื• ื”ืคืš ืขื›ืฉื™ื• ืœื™ืจื•ืง, ืฉืœื• ืœื’ืžืจื™ ืื“ื•ื,
13:08
and we now anticipate that this bike is going to come all the way across.
285
788718
4292
ื•ืื ื—ื ื• ืžืฆืคื™ื ืฉื”ืื•ืคื ื™ื™ื ื™ืขื‘ืจื• ืœื’ืžืจื™.
13:13
Unfortunately the other drivers next to us were not paying as much attention.
286
793010
3742
ืœืฆืขืจื ื• ื”ื ื”ื’ื™ื ืœื™ื“ื ื• ืขื›ืฉื™ื• ืœื ืฉืžื• ื›ืœ ื›ืš ืœื‘.
13:16
They started to pull forward, and fortunately for everyone,
287
796752
3157
ื”ื ื”ืชื—ื™ืœื• ืœื ืกื•ืข ืงื“ื™ืžื”, ื•ืœืžื–ืœื ืฉืœ ื›ื•ืœื,
13:19
this cyclists reacts, avoids,
288
799909
3011
ืจื•ื›ื‘ ื”ืื•ืคื ื™ื™ื ื”ื’ื™ื‘, ื ืžื ืข,
13:22
and makes it through the intersection.
289
802920
2191
ื•ืขื‘ืจ ืืช ื”ืฆื•ืžืช.
13:25
And off we go.
290
805111
1568
ื•ื”ื ื” ืื ื—ื ื• ื™ื•ืฆืื™ื.
13:26
Now, as you can see, we've made some pretty exciting progress,
291
806679
2948
ืขื›ืฉื™ื•, ื›ืžื• ืฉืืชื ืจื•ืื™ื, ืขืฉื™ื ื• ื”ืชืงื“ืžื•ืช ื“ื™ ืžืจื’ืฉืช,
13:29
and at this point we're pretty convinced
292
809627
1902
ื•ื‘ื ืงื•ื“ื” ื”ื–ื• ืื ื—ื ื• ื“ื™ ืžืฉื•ื›ื ืขื™ื
13:31
this technology is going to come to market.
293
811529
2010
ืฉื”ื˜ื›ื ื•ืœื•ื’ื™ื” ื”ื–ื• ืชื’ื™ืข ืœืฉื•ืง.
13:33
We do three million miles of testing in our simulators every single day,
294
813539
4783
ืื ื—ื ื• ืขื•ืฉื™ื 5 ืžืœื™ื•ืŸ ืงื™ืœื•ืžื˜ืจ ืฉืœ ื‘ื“ื™ืงื•ืช ื‘ืกื™ืžื•ืœืฆื™ื” ืฉืœื ื• ื›ืœ ื™ื•ื,
13:38
so you can imagine the experience that our vehicles have.
295
818322
2689
ื›ืš ืฉืืชื ื™ื›ื•ืœื™ื ืœื“ืžื™ื™ืŸ ืืช ื”ื ืกื™ื•ืŸ ืฉื™ืฉ ืœืจื›ื‘ื™ื ืฉืœื ื•.
13:41
We are looking forward to having this technology on the road,
296
821011
2864
ืื ื—ื ื• ืžื‘ื™ื˜ื™ื ืงื“ื™ืžื” ืฉืชื”ื™ื” ืœื ื• ื˜ื›ื ื•ืœื•ื’ื™ื” ืขืœ ื”ื›ื‘ื™ืฉ,
13:43
and we think the right path is to go through the self-driving
297
823875
2890
ื•ืื ื—ื ื• ื—ื•ืฉื‘ื™ื ืฉื”ื ืชื™ื‘ ื”ื ื›ื•ืŸ ื”ื•ื ืœืขื‘ื•ืจ ื“ืจืš ื ื”ื™ื’ื” ืขืฆืžื™ืช
13:46
rather than driver assistance approach
298
826765
1844
ื‘ืžืงื•ื ื“ืจืš ื’ื™ืฉืช ื”ืกื™ื•ืข ืœื ื”ื™ื’ื”
13:48
because the urgency is so large.
299
828609
2621
ื‘ื’ืœืœ ืฉื”ื“ื—ื™ืคื•ืช ื›ื–ื• ื’ื“ื•ืœื”.
13:51
In the time I have given this talk today,
300
831230
2393
ื‘ื–ืžืŸ ืฉื ื™ืชืŸ ืœื”ืจืฆืื” ืฉืœื™ ื”ื™ื•ื,
13:53
34 people have died on America's roads.
301
833623
3135
34 ืื ืฉื™ื ืžืชื• ืขืœ ื›ื‘ื™ืฉื™ ืืžืจื™ืงื”.
13:56
How soon can we bring it out?
302
836758
2368
ื›ืžื” ืžื”ืจ ื ื•ื›ืœ ืœื”ื•ืฆื™ื ืื•ืชื”?
