TEDGlobal 2010
Tan Le: A headset that reads your brainwaves
Tan Le: Uređaj koji čita misli
Filmed:
Readability: 5
2,732,929 views
Tan Le predstavlja novi i neverovatni kompjuterski interfejs koji čitajući i tumačeći moždane talase omogućava korisniku da mislima (uz malo koncentracije) kontroliše virtuelne objekte, a i elektronske uređaje uopšte. Demonstrira uređaj i iznosi predviđanja budućih primena.
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 nedavno, komunikacija sa mašinama
00:18
has always been limited
1
3000
2000
je bila ograničena
00:20
to conscious and direct forms.
2
5000
2000
na namerne i direktne postupke.
00:22
Whether it's something simple
3
7000
2000
Svejedno da li je u pitanju nešto jednostavno,
00:24
like turning on the lights with a switch,
4
9000
2000
recimo, paljenje svetla prekidačem,
00:26
or even as complex as programming robotics,
5
11000
3000
ili složeno, poput programiranja robota,
00:29
we have always had to give a command to a machine,
6
14000
3000
mašini smo uvek morali zadati naredbu,
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 ona tad nešto izvršila.
00:37
Communication between people, on the other hand,
9
22000
2000
Komunikacija između ljudi
00:39
is far more complex and a lot more interesting
10
24000
3000
je daleko složenija i zanimljivija
00:42
because we take into account
11
27000
2000
jer obuhvata mnogo više
00:44
so much more than what is explicitly expressed.
12
29000
3000
od onoga što se iskazuje rečima.
00:47
We observe facial expressions, body language,
13
32000
3000
Bitan je izraz lica, govor tela,
00:50
and we can intuit feelings and emotions
14
35000
2000
jer neposredno opažamo osećanja sagovornika
00:52
from our dialogue with one another.
15
37000
3000
iz samog dijaloga ali i ponašanja.
00:55
This actually forms a large part
16
40000
2000
To je jako veliki deo
00:57
of our decision-making process.
17
42000
2000
procesa donošenja odluka.
00:59
Our vision is to introduce
18
44000
2000
Naš cilj je da uvedemo
01:01
this whole new realm of human interaction
19
46000
3000
tu novu dimenziju komunikacije
01:04
into human-computer interaction
20
49000
2000
u interakciju čoveka sa kompjuterom,
01:06
so that computers can understand
21
51000
2000
da omogućimo kompjuteru da razume
01:08
not only what you direct it to do,
22
53000
2000
ne samo šta treba da uradi,
01:10
but it can also respond
23
55000
2000
već da reaguje
01:12
to your facial expressions
24
57000
2000
i na izraze lica
01:14
and emotional experiences.
25
59000
2000
i ispoljavanje emocija.
01:16
And what better way to do this
26
61000
2000
A nema boljeg načina da postignemo cilj
01:18
than by interpreting the signals
27
63000
2000
od tumačenja signala
01:20
naturally produced by our brain,
28
65000
2000
koje i inače emituje čovekov mozak,
01:22
our center for control and experience.
29
67000
3000
centar za kontrolu i opažanje.
01:25
Well, it sounds like a pretty good idea,
30
70000
2000
Jeste, zvuči kao jako lepa ideja,
01:27
but this task, as Bruno mentioned,
31
72000
2000
ali, kao što Bruno reče,
01:29
isn't an easy one for two main reasons:
32
74000
3000
nije je lako ostvariti, iz dva razloga:
01:32
First, the detection algorithms.
33
77000
3000
Prvi su algoritmi za detekciju.
01:35
Our brain is made up of
34
80000
2000
Naš mozak sačinjavaju
01:37
billions of active neurons,
35
82000
2000
milijarde aktivnih neurona,
01:39
around 170,000 km
36
84000
3000
ukupne dužine aksona
01:42
of combined axon length.
37
87000
2000
preko 170.000 km.
01:44
When these neurons interact,
38
89000
2000
Pri radu neurona,
01:46
the chemical reaction emits an electrical impulse,
39
91000
2000
hemijske reakcije u njima prave električne impulse
01:48
which can be measured.
40
93000
2000
koji su merljivi.
01:50
The majority of our functional brain
41
95000
3000
Deo mozga koji vrši nama potrebne funkcije
01:53
is distributed over
42
98000
2000
je raspoređen po
01:55
the outer surface layer of the brain,
43
100000
2000
spoljnoj površini mozga.
