Chris Urmson: How a driverless car sees the road

862,221 views ใƒป 2015-06-26

TED


์•„๋ž˜ ์˜๋ฌธ์ž๋ง‰์„ ๋”๋ธ”ํด๋ฆญํ•˜์‹œ๋ฉด ์˜์ƒ์ด ์žฌ์ƒ๋ฉ๋‹ˆ๋‹ค.

๋ฒˆ์—ญ: ChulGi Han ๊ฒ€ํ† : ํƒœ์ค€ ๊ณต
00:12
So in 1885, Karl Benz invented the automobile.
0
12528
3949
1885๋…„, ์นด๋ฅผ ๋ฒค์ธ ๊ฐ€ ์ž๋™์ฐจ๋ฅผ ๋ฐœ๋ช…ํ–ˆ์Šต๋‹ˆ๋‹ค.
00:16
Later that year, he took it out for the first public test drive,
1
16707
3762
์–ผ๋งˆํ›„์—, ๊ทธ๋Š” ์ฒ˜์Œ์œผ๋กœ ์‚ฌ๋žŒ๋“ค ์•ž์—์„œ ์‹œํ—˜ ์šดํ–‰์„ ํ–ˆ์Šต๋‹ˆ๋‹ค.
00:20
and -- true story -- crashed into a wall.
2
20469
3375
๊ทธ๋ฆฌ๊ณ  ๋ฒฝ์— ์ถฉ๋Œํ–ˆ์ฃ .
00:24
For the last 130 years,
3
24184
2043
130๋…„ ๋™์•ˆ์—
00:26
we've been working around that least reliable part of the car, the driver.
4
26227
4319
์šฐ๋ฆฌ๋Š” ์ž๋™์ž์˜ ๊ฐ€์žฅ ์ทจ์•ฝํ•œ ๋ถ€๋ถ„์ธ ์šด์ „์ž์— ๋Œ€ํ•ด์„œ ์—ฐ๊ตฌ๋ฅผ ํ–ˆ์Šต๋‹ˆ๋‹ค.
00:30
We've made the car stronger.
5
30546
1354
์šฐ๋ฆฌ๋Š” ์ž๋™์ฐจ๋ฅผ ํŠผํŠผํ•˜๊ฒŒ ๋งŒ๋“ค์—ˆ๊ณ 
00:32
We've added seat belts, we've added air bags,
6
32200
2548
์šฐ๋ฆฌ๋Š” ์•ˆ์ „๋ฒจํŠธ์™€ ์—์–ด๋ฐฑ์„ ์ถ”๊ฐ€์‹œ์ผฐ๊ณ 
00:34
and in the last decade, we've actually started trying to make the car smarter
7
34748
3971
๊ทธ๋ฆฌ๊ณ  ์ตœ๊ทผ์— ์šฐ๋ฆฌ๋Š” ์ž๋™์ฐจ๋ฅผ ๋˜‘๋˜‘ํ•˜๊ฒŒ ๋งŒ๋“ค๊ธฐ ์œ„ํ•œ ์‹œ๋„๋ฅผ ์‹œ์ž‘ํ–ˆ์Šต๋‹ˆ๋‹ค.
00:38
to fix that bug, the driver.
8
38719
2938
์šด์ „์ž๋ผ๋Š” ๊ฒฐํ•จ์„ ๊ณ ์น˜๊ธฐ ์œ„ํ•ด์„œ์ฃ .
00:41
Now, today I'm going to talk to you a little bit about the difference
9
41657
3261
์ €๋Š” ์˜ค๋Š˜ ์šด์ „์ž ๋ณด์กฐ ์‹œ์Šคํ…œ์˜
00:44
between patching around the problem with driver assistance systems
10
44918
3808
๋ฌธ์ œ ํ•ด๊ฒฐ ๋ฐฉ์‹ ์ฐจ์ด์— ๋Œ€ํ•ด ์ด์•ผ๊ธฐ ํ•˜๊ณ ์ž ํ•ฉ๋‹ˆ๋‹ค.
00:48
and actually having fully self-driving cars
11
48726
2564
๊ทธ๋ฆฌ๊ณ  ์™„์ „ํ•œ ๋ฌด์ธ์ž๋™์ฐจ์™€
00:51
and what they can do for the world.
12
51290
1880
๊ทธ๊ฒƒ์ด ์„ธ์ƒ์— ๋ฏธ์น  ์˜ํ–ฅ๋„์š”.
00:53
I'm also going to talk to you a little bit about our car
13
53170
2995
์šฐ๋ฆฌ์˜ ์ž๋™์ฐจ์— ๋Œ€ํ•ด์„œ๋„ ์ž ์‹œ ์ด์•ผ๊ธฐ ํ•  ์˜ˆ์ •์ž…๋‹ˆ๋‹ค.
00:56
and allow you to see how it sees the world and how it reacts and what it does,
14
56165
3999
๊ทธ๊ฒƒ์ด ์–ด๋–ป๊ฒŒ ์„ธ์ƒ์— ์žˆ๊ณ  ๋ฐ˜์‘ํ•˜๋ฉฐ ์‹ค์ œ๋กœ ๋ฌด์—‡์ธ์ง€ ๋ง์ด์ฃ .
01:00
but first I'm going to talk a little bit about the problem.
15
60164
3187
ํ•˜์ง€๋งŒ ๋จผ์ € ์ €๋Š” ๋ฌธ์ œ์ ์— ๊ด€ํ•ด ์ด์•ผ๊ธฐ ํ• ๊นŒ ํ•ฉ๋‹ˆ๋‹ค.
01:03
And it's a big problem:
16
63651
1648
๊ทธ๋ฆฌ๊ณ  ์ด๊ฒƒ์€ ํฐ ๋ฌธ์ œ์ž…๋‹ˆ๋‹ค.
01:05
1.2 million people are killed on the world's roads every year.
17
65299
3089
๋งค๋…„ 120๋งŒ๋ช…์˜ ์‚ฌ๋žŒ๋“ค์ด ์ „์„ธ๊ณ„์˜ ๋„๋กœ์—์„œ ์ฃฝ์Šต๋‹ˆ๋‹ค.
01:08
In America alone, 33,000 people are killed each year.
18
68388
3784
๋ฏธ๊ตญ์—์„œ๋งŒ 33๋งŒ๋ช…์˜ ์‚ฌ๋žŒ๋“ค์ด ๋งคํ•ด ์ฃฝ๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
01:12
To put that in perspective,
19
72172
2028
์ด๊ฒƒ์„ ๋„“์€ ์‹œ๊ฐ์œผ๋กœ ๋ณด๋ฉด,
01:14
that's the same as a 737 falling out of the sky every working day.
20
74200
4797
์ฃผ๋ง์„ ์ œ์™ธํ•˜๊ณ  ๋งค์ผ ๋น„ํ–‰๊ธฐ ํ•œ ๋Œ€๊ฐ€ ์ถ”๋ฝํ•˜๋Š” ๊ฒƒ๊ณผ ๊ฐ™์Šต๋‹ˆ๋‹ค.
01:19
It's kind of unbelievable.
21
79342
1786
๋ฏฟ์„ ์ˆ˜ ์—†๋Š” ์ผ์ž…๋‹ˆ๋‹ค.
01:21
Cars are sold to us like this,
22
81548
2298
์ž๋™์ฐจ๋Š” ์ด๋ ‡๊ฒŒ ๋งŽ์ด ํŒ”๋ฆฌ์ง€๋งŒ
01:23
but really, this is what driving's like.
23
83846
2717
์ด ํ†ต๊ณ„๊ฐ€ ์šด์ „์˜ ํ˜„์‹ค์ž…๋‹ˆ๋‹ค.
01:26
Right? It's not sunny, it's rainy,
24
86563
2159
๊ทธ๋ ‡์ฃ ? ํ™”์ฐฝํ•˜์ง€ ์•Š๊ณ  ๋น„์˜ค๋Š” ๋‚ ์”จ์—๋Š”
01:28
and you want to do anything other than drive.
25
88722
2488
์—ฌ๋Ÿฌ๋ถ„์€ ์šด์ „๋ณด๋‹จ ๋‹ค๋ฅธ ๊ฒƒ์ด ํ•˜๊ณ  ์‹ถ์„ ๊ฒ๋‹ˆ๋‹ค.
01:31
And the reason why is this:
26
91210
1622
๊ทธ๋ฆฌ๊ณ  ๊ทธ ์ด์œ ๋Š”
01:32
Traffic is getting worse.
27
92832
1858
๊ตํ†ต๋Ÿ‰์ด ์ ์  ์•…ํ™”๋˜๊ณ  ์žˆ๋‹ค๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
01:34
In America, between 1990 and 2010,
28
94690
3506
๋ฏธ๊ตญ์—์„œ 1990๋…„๊ณผ 2010๋…„ ์‚ฌ์ด์—
01:38
the vehicle miles traveled increased by 38 percent.
29
98196
3504
์šดํ–‰ ๊ฑฐ๋ฆฌ๊ฐ€ 38% ๋Š˜์–ด๋‚ฌ์Šต๋‹ˆ๋‹ค.
01:42
We grew by six percent of roads,
30
102213
2749
๊ฐ™์€ ๊ธฐ๊ฐ„์— ๋„๋กœ๋Š” 6% ์ฆ๊ฐ€ํ–ˆ์Šต๋‹ˆ๋‹ค.
01:44
so it's not in your brains.
31
104962
1602
์ด๊ฒƒ์€ ์ƒ์ƒ์†์˜ ์ผ์ด ์•„๋‹ˆ๋ฉฐ
01:46
Traffic really is substantially worse than it was not very long ago.
32
106564
4276
๊ตํ†ต์ด ์‹ค์ œ๋กœ ์˜ˆ์ „๋ณด๋‹ค ๋‚˜๋น ์ง„ ๊ฒƒ์ด ๊ทธ๋ฆฌ ์˜ค๋ž˜๋˜์ง€๋Š” ์•Š์•˜์Šต๋‹ˆ๋‹ค.
01:50
And all of this has a very human cost.
33
110840
2409
์ด ๋ชจ๋“  ๊ฒฐ๊ณผ๋Š” ์‹ฌ๊ฐํ•œ ์ธ์ ๋น„์šฉ์„ ์ดˆ๋ž˜ํ•ฉ๋‹ˆ๋‹ค.
01:53
So if you take the average commute time in America, which is about 50 minutes,
34
113529
3948
๊ทธ๋ž˜์„œ ๋งŒ์•ฝ ๋ฏธ๊ตญ์˜ ํ‰๊ท ์ด๋™์‹œ๊ฐ„์ธ 50๋ถ„์„
01:57
you multiply that by the 120 million workers we have,
35
117477
3649
1์–ต 2์ฒœ๋งŒ์˜ ์ผํ•˜๋Š” ์‚ฌ๋žŒ์— ๊ณฑํ•˜๊ฒŒ ๋˜๋ฉด
02:01
that turns out to be about six billion minutes
36
121126
2225
60์–ต๋ถ„์ด๋ผ๋Š” ์‹œ๊ฐ„์ด
02:03
wasted in commuting every day.
37
123351
2026
๋งค์ผ ๋‚ญ๋น„๋˜๊ณ  ์žˆ๋‹ค๋Š” ๊ฒฐ๋ก ์ด ๋‚˜์˜ต๋‹ˆ๋‹ค.
02:05
Now, that's a big number, so let's put it in perspective.
