TEDGlobal 2010
Tan Le: A headset that reads your brainwaves
Tan Le: 解讀腦電波的頭戴式耳機
Filmed:
Readability: 5
2,732,929 views
Tan Le 展示一個影響深遠應用程式，只需要運用意念和一點專注力，這令人耳目一新的電腦界面可以透過頭戴式耳機來解讀使用者的大腦電波，從而控制虛擬物件和家電用品。
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
直到現在，我們與機器的溝通
00:18
has always been limited
1
3000
2000
仍局限於
00:20
to conscious and direct forms.
2
5000
2000
有意識和直接的模式
00:22
Whether it's something simple
3
7000
2000
不論是一些簡單的事情
00:24
like turning on the lights with a switch,
4
9000
2000
如用開關開燈
00:26
or even as complex as programming robotics,
5
11000
3000
或一些複雜的程式來控制機械人
00:29
we have always had to give a command to a machine,
6
14000
3000
我們都要給機器輸入一個
00:32
or even a series of commands,
7
17000
2000
甚至一系列的指令
00:34
in order for it to do something for us.
8
19000
3000
才能命令它執行一些動作
00:37
Communication between people, on the other hand,
9
22000
2000
相反的，人與人的溝通
00:39
is far more complex and a lot more interesting
10
24000
3000
就更加複雜和有趣得多
00:42
because we take into account
11
27000
2000
因為我們會考慮到
00:44
so much more than what is explicitly expressed.
12
29000
3000
言語未表達的言外之意
00:47
We observe facial expressions, body language,
13
32000
3000
我們會觀察表情、肢體語言
00:50
and we can intuit feelings and emotions
14
35000
2000
在對話中我們會用直覺來
00:52
from our dialogue with one another.
15
37000
3000
感受對方的感覺和情緒
00:55
This actually forms a large part
16
40000
2000
這些都是做決定時
00:57
of our decision-making process.
17
42000
2000
一些重要的因素
00:59
Our vision is to introduce
18
44000
2000
我們的願景是引進
01:01
this whole new realm of human interaction
19
46000
3000
全新的人與電腦的互動科技
01:04
into human-computer interaction
20
49000
2000
到人類互動的領域
01:06
so that computers can understand
21
51000
2000
這麼一來電腦不只可以
01:08
not only what you direct it to do,
22
53000
2000
明白你指示它所做的事情
01:10
but it can also respond
23
55000
2000
而且也會對面部表情
01:12
to your facial expressions
24
57000
2000
和情緒經歷
01:14
and emotional experiences.
25
59000
2000
作出反應
01:16
And what better way to do this
26
61000
2000
還有什麼比從大腦的
01:18
than by interpreting the signals
27
63000
2000
情感控制中樞直接解譯
01:20
naturally produced by our brain,
28
65000
2000
大腦產生的電波
01:22
our center for control and experience.
29
67000
3000
來得更好呢？
01:25
Well, it sounds like a pretty good idea,
30
70000
2000
這聽起來好像是不錯的主意
01:27
but this task, as Bruno mentioned,
31
72000
2000
但這個任務，正如Bruno所說
01:29
isn't an easy one for two main reasons:
32
74000
3000
並不容易，原因有兩個
01:32
First, the detection algorithms.
33
77000
3000
第一是大腦的偵查演算法
01:35
Our brain is made up of
34
80000
2000
我們的腦是由
01:37
billions of active neurons,
35
82000
2000
數十億個活躍的神經元所組成
01:39
around 170,000 km
36
84000
3000
如果把神經細胞的軸索連在一起
01:42
of combined axon length.
37
87000
2000
大概有十七萬公里
01:44
When these neurons interact,
38
89000
2000
這些神經元互動時
01:46
the chemical reaction emits an electrical impulse,
39
91000
2000
產生的化學作用所發射出的電脈衝
01:48
which can be measured.
40
93000
2000
能夠被測量到
01:50
The majority of our functional brain
41
95000
3000
大部分功能性腦
01:53
is distributed over
42
98000
2000
是分佈在
01:55
the outer surface layer of the brain,
43
100000
2000
大腦的表層
01:57
and to increase the area that's available for mental capacity,
44
102000
3000
心智能力功能也位於此，為了增加表面積
02:00
the brain surface is highly folded.