01:57
and to increase the area that's available for mental capacity,
44
102000
3000
A radi uvećanja površine te aktivne oblasti
02:00
the brain surface is highly folded.
45
105000
3000
kora mozga je veoma naborana.
02:03
Now this cortical folding
46
108000
2000
Zbog svog tog savijanja i nabiranja
02:05
presents a significant challenge
47
110000
2000
veliki je problem
02:07
for interpreting surface electrical impulses.
48
112000
3000
tačno razabrati električne impulse.
02:10
Each individual's cortex
49
115000
2000
Kora mozga svakog čoveka
02:12
is folded differently,
50
117000
2000
se nabira drugačije, jedinstveno,
02:14
very much like a fingerprint.
51
119000
2000
kao otisci prstiju.
02:16
So even though a signal
52
121000
2000
Mada signali dolaze
02:18
may come from the same functional part of the brain,
53
123000
3000
iz istog moždanog centra,
02:21
by the time the structure has been folded,
54
126000
2000
zbog nabiranja površine mozga
02:23
its physical location
55
128000
2000
lokacije samih centara
02:25
is very different between individuals,
56
130000
2000
vrlo variraju među ljudima,
02:27
even identical twins.
57
132000
3000
čak i kod identičnih blizanaca.
02:30
There is no longer any consistency
58
135000
2000
Tako se gubi poreklo
02:32
in the surface signals.
59
137000
2000
površinskih električnih signala.
02:34
Our breakthrough was to create an algorithm
60
139000
2000
Proboj smo napravili izradom algoritma
02:36
that unfolds the cortex,
61
141000
2000
koji "izravna" površinu velikog mozga,
02:38
so that we can map the signals
62
143000
2000
pa signale sad tačnije mapiramo
02:40
closer to its source,
63
145000
2000
na njihova izvorišta,
02:42
and therefore making it capable of working across a mass population.
64
147000
3000
što nam omogućava masovnu primenu.
02:46
The second challenge
65
151000
2000
Drugi problem je
02:48
is the actual device for observing brainwaves.
66
153000
3000
sam uređaj za hvatanje moždanih talasa.
02:51
EEG measurements typically involve
67
156000
2000
EEG snimci se obično rade
02:53
a hairnet with an array of sensors,
68
158000
3000
sa mrežicom za glavu načičkanom senzorima,
02:56
like the one that you can see here in the photo.
69
161000
3000
kao ova na slici.
02:59
A technician will put the electrodes
70
164000
2000
Tehničar stavlja elektrode
03:01
onto the scalp
71
166000
2000
direktno na površinu glave
03:03
using a conductive gel or paste
72
168000
2000
namazanu provodnim gelom ili namazom,
03:05
and usually after a procedure of preparing the scalp
73
170000
3000
a sve to nakon pripremanja
03:08
by light abrasion.
74
173000
2000
i plitke abrazije kože glave.
03:10
Now this is quite time consuming
75
175000
2000
To sve zahteva dosta vremena
03:12
and isn't the most comfortable process.
76
177000
2000
a nije baš ni prijatno.
03:14
And on top of that, these systems
77
179000
2000
Povrh svega, ovakvi sistemi
03:16
actually cost in the tens of thousands of dollars.
78
181000
3000
koštaju desetihe hiljada dolara.
03:20
So with that, I'd like to invite onstage
79
185000
3000
Sa svim tim na umu, molim vas da pozdravite
03:23
Evan Grant, who is one of last year's speakers,
80
188000
2000
Evana Granta, prošlogodišnjeg govornika,
03:25
who's kindly agreed
81
190000
2000
koji je ljubazno pristao
03:27
to help me to demonstrate
82
192000
2000
da mi pomogne da pokažem
03:29
what we've been able to develop.
83
194000
2000
šta smo napravili.
03:31
(Applause)
84
196000
6000
(Aplauz)
03:37
So the device that you see
85
202000
2000
Uređaj koji vidite je
03:39
is a 14-channel, high-fidelity
86
204000
2000
14-kanalni, vrlo precizni
03:41
EEG acquisition system.
87
206000
2000
EEG snimač.
03:43
It doesn't require any scalp preparation,
88
208000
3000
Ne zahteva prethodnu pripremu glave,
03:46
no conductive gel or paste.
89
211000
2000
nikakav provodni gel.
