TEDGlobal 2010
Tan Le: A headset that reads your brainwaves
Uređaj koji čita moždane valove
Filmed:
Readability: 5
2,732,929 views
Tan Le predstavlja novo zadivljujuće računalno sučelje koje čita korisnikove moždane valove, omogučujući da mislima (uz malo koncentracije) kontroliramo virtualne objekte, i čak elektronske uređaje. Ona nam demonstrira uređaj i dijeli s nama predviđanja budućih primjena.
Tan Le - Entrepreneur
Tan Le is the founder & CEO of Emotiv, a bioinformatics company that's working on identifying biomarkers for mental and other neurological conditions using electroencephalography (EEG). Full bio
Tan Le is the founder & CEO of Emotiv, a bioinformatics company that's working on identifying biomarkers for mental and other neurological conditions using electroencephalography (EEG). Full bio
Double-click the English transcript below to play the video.
00:16
Up until now, our communication with machines
0
1000
2000
Sve do sada je, naša komunikacija sa strojevima
00:18
has always been limited
1
3000
2000
uvijek bila ograničena
00:20
to conscious and direct forms.
2
5000
2000
na svjesne i izravne postupke.
00:22
Whether it's something simple
3
7000
2000
Bez obzira radi li se o nečem jednostavnom,
00:24
like turning on the lights with a switch,
4
9000
2000
poput paljenja svjetla prekidačem,
00:26
or even as complex as programming robotics,
5
11000
3000
ili o nečem složenom poput programiranja robota,
00:29
we have always had to give a command to a machine,
6
14000
3000
oduvijek smo trebali dati naredbu stroju,
00:32
or even a series of commands,
7
17000
2000
ili čak niz naredbi,
00:34
in order for it to do something for us.
8
19000
3000
kako bi on nešto napravio za nas.
00:37
Communication between people, on the other hand,
9
22000
2000
Komunikacija između ljudi, s druge strane,
00:39
is far more complex and a lot more interesting
10
24000
3000
je mnogo složenija i puno zanimljivija,
00:42
because we take into account
11
27000
2000
jer uzimamo u obzir
00:44
so much more than what is explicitly expressed.
12
29000
3000
puno više od onoga što se izričito iskazuje.
00:47
We observe facial expressions, body language,
13
32000
3000
Promatramo izraz lica, govor tijela,
00:50
and we can intuit feelings and emotions
14
35000
2000
i možemo osjetiti emocije
00:52
from our dialogue with one another.
15
37000
3000
u razgovoru s drugima.
00:55
This actually forms a large part
16
40000
2000
To je zapravo veliki dio
00:57
of our decision-making process.
17
42000
2000
našeg procesa donošenja odluka.
00:59
Our vision is to introduce
18
44000
2000
Naša vizija je uvesti
01:01
this whole new realm of human interaction
19
46000
3000
tu potpuno novu dimenziju ljudske komunikacije
01:04
into human-computer interaction
20
49000
2000
u interakciju između čovjeka i računala,
01:06
so that computers can understand
21
51000
2000
kako bi računala mogla razumijeti
01:08
not only what you direct it to do,
22
53000
2000
ne samo ono što im naredite da naprave,
01:10
but it can also respond
23
55000
2000
već kako bi mogla reagirati
01:12
to your facial expressions
24
57000
2000
na vaš izraz lica
01:14
and emotional experiences.
25
59000
2000
i emocionalna iskustva.
01:16
And what better way to do this
26
61000
2000
A koji je bolji način za to napraviti
01:18
than by interpreting the signals
27
63000
2000
od interpretacije signala
01:20
naturally produced by our brain,
28
65000
2000
koje prirodno proizvodi naš mozak,
01:22
our center for control and experience.
29
67000
3000
naš centar za kontrolu i iskustvo.
01:25
Well, it sounds like a pretty good idea,
30
70000
2000
Zvuči kao prilično dobra ideja,
01:27
but this task, as Bruno mentioned,
31
72000
2000
ali taj zadatak, kao što je Bruno spomenuo,
01:29
isn't an easy one for two main reasons:
32
74000
3000
nije jednostavan iz dva glavna razloga:
01:32
First, the detection algorithms.