45
105000
3000
大腦皮質層有非常多的褶皺
02:03
Now this cortical folding
46
108000
2000
大腦皮質褶皺
02:05
presents a significant challenge
47
110000
2000
對分析電脈衝
02:07
for interpreting surface electrical impulses.
48
112000
3000
帶來一個很大的挑戰
02:10
Each individual's cortex
49
115000
2000
每個人大腦皮質層
02:12
is folded differently,
50
117000
2000
的褶皺都不同
02:14
very much like a fingerprint.
51
119000
2000
就像指紋一樣
02:16
So even though a signal
52
121000
2000
因此電脈衝訊息
02:18
may come from the same functional part of the brain,
53
123000
3000
雖然來自功能腦同樣的區域
02:21
by the time the structure has been folded,
54
126000
2000
但大腦皮質褶皺結構早已形成
02:23
its physical location
55
128000
2000
在不同的人的大腦裡
02:25
is very different between individuals,
56
130000
2000
即使是雙胞胎
02:27
even identical twins.
57
132000
3000
訊息發生位置也不同
02:30
There is no longer any consistency
58
135000
2000
大腦皮質層電脈衝訊息
02:32
in the surface signals.
59
137000
2000
沒有一致性
02:34
Our breakthrough was to create an algorithm
60
139000
2000
我們的突破是建立一個演算法
02:36
that unfolds the cortex,
61
141000
2000
攤開大腦皮質層
02:38
so that we can map the signals
62
143000
2000
去勘測這些
02:40
closer to its source,
63
145000
2000
訊息的原點
02:42
and therefore making it capable of working across a mass population.
64
147000
3000
繼而把它運用在大眾身上
02:46
The second challenge
65
151000
2000
第二項挑戰是
02:48
is the actual device for observing brainwaves.
66
153000
3000
觀察腦電波的儀器
02:51
EEG measurements typically involve
67
156000
2000
腦波測量基本上包括
02:53
a hairnet with an array of sensors,
68
158000
3000
一個有許多感應器的髮網
02:56
like the one that you can see here in the photo.
69
161000
3000
就像現在圖中所看到的
02:59
A technician will put the electrodes
70
164000
2000
技術人員會把電極
03:01
onto the scalp
71
166000
2000
用導電的膠或漿糊
03:03
using a conductive gel or paste
72
168000
2000
固定在頭皮上
03:05
and usually after a procedure of preparing the scalp
73
170000
3000
這個準備程序需要在頭皮製造
03:08
by light abrasion.
74
173000
2000
輕微的擦傷
03:10
Now this is quite time consuming
75
175000
2000
這個程序既費時
03:12
and isn't the most comfortable process.
76
177000
2000
又不舒服
03:14
And on top of that, these systems
77
179000
2000
再加上，這些系統
03:16
actually cost in the tens of thousands of dollars.
78
181000
3000
非常昂貴，得花上數萬美金
03:20
So with that, I'd like to invite onstage
79
185000
3000
現在，我邀請Evan Grant
03:23
Evan Grant, who is one of last year's speakers,
80
188000
2000
去年的演講者上台
03:25
who's kindly agreed
81
190000
2000
他很樂意
03:27
to help me to demonstrate
82
192000
2000
幫忙示範
03:29
what we've been able to develop.
83
194000
2000
我們所設計的儀器
03:31
(Applause)
84
196000
6000
(鼓掌)
03:37
So the device that you see
85
202000
2000
你們所看到的儀器是
03:39
is a 14-channel, high-fidelity
86
204000
2000
有十四個頻道，高傳真的
03:41
EEG acquisition system.
87
206000
2000
腦電波訊號擷取系統
03:43
It doesn't require any scalp preparation,
88
208000
3000
不需要任何頭皮準備程序
03:46
no conductive gel or paste.
89
211000
2000
沒有導電的膠或漿糊
03:48
It only takes a few minutes to put on
90
213000
3000
戴上它，等訊號穩定
03:51
and for the signals to settle.