38
125377
2827
๋งค์šฐ ํฐ ์ˆซ์ž์ด์ฃ . ์กฐ๊ธˆ ๋‹ค๋ฅธ ๊ด€์ ์—์„œ ๋ณด๋ฉด,
02:08
You take that six billion minutes
39
128204
1774
๊ทธ 60์–ต๋ถ„์„ ๊ฐ€์ ธ์™€
02:09
and you divide it by the average life expectancy of a person,
40
129978
3784
ํ‰๊ท  ์ˆ˜๋ช…์œผ๋กœ ๋‚˜๋ˆ„๋ฉด
02:13
that turns out to be 162 lifetimes
41
133762
3135
162๋ช…๋ถ„์˜ ์ˆ˜๋ช…์ด
02:16
spent every day, wasted,
42
136897
2925
๋งค์ผ ๋‚ญ๋น„๋œ๋‹ค๊ณ  ๋ณผ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
02:19
just getting from A to B.
43
139822
2044
๊ทธ๋ƒฅ ํ†ต๊ทผ์‹œ๊ฐ„์— ๋ง์ด์ฃ .
02:21
It's unbelievable.
44
141866
1730
์ด๊ฑด ๋ฏฟ์„ ์ˆ˜ ์—†๋Š” ์ผ์ž…๋‹ˆ๋‹ค.
02:23
And then, there are those of us who don't have the privilege
45
143596
2844
๊ทธ๋ฆฌ๊ณ  ํ†ต๊ทผ์‹œ๊ฐ„์— ์„œ์„œ๊ฐ€์•ผํ•˜๋Š”
02:26
of sitting in traffic.
46
146440
1672
์‚ฌ๋žŒ๋“ค๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
02:28
So this is Steve.
47
148112
1578
์ด ๋ถ„์€ ์Šคํ‹ฐ๋ธŒ์”จ ์ž…๋‹ˆ๋‹ค.
02:29
He's an incredibly capable guy,
48
149690
1765
๊ต‰์žฅํžˆ ๋Šฅ๋ ฅ ์žˆ๋Š” ๋ถ„์ด์ฃ .
02:31
but he just happens to be blind,
49
151455
2516
ํ•˜์ง€๋งŒ ๊ทธ๋Š” ์‹œ๊ฐ์žฅ์• ์ธ ์ž…๋‹ˆ๋‹ค.
02:33
and that means instead of a 30-minute drive to work in the morning,
50
153971
3217
๊ทธ ๋ง์€ ์•„์นจ์— 30๋ถ„ ์šด์ „๋Œ€์‹ 
02:37
it's a two-hour ordeal of piecing together bits of public transit
51
157188
3979
๊ทธ๋Š” 2์‹œ๊ฐ„๋™์•ˆ ๋ถˆํŽธํ•œ ๋Œ€์ค‘๊ตํ†ต์„ ์ด์šฉํ•˜๊ฑฐ๋‚˜
02:41
or asking friends and family for a ride.
52
161167
2385
์นœ๊ตฌ์™€ ๊ฐ€์กฑ๋“ค์—๊ฒŒ ํ”ฝ์—…์„ ๋ถ€ํƒํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
02:43
He doesn't have that same freedom that you and I have to get around.
53
163552
3669
๊ทธ๋Š” ์—ฌ๋Ÿฌ๋ถ„๊ณผ ์ œ๊ฐ€ ๊ฐ€์ง€๊ณ  ์žˆ๋Š” ์ž์œ ๊ฐ€ ์—†์Šต๋‹ˆ๋‹ค.
02:47
We should do something about that.
54
167221
2460
์šฐ๋ฆฌ๋Š” ๊ทธ๊ฒƒ์„ ํ•ด๊ฒฐํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
02:49
Now, conventional wisdom would say
55
169891
1757
๊ธฐ์กด ํ•ด๊ฒฐ์ฑ…์€
02:51
that we'll just take these driver assistance systems
56
171648
2492
์šด์ „๋ณด์กฐ์‹œ์Šคํ…œ์„ ๋„์ž…ํ•˜๊ณ 
02:54
and we'll kind of push them and incrementally improve them,
57
174140
3750
์ ์ฐจ์ ์œผ๋กœ ๋ฐœ์ „์‹œ์ผœ
02:57
and over time, they'll turn into self-driving cars.
58
177890
2542
๊ฒฐ๊ตญ, ๋ฌด์ธ์ž๋™์ฐจ๋ฅผ ๊ฐœ๋ฐœํ•˜๋Š” ๊ฒƒ ์ž…๋‹ˆ๋‹ค.
03:00
Well, I'm here to tell you that's like me saying
59
180432
2409
๊ธ€์Ž„์š”, ์ด๊ฑด ์‚ฌ์‹ค ์ด๋Ÿฐ ๋ง๊ณผ ๋น„์Šทํ•˜์ฃ .
03:02
that if I work really hard at jumping, one day I'll be able to fly.
60
182841
4057
"์ ํ”„๋ฅผ ์ •๋ง ์—ด์‹ฌํžˆ ์—ฐ์Šตํ•œ๋‹ค๋ฉด ์–ธ์  ๊ฐ€ ํ•˜๋Š˜์„ ๋‚  ์ˆ˜ ์žˆ์„๊บผ์•ผ"
03:06
We actually need to do something a little different.
61
186898
2728
์šฐ๋ฆฌ๋Š” ์‚ฌ์‹ค ์‚ด์ง ๋‹ค๋ฅธ ์ผ์„ ํ•  ํ•„์š”๊ฐ€ ์žˆ์Šต๋‹ˆ๋‹ค.
03:09
And so I'm going to talk to you about three different ways
62
189626
2711
๊ทธ๋ž˜์„œ ์ €๋Š” ๋ฌด์ธ์ž๋™์ฐจ์™€ ์šด์ „๋ณด์กฐ ์‹œ์Šคํ…œ์ด
03:12
that self-driving systems are different than driver assistance systems.
63
192337
3346
๋‹ค๋ฅธ 3๊ฐ€์ง€์— ๋Œ€ํ•ด ์ด์•ผ๊ธฐํ•ด๋ณด๊ณ ์ž ํ•ฉ๋‹ˆ๋‹ค.
03:15
And I'm going to start with some of our own experience.
64
195683
2651
์šฐ๋ฆฌ๋“ค์˜ ๊ฒฝํ—˜์„ ์ด์•ผ๊ธฐํ•˜๋ฉฐ ์‹œ์ž‘ํ• ๊นŒ ํ•ฉ๋‹ˆ๋‹ค.
03:18
So back in 2013,
65
198334
2253
2013๋…„์œผ๋กœ ๋Œ์•„๊ฐ€์„œ,
03:20
we had the first test of a self-driving car
66
200587
2663
์šฐ๋ฆฌ๋Š” ๋ฌด์ธ ์ž๋™์ฐจ ์ฒซ ์‹œ๋ฒ” ์šดํ–‰์„ ํ–ˆ์Šต๋‹ˆ๋‹ค.
03:23
where we let regular people use it.
67
203250
2027
๋ณดํ†ต ์‚ฌ๋žŒ๋“ค์ด ์ž˜ ๋‹ค๋‹ˆ๋Š” ์žฅ์†Œ์—์„œ์š”.
03:25
Well, almost regular -- they were 100 Googlers,
68
205277
2202
์ผ๋ฐ˜์ ์ธ 100๋ช…์˜ ๊ตฌ๊ธ€ ์ด์šฉ์ž๋“ค์ž…๋‹ˆ๋‹ค.
03:27
but they weren't working on the project.
69
207479
2003
ํ”„๋กœ์ ํŠธ์™€๋Š” ๋ฌด๊ด€ํ•œ ์‚ฌ๋žŒ๋“ค์ž…๋‹ˆ๋‹ค.
03:29
And we gave them the car and we allowed them to use it in their daily lives.
70
209482
3621
์šฐ๋ฆฌ๋Š” ๊ทธ๋“ค์—๊ฒŒ ์ž๋™์ฐจ๋ฅผ ์ฃผ๊ณ  ์ผ์ƒ ์ƒํ™œ์— ์‚ฌ์šฉํ•˜๋„๋ก ํ–ˆ์Šต๋‹ˆ๋‹ค.
03:33
But unlike a real self-driving car, this one had a big asterisk with it:
71
213103
3719
ํ•˜์ง€๋งŒ ์ง„์งœ ๋ฌด์ธ์ฐจ์™€๋Š” ๋‹ค๋ฅด๊ฒŒ ํฌ๊ฒŒ ์ฃผ๋ชฉํ•ด์•ผ ํ•  ์ ์ด ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค.
03:36
They had to pay attention,
72
216822
1504
์ง‘์ค‘ํ•ด์•ผ ํ–ˆ์ฃ .
03:38
because this was an experimental vehicle.
73
218326
2633
์™œ๋ƒํ•˜๋ฉด ๊ทธ๊ฒƒ์€ ํ…Œ์ŠคํŠธ ์ฐจ๋Ÿ‰์ด์—ˆ์œผ๋‹ˆ๊นŒ์š”.
03:40
We tested it a lot, but it could still fail.
74
220959
3525
์šฐ๋ฆฌ๋Š” ๋งŽ์€ ์‹คํ—˜์„ ํ–ˆ์ง€๋งŒ ๊ณ„์† ์‹คํŒจํ–ˆ์Šต๋‹ˆ๋‹ค.
03:44
And so we gave them two hours of training,
75
224484
2059
2์‹œ๊ฐ„์˜ ํ›ˆ๋ จ ๋์—
03:46
we put them in the car, we let them use it,
76
226543
2092
๊ทธ๋“ค์€ ์ž๋™์ฐจ๋ฅผ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค.
03:48
and what we heard back was something awesome,
77
228635
2127
๊ทธ๋ฆฌ๊ณ  ํ›„๊ธฐ๋Š” ๋†€๋ผ์› ์Šต๋‹ˆ๋‹ค.
03:50
as someone trying to bring a product into the world.
78
230762
2524
์–ด๋–ค ์‚ฌ๋žŒ์ด ์ƒํ’ˆ์„ ์†Œ๊ฐœํ•˜๋ ค๊ณ  ์‹œ๋„ํ•  ๋•Œ์ฒ˜๋Ÿผ
03:53
Every one of them told us they loved it.
79
233286
1925
๋ชจ๋“  ์šด์ „์ž๋“ค์ด ๊ทน์ฐฌํ–ˆ์Šต๋‹ˆ๋‹ค.
03:55
In fact, we had a Porsche driver who came in and told us on the first day,
80
235211
3566
์‚ฌ์‹ค, ํฌ๋ฅด์‰ ์˜ค๋„ˆ๊ฐ€ ์šฐ๋ฆฌ์—๊ฒŒ ์™€์„œ ์ฒซ ๋‚  ์ด๋Ÿฐ ๋ง์„ ํ–ˆ์Šต๋‹ˆ๋‹ค.
03:58
"This is completely stupid. What are we thinking?"
81
238777
2663
"์ •๋ง ๋ฉ์ฒญํ•œ ์ง“์ž…๋‹ˆ๋‹ค."
04:01
But at the end of it, he said, "Not only should I have it,
82
241850
2840
ํ•˜์ง€๋งŒ ๋งˆ์ง€๋ง‰ ๋‚ ์— ๊ทธ๋Š” "๋‚˜๋งŒ ๊ฐ€์งˆ ๊ฒƒ์ด ์•„๋‹ˆ๋ผ,
04:04
everyone else should have it, because people are terrible drivers."
83
244690
3175
๋ชจ๋“  ์‚ฌ๋žŒ์—๊ฒŒ ํ•„์š”ํ•˜๋‹ค." ๋ผ๊ณ  ๋งํ–ˆ์Šต๋‹ˆ๋‹ค.
04:09
So this was music to our ears,
84
249135
1735
์šฐ๋ฆฌ์—๊ฒŒ ์Œ์•…์ฒ˜๋Ÿผ ๋“ค๋ ธ์ฃ .