33
77000
3000
Prvo, algoritmi za detekciju.
01:35
Our brain is made up of
34
80000
2000
Naš mozak je napravljen od
01:37
billions of active neurons,
35
82000
2000
milijardi aktivnih neurona
01:39
around 170,000 km
36
84000
3000
i oko 170,000 km
01:42
of combined axon length.
37
87000
2000
ukupne dužine aksona.
01:44
When these neurons interact,
38
89000
2000
Kada su ti neuroni u interakciji,
01:46
the chemical reaction emits an electrical impulse,
39
91000
2000
kemijska reakcija emitira električne impulse
01:48
which can be measured.
40
93000
2000
koji se mogu mjeriti.
01:50
The majority of our functional brain
41
95000
3000
Većina naših moždanih funkcija
01:53
is distributed over
42
98000
2000
je raspodijeljena po
01:55
the outer surface layer of the brain,
43
100000
2000
vanjskoj površini mozga.
01:57
and to increase the area that's available for mental capacity,
44
102000
3000
A kako bi se povećalo područje koje je dostupno za mentalne aktivnosti,
02:00
the brain surface is highly folded.
45
105000
3000
površina mozga je jako naborana.
02:03
Now this cortical folding
46
108000
2000
Sva ta kortikalna pregibanja
02:05
presents a significant challenge
47
110000
2000
predstavljaju značajan izazov
02:07
for interpreting surface electrical impulses.
48
112000
3000
za interpretaciju površinskih električnih impulsa.
02:10
Each individual's cortex
49
115000
2000
Korteks svake osobe
02:12
is folded differently,
50
117000
2000
je naboran drugačije,
02:14
very much like a fingerprint.
51
119000
2000
nešto poput otiska prsta.
02:16
So even though a signal
52
121000
2000
Pa premda signali
02:18
may come from the same functional part of the brain,
53
123000
3000
možda dolaze iz istog funkcijskog dijela mozga,
02:21
by the time the structure has been folded,
54
126000
2000
ali zbog različitog nabiranja mozga
02:23
its physical location
55
128000
2000
njihova fizička lokacija
02:25
is very different between individuals,
56
130000
2000
značajno varira među pojedinicima,
02:27
even identical twins.
57
132000
3000
čak i među identičnim blizanicima.
02:30
There is no longer any consistency
58
135000
2000
Tako nema nikakve konzistentnosti
02:32
in the surface signals.
59
137000
2000
u površinskim signalima.
02:34
Our breakthrough was to create an algorithm
60
139000
2000
Naše otkriće je što smo napravili algoritam
02:36
that unfolds the cortex,
61
141000
2000
koji je "izravnao" korteks,
02:38
so that we can map the signals
62
143000
2000
kako bismo mogli mapirati signale
02:40
closer to its source,
63
145000
2000
bliže njihovu izvoru,
02:42
and therefore making it capable of working across a mass population.
64
147000
3000
što nas čini sposobnim za rad s masama.
02:46
The second challenge
65
151000
2000
Drugi izazov
02:48
is the actual device for observing brainwaves.
66
153000
3000
jest sam uređaj za promatranje moždanih valova.
02:51
EEG measurements typically involve
67
156000
2000
EEG mjerenja tipično rade
02:53
a hairnet with an array of sensors,
68
158000
3000
s mrežom senzora na glavi,
02:56
like the one that you can see here in the photo.
69
161000
3000
poput ove koju možete vidjeti na slici.
02:59
A technician will put the electrodes
70
164000
2000
Tehničar će staviti elektrode
03:01
onto the scalp
71
166000
2000
izravno na glavu
03:03
using a conductive gel or paste
72
168000
2000
koristeći provodivi gel ili pastu
03:05
and usually after a procedure of preparing the scalp
73
170000
3000
i obično nakon pripreme glave
03:08
by light abrasion.
74
173000
2000
laganim struganjem kože.
03:10
Now this is quite time consuming
75
175000
2000
To sve zahtjeva dosta vremena
03:12
and isn't the most comfortable process.
76
177000
2000
i nije najudobniji proces.
