TEDxBerkeley
Ken Goldberg: 4 lessons from robots about being human
Ken Goldberg: Četiri lekcije koje nas roboti mogu naučiti kako bismo postali bolji ljudi
Filmed:
Readability: 4.6
387,467 views
Što su roboti učestaliji u našem svakodnevnom životu, to smo više prisiljeni preispitati sebe kao ljude. Na TEDxBerkeleyju, Ken Goldberg predstavlja četiri vrlo ljudske lekcije koje je naučio iz rada s robotima. (Snimljeno na TEDxBerkeley)
Ken Goldberg - Roboticist
Ken Goldberg works reflect the intersection of robotics, social media, and art. Full bio
Ken Goldberg works reflect the intersection of robotics, social media, and art. Full bio
Double-click the English transcript below to play the video.
00:16
I know this is going to sound strange,
0
577
2475
Znam da će ovo zvučati čudno,
00:18
but I think robots can inspire us
1
3052
3294
ali mislim da nas roboti mogu nadahnuti
00:22
to be better humans.
2
6346
2388
da postanemo bolji ljudi.
00:24
See, I grew up in Bethlehem, Pennsylvania,
3
8734
3629
Vidite, odrastao sam u Bethlehemu, u Pennsylvaniji,
00:28
the home of Bethlehem Steel.
4
12363
2321
domu tvrtke Bethlehem Steel.
00:30
My father was an engineer,
5
14684
2079
Moj otac je bio inženjer
00:32
and when I was growing up, he would teach me
6
16763
2851
i dok sam odrastao, učio me
00:35
how things worked.
7
19614
1159
kako stvari rade.
00:36
We would build projects together,
8
20773
2815
Radili smo na zajedničkim projektima,
00:39
like model rockets and slot cars.
9
23588
2792
poput modela raketa i autića za utrkivanje.
00:42
Here's the go-kart that we built together.
10
26380
3284
Ovo je go-kart koji smo zajedno izradili.
00:45
That's me behind the wheel,
11
29664
2219
To sam ja za volanom,
00:47
with my sister and my best friend at the time,
12
31883
3819
sa svojom sestrom i tadašnjim najboljim prijateljem.
00:51
and one day,
13
35702
2123
Jednog dana,
00:53
he came home, when I was about 10 years old,
14
37825
3107
otac je došao kući, kad sam imao 10-ak godina,
00:56
and at the dinner table, he announced
15
40932
2304
i za večerom objavio
00:59
that for our next project, we were going to build a robot.
16
43236
6438
da ćemo za sljedeći projekt izgraditi robota.
01:05
A robot.
17
49674
1109
Robota.
01:06
Now, I was thrilled about this,
18
50783
2252
Naravno da sam bio ushićen zbog toga
01:08
because at school,
19
53035
1590
jer je u školi bio
01:10
there was a bully named Kevin,
20
54625
2075
nasilnik imenom Kevin,
01:12
and he was picking on me
21
56700
2246
koji me maltretirao
01:14
because I was the only Jewish kid in class.
22
58946
2414
jer sam bio jedini Židov u razredu.
01:17
So I couldn't wait to get started to work on this
23
61360
2813
Jedva sam čekao da počnemo raditi na tome
01:20
so I could introduce Kevin to my robot. (Laughter)
24
64173
3822
kako bih mogao upoznati Kevina
sa svojim robotom. (Smijeh)
sa svojim robotom. (Smijeh)
01:23
(Robot noises)
25
67995
11063
(Zvuci robota)
01:34
But that wasn't the kind of robot my dad had in mind.
26
79058
4875
No, moj otac nije na umu imao takvog robota.
01:39
See, he owned a chromium plating company,
27
83933
3728
On je imao tvrtku za kromirane oplate,
01:43
and they had to move
28
87661
2176
u kojoj su morali micati
01:45
heavy steel parts between tanks of chemicals,
29
89837
3096
teške čelične dijelove između spremnika s kemikalijama,
01:48
and so he needed an industrial robot like this
30
92933
3790
i trebao je ovakvog industrijskog robota
01:52
that could basically do the heavy lifting.
31
96723
3099
koji bi uglavnom mogao dizati te teške stvari.
01:55
But my dad didn't get the kind of robot he wanted, either.
32
99822
3905
No, ni tata nije dobio robota kakvog je htio.
01:59
He and I worked on it for several years,
33
103727
2597
On i ja radili smo na njemu nekoliko godina,
02:02
but it was the 1970s,
34
106324
1978
ali to su bile 1970-e
02:04
and the technology that was available to amateurs
35
108302
2526
i tehnologija koja bi bila dostupna amaterima
02:06
just wasn't there yet.
36
110828
2657
jednostavno nije postojala.
