TED2003
Torsten Reil: Animate characters by evolving them
托司登•里爾 — 研究生物學以製作動畫
Filmed:
Readability: 3.5
363,842 views
托司登•里爾 (Torsten Reil) 介紹了一項能夠模擬人類生物科技，模擬身體及其神經控制系統，這項科技可以以從裡到外都模擬，如骨頭，肌肉以及神經系統。這是他2003年在Ted的演講，你可以在GTA4看到這項技術。
Torsten Reil - Animating neurobiologist
By coding computer simulations with biologically modeled nervous systems, Torsten Reil and his company NaturalMotion breathe life into the animated characters inhabiting the most eye-poppingly realistic games and movies around. Full bio
By coding computer simulations with biologically modeled nervous systems, Torsten Reil and his company NaturalMotion breathe life into the animated characters inhabiting the most eye-poppingly realistic games and movies around. Full bio
Double-click the English transcript below to play the video.
00:15
I'm going to talk about a technology that we're developing at Oxford now,
0
3000
4000
我將向各位介紹一項目前我們正在牛津研究發展的科技
00:19
that we think is going to change the way that
1
7000
3000
我們認為它將改變
00:22
computer games and Hollywood movies are being made.
2
10000
3000
電玩和好萊塢電影的製作方式。
00:26
That technology is simulating humans.
3
14000
3000
這一項科技就是模擬人類，
00:29
It's simulated humans with a simulated body
4
17000
3000
它以模擬的人類身體
00:32
and a simulated nervous system to control that body.
5
20000
3000
及用以控制那身體的模擬神經系統來模擬人類。
00:36
Now, before I talk more about that technology,
6
24000
3000
在往下介紹這項科技之前，
00:39
let's have a quick look at what human characters look like
7
27000
3000
先讓我們看一下現在電玩裡頭
00:42
at the moment in computer games.
8
30000
3000
人物運動的樣子。
00:45
This is a clip from a game called "Grand Theft Auto 3."
9
33000
3000
這是俠盜獵車手 3 的片段，
00:48
We already saw that briefly yesterday.
10
36000
2000
昨天我們有稍微看了一些。
00:50
And what you can see is -- it is actually a very good game.
11
38000
3000
就如你看到的, 它是一個非常棒的遊戲。
00:53
It's one of the most successful games of all time.
12
41000
3000
所有最成功遊戲的其中一個。
00:56
But what you'll see is that all the animations in this game are very repetitive.
13
44000
4000
不過你可以看出遊戲中動畫人物的動作不斷地重覆，
01:00
They pretty much look the same.
14
48000
2000
它們看起來都一樣。
01:02
I've made him run into a wall here, over and over again.
15
50000
3000
這個角色撞上牆之後，
01:05
And you can see he looks always the same.
16
53000
2000
一直重覆一樣的動作。
01:07
The reason for that is that these characters
17
55000
3000
主要的原因是這些角色
01:10
are actually not real characters.
18
58000
2000
並不是真實的人物。
01:12
They are a graphical visualization of a character.
19
60000
4000
他們是一個角色的圖像視覺呈現結果。
01:16
To produce these animations, an animator at a studio has to anticipate
20
64000
5000
遊戲公司裡的動畫師必需先預測
01:21
what's going to happen in the actual game,
21
69000
3000
遊戲中的情節，
01:24
and then has to animate that particular sequence.
22
72000
3000
並針對特定橋段繪製，才能製作出這些動畫。
01:27
So, he or she sits down, animates it, and tries to anticipate what's going to happen,
23
75000
4000
因此動畫師只是坐在那，埋頭繪製並企圖預測將會發生的事，
01:31
and then these particular animations are just played back
24
79000
3000
而這些動畫成果會在遊戲的
01:34
at appropriate times in the computer game.
25
82000
3000
適當時候播放。
01:37
Now, the result of that is that you can't have real interactivity.
26
85000
5000
但這麼做的結果是玩家無法擁有真實的互動。
01:42
All you have is animations that are played back
27
90000
3000
你只能不斷看到
01:45
at more or less the appropriate times.
28
93000
2000
相同的動作
01:47
It also means that games aren't really going to be as surprising as they could be,
29
95000
5000
這也表示遊戲中不會發生驚喜角色
01:52
because you only get out of it, at least in terms of the character,
30
100000
3000
只能做預設的內容
01:55
what you actually put into it.
31
103000
2000
你當時放了什麼在裡面
01:57
There's no real emergence there.