03:14
And on top of that, these systems
77
179000
2000
I pored svega, ti sustavi
03:16
actually cost in the tens of thousands of dollars.
78
181000
3000
koštaju desetine tisuća dolara.
03:20
So with that, I'd like to invite onstage
79
185000
3000
Imajući to na umu, željela bih pozvati
03:23
Evan Grant, who is one of last year's speakers,
80
188000
2000
Evana Granta, koji je jedan o prošlogodišnjih govornika
03:25
who's kindly agreed
81
190000
2000
koji je ljubazno pristao
03:27
to help me to demonstrate
82
192000
2000
pomoći mi demonstrirati
03:29
what we've been able to develop.
83
194000
2000
ono što smo uspjeli razviti.
03:31
(Applause)
84
196000
6000
(Pljesak)
03:37
So the device that you see
85
202000
2000
Dakle, uređaj koji vidite
03:39
is a 14-channel, high-fidelity
86
204000
2000
jest 14-kanalni, jako precizni
03:41
EEG acquisition system.
87
206000
2000
EEG sustav za mjerenje.
03:43
It doesn't require any scalp preparation,
88
208000
3000
Ne zahtjeva nikakvu pripremu glave,
03:46
no conductive gel or paste.
89
211000
2000
nikakav provodivi gel ili pastu.
03:48
It only takes a few minutes to put on
90
213000
3000
Treba mu samo nekoliko minuta da se postavi
03:51
and for the signals to settle.
91
216000
2000
i da se signali smire.
03:53
It's also wireless,
92
218000
2000
Također je bežičan,
03:55
so it gives you the freedom to move around.
93
220000
3000
tako da vam daje slobodu kretanja.
03:58
And compared to the tens of thousands of dollars
94
223000
3000
I u usporedbi s desetinama tisuća dolara
04:01
for a traditional EEG system,
95
226000
3000
za tradicionalni EEG sustav,
04:04
this headset only costs
96
229000
2000
ovaj uređaj košta samo
04:06
a few hundred dollars.
97
231000
2000
nekoliko stotina dolara.
04:08
Now on to the detection algorithms.
98
233000
3000
A sada nešto o algoritmu za prepoznavanje signala.
04:11
So facial expressions --
99
236000
2000
Dakle izrazi lica --
04:13
as I mentioned before in emotional experiences --
100
238000
2000
bitni za spoznaju o emocionalnim iskustvima --
04:15
are actually designed to work out of the box
101
240000
2000
su dizajnirani tako da funkcionira bez podešavanja
04:17
with some sensitivity adjustments
102
242000
2000
a osjetljivost se može fino prilagoditi
04:19
available for personalization.
103
244000
3000
u ovisnosti o korisniku.
04:22
But with the limited time we have available,
104
247000
2000
Ali s obzirom da nam je vrijeme ograničeno,
04:24
I'd like to show you the cognitive suite,
105
249000
2000
željela bih vam pokazati kognitivnu aplikaciju,
04:26
which is the ability for you
106
251000
2000
koja omogućuje
04:28
to basically move virtual objects with your mind.
107
253000
3000
da umom pomičete virtualne objekte.
04:32
Now, Evan is new to this system,
108
257000
2000
Evan nije prije koristio ovaj sustav,
04:34
so what we have to do first
109
259000
2000
zato prvo moramo
04:36
is create a new profile for him.
110
261000
2000
napraviti novi profil za njega.
04:38
He's obviously not Joanne -- so we'll "add user."
111
263000
3000
On očito nije Joanne -- dakle "dodati ćemo korisnika".
04:41
Evan. Okay.
112
266000
2000
Evan. OK.
04:43
So the first thing we need to do with the cognitive suite
113
268000
3000
Dakle prva stvar koju moramo napraviti u kognitivnoj aplikaciji
04:46
is to start with training
114
271000
2000
jest započeti s podešavanjem
04:48
a neutral signal.
115
273000
2000
na neutralni signal.
04:50
With neutral, there's nothing in particular
116
275000
2000
Na neutralnom, Evan ne treba ništa posebno
04:52
that Evan needs to do.
117
277000
2000
napraviti.
04:54
He just hangs out. He's relaxed.