91
216000
2000
只要幾分鐘
03:53
It's also wireless,
92
218000
2000
而且是無線的
03:55
so it gives you the freedom to move around.
93
220000
3000
它讓你活動自如
03:58
And compared to the tens of thousands of dollars
94
223000
3000
比起那些幾萬美元的
04:01
for a traditional EEG system,
95
226000
3000
傳統腦電波系統
04:04
this headset only costs
96
229000
2000
這個頭戴式耳機
04:06
a few hundred dollars.
97
231000
2000
只要幾百美金
04:08
Now on to the detection algorithms.
98
233000
3000
現在來談談大腦感應演算法
04:11
So facial expressions --
99
236000
2000
好，面部表情--
04:13
as I mentioned before in emotional experiences --
100
238000
2000
如同之前講到的情緒經驗--
04:15
are actually designed to work out of the box
101
240000
2000
這套系統有令人意想不到的設計
04:17
with some sensitivity adjustments
102
242000
2000
只要做一些敏感度調整
04:19
available for personalization.
103
244000
3000
就可以運用於個人化的使用
04:22
But with the limited time we have available,
104
247000
2000
但因時間的關係
04:24
I'd like to show you the cognitive suite,
105
249000
2000
現在只示範認知的部份
04:26
which is the ability for you
106
251000
2000
這套系統能夠讓您
04:28
to basically move virtual objects with your mind.
107
253000
3000
只用意念移動虛擬物件
04:32
Now, Evan is new to this system,
108
257000
2000
Evan是第一次接觸這個系統
04:34
so what we have to do first
109
259000
2000
因此我們要先
04:36
is create a new profile for him.
110
261000
2000
建立一個新的檔案
04:38
He's obviously not Joanne -- so we'll "add user."
111
263000
3000
他當然不是Joanne， 所以要增加一個用戶
04:41
Evan. Okay.
112
266000
2000
Evan，好了!
04:43
So the first thing we need to do with the cognitive suite
113
268000
3000
首先要做的是
04:46
is to start with training
114
271000
2000
練習發出一個
04:48
a neutral signal.
115
273000
2000
中立的訊號
04:50
With neutral, there's nothing in particular
116
275000
2000
Evan不需要做
04:52
that Evan needs to do.
117
277000
2000
什麼特別的事
04:54
He just hangs out. He's relaxed.
118
279000
2000
就這樣放輕鬆
04:56
And the idea is to establish a baseline
119
281000
2000
重點是建立一個基準線
04:58
or normal state for his brain,
120
283000
2000
或是大腦的正常狀態
05:00
because every brain is different.
121
285000
2000
因為每個人的腦都不相同
05:02
It takes eight seconds to do this,
122
287000
2000
這大概需要八秒的時間
05:04
and now that that's done,
123
289000
2000
完成了
05:06
we can choose a movement-based action.
124
291000
2000
我們可以選擇一個有動作的活動
05:08
So Evan, choose something
125
293000
2000
Evan，你可選擇一個
05:10
that you can visualize clearly in your mind.
126
295000
2000
在你腦海中可以清楚看到的事情
05:12
Evan Grant: Let's do "pull."
127
297000
2000
讓我們做一個"拉"的動作
05:14
Tan Le: Okay, so let's choose "pull."
128
299000
2000
好，點選"拉"
05:16
So the idea here now
129
301000
2000
我們現在
05:18
is that Evan needs to
130
303000
2000
需要Evan想像
05:20
imagine the object coming forward
131
305000
2000
一件物品在螢幕上
05:22
into the screen,
132
307000
2000
往前移動
05:24
and there's a progress bar that will scroll across the screen
133
309000
3000
他這樣做的時候
05:27
while he's doing that.
134
312000
2000
螢幕上會出現一個測量棒
05:29
The first time, nothing will happen,
135
314000
2000
第一次沒有任何事情發生
05:31
because the system has no idea how he thinks about "pull."
136
316000
3000
因為系統還不知道他怎麼想像"拉"的動作
05:34
But maintain that thought
137
319000
2000
在這八秒中
05:36
for the entire duration of the eight seconds.
138
321000
2000
持續想著這個念頭
05:38
So: one, two, three, go.
