Meet Spot, the robot dog that can run, hop and open doors | Marc Raibert

3,212,884 views ใƒป 2017-08-14

TED


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

๋ฒˆ์—ญ: ์€์ง€ ๊ณ  ๊ฒ€ํ† : Jihyeon J. Kim
00:19
(Laughter)
0
19085
1800
(์›ƒ์Œ)
00:24
(Laughter)
1
24323
1150
(์›ƒ์Œ)
00:36
That's SpotMini.
2
36710
1150
์ด๊ฑด ์ŠคํŒŸ๋ฏธ๋‹ˆ์ž…๋‹ˆ๋‹ค.
00:37
He'll be back in a little while.
3
37884
1618
์กฐ๊ธˆ ํ›„์— ๋‹ค์‹œ ๋ณด์—ฌ๋“œ๋ฆฌ๊ฒ ์Šต๋‹ˆ๋‹ค.
00:39
I --
4
39526
1164
์ €๋Š”
00:40
(Applause)
5
40714
3838
(๋ฐ•์ˆ˜)
00:45
I love building robots.
6
45472
1737
์ €๋Š” ๋กœ๋ด‡ ๋งŒ๋“œ๋Š” ๊ฒƒ์„ ์ข‹์•„ํ•ฉ๋‹ˆ๋‹ค.
00:48
And my long-term goal is to build robots
7
48419
2452
์ œ ์žฅ๊ธฐ์  ๋ชฉํ‘œ๋Š” ์‚ฌ๋žŒ๊ณผ ๋™๋ฌผ์ด ํ•˜๋Š” ์ผ์„ ํ•  ์ˆ˜ ์žˆ๋Š”
00:50
that can do what people and animals do.
8
50895
2082
๋กœ๋ด‡์„ ๋งŒ๋“œ๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
00:53
And there's three things in particular
9
53964
3099
์šฐ๋ฆฌ๊ฐ€ ๊ด€์‹ฌ์„ ๊ฐ–๋Š”
00:57
that we're interested in.
10
57541
1703
์„ธ ๊ฐ€์ง€ ์‚ฌํ•ญ์ด ์žˆ๋Š”๋ฐ์š”.
01:00
One is balance and dynamic mobility,
11
60008
3302
์ฒซ ๋ฒˆ์งธ๋Š” ๊ท ํ˜•๊ณผ ์—ญ๋™์ ์ธ ์›€์ง์ž„์ด๊ณ 
01:03
the second one is mobile manipulation,
12
63334
2630
๋‘ ๋ฒˆ์งธ๋Š” ์ด๋™ ์กฐ์ž‘ ์ž‘์—…
01:05
and the third one is mobile perception.
13
65988
2365
๊ทธ๋ฆฌ๊ณ  ์„ธ ๋ฒˆ์งธ๋Š” ์ด๋™ ์ธ์‹ ์ž‘์—…์ž…๋‹ˆ๋‹ค.
01:08
So, dynamic mobility and balance --
14
68944
2911
์—ญ๋™์ ์ธ ์›€์ง์ž„๊ณผ ๊ท ํ˜•์€
01:11
I'm going to do a demo for you.
15
71879
1637
์‹œ๋ฒ”์œผ๋กœ ๋ณด์—ฌ๋“œ๋ฆฌ๊ฒ ์Šต๋‹ˆ๋‹ค.
01:15
I'm standing here, balancing.
16
75099
1547
์ €๋Š” ์—ฌ๊ธฐ ์„œ์žˆ์Šต๋‹ˆ๋‹ค, ๊ท ํ˜•์„ ์žก๊ณ ์š”.
01:18
I can see you're not very impressed. OK, how about now?
17
78121
2714
๋ณ„๋กœ ์ธ์ƒ์ ์ด์ง€ ์•Š์œผ์‹  ๊ฒƒ ๊ฐ™๋„ค์š”. ์ด์ œ ์–ด๋–ค๊ฐ€์š”?
01:20
(Laughter)
18
80859
1160
(์›ƒ์Œ)
01:22
How about now?
19
82043
1193
์ง€๊ธˆ์€์š”?
01:23
(Applause)
20
83260
2043
(๋ฐ•์ˆ˜)
01:26
Those simple capabilities mean that people can go almost anywhere on earth,
21
86049
4373
์ด๋Ÿฐ ๋Šฅ๋ ฅ๋“ค ๋•๋ถ„์— ์‚ฌ๋žŒ๋“ค์€ ์ง€๊ตฌ์ƒ์˜ ๊ฑฐ์˜ ๋ชจ๋“  ๊ณณ
01:30
on any kind of terrain.
22
90446
1652
์–ด๋–ค ์ง€ํ˜•์—๋“  ๊ฐˆ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
01:32
We want to capture that for robots.
23
92122
2655
์šฐ๋ฆฌ๋Š” ๋กœ๋ด‡์ด ์ด๋Ÿฐ ๋Šฅ๋ ฅ์„ ๊ฐ–๊ธฐ ์›ํ•ฉ๋‹ˆ๋‹ค.
01:35
What about manipulation?
24
95772
1392
์กฐ์ž‘ ๋Šฅ๋ ฅ์€ ์–ด๋–จ๊นŒ์š”?
01:37
I'm holding this clicker in my hand;
25
97614
1716
์ €๋Š” ์ง€๊ธˆ ๋ฆฌ๋ชจ์ฝ˜์„ ๋“ค๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
01:39
I'm not even looking at it,
26
99354
1292
์ €๋Š” ์ด๊ฒƒ์„ ๋ณด์ง€ ์•Š๊ณ ์„œ๋„
01:40
and I can manipulate it without any problem.
27
100670
2730
์กฐ์ž‘ํ•˜๋Š”๋ฐ ์•„๋ฌด๋Ÿฐ ๋ฌธ์ œ๋„ ์—†์Šต๋‹ˆ๋‹ค.
01:43
But even more important,
28
103424
2640
๋”์šฑ ์ค‘์š”ํ•œ ๊ฒƒ์€
01:46
I can move my body while I hold the manipulator, the clicker,
29
106088
5160
์ €๋Š” ์ด ๋ฆฌ๋ชจ์ปจ์„ ๋“ค๊ณ  ์›€์ง์ผ ์ˆ˜๋„ ์žˆ๊ณ 
01:52
and stabilize and coordinate my body,
30
112115
2174
์ œ ๋ชธ์„ ๊ณ ์ •์‹œํ‚ค๊ณ , ๋‘ ๊ฐ€์ง€๋ฅผ ๋™์‹œ์— ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
01:54
and I can even walk around.
31
114313
1522
์ €๋Š” ์‹ฌ์ง€์–ด ๊ฑธ์–ด๋‹ค๋‹ ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
01:56
And that means I can move around in the world
32
116367
2898
์ด๊ฒƒ์€ ์ œ๊ฐ€ ์ „ ์„ธ๊ณ„๋ฅผ ๋Œ์•„๋‹ค๋‹ ์ˆ˜ ์žˆ์œผ๋ฉฐ
01:59
and expand the range of my arms and my hands
33
119289
3302
์ €์˜ ํŒ”๊ณผ ์†์˜ ๋ฒ”์œ„๋ฅผ ํ™•์žฅํ•˜์—ฌ
02:02
and really be able to handle almost anything.
34
122615
2169
๊ฑฐ์˜ ๋ชจ๋“  ๊ฒƒ๋“ค์„ ์กฐ์ž‘ํ•  ์ˆ˜ ์žˆ์Œ์„ ์˜๋ฏธํ•ฉ๋‹ˆ๋‹ค.
02:04
So that's mobile manipulation.
35
124808
1592
์ด๊ฒƒ์ด ์ด๋™ ์กฐ์ž‘์ž…๋‹ˆ๋‹ค.
02:07
And all of you can do this.
36
127454
1775
์—ฌ๋Ÿฌ๋ถ„ ๋ชจ๋‘ ํ•˜์‹ค ์ˆ˜ ์žˆ๋Š” ๊ฒƒ์ด์ฃ .
02:09
Third is perception.
37
129253
1917
์„ธ ๋ฒˆ์งธ๋Š” ์ธ์‹ ์ž‘์—…์ž…๋‹ˆ๋‹ค.
02:11
I'm looking at a room with over 1,000 people in it,
38
131194
3265
์ €๋Š” ์ฒœ ๋ช…์ด ์žˆ๋Š” ๊ณณ์„ ๋ณด๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
02:14
and my amazing visual system can see every one of you --
39
134483
4775
์ €์˜ ๋†€๋ผ์šด ์‹œ๊ฐ๊ณ„๋Š” ํ•œ ๋ช… ํ•œ ๋ช…๋„ ๋ณผ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
02:19
you're all stable in space,
40
139282
1961
์—ฌ๋Ÿฌ๋ถ„ ๋ชจ๋‘ ๊ฐ€๋งŒํžˆ ๊ณ„์‹ญ๋‹ˆ๋‹ค.
02:21
even when I move my head,
41
141267
1319
์‹ฌ์ง€์–ด ์ œ๊ฐ€ ๋จธ๋ฆฌ๋ฅผ ์›€์ง์—ฌ๋„
02:22
even when I move around.