02:09
So Dad continued to do this kind of work by hand,
37
113485
3745
Tata je nastavio raditi takve poslove ručno
02:13
and a few years later,
38
117230
2275
i par godina kasnije
02:15
he was diagnosed with cancer.
39
119505
4139
dijagnosticirali su mu rak.
02:19
You see, what the robot we were trying to build
40
123644
3305
Robot kojeg smo pokušavali napraviti
02:22
was telling him was not about doing the heavy lifting.
41
126949
3267
nije mu pomagao pri dizanju teških stvari,
02:26
It was a warning about his exposure to the toxic chemicals.
42
130216
4308
već ga je upozoravao na izloženost otrovnim kemikalijama.
02:30
He didn't recognize that at the time,
43
134524
2977
On to tada nije prepoznao
02:33
and he contracted leukemia,
44
137501
2139
i dobio je leukemiju
02:35
and he died at the age of 45.
45
139640
3222
i umro u 45. godini života.
02:38
I was devastated by this,
46
142862
2841
To me shrvalo,
02:41
and I never forgot the robot that he and I tried to build.
47
145703
4575
ali nikad nisam zaboravio robota
kojeg smo pokušali izraditi.
kojeg smo pokušali izraditi.
02:46
When I was in college, I decided to study engineering, like him.
48
150278
4311
Odlučio sam studirati inženjerstvo, poput oca.
02:50
And I went to Carnegie Mellon, and I earned my PhD in robotics.
49
154589
4946
Studirao sam na sveučilištu Carnegie Mellon
i doktrorirao robotiku.
i doktrorirao robotiku.
02:55
I've been studying robots ever since.
50
159535
3094
Od tada proučavam robote.
02:58
So what I'd like to tell you about
51
162629
1638
Htio bih vam, dakle, govoriti
03:00
are four robot projects
52
164267
2714
o četiri projekta s robotima
03:02
and how they've inspired me to be a better human.
53
166981
7044
i o tome kako su me oni nadahnuli da postanem bolji čovjek.
03:09
By 1993, I was a young professor at USC,
54
174025
5749
1993. godine bio sam mladi profesor na USC-u,
03:15
and I was just building up my own robotics lab,
55
179774
3037
osnivao sam vlastiti laboratorij za robotiku
03:18
and this was the year that the World Wide Web came out.
56
182811
3585
a te se godine pojavio i World Wide Web.
03:22
And I remember my students were the ones
57
186396
1176
Sjećam se da su mi moji studenti
03:23
who told me about it,
58
187572
1704
rekli za to
03:25
and we would -- we were just amazed.
59
189276
2619
i bili smo -- bili smo zapanjeni.
03:27
We started playing with this, and that afternoon,
60
191895
3434
Počeli smo se igrati time i tog smo poslijepodneva
03:31
we realized that we could use this new, universal interface
61
195329
3853
shvatili da preko tog novog, univerzalnog sučelja
03:35
to allow anyone in the world
62
199182
2543
možemo bilo kome u svijetu omogućiti
03:37
to operate the robot in our lab.
63
201725
3048
da upravlja robotom u našem laboratoriju.
03:40
So, rather than have it fight or do industrial work,
64
204773
5708
Umjesto da se bori ili radi industrijske poslove,
03:46
we decided to build a planter,
65
210481
2486
odlučili smo izraditi sadilicu,
03:48
put the robot into the center of it,
66
212967
1976
i staviti robota u središte.
03:50
and we called it the Telegarden.
67
214943
2353
To smo nazvali Telegarden.
03:53
And we had put a camera in the gripper of the hand
68
217296
3603
Stavili smo kamere na hvataljke ruke robota
03:56
of the robot, and we wrote some special scripts
69
220899
2709
i napisali posebne upute i softver
03:59
and software so that anyone in the world could come in
70
223608
3161
kako bi bilo tko u svijetu mogao doći
04:02
and by clicking on the screen
71
226769
2329
i klikanjem po ekranu
04:04
they could move the robot around
72
229098
2173
micati robota uokolo
04:07
and visit the garden.
73
231271
2316
te posjetiti vrt.
04:09
But we also allowed, set up some other software
74
233587
3620
Također smo nadogradili drugim softverom
04:13
that lets you participate and help us water the garden
75
237207
3419
koji vam omogućava da sudjelujete
i pomognete nam u zalijevanju vrta
i pomognete nam u zalijevanju vrta
04:16
remotely, and if you water it a few times,
76
240626
3045
daljinskim upravljanjem. Kad ga zalijete nekoliko puta,
04:19
we'd give you your own seed to plant.
77
243671
3585
dali bismo vam vlastito sjeme koje možete zasaditi.