32
105000
2000
因為裡面沒有真實的結合
01:59
And thirdly, as I said, most of the animations are very repetitive because of that.
33
107000
4000
所以大部份的動作只能反覆
02:03
Now, the only way to get around that
34
111000
2000
避免的唯一方法就是實際地
02:05
is to actually simulate the human body
35
113000
2000
模擬人體
02:07
and to simulate that bit of the nervous system of the brain that controls that body.
36
115000
5000
模擬控制的神經系統
02:12
And maybe, if I could have you for a quick demonstration
37
120000
3000
可以請你上來做個簡單示範嗎
02:15
to show what the difference is --
38
123000
2000
看看哪裡不一樣
02:17
because, I mean, it's very, very trivial.
39
125000
4000
這是一個微不足道的現象
02:21
If I push Chris a bit, like this, for example, he'll react to it.
40
129000
3000
如果我推Chris一下，他會產生反應
02:24
If I push him from a different angle, he'll react to it differently,
41
132000
3000
如果我從另一個角度推，他會有不同反應
02:27
and that's because he has a physical body,
42
135000
2000
這是因為他有一個真實的身體
02:29
and because he has the motor skills to control that body.
43
137000
3000
和控制身體的能力
02:32
It's a very trivial thing.
44
140000
2000
這是一個微不足道的
02:34
It's not something you get in computer games at the moment, at all.
45
142000
2000
這是一個與電玩無關的小事
02:36
Thank you very much. Chris Anderson: That's it?
46
144000
2000
謝謝你就這樣。就這樣嗎？
02:38
Torsten Reil: That's it, yes.
47
146000
2000
是的
02:40
So, that's what we're trying to simulate --
48
148000
1000
卻正是我們要模擬的
02:41
not Chris specifically, I should say, but humans in general.
49
149000
4000
不是模擬Chris 而是模擬人體
02:46
Now, we started working on this a while ago at Oxford University,
50
154000
5000
我們在牛津大學開始一段時間了
02:51
and we tried to start very simply.
51
159000
2000
一切從最簡單的事開始
02:53
What we tried to do was teach a stick figure how to walk.
52
161000
3000
也就是教這個火柴人走路
02:56
That stick figure is physically stimulated. You can see it here on the screen.
53
164000
3000
它已經完全地模擬人體
02:59
So, it's subject to gravity, has joints, etc.
54
167000
3000
會受到地心引力影響也有關節
03:02
If you just run the simulation, it will just collapse, like this.
55
170000
3000
一旦啟動模擬它就會像這樣跌倒，就像這樣
03:05
The tricky bit is now to put an AI controller in it
56
173000
4000
困難的部份是加入控制
03:09
that actually makes it work.
57
177000
2000
也就是人工智慧讓它動起來
03:11
And for that, we use the neural network, which we based on
58
179000
3000
我們用在神經系統上的是
03:14
that part of the nervous system that we have in our spine
59
182000
2000
脊椎上控制走路的
03:16
that controls walking in humans.
60
184000
2000
神經網絡
03:18
It's called the central pattern generator.
61
186000
2000
叫中樞模式產生器
03:20
So, we simulated that as well, and then the really tricky bit
62
188000
3000
我們同樣模擬了這套網絡，但真正困難的是
03:23
is to teach that network how to walk.
63
191000
2000
訓練網絡走路
03:25
For that we used artificial evolution -- genetic algorithms.
64
193000
4000
為此我們使用人工演化以取得自然的演算法
03:29
We heard about those already yesterday,
65
197000
2000
我們昨天已聽過這個主題演講
03:31
and I suppose that most of you are familiar with that already.
66
199000
3000
我想大部份的人都蠻熟悉了
03:34
But, just briefly, the concept is that
67
202000
2000
但是，簡單地來說， 它的概念
03:36
you create a large number of different individuals --
68
204000
3000
就是要產生大量不同的個體
03:39
neural networks, in this case --
69
207000
2000
以這個例子來說
03:41
all of which are random at the beginning.
70
209000
2000
起初所有個體都是亂數產生
03:43
You hook these up -- in this case, to the virtual muscles
71
211000
2000
再將它們連結火柴人的虛擬肌肉
03:45
of that two-legged creature here --
72
213000
3000
火柴人的虛擬肌肉
03:48
and hope that it does something interesting.
73
216000
3000
希望它可以做出有趣的事
03:51
At the beginning, they're all going to be very boring.