04:10
but then we started to look at what the people inside the car were doing,
85
250870
3803
๊ทธ๋ฆฌ๊ณ  ์šฐ๋ฆฌ๋Š” ์‚ฌ๋žŒ๋“ค์ด ์ฐจ ์•ˆ์—์„œ ๋ฌด์Šจ ์ผ์„ ํ•˜๋Š”์ง€ ์‚ดํŽด๋ณด์•˜์Šต๋‹ˆ๋‹ค.
04:14
and this was eye-opening.
86
254673
1579
๊ทธ๋ฆฌ๊ณ  ์ด๊ฒƒ์€ ๋†€๋ผ์› ์Šต๋‹ˆ๋‹ค.
04:16
Now, my favorite story is this gentleman
87
256252
2438
๊ฐ€์žฅ ์ข‹์•„ํ•˜๋Š” ์ผํ™”๋Š” ํ•œ ์‹ ์‚ฌ๋ถ„์˜ ์ด์•ผ๊ธฐ์ž…๋‹ˆ๋‹ค.
04:18
who looks down at his phone and realizes the battery is low,
88
258690
3829
๊ทธ๋Š” ํ•ธ๋“œํฐ์„ ๋ณด๊ณ  ๋ฐฐํ„ฐ๋ฆฌ๊ฐ€ ์–ผ๋งˆ ๋‚จ์ง€ ์•Š์•˜๋‹ค๋Š” ๊ฒƒ์„ ์•Œ์•˜์Šต๋‹ˆ๋‹ค.
04:22
so he turns around like this in the car and digs around in his backpack,
89
262519
4548
๊ทธ๋ฆฌ๊ณค ๊ทธ๋Š” ์ฐจ ์•ˆ์—์„œ ์ด๋ ‡๊ฒŒ ๋‘˜๋Ÿฌ๋ณด๋ฉฐ ๊ทธ์˜ ๊ฐ€๋ฐฉ์•ˆ์„ ๋’ค์ง‘๋‹ˆ๋‹ค.
04:27
pulls out his laptop,
90
267067
2153
๊ทธ์˜ ๋…ธํŠธ๋ถ์„ ๊บผ๋‚ด๊ณ 
04:29
puts it on the seat,
91
269220
1567
๊ทธ๊ฒƒ์„ ์ขŒ์„์— ๋‘๊ณ 
04:30
goes in the back again,
92
270787
1764
๋‹ค์‹œ ์ฐพ๊ธฐ ์‹œ์ž‘ํ•ฉ๋‹ˆ๋‹ค.
04:32
digs around, pulls out the charging cable for his phone,
93
272551
3367
๊ทธ๋ฆฌ๊ณ ๋Š” ํ•ธ๋“œํฐ ์ถฉ์ „๊ธฐ๋ฅผ ๊บผ๋ƒ…๋‹ˆ๋‹ค.
04:35
futzes around, puts it into the laptop, puts it on the phone.
94
275918
3367
๊ทธ์˜ ๋…ธํŠธ๋ถ๊ณผ ํ•ธ๋“œํฐ์„ ์—ฐ๊ฒฐํ•ฉ๋‹ˆ๋‹ค.
04:39
Sure enough, the phone is charging.
95
279285
2043
์•„๋‹ˆ๋‚˜ ๋‹ค๋ฅผ๊นŒ ํ•ธ๋“œํฐ์„ ์ถฉ์ „ํ•ฉ๋‹ˆ๋‹ค.
04:41
All the time he's been doing 65 miles per hour down the freeway.
96
281328
3994
๊ทธ๊ฐ€ ์‹œ์† 60 ๋งˆ์ผ๋กœ ๊ณ ์†๋„๋กœ์„ ๋‹ฌ๋ฆฌ๋Š” ๋™์•ˆ์— ๋ง์ด์ฃ .
04:45
Right? Unbelievable.
97
285322
2484
๊ทธ๋ ‡์ฃ ? ๋†€๋ผ์šด ์ผ์ž…๋‹ˆ๋‹ค.
04:47
So we thought about this and we said, it's kind of obvious, right?
98
287806
3121
์ด๊ฒƒ์€ ๊ต‰์žฅํžˆ ๋ช…๋ฐฑํ•ฉ๋‹ˆ๋‹ค.
04:50
The better the technology gets,
99
290927
2263
๊ธฐ์ˆ ์ด ์ ์  ๋‚˜์•„์งˆ ์ˆ˜๋ก
04:53
the less reliable the driver is going to get.
100
293190
2121
์šด์ „์ž๋“ค์ด ํ•ด์•ผํ•  ๊ฒƒ์€ ์ค„์–ด๋“ญ๋‹ˆ๋‹ค.
04:55
So by just making the cars incrementally smarter,
101
295311
2396
์ž๋™์ฐจ๋ฅผ ํ˜์‹ ์ ์œผ๋กœ ๋˜‘๋˜‘ํ•˜๊ฒŒ ๋งŒ๋“œ๋Š” ๊ฒƒ์œผ๋กœ๋Š”
04:57
we're probably not going to see the wins we really need.
102
297707
2902
์šฐ๋ฆฌ๊ฐ€ ์ •๋ง๋กœ ํ•„์š”๋กœ ํ•˜๋Š” ๊ฒƒ์„ ๋ณผ ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค.
05:00
Let me talk about something a little technical for a moment here.
103
300609
3901
์—ฌ๊ธฐ์„œ ์ œ๊ฐ€ ๊ธฐ์ˆ ์— ๋Œ€ํ•ด ์•ฝ๊ฐ„ ์„ค๋ช…ํ•˜๊ฒ ์Šต๋‹ˆ๋‹ค.
05:04
So we're looking at this graph, and along the bottom
104
304510
2438
์•„๋ž˜ ์ชฝ๋ถ€ํ„ฐ ๊ทธ๋ž˜ํ”„๋ฅผ ๋ณด์‹œ๋ฉด
05:06
is how often does the car apply the brakes when it shouldn't.
105
306948
3051
์•ˆ์ข‹์€ ์‹œ์ ์— ๋ธŒ๋ ˆ์ดํฌ๋ฅผ ์–ผ๋งˆ๋‚˜ ๋ฐŸ์•˜๋‚˜ ๋ณด์—ฌ์ค๋‹ˆ๋‹ค.
05:09
You can ignore most of that axis,
106
309999
1621
๋Œ€๋ถ€๋ถ„์˜ ์ถ•์„ ๋ฌด์‹œํ•ด๋„ ์ข‹์Šต๋‹ˆ๋‹ค.
05:11
because if you're driving around town, and the car starts stopping randomly,
107
311620
3719
์™œ๋ƒํ•˜๋ฉด ์—ฌ๋Ÿฌ๋ถ„์ด ์‹œ๊ณจ์—์„œ ์šด์ „ํ•œ๋‹ค๋ฉด ์ž๋™์ฐจ๋Š” ์–ด๋Š๋•Œ๋‚˜ ๋ฉˆ์ถœํ…Œ๋‹ˆ๊นŒ์š”.
05:15
you're never going to buy that car.
108
315339
1701
์šฐ๋ฆฌ๋Š” ๊ทธ๋Ÿฐ ์ฐจ๋“ค์„ ์•ˆ์‚ฌ๊ฒ ์ฃ .
05:17
And the vertical axis is how often the car is going to apply the brakes
109
317040
3375
๊ทธ๋ฆฌ๊ณ  ์ˆ˜์ง์„ ์€ ์ž๋™์ฐจ๊ฐ€ ์–ผ๋งˆ๋‚˜ ์ž์ฃผ ๋ธŒ๋ ˆ์ดํฌ๋ฅผ
05:20
when it's supposed to to help you avoid an accident.
110
320415
3049
์‚ฌ๊ณ ๋ฅผ ๋ง‰๊ธฐ ์œ„ํ•ด ๋ฐŸ๋Š”์ง€ ๋ณด์—ฌ์ค๋‹ˆ๋‹ค.
05:23
Now, if we look at the bottom left corner here,
111
323464
2221
์ž ๊ทธ๋Ÿผ ์—ฌ๊ธฐ ์•„๋ž˜์ชฝ ๊ตฌ์„์„ ๋ณด์‹œ๋ฉด
05:25
this is your classic car.
112
325685
1845
์ด๊ฒƒ์ด ์ „ํ˜•์ ์ธ ์ž๋™์ฐจ์ž…๋‹ˆ๋‹ค.
05:27
It doesn't apply the brakes for you, it doesn't do anything goofy,
113
327530
3133
์Šค์Šค๋กœ ๋ธŒ๋ ˆ์ดํฌ๊ฐ€ ์ž‘๋™ํ•˜์ง€ ์•Š์Šต๋‹ˆ๋‹ค.
05:30
but it also doesn't get you out of an accident.
114
330663
2779
๊ทธ๋ ‡์ง€๋งŒ ๋˜ํ•œ ์ด๊ฒƒ์€ ์‚ฌ๊ณ ๋ฐฉ์ง€ ์‹œ์Šคํ…œ๋„ ์—†์Šต๋‹ˆ๋‹ค.
05:33
Now, if we want to bring a driver assistance system into a car,
115
333442
3018
์šด์ „๋ณด์กฐ ์‹œ์Šคํ…œ์„ ์ž๋™์ฐจ์— ์ถ”๊ฐ€์‹œํ‚ค๊ธฐ ์œ„ํ•ด
05:36
say with collision mitigation braking,
116
336460
1828
05:38
we're going to put some package of technology on there,
117
338288
2612
์šฐ๋ฆฌ๋Š” ์•ฝ๊ฐ„์˜ ๊ธฐ์ˆ ์ ์ธ ๊ฒƒ๋“ค์„ ๋„ฃ์–ด๋ณผ๊นŒ ํ•ฉ๋‹ˆ๋‹ค.
05:40
and that's this curve, and it's going to have some operating properties,
118
340900
3418
์ด ์ปค๋ธŒ๊ฐ€ ์šฐ๋ฆฌ๊ฐ€ ๊ธฐ์ˆ ์„ ์ ์šฉํ• ๋•Œ ๋‚˜ํƒ€๋‚  ๊ทธ๋ž˜ํ”„์ž…๋‹ˆ๋‹ค.
05:44
but it's never going to avoid all of the accidents,
119
344318
2490
ํ•˜์ง€๋งŒ ์ด๊ฒƒ์ด ๋ชจ๋“  ์‚ฌ๊ณ ๋ฅผ ์˜ˆ๋ฐฉํ•  ์ˆ˜๋Š” ์—†์Šต๋‹ˆ๋‹ค.
05:46
because it doesn't have that capability.
120
346808
2059
์™œ๋ƒํ•˜๋ฉด ๊ทธ๋Ÿฐ ์—ญ๋Ÿ‰์ด ์—†๊ธฐ ๋•Œ๋ฌธ์ด์ฃ .
05:48
But we'll pick some place along the curve here,
121
348867
2249
์šฐ๋ฆฌ๋Š” ์ด ์ปค๋ธŒ๋ฅผ ์ค‘์‹ฌ์œผ๋กœ ๋‹ค๋ฃจ์–ด๋ณผ๊นŒํ•ฉ๋‹ˆ๋‹ค.
05:51
and maybe it avoids half of accidents that the human driver misses,
122
351116
3254
์ด๊ฒƒ์€ ์šด์ „์ž๋“ค์ด ๋†“์น˜๋Š” ์ ˆ๋ฐ˜์˜ ์‚ฌ๊ณ ๋ฅผ ์ค„์—ฌ์ค๋‹ˆ๋‹ค.
05:54
and that's amazing, right?