42
142610
1546
์‹ฌ์ง€์–ด ์ œ๊ฐ€ ๋Œ์•„๋‹ค๋…€๋„์š”.
02:24
That kind of mobile perception is really important for robots
43
144180
3779
์ด๋Ÿฌํ•œ ์ด๋™ ์ธ์‹ ์ž‘์—…์€ ์„ธ๊ณ„๋กœ ๋‚˜๊ฐ€์„œ
02:27
that are going to move and act
44
147983
1644
๋Œ์•„๋‹ค๋‹ˆ๋ฉฐ ํ™œ๋™ํ•˜๋Š”
02:29
out in the world.
45
149651
1213
๋กœ๋ด‡์—๊ฒŒ ๋งค์šฐ ์ค‘์š”ํ•ฉ๋‹ˆ๋‹ค.
02:31
I'm going to give you a little status report
46
151865
2278
์—ฌ๋Ÿฌ๋ถ„๊ป˜ ์ž‘์—… ์ง„ํ–‰ ๋ณด๊ณ ์„œ ํ•˜๋‚˜๋ฅผ ๋ณด์—ฌ๋“œ๋ฆฌ๊ฒ ์Šต๋‹ˆ๋‹ค.
02:34
on where we are in developing robots toward these ends.
47
154167
3846
์ €ํฌ๊ฐ€ ์ž‘์—…ํ•˜๊ณ  ์žˆ๋Š” ๋กœ๋ด‡๋“ค์€ ์—ฌ๊ธฐ๊นŒ์ง€ ์™”์Šต๋‹ˆ๋‹ค.
02:40
The first three robots are all dynamically stabilized robots.
48
160338
4540
์ฒซ ๋ฒˆ์งธ ์„ธ ๋กœ๋ด‡๋“ค์€ ๋ชจ๋‘ ์•ˆ์ •์ ์œผ๋กœ ์›€์ง์ด๋Š” ๋กœ๋ด‡๋“ค์ž…๋‹ˆ๋‹ค.
02:44
This one goes back a little over 10 years ago --
49
164902
2648
10๋…„ ์ „์œผ๋กœ ๋Œ์•„๊ฐ€๋ณด๋ฉด
02:47
"BigDog."
50
167574
1168
"๋น…๋…"์ด ์žˆ์—ˆ์ฃ .
02:48
It's got a gyroscope that helps stabilize it.
51
168766
3310
๋น…๋…์€ ๊ท ํ˜•์„ ์žก๊ธฐ ์œ„ํ•œ ํšŒ์ „์ถ•์„ ๊ฐ€์ง€๊ณ  ์žˆ์—ˆ๋Š”๋ฐ
02:52
It's got sensors and a control computer.
52
172100
3336
์„ผ์„œ์™€ ์ œ์–ด ์ปดํ“จํ„ฐ๊ฐ€ ๋‚ด์žฅ๋˜์–ด ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค.
02:55
Here's a Cheetah robot that's running with a galloping gait,
53
175460
3167
์—ฌ๊ธฐ ์ „์†๋ ฅ์œผ๋กœ ์งˆ์ฃผํ•˜๋Š” ์น˜ํƒ€ ๋กœ๋ด‡์€
02:58
where it recycles its energy,
54
178651
1696
์—๋„ˆ์ง€๋ฅผ ์žฌํ™œ์šฉํ•ฉ๋‹ˆ๋‹ค.
03:00
it bounces on the ground,
55
180371
1567
๋•…์—์„œ ํŠ€์–ด์˜ค๋ฅด๋ฉฐ
03:01
and it's computing all the time
56
181962
1554
์Šค์Šค๋กœ ๊ท ํ˜•์„ ์žก๊ณ  ์•ž์œผ๋กœ ๋‚˜์•„๊ฐ€๊ธฐ ์œ„ํ•ด
03:03
in order to keep itself stabilized and propelled.
57
183540
2887
ํ•ญ์ƒ ์ปดํ“จํ„ฐ๋ฅผ ์‚ฌ์šฉํ•ฉ๋‹ˆ๋‹ค.
03:07
And here's a bigger robot
58
187934
1828
๊ทธ๋ฆฌ๊ณ  ์—ฌ๊ธฐ ๋” ํฐ ๋กœ๋ด‡์€
03:09
that's got such good locomotion using its legs,
59
189786
2705
๋‹ค๋ฆฌ๋ฅผ ํ™œ์šฉํ•œ ํ›Œ๋ฅญํ•œ ์šด๋™ ๋Šฅ๋ ฅ์„ ๋ณด์—ฌ์ค๋‹ˆ๋‹ค.
03:12
that it can go in deep snow.
60
192515
1404
25cm์˜ ๊นŠ์€ ๋ˆˆ ์†์—์„œ๋„
03:13
This is about 10 inches deep,
61
193943
2411
์–ด๋–ค ์–ด๋ ค์›€๋„ ์—†์ด
03:16
and it doesn't really have any trouble.
62
196378
2111
์ด๋™ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
03:20
This is Spot, a new generation of robot --
63
200166
2629
์ด๊ฑด ์ŠคํŒŸ์ด๋ผ๋Š” ์ƒˆ๋กœ์šด ์„ธ๋Œ€์˜ ๋กœ๋ด‡์ž…๋‹ˆ๋‹ค.
03:22
just slightly older than the one that came out onstage.
64
202819
2808
๋ฌด๋Œ€์— ์˜ค๋ฅธ ๋กœ๋ด‡๋ณด๋‹ค ์‚ด์ง ๊ตฌํ˜•์ธ ๋ฒ„์ „์ž…๋‹ˆ๋‹ค.
03:26
And we've been asking the question --
65
206258
1832
๊ทธ๋ฆฌ๊ณ  ์ €ํฌ๋Š” ์ด ์งˆ๋ฌธ์„ ํ•ญ์ƒ ํ•ด์™”์Šต๋‹ˆ๋‹ค.
03:28
you've all heard about drone delivery:
66
208114
1974
์—ฌ๋Ÿฌ๋ถ„ ๋ชจ๋‘ ๋“œ๋ก  ํƒ๋ฐฐ์— ๋Œ€ํ•ด ๋“ค์–ด๋ณด์…จ์„ ๊ฒ๋‹ˆ๋‹ค.
03:30
Can we deliver packages to your houses with drones?
67
210112
2623
๊ณผ์—ฐ ๋“œ๋ก ์œผ๋กœ ์—ฌ๋Ÿฌ๋ถ„ ์ง‘์— ํƒ๋ฐฐ๋ฅผ ๋ฐฐ๋‹ฌํ•  ์ˆ˜ ์žˆ์„๊นŒ์š”?
03:32
Well, what about plain old legged-robot delivery?
68
212759
2787
๊ธ€์Ž„์š”, ํ‰๋ฒ”ํ•œ ๊ตฌ์‹ ๋ณดํ–‰ ๋กœ๋ด‡ ๋ฐฐ๋‹ฌ์€ ์–ด๋– ์‹ ๊ฐ€์š”?
03:35
(Laughter)
69
215570
1132
(์›ƒ์Œ)
03:36
So we've been taking our robot to our employees' homes
70
216726
3397
๊ทธ๋ž˜์„œ ์ €ํฌ๋Š” ์šฐ๋ฆฌ ๋กœ๋ด‡์„ ์šฐ๋ฆฌ ์ง์›์˜ ์ง‘์— ๋ณด๋‚ด ๋ณด์•˜์Šต๋‹ˆ๋‹ค.
03:40
to see whether we could get in --
71
220147
1583
๋กœ๋ด‡์ด ๋‹ค์–‘ํ•œ ์ž…๊ตฌ์—
03:41
(Laughter)
72
221754
1024
(์›ƒ์Œ)
03:42
the various access ways.
73
222802
1228
๋“ค์–ด๊ฐˆ ์ˆ˜ ์žˆ๋Š”์ง€ ๋ณด๊ธฐ ์œ„ํ•ด์„œ์š”.
03:44
And believe me, in the Boston area,
74
224054
1884
๊ทธ๋ฆฌ๊ณ  ๋ณด์Šคํ„ด ์ง€์—ญ์—๋Š”
03:45
there's every manner of stairway twists and turns.
75
225962
3174
์˜จ๊ฐ– ์ข…๋ฅ˜์˜ ๊ผฌ์ด๊ณ  ๊ตฝ์–ด์ง„ ๊ณ„๋‹จ๋“ค์ด ์žˆ์Šต๋‹ˆ๋‹ค.
03:49
So it's a real challenge.
76
229160
1237
๊ทธ๋ž˜์„œ ์ด ์‹œ๋„๋Š” ์ง„์ •ํ•œ ๋ชจํ—˜์ด์—ˆ์Šต๋‹ˆ๋‹ค.
03:50
But we're doing very well, about 70 percent of the way.
77
230421
2817
ํ•˜์ง€๋งŒ ์•ฝ 70%์˜ ๊ณ„๋‹จ์—์„œ ๋งค์šฐ ์ž˜ ์ด๋™ํ•˜์˜€์Šต๋‹ˆ๋‹ค.