13:59
Well, it's hard to say because it's a really complicated problem,
303
839126
3832
ื•ื‘ื›ืŸ, ื–ื” ืงืฉื” ืœื”ื’ื™ื“ ื‘ื’ืœืœ ืฉื–ื• ื‘ืขื™ื” ืžืžืฉ ืžืกื•ื‘ื›ืช,
14:02
but these are my two boys.
304
842958
2214
ืื‘ืœ ืืœื” ืฉื ื™ ื”ื‘ื ื™ื ืฉืœื™.
14:05
My oldest son is 11, and that means in four and a half years,
305
845172
3623
ื‘ื ื™ ื”ื‘ื›ื•ืจ ื‘ืŸ 11, ื•ื–ื” ืื•ืžืจ ืฉื‘ืขื•ื“ ืืจื‘ืข ื•ื—ืฆื™ ืฉื ื™ื,
14:08
he's going to be able to get his driver's license.
306
848795
2577
ื”ื•ื ื™ื”ื™ื” ืžืกื•ื’ืœ ืœืงื‘ืœ ืจื™ืฉื™ื•ืŸ ื ื”ื™ื’ื”.
14:11
My team and I are committed to making sure that doesn't happen.
307
851372
3204
ื”ืฆื•ื•ืช ืฉืœื™ ื•ืื ื™ ืžืชื—ื™ื™ื‘ื™ื ืœื“ืื•ื’ ืฉื–ื” ืœื ื™ืงืจื”.
14:14
Thank you.
308
854576
1904
ืชื•ื“ื” ืœื›ื.
14:16
(Laughter) (Applause)
309
856480
3667
(ืฆื—ื•ืง)(ืžื—ื™ืื•ืช ื›ืคื™ื™ื)
14:21
Chris Anderson: Chris, I've got a question for you.
310
861110
2568
ื›ืจื™ืก ืื ื“ืจืกื•ืŸ: ื›ืจื™ืก, ื™ืฉ ืœื™ ืฉืืœื” ืืœื™ืš.
14:23
Chris Urmson: Sure.
311
863678
2809
ื›ืจื™ืก ืื•ืจืžืกื•ืŸ: ื›ืŸ.
14:26
CA: So certainly, the mind of your cars is pretty mind-boggling.
312
866487
3924
ื›"ื: ืื– ื‘ื”ื—ืœื˜, ื”ืžื•ื— ืฉืœ ื”ืžื›ื•ื ื™ื•ืช ืฉืœื›ื ื”ื•ื ื‘ื”ื—ืœื˜ ืžื˜ืจื™ืฃ.
14:30
On this debate between driver-assisted and fully driverless --
313
870411
4459
ื‘ื“ื™ื•ืŸ ื”ื–ื” ื‘ื™ืŸ ืกื™ื•ืข ืœื ื”ื’ ืœื—ืกืจ ื ื”ื’ ืœื—ืœื•ื˜ื™ืŸ --
14:34
I mean, there's a real debate going on out there right now.
314
874870
3041
ืื ื™ ืžืชื›ื•ื•ืŸ, ื™ืฉ ื“ื™ื•ืŸ ืืžื™ืชื™ ืฉืžืชืจื—ืฉ ืฉื ืขื›ืฉื™ื•.
14:37
So some of the companies, for example, Tesla,
315
877911
2833
ืื– ื›ืžื” ืžื”ื—ื‘ืจื•ืช, ืœื“ื•ื’ืžื” ื˜ืกืœื”,
14:40
are going the driver-assisted route.
316
880744
2159
ื”ื•ืœื›ื™ื ื‘ื“ืจืš ื”ืกื™ื•ืข ืœื ื”ื’.
14:42
What you're saying is that that's kind of going to be a dead end
317
882903
5248
ืžื” ืฉืืชื” ืื•ืžืจ ื–ื” ืฉื–ื” ืกื•ื’ ืฉืœ ื“ืจืš ืœืœื ืžื•ืฆื
14:48
because you can't just keep improving that route and get to fully driverless
318
888151
5456
ืžืคื ื™ ืฉืืชื ืœื ื™ื›ื•ืœื™ื ืคืฉื•ื˜ ืœื”ืžืฉื™ืš ืœื”ืฉืชืคืจ ื‘ื“ืจืš ื”ื–ื• ื•ืœื”ื’ื™ืข ืœื ื”ื™ื’ื” ืื•ื˜ื•ืžื˜ื™ืช
14:53
at some point, and then a driver is going to say, "This feels safe,"
319
893607
3530
ื‘ื ืงื•ื“ื” ืžืกื•ื™ื™ืžืช, ื•ืื– ื”ื ื”ื’ ื™ื’ื™ื“, "ื–ื” ืžืจื’ื™ืฉ ื‘ื˜ื•ื—,"
14:57
and climb into the back, and something ugly will happen.
320
897137
2647
ื•ื™ืขื‘ื•ืจ ืื—ื•ืจื”, ื•ืžืฉื”ื• ืžื’ืขื™ืœ ื™ืงืจื”.