123
354370
1297
์ฐธ ๋†€๋ž์Šต๋‹ˆ๋‹ค. ๊ทธ๋ ‡์ฃ ?
05:55
We just reduced accidents on our roads by a factor of two.
124
355667
2727
๋„๋กœ ์œ„ ์‚ฌ๊ณ ๋ฅผ ์ ˆ๋ฐ˜์œผ๋กœ ์ค„์ผ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
05:58
There are now 17,000 less people dying every year in America.
125
358394
3987
์ด์ œ 1๋งŒ 7์ฒœ๋ช…๋ณด๋‹ค ์ ์€ ์‚ฌ๋žŒ๋“ค์ด ๋ฏธ๊ตญ์—์„œ ๋งคํ•ด ์‚ฌ๋งํ•  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
06:02
But if we want a self-driving car,
126
362381
2020
๋งŒ์•ฝ ์šฐ๋ฆฌ๊ฐ€ ๋ฌด์ธ์ž๋™์ฐจ๋ฅผ ์›ํ•œ๋‹ค๋ฉด,
06:04
we need a technology curve that looks like this.
127
364401
2307
๊ทธ๋ž˜ํ”„๊ฐ€ ์ด๋Ÿฌํ•œ ๋ชจ์–‘์œผ๋กœ ๋ณด์—ฌ์•ผํ•ฉ๋‹ˆ๋‹ค.
06:06
We're going to have to put more sensors in the vehicle,
128
366708
2599
์šฐ๋ฆฌ๋Š” ๋” ๋งŽ์€ ๊ฐ์ง€ ์žฅ์น˜๋“ค์„ ์‚ฝ์ž…ํ•  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
06:09
and we'll pick some operating point up here
129
369307
2021
์ฃผํ™ฉ์ƒ‰ ์„ ๊นŒ์ง€ ์„ฑ๋Šฅ์„ ๊ฐœ์„ ์‹œํ‚ฌ ๊ฒƒ์ž…๋‹ˆ๋‹ค.
06:11
where it basically never gets into a crash.
130
371328
2019
์ ˆ๋Œ€ ์ถฉ๋Œ์ด ์ผ์–ด๋‚˜์ง€ ์•Š์ฃ .
06:13
They'll happen, but very low frequency.
131
373347
2443
์ถฉ๋Œ์ด ์ผ์–ด๋‚œ๋‹คํ•ด๋„, ๋งค์šฐ ๋‚ฎ์€ ํšŸ์ˆ˜์ผ ๊ฒƒ์ž…๋‹ˆ๋‹ค.
06:15
Now you and I could look at this and we could argue
132
375790
2461
์ด์ œ ์ด๊ฒƒ์ด ์ ์ง„์ ์œผ๋กœ ๊ฐ€๋Šฅํ•œ์ง€ ์ด์•ผ๊ธฐ ํ•ด๋ด…์‹œ๋‹ค.
06:18
about whether it's incremental, and I could say something like "80-20 rule,"
133
378251
3605
์ €๋Š” ์ด๊ฒƒ์€ "80-20 ๊ทœ์น™" ์ด๋ผ๊ณ  ๋งํ•ฉ๋‹ˆ๋‹ค.
06:21
and it's really hard to move up to that new curve.
134
381856
2568
๊ทธ๋ฆฌ๊ณ  ๊ทธ๋ž˜ํ”„๋ฅผ ๋ณ€ํ™”์‹œํ‚ค๋Š” ๊ฒƒ์€ ์ •๋ง ํž˜๋“ญ๋‹ˆ๋‹ค.
06:24
But let's look at it from a different direction for a moment.
135
384424
2934
์ž ๊น ๋‹ค๋ฅธ ๋ฐฉํ–ฅ์œผ๋กœ ์ƒ๊ฐํ•ด๋ด…์‹œ๋‹ค.
06:27
So let's look at how often the technology has to do the right thing.
136
387358
3512
๊ธฐ์ˆ ์˜ ์‹ ๋ขฐ๋„๋ฅผ ํ•œ๋ฒˆ ์‚ดํŽด๋ณผ๊นŒ์š”?
06:30
And so this green dot up here is a driver assistance system.
137
390870
3506
์—ฌ๊ธฐ ์ดˆ๋ก์ƒ‰ ์ ์€ ์šด์ „๋ณด์กฐ ์‹œ์Šคํ…œ์ž…๋‹ˆ๋‹ค.
06:34
It turns out that human drivers
138
394376
2485
์ด๊ฒƒ์€ ์šด์ „์ž๋“ค์ด
06:36
make mistakes that lead to traffic accidents
139
396861
2647
๋ฏธ๊ตญ์—์„œ ๊ฑฐ์˜ ์‹ญ๋งŒ ๋งˆ์ผ์— ํ•œ๋ฒˆ์”ฉ
06:39
about once every 100,000 miles in America.
140
399508
3172
๊ตํ†ต์‚ฌ๊ณ ๋กœ ์ด์–ด์ง€๋Š” ์‹ค์ˆ˜๋ฅผ ํ•˜๋Š” ๊ฒƒ์„ ๋ณด์—ฌ์ค๋‹ˆ๋‹ค.
06:42
In contrast, a self-driving system is probably making decisions
141
402680
3167
๊ทธ์™€ ๋ฐ˜๋Œ€๋กœ, ๋ฌด์ธ ์ž๋™์ฐจ๋Š” ๋Œ€๋žต
06:45
about 10 times per second,
142
405847
3663
์ดˆ๋‹น 10๋ฒˆ์”ฉ ๊ฒฐ์ •์„ ํ•ฉ๋‹ˆ๋‹ค.
06:49
so order of magnitude,
143
409510
1422
ํฌ๊ธฐ์— ๋น„๊ตํ•˜๋ฉด,
06:50
that's about 1,000 times per mile.
144
410932
2832
์ผ ๋งˆ์ผ๋‹น ์ฒœ ๋ฒˆ ์ •๋„ ํ•˜๋Š” ๊ฒƒ์ด์ฃ .
06:53
So if you compare the distance between these two,
145
413764
2485
๊ทธ๋ž˜์„œ ๋งŒ์•ฝ ๊ฑฐ๋ฆฌ์— ์ด ๋‘๊ฐ€์ง€๋ฅผ ๋น„๊ตํ•œ๋‹ค๋ฉด,
06:56
it's about 10 to the eighth, right?
146
416249
2600
10์˜ ์—ฌ๋Ÿ ์ œ๊ณฑ์„ ํ•œ ๊ฒƒ์ž…๋‹ˆ๋‹ค. ๊ทธ๋ ‡์ฃ ?
06:58
Eight orders of magnitude.
147
418849
1765
10์˜ ์—ฌ๋Ÿ ์ œ๊ณฑ์ž…๋‹ˆ๋‹ค.
07:00
That's like comparing how fast I run
148
420614
2809
์ด๊ฒƒ์€ ๋‚ด๊ฐ€ ๋น›๊ณผ ๋น„๊ต ํ–ˆ์„ ๋•Œ ์–ผ๋งˆ๋‚˜ ๋นจ๋ฆฌ ๋‹ฌ๋ฆด ์ˆ˜
07:03
to the speed of light.
149
423423
2206
์žˆ๋Š”์ง€์™€ ๋น„์Šทํ•ฉ๋‹ˆ๋‹ค.
07:05
It doesn't matter how hard I train, I'm never actually going to get there.
150
425629
3785
์ด๊ฒƒ์€ ํ›ˆ๋ จ์˜ ๋ฌธ์ œ๊ฐ€ ์•„๋‹™๋‹ˆ๋‹ค. ์ €๋Š” ์ ˆ๋Œ€ ๋”ฐ๋ผ์žก์„ ์ˆ˜ ์—†์„ ๊ฒƒ์ž…๋‹ˆ๋‹ค.
07:09
So there's a pretty big gap there.
151
429414
2438
๊ทธ๋Ÿฌ๋‹ˆ๊นŒ ์—„์ฒญ๋‚œ ์ฐจ์ด์ธ ๊ฒƒ์ž…๋‹ˆ๋‹ค.
07:11
And then finally, there's how the system can handle uncertainty.
152
431852
3729
๊ทธ๋ฆฌ๊ณ  ์–ด๋–ป๊ฒŒ ์‹œ์Šคํ…œ์ด ๋ถˆํ™•์‹คํ•œ ๊ฒƒ์„ ๋‹ค๋ฃจ๋Š” ์ง€ ์•Œ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
07:15
So this pedestrian here might be stepping into the road, might not be.
153
435581
3323
์ด ์‚ฌ๋žŒ์€ ๋„๋กœ๋กœ ๊ฑธ์–ด๊ฐˆ ์ˆ˜๋„ ์žˆ๊ณ  ์•ˆ ๊ฐˆ ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
07:18
I can't tell, nor can any of our algorithms,
154
438904
3395
์ €๋„ ๋งํ• ์ˆ˜ ์—†๊ณ  ์–ด๋–ค ์•Œ๊ณ ๋ฆฌ์ฆ˜๋„ ๋งˆ์ฐฌ๊ฐ€์ง€ ์ž…๋‹ˆ๋‹ค.
07:22
but in the case of a driver assistance system,
155
442310
2284
ํ•˜์ง€๋งŒ ์šด์ „๋ณด์กฐ ์‹œ์Šคํ…œ์˜ ๊ฒฝ์šฐ์—๋Š”,
07:24
that means it can't take action, because again,
156
444594
2806
ํ–‰๋™์„ ์ทจํ•˜์ง€ ์•Š์„ ๊ฒƒ์ž…๋‹ˆ๋‹ค. ์™œ๋ƒํ•˜๋ฉด
07:27
if it presses the brakes unexpectedly, that's completely unacceptable.
157
447400
3339
์˜ˆ์ธก๋˜์ง€ ์•Š์€ ๋ธŒ๋ ˆ์ดํฌ๋Š” ์ ˆ๋Œ€ ์šฉ๋‚ฉํ•  ์ˆ˜ ์—†๋Š” ์ผ์ด๊ธฐ ๋•Œ๋ฌธ์ž…๋‹ˆ๋‹ค.
07:30
Whereas a self-driving system can look at that pedestrian and say,
158
450739
3133
๋ฐ˜๋ฉด์— ๋ฌด์ธ์ž๋™์ฐจ๋Š” ๋ณดํ–‰์ž๋ฅผ ๋ณผ ์ˆ˜์žˆ๊ณ 
07:33
I don't know what they're about to do,
159
453872
1890
์–ด๋–คํ–‰๋™์„ ์ทจํ• ์ง€๋Š” ๋ชจ๋ฅด๊ฒ ์Šต๋‹ˆ๋‹ค.
07:35
slow down, take a better look, and then react appropriately after that.
160
455762
3762
์†๋„๋ฅผ ์ค„์ด๊ณ  ์ฃผ์œ„๋ฅผ ์‚ดํ”ผ๊ณ  ๊ทธ ํ›„์— ์ ์ ˆํ•œ ํ–‰๋™์„ ํ•  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
07:39
So it can be much safer than a driver assistance system can ever be.
161
459524
3702
๊ทธ๋Ÿฌ๋‹ˆ ์šด์ „๋ณด์กฐ ์‹œ์Šคํ…œ ๋ณด๋‹ค ๋”์šฑ ์•ˆ์ „ํ•  ์ˆ˜ ๋ฐ–์— ์—†์Šต๋‹ˆ๋‹ค.
07:43
So that's enough about the differences between the two.
162
463226
2730
์ง€๊ธˆ๊นŒ์ง€ ๋‘ ์‹œ์Šคํ…œ์— ์ฐจ์ด์— ๋Œ€ํ•ด์„œ ์„ค๋ช…ํ–ˆ์Šต๋‹ˆ๋‹ค.