03:54
And here's mobile manipulation,
78
234479
1565
๊ทธ๋ฆฌ๊ณ  ์ด๊ฑด ์ด๋™ ์กฐ์ž‘ ์ž‘์—…์ธ๋ฐ์š”.
03:56
where we've put an arm on the robot,
79
236068
2591
๋กœ๋ด‡์— ํŒ”์„ ์žฅ์ฐฉํ•˜๋ฉด
03:58
and it's finding its way through the door.
80
238683
2334
๋กœ๋ด‡์ด ๋ฌธ์„ ํ–ฅํ•œ ๊ธธ์„ ์ฐพ์•„๋ƒ…๋‹ˆ๋‹ค.
04:01
Now, one of the important things about making autonomous robots
81
241742
3159
์ด์ œ, ์ž์œจ ๋กœ๋ด‡ ์ œ์ž‘์— ์žˆ์–ด ์ค‘์š”ํ•œ ์‚ฌํ•ญ ์ค‘ ํ•˜๋‚˜๋Š”
04:04
is to make them not do just exactly what you say,
82
244925
3220
๋กœ๋ด‡์ด ๋‹จ์ง€ ์šฐ๋ฆฌ๊ฐ€ ๋งํ•˜๋Š” ๊ฒƒ๋งŒ ์‹คํ–‰ํ•˜๋„๋ก ํ•˜๋Š” ๊ฒƒ์ด ์•„๋‹ˆ๋ผ,
04:08
but make them deal with the uncertainty of what happens in the real world.
83
248169
5141
์‹ค์ƒํ™œ์—์„œ ์ผ์–ด๋‚˜๋Š” ๋ถˆํ™•์‹ค์„ฑ์— ๋Œ€์ฒ˜ํ•˜๋„๋ก ๋งŒ๋“œ๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
04:14
So we have Steve there, one of the engineers,
84
254054
3011
์—ฌ๊ธฐ ์Šคํ‹ฐ๋ธŒ๊ฐ€ ์žˆ์ฃ , ์šฐ๋ฆฌ ๊ธฐ์ˆ ์ž์ค‘ ํ•œ ๋ช…์ธ๋ฐ์š”.
04:17
giving the robot a hard time.
85
257089
1608
๋กœ๋ด‡์—๊ฒŒ ์‹œ๋ จ์„ ์ค๋‹ˆ๋‹ค.
04:18
(Laughter)
86
258721
1032
(์›ƒ์Œ)
04:19
And the fact that the programming still tolerates all that disturbance --
87
259777
4190
๊ทธ๋ฆฌ๊ณ  ํ”„๋กœ๊ทธ๋žจ์€ ๋ชจ๋“  ์ œ์•ฝ๋“ค์„ ๊ฒฌ๋ŽŒ๋ƒ…๋‹ˆ๋‹ค.
04:23
it does what it's supposed to.
88
263991
1497
๊ทธ๋ ‡๊ฒŒ ํ•˜๋„๋ก ์ œ์ž‘๋œ ๊ฒƒ์ด์ฃ .
04:25
Here's another example, where Eric is tugging on the robot
89
265512
2791
์—ฌ๊ธฐ ๋‹ค๋ฅธ ์˜ˆ๊ฐ€ ์žˆ๋Š”๋ฐ์š”. ์—๋ฆญ์ด ๋กœ๋ด‡์„ ์žก์•„๋‹น๊ฒจ๋„
04:28
as it goes up the stairs.
90
268327
1298
๋กœ๋ด‡์€ ์œ„๋กœ ์˜ฌ๋ผ๊ฐ‘๋‹ˆ๋‹ค.
04:29
And believe me,
91
269649
1152
์—ฌ๋Ÿฌ๋ถ„
04:30
getting it to do what it's supposed to do in those circumstances
92
270825
3272
์ €๋Ÿฐ ํ™˜๊ฒฝ ์†์—์„œ ๋ช…๋ น์„ ์ˆ˜ํ–‰ํ•˜๋Š” ๊ฒƒ์€
04:34
is a real challenge,
93
274121
1341
์ •๋ง ๋„์ „์ ์ธ ์ผ์ด์ง€๋งŒ
04:35
but the result is something that's going to generalize
94
275486
2740
์ด ๊ฒฐ๊ณผ๋Š” ์•ž์œผ๋กœ ์ผ๋ฐ˜ํ™” ๋  ๊ฒƒ์ด๋ฉฐ
04:38
and make robots much more autonomous than they would be otherwise.
95
278250
3871
๋‹ค๋ฅธ ์–ด๋–ค ํ›ˆ๋ จ๋ณด๋‹ค๋„ ๋กœ๋ด‡์„ ํ›จ์”ฌ ๋” ์ž์œจ์ ์œผ๋กœ ๋งŒ๋“ญ๋‹ˆ๋‹ค.
04:43
This is Atlas, a humanoid robot.
96
283317
2431
์ด๊ฒƒ์€ ์•„ํ‹€๋ผ์Šค, ์ธ๊ฐ„ํ˜• ๋กœ๋ด‡์ž…๋‹ˆ๋‹ค.
04:46
It's a third-generation humanoid that we've been building.
97
286427
3905
์ด๊ฒƒ์€ ์ €ํฌ๊ฐ€ ์ œ์ž‘ํ•œ 3์„ธ๋Œ€ ์ธ๊ฐ„ํ˜• ๋กœ๋ด‡์ž…๋‹ˆ๋‹ค.
04:50
I'll tell you a little bit about the hardware design later.
98
290671
2818
์™ธํ˜• ๋””์ž์ธ์— ๋Œ€ํ•ด์„œ๋Š” ํ›„์— ์กฐ๊ธˆ ์ด์•ผ๊ธฐ ํ•ด๋“œ๋ฆฌ๊ฒ ์Šต๋‹ˆ๋‹ค.
04:53
And we've been saying:
99
293513
1176
์ €ํฌ๊ฐ€ ์ด์•ผ๊ธฐํ–ˆ๋˜ ๊ฒƒ์€
04:54
How close to human levels of performance and speed could we get
100
294713
4423
์ธ๊ฐ„ ์ˆ˜์ค€์˜ ์ˆ˜ํ–‰๊ณผ ์†๋„์— ์–ผ๋งˆ๋‚˜ ๊ฐ€๊นŒ์ด ๋„๋‹ฌํ•  ์ˆ˜ ์žˆ๋Š”๊ฐ€๋Š”
04:59
in an ordinary task,
101
299160
1575
์ผ๋ฐ˜์ ์ธ ๊ณผ์ œ์ด๊ณ 
05:00
like moving boxes around on a conveyor?
102
300759
2469
์ปจ๋ฒ ์ด์–ด ์ฃผ๋ณ€์˜ ์ƒ์ž๋ฅผ ์˜ฎ๊ธฐ๋Š” ๊ฒƒ ๊ฐ™์€ ์ผ ๋ง์ด์ฃ .
05:03
We're getting up to about two-thirds of the speed that a human operates
103
303931
5306
์ €ํฌ๋Š” ํ‰๊ท ์ ์œผ๋กœ ์ธ๊ฐ„์˜ ์ˆ˜ํ–‰ ์†๋„์˜
์•ฝ 3๋ถ„์˜ 2 ์ˆ˜์ค€์— ๋„๋‹ฌํ–ˆ์Šต๋‹ˆ๋‹ค.
05:09
on average.
104
309261
1162
05:10
And this robot is using both hands, it's using its body,
105
310758
2929
๊ทธ๋ฆฌ๊ณ  ์ด ๋กœ๋ด‡์€ ์–‘์†์„ ์‚ฌ์šฉํ•˜๋ฉด์„œ, ๋ชธ์„ ์›€์ง์ด๊ณ  ๊ฑท์Šต๋‹ˆ๋‹ค.
05:13
it's stepping,
106
313711
1169
05:14
so it's really an example of dynamic stability,
107
314904
2727
์ด ๋กœ๋ด‡์€ ์—ญ๋™์ ์ธ ์•ˆ์ •์„ฑ์„ ๋ณด์—ฌ์ฃผ๋Š” ์ข‹์€ ์˜ˆ์ž…๋‹ˆ๋‹ค.
05:17
mobile manipulation
108
317655
1379
์ด๋™ ์กฐ์ž‘ ์ž‘์—…
05:19
and mobile perception.
109
319058
1611
๊ทธ๋ฆฌ๊ณ  ์ด๋™ ์ธ์‹ ์ž‘์—…์ž…๋‹ˆ๋‹ค,
05:22
Here --
110
322192
1173
์—ฌ๊ธฐ
05:23
(Laughter)
111
323905
1907
(์›ƒ์Œ)
05:26
We actually have two Atlases.
112
326389
1610
์‚ฌ์‹ค ์ €ํฌ๋Š” ์•„ํ‹€๋ผ์Šค๊ฐ€ 2๊ฐœ ์žˆ์Šต๋‹ˆ๋‹ค.
05:28
(Laughter)
113
328483
1185
(์›ƒ์Œ)
05:30
Now, everything doesn't go exactly the way it's supposed to.