118
279000
2000
Miran je. Opušten.
04:56
And the idea is to establish a baseline
119
281000
2000
I ideja je da se formira baza
04:58
or normal state for his brain,
120
283000
2000
ili normalno stanje njegova mozga,
05:00
because every brain is different.
121
285000
2000
jer je svaki mozak drugačiji.
05:02
It takes eight seconds to do this,
122
287000
2000
Potrebno je osam sekundi za ovo.
05:04
and now that that's done,
123
289000
2000
I sada kada je to napravljeno,
05:06
we can choose a movement-based action.
124
291000
2000
možemo izabrati akciju vezanu za pokret.
05:08
So Evan, choose something
125
293000
2000
Dakle Evane izaberi nešto
05:10
that you can visualize clearly in your mind.
126
295000
2000
što možeš jasno vizualizirati u svom umu.
05:12
Evan Grant: Let's do "pull."
127
297000
2000
Evan Grant: "Idemo pokušati "povući"."
05:14
Tan Le: Okay, so let's choose "pull."
128
299000
2000
Tan Le: "OK. Izaberimo "povući"."
05:16
So the idea here now
129
301000
2000
Dakle ideja je
05:18
is that Evan needs to
130
303000
2000
da Evan mora
05:20
imagine the object coming forward
131
305000
2000
zamisliti objekt koji dolazi prema naprijed
05:22
into the screen,
132
307000
2000
na ekran.
05:24
and there's a progress bar that will scroll across the screen
133
309000
3000
Ovdje je pokazivač napretka koji klizi preko ekrana
05:27
while he's doing that.
134
312000
2000
dok on to radi.
05:29
The first time, nothing will happen,
135
314000
2000
Prvi puta, ništa se neće dogoditi,
05:31
because the system has no idea how he thinks about "pull."
136
316000
3000
jer sustav nema pojma na koji način on zamišlja "povuci".
05:34
But maintain that thought
137
319000
2000
Ali zadrži tu misao
05:36
for the entire duration of the eight seconds.
138
321000
2000
svih osam sekundi trajanja.
05:38
So: one, two, three, go.
139
323000
3000
Dakle: jedan, dva, tri, počni.
05:49
Okay.
140
334000
2000
OK.
05:51
So once we accept this,
141
336000
2000
Kako smo jednom unijeli naredbu,
05:53
the cube is live.
142
338000
2000
kocka postaje živa.
05:55
So let's see if Evan
143
340000
2000
Pogledajmo može li Evan
05:57
can actually try and imagine pulling.
144
342000
3000
stvarno zamisliti "povlačenje".
06:00
Ah, good job!
145
345000
2000
Ah, dobar posao!
06:02
(Applause)
146
347000
3000
(Pljesak)
06:05
That's really amazing.
147
350000
2000
To je prilično zadivljujuće.
06:07
(Applause)
148
352000
4000
(Pljesak)
06:11
So we have a little bit of time available,
149
356000
2000
Imamo još malo vremena na raspolaganju,
06:13
so I'm going to ask Evan
150
358000
2000
pa ću zamoliti Evana
06:15
to do a really difficult task.
151
360000
2000
da izvede stvarno težak zadatak.
06:17
And this one is difficult
152
362000
2000
A ovaj je težak
06:19
because it's all about being able to visualize something
153
364000
3000
jer treba zamisliti nešto
06:22
that doesn't exist in our physical world.
154
367000
2000
što ne postoji u stvarnom svijetu.
06:24
This is "disappear."
155
369000
2000
To je naredba "nestani".
06:26
So what you want to do -- at least with movement-based actions,
156
371000
2000
Ono što želimo -- barem vezano s akcijom kretanja
06:28
we do that all the time, so you can visualize it.
157
373000
3000
to radimo stalno, tako da je možemo vizualizirati.
06:31
But with "disappear," there's really no analogies --
158
376000
2000
Ali s "nestani", ne postoje stvarne analogije.
06:33
so Evan, what you want to do here
159
378000
2000
Evane, zato sada želimo da
06:35
is to imagine the cube slowly fading out, okay.
160
380000
3000
zamisliš kocku kako polako nestaje, OK.