07:45
Let's spend some time talking about how the car sees the world.
163
465956
3484
์ด์ œ ์–ด๋–ป๊ฒŒ ์ฐจ๊ฐ€ ์„ธ์ƒ์„ ๋ณด๋Š”์ง€์— ๋Œ€ํ•ด ์ด์•ผ๊ธฐ ๋‚˜๋ˆ ๋ณด๋„๋ก ํ•ฉ์‹œ๋‹ค.
07:49
So this is our vehicle.
164
469440
1252
์ด๊ฒƒ์ด ์ž๋™์ฐจ ์ž…๋‹ˆ๋‹ค.
07:50
It starts by understanding where it is in the world,
165
470692
2438
๊ทธ๊ฒƒ์ด ์–ด๋””์— ์žˆ๋Š”์ง€๋ฅผ ๊ฐ์ง€ํ•˜๋ฉด์„œ ์‹œ์ž‘ํ•ฉ๋‹ˆ๋‹ค.
07:53
by taking a map and its sensor data and aligning the two,
166
473130
2787
์ง€๋„์™€ ์„ผ์„œ์˜ ์ž๋ฃŒ๋ฅผ ๋ณด๊ณ  ์ •๋ ฌํ•ฉ๋‹ˆ๋‹ค.
07:55
and then we layer on top of that what it sees in the moment.
167
475917
2948
๊ทธ๋ฆฌ๊ณ  ์ˆœ๊ฐ„์ ์œผ๋กœ ์ธ์‹ํ•˜๋Š” ์ฃผ๋ณ€์ƒํ™ฉ์„ ์‚ฝ์ž…ํ•ฉ๋‹ˆ๋‹ค.
07:58
So here, all the purple boxes you can see are other vehicles on the road,
168
478865
3655
์—ฌ๊ธฐ ๋ณด๋ผ์ƒ‰ ๋ฐ•์Šค๋“ค์€ ๋„๋กœ์œ„์— ๋‹ค๋ฅธ ์ฐจ๋“ค์„ ์˜๋ฏธํ•˜๊ณ 
08:02
and the red thing on the side over there is a cyclist,
169
482520
2528
๋นจ๊ฐ„์ƒ‰์€ ์ž์ „๊ฑฐ๋ฅผ ์˜๋ฏธํ•ฉ๋‹ˆ๋‹ค.
08:05
and up in the distance, if you look really closely,
170
485048
2402
๊ทธ๋ฆฌ๊ณ  ์ € ๋ฉ€๋ฆฌ ์ž์„ธํžˆ๋ณด๋ฉด
08:07
you can see some cones.
171
487450
1794
๋ช‡๋ช‡ ์›๋ฟ”๋„ ๋ณผ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
08:09
Then we know where the car is in the moment,
172
489244
2773
์šฐ๋ฆฌ๋Š” ์ฃผ๋ณ€ ๋„๋กœ์ƒํ™ฉ์„ ์ดํ•ดํ•˜์ง€๋งŒ
08:12
but we have to do better than that: we have to predict what's going to happen.
173
492017
3833
์ด๋ฅผ ๋ฐ”ํƒ•์œผ๋กœ ์˜ˆ์ธก๋Šฅ๋ ฅ์„ ํ‚ค์›Œ์•ผ ํ•ฉ๋‹ˆ๋‹ค.
08:15
So here the pickup truck in top right is about to make a left lane change
174
495850
3488
์˜ค๋ฅธ์ชฝ์— ์žˆ๋Š” ํŠธ๋Ÿญ์€ ์•ž์ชฝ ๋„๋กœ๊ฐ€ ๋ง‰ํ˜€์„œ
08:19
because the road in front of it is closed,
175
499338
2223
ํ˜„์žฌ ์ฐจ์„ ์—์„œ ๋ฒ—์–ด๋‚˜์•ผ ํ•ฉ๋‹ˆ๋‹ค.
08:21
so it needs to get out of the way.
176
501561
1731
์™ผ์ชฝ์œผ๋กœ ์ฐจ์„ ๋ณ€๊ฒฝ์„ ์‹œ๋„ํ•ฉ๋‹ˆ๋‹ค.
08:23
Knowing that one pickup truck is great,
177
503292
1863
์ด ํŠธ๋Ÿญ์„ ๊ฐ์ง€ํ•œ ๊ฒƒ์€ ํ›Œ๋ฅญํ•ฉ๋‹ˆ๋‹ค.
08:25
but we really need to know what everybody's thinking,
178
505155
2479
ํ•˜์ง€๋งŒ ์šฐ๋ฆฌ๋Š” ๋ชจ๋‘์˜ ์ƒ๊ฐ์„ ์ฝ์–ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
08:27
so it becomes quite a complicated problem.
179
507634
2507
์ด์ œ ๊ฝค ๋ฌธ์ œ๊ฐ€ ๋ณต์žกํ•ด ์ง‘๋‹ˆ๋‹ค.
08:30
And then given that, we can figure out how the car should respond in the moment,
180
510141
4749
์ฃผ์–ด์ง„ ์ƒํ™ฉ์œผ๋กœ ๋ถ€ํ„ฐ ๋ฌด์ธ์ž๋™์ฐจ๋Š” ์ˆœ๊ฐ„์ ์œผ๋กœ ํŒ๋‹จํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
08:34
so what trajectory it should follow, how quickly it should slow down or speed up.
181
514890
3866
์–ด๋–ค ํ๋ฆ„์„ ๋”ฐ๋ฅผ ๊ฒƒ์ธ๊ฐ€ ์–ผ๋งˆ๋‚˜ ์†๋„๋ฅผ ์กฐ์ ˆํ•  ๊ฒƒ์ธ๊ฐ€
08:38
And then that all turns into just following a path:
182
518756
3065
๊ทธ๋ฆฌ๊ณ  ๋ชจ๋“  ๊ฒƒ์€ ํ•˜๋‚˜์˜ ๊ฒฐ๋ก ์œผ๋กœ ๊ท€๊ฒฐ๋ฉ๋‹ˆ๋‹ค.
08:41
turning the steering wheel left or right, pressing the brake or gas.
183
521821
3197
์™ผ์ชฝ์ด๋‚˜ ์˜ค๋ฅธ์ชฝ์ด๋ƒ ๋ธŒ๋ ˆ์ดํฌ๋ฅผ ๋ฐŸ๋Š๋ƒ ์•ˆ๋ฐŸ์œผ๋ƒ ์ž…๋‹ˆ๋‹ค.
08:45
It's really just two numbers at the end of the day.
184
525018
2464
๋งˆ์ง€๋ง‰์—๋Š” ์ˆซ์ž ๋‘๊ฐœ๊ฐ€ ๋์ž…๋‹ˆ๋‹ค.
08:47
So how hard can it really be?
185
527482
2241
์ •๋ง ํž˜๋“ ์ผ์ž…๋‹ˆ๋‹ค.
08:50
Back when we started in 2009,
186
530433
1952
2009๋…„์— ์ด๊ฒƒ์„ ์‹œ์ž‘ํ–ˆ์„๋•Œ
08:52
this is what our system looked like.
187
532385
1798
์ด๊ฒƒ์ด ์šฐ๋ฆฌ์˜ ์‹œ์Šคํ…œ์ด์—ˆ์Šต๋‹ˆ๋‹ค.
08:54
So you can see our car in the middle and the other boxes on the road,
188
534183
3391
๊ฐ€์šด๋ฐ ์ž๋™์ฐจ๊ฐ€ ์žˆ๊ณ  ๋‹ค๋ฅธ ๋ฐ•์Šค๋“ค์ด
08:57
driving down the highway.
189
537574
1271
๊ณ ์†๋„๋กœ์— ์žˆ์Šต๋‹ˆ๋‹ค.
08:58
The car needs to understand where it is and roughly where the other vehicles are.
190
538845
3818
๋ฌด์ธ์ž๋™์ฐจ๋Š” ์Šค์Šค๋กœ์˜ ์œ„์น˜์™€ ๋‹ค๋ฅธ ์ฐจ๋Ÿ‰๋“ค์˜ ์œ„์น˜๋„ ์•Œ์•„์•ผ ํ•ฉ๋‹ˆ๋‹ค.
09:02
It's really a geometric understanding of the world.
191
542663
2429
๊ธฐํ•˜ํ•™์  ์ดํ•ด๊ฐ€ ํ•„์ˆ˜์ ์ž…๋‹ˆ๋‹ค.
09:05
Once we started driving on neighborhood and city streets,
192
545092
2948
์šฐ๋ฆฌ๊ฐ€ ๊ธธ๊ฑฐ๋ฆฌ์—์„œ ํ…Œ์ŠคํŠธ๋ฅผ ์ง„ํ–‰ํ•˜๋ฉด์„œ
09:08
the problem becomes a whole new level of difficulty.
193
548040
2445
์ƒˆ๋กœ์šด ๋‹จ๊ณ„์˜ ์–ด๋ ค์›€์ด ๋‚˜ํƒ€๋‚ฌ์Šต๋‹ˆ๋‹ค.
09:10
You see pedestrians crossing in front of us, cars crossing in front of us,
194
550485
3494
๋ณดํ–‰์ž๋“ค์ด ์ฐจ ์ฃผ๋ณ€์— ๋‚˜ํƒ€๋‚˜๋ฉฐ
09:13
going every which way,
195
553979
1811
์ž์œ ๋กญ๊ฒŒ ๋‹ค๋‹ˆ๊ณ  ์‹ ํ˜ธ๋“ฑ, ํšก๋‹จ๋ณด๋„๊ฐ€ ๋‚˜ํƒ€๋‚ฌ์Šต๋‹ˆ๋‹ค.
09:15
the traffic lights, crosswalks.
196
555790
1527
09:17
It's an incredibly complicated problem by comparison.
197
557317
2797
์ด์ „๊ณผ๋Š” ๋น„๊ต๋„ ์•ˆ๋˜๋Š” ๋ณต์žกํ•œ ๋ฌธ์ œ์˜€์ฃ .
09:20
And then once you have that problem solved,
198
560114
2103
์ด ๋ฌธ์ œ๋ฅผ ํ•ด๊ฒฐํ•˜์ž
09:22
the vehicle has to be able to deal with construction.
199
562217
2512
์ด์ œ ๋„๋กœ์œ„์˜ ์ž‘์—…ํ˜„์žฅ์— ๋Œ€์ฒ˜ํ•ด์•ผ ํ–ˆ์ฃ .
09:24
So here are the cones on the left forcing it to drive to the right,
200
564729
3151
ํ™”๋ฉด ์† ์›๋ฟ”์€ ์˜ค๋ฅธ์ชฝ์œผ๋กœ ์ฐจ๋ฅผ ์œ ๋„ํ•ฉ๋‹ˆ๋‹ค.
09:27
but not just construction in isolation, of course.
201
567880
2402
ํ•˜์ง€๋งŒ ๋™์‹œ์— ๋‹ค๋ฅธ ๋ฌธ์ œ๋“ค๋„ ์กด์žฌํ•ฉ๋‹ˆ๋‹ค.
09:30
It has to deal with other people moving through that construction zone as well.
202
570282
3723
๋‹ค๋ฅธ ์‚ฌ๋žŒ๋“ค์ด ๊ทธ ํ˜„์žฅ์—์„œ ์›€์ง์ด๋Š” ๊ฒƒ๋„ ๊ณ ๋ คํ•ด์•ผํ•˜์ฃ .
