David Hanson: Robots that "show emotion"

187,797 views ・ 2009-10-14

TED


Dvaput kliknite na engleske titlove ispod za reprodukciju videozapisa.

Prevoditelj: Tilen Pigac - EFZG Recezent: Mislav Ante Omazić - EFZG
00:16
I'm Dr. David Hanson, and I build robots with character.
0
16260
3000
Ja sam Dr. David Hanson, i izrađujem robote s karakterom.
00:19
And by that, I mean
1
19260
2000
A pod time, mislim
00:21
that I develop robots that are characters,
2
21260
2000
da razvijam robote koji su likovi,
00:23
but also robots that will eventually
3
23260
3000
ali isto tako, robote koji će konačno
00:26
come to empathize with you.
4
26260
2000
moći suosjećati s vama.
00:28
So we're starting with a variety of technologies
5
28260
2000
Dakle, započinjemo s nizom tehnologija
00:30
that have converged into these conversational character robots
6
30260
4000
koje su se konvergirale u ove razgovorne likove robota
00:34
that can see faces, make eye contact with you,
7
34260
2000
koji mogu vidjeti lica, ostvariti kontakt očima,
00:36
make a full range of facial expressions, understand speech
8
36260
3000
pokazati pun niz facijalnih ekspresija, razumijeti govor,
00:39
and begin to model how you're feeling
9
39260
4000
i početi modelirati kako se osjećate,
00:43
and who you are, and build a relationship with you.
10
43260
3000
i tko ste, te izgraditi vezu s vama.
00:46
I developed a series of technologies
11
46260
2000
Razvio sam niz tehnologija
00:48
that allowed the robots to make more realistic facial expressions
12
48260
3000
koje su omogućile robotima da pokazuju realističnije facijalne ekspresije
00:51
than previously achieved, on lower power,
13
51260
2000
nego prije, uz manje energije,
00:53
which enabled the walking biped robots, the first androids.
14
53260
4000
što je rezultiralo s hodajućim robotima na dvije noge, prvim androidima.
00:57
So, it's a full range of facial expressions
15
57260
2000
Dakle, njihov cijeli niz facijalnih ekspresija
00:59
simulating all the major muscles in the human face,
16
59260
2000
simulira sve važne mišiće u ljudskom licu,
01:01
running on very small batteries,
17
61260
2000
pogonjen jako malim baterijama,
01:03
extremely lightweight.
18
63260
2000
i krajnje su lagani.
01:05
The materials that allowed the battery-operated facial expressions
19
65260
3000
Materijal koji je omogućava facijalne ekspresije pogonjene baterijama
01:08
is a material that we call Frubber,
20
68260
2000
je materijal kojeg nazivamo Frubber,
01:10
and it actually has three major innovations
21
70260
2000
i u stvari sadrži tri velike inovacije
01:12
in the material that allow this to happen.
22
72260
2000
u materijalu koji nam to omogućava.
01:14
One is hierarchical pores,
23
74260
2000
Jedno su hijerarhijske pore.
01:16
and the other is a macro-molecular nanoscale porosity in the material.
24
76260
4000
A drugo je makro-molekularna nanostupanjska poroznost u materijalu.
01:20
There he's starting to walk.
25
80260
3000
Ovdje on pokušava hodati.
01:23
This is at the Korean Advanced Institute of Science and Technology.
26
83260
3000
Ovo je u korejskom Institutu napredne znanosti i tehnologije.
01:26
I built the head. They built the body.
27
86260
4000
Izradio sam glavu. Oni su izradili tijelo.
01:30
So the goal here is to achieve sentience in machines,
28
90260
3000
Cilj je ovdje postići osjećaj u strojevima,
01:33
and not just sentience, but empathy.
29
93260
4000
i ne samo osjećaj, već empatiju.
01:37
We're working with the Machine Perception Laboratory
30
97260
2000
Radimo s Laboratorijem perceptivnih strojeva
01:39
at the U.C. San Diego.
31
99260
2000
na Sveučilištu u Kaliforniji, San Diego.
01:41
They have this really remarkable facial expression technology
32
101260
3000
Oni imaju tu doista nevjerojatnu tehnologiju
01:44
that recognizes facial expressions,
33
104260
2000