114
330198
3396
๋ชจ๋“  ์ผ์ด ์šฐ๋ฆฌ๊ฐ€ ์˜๋„ํ•œ ๊ทธ๋Œ€๋กœ ์ง„ํ–‰๋˜์ง€๋Š” ์•Š์Šต๋‹ˆ๋‹ค.
05:33
(Laughter)
115
333618
1702
(์›ƒ์Œ)
05:38
(Laughter)
116
338318
1528
(์›ƒ์Œ)
05:40
(Laughter)
117
340536
1871
(์›ƒ์Œ)
05:45
And here's our latest robot, called "Handle."
118
345292
2544
์ด๊ฒƒ์€ ์ตœ์‹ ํ˜• ๋กœ๋ด‡, ํ•ธ๋“ค์ž…๋‹ˆ๋‹ค.
05:48
Handle is interesting, because it's sort of half like an animal,
119
348457
4118
ํ•ธ๋“ค์ด ํฅ๋ฏธ๋กœ์šด ์ด์œ ๋Š”, ๋ฐ˜์€ ๋™๋ฌผ์— ๊ฐ€๊น๊ณ 
05:52
and it's half something else
120
352599
2314
๋ฐ˜์€ ๋‹ค๋ฅธ ์–ด๋–ค ๊ฒƒ์— ๊ฐ€๊นŒ์šด๋ฐ
05:54
with these leg-like things and wheels.
121
354937
2756
๋‹ค๋ฆฌ ๋ถ€๋ถ„์— ๋ฐ”ํ€ด๊ฐ€ ๋‹ฌ๋ ค์žˆ์Šต๋‹ˆ๋‹ค.
05:58
It's got its arms on in kind of a funny way,
122
358141
3026
์ด ๋กœ๋ด‡์€ ํŒ”์„ ๋‹ค์†Œ ์šฐ์Šค๊ฝ์Šค๋Ÿฝ๊ฒŒ ์“ฐ๊ธด ํ•˜์ง€๋งŒ
06:01
but it really does some remarkable things.
123
361191
2096
์ •๋ง ์ฃผ๋ชฉํ• ๋งŒํ•œ ์ผ์„ ํ•ด ๋ƒ…๋‹ˆ๋‹ค.
06:03
It can carry 100 pounds.
124
363311
3331
45kg์„ ๋“ค์–ด ์˜ฌ๋ฆฝ๋‹ˆ๋‹ค.
06:06
It's probably going to lift more than that,
125
366666
2059
์•ž์œผ๋กœ ๊ทธ๋ณด๋‹ค ๋” ๋งŽ์ด ๋“ค์–ด์˜ฌ๋ฆฌ๊ฒŒ ๋˜๊ฒ ์ง€๋งŒ
06:08
but so far we've done 100.
126
368749
1778
์ง€๊ธˆ๊นŒ์ง€๋Š” 45kg์„ ๋“ค์–ด์˜ฌ๋ ธ์Šต๋‹ˆ๋‹ค.
06:10
It's got some pretty good rough-terrain capability,
127
370551
2436
ํ•ธ๋“ค์€ ๊ฝค ํ›Œ๋ฅญํ•œ ๊ฑฐ์นœ ์ง€ํ˜• ์ด๋™ ๋Šฅ๋ ฅ์„ ๊ฐ–์ท„๊ณ 
06:13
even though it has wheels.
128
373011
1428
์‹ฌ์ง€์–ด๋Š” ๋ฐ”ํ€ด์ธ๋ฐ๋„์š”.
06:17
And Handle loves to put on a show.
129
377881
2366
๊ทธ๋ฆฌ๊ณ  ํ•ธ๋“ค์€ ๋ฝ๋‚ด๊ธฐ๋„ ์ข‹์•„ํ•ฉ๋‹ˆ๋‹ค.
06:20
(Laughter)
130
380686
1358
(์›ƒ์Œ)
06:24
(Applause)
131
384644
5129
(๋ฐ•์ˆ˜)
06:30
I'm going to give you a little bit of robot religion.
132
390740
2998
์ด์ œ ๋กœ๋ด‡์˜ ์›์น™์— ๋Œ€ํ•ด ์กฐ๊ธˆ ๋ง์”€๋“œ๋ฆฌ๊ฒ ์Šต๋‹ˆ๋‹ค.
06:34
A lot of people think that a robot is a machine where there's a computer
133
394356
4329
๋งŽ์€ ๋ถ„๋“ค์ด ๋กœ๋ด‡์„ ๋ช…๋ น์„ ๋‚ด๋ฆฌ๋Š” ์ปดํ“จํ„ฐ๋ฅผ
06:38
that's telling it what to do,
134
398709
1634
๋‚ด์žฅํ•œ ๊ธฐ๊ณ„์ด๋ฉฐ
06:40
and the computer is listening through its sensors.
135
400900
2816
์ปดํ“จํ„ฐ๋Š” ์„ผ์„œ๋ฅผ ํ†ตํ•ด ์ž…๋ ฅ์„ ๋ฐ›๋Š”๋‹ค๊ณ  ์ƒ๊ฐํ•˜์ง€๋งŒ
06:44
But that's really only half of the story.
136
404349
2404
๊ทธ๊ฒƒ์€ ์ ˆ๋ฐ˜๋งŒ์„ ์ดํ•ดํ•˜๊ณ  ์žˆ๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
06:46
The real story is that the computer is on one side,
137
406777
3109
์‹ค์ œ๋กœ๋Š” ์ปดํ“จํ„ฐ๋Š” ํ•œํŽธ์—์„œ
06:49
making suggestions to the robot,
138
409910
1944
๋กœ๋ด‡์—๊ฒŒ ์ œ์•ˆ์„ ํ•˜๊ณ  ์žˆ๊ณ 
06:51
and on the other side are the physics of the world.
139
411878
2492
๋‹ค๋ฅธ ํ•œํŽธ์—๋Š” ์„ธ์ƒ์˜ ๋ฌผ๋ฆฌ์  ์š”์†Œ๋“ค์ด ์žˆ์Šต๋‹ˆ๋‹ค.
06:54
And that physics involves gravity, friction, bouncing into things.
140
414778
4922
๊ทธ๋ฆฌ๊ณ  ๋ฌผ๋ฆฌ์  ์š”์†Œ๋Š” ์ค‘๋ ฅ, ๋งˆ์ฐฐ, ๋ฐ˜์ž‘์šฉ์„ ํฌํ•จํ•ฉ๋‹ˆ๋‹ค.
07:00
In order to have a successful robot,
141
420238
1835
์„ฑ๊ณต์ ์ธ ๋กœ๋ด‡์„ ๋งŒ๋“ค์–ด๋‚ด๊ธฐ ์œ„ํ•œ
07:02
my religion is that you have to do a holistic design,
142
422097
4591
์ €์˜ ์›์น™์€, ์ „์ฒด๋ฅผ ์•„์šฐ๋ฅด๋Š” ๋””์ž์ธ์„ ํ•ด์•ผ ํ•œ๋‹ค๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
07:06
where you're designing the software, the hardware and the behavior
143
426712
3553
์†Œํ”„ํŠธ์›จ์–ด์™€ ํ•จ๊ป˜, ํ•˜๋“œ์›จ์–ด์™€ ๋™์ž‘๋“ค์„
07:10
all at one time,
144
430289
1236
๋™์‹œ์— ์„ค๊ณ„ํ•ด์•ผ ํ•˜์ฃ .
07:11
and all these parts really intermesh and cooperate with each other.
145
431549
3702
๋ชจ๋“  ๋ถ€๋ถ„๋“ค์ด ์™„๋ฒฝํžˆ ๋”ฑ ๋“ค์–ด๋งž์•„ ์„œ๋กœ ํ˜‘์‘ํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
07:15
And when you get the perfect design, you get a real harmony
146
435275
3107
๋‹น์‹ ์ด ์™„๋ฒฝํ•œ ๋””์ž์ธ์„ ํ–ˆ๋‹ค๋ฉด ์ƒํ˜ธ์ž‘์šฉํ•˜๋Š” ๋ถ€๋ถ„๋“ค ์‚ฌ์ด์˜
07:18
between all those parts interacting with each other.
147
438406
2879
์™„์ „ํ•œ ์กฐํ™”๋ฅผ ์–ป๊ฒŒ ๋  ๊ฒ๋‹ˆ๋‹ค
07:22
So it's half software and half hardware,
148
442269
2260
์†Œํ”„ํŠธ์›จ์–ด ๋ฐ˜, ํ•˜๋“œ์›จ์–ด ๋ฐ˜
07:24
plus the behavior.
149
444553
1291
์—ฌ๊ธฐ์— ๋™์ž‘ ์ˆ˜ํ–‰์ด ๋”ํ•ด์ง‘๋‹ˆ๋‹ค.
07:26
We've done some work lately on the hardware, where we tried to go --
150
446698
3542
์ €ํฌ๋Š” ์ตœ๊ทผ์— ํ•˜๋“œ์›จ์–ด ์ž‘์—…์„ ์กฐ๊ธˆ ํ–ˆ๋Š”๋ฐ
07:30
the picture on the left is a conventional design,
151
450264
2477
์™ผ์ชฝ ๊ทธ๋ฆผ์€ ์ „ํ†ต์ ์ธ ๋””์ž์ธ์ด๊ณ 
07:32
where you have parts that are all bolted together,
152
452765
2900
๋ถ€ํ’ˆ๋“ค์ด ๋ณผํŠธ๋กœ ์กฐ๋ฆฝ์–ด ์žˆ์ฃ ,
07:35
conductors, tubes, connectors.