09:34
And of course, if anyone's breaking the rules, the police are there
203
574005
3263
๊ทธ๋ฆฌ๊ณ  ๋ฌผ๋ก  ํ˜„์žฅ์— ๋ฌธ์ œ๊ฐ€ ์ƒ๊ธฐ๋ฉด ๊ฒฝ์ฐฐ์ด ์ถœ๋™ํ•  ์ˆ˜ ์žˆ๊ณ 
09:37
and the car has to understand that that flashing light on the top of the car
204
577268
3622
๋ฌด์ธ์ž๋™์ฐจ๋Š” ์œ„์ชฝ์— ๋ถˆ๋น›์ด ๋ฐ˜์ง์ด๋Š” ์ฐจ๋Š”
09:40
means that it's not just a car, it's actually a police officer.
205
580890
3105
๊ฒฝ์ฐฐ์ด๋ผ๋Š” ๊ฒƒ์„ ์ธ์ง€ํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
09:43
Similarly, the orange box on the side here,
206
583995
2032
๋น„์Šทํ•˜๊ฒŒ ๊ฐ“๊ธธ์ชฝ์— ์˜ค๋ Œ์ง€์ƒ‰ ๋ฐ•์Šค๋Š”
09:46
it's a school bus,
207
586027
1109
ํ•™๊ต ๋ฒ„์Šค์ž…๋‹ˆ๋‹ค.
09:47
and we have to treat that differently as well.
208
587136
2520
๊ทธ๊ฒƒ ๋˜ํ•œ ๋‹ค๋ฅด๊ฒŒ ๋Œ€์ฒ˜ํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
09:50
When we're out on the road, other people have expectations:
209
590576
2793
๋„๋กœ ๋ฐ–์—์„œ๋Š” ๋‹ค๋ฅธ ์ƒ์‹๋“ค์ด ์žˆ์Šต๋‹ˆ๋‹ค.
09:53
So, when a cyclist puts up their arm,
210
593369
1780
๋งŒ์•ฝ ์ž์ „๊ฑฐ ํƒ„ ์‚ฌ๋žŒ์ด ์†์„ ๋ป—์œผ๋ฉด
09:55
it means they're expecting the car to yield to them and make room for them
211
595149
3518
๊ทธ๊ฒƒ์€ ๊ทธ ์ฐจ์„ ์œผ๋กœ ์ด๋™ํ• ํƒœ๋‹ˆ
09:58
to make a lane change.
212
598667
2053
์–‘๋ณดํ•ด ๋‹ฌ๋ผ๋Š” ์˜๋ฏธ์ž…๋‹ˆ๋‹ค.
10:01
And when a police officer stood in the road,
213
601030
2173
๊ฒฝ์ฐฐ์ด ๊ธธ์— ์„œ์žˆ์œผ๋ฉด
10:03
our vehicle should understand that this means stop,
214
603203
2740
๋ฌด์ธ์ž๋™์ฐจ๋Š” ๊ทธ ์‹ ํ˜ธ๊ฐ€ ๋ฉˆ์ถ”๋ผ๋Š” ๋œป์ž„์„ ์•Œ์•„์ฑ„์•ผ ํ•ฉ๋‹ˆ๋‹ค.
10:05
and when they signal to go, we should continue.
215
605943
3506
๊ฐ€๋„ ์ข‹๋‹ค๋Š” ์‹ ํ˜ธ๋„ ๋ฌผ๋ก  ์•Œ์•„์•ผ ๊ฒ ์ฃ .
10:09
Now, the way we accomplish this is by sharing data between the vehicles.
216
609449
3761
์šฐ๋ฆฌ๋Š” ์ฐจ๋Ÿ‰๋“ค๊ฐ„์˜ ์ •๋ณด๋ฅผ ๊ณต์œ ํ•จ์œผ๋กœ์จ ํ•ด๊ฒฐ์ฑ…์„ ์ฐพ์•˜์Šต๋‹ˆ๋‹ค.
10:13
The first, most crude model of this
217
613210
1696
์ฒ˜์Œ ์‹œ๋„ํ•œ ๋Œ€๋žต์  ๋ชจ๋ธ์€
10:14
is when one vehicle sees a construction zone,
218
614906
2113
ํ•œ ์ฐจ๋Ÿ‰์ด ์ž‘์—…ํ˜„์žฅ์„ ๋ณด๋ฉด
10:17
having another know about it so it can be in the correct lane
219
617019
3062
๋‹ค๋ฅธ ์ฐจ๋Ÿ‰์ด ๊ทธ ์ •๋ณด๋ฅผ ๋ฐ›์•„
10:20
to avoid some of the difficulty.
220
620081
1570
์ฐจ์„ ์„ ๋ณ€๊ฒฝํ•ฉ๋‹ˆ๋‹ค.
10:21
But we actually have a much deeper understanding of this.
221
621651
2664
์šฐ๋ฆฌ๋Š” ๋ฌด์ธ์ž๋™์ฐจ์—๊ฒŒ ์ƒํ™ฉ์— ๋Œ€ํ•ด ์ž˜ ์ดํ•ด์‹œ์ผฐ์Šต๋‹ˆ๋‹ค.
10:24
We could take all of the data that the cars have seen over time,
222
624315
3009
์šฐ๋ฆฌ๋Š” ์˜ค๋žœ ์‹œ๊ฐ„๋™์•ˆ ์ถ•์ ํ•œ
10:27
the hundreds of thousands of pedestrians, cyclists,
223
627324
2376
์ˆ˜๋ฐฑ๋งŒ์˜ ์ž๋™์ฐจ, ๋ณดํ–‰์ž, ์ž์ „๊ฑฐ๋“ค์˜
10:29
and vehicles that have been out there
224
629700
1787
์ •๋ณด๋ฅผ ๋ฐ›์•„์„œ
10:31
and understand what they look like
225
631487
1695
์ข…ํ•ฉ์ ์ธ ์ƒํ™ฉ์„ ์ดํ•ดํ•˜๊ณ 
10:33
and use that to infer what other vehicles should look like
226
633182
2831
๋‹ค๋ฅธ ์ž๋™์ฐจ๋“ค๊ณผ ๋ณดํ–‰์ž๋“ค์˜
10:36
and other pedestrians should look like.
227
636013
1926
์ƒํ™ฉ์„ ์ถ”๋ก ํ–ˆ์Šต๋‹ˆ๋‹ค.
10:37
And then, even more importantly, we could take from that a model
228
637939
3021
๋” ์ค‘์š”ํ•œ์ ์€ ์šฐ๋ฆฌ์˜ ์˜ˆ์ธก๋ชจ๋ธ์„ ํ† ๋Œ€๋กœ
10:40
of how we expect them to move through the world.
229
640960
2330
์„ธ์ƒ์— ์ ์šฉ์‹œํ‚ฌ ์ˆ˜ ์žˆ๋‹ค๋Š”์  ์ž…๋‹ˆ๋‹ค.
10:43
So here the yellow box is a pedestrian crossing in front of us.
230
643290
2963
์—ฌ๊ธฐ ๋…ธ๋ž€์ƒ‰ ๋ฐ•์Šค๋Š” ์šฐ๋ฆฌ ์•ž์„ ์ง€๋‚˜๋Š” ๋ณดํ–‰์ž๋“ค์ž…๋‹ˆ๋‹ค.
10:46
Here the blue box is a cyclist and we anticipate
231
646253
2250
ํŒŒ๋ž€์ƒ‰ ๋ฐ•์Šค๋Š” ์ž์ „๊ฑฐ๋“ค์ด๊ณ 
10:48
that they're going to nudge out and around the car to the right.
232
648503
3312
์šฐ๋ฆฌ๋Š” ๊ทธ ์ž์ „๊ฑฐ๊ฐ€ ์šฐํšŒ์ „ ํ•  ๊ฒƒ์ด๋ผ๋Š” ๊ฒƒ์„ ์˜ˆ์ƒํ•ฉ๋‹ˆ๋‹ค.
10:52
Here there's a cyclist coming down the road
233
652115
2092
์ž์ „๊ฑฐ๊ฐ€ ๋งž์€ํŽธ์—์„œ ์˜ค๊ณ ์žˆ๊ณ 
10:54
and we know they're going to continue to drive down the shape of the road.
234
654207
3486
๋„๋กœ๋ฅผ ๋”ฐ๋ผ ์ง์ง„ํ•  ๊ฒƒ์ด๋ผ๋Š” ๊ฒƒ์„ ์•Œ๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
10:57
Here somebody makes a right turn,
235
657693
1867
๋ˆ„๊ตฐ๊ฐ€ ์šฐํšŒ์ „ํ•˜๊ณ  ์žˆ๊ณ 
10:59
and in a moment here, somebody's going to make a U-turn in front of us,
236
659560
3360
๋’ค์ด์–ด ๋ˆ„๊ตฐ๊ฐ€ ์šฐ๋ฆฌ ์•ž์—์„œ ์œ ํ„ดํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
11:02
and we can anticipate that behavior and respond safely.
237
662920
2614
์šฐ๋ฆฌ๋Š” ๋ชจ๋“  ํ–‰๋™์„ ์˜ˆ์ƒํ•˜๊ณ  ์•ˆ์ „ํ•˜๊ฒŒ ๋ฐ˜์‘ํ•ฉ๋‹ˆ๋‹ค.
11:05
Now, that's all well and good for things that we've seen,
238
665534
2728
์ง€๊ธˆ๊นŒ์ง€ ์ž˜ ๋Œ€์ฒ˜๋œ ์ƒํ™ฉ๋“ค์„ ๋ดค์ง€๋งŒ
11:08
but of course, you encounter lots of things that you haven't
239
668262
2865
๋ฌผ๋ก  ์ด์ „์— ๋ณผ ์ˆ˜ ์—†์—ˆ๋˜ ๋Œ๋ฐœ์ƒํ™ฉ๋„
11:11
seen in the world before.
240
671127
1231
๋งŽ์ด ๊ฒช์—ˆ์Šต๋‹ˆ๋‹ค.
11:12
And so just a couple of months ago,
241
672358
1741
๋ฐ”๋กœ ๋ช‡๋‹ฌ์ „์—
11:14
our vehicles were driving through Mountain View,
242
674099
2235
์ฐจ๋Ÿ‰์€ ๋งˆ์šดํ‹ด๋ทฐ(๋„์‹œ)์—์„œ ์šดํ–‰ํ–ˆ์Šต๋‹ˆ๋‹ค.
11:16
and this is what we encountered.
243
676334
1644
๊ทธ๋ฆฌ๊ณ  ์ด ์ƒํ™ฉ์„ ๋งˆ์ฃผ์ณค์Šต๋‹ˆ๋‹ค.
11:17
This is a woman in an electric wheelchair
244
677978
2082
์ด ์—ฌ์„ฑ์€ ์ „์ž ํœ ์ฒด์–ด๋ฅผ ํƒ€๊ณ  ์žˆ์—ˆ๋Š”๋ฐ
11:20
chasing a duck in circles on the road. (Laughter)
245
680060
2617
๋„๋กœ์—์„œ ์˜ค๋ฆฌ๋ฅผ ์ซ’์•„ ๋น™๋น™๋Œ๊ณ  ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค.
11:22
Now it turns out, there is nowhere in the DMV handbook
246
682677
3111
๋„๋กœ๊ตํ†ต๋ถ€ ์ง€์นจ์„œ์—๋Š” ์ด ์ƒํ™ฉ์— ๋Œ€ํ•œ
11:25
that tells you how to deal with that,
247
685788
2245
๋Œ€์ฒ˜๋ฒ•์ด ์—†์—ˆ์ง€๋งŒ
11:28
but our vehicles were able to encounter that,
248
688033
2143
์šฐ๋ฆฌ ์ฐจ๋Ÿ‰์€ ์†๋„๋ฅผ ์ค„์ด๊ณ 
11:30
slow down, and drive safely.