04:23
Now, this was a project, an engineering project,
78
247256
3271
To je bio inženjerski projekt
04:26
and we published some papers on the design,
79
250527
2776
pa smo objavili nekoliko radova o oblikovanju,
04:29
the system design of it, but we also thought of it
80
253303
2249
o oblikovanju sustava, ali smo ga smatrali
04:31
as an art installation.
81
255552
3086
i umjetničkom instalacijom.
04:34
It was invited, after the first year,
82
258638
2173
Nakon prve godine pozvao nas je
04:36
by the Ars Electronica Museum in Austria
83
260811
3044
muzej Ars Electronica iz Austrije
04:39
to have it installed in their lobby,
84
263855
3000
da ga postavimo u njihovo predvorje.
04:42
and I'm happy to say it remained online there,
85
266855
2418
Sretan sam što mogu reći da je ondje bio online
04:45
24 hours a day, for almost nine years.
86
269273
4983
24 sata na dan gotovo devet godina.
04:50
That robot was operated by more people
87
274256
3799
Tim je robotom upravljalo više ljudi
04:53
than any other robot in history.
88
278055
3086
nego ikojim drugim robotom u povijesti.
04:57
Now, one day,
89
281141
1554
Jednog dana,
04:58
I got a call out of the blue
90
282695
2317
dobio sam neočekivan poziv
05:00
from a student,
91
285012
2015
od jednog studenta
05:02
who asked a very simple but profound question.
92
287027
4670
koji me pitao vrlo jednostavno, ali duboko pitanje.
05:07
He said, "Is the robot real?"
93
291697
4538
Rekao je: "Postoji li stvarno taj robot?"
05:12
Now, everyone else had assumed it was,
94
296235
2765
Svi drugi pretpostavljali su da postoji,
05:14
and we knew it was because we were working with it.
95
299000
2331
a mi smo to znali jer smo na njemu radili.
05:17
But I knew what he meant,
96
301331
1540
No, znao sam na što je mislio
05:18
because it would be possible to take a bunch of pictures
97
302871
2593
jer bilo bi moguće uzeti mnoštvo slika cvjetova iz vrta
05:21
of flowers in a garden and then, basically, index them
98
305464
4361
i onda ih samo ubaciti
05:25
in a computer system such that it would appear
99
309825
2229
u računalni sustav kako bi izgledalo
05:27
that there was a real robot when there wasn't.
100
312054
3074
kao da postoji robot, a zapravo ga nema.
05:31
And the more I thought about it, I couldn't think
101
315128
1241
Što sam više razmišljao o tome, nisam mogao smisliti
05:32
of a good answer for how he could tell the difference.
102
316369
3551
dobar odgovor kako vidjeti razliku.
05:35
This was right about the time that I was offered a position
103
319920
2887
To se dogodilo otprilike u vrijeme
kad mi je bilo ponuđen posao
kad mi je bilo ponuđen posao
05:38
here at Berkeley,
104
322807
2073
ovdje u Berkeleyju.
05:40
and when I got here, I looked up Hubert Dreyfus,
105
324880
3552
Kad sam stigao ovamo, potražio sam Huberta Dreyfusa,
05:44
who's a world-renowned professor of philosophy,
106
328432
3665
svjetski poznatog profesora filozofije.
05:47
and I talked with him about this, and he said,
107
332097
2374
Razgovarao sam s njime o tome i rekao je:
05:50
"This is one of the oldest and most central problems
108
334471
3560
"To je jedan od najstarijih i najvećih problema
05:53
in philosophy. It goes back to the Skeptics,
109
338031
3602
u filozofiji. Postoji još od Skeptika,
05:57
and up through Descartes.
110
341633
1960
pa sve do Descartesa.
05:59
It's the issue of epistemology,
111
343593
3170
To je problem epistemologije,
06:02
the study of how do we know that something is true."
112
346763
3750
proučavanja toga kako znamo da je nešto istina."
06:06
So he and I started working together,
113
350513
2223
Tako smo počeli raditi zajedno
06:08
and we coined a new term: telepistemology,
114
352736
3041
i skovali smo novi termin: telepistemologiju,
06:11
the study of knowledge at a distance.
115
355777
3526
proučavanje znanja na daljinu.
06:15
We invited leading artists, engineers,
116
359303
2752
Pozvali smo vodeće umjetnike, inženjere i filozofe
06:17
and philosophers to write essays about this,
117
362055
3064
da napišu eseje o tome,
06:21
and the results, the results are collected in this book
118
365119
2340
a rezultati su skupljeni u ovoj knjizi
06:23
from MIT Press.
119
367459
2621
u izdanju MIT Pressa.
06:25
So thanks to this student who questioned
120
370080
2332
Zahvaljujući tom studentu koji je posumnjao
06:28
what everyone else had assumed to be true,
121
372412
2803
u ono za što su svi drugi pretpostavili da je istina,
06:31
this project taught me an important lesson about life,
122
375215
4208
taj me projekt naučio važnu lekciju o životu,
06:35
which is to always question assumptions.