139
323000
3000
一、二、三、開始
05:49
Okay.
140
334000
2000
好了
05:51
So once we accept this,
141
336000
2000
當我們按了接受
05:53
the cube is live.
142
338000
2000
這個方塊就活了起來
05:55
So let's see if Evan
143
340000
2000
讓我們看看Evan
05:57
can actually try and imagine pulling.
144
342000
3000
能否真的嘗試想像"拉"的動作
06:00
Ah, good job!
145
345000
2000
哇! 非常好!
06:02
(Applause)
146
347000
3000
(鼓掌)
06:05
That's really amazing.
147
350000
2000
真是令人驚訝！
06:07
(Applause)
148
352000
4000
(鼓掌)
06:11
So we have a little bit of time available,
149
356000
2000
我們還有一些時間
06:13
so I'm going to ask Evan
150
358000
2000
我要請Evan
06:15
to do a really difficult task.
151
360000
2000
做一些比較困難的動作
06:17
And this one is difficult
152
362000
2000
這個有點難
06:19
because it's all about being able to visualize something
153
364000
3000
因為要想像
06:22
that doesn't exist in our physical world.
154
367000
2000
在物質界裡不存在的事物
06:24
This is "disappear."
155
369000
2000
就是 "消失"
06:26
So what you want to do -- at least with movement-based actions,
156
371000
2000
就動作而言
06:28
we do that all the time, so you can visualize it.
157
373000
3000
因為經常做這些動作，所以能"看見"它
06:31
But with "disappear," there's really no analogies --
158
376000
2000
但"消失"沒有任何類似的動作
06:33
so Evan, what you want to do here
159
378000
2000
Evan, 現在請你
06:35
is to imagine the cube slowly fading out, okay.
160
380000
3000
想像這個方塊慢慢消失
06:38
Same sort of drill. So: one, two, three, go.
161
383000
3000
一樣的練習。 一、二、三、開始
06:50
Okay. Let's try that.
162
395000
3000
可以了，我們試試吧
06:53
Oh, my goodness. He's just too good.
163
398000
3000
我的天啊！他真的是非常厲害
06:57
Let's try that again.
164
402000
2000
再試一次
07:04
EG: Losing concentration.
165
409000
2000
（EG儀器:） 失去專注力
07:06
(Laughter)
166
411000
2000
(笑聲)
07:08
TL: But we can see that it actually works,
167
413000
2000
這套系統真的辦到了
07:10
even though you can only hold it
168
415000
2000
雖然只維持
07:12
for a little bit of time.
169
417000
2000
一段很短的時間
07:14
As I said, it's a very difficult process
170
419000
3000
我認為想像"消失"
07:17
to imagine this.
171
422000
2000
真的是非常困難
07:19
And the great thing about it is that
172
424000
2000
這個系統了不起的是
07:21
we've only given the software one instance
173
426000
2000
這套軟體只有一次機會
07:23
of how he thinks about "disappear."
174
428000
3000
知道Evan是怎麼想像"消失"的
07:26
As there is a machine learning algorithm in this --
175
431000
3000
而這部機器便學會了演算它
07:29
(Applause)
176
434000
4000
(鼓掌)
07:33
Thank you.
177
438000
2000
謝謝
07:35
Good job. Good job.
178
440000
3000
很棒！很棒！
07:38
(Applause)
179
443000
2000
(鼓掌)
07:40
Thank you, Evan, you're a wonderful, wonderful
180
445000
3000
謝謝，Evan你真的是這項科技
07:43
example of the technology.
181
448000
3000
最佳的展示人員
07:46
So, as you can see, before,
182
451000
2000
正如你們所見
07:48
there is a leveling system built into this software
183
453000
3000
這個軟體有一個水準測量系統
07:51
so that as Evan, or any user,
184
456000
2000
Evan或其他使用者
07:53
becomes more familiar with the system,
185
458000
2000
對這個系統越熟悉
07:55
they can continue to add more and more detections,
186
460000
3000
就能不斷地增加更多，更多的檢測項目
07:58
so that the system begins to differentiate
187
463000
2000
這個系統就能開始分辨
08:00
between different distinct thoughts.