249
690176
2255
์•ˆ์ „ํ•˜๊ฒŒ ์ฃผํ–‰ํ–ˆ์Šต๋‹ˆ๋‹ค.
11:32
Now, we don't have to deal with just ducks.
250
692431
2041
์˜ค๋ฆฌ ๋ฟ๋งŒ์ด ์•„๋‹ˆ๋ผ
11:34
Watch this bird fly across in front of us. The car reacts to that.
251
694472
3708
์šฐ๋ฆฌ ์•ž์œผ๋กœ ์˜ค๋Š” ์ƒˆ์—๋„ ๋ฌด์ธ์ž๋™์ฐจ๋Š” ๋ฐ˜์‘ํ•ฉ๋‹ˆ๋‹ค.
11:38
Here we're dealing with a cyclist
252
698180
1615
์ž์ „๊ฑฐ์— ๋Œ€์ฒ˜ํ•˜๋Š” ์‚ฌ๋ก€์ž…๋‹ˆ๋‹ค.
11:39
that you would never expect to see anywhere other than Mountain View.
253
699795
3290
๋งˆ์šดํ‹ด๋ทฐ(๋„์‹œ)๊ฐ€ ์•„๋‹ˆ๋ผ๋ฉด ์˜ˆ์ƒํ•˜๊ธฐ ์–ด๋ ต๊ฒ ์ฃ .
11:43
And of course, we have to deal with drivers,
254
703085
2068
๋ฌผ๋ก  ์กฐํ™”๋กœ์šด ์šดํ–‰์€ ํ•„์ˆ˜์ž…๋‹ˆ๋‹ค.
11:45
even the very small ones.
255
705153
3715
๋งค์šฐ ์ž‘์€ ์ž๋™์ฐจ๋ผ๋„ ๋ง์ด์ฃ .
11:48
Watch to the right as someone jumps out of this truck at us.
256
708868
4131
์˜ค๋ฅธ์ชฝ ํŠธ๋Ÿญ์—์„œ ์šด์ „์ž๊ฐ€ ์ž ๊น ๋‚ด๋ฆฌ๋Š”๊ฑธ ๋ณด์„ธ์š”.
11:54
And now, watch the left as the car with the green box decides
257
714460
2929
์™ผ์ชฝ ์ฐจ์„ ์—์„œ ๊ฐ‘์ž๊ธฐ ์šฐํšŒ์ „ ํ•˜๋Š” ์ฐจ๋Ÿ‰์„ ๋ณด์„ธ์š”.
11:57
he needs to make a right turn at the last possible moment.
258
717389
3325
๋งˆ์ง€๋ง‰ ์ˆœ๊ฐ„์— ๊ธ‰ํ•œ ๊ฒฐ์ •์„ ํ–ˆ์ฃ .
12:00
Here, as we make a lane change, the car to our left decides
259
720714
2851
์ฐจ์„ ๋ณ€๊ฒฝ์ด ๋™์‹œ์— ์ผ์–ด๋‚˜์ž
12:03
it wants to as well.
260
723565
3553
์–‘๋ณดํ•˜๋Š” ๋ชจ์Šต์„ ๋ณด์ž…๋‹ˆ๋‹ค.
12:07
And here, we watch a car blow through a red light
261
727118
2693
์‹ ํ˜ธ์œ„๋ฐ˜ํ•œ ์ฐจ๋Ÿ‰์—๋„
12:09
and yield to it.
262
729811
2090
์ž˜ ๋Œ€์ฒ˜ํ•ฉ๋‹ˆ๋‹ค.
12:11
And similarly, here, a cyclist blowing through that light as well.
263
731901
3854
๋น„์Šทํ•˜๊ฒŒ ์ž์ „๊ฑฐ์˜ ์‹ ํ˜ธ์œ„๋ฐ˜์—๋„
12:15
And of course, the vehicle responds safely.
264
735755
2746
๋ฌด์ธ์ž๋™์ฐจ๋Š” ์ž˜ ๋Œ€์ฒ˜ํ•ฉ๋‹ˆ๋‹ค.
12:18
And of course, we have people who do I don't know what
265
738501
2601
๋ฌผ๋ก  ์ œ๊ฐ€ ์•Œ์ง€ ๋ชปํ•˜๋Š” ์‚ฌ๋žŒ๋“ค์ด ์žˆ์Šต๋‹ˆ๋‹ค.
12:21
sometimes on the road, like this guy pulling out between two self-driving cars.
266
741102
3823
์ด ์‚ฌ๋žŒ์€ ๋ฌด์ธ์ž๋™์ฐจ ์‚ฌ์ด์— ๋ณธ์ธ ์ฐจ๋ฅผ ์ง‘์–ด ๋„ฃ์—ˆ์Šต๋‹ˆ๋‹ค.
12:24
You have to ask, "What are you thinking?"
267
744925
2045
๋ฌผ์–ด๋ณด๊ณ  ์‹ถ๊ตฐ์š” "๋ฌด์Šจ ์ƒ๊ฐ ์ธ๊ฐ€์š”?"
12:26
(Laughter)
268
746970
1212
(์›ƒ์Œ)
12:28
Now, I just fire-hosed you with a lot of stuff there,
269
748182
2521
์ฃผ๋ณ€ ๋„์›€์œผ๋กœ ์žฌ๋นจ๋ฆฌ ์ˆ˜์Šตํ–ˆ๊ณ 
12:30
so I'm going to break one of these down pretty quickly.
270
750703
2650
๋Œ๋ฐœ์ƒํ™ฉ ์ค‘ ํ•˜๋‚˜๋ฅผ ๊ทน๋ณตํ–ˆ์Šต๋‹ˆ๋‹ค.
12:33
So what we're looking at is the scene with the cyclist again,
271
753353
2940
์ด๋ฒˆ ์žฅ๋ฉด์€ ๋˜ ๋‹ค๋ฅธ ์ž์ „๊ฑฐ์ž…๋‹ˆ๋‹ค.
12:36
and you might notice in the bottom, we can't actually see the cyclist yet,
272
756293
3491
์—ฌ๋Ÿฌ๋ถ„์€ ๋ณด์ผ์ˆ˜๋„ ์žˆ์ง€๋งŒ ์šด์ „์ž ์‹œ๊ฐ์—์„œ ์ž์ „๊ฑฐ๊ฐ€ ๋ณด์ด์ง€ ์•Š์Šต๋‹ˆ๋‹ค.
12:39
but the car can: it's that little blue box up there,
273
759784
2504
ํ•˜์ง€๋งŒ ๋ฌด์ธ์ž๋™์ฐจ๋Š” ๊ฐ€๋Šฅํ•ฉ๋‹ˆ๋‹ค.
12:42
and that comes from the laser data.
274
762288
2081
๋ ˆ์ด์ €๋กœ๋ถ€ํ„ฐ ์ •๋ณด๋ฅผ ์–ป๊ธฐ ๋•Œ๋ฌธ์ž…๋‹ˆ๋‹ค.
12:44
And that's not actually really easy to understand,
275
764369
2418
์ด๊ฒƒ์€ ์‰ฝ๊ฒŒ ์ดํ•ดํ•˜๊ธฐ๋Š” ์–ด๋ ต์ง€๋งŒ
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
์ด ๋ ˆ์ด์ € ๋ฐ์ดํ„ฐ๋ฅผ
12:50
and if you're really good at looking at laser data, you can see
277
770371
3029
์ž์„ธํžˆ ๋ณด๋ฉด ๊ณก์„ ์ƒ์˜ ๋ช‡๊ฐœ์˜ ์ ๋“ค์ด ๋ณด์ž…๋‹ˆ๋‹ค.
12:53
a few dots on the curve there,
278
773400
1487
12:54
right there, and that blue box is that cyclist.
279
774887
2372
๊ทธ ํŒŒ๋ž€์ƒ‰ ๋ฐ•์Šค๊ฐ€ ์ž์ „๊ฑฐ์ž…๋‹ˆ๋‹ค.
12:57
Now as our light is red,
280
777259
1149
์‹ ํ˜ธ๋“ฑ์€ ๋นจ๊ฐ„๋ถˆ์ด์ง€๋งŒ
12:58
the cyclist's light has turned yellow already,
281
778408
2192
์ž์ „๊ฑฐ ์‹ ํ˜ธ๋“ฑ์€ ๋…ธ๋ž€๋ถˆ์ด์—ˆ์Šต๋‹ˆ๋‹ค.
13:00
and if you squint, you can see that in the imagery.
282
780600
2438
์—ฌ๋Ÿฌ๋ถ„์ด ์‚ฌ์‹œ๋ผ๋ฉด ๋ญ”๊ฐ€ ๋ดค์„ํ…Œ์ง€๋งŒ
13:03
But the cyclist, we see, is going to proceed through the intersection.
283
783038
3286
์ž์ „๊ฑฐ์— ํƒ„ ์‚ฌ๋žŒ์€ ๊ต์ฐจ๋กœ์— ์ง„์ž…ํ–ˆ์Šต๋‹ˆ๋‹ค.
13:06
Our light has now turned green, his is solidly red,
284
786324
2394
์ž๋™์ฐจ๋“ฑ์€ ๋…น์ƒ‰๋“ฑ ์ž์ „๊ฑฐ๋“ฑ์€ ๋นจ๊ฐ„๋“ฑ์ด ๋์Šต๋‹ˆ๋‹ค.
13:08
and we now anticipate that this bike is going to come all the way across.
285
788718
4292
๊ทธ ์ž์ „๊ฑฐ๋Š” ๊ฑด๋„ˆ ์˜ฌ๊ฒŒ ๋ป”ํ–ˆ์ฃ .
13:13
Unfortunately the other drivers next to us were not paying as much attention.
286
793010
3742
๋ถˆํ–‰ํ•˜๊ฒŒ๋„ ์šฐ๋ฆฌ ์˜† ์šด์ „์ž๋Š” ๊ทธ ์‚ฌ์‹ค์„ ๋ชฐ๋ž์Šต๋‹ˆ๋‹ค.
13:16
They started to pull forward, and fortunately for everyone,
287
796752
3157
์ž๋™์ฐจ๋Š” ์ถœ๋ฐœํ–ˆ๊ณ  ์šด์ข‹๊ฒŒ
13:19
this cyclists reacts, avoids,
288
799909
3011
์ž์ „๊ฑฐ๋Š” ๋ฐ˜์‘ํ–ˆ๊ณ  ํ”ผํ–ˆ์Šต๋‹ˆ๋‹ค.
13:22
and makes it through the intersection.
289
802920
2191
์œ„ํ—˜์ƒํ™ฉ์ด ๋๋‚ฌ์Šต๋‹ˆ๋‹ค.
13:25
And off we go.
290
805111
1568
๊ทธ๋ฆฌ๊ณ  ์šฐ๋ฆฌ๋Š” ์ถœ๋ฐœํ–ˆ์ฃ .
13:26
Now, as you can see, we've made some pretty exciting progress,
291
806679
2948
์ง€๊ธˆ๊นŒ์ง€ ๋ณด์‹ ๋Œ€๋กœ ์šฐ๋ฆฌ๋Š” ํฅ๋ฏธ๋กœ์šด ์ง„ํ–‰์ƒํ™ฉ์„ ๋ณด์˜€์Šต๋‹ˆ๋‹ค.
13:29
and at this point we're pretty convinced
292
809627
1902
์–ด๋Š ์‹œ์ ์—์„œ ์šฐ๋ฆฌ๋Š” ์ด ๊ธฐ์ˆ ์ด
13:31
this technology is going to come to market.
293
811529
2010
์‹œ์žฅ์— ๋‚˜์˜ฌ ์ˆ˜ ์žˆ๋‹ค๊ณ  ๋ฏฟ๊ฒŒ ๋์Šต๋‹ˆ๋‹ค.