123
379423
4073
a to je da uvijek treba preispitivati pretpostavke.
06:39
Now, the second project I'll tell you about
124
383496
2648
Drugi projekt o kojem ću vam govoriti
06:42
grew out of the Telegarden.
125
386144
1879
proizašao je iz Telegardena.
06:43
As it was operating, my students and I were very interested
126
388023
2576
Dok je radio, moje studente i mene zanimalo je
06:46
in how people were interacting with each other
127
390599
2762
u kakvoj su ljudi bili interakciji jedni s drugima
06:49
and what they were doing with the garden.
128
393361
1621
i što su radili s vrtom.
06:50
So we started thinking, what if the robot could leave
129
394982
2262
Počeli smo razmišljati što bi bilo
kad bi robot mogao izići iz vrta
kad bi robot mogao izići iz vrta
06:53
the garden and go out into some other
130
397244
2083
i otići u neko drugo
06:55
interesting environment?
131
399327
1992
zanimljivo okruženje?
06:57
Like, for example, what if it could go to a dinner party
132
401319
2179
Na primjer, što kad bi mogao otići na večeru
06:59
at the White House? (Laughter)
133
403498
5198
u Bijelu kuću? (Smijeh)
07:04
So, because we were interested more in the system design
134
408696
2841
Budući da su nas oblikovanje sustava
07:07
and the user interface than in the hardware,
135
411537
3286
i korisničko sučelje zanimali više nego hardver,
07:10
we decided that, rather than have
136
414823
2034
odlučili smo,
07:12
a robot replace the human to go to the party,
137
416857
3678
umjesto da robot zamijeni čovjeka na večeri,
07:16
we'd have a human replace the robot.
138
420535
2843
imati čovjeka da zamijeni robota.
07:19
We called it the Tele-Actor.
139
423378
2600
Nazvali smo ga Tele-Actor.
07:21
We got a human,
140
425978
2032
Uzeli smo čovjeka,
07:23
someone who's very outgoing and gregarious,
141
428010
3007
nekoga tko je vrlo otvoren i društven.
07:26
and she was outfitted with a helmet
142
431017
3142
Bila je opremljena kacigom
07:30
with various equipment, cameras and microphones,
143
434159
2570
s raznom opremom, kamerama i mikrofonima,
07:32
and then a backpack with wireless Internet connection,
144
436729
3740
te ruksakom s bežičnim pristupom Internetu.
07:36
and the idea was that she could go into a remote and
145
440469
3359
Ideja je bila da bi mogla otići u udaljenu,
07:39
interesting environment, and then over the Internet,
146
443828
3815
zanimljivu okolinu, a ljudi bi, preko Interneta,
07:43
people could experience what she was experiencing,
147
447643
3151
mogli doživjeti isto što i ona,
07:46
so they could see what she was seeing,
148
450794
2937
mogli bi vidjeti što ona vidi.
07:49
but then, more importantly, they could participate
149
453731
3307
Što je još važnije, mogli bi sudjelovati
07:52
by interacting with each other
150
457038
2948
međusobnom interakcijom
07:55
and coming up with ideas about what she should do next
151
459986
3705
i davanjem ideja što bi sljedeće mogla učiniti
07:59
and where she should go,
152
463691
2216
i kamo da ide
08:01
and then conveying those to the Tele-Actor.
153
465907
3162
te bi to prenijeli Tele-Actoru.
08:04
So we got a chance to take the Tele-Actor
154
469069
2445
Dobili smo priliku da predstavimo Tele-Actora
08:07
to the Webby Awards in San Francisco,
155
471514
3615
na Webby Awards u San Franciscu.
08:11
and that year, Sam Donaldson was the host.
156
475129
4111
Te je godine domaćin bio Sam Donaldson.
08:15
Just before the curtain went up, I had about 30 seconds
157
479240
3642
Malo prije no što se digao zastor, imao sam oko 30 sekundi
08:18
to explain to Mr. Donaldson what we were gonna do,
158
482882
4458
da objasnim g. Donaldsonu što ćemo učiniti.
08:23
and I said, "The Tele-Actor
159
487340
1864
Rekao sam:
08:25
is going to be joining you on stage,
160
489204
2456
"Tele-Actor će biti s vama na pozornici.
08:27
and this is a new experimental project,
161
491660
2198
To je novi pokusni projekt,
08:29
and people are watching her on their screens,
162
493858
2625
ljudi je gledaju na svojim ekranima.
08:32
and she's got -- there's cameras involved and there's
163
496483
2305
Ima -- tu su kamere i mikrofoni,
08:34
microphones and she's got an earbud in her ear,
164
498788
2911
a ima i bubu u uhu.