74
219000
2000
一開始挺無聊的
03:53
Most of them won't move at all,
75
221000
2000
大部份火柴人不會動
03:55
but some of them might make a tiny step.
76
223000
2000
但有些會走小步路
03:57
Those are then selected by the algorithm,
77
225000
2000
這些演算法就會被選用
03:59
reproduced with mutation and recombinations to introduce sex as well.
78
227000
4000
加上突變和重組之後進行繁殖
04:03
And you repeat that process over and over again,
79
231000
2000
接下來不斷重覆這些步驟
04:05
until you have something that walks --
80
233000
2000
直到它能像這樣走直線
04:07
in this case, in a straight line, like this.
81
235000
2000
這就是它背後的概念
04:09
So that was the idea behind this.
82
237000
2000
現在我們開始示範
04:11
When we started this, I set up the simulation one evening.
83
239000
3000
我在前一天晚上設定完畢
04:14
It took about three to four hours to run the simulation.
84
242000
3000
花幾個小時執行模擬運算
04:17
I got up the next morning, went to the computer and looked at the results,
85
245000
4000
隔天早晨回來檢查成果
04:21
and was hoping for something that walked in a straight line,
86
249000
3000
我希望能看到它走直線
04:24
like I've just demonstrated,
87
252000
2000
就像我所證明的一樣
04:26
and this is what I got instead.
88
254000
2000
但這卻是我得到的
04:28
(Laughter)
89
256000
10000
(笑聲)
04:38
So, it was back to the drawing board for us.
90
266000
3000
結果它變成關節
04:42
We did get it to work eventually,
91
270000
3000
所以我們做了些許調整
04:45
after tweaking a bit here and there.
92
273000
2000
最後還是成功了
04:47
And this is an example of a successful evolutionary run.
93
275000
3000
人工演化成功地運行
04:50
So, what you'll see in a moment is a very simple biped
94
278000
3000
待會將看到一個簡易的雙足生物
04:53
that's learning how to walk using artificial evolution.
95
281000
3000
藉由人工演化學習如何走路
04:56
At the beginning, it can't walk at all,
96
284000
2000
一開始它完全不會走路
04:58
but it will get better and better over time.
97
286000
2000
但是有愈來愈進步
05:02
So, this is the one that can't walk at all.
98
290000
3000
這個完全不能走路
05:05
(Laughter)
99
293000
6000
(笑聲)
05:11
Now, after five generations of applying evolutionary process,
100
299000
3000
然後我們改變演算法
05:14
the genetic algorithm is getting a tiny bit better.
101
302000
3000
在演化的第五次演算它有點好轉
05:17
(Laughter)
102
305000
8000
(笑聲)
05:25
Generation 10 and it'll take a few steps more --
103
313000
2000
第十次演算能夠往前走幾步
05:31
still not quite there.
104
319000
2000
但還是沒有成功
05:34
But now, after generation 20, it actually walks in a straight line without falling over.
105
322000
5000
到了第二十次演算它完全成功，不但能走直線也不會跌倒
05:40
That was the real breakthrough for us.
106
328000
3000
對我們來說是一個突破
05:43
It was, academically, quite a challenging project,
107
331000
3000
這是一個很有挑戰性的計劃
05:46
and once we had reached that stage, we were quite confident
108
334000
3000
一旦發展到下個階段，我們相當有信心
05:49
that we could try and do other things as well with this approach --
109
337000
3000
我們相信能以同樣的方法，讓它做其他事
05:52
actually simulating the body
110
340000
2000
模擬人體
05:54
and simulating that part of the nervous system that controls it.
111
342000
3000
及其控制神經系統
05:57
Now, at this stage, it also became clear that this could be very exciting
112
345000
3000
到了這個階段對電玩和線上遊戲
06:00
for things like computer games or online worlds.
113
348000
3000
無疑地是一個興奮的消息
06:03
What you see here is the character standing there,
114
351000
2000
你們可以看到一個角色站在那兒
06:05
and there's an obstacle that we put in its way.
115
353000
2000
在那裡我們放了一個障礙物
06:07
And what you see is, it's going to fall over the obstacle.
116
355000
5000
它會在絆到障礙物時跌倒
06:12
Now, the interesting bit is, if I move the obstacle a tiny bit to the right,
117
360000
3000
現在有趣的是，如果現在我把障礙物挪右邊一點
06:15
which is what I'm doing now, here,
118
363000
2000
就跟我現在做的一樣
06:17
it will fall over it in a completely different way.