13:33
We do three million miles of testing in our simulators every single day,
294
813539
4783
์šฐ๋ฆฌ๋Š” 3๋ฐฑ๋งŒ ๋งˆ์ผ์˜ ํ…Œ์ŠคํŠธ ์ฃผํ–‰์„ ๋งค์ผ ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
13:38
so you can imagine the experience that our vehicles have.
295
818322
2689
์–ผ๋งˆ๋‚˜ ๋งŽ์€ ๊ฒฝํ—˜์ด ์žˆ๋Š”์ง€ ์ƒ์ƒํ•  ์ˆ˜ ์žˆ๊ฒ ์ฃ .
์šฐ๋ฆฌ๋Š” ์ด ๊ธฐ์ˆ ์ด ์‹ค์ œ๋กœ ์ ์šฉ๋˜๊ธฐ๋ฅผ ๊ณ ๋Œ€ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
13:41
We are looking forward to having this technology on the road,
296
821011
2864
13:43
and we think the right path is to go through the self-driving
297
823875
2890
์šฐ๋ฆฌ๋Š” ์šด์ „๋ณด์กฐ์‹œ์Šคํ…œ๋ณด๋‹ค ๋ฌด์ธ์ž๋™์ฐจ๊ฐ€
13:46
rather than driver assistance approach
298
826765
1844
์ ์ ˆํ•˜๋‹ค๊ณ  ์ƒ๊ฐํ•ฉ๋‹ˆ๋‹ค.
13:48
because the urgency is so large.
299
828609
2621
์™œ๋ƒํ•˜๋ฉด ๊ทธ๋งŒํผ ์œ„๊ธ‰ํ•˜๊ธฐ ๋•Œ๋ฌธ์ž…๋‹ˆ๋‹ค.
13:51
In the time I have given this talk today,
300
831230
2393
์ œ๊ฐ€ ์—ฌ๊ธฐ์„œ ๊ฐ•์—ฐํ•˜๊ณ  ์žˆ๋Š” ๋™์•ˆ์—
13:53
34 people have died on America's roads.
301
833623
3135
34๋ช…์˜ ์‚ฌ๋žŒ์ด ๋ฏธ๊ตญ ๋„๋กœ์—์„œ ์‚ฌ๋งํ•ฉ๋‹ˆ๋‹ค.
13:56
How soon can we bring it out?
302
836758
2368
์–ธ์ œ ์ด ๊ธฐ์ˆ ์„ ๊ณต๊ฐœํ•  ์ˆ˜ ์žˆ์„๊นŒ์š”?
13:59
Well, it's hard to say because it's a really complicated problem,
303
839126
3832
์‚ฌ์‹ค ์ด๊ฑด ๊ต‰์žฅํžˆ ๋ณต์žกํ•œ ๋ฌธ์ œ๋ผ์„œ ์•Œ ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค.
14:02
but these are my two boys.
304
842958
2214
์ €๋Š” ๋‘ ์•„๋“ค์ด ์žˆ์Šต๋‹ˆ๋‹ค.
14:05
My oldest son is 11, and that means in four and a half years,
305
845172
3623
ํฐ ์•„๋“ค์€ 11์‚ด์ด๊ณ  ๊ทธ ์˜๋ฏธ๋Š”
14:08
he's going to be able to get his driver's license.
306
848795
2577
4๋…„ 6๊ฐœ์›” ํ›„๋ฉด ์šด์ „๋ฉดํ—ˆ๋ฅผ ๋”ธ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
14:11
My team and I are committed to making sure that doesn't happen.
307
851372
3204
์ œ ํŒ€๊ณผ ์ €๋Š” ๊ทธ ์ผ์ด ๋ฒŒ์–ด์ง€์ง€ ์•Š๊ธฐ ์œ„ํ•ด์„œ ๋…ธ๋ ฅํ•ฉ๋‹ˆ๋‹ค.
14:14
Thank you.
308
854576
1904
๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.
14:16
(Laughter) (Applause)
309
856480
3667
(์›ƒ์Œ) (๋ฐ•์ˆ˜)
14:21
Chris Anderson: Chris, I've got a question for you.
310
861110
2568
ํฌ๋ฆฌ์Šค ์•ค๋”์Šจ: ํฌ๋ฆฌ์Šค, ์งˆ๋ฌธ์ด ์žˆ์Šต๋‹ˆ๋‹ค.
14:23
Chris Urmson: Sure.
311
863678
2809
ํฌ๋ฆฌ์Šค ์—„์Šจ: ๋„ค ๋ง์”€ํ•˜์„ธ์š”.
14:26
CA: So certainly, the mind of your cars is pretty mind-boggling.
312
866487
3924
ํฌ๋ฆฌ์Šค ์•ค๋”์Šจ: ๋‹น์‹  ์ฐจ์— ๋Œ€ํ•œ ์ƒ๊ฐ์€ ๋ฌด์ฒ™ ๋†€๋ผ์šด๋ฐ์š”.
14:30
On this debate between driver-assisted and fully driverless --
313
870411
4459
์šด์ „๋ณด์กฐ ์‹œ์Šคํ…œ๊ณผ ๋ฌด์ธ์ž๋™์ฐจ์— ๋Œ€ํ•œ ํ† ๋ก ๋“ค์ด ๋งŽ์Šต๋‹ˆ๋‹ค.
14:34
I mean, there's a real debate going on out there right now.
314
874870
3041
์ง€๊ธˆ ์ง„์ง€ํ•œ ํ† ๋ก ๋“ค์ด ๋งŽ์ด ์ง„ํ–‰์ค‘์ธ๋ฐ์š”.
14:37
So some of the companies, for example, Tesla,
315
877911
2833
ํ…Œ์Šฌ๋ผ๊ฐ™์€ ํšŒ์‚ฌ๋Š”
14:40
are going the driver-assisted route.
316
880744
2159
์šด์ „๋ณด์กฐ ์‹œ์Šคํ…œ์„ ๋ฐœ์ „์‹œํ‚ค๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
14:42
What you're saying is that that's kind of going to be a dead end
317
882903
5248
๋‹น์‹ ์ƒ๊ฐ์€ ์ด๋Ÿฐ ๋ฐฉ์‹์€ ๋ง‰๋‹ค๋ฅธ ๊ธธ์— ๋‹ค๋‹ค๋ฅผ ๊ฒƒ์ด๋ฉฐ
14:48
because you can't just keep improving that route and get to fully driverless
318
888151
5456
์™œ๋ƒํ•˜๋ฉด ๊ทธ์ € ๋ฐœ์ „์‹œํ‚ค๋Š” ๊ฒƒ์œผ๋กœ๋Š” ๋ฌด์ธ์ž๋™์ฐจ๋ฅผ ๋งŒ๋“ค ์ˆ˜ ์—†์œผ๋ฉฐ
14:53
at some point, and then a driver is going to say, "This feels safe,"
319
893607
3530
์šด์ „์ž๊ฐ€ ์•ˆ์ „ํ•˜๋‹ค๊ณ  ์ƒ๊ฐ๋ ๋•Œ
14:57
and climb into the back, and something ugly will happen.
320
897137
2647
์œ„ํ—˜์ด ์ƒ๊ธด๋‹ค๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
14:59
CU: Right. No, that's exactly right, and it's not to say
321
899784
2676
ํฌ๋ฆฌ์Šค ์—„์Šจ: ๋งž์Šต๋‹ˆ๋‹ค.
15:02
that the driver assistance systems aren't going to be incredibly valuable.
322
902460
3537
์šด์ „ ๋ณด์กฐ ์‹œ์Šคํ…œ์ด ๊ฐ€์น˜๊ฐ€ ์—†๋Š” ์ผ์€ ์•„๋‹™๋‹ˆ๋‹ค.
15:05
They can save a lot of lives in the interim,
323
905997
2058
๋งŽ์€ ์ƒ๋ช…์„ ๊ตฌํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
15:08
but to see the transformative opportunity to help someone like Steve get around,
324
908055
3833
ํ•˜์ง€๋งŒ ์Šคํ‹ฐ๋ธŒ๊ฐ™์€ ์‚ฌ๋žŒ์„
15:11
to really get to the end case in safety,
325
911888
1969
๊ตฌํ•  ๋ณ€ํ™”์˜ ํž˜์ด๋‚˜
15:13
to have the opportunity to change our cities
326
913857
2479
์šฐ๋ฆฌ์˜ ๋„์‹œ๋ฅผ ๋ณ€ํ™”์‹œํ‚ค๊ณ 
15:16
and move parking out and get rid of these urban craters we call parking lots,
327
916336
4204
์šฐ๋ฆฌ๊ฐ€ ์ฃผ์ฐจ์žฅ์ด๋ผ๊ณ  ๋ถ€๋ฅด๋Š” ๋„์‹œ ๋ถ„ํ™”๊ตฌ๋ฅผ ์‚ฌ๋ผ์ง€๊ฒŒํ•  ๋ฐฉ๋ฒ•์€
15:20
it's the only way to go.
328
920540
1240
๋ฌด์ธ์ž๋™์ฐจ๊ฐ€ ์œ ์ผํ•ฉ๋‹ˆ๋‹ค.
15:21
CA: We will be tracking your progress with huge interest.
329
921780
2718
ํฌ๋ฆฌ์Šค ์•ค๋”์Šจ: ๋ชจ๋‘๋“ค ๋ฌด์ธ์ž๋™์ฐจ์˜
15:24
Thanks so much, Chris. CU: Thank you. (Applause)
330
924498
4232
๋ฏธ๋ž˜๋ฅผ ํฐ ๊ด€์‹ฌ์„ ๊ฐ€์ง€๊ณ  ์ง€์ผœ๋ณผ ๊ฒƒ์ž…๋‹ˆ๋‹ค. ๊ณ ๋ง™์Šต๋‹ˆ๋‹ค. ํฌ๋ฆฌ์Šค์”จ
์ด ์›น์‚ฌ์ดํŠธ ์ •๋ณด

์ด ์‚ฌ์ดํŠธ๋Š” ์˜์–ด ํ•™์Šต์— ์œ ์šฉํ•œ YouTube ๋™์˜์ƒ์„ ์†Œ๊ฐœํ•ฉ๋‹ˆ๋‹ค. ์ „ ์„ธ๊ณ„ ์ตœ๊ณ ์˜ ์„ ์ƒ๋‹˜๋“ค์ด ๊ฐ€๋ฅด์น˜๋Š” ์˜์–ด ์ˆ˜์—…์„ ๋ณด๊ฒŒ ๋  ๊ฒƒ์ž…๋‹ˆ๋‹ค. ๊ฐ ๋™์˜์ƒ ํŽ˜์ด์ง€์— ํ‘œ์‹œ๋˜๋Š” ์˜์–ด ์ž๋ง‰์„ ๋”๋ธ” ํด๋ฆญํ•˜๋ฉด ๊ทธ๊ณณ์—์„œ ๋™์˜์ƒ์ด ์žฌ์ƒ๋ฉ๋‹ˆ๋‹ค. ๋น„๋””์˜ค ์žฌ์ƒ์— ๋งž์ถฐ ์ž๋ง‰์ด ์Šคํฌ๋กค๋ฉ๋‹ˆ๋‹ค. ์˜๊ฒฌ์ด๋‚˜ ์š”์ฒญ์ด ์žˆ๋Š” ๊ฒฝ์šฐ ์ด ๋ฌธ์˜ ์–‘์‹์„ ์‚ฌ์šฉํ•˜์—ฌ ๋ฌธ์˜ํ•˜์‹ญ์‹œ์˜ค.

https://forms.gle/WvT1wiN1qDtmnspy7