08:37
and people over the network are giving her advice
165
501699
1447
Ljudi u mreži daju joj savjete
08:39
about what to do next."
166
503146
1368
što da sljedeće napravi."
08:40
And he said, "Wait a second,
167
504514
3209
On je rekao: "Čekaj malo,
08:43
that's what I do." (Laughter)
168
507723
6375
to je moj posao." (Smijeh)
08:49
So he loved the concept,
169
514098
1931
Svidjela mu se ideja,
08:51
and when the Tele-Actor walked onstage,
170
516029
2340
i kad je Tele-Actor stupio na pozornicu,
08:54
she walked right up to him, and she gave him a big kiss
171
518369
2821
otišla je do njega i dala mu velik poljubac
08:57
right on the lips. (Laughter)
172
521190
3106
ravno u usta. (Smijeh)
09:00
We were totally surprised.
173
524296
1131
Bili smo potpuno iznenađeni.
09:01
We had no idea that would happen.
174
525427
2017
Nismo imali pojma da će se to dogoditi.
09:03
And he was great. He just gave her a big hug in return,
175
527444
2692
Bio je odličan. Uzvratio joj je velikim zagrljajem
09:06
and it worked out great.
176
530136
1769
i ispalo je sjajno.
09:07
But that night, as we were packing up,
177
531905
2064
No, te noći, dok smo se pakirali,
09:09
I asked the Tele-Actor, how did the Tele-Directors
178
533969
3608
pitao sam Tele-Actora kako su Tele-Direktori odlučili
09:13
decide that they would give a kiss to Sam Donaldson?
179
537577
5558
dati poljubac Samu Donaldsonu?
09:19
And she said they hadn't.
180
543135
2212
Rekla je da nisu to odlučili.
09:21
She said, when she was just about to walk on stage,
181
545347
2434
Rekla je da, baš kad je trebala stupiti na pozornicu,
09:23
the Tele-Directors were still trying to agree on what to do,
182
547781
2312
Tele-Direktori su se još pokušavali dogovoriti što da učine,
09:25
and so she just walked on stage and did
183
550093
2407
pa je tako samo ušla na pozornicu
09:28
what felt most natural. (Laughter)
184
552500
5522
i učinila ono što joj je bilo najprirodnije. (Smijeh)
09:33
So, the success of the Tele-Actor that night
185
558022
3670
Dakle, za uspjeh Tele-Actora te noći
09:37
was due to the fact that she was a wonderful actor.
186
561692
4373
zaslužno je to što je ona odlična glumica.
09:41
She knew when to trust her instincts,
187
566065
2357
Znala je kada treba vjerovati instinktima.
09:44
and so that project taught me another lesson about life,
188
568422
3864
Tako me taj projekt naučio još jednu lekciju o životu:
09:48
which is that, when in doubt, improvise. (Laughter)
189
572286
6379
kad ne znaš što bi, improviziraj. (Smijeh)
09:54
Now, the third project grew out of
190
578665
3080
Treći projekt proizašao je
09:57
my experience when my father was in the hospital.
191
581745
4893
iz mog iskustva kad mi je otac bio u bolnici.
10:02
He was undergoing a treatment,
192
586638
2240
Bio je na liječenju,
10:04
chemotherapy treatments, and there's a related treatment
193
588878
3633
na kemoterapiji, a postoji i slična terapija,
10:08
called brachytherapy, where tiny, radioactive seeds
194
592511
5048
brahiterapija, u kojoj se sitne radioaktivne čestice
10:13
are placed into the body to treat cancerous tumors.
195
597559
4211
stavljaju u tijelo kako bi izliječile kancerogene tumore.
10:17
And the way it's done, as you can see here,
196
601770
2097
To se izvodi, kao što vidite ovdje,
10:19
is that surgeons insert needles into the body
197
603867
4391
tako da doktori ubadaju igle po tijelu
10:24
to deliver the seeds, and all this,
198
608258
2592
kako bi doveli čestice i sve to,
10:26
all these needles are inserted in parallel,
199
610850
3433
sve te igle postavljene su paralelno
10:30
so it's very common that some of the needles
200
614283
2975
pa vrlo često neke od igala
10:33
penetrate sensitive organs, and as a result,
201
617258
4817
probiju osjetljive organe
10:37
the needles damage these organs, cause damage
202
622075
5063
i tako oštećuju organe i prouzročuju štetu
10:43
which leads to trauma and side effects.
203
627138
3487
koja dovodi do traume i nuspojava.
10:46
So my students and I wondered, what if we could
204
630625
2500
Tako smo se moji studenti i ja pitali, što kad bismo mogli
10:49
modify the system
205
633125
3485
promijeniti sustav
10:52
so that the needles could come in at different angles?
206
636610
3785
tako da igle mogu ulaziti pod različitim kutovima?