koja prepoznaje facijalne ekspresije,
01:46
what facial expressions you're making.
34
106260
2000
i koje facijalne ekspresije pokazujete.
01:48
It also recognizes where you're looking, your head orientation.
35
108260
3000
Ujedno prepoznaje gdje gledate, orijentaciju vaše glave.
01:51
We're emulating all the major facial expressions,
36
111260
2000
Simuliramo sve važne facijalne ekspresije,
01:53
and then controlling it with the software
37
113260
2000
i zatim ih kontroliramo s programom
01:55
that we call the Character Engine.
38
115260
2000
kojeg zovemo "Karakterni stroj".
01:57
And here is a little bit of the technology that's involved in that.
39
117260
4000
A ovdje je mali dio tehnologije koji je uključen u to.
02:01
In fact, right now -- plug it from here, and then plug it in here,
40
121260
8000
Zapravo, baš sada -- priključite ga odavde, a zatim ga priključite ovdje,
02:09
and now let's see if it gets my facial expressions.
41
129260
3000
pa da sada vidimo hoće li prepoznati moje facijalne ekspresije.
02:12
Okay. So I'm smiling.
42
132260
5000
Dobro. Smiješim se.
02:17
(Laughter)
43
137260
2000
(Smijeh)
02:19
Now I'm frowning.
44
139260
2000
Sada se mrštim.
02:21
And this is really heavily backlit.
45
141260
4000
A ovo je uistinu teško pozadinsko osvijetljenje.
02:25
Okay, here we go.
46
145260
2000
Dobro, krećemo.
02:27
Oh, it's so sad.
47
147260
2000
O, tako je tužno.
02:29
Okay, so you smile, frowning.
48
149260
3000
Dobro, smiješiš se, mrštiš.
02:32
So his perception of your emotional states
49
152260
2000
Njegova percepcija vaših emocionalnih stanja
02:34
is very important for machines to effectively become empathetic.
50
154260
4000
je jako važna strojevima da učinkovito postanu empatični.
02:38
Machines are becoming devastatingly capable
51
158260
3000
Strojevi postaju razorno sposobni
02:41
of things like killing. Right?
52
161260
4000
za stvari poput ubijanja. Točno?
02:45
Those machines have no place for empathy.
53
165260
2000
Ti strojevi nemaju mjesta za empatiju.
02:47
And there is billions of dollars being spent on that.
54
167260
2000
A utrošene su milijarde dolara na to.
02:49
Character robotics could plant the seed
55
169260
2000
Karakterna robotika bi mogla posaditi sjeme
02:51
for robots that actually have empathy.
56
171260
2000
za robote koji doista imaju empatiju.
02:53
So, if they achieve human level intelligence
57
173260
2000
Dakle, ako dosegnu ljudsku razinu inteligencije
02:55
or, quite possibly, greater than human levels of intelligence,
58
175260
4000
ili, sasvim moguće, veću od ljudske razine inteligencije,
02:59
this could be the seeds of hope for our future.
59
179260
3000
to bi mogla biti sjemena nade za našu budućnost.
03:02
So, we've made 20 robots in the last eight years, during the course of getting my Ph.D.
60
182260
4000
Izradili smo 20 robota u posljednjih osam godina, tijekom mog doktorata.
03:06
And then I started Hanson Robotics,
61
186260
2000
I nakon toga sam pokrenuo "Hanson Robotiku",
03:08
which has been developing these things for mass manufacturing.
62
188260
4000
koja razvija te stvari za masovnu proizvodnju.
03:12
This is one of our robots
63
192260
2000
Ovo je jedan od naših robota
03:14
that we showed at Wired NextFest a couple of years ago.
64
194260
2000
koji smo pokazali na "Wired NextFestu" prije par godina.
03:16
And it sees multiple people in a scene,
65
196260
3000
I vidi više ljudi u jednom prizoru,
03:19
remembers where individual people are,
66
199260
2000
pamti gdje su pojedini ljudi,
03:21
and looks from person to person, remembering people.
67
201260
4000
i gleda od osobe do osobe, pamteći ljude.
03:25
So, we're involving two things.
68
205260
2000
Dakle, uključujemo dvije stvari.
03:27
One, the perception of people,
69
207260
2000
Prvo, percepciju ljudi.
03:29
and two, the natural interface,
70
209260
4000