03:48
It only takes a few minutes to put on
90
213000
3000
Namesti se i kalibriše
03:51
and for the signals to settle.
91
216000
2000
za dva-tri minuta.
03:53
It's also wireless,
92
218000
2000
Takođe je bežičan,
03:55
so it gives you the freedom to move around.
93
220000
3000
i omogućava punu slobodu kretanja.
03:58
And compared to the tens of thousands of dollars
94
223000
3000
Za razliku od dosadašnjih EEG sistema,
04:01
for a traditional EEG system,
95
226000
3000
koji koštaju desetine hiljada dolara,
04:04
this headset only costs
96
229000
2000
ovaj uređaj košta
04:06
a few hundred dollars.
97
231000
2000
nekoliko stotina dolara.
04:08
Now on to the detection algorithms.
98
233000
3000
Nazad na algoritme detekcije.
04:11
So facial expressions --
99
236000
2000
Prepoznavanje izraza lica,
04:13
as I mentioned before in emotional experiences --
100
238000
2000
-- bitno za prepoznavanje emotivnog stanja --
04:15
are actually designed to work out of the box
101
240000
2000
funkcioniše bez prethodnog podešavanja,
04:17
with some sensitivity adjustments
102
242000
2000
a osetljivost se može naknadno
04:19
available for personalization.
103
244000
3000
fino podešavati prema korisniku.
04:22
But with the limited time we have available,
104
247000
2000
Ali, pošto nam je vreme ograničeno,
04:24
I'd like to show you the cognitive suite,
105
249000
2000
prikazaću vam kognitivnu aplikaciju
04:26
which is the ability for you
106
251000
2000
koja daje mogućnost
04:28
to basically move virtual objects with your mind.
107
253000
3000
da umom pomerate virtuelne objekte.
04:32
Now, Evan is new to this system,
108
257000
2000
Evan prvi put koristi sistem,
04:34
so what we have to do first
109
259000
2000
pa prvo moramo
04:36
is create a new profile for him.
110
261000
2000
da mu napravimo lični profil.
04:38
He's obviously not Joanne -- so we'll "add user."
111
263000
3000
Očigledno, on nije "Džoana", dodaću 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
Prvo je nephodno da
04:46
is to start with training
114
271000
2000
kalibrišemo aplikaciju
04:48
a neutral signal.
115
273000
2000
na neutralan signal.
04:50
With neutral, there's nothing in particular
116
275000
2000
Na neutralnom, Evan ne treba da
04:52
that Evan needs to do.
117
277000
2000
radi ništa konkretno.
04:54
He just hangs out. He's relaxed.
118
279000
2000
Treba da je miran i opušten.
04:56
And the idea is to establish a baseline
119
281000
2000
Cilj je da se snimi
04:58
or normal state for his brain,
120
283000
2000
"normalno" stanje njegovog mozga,
05:00
because every brain is different.
121
285000
2000
jer svaki je mozak drugačiji.
05:02
It takes eight seconds to do this,
122
287000
2000
Ovo traje osam sekundi.
05:04
and now that that's done,
123
289000
2000
Sad smo to završili,
05:06
we can choose a movement-based action.
124
291000
2000
možemo da radimo neki pokret.
05:08
So Evan, choose something
125
293000
2000
Evane, izaberi nešto
05:10
that you can visualize clearly in your mind.
126
295000
2000
što možeš jasno da zamisliš.
05:12
Evan Grant: Let's do "pull."
127
297000
2000
Evan Grant: Hajde da "povučemo".
05:14
Tan Le: Okay, so let's choose "pull."
128
299000
2000
Tan Le: Ok, izabrali smo "povlačenje".
05:16
So the idea here now
129
301000
2000
E sad,
05:18
is that Evan needs to
130
303000
2000
Evan bi sada trebalo da
05:20
imagine the object coming forward
131
305000
2000
zamišlja kako povlači objekat
05:22
into the screen,
132
307000
2000
ka ekranu, ka sebi.
05:24
and there's a progress bar that will scroll across the screen
133
309000
3000
Tu je i pokazivač koji će
05:27
while he's doing that.
134
312000
2000
da prati kalibraciju.
05:29
The first time, nothing will happen,
135
314000
2000
Prvi put se neće ništa desiti,
05:31
because the system has no idea how he thinks about "pull."
136
316000
3000
jer sistem ne zna kako Evan misli o "povlačenju".
05:34
But maintain that thought
137
319000
2000
Ali ako zadrži tu misao
05:36
for the entire duration of the eight seconds.