10:56
So we simulated this, and we developed some
207
640395
2777
Simulirali smo to i razvili
10:59
optimization algorithms and we simulated this,
208
643172
2589
nekoliko optimizacijskih algoritama
11:01
and we were able to show that we are able to avoid
209
645761
2277
te smo uspjeli pokazati da možemo izbjeći
11:03
the delicate organs and yet still achieve the coverage
210
648038
3767
osjetljive organe, a ipak postići
11:07
of the tumors with the radiation.
211
651805
3508
pokrivenost tumora radijacijom.
11:11
So now, we're working with doctors at UCSF
212
655313
3498
Trenutno radimo s liječnicima na UCSF-u
11:14
and engineers at Johns Hopkins
213
658811
2696
i inženjerima iz Johns Hopkinsa
11:17
and we're building a robot that has a number of,
214
661507
3582
i gradimo robota koji ima brojne --
11:20
it's a specialized design with different joints that can allow
215
665089
3257
specijaliziranog je dizajna, sa zglobovima koji omogućuju
11:24
the needles to come in at an infinite variety of angles,
216
668346
4258
da igle budu ubodene pod beskrajno mnogo kutova.
11:28
and as you can see here, they can avoid delicate organs
217
672604
3166
Kao što možete ovdje vidjeti, izbjeći će osjetljive organe,
11:31
and still reach the targets they're aiming for.
218
675770
4138
a opet doseći ciljana mjesta.
11:35
So, by questioning this assumption that all the needles
219
679908
3317
Preispitivanjem pretpostavke da igle
11:39
have to be parallel, this project also taught me
220
683225
2945
moraju biti postavljene paralelno, taj me projekt naučio
11:42
an important lesson: When in doubt --
221
686170
3300
važnu lekciju: Kad ne znaš što bi --
11:45
When your path is blocked, pivot.
222
689470
4367
Kada ti je put zakrčen, zakreni se.
11:49
And the last project also has to do with medical robotics.
223
693837
4401
Zadnji projekt također ima veze s medicinskom robotikom.
11:54
And this is something that's grown out of a system called
224
698238
4040
Ovo je proizašlo iz sustava
11:58
the da Vinci surgical robot,
225
702278
3588
koji se zove da Vincijev kirurški robot,
12:01
and this is a commercially available device.
226
705866
2468
koji je komercijalno dostupan uređaj.
12:04
It's being used in over 2,000 hospitals around the world,
227
708334
3332
Koristi ga više od 2000 bolnica diljem svijeta,
12:07
and the idea is it allows the surgeon
228
711666
2528
a omogućuje kirurgu
12:10
to operate comfortably in his own coordinate frame,
229
714194
4249
da udobno djeluje u svojem vlastitom koordinatnom okviru.
12:14
but many of the subtasks in surgery
230
718443
4991
No, mnogi podzadaci u kirurgiji
12:19
are very routine and tedious, like suturing,
231
723434
3047
vrlo su rutinski i dosadni, poput šivanja,
12:22
and currently, all of these are performed
232
726481
2365
i trenutno se svi provode
12:24
under the specific and immediate control of the surgeon,
233
728846
4420
pod posebnom i neposrednom kontrolom kirurga
12:29
so the surgeon becomes fatigued over time.
234
733266
2658
pa se kirurg s vremenom umara.
12:31
And we've been wondering,
235
735924
1295
Razmišljali smo,
12:33
what if we could program the robot
236
737219
2265
što kad bismo mogli programirati robota
12:35
to perform some of these subtasks,
237
739484
2487
da obavlja neke od tih podzadataka
12:37
and thereby free the surgeons to focus
238
741971
1720
kako bi se kirurzi mogli slobodno koncentrirati
12:39
on the more complicated parts of the surgery,
239
743691
2656
na kompliciranije dijelove operacije?
12:42
and also cut down on the time that the surgery would take
240
746347
3248
I bi li operacije mogle biti kraće
12:45
if we could get the robot to do them a little bit faster?
241
749595
3023
kad bi robot te zadatke mogao obavljati malo brže?
12:48
Now, it's hard to program a robot to do delicate things
242
752618
2434
Teško je programirati robota da radi takve osjetljive stvari,
12:50
like this, but it turns out my colleague, Pieter Abbeel,
243
755052
4079
ali doznao sam da je moj kolega Pieter Abbeel,
12:55
who's here at Berkeley, has develeloped
244
759131
2416
koji je ovdje na Berkeleyju,
12:57
a new set of techniques for teaching robots from example.
245
761547
5623
razvio nove tehnike kojima uči robote na primjerima.
13:03
So he's gotten robots to fly helicopters,
246
767170
2767
Tako je imao robote koji upravljaju helikopterima,
13:05
do incredibly interesting, beautiful acrobatics,
247
769937
3104
izvode nevjerojatno zanimljive, prekrasne akrobacije
13:08
by watching human experts fly them.