14:59
CU: Right. No, that's exactly right, and it's not to say
321
899784
2676
ื›"ื: ื ื›ื•ืŸ, ืœื, ื–ื” ื‘ื“ื™ื•ืง ื ื›ื•ืŸ, ื•ื–ื” ืœื ืื•ืžืจ
15:02
that the driver assistance systems aren't going to be incredibly valuable.
322
902460
3537
ืฉืžืขืจื›ื•ืช ื”ืกื™ื•ืข ืœื ื”ื’ ืœื ื™ื”ื™ื• ืžืžืฉ ื‘ืขืœื•ืช ืขืจืš.
15:05
They can save a lot of lives in the interim,
323
905997
2058
ื”ืŸ ื™ื›ื•ืœื•ืช ืœื”ืฆื™ืœ ื”ืจื‘ื” ื—ื™ื™ื ื‘ื™ื ืชื™ื™ื,
15:08
but to see the transformative opportunity to help someone like Steve get around,
324
908055
3833
ืื‘ืœ ื›ื“ื™ ืœืจืื•ืช ืืช ื”ื”ื–ื“ืžื ื•ืช ืžืฉื ืช ื”ื“ืจืš ื”ื–ื• ื›ื“ื™ ืœืขื–ื•ืจ ืœืžื™ืฉื”ื• ื›ืžื• ืกื˜ื™ื‘ ืœื”ืชื ื™ื™ื“,
15:11
to really get to the end case in safety,
325
911888
1969
ื›ื“ื™ ื‘ืืžืช ืœื”ื’ื™ืข ืœืžืงืจื” ื”ืกื•ืคื™ ื‘ื‘ื˜ื™ื—ื•ืช,
15:13
to have the opportunity to change our cities
326
913857
2479
ื›ื“ื™ ืฉืชื”ื™ื” ื”ื–ื“ืžื ื•ืช ืœืฉื ื•ืช ืืช ื”ืขืจื™ื ืฉืœื ื•
15:16
and move parking out and get rid of these urban craters we call parking lots,
327
916336
4204
ื•ืœื”ื•ืฆื™ื ืืช ื”ื—ื ื™ื” ื•ืœื”ืคืชืจ ืžื”ืžื›ืชืฉื™ื ื”ืขื™ืจื•ื ื™ื™ื ืฉืื ื—ื ื• ืงื•ืจืื™ื ืœื”ื ืžื’ืจืฉื™ ื—ื ื™ื”,
15:20
it's the only way to go.
328
920540
1240
ื–ื• ื”ื“ืจืš ื”ื™ื—ื™ื“ื” ืฉืชืขื‘ื•ื“.
15:21
CA: We will be tracking your progress with huge interest.
329
921780
2718
ื›"ื: ืื ื—ื ื• ื ืขืงื•ื‘ ืื—ืจื™ ื”ื”ืชืงื“ืžื•ืช ืฉืœืš ื‘ืขื ื™ื™ืŸ ื’ื“ื•ืœ.
15:24
Thanks so much, Chris. CU: Thank you. (Applause)
330
924498
4232
ืชื•ื“ื” ืจื‘ื” ืœืš, ื›ืจื™ืก. ื›"ื: ืชื•ื“ื” ืœื›ื.(ืžื—ื™ืื•ืช ื›ืคื™ื™ื)
ืขืœ ืืชืจ ื–ื”

ืืชืจ ื–ื” ื™ืฆื™ื’ ื‘ืคื ื™ื›ื ืกืจื˜ื•ื ื™ YouTube ื”ืžื•ืขื™ืœื™ื ืœืœื™ืžื•ื“ ืื ื’ืœื™ืช. ืชื•ื›ืœื• ืœืจืื•ืช ืฉื™ืขื•ืจื™ ืื ื’ืœื™ืช ื”ืžื•ืขื‘ืจื™ื ืขืœ ื™ื“ื™ ืžื•ืจื™ื ืžื”ืฉื•ืจื” ื”ืจืืฉื•ื ื” ืžืจื—ื‘ื™ ื”ืขื•ืœื. ืœื—ืฅ ืคืขืžื™ื™ื ืขืœ ื”ื›ืชื•ื‘ื™ื•ืช ื‘ืื ื’ืœื™ืช ื”ืžื•ืฆื’ื•ืช ื‘ื›ืœ ื“ืฃ ื•ื™ื“ืื• ื›ื“ื™ ืœื”ืคืขื™ืœ ืืช ื”ืกืจื˜ื•ืŸ ืžืฉื. ื”ื›ืชื•ื‘ื™ื•ืช ื’ื•ืœืœื•ืช ื‘ืกื ื›ืจื•ืŸ ืขื ื”ืคืขืœืช ื”ื•ื•ื™ื“ืื•. ืื ื™ืฉ ืœืš ื”ืขืจื•ืช ืื• ื‘ืงืฉื•ืช, ืื ื ืฆื•ืจ ืื™ืชื ื• ืงืฉืจ ื‘ืืžืฆืขื•ืช ื˜ื•ืคืก ื™ืฆื™ืจืช ืงืฉืจ ื–ื”.

https://forms.gle/WvT1wiN1qDtmnspy7