153
455689
2740
๋„์ฒด, ํŠœ๋ธŒ, ์ปค๋„ฅํ„ฐ
07:38
And on the right is a more integrated thing;
154
458453
2049
์˜ค๋ฅธ์ชฝ์€ ์ข€ ๋” ํ†ตํ•ฉ๋œ ๋””์ž์ธ์ธ
07:40
it's supposed to look like an anatomy drawing.
155
460526
2401
ํ•ด๋ถ€ํ•™ ๊ตฌ์กฐ์™€ ๋น„์Šทํ•˜๊ฒŒ ์„ค๊ณ„๋œ ๊ฒƒ์ž…๋‹ˆ๋‹ค.
07:43
Using the miracle of 3-D printing,
156
463330
2510
3-D ํ”„๋ฆฐํ„ฐ์˜ ๊ธฐ์ ์„ ์ด์šฉํ•˜์—ฌ
07:45
we're starting to build parts of robots
157
465864
2637
๋™๋ฌผ์˜ ํ•ด๋ถ€ํ•™์  ๊ตฌ์กฐ์™€ ํ›จ์”ฌ ๋” ๋‹ฏ์€
07:48
that look a lot more like the anatomy of an animal.
158
468525
2897
๋กœ๋ด‡ ๋ถ€ํ’ˆ์„ ์ œ์ž‘ํ•˜๊ธฐ ์‹œ์ž‘์˜€์Šต๋‹ˆ๋‹ค.
07:51
So that's an upper-leg part that has hydraulic pathways --
159
471446
3344
์ด๊ฒƒ์ด ์œ ์•• ํ†ต๋กœ๋ฅผ ๊ฐ€์ง„ ๋‹ค๋ฆฌ ์ƒ๋ถ€ ๋ถ€๋ถ„์ž…๋‹ˆ๋‹ค.
07:54
actuators, filters --
160
474814
1930
์ž‘๋™๊ธฐ, ํ•„ํ„ฐ
07:56
all embedded, all printed as one piece,
161
476768
2380
๋ชจ๋‘ ๋‚ด์žฅ๋˜์–ด, ํ•˜๋‚˜์˜ ๋ถ€ํ’ˆ์œผ๋กœ ํ”„๋ฆฐํŠธ๋˜์–ด ๋‚˜์˜ค๊ฒŒ ๋ฉ๋‹ˆ๋‹ค.
07:59
and the whole structure is developed
162
479172
3202
๋กœ๋ด‡๋“ค์—๊ฒŒ์„œ ๊ธฐ๋ก๋œ ๋ฐ์ดํ„ฐ๋“ค๊ณผ
08:02
with a knowledge of what the loads and behavior are going to be,
163
482398
3036
์‹œ๋ฎฌ๋ ˆ์ด์…˜ ๋“ฑ์„ ํ†ตํ•˜์—ฌ
ํ•˜์ค‘๊ณผ ๋™์ž‘๋“ค์ด ์–ด๋–ป๊ฒŒ ๋ ์ง€ ์ง€์‹์„ ์ด์šฉํ•˜์—ฌ
08:05
which is available from data recorded from robots
164
485458
2903
08:08
and simulations and things like that.
165
488385
1809
์ „์ฒด ํ˜•ํƒœ๋ฅผ ๊ฐœ์„ ํ•˜์˜€์Šต๋‹ˆ๋‹ค.
08:10
So it's a data-driven hardware design.
166
490218
2937
์ด๊ฒƒ์€ ๋ฐ์ดํ„ฐ ์ค‘์‹ฌ ํ•˜๋“œ์›จ์–ด ๋””์ž์ธ์ž…๋‹ˆ๋‹ค.
08:13
And using processes like that,
167
493547
1726
๊ทธ๋ฆฌ๊ณ  ์ด๋Ÿฌํ•œ ์ ˆ์ฐจ๋ฅผ ์ด์šฉํ•˜์—ฌ
08:15
not only the upper leg but some other things,
168
495297
2244
๋‹ค๋ฆฌ ์ƒ๋ถ€ ๋ฟ๋งŒ ์•„๋‹ˆ๋ผ ๋‹ค๋ฅธ ๋ถ€๋ถ„๋“ค๋„
08:17
we've gotten our robots to go from big, behemoth, bulky, slow, bad robots --
169
497565
5140
๊ฑฐ๋Œ€ํ•˜๊ณ , *๋ฒ ํ—ค๋ชจ์Šค ๊ฐ™์€, ๋ฉ์น˜ ํฐ, ๋Š๋ฆฐ, ๋‚˜์œ ๋กœ๋ด‡์—์„œ(์„ฑ๊ฒฝ์— ์–ธ๊ธ‰๋œ ์ง์Šด)
08:22
that one on the right, weighing almost 400 pounds --
170
502729
3619
์˜ค๋ฅธ์ชฝ์— ์žˆ๋Š” ๊ฒƒ์€ ๊ฑฐ์˜ 180kg์— ์ด๋ฅด๋Š”๋ฐ์š”.
08:26
down to the one in the middle which was just in the video,
171
506372
3109
๊ฐ€์šด๋ฐ์— ์žˆ๋Š” ๋กœ๋ด‡์€ ๋น„๋””์˜ค์— ๋‚˜์˜จ ๊ฒƒ์ธ๋ฐ
08:29
weighs about 190 pounds,
172
509505
1563
์•ฝ 85kg์œผ๋กœ
08:31
just a little bit more than me,
173
511092
1697
์ €๋ณด๋‹ค ์•ฝ๊ฐ„ ๋ฌด๊ฑฐ์šด ์ •๋„๋กœ ์ค„์˜€๊ณ 
08:32
and we have a new one,
174
512813
1486
์ตœ์‹ ํ˜• ๋กœ๋ด‡์€
08:34
which is working but I'm not going to show it to you yet,
175
514323
2742
๋™์ž‘์€ ํ•˜์ง€๋งŒ, ์—ฌ๊ธฐ์— ๊ฐ€์ ธ์˜ค์ง€๋Š” ์•Š์•˜์Šต๋‹ˆ๋‹ค.
08:37
on the left,
176
517089
1162
์™ผ์ชฝ์— ์žˆ๋Š” 75kg๋ฐ–์— ์•ˆ๋˜๋Š” ๋กœ๋ด‡์€
08:38
which weighs just 165 pounds,
177
518275
1644
08:39
with all the same strength and capabilities.
178
519943
2266
๋˜‘๊ฐ™์€ ํž˜๊ณผ ๋Šฅ๋ ฅ์„ ๊ฐ€์ง€๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
08:42
So these things are really getting better very quickly.
179
522233
2730
์ด๋Ÿฐ ๊ฒƒ๋“ค์€ ๋งค์šฐ ๋น ๋ฅด๊ฒŒ ๊ฐœ์„ ๋˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
08:46
So it's time for Spot to come back out,
180
526280
3262
์ด์ œ ์ŠคํŒŸ์„ ๋‹ค์‹œ ๋ถˆ๋Ÿฌ ๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค,
08:49
and we're going to demonstrate a little bit of mobility,
181
529566
3748
์ด๋™ ๋Šฅ๋ ฅ, ์ž‘์—…๋Šฅ๋ ฅ, ์ง€๊ฐ ๋Šฅ๋ ฅ์„
08:53
dexterity and perception.
182
533338
1600
์‹œ์—ฐํ•ด ๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค.
08:55
This is Seth Davis, who's my robot wrangler today,
183
535681
3764
์„ธ์Šค ๋ฐ์ด๋น„์Šค, ์˜ค๋Š˜ ์ €์˜ ๋กœ๋ด‡ ์กฐ์ข…์‚ฌ๊ฐ€ ๋˜์–ด ์ค„ ๋ถ„์ž…๋‹ˆ๋‹ค.
08:59
and he's giving Spot some general direction
184
539469
3040
๊ทธ๊ฐ€ ์กฐ์ข…์„ ํ•ด์„œ ์ŠคํŒŸ์—๊ฒŒ
09:02
by steering it around,
185
542533
1826
์ผ๋ฐ˜์ ์ธ ๋ช…๋ น์„ ๋‚ด๋ฆฌ๋”๋ผ๋„
09:04
but all the coordination of the legs and the sensors
186
544383
3071
๋‹ค๋ฆฌ์™€ ์„ผ์„œ์˜ ํ˜‘์‘์€
09:07
is done by the robot's computers on board.