248
773041
2719
gledajući ljudske majstore kako ih izvode.
13:11
So we got one of these robots.
249
775760
2588
Dobili smo jednoga od tih robota.
13:14
We started working with Pieter and his students,
250
778348
2182
Počeli smo raditi s Pieterom i njegovim studentima
13:16
and we asked a surgeon to perform
251
780530
2663
i zamolili smo jednoga kirurga da izvede zadatak
13:19
a task, and what we do is we, with the robot,
252
783193
4451
a mi tada s robotom,
13:23
so what we're doing is asking the robot,
253
787644
2063
tražimo od robota --
13:25
the surgeon to perform the task,
254
789707
1278
kirurg treba izvesti zadatak,
13:26
and we record the motions of the robot.
255
790985
2272
a mi snimamo pokrete robota.
13:29
So here's an example. I'll use a figure eight,
256
793257
2128
Evo primjera. Uzet ću oblik osmice,
13:31
tracing out a figure eight as an example.
257
795385
2240
pratit ću oblik osmice za primjer.
13:33
So here's what it looks like when the robot,
258
797625
3630
Ovako to izgleda kad robot --
13:37
this is what the robot's path looks like,
259
801255
2317
ovako izgleda robotov put,
13:39
those three examples.
260
803572
1174
ta tri primjera.
13:40
Now, those are much better than what a novice
261
804746
2462
To je mnogo bolje nego što bi početnik kao ja
13:43
like I could do, but they're still jerky and imprecise.
262
807208
4657
mogao napraviti, ali još uvijek je grčevito i neprecizno.
13:47
So we record all these examples, the data,
263
811865
2072
Snimili smo sve te primjere, podatke,
13:49
and then we go through a sequence of steps.
264
813937
3712
i prošli kroz slijed koraka.
13:53
First, we used a technique called dynamic time warping
265
817649
3632
Prvo smo koristili tehniku dinamičkog savijanja vremena
13:57
from speech recognition, and this allows us to
266
821281
2182
iz prepoznavanja govora, i to nam je omogućilo
13:59
temporally align all of the examples,
267
823463
2840
da privremeno poravnamo sve primjere.
14:02
and then we apply Kalman filtering,
268
826303
2929
Zatim izvršimo Kalmanovo filtriranje,
14:05
a technique from control theory, that allows us
269
829232
2983
tehniku iz teorije kontrole, koja nam omogućava
14:08
to statistically analyze all the noise
270
832215
2672
da statistički analiziramo buku
14:10
and extract the desired trajectory that underlies them.
271
834887
6183
i izlučimo željenu putanju koja joj je temelj.
14:16
Now, so what we're doing is that we take those
272
841070
1994
Zatim uzmemo te ljudske demonstracije,
14:18
human demonstrations, they're all noisy and imperfect,
273
843064
2023
bučne i nesavršene,
14:20
and we extract from them an inferred task trajectory
274
845087
3091
i izlučimo iz njih pretpostavljenu putanju zadatka
14:24
and control sequence for the robot.
275
848178
3003
i kontrolni slijed za robota.
14:27
We then execute that on the robot,
276
851181
2184
To primijenimo na robotu,
14:29
we observe what happens,
277
853365
2172
gledamo što se događa,
14:31
then we adjust the controls using a sequence of techniques
278
855537
2662
te prilagodimo kontrole koristeći slijed tehnika
14:34
called iterative learning.
279
858199
2930
koji se zove iterativno učenje.
14:37
Then what we do is, we increase the velocity a little bit.
280
861129
3977
Zatim malo povećamo brzinu.
14:41
We observe the results, adjust the controls again,
281
865106
3563
Promatramo rezultate, ponovno prilagodimo kontrole
14:44
and observe what happens.
282
868669
2522
i promatramo što se događa.
14:47
And we go through this several rounds.
283
871191
2136
Nekoliko puta prolazimo kroz taj postupak.
14:49
And here's the result.
284
873327
1356
Evo rezultata.
14:50
That's the inferred task trajectory,
285
874683
1845
To je pretpostavljena putanja zadatka,
14:52
and here's the robot moving at the speed of the human.
286
876528
3463
a ovo je robot koji se miče ljudskom brzinom.
14:55
Here's four times the speed of the human.
287
879991
2442
Ovo je četiri puta brže.
14:58
Here's seven times.
288
882433
2571
Ovdje sedam puta.
15:00
And here's the robot operating at 10 times
289
885004
3637
I ovdje je robot koji radi 10 puta brže
15:04
the speed of the human.
290
888641
2200
od brzine čovjeka.