06:38
Same sort of drill. So: one, two, three, go.
161
383000
3000
Isti postupak. Dakle: jedan, dva, tri, počni.
06:50
Okay. Let's try that.
162
395000
3000
OK. Idemo pokušati to.
06:53
Oh, my goodness. He's just too good.
163
398000
3000
Oh, moj Bože. On je jednostavno predobar.
06:57
Let's try that again.
164
402000
2000
Pokušajmo ponovno.
07:04
EG: Losing concentration.
165
409000
2000
EG: "Gubim koncentraciju."
07:06
(Laughter)
166
411000
2000
(Smijeh)
07:08
TL: But we can see that it actually works,
167
413000
2000
TL: "Ali možemo vidjeti da to stvarno radi,
07:10
even though you can only hold it
168
415000
2000
premda se ne možeš koncentrirati
07:12
for a little bit of time.
169
417000
2000
duže od trenutka."
07:14
As I said, it's a very difficult process
170
419000
3000
Ponavljam, jako je težak proces
07:17
to imagine this.
171
422000
2000
ovo zamisliti.
07:19
And the great thing about it is that
172
424000
2000
I moćna stvar oko toga jest
07:21
we've only given the software one instance
173
426000
2000
da smo dali softveru samo jedan primjer
07:23
of how he thinks about "disappear."
174
428000
3000
kako on misli o "nestati".
07:26
As there is a machine learning algorithm in this --
175
431000
3000
Postoji algoritam stroja koji uči --
07:29
(Applause)
176
434000
4000
(Pljesak)
07:33
Thank you.
177
438000
2000
Hvala.
07:35
Good job. Good job.
178
440000
3000
Dobar posao. Dobar posao.
07:38
(Applause)
179
443000
2000
(Pljesak)
07:40
Thank you, Evan, you're a wonderful, wonderful
180
445000
3000
Hvala, Evane, ti si divan, divno si
07:43
example of the technology.
181
448000
3000
prikazao tehnologiju.
07:46
So, as you can see, before,
182
451000
2000
Kao što ste mogli vidjeti,
07:48
there is a leveling system built into this software
183
453000
3000
postoji višerazinski sustav ugrađen u ovaj softver
07:51
so that as Evan, or any user,
184
456000
2000
kako bi Evan, ili neki drugi korisnik,
07:53
becomes more familiar with the system,
185
458000
2000
kada se priviknu na sustav,
07:55
they can continue to add more and more detections,
186
460000
3000
mogu nastaviti dodavati sve više obrazaca
07:58
so that the system begins to differentiate
187
463000
2000
kako bi sustav mogao početi razlikovati
08:00
between different distinct thoughts.
188
465000
3000
različite obrasce misli.
08:04
And once you've trained up the detections,
189
469000
2000
I jednom kada ste uvježbali obrasce,
08:06
these thoughts can be assigned or mapped
190
471000
2000
te misli se mogu dodijeliti ili prebaciti
08:08
to any computing platform,
191
473000
2000
na bilo koju računalnu platformu,
08:10
application or device.
192
475000
2000
aplikaciju ili uređaj.
08:12
So I'd like to show you a few examples,
193
477000
2000
Zato bih vam voljela pokazati nekoliko primjera,
08:14
because there are many possible applications
194
479000
2000
jer postoji jako puno mogućih primjena
08:16
for this new interface.
195
481000
2000
ovog novog sučelja.
08:19
In games and virtual worlds, for example,
196
484000
2000
U igrama i virtualnom svijetu, na primjer,
08:21
your facial expressions
197
486000
2000
vaš izraz lica
08:23
can naturally and intuitively be used
198
488000
2000
može prirodno i intuitivno biti korišten
08:25
to control an avatar or virtual character.
199
490000
3000
za upravljanje avatarom ili virtualnim likom.
08:29
Obviously, you can experience the fantasy of magic
200
494000
2000
Očito, možete iskusiti čaroliju mašte
08:31
and control the world with your mind.
201
496000
3000
i upravljati svijetom svojim mislima.
08:36
And also, colors, lighting,
202
501000
3000
I također, boje, osvjetljenje,
08:39
sound and effects
203
504000
2000
zvuk i efekti,
08:41
can dynamically respond to your emotional state
204
506000
2000
mogu dinamično odgovarati na vaše emotivno stanje
08:43
to heighten the experience that you're having, in real time.
205
508000
3000
kako bi naglasili iskustvo koje imate, u realnom vremenu.
08:47
And moving on to some applications
206
512000
2000
Evo nekih primjera
08:49
developed by developers and researchers around the world,
207
514000
3000
koji su razvili istraživači širom svijeta,
08:52
with robots and simple machines, for example --
208
517000
3000
s robotima i jednostavnim strojevima, na primjer --
08:55
in this case, flying a toy helicopter
209
520000
2000
u ovom slučaju, letenje igračkom helikopterom
08:57
simply by thinking "lift" with your mind.
210
522000
3000
jednostavno razmišljajući o uzletanju.
09:00
The technology can also be applied
211
525000
2000
Tehnologija se može primjeniti
09:02
to real world applications --
212
527000
2000
u svakodnevnom životu --
09:04
in this example, a smart home.
213
529000
2000
u ovom primjeru, u pametnoj kući.
09:06
You know, from the user interface of the control system
214
531000
3000
Znate, od korisničkog sučelja kontrolnog sustava
09:09
to opening curtains
215
534000
2000
do otvaranja
09:11
or closing curtains.
216
536000
3000
ili zatvaranja zastora.
09:22
And of course, also to the lighting --
217
547000
3000
Naravno i osvijetljenje --
09:25
turning them on
218
550000
3000
paleći
09:28
or off.
219
553000
2000
ili gaseći ih.
09:30
And finally,
220
555000
2000
I konačno,
09:32
to real life-changing applications,
221
557000
2000
aplikacija koje mogu izmjeniti život
09:34
such as being able to control an electric wheelchair.
222
559000
3000
poput toga da smo sposobni upravljati električnim kolicima.
09:37
In this example,
223
562000
2000
U ovom primjeru,
09:39
facial expressions are mapped to the movement commands.
224
564000
3000
izrazi lica su povezani s naredbama za kretanje.
09:42
Man: Now blink right to go right.
225
567000
3000
Muškarac: Sada namigni desnim okom kako bi išao desno.
09:50
Now blink left to turn back left.
226
575000
3000
Sada namigni lijevim okom kako bi išao lijevo.
10:02
Now smile to go straight.
227
587000
3000
Sada se nasmiji za ravno.
10:08
TL: We really -- Thank you.
228
593000
2000
TL: Mi stvarno -- Hvala vam.
10:10
(Applause)
229
595000
5000
(Pljesak)
10:15
We are really only scratching the surface of what is possible today,
230
600000
3000
Mi samo grebemo po površini onoga što je danas moguće.
10:18
and with the community's input,
231
603000
2000
A s idejama zajednice,
10:20
and also with the involvement of developers
232
605000
2000
i uključenošću developera
10:22
and researchers from around the world,
233
607000
3000
i istraživača širom svijeta,
10:25
we hope that you can help us to shape
234
610000
2000
nadamo se da ćete nam pomoći oblikovati
10:27
where the technology goes from here. Thank you so much.
235
612000
3000
kamo ova tehnologije treba ići dalje. Hvala vam puno.
ABOUT THE SPEAKER
Tan Le - EntrepreneurTan Le is the founder & CEO of Emotiv, a bioinformatics company that's working on identifying biomarkers for mental and other neurological conditions using electroencephalography (EEG).
Why you should listen
Tan Le is the co-founder and president of Emotiv. Before this, she headed a firm that worked on a new form of remote control that uses brainwaves to control digital devices and digital media. It's long been a dream to bypass the mechanical (mouse, keyboard, clicker) and have our digital devices respond directly to what we think. Emotiv's EPOC headset uses 16 sensors to listen to activity across the entire brain. Software "learns" what each user's brain activity looks like when one, for instance, imagines a left turn or a jump.
Le herself has an extraordinary story -- a refugee from Vietnam at age 4, she entered college at 16 and has since become a vital young leader in her home country of Australia.
Tan Le | Speaker | TED.com