187
547478
2509
๋‚ด์žฅ๋œ ์ปดํ“จํ„ฐ์— ์˜ํ•ด ์ด๋ค„์ง€๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
09:10
The robot can walk with a number of different gaits;
188
550543
3446
์ด ๋กœ๋ด‡์€ ๋ช‡๊ฐ€์ง€ ๋‹ค๋ฅธ ๊ธธ๋“ค์„ ๊ฑธ์„ ์ˆ˜ ์žˆ๋Š”๋ฐ
์ •์ง€ ์ƒํƒœ์˜ ๋ฐ”ํ€ด๋ฅผ ๊ฐ€์ง€๊ณ  ์žˆ์œผ๋ฉฐ
09:14
it's got a gyro,
189
554013
2159
09:16
or a solid-state gyro,
190
556196
1337
09:17
an IMU on board.
191
557557
1420
๊ด€์„ฑ์ธก์ •์žฅ์น˜๊ฐ€ ๋‚ด์žฅ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.
09:19
Obviously, it's got a battery, and things like that.
192
559442
3027
๋ถ„๋ช…ํžˆ, ์ŠคํŒŸ์—๋Š” ๋ฐฐํ„ฐ๋ฆฌ ๋“ฑ์ด ๋‚ด์žฅ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.
09:23
One of the cool things about a legged robot is,
193
563352
2506
๋ณดํ–‰ ๋กœ๋ด‡์˜ ๋ฉ‹์ง„ ์ ์€
09:25
it's omnidirectional.
194
565882
1449
์ „๋ฐฉํ–ฅ์ ์ด๋ผ๋Š” ๊ฒ๋‹ˆ๋‹ค.
09:27
In addition to going forward, it can go sideways,
195
567355
2773
์•ž์œผ๋กœ ๊ฐ€๋Š” ๊ฒƒ์— ๋”ํ•˜์—ฌ ์˜†์œผ๋กœ ๊ฐˆ ์ˆ˜๋„ ์žˆ๊ณ 
09:31
it can turn in place.
196
571413
1440
์ œ์ž๋ฆฌ์—์„œ ๋Œ ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
09:36
And this robot is a little bit of a show-off.
197
576482
2268
๊ทธ๋ฆฌ๊ณ  ์ด ๋กœ๋ด‡์€ ๋ฝ๋‚ด๊ธฐ๋ฅผ ์ข‹์•„ํ•˜๋Š”๋ฐ์š”.
09:39
It loves to use its dynamic gaits,
198
579675
1960
์—ญ๋™์ ์œผ๋กœ ๊ฑท๊ธฐ๋ฅผ ์ข‹์•„ํ•˜๊ณ ์š”.
09:41
like running --
199
581659
1158
๋›ฐ๋“ฏ์ด์š”.
09:42
(Laughter)
200
582841
1044
(์›ƒ์Œ)
09:43
And it's got one more.
201
583909
1516
ํ•œ ๊ฐ€์ง€ ๋” ์žˆ์Šต๋‹ˆ๋‹ค.
09:47
(Laughter)
202
587104
1830
(์›ƒ์Œ)
09:49
Now if it were really a show-off, it would be hopping on one foot,
203
589858
3236
์ •๋ง ๋ฝ๋‚ด๊ณ  ์‹ถ๋‹ค๋ฉด ํ•œ ๋ฐœ๋กœ ๋›ฐ์–ด์•ผ ๊ฒ ์ฃ ,
ํ•˜์ง€๋งŒ, ์•„์‹œ์ž–์•„์š”.
09:53
but, you know.
204
593118
1168
09:54
Now, Spot has a set of cameras here, stereo cameras,
205
594310
4043
์ŠคํŒŸ์—๋Š” ์ž…์ฒด ์นด๋ฉ”๋ผ ์„ธํŠธ๊ฐ€ ์žฅ์ฐฉ๋˜์–ด ์žˆ๋Š”๋ฐ์š”.
09:58
and we have a feed up in the center.
206
598377
1830
์œ„ ์ค‘์•™์— ์ž…๋ ฅ์„ ํ•˜๋ฉด
10:00
It's kind of dark out in the audience,
207
600591
1824
์ฒญ์ค‘๋“ค์ด ์–ด๋‘ก๊ฒŒ ๋ณด์ด๋„ค์š”.
10:02
but it's going to use those cameras in order to look at the terrain
208
602439
3220
์ด์ œ ์ € ์นด๋ฉ”๋ผ๋“ค๋กœ ์ง€ํ˜•์„ ์ธ์‹ํ•˜๋„๋ก ํ•˜๋ฉด
10:05
right in front of it,
209
605683
1173
๋ฐ”๋กœ ์ด ์•ž์ด์š”,
10:06
while it goes over these obstacles back here.
210
606880
2761
์ด ๋’ค์— ์žˆ๋Š” ๋ฐฉํ•ด๋ฌผ์„ ์ง€๋‚˜๊ฒŒ ๋ฉ๋‹ˆ๋‹ค.
10:09
For this demo, Seth is steering,
211
609665
3313
์ด ์‹œ์—ฐ์„ ์œ„ํ•ด ์„ธ์Šค๊ฐ€ ์กฐ์ข…์„ ํ•˜๊ณ  ์žˆ์ง€๋งŒ
10:13
but the robot's doing all its own terrain planning.
212
613002
2505
๋กœ๋ด‡์€ ์ž์‹ ์˜ ์ง€ํ˜• ๊ณ„ํš์„ ์„ธ์šฐ๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
10:15
This is a terrain map,
213
615531
1502
์ด๊ฒƒ์ด ์ง€ํ˜• ์ง€๋„์ธ๋ฐ์š”.
10:17
where the data from the cameras is being developed in real time,
214
617057
5170
์นด๋ฉ”๋ผ๋กœ๋ถ€ํ„ฐ ์‹ค์‹œ๊ฐ„ ๋ฐ์ดํ„ฐ๊ฐ€ ๋“ค์–ด์™€
10:22
showing the red spots, which are where it doesn't want to step,
215
622251
3237
๋นจ๊ฐ„ ์ ๋“ค์„ ํ‘œ์‹œํ•ด์ฃผ๋Š”๋ฐ, ๊ฑธ์Œ์„ ๋”›๊ธฐ ํž˜๋“  ๊ณณ๋“ค์ด์ฃ .
10:25
and the green spots are the good places.
216
625512
1991
๊ทธ๋ฆฌ๊ณ  ์ดˆ๋ก ์ ๋“ค์€ ์ข‹์€ ๊ณณ๋“ค์ž…๋‹ˆ๋‹ค.
10:27
And here it's treating them like stepping-stones.
217
627527
2449
๊ทธ๋ฆฌ๊ณ  ์ด ๋ถ€๋ถ„๋“ค์„ ๋””๋”ค๋Œ๋กœ ์ธ์‹ํ•ฉ๋‹ˆ๋‹ค.
10:30
So it's trying to stay up on the blocks,
218
630000
2755
์ŠคํŒŸ์„ ๋ธ”๋ก ์œ„์—๋งŒ ์„œ์žˆ๋„๋ก ํ•˜๋ฉด
10:32
and it adjusts its stride,
219
632779
1273
์ŠคํŒŸ์€ ์ž์‹ ์˜ ๊ฑธ์Œ์„ ์กฐ์ •ํ•˜๊ณ 
10:34
and there's a ton of planning
220
634076
1461
์ด๋Ÿฌํ•œ ์กฐ์ž‘์„ ์ˆ˜ํ–‰ํ•˜๊ธฐ ์œ„ํ•œ
10:35
that has to go into an operation like that,
221
635561
2241
์ˆ˜๋งŽ์€ ๊ณ„ํš๋“ค์ด ์ˆ˜๋ฆฝํ•˜๋ฉฐ
10:37
and it does all that planning in real time,
222
637826
2262
๊ฑธ์Œ์„ ์•ฝ๊ฐ„ ๊ธธ๊ฒŒ ๋˜๋Š” ์•ฝ๊ฐ„ ์งง๊ฒŒ
10:40
where it adjusts the steps a little bit longer
223
640112
2430
์กฐ์ •ํ•˜๋Š” ๊ณผ์ •์—์„œ
์ด ๋ชจ๋“  ๊ณ„ํš์„ ์‹ค์‹œ๊ฐ„์œผ๋กœ ์„ธ์›๋‹ˆ๋‹ค.
10:42
or a little bit shorter.
224
642566
1276
10:45
Now we're going to change it into a different mode,
225
645216
2430
์ด์ œ ๋‹ค๋ฅธ ๋ฐฉ์‹์œผ๋กœ ๋ฐ”๊พธ์–ด ๋ณผ ๊ฑด๋ฐ์š”.
10:47
where it's just going to treat the blocks like terrain
226
647670
3423
๋ธ”๋ก๋“ค์„ ๋‹จ์ง€ ์ง€ํ˜•์˜ ์ผ๋ถ€๋กœ ์ธ์‹ํ•˜๋„๋ก ํ•˜๊ณ 
10:51
and decide whether to step up or down
227
651117
3719
์˜ฌ๋ผ๊ฐˆ์ง€ ๋˜๋Š” ๋‚ด๋ ค๊ฐˆ์ง€ ๊ฒฐ์ •ํ•˜๋ฉด์„œ
10:54
as it goes.
228
654860
1285
์ด๋™ํ•˜๊ฒŒ ํ•ฉ๋‹ˆ๋‹ค.