15:06
So we're able to get a robot to perform a delicate task,
291
890841
2950
Dakle, robot može izvršiti osjetljiv zadatak
15:09
like a surgical subtask,
292
893791
3224
poput kirurškog podzadatka
15:12
at 10 times the speed of a human.
293
897015
3247
u brzini deset puta većoj od čovjekove.
15:16
So this project also, because of its involved practicing
294
900262
4223
Ovaj projekt također, budući da uključuje vježbanje
15:20
and learning, doing something over and over again,
295
904485
2173
i učenje, neprestano ponavljanje nečega,
15:22
this project also has a lesson, which is,
296
906658
2757
iz ovog projekta također možemo naučiti jednu lekciju:
15:25
if you want to do something well,
297
909415
3126
ako želiš nešto učiniti dobro,
15:28
there's no substitute for practice, practice, practice.
298
912541
7948
nema druge nego vježbati, vježbati, vježbati.
15:36
So these are four of the lessons that I've learned
299
920505
3120
To su četiri pouke koje sam tijekom godina
15:39
from robots over the years,
300
923625
3127
naučio od robota.
15:42
and robotics, the field of robotics has gotten much better
301
926752
5369
I robotika -- područje robotike mnogo se poboljšalo
15:48
over time.
302
932121
2168
tijekom vremena.
15:50
Nowadays, high school students can build robots
303
934289
2167
Danas srednjškolci mogu izrađivati robote
15:52
like the industrial robot my dad and I tried to build.
304
936456
4025
poput onog industrijskog kojeg smo
moj otac i ja pokušali izraditi.
moj otac i ja pokušali izraditi.
15:56
And now, I have a daughter,
305
940481
6982
Sada imam kćer,
16:03
named Odessa.
306
947463
2386
zove se Odessa.
16:05
She's eight years old,
307
949849
1833
Ima osam godina
16:07
and she likes robots, too.
308
951682
2424
i također voli robote.
16:10
Maybe it runs in the family. (Laughter)
309
954106
2414
Možda je to nešto nasljedno. (Smijeh)
16:12
I wish she could meet my dad.
310
956520
3647
Volio bih da je mogla upoznati mojega oca.
16:16
And now I get to teach her how things work,
311
960167
2900
Sada je mogu učiti kako stvari rade,
16:18
and we get to build projects together, and I wonder
312
963067
2772
možemo zajedno raditi na projektima i pitam se
16:21
what kind of lessons that she'll learn from them.
313
965839
4308
kakve će ona pouke iz njih izvući.
16:26
Robots are the most human
314
970147
2607
Roboti su najljudskiji
16:28
of our machines.
315
972754
2229
od svih strojeva.
16:30
They can't solve all of the world's problems,
316
974983
3085
Oni ne mogu riješiti sve svjetske probleme,
16:33
but I think they have something important to teach us.
317
978068
4358
ali mislim da nas mogu naučiti nečemu bitnome.
16:38
I invite all of you to think about the innovations
318
982426
3343
Pozivam vas sve da razmislite o inovacijama
16:41
that you're interested in,
319
985769
2675
koje vas zanimaju,
16:44
the machines that you wish for,
320
988444
3216
strojevima koje želite
16:47
and think about what they might be telling you,
321
991660
3169
i promislite što bi vam mogli reći,
16:50
because I have a hunch
322
994829
2063
jer imam osjećaj
16:52
that many of our technological innovations,
323
996892
2087
da nas mnoge naše tehnološke inovacije,
16:54
the devices we dream about,
324
998979
2658
uređaji o kojima sanjamo,
16:57
can inspire us to be better humans.
325
1001637
3964
mogu potaknuti da postanemo bolji ljudi.
17:01
Thank you. (Applause)
326
1005601
3585
Hvala. (Pljesak)
ABOUT THE SPEAKER
Ken Goldberg - RoboticistKen Goldberg works reflect the intersection of robotics, social media, and art.
Why you should listen
Ken Goldberg is a Professor of Industrial Engineering and Operations Research in Robotics, Automation, and New Media at UC Berkeley and holds a position at UC San Francisco Medical School where he researches medical applications for robotics. Born in Nigeria and raised in Bethlehem, Pennsylvania, Ken hold degrees in Electrical Engineering and Economics from the University of Pennsylvania and received his Ph.D. in Computer Science from Carnegie Mellon University. He is widely recognized as an engineer, a teacher, and an artist – receiving the Joseph F. Engelberger Robotics Award in 2000, the IEEE Major Educational Innovation Award in 2001, and Isadora Duncan Award in 2006 for his Ballet Mori project, performed by the San Francisco Ballet. His works have been exhibited at the Whitney Biennial in New York City, the Pompidou Centre in Paris, and the Ars Electronica in Linz. His book, The Robot in the Garden, was published in March of 2000 by the MIT Press.
Ken Goldberg | Speaker | TED.com