188
465000
3000
不同的明顯想法
08:04
And once you've trained up the detections,
189
469000
2000
當你訓練做這些檢測項目
08:06
these thoughts can be assigned or mapped
190
471000
2000
這些念頭、想法就能指定或聯繫到
08:08
to any computing platform,
191
473000
2000
任何的電腦平台、
08:10
application or device.
192
475000
2000
應用程式或儀器上
08:12
So I'd like to show you a few examples,
193
477000
2000
讓我為你們展示幾個例子
08:14
because there are many possible applications
194
479000
2000
這個新界面有
08:16
for this new interface.
195
481000
2000
很多可運用的應用程式
08:19
In games and virtual worlds, for example,
196
484000
2000
例如在遊戲或虛擬世界
08:21
your facial expressions
197
486000
2000
你可以用臉部表情
08:23
can naturally and intuitively be used
198
488000
2000
自然、直覺地
08:25
to control an avatar or virtual character.
199
490000
3000
操控遊戲角色或虛擬人物
08:29
Obviously, you can experience the fantasy of magic
200
494000
2000
無庸置疑，你將會親身體驗幻想的魔力
08:31
and control the world with your mind.
201
496000
3000
和運用意念來控制世界
08:36
And also, colors, lighting,
202
501000
3000
顏色，燈光
08:39
sound and effects
203
504000
2000
聲音和音效
08:41
can dynamically respond to your emotional state
204
506000
2000
也可以不斷地變化來反映你的情緒狀態
08:43
to heighten the experience that you're having, in real time.
205
508000
3000
即時強化你的感受
08:47
And moving on to some applications
206
512000
2000
現在來看看應用程式
08:49
developed by developers and researchers around the world,
207
514000
3000
全世界的研發人員發明了
08:52
with robots and simple machines, for example --
208
517000
3000
不同的機械人和簡單的機器，例如
08:55
in this case, flying a toy helicopter
209
520000
2000
這個例子是操作玩具直昇機
08:57
simply by thinking "lift" with your mind.
210
522000
3000
只要用意念就可以讓它飛起來
09:00
The technology can also be applied
211
525000
2000
這項科技也可以應用在
09:02
to real world applications --
212
527000
2000
實際生活中
09:04
in this example, a smart home.
213
529000
2000
看看智能家居的例子
09:06
You know, from the user interface of the control system
214
531000
3000
從使用者界面控制系統
09:09
to opening curtains
215
534000
2000
來打開
09:11
or closing curtains.
216
536000
3000
或關上窗簾
09:22
And of course, also to the lighting --
217
547000
3000
當然電燈也可以
09:25
turning them on
218
550000
3000
開
09:28
or off.
219
553000
2000
或關
09:30
And finally,
220
555000
2000
最後
09:32
to real life-changing applications,
221
557000
2000
是應用在改善真實生活
09:34
such as being able to control an electric wheelchair.
222
559000
3000
例如能夠控制電動輪椅
09:37
In this example,
223
562000
2000
這個例子裡
09:39
facial expressions are mapped to the movement commands.
224
564000
3000
面部表情對應於移動方向的指令
09:42
Man: Now blink right to go right.
225
567000
3000
男聲: 現在眨右眼右轉
09:50
Now blink left to turn back left.
226
575000
3000
眨左眼左轉
10:02
Now smile to go straight.
227
587000
3000
微笑往前
10:08
TL: We really -- Thank you.
228
593000
2000
TL: 我們真的.... 多謝各位。
10:10
(Applause)
229
595000
5000
(鼓掌)
10:15
We are really only scratching the surface of what is possible today,
230
600000
3000
現今我們所做到的只是很小的一部分
10:18
and with the community's input,
231
603000
2000
有研發團隊的投入
10:20
and also with the involvement of developers
232
605000
2000
及全世界的研發和
10:22
and researchers from around the world,
233
607000
3000
研究人員的參與
10:25
we hope that you can help us to shape
234
610000
2000
我們希望這一項科技能夠
10:27
where the technology goes from here. Thank you so much.
235
612000
3000
從這裡一路順利發展。謝謝各位。
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