10:57
So this is using dynamic balance
229
657085
2969
์ด๊ฒƒ์€ ์—ญ๋™์ ์ธ ๊ท ํ˜• ๋Šฅ๋ ฅ๊ณผ
11:00
and mobile perception,
230
660078
1858
์ด๋™ ์ธ์‹ ๋Šฅ๋ ฅ์„ ์ด์šฉํ•˜๋Š”๋ฐ์š”.
11:01
because it has to coordinate what it sees along with how it's moving.
231
661960
5387
์ž์‹ ์ด ๋ณธ ๊ฒƒ๊ณผ ์–ด๋–ป๊ฒŒ ์›€์ง์ผ์ง€๋ฅผ ๊ฒฐํ•ฉํ•ด์•ผ ํ•˜๊ธฐ ๋•Œ๋ฌธ์ด์ง€์š”.
11:08
The other thing Spot has is a robot arm.
232
668988
4318
์ŠคํŒŸ์ด ๊ฐ€์ง€๊ณ  ์žˆ๋Š” ๋‹ค๋ฅธ ํ•œ ๊ฐ€์ง€๋Š” ๋กœ๋ด‡ ํŒ”์ž…๋‹ˆ๋‹ค.
11:14
Some of you may see that as a head and a neck,
233
674337
2490
๋ช‡๋ถ„์€ ์ด๊ฒƒ์„ ๋จธ๋ฆฌ๋‚˜ ๋ชฉ์ด๋ผ๊ณ  ์ƒ๊ฐํ•˜์…จ์„ ํ…๋ฐ์š”.
11:16
but believe me, it's an arm.
234
676851
1585
์—ฌ๋Ÿฌ๋ถ„, ์ด๊ฑด ํŒ”์ž…๋‹ˆ๋‹ค.
11:18
Seth is driving it around.
235
678460
1765
์„ธ์Šค๊ฐ€ ์ฃผ์œ„๋กœ ์›€์ง์ด๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
11:20
He's actually driving the hand and the body is following.
236
680249
3768
์‚ฌ์‹ค ๊ทธ๋Š” ์†์„ ์›€์ง์ด๊ณ  ์žˆ๊ณ  ๋ชธ์€ ๋”ฐ๋ผ๊ฐ€๊ณ  ์žˆ๋Š” ๊ฒ๋‹ˆ๋‹ค.
11:24
So the two are coordinated in the way I was talking about before --
237
684041
4133
์ด ๋‘˜์€ ์•ž์„œ ๋ง์”€๋“œ๋ฆฐ ๋ฐฉ์‹์œผ๋กœ ์‚ฌ๋žŒ๋“ค์ด ํ•˜๋Š” ๋ฐฉ์‹์ฒ˜๋Ÿผ
11:28
in the way people can do that.
238
688198
1864
ํ˜‘์‘ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
11:30
In fact, one of the cool things Spot can do we call, "chicken-head mode,"
239
690086
4643
์‚ฌ์‹ค, ๋ฉ‹์ง„ ์  ์ค‘ ํ•˜๋‚˜๋Š” ์ŠคํŒŸ์ด "์น˜ํ‚จ ํ—ค๋“œ ๋ชจ๋“œ"๋กœ ์ž‘๋™ํ•˜๋Š” ๊ฒƒ์ธ๋ฐ
11:34
and it keeps its head in one place in space,
240
694753
3184
์ด๊ฒƒ์€ ๋จธ๋ฆฌ๋ฅผ ํ•œ ์žฅ์†Œ์— ๊ณ ์ •ํ•˜๊ณ 
11:37
and it moves its body all around.
241
697961
1845
๋ชธ์„ ๋ชจ๋“  ๊ณณ์œผ๋กœ ์›€์ง์ด๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
11:40
There's a variation of this that's called "twerking" --
242
700553
2602
์ด๊ฒƒ์˜ ๋ณ€์ฃผ๋Š”"*ํŠธ์›Œํ‚น"์ด๋ผ ๋ถˆ๋ฆฌ๋Š”๋ฐ (์—‰๋ฉ์ด๋ฅผ ํ”๋“œ๋Š” ์ถค)
11:43
(Laughter)
243
703179
1016
(์›ƒ์Œ)
11:44
but we're not going to use that today.
244
704219
1823
์˜ค๋Š˜์€ ์‚ฌ์šฉํ•˜์ง€ ์•Š์„ ๊ฒ๋‹ˆ๋‹ค.
11:46
(Laughter)
245
706066
1071
(์›ƒ์Œ)
11:47
So, Spot: I'm feeling a little thirsty. Could you get me a soda?
246
707161
3586
์ŠคํŒŸ, ๋ชฉ์ด ์ข€ ๋งˆ๋ฅธ๋ฐ, ์†Œ๋‹ค๋ฅผ ๊ฐ€์ ธ๋‹ค ์ฃผ๊ฒ ๋‹ˆ?
11:51
For this demo, Seth is not doing any driving.
247
711293
3773
์ด ์‹œ์—ฐ์—, ์„ธ์Šค๋Š” ์–ด๋–ค ์กฐ์ข…๋„ ํ•˜์ง€ ์•Š์„ ๊ฒ๋‹ˆ๋‹ค.
11:55
We have a LIDAR on the back of the robot,
248
715090
2113
๋กœ๋ด‡์˜ ๋“ฑ์— ๊ด‘์„  ๋ ˆ์ด๋”๊ฐ€ ์žˆ์–ด์„œ
11:57
and it's using these props we've put on the stage
249
717227
2537
๋ฌด๋Œ€์— ์„ค์น˜ํ•ด ๋†“์€ ์ด ๊ธฐ๋‘ฅ๋“ค์„ ์ด์šฉํ•˜์—ฌ
11:59
to localize itself.
250
719788
1393
์ž์‹ ์˜ ์œ„์น˜๋ฅผ ํŒŒ์•…ํ•ฉ๋‹ˆ๋‹ค.
12:01
It's gone over to that location.
251
721205
2281
์ € ์žฅ์†Œ์— ๊ฐ€ ์žˆ๋„ค์š”.
12:03
Now it's using a camera that's in its hand
252
723510
2882
์ด์ œ ์†์— ์žˆ๋Š” ์นด๋ฉ”๋ผ๋ฅผ ์ด์šฉํ•ด
12:06
to find the cup,
253
726416
1786
์ปต์„ ์ฐพ๊ณ 
12:08
picks it up --
254
728853
1255
๋“ค์–ด ์˜ฌ๋ ค์„œ
12:10
and again, Seth's not driving.
255
730132
1951
๋‹ค์‹œ ๋ง์”€๋“œ๋ฆฌ์ง€๋งŒ, ์„ธ์Šค๋Š” ์กฐ์ข…ํ•˜๊ณ  ์žˆ์ง€ ์•Š์Šต๋‹ˆ๋‹ค.
12:13
We've planned out a path for it to go --
256
733372
3241
์ŠคํŒŸ์ด ๊ฐˆ ๊ธธ์„ ์ €ํฌ๊ฐ€ ๊ณ„ํšํ•ด ๋†“์•˜์Šต๋‹ˆ๋‹ค.
12:16
it looked like it was going off the path --
257
736637
2107
๋ฐฉ๊ธˆ ๊ธธ์„ ์ข€ ๋ฒ—์–ด๋‚œ ๊ฒƒ ๊ฐ™์€๋ฐ์š”.
12:18
and now Seth's going to take over control again,
258
738768
2358
๊ทธ๋ฆฌ๊ณ  ์ด์ œ ์„ธ์Šค๊ฐ€ ๋‹ค์‹œ ์กฐ์ข… ํ•  ๊ฒ๋‹ˆ๋‹ค.
12:21
because I'm a little bit chicken about having it do this by itself.
259
741150
3449
์ŠคํŒŸ ์Šค์Šค๋กœ ํ•ด๋‚ผ ์ˆ˜ ์žˆ์„์ง€ ์กฐ๊ธˆ ๊ฑฑ์ •์ด ๋˜์–ด์„œ์š”.
12:24
Thank you, Spot.
260
744623
1376
๊ณ ๋งˆ์›Œ, ์ŠคํŒŸ.
12:28
(Applause)
261
748231
5283
(๋ฐ•์ˆ˜)
12:34
So, Spot:
262
754889
1590
์ŠคํŒŸ
12:36
How do you feel about having just finished your TED performance?
263
756503
3567
TED ๊ณต์—ฐ์„ ๋๋งˆ์นœ ์†Œ๊ฐ์ด ์–ด๋•Œ?
12:41
(Laughter)
264
761014
2689
(์›ƒ์Œ)
12:44
Me, too!
265
764068
1152
๋‚˜๋„!
12:45
(Laughter)
266
765244
1032
(์›ƒ์Œ)
12:46
Thank you all,
267
766300
1816
๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค,
12:48
and thanks to the team at Boston Dynamics,
268
768140
2395
๋ณด์ด์ง€ ์•Š๋Š” ๊ณณ์—์„œ ์ˆ˜๊ณ ํ•ด ์ค€ ๋ณด์Šคํ„ด ๋‹ค์ด๋‚˜๋ฏน์Šค ํŒ€์—๊ฒŒ๋„
12:50
who did all the hard work behind this.
269
770559
2114
๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.