119
365000
4000
它會以完全不同的方式跌倒
06:24
And again, if you move the obstacle a tiny bit, it'll again fall differently.
120
372000
5000
再把障礙物挪右邊一點，它還是會以不同的方式跌倒
06:29
(Laughter)
121
377000
2000
(笑聲)
06:31
Now, what you see, by the way, at the top there,
122
379000
2000
對了，畫面上方顯示的是
06:33
are some of the neural activations being fed into the virtual muscles.
123
381000
3000
虛擬肌肉系統的神經運動
06:36
Okay. That's the video. Thanks.
124
384000
2000
以上就是我的示範影片。謝謝
06:38
Now, this might look kind of trivial, but it's actually very important
125
386000
3000
這或許微不足道但卻很重要
06:41
because this is not something you get at the moment
126
389000
2000
現在的虛擬的世界
06:43
in any interactive or any virtual worlds.
127
391000
2000
並沒有達到互動
06:48
Now, at this stage, we decided to start a company and move this further,
128
396000
3000
發展到這個階段，我們決定要開一家公司繼續發展下去
06:51
because obviously this was just a very simple, blocky biped.
129
399000
3000
這不過是一個簡單的雙足生物
06:54
What we really wanted was a full human body.
130
402000
2000
我們的目標要模擬人體全身
06:56
So we started the company.
131
404000
1000
所以我們開了一家公司
06:57
We hired a team of physicists, software engineers and biologists
132
405000
5000
聘了物理學家軟體工程師生物學家
07:02
to work on this, and the first thing we had to work on
133
410000
3000
第一個任務就是
07:05
was to create the human body, basically.
134
413000
4000
建造一個人體
07:09
It's got to be relatively fast, so you can run it on a normal machine,
135
417000
3000
它得輕巧以便在一般機器上執行
07:12
but it's got to be accurate enough, so it looks good enough, basically.
136
420000
3000
外觀也要準確好看
07:15
So we put quite a bit of biomechanical knowledge into this thing,
137
423000
3000
我們也加了不少生化科技進去
07:18
and tried to make it as realistic as possible.
138
426000
4000
盡力把它做得精巧
07:22
What you see here on the screen right now
139
430000
2000
你們現在看到的是
07:24
is a very simple visualization of that body.
140
432000
2000
簡易的外型可以輕易地加上頭髮衣物等
07:26
I should add that it's very simple to add things like hair, clothes, etc.,
141
434000
4000
我應該要加一些簡單的東西，如頭髮、衣服等等
07:30
but what we've done here is use a very simple visualization,
142
438000
3000
我們現在只是用簡單的方式
07:33
so you can concentrate on the movement.
143
441000
2000
所以你們可以專注在它的動作
07:35
Now, what I'm going to do right now, in a moment,
144
443000
3000
我們現在要做的是
07:38
is just push this character a tiny bit and we'll see what happens.
145
446000
3000
輕推它一下，看看會怎麼樣
07:46
Nothing really interesting, basically.
146
454000
2000
沒什麼有趣的事發生
07:48
It falls over, but it falls over like a rag doll, basically.
147
456000
3000
它像個布娃娃一樣跌倒
07:51
The reason for that is that there's no intelligence in it.
148
459000
3000
因為還沒有為它加入人工智慧
07:54
It becomes interesting when you put artificial intelligence into it.
149
462000
4000
如果加上會產生有趣的結果
07:58
So, this character now has motor skills in the upper body --
150
466000
4000
現在它的上半身可以做很多動作
08:02
nothing in the legs yet, in this particular one.
151
470000
2000
下半身則未放入任何東西
08:04
But what it will do -- I'm going to push it again.
152
472000
3000
我現在再次推倒它
08:07
It will realize autonomously that it's being pushed.
153
475000
2000
它知道自己被推了
08:09
It's going to stick out its hands.
154
477000
2000
它會伸出手
08:11
It's going to turn around into the fall, and try and catch the fall.
155
479000
3000
轉身試圖不摔倒
08:20
So that's what you see here.
156
488000
2000
就像這樣
08:22
Now, it gets really interesting
157
490000
2000
把人工智慧加到下半身
08:24
if you then add the AI for the lower part of the body as well.
158
492000
4000
會更有趣
08:28
So here, we've got the same character.
159
496000
2000
現在使用同一個角色
08:30
I'm going to push it a bit harder now,
160
498000
2000
當我更用力地推它
08:32
harder than I just pushed Chris.