138
321000
2000
svih osam sekundi...
05:38
So: one, two, three, go.
139
323000
3000
Ajmo: jedan, dva, tri, kreni!
05:49
Okay.
140
334000
2000
OK.
05:51
So once we accept this,
141
336000
2000
Nakon što smo uneli komandu,
05:53
the cube is live.
142
338000
2000
kocka može odmah da reaguje.
05:55
So let's see if Evan
143
340000
2000
Hajde da vidimo da li Evan
05:57
can actually try and imagine pulling.
144
342000
3000
može da je povuče.
06:00
Ah, good job!
145
345000
2000
Aaa, odlično!
06:02
(Applause)
146
347000
3000
(aplauz)
06:05
That's really amazing.
147
350000
2000
To je bilo neverovatno.
06:07
(Applause)
148
352000
4000
(tapšu)
06:11
So we have a little bit of time available,
149
356000
2000
Imamo još nešto vremena,
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 probamo teži zadatak.
06:17
And this one is difficult
152
362000
2000
Ovaj zadatak je teži
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 svakodnevici.
06:24
This is "disappear."
155
369000
2000
To je komanda "nestani".
06:26
So what you want to do -- at least with movement-based actions,
156
371000
2000
Komande vezane za kretanje su lake,
06:28
we do that all the time, so you can visualize it.
157
373000
3000
to radimo i zamišljamo i inače,
06:31
But with "disappear," there's really no analogies --
158
376000
2000
ali za "nestani" nema dobrih analogija.
06:33
so Evan, what you want to do here
159
378000
2000
Dakle, Evane,
06:35
is to imagine the cube slowly fading out, okay.
160
380000
3000
zamisli kocku kako polako nestaje.
06:38
Same sort of drill. So: one, two, three, go.
161
383000
3000
Isti je postupak. Jedan, dva, tri.
06:50
Okay. Let's try that.
162
395000
3000
Ok, sad da probamo.
06:53
Oh, my goodness. He's just too good.
163
398000
3000
O moj bože. Mnogo je dobar.
06:57
Let's try that again.
164
402000
2000
Probaj opet.
07:04
EG: Losing concentration.
165
409000
2000
Evan: Gubim koncentraciju.
07:06
(Laughter)
166
411000
2000
(smeju se)
07:08
TL: But we can see that it actually works,
167
413000
2000
Tan Le: Vidimo da proces počinje,
07:10
even though you can only hold it
168
415000
2000
mada ne možeš dugo da
07:12
for a little bit of time.
169
417000
2000
održiš misao.
07:14
As I said, it's a very difficult process
170
419000
3000
Kažem opet, jako je teško
07:17
to imagine this.
171
422000
2000
zamišljati "nestajanje".
07:19
And the great thing about it is that
172
424000
2000
Ono što je bitno je
07:21
we've only given the software one instance
173
426000
2000
da smo programu samo jednom dali
07:23
of how he thinks about "disappear."
174
428000
3000
kako Evan misli "nestani".
07:26
As there is a machine learning algorithm in this --
175
431000
3000
Program je u stanju da uči --
07:29
(Applause)
176
434000
4000
(aplauz)
07:33
Thank you.
177
438000
2000
Hvala.
07:35
Good job. Good job.
178
440000
3000
Bravo, bravo.
07:38
(Applause)
179
443000
2000
(tapšu)
07:40
Thank you, Evan, you're a wonderful, wonderful
180
445000
3000
Hvala ti, Evane, divno si,
07:43
example of the technology.
181
448000
3000
divno prikazao ovu tehnologiju.
07:46
So, as you can see, before,
182
451000
2000
Kao što vidite,
07:48
there is a leveling system built into this software
183
453000
3000
postoji više nivoa i komandi u progamu,
07:51
so that as Evan, or any user,
184
456000
2000
tako da Evan, i bilo koji drugi korisnik,
07:53
becomes more familiar with the system,
185
458000
2000
kad se privikne na sistem,
07:55
they can continue to add more and more detections,
186
460000
3000
može da dodaje sve više i više obrazaca,
07:58
so that the system begins to differentiate
187
463000
2000
te će sistem biti u stanju da razlikuje
08:00
between different distinct thoughts.
188
465000
3000
više različitih pojedinačnih misli.