12:52
(Applause)
270
772697
2123
(๋ฐ•์ˆ˜)
ํ—ฌ๋ Œ ์›”ํ„ฐ์Šค: ๋งˆํฌ, ๊ฐ€์šด๋ฐ๋กœ ์™€์ฃผ์‹œ๊ฒ ์–ด์š”?
13:03
Helen Walters: Marc, come back in the middle.
271
783059
2163
์ •๋ง ๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.
13:05
Thank you so much.
272
785246
1154
์ด์ชฝ์œผ๋กœ ์™€ ์ฃผ์„ธ์š”, ์งˆ๋ฌธ์ด ์žˆ์Šต๋‹ˆ๋‹ค.
13:06
Come over here, I have questions.
273
786424
2095
13:08
So, you mentioned the UPS and the package delivery.
274
788543
3415
๋„ค, ๋ฏธ๊ตญ ์†Œํฌ ์‹œ์Šคํ…œ(UPS)๊ณผ ํƒ๋ฐฐ์— ๋Œ€ํ•ด ์–ธ๊ธ‰ํ•˜์…จ๋Š”๋ฐ์š”.
13:11
What are the other applications that you see for your robots?
275
791982
3937
๊ทธ ์™ธ์— ๋กœ๋ด‡์ด ํ•  ์ˆ˜ ์žˆ๋Š” ์ผ์€ ์–ด๋–ค ๊ฒƒ๋“ค์ด ์žˆ์„๊นŒ์š”?
13:15
Marc Raibert: You know, I think that robots
276
795943
2027
๋งˆํฌ ๋ ˆ์ด๋ฒ„ํŠธ: ์ œ๊ฐ€ ์ง€๊ธˆ๊นŒ์ง€ ๋งํ–ˆ๋˜
13:17
that have the capabilities I've been talking about
277
797994
2406
๋Šฅ๋ ฅ๋“ค์„ ๊ฐ€์ง„ ์ด ๋กœ๋ด‡๋“ค์€
13:20
are going to be incredibly useful.
278
800424
1660
์—„์ฒญ๋‚˜๊ฒŒ ์œ ์šฉํ•˜๊ฒŒ ์‚ฌ์šฉ๋  ๊ฒ๋‹ˆ๋‹ค.
13:22
About a year ago, I went to Fukushima
279
802108
2497
๋Œ€๋žต ์ผ ๋…„ ์ „์—, ํ›„์ฟ ์‹œ๋งˆ ์ƒํ™ฉ์„ ํŒŒ์•…ํ•˜๊ธฐ ์œ„ํ•ด ๋‹ค๋…€์™”๋Š”๋ฐ์š”.
13:24
to see what the situation was there,
280
804629
2031
13:26
and there's just a huge need
281
806684
1877
๊ทธ๊ณณ์—๋Š”, ์˜ค์—ผ๋œ ์žฅ์†Œ์— ํˆฌ์ž…ํ•˜์—ฌ
13:28
for machines that can go into some of the dirty places
282
808585
3338
๋ณด์ˆ˜ํ•˜๋Š” ๊ฒƒ์„ ๋„์šธ ๊ธฐ๊ณ„๋“ค์ด
13:31
and help remediate that.
283
811947
1968
์ ˆ์‹คํžˆ ํ•„์š”ํ–ˆ์Šต๋‹ˆ๋‹ค.
13:34
I think it won't be too long until we have robots like this in our homes,
284
814528
4599
์ด๋Ÿฐ ๋กœ๋ด‡๋“ค์„ ์ง‘์—์„œ ์‚ฌ์šฉํ•˜๊ธฐ๊นŒ์ง€ ๋งŽ์€ ์‹œ๊ฐ„์ด ๊ฑธ๋ฆฌ์ง€ ์•Š์„ ๊ฑฐ๋ผ๊ณ  ์ƒ๊ฐํ•˜๊ณ 
13:39
and one of the big needs is to take care of the aging
285
819151
5321
๊ฐ€์žฅ ์ˆ˜์š”๊ฐ€ ํฐ ๋ถ„์•ผ๋Š” ๋…ธ์ธ๋“ค๊ณผ ํ™˜์ž๋ฅผ
13:44
and invalids.
286
824496
1366
๊ฐ„๋ณ‘ํ•˜๋Š” ์ผ์ž…๋‹ˆ๋‹ค.
13:45
I think that it won't be too long till we're using robots
287
825886
3989
์šฐ๋ฆฌ์˜ ๋ถ€๋ชจ๋‹˜์„ ๊ฐ„๋ณ‘ํ•˜๋Š”๋ฐ ๋กœ๋ด‡์„ ์ด์šฉํ•  ๋‚ ์ด ๋ฉ€์ง€ ์•Š์•˜์Šต๋‹ˆ๋‹ค.
13:49
to help take care of our parents,
288
829899
2462
๋˜๋Š”, ๊ฐ€๋Šฅ์„ฑ์ด ๋” ๋†’์€ ๊ฒƒ์€
13:52
or probably more likely, have our children help take care of us.
289
832385
4415
์•„์ด๋“ค์ด ์šฐ๋ฆฌ๋ฅผ ๊ฐ„๋ณ‘ํ•˜๋Š”๋ฐ ๋กœ๋ด‡์˜ ๋„์›€์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์„ ๊ฒ๋‹ˆ๋‹ค.
13:57
And there's a bunch of other things.
290
837721
1750
๊ทธ๋ฆฌ๊ณ  ์ˆ˜๋งŽ์€ ๋‹ค๋ฅธ ์ผ๋“ค์ด ์žˆ์Šต๋‹ˆ๋‹ค.
13:59
I think the sky's the limit.
291
839495
1366
์ œ ์ƒ๊ฐ์—” ํ•ญ๊ณต ๋ถ„์•ผ์—๋Š” ํ•œ๊ณ„๊ฐ€ ์žˆ๋Š” ๊ฒƒ ๊ฐ™์Šต๋‹ˆ๋‹ค.
14:00
Many of the ideas we haven't thought of yet,
292
840885
2258
์ €ํฌ๊ฐ€ ์•„์ง ์ƒ๊ฐํ•˜์ง€ ๋ชปํ•œ ๋งŽ์€ ์•„์ด๋””์–ด๋“ค
14:03
and people like you will help us think of new applications.
293
843167
3595
์ƒˆ๋กœ์šด ์ ์šฉ๋ฐฉ๋ฒ•์„ ์ƒ๊ฐํ•ด ๋‚ด๋Š”๋ฐ ์—ฌ๋Ÿฌ๋ถ„๊ป˜์„œ ๋„์›€์„ ์ฃผ์‹ค ์ˆ˜ ์žˆ์„ ๊ฒ๋‹ˆ๋‹ค.
14:06
HW: So what about the dark side?
294
846786
1587
ํ—ฌ๋ Œ ์›”ํ„ฐ์Šค: ์–ด๋‘์šด ์ธก๋ฉด์€ ์–ด๋–ค๊ฐ€์š”?
14:08
What about the military?
295
848397
1833
๊ตฐ์‚ฌ์šฉ ๋กœ๋ด‡์€์š”?
14:10
Are they interested?
296
850254
1503
๊ด€์‹ฌ ์žˆ์œผ์‹ ๊ฐ€์š”?
14:12
MR: Sure, the military has been a big funder of robotics.
297
852441
3634
๋งˆํฌ ๋ ˆ์ด๋ฒˆํŠธ: ๋ฌผ๋ก ์ด์ฃ , ๊ตฐ๋Œ€์—์„œ ๋ง‰๋Œ€ํ•œ ์ž๊ธˆ์„ ์ œ๊ณตํ•ด ์™”์Šต๋‹ˆ๋‹ค.
14:16
I don't think the military is the dark side myself,
298
856099
4202
๊ตฐ์‚ฌ์šฉ ๋กœ๋ด‡์ด ์–ด๋‘์šด ์ธก๋ฉด์ด๋ผ๊ณ  ์ƒ๊ฐํ•˜์ง€ ์•Š์Šต๋‹ˆ๋‹ค.
14:20
but I think, as with all advanced technology,
299
860325
3871
์ด๊ฒƒ ๋˜ํ•œ ๊ธฐ์ˆ ์˜ ๋ฐœ์ „ ์ค‘ ํ•œ ๊ฐ€์ง€๋กœ
14:24
it can be used for all kinds of things.
300
864220
2047
๋ชจ๋“  ์ข…๋ฅ˜์˜ ์ผ์— ์‚ฌ์šฉ ๋  ์ˆ˜ ์žˆ๋Š” ๊ฒƒ์ด์ฃ .
14:26
HW: Awesome. Thank you so much.
301
866291
1641
ํ—ฌ๋ Œ ์›”ํ„ฐ์Šค: ๋ฉ‹์ง€๋„ค์š”. ๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.
14:27
MR: OK, you're welcome.
302
867956
1405
๋งˆํฌ ๋ ˆ์ด๋ฒˆํŠธ: ๋ณ„๋ง์”€์„์š”.
๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.
14:29
Thank you.
303
869385
1152
(๋ฐ•์ˆ˜)
14:30
(Applause)
304
870561
1586
์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