161
500000
2000
就像我推Chris一樣
08:34
But what you'll see is -- it's going to receive a push now from the left.
162
502000
4000
它會試圖抵抗左邊來的力量
08:41
What you see is it takes steps backwards,
163
509000
2000
你們可以看到它先退了一步
08:43
it tries to counter-balance,
164
511000
2000
試著保持平衡
08:45
it tries to look at the place where it thinks it's going to land.
165
513000
4000
眼睛還會看向
08:49
I'll show you this again.
166
517000
2000
我再播一次
08:51
And then, finally hits the floor.
167
519000
3000
最後它才跌倒
08:55
Now, this becomes really exciting
168
523000
3000
這是非常有趣的
08:58
when you push that character in different directions, again, just as I've done.
169
526000
5000
如果你把它推向不同的方向，就像我剛剛做的一樣
09:03
That's something that you cannot do right now.
170
531000
4000
這是現在的遊戲做不到的
09:07
At the moment, you only have empty computer graphics in games.
171
535000
3000
這裡頭可沒有預設動作
09:10
What this is now is a real simulation. That's what I want to show you now.
172
538000
3000
這才是真實的模擬，也就是我現在要展示的
09:13
So, here's the same character with the same behavior I've just shown you,
173
541000
3000
再次現在使用同一個角色
09:16
but now I'm just going to push it from different directions.
174
544000
2000
我把它推到不同方向
09:18
First, starting with a push from the right.
175
546000
2000
第一次是往右推
09:23
This is all slow motion, by the way, so we can see what's going on.
176
551000
3000
這些是慢動作影片讓你們能看清楚
09:26
Now, the angle will have changed a tiny bit,
177
554000
3000
現在角度變了
09:29
so you can see that the reaction is different.
178
557000
4000
它倒下的方向也變了
09:33
Again, a push, now this time from the front.
179
561000
3000
下一次我從前面推
09:37
And you see it falls differently.
180
565000
2000
看它跌倒的方式不一樣
09:39
And now from the left --
181
567000
2000
從左邊推
09:43
and it falls differently.
182
571000
2000
它跌倒的方式也不同
09:45
That was really exciting for us to see that.
183
573000
2000
我們對此結果感到十分高興
09:47
That was the first time we've seen that.
184
575000
2000
這是本計畫結果第一次公開
09:49
This is the first time the public sees this as well,
185
577000
2000
我們還沒有讓任何人看過
09:51
because we have been in stealth mode.
186
579000
2000
因為我們是祕密進行的
09:53
I haven't shown this to anybody yet.
187
581000
2000
我還沒有把這個給任何人看過
09:55
Now, just a fun thing:
188
583000
2000
現在來點有趣的
09:57
what happens if you put that character --
189
585000
2000
它會發生的事是
09:59
this is now a wooden version of it, but it's got the same AI in it --
190
587000
2000
這是木頭人的版本有相同的智慧
10:01
but if you put that character on a slippery surface, like ice.
191
589000
2000
如果把它放到平滑的冰面
10:03
We just did that for a laugh, just to see what happens.
192
591000
3000
我們這麼試只想看點滑稽的東西
10:06
(Laughter)
193
594000
1000
(笑聲)
10:07
And this is what happens.
194
595000
2000
而結果是這樣
10:09
(Laughter)
195
597000
3000
(笑聲)
10:12
(Applause)
196
600000
3000
(掌聲)
10:15
It's nothing we had to do about this.
197
603000
2000
我們不需要在它身上做什麼
10:17
We just took this character that I just talked about,
198
605000
2000
只是把它
10:19
put it on a slippery surface, and this is what you get out of it.
199
607000
3000
放在平滑表面就能得到這個結果
10:22
And that's a really fascinating thing about this approach.
200
610000
3000
這就是我們的模擬方法神奇之處
10:26
Now, when we went to film studios and games developers
201
614000
3000
當這項技術介紹給電玩公司時
10:29
and showed them that technology, we got a very good response.
202
617000
3000
介紹給電玩公司時，我們得到很好的回應
10:32
And what they said was, the first thing they need immediately is virtual stuntmen.
203
620000
4000
他們的第一個反應是用在特技演員
10:36
Because stunts are obviously very dangerous, they're very expensive,
204
624000
4000
因為特技很危險很貴
10:40
and there are a lot of stunt scenes that you cannot do, obviously,
205
628000
2000
還有更多的特技鏡頭是做不到的
10:42
because you can't really allow the stuntman to be seriously hurt.
206
630000
3000
因為不能讓特技演員受傷
10:45
So, they wanted to have a digital version of a stuntman
207
633000
3000
所以他們想要數位的特技演員
10:48
and that's what we've been working on for the past few months.
208
636000
2000
這正是我們過去幾個月來的工作
10:50
And that's our first product that we're going to release in a couple of weeks.
209
638000
5000
我們很榮幸能在幾個星期內發表
10:55
So, here are just a few very simple scenes of the guy just being kicked.
210
643000
5000
這裡有幾個簡單的鏡頭，一個傢伙被踢
11:00
That's what people want. That's what we're giving them.
211
648000
2000
那是他們要的，這是我們給的
11:02
(Laughter)
212
650000
7000
(笑聲)
11:09
You can see, it's always reacting.
213
657000
2000
你們可以看到不停地表演
11:11
This is not a dead body. This is a body who basically, in this particular case,
214
659000
4000
一點都不僵硬，在這個鏡頭
11:15
feels the force and tries to protect its head.
215
663000
2000
他試著平衡也會保護自己的頭
11:17
Only, I think it's quite a big blow again.
216
665000
2000
另一個鏡頭又是一記重擊
11:19
You feel kind of sorry for that thing,
217
667000
2000
你們或許為木頭人感到難過
11:21
and we've seen it so many times now that
218
669000
2000
但我們已經看了太多遍了
11:23
we don't really care any more.
219
671000
2000
現在可是一點感覺也沒有
11:25
(Laughter)
220
673000
1000
(笑聲)
11:26
There are much worse videos than this, by the way, which I have taken out, but ...
221
674000
4000
後面還有很多更痛的鏡頭我得拿掉
11:31
Now, here's another one.
222
679000
2000
另一個
11:33
What people wanted as a behavior was to have an explosion,
223
681000
4000
人們想要的是在爆炸之後
11:37
a strong force applied to the character,
224
685000
2000
角色在空中
11:39
and have the character react to it in midair.
225
687000
2000
如何反應強大的力量
11:41
So that you don't have a character that looks limp,
226
689000
2000
它看起來不可以軟綿綿的
11:43
but actually a character that you can use in an action film straight away,
227
691000
3000
它得是可以用在電影裡的角色
11:46
that looks kind of alive in midair as well.
228
694000
2000
能飛在空中看起來有活力
11:48
So this character is going to be hit by a force,
229
696000
2000
現在這個角色會被用力一擊
11:50
it's going to realize it's in the air,
230
698000
2000
它會發現自己在空中
11:52
and it's going to try and, well,
231
700000
3000
而試著抓住些什麼
11:55
stick out its arm in the direction where it's landing.
232
703000
2000
它被推出去然後著地
11:59
That's one angle; here's another angle.
233
707000
3000
這是一個拍攝角度，還有另一個角度
12:02
We now think that the realism we're achieving with this
234
710000
2000
我們認為達到這個程度
12:04
is good enough to be used in films.
235
712000
2000
就已經可以用在電影上
12:06
And let's just have a look at a slightly different visualization.
236
714000
3000
現在我們來看點不一樣的的圖像
12:09
This is something I just got last night
237
717000
2000
這是我昨天拿到的影片
12:11
from an animation studio in London, who are using our software
238
719000
3000
一家倫敦動畫公司正在試用我們軟體
12:14
and experimenting with it right now.
239
722000
2000
現在正在試驗中
12:16
So this is exactly the same behavior that you saw,
240
724000
3000
它會做一樣的動作
12:19
but in a slightly better rendered version.
241
727000
4000
算圖看起來比較漂亮
12:23
So if you look at the character carefully,
242
731000
3000
仔細看身體每一部份
12:26
you see there are lots of body movements going on,
243
734000
2000
都有反應動作
12:28
none of which you have to animate like in the old days.
244
736000
2000
不再像以往得親自調動畫
12:30
Animators had to actually animate them.
245
738000
2000
現在動作
12:32
This is all happening automatically in the simulation.
246
740000
2000
都能自動模擬出來
12:34
This is a slightly different angle,
247
742000
2000
從不同角度看
12:39
and again a slow motion version of this.
248
747000
2000
用慢動作再看一次
12:41
This is incredibly quick. This is happening in real time.
249
749000
4000
這非常快即時運算馬上就能看到
12:45
You can run this simulation in real time, in front of your eyes,
250
753000
2000
你可以執行模擬
12:47
change it, if you want to, and you get the animation straight