Drugo, prirodno sučelje,
03:33
the natural form of the interface,
71
213260
2000
prirodan oblik sučelja,
03:35
so that it's more intuitive for you to interact with the robot.
72
215260
3000
tako da je što intuitivnije za vas kada imate interakciju s robotom.
03:38
You start to believe that it's alive and aware.
73
218260
3000
Počinjete vjerovati da je živ i svjestan.
03:41
So one of my favorite projects was bringing all this stuff together
74
221260
3000
Jedan od mojih najdražih projekata je bio prikazati sve te stvari zajedno
03:44
in an artistic display of an android portrait
75
224260
3000
u umjetničkom prikazu potreta androida
03:47
of science-fiction writer Philip K. Dick,
76
227260
2000
pisca znanstvene fantastike Philip K. Dicka,
03:49
who wrote great works like, "Do Androids Dream of Electric Sheep?"
77
229260
3000
koji je napisao velika djela poput, "Sanjaju li androidi o električnim ovcama?",
03:52
which was the basis of the movie "Bladerunner."
78
232260
2000
koji je bio osnova za film "Bladerunner."
03:54
In these stories, robots often think
79
234260
3000
U tim pričama, roboti često misle
03:57
that they're human, and they sort of come to life.
80
237260
2000
kako su ljudi. I na neki način ožive.
03:59
So we put his writings, letters,
81
239260
3000
Stoga smo stavili njegove zapiske, pisma,
04:02
his interviews, correspondences,
82
242260
3000
njegove intervjue, prepiske,
04:05
into a huge database of thousands of pages,
83
245260
2000
u ogromnu bazu podataka s tisućama stranica,
04:07
and then used some natural language processing
84
247260
2000
i zatim smo upotrijebili neko prirodno procesuiranje jezika
04:09
to allow you to actually have a conversation with him.
85
249260
2000
kako bi omogućili vama da vodite razgovor s njim.
04:11
And it was kind of spooky, because he would say these things
86
251260
2000
I bilo je pomalo zastrašujuće. Jer bi rekao stvari
04:13
that just sounded like they really understood you.
87
253260
3000
koje su zvučale kao da vas stvarno razumiju.
04:16
And this is one of the most exciting projects that we're developing,
88
256260
3000
A ovo je jedan od najuzbudljivijih projekata koje razvijamo,
04:19
which is a little character that's a spokesbot
89
259260
3000
mali lik, a koji je robot zagovornik
04:22
for friendly artificial intelligence, friendly machine intelligence.
90
262260
3000
prijateljske umjetne inteligencije, prijateljske strojne inteligencije.
04:25
And we're getting this mass-manufactured.
91
265260
2000
I počinjemo ga masovno proizvoditi.
04:27
We specked it out to actually be doable
92
267260
3000
Specificirali smo ga tako da bude izvediv
04:30
with a very, very low-cost bill of materials,
93
270260
3000
s jako, jako malim troškovima za materijal,
04:33
so that it can become a childhood companion for kids.
94
273260
4000
kako bi mogao postati suputnik kroz djetinjstvo za djecu.
04:37
Interfacing with the Internet, it gets smarter over the years.
95
277260
3000
Komunicirajući s Internetom, s godinama postaje pametniji.
04:40
As artificial intelligence evolves, so does his intelligence.
96
280260
3000
Kako se umjetna inteligencija razvija, tako se razvija i njegova inteligencija.
04:43
Chris Anderson: Thank you so much. That's incredible.
97
283260
2000
Chris Anderson: Puno ti hvala. To je nevjerojatno.
04:45
(Applause)
98
285260
7000
(Pljesak)
O ovoj web stranici

Ova stranica će vas upoznati s YouTube videozapisima koji su korisni za učenje engleskog jezika. Vidjet ćete lekcije engleskog koje vode vrhunski profesori iz cijelog svijeta. Dvaput kliknite na engleske titlove prikazane na svakoj video stranici da biste reproducirali video s tog mjesta. Titlovi se pomiču sinkronizirano s reprodukcijom videozapisa. Ako imate bilo kakvih komentara ili zahtjeva, obratite nam se putem ovog obrasca za kontakt.

https://forms.gle/WvT1wiN1qDtmnspy7