08:04
And once you've trained up the detections,
189
469000
2000
A jednom kad se potpuno izvežbate,
08:06
these thoughts can be assigned or mapped
190
471000
2000
te komande se mogu dodeliti ili prebaciti
08:08
to any computing platform,
191
473000
2000
drugim kompjuterskim platformama,
08:10
application or device.
192
475000
2000
programima ili uređajima.
08:12
So I'd like to show you a few examples,
193
477000
2000
Prikazaću vam samo nekoliko primera,
08:14
because there are many possible applications
194
479000
2000
jer ima puno mogućih primena
08:16
for this new interface.
195
481000
2000
za ovaj novi interfejs.
08:19
In games and virtual worlds, for example,
196
484000
2000
U igrama i virtuelnim svetovima,
08:21
your facial expressions
197
486000
2000
vaš izraz lica
08:23
can naturally and intuitively be used
198
488000
2000
se može prirodno i interaktivno koristiti
08:25
to control an avatar or virtual character.
199
490000
3000
da upravljate avatarom ili virtuelnim likom.
08:29
Obviously, you can experience the fantasy of magic
200
494000
2000
Možete iskusiti fantastiku magije
08:31
and control the world with your mind.
201
496000
3000
i kontrolisati svet svojim mislima.
08:36
And also, colors, lighting,
202
501000
3000
Boje, osvetljenje,
08:39
sound and effects
203
504000
2000
zvuk i efekti,
08:41
can dynamically respond to your emotional state
204
506000
2000
sve može dinamički da reaguje na vaše raspoloženje
08:43
to heighten the experience that you're having, in real time.
205
508000
3000
da dodatno pojača doživljaj.
08:47
And moving on to some applications
206
512000
2000
Evo nekih primena
08:49
developed by developers and researchers around the world,
207
514000
3000
razvijanih širom sveta
08:52
with robots and simple machines, for example --
208
517000
3000
sa robotima i jednostavnim uređajima.
08:55
in this case, flying a toy helicopter
209
520000
2000
Ovo je mali helikopter,
08:57
simply by thinking "lift" with your mind.
210
522000
3000
koji poleće na misaonu komandu "poleti".
09:00
The technology can also be applied
211
525000
2000
Ista tehnologija se može primeniti
09:02
to real world applications --
212
527000
2000
u svakodnevnom životu,
09:04
in this example, a smart home.
213
529000
2000
recimo u "pametnoj kući".
09:06
You know, from the user interface of the control system
214
531000
3000
Iz interfejsa kontrolog sistema možete
09:09
to opening curtains
215
534000
2000
razvući zavese,
09:11
or closing curtains.
216
536000
3000
navući zavese.
09:22
And of course, also to the lighting --
217
547000
3000
Naravno, osvetljenje.
09:25
turning them on
218
550000
3000
Možete paliti
09:28
or off.
219
553000
2000
ili gasiti svetla.
09:30
And finally,
220
555000
2000
I najzad,
09:32
to real life-changing applications,
221
557000
2000
primene koje menjaju živote ljudima,
09:34
such as being able to control an electric wheelchair.
222
559000
3000
poput mogućnosti da se upravlja električnim kolicima.
09:37
In this example,
223
562000
2000
U ovom primeru,
09:39
facial expressions are mapped to the movement commands.
224
564000
3000
izrazi lica se povezuju na kontrole kretanja.
09:42
Man: Now blink right to go right.
225
567000
3000
"Sad namigni desnim da skreneš desno."
09:50
Now blink left to turn back left.
226
575000
3000
"Sad levim, da skreneš levo."
10:02
Now smile to go straight.
227
587000
3000
"Sad se smeši da ideš pravo."
10:08
TL: We really -- Thank you.
228
593000
2000
TL: Hvala...
10:10
(Applause)
229
595000
5000
(aplauz)
10:15
We are really only scratching the surface of what is possible today,
230
600000
3000
Stvarno smo tek na početku shvatanja šta je sve sa ovim moguće.
10:18
and with the community's input,
231
603000
2000
A sa uplivom zajednice,
10:20
and also with the involvement of developers
232
605000
2000
sa tehničkom saradnjom,
10:22
and researchers from around the world,
233
607000
3000
sa istraživačima širom sveta,
10:25
we hope that you can help us to shape
234
610000
2000
nadamo se da ćete nam pomoći da
10:27
where the technology goes from here. Thank you so much.
235
612000
3000
oblikujemo budućnost ove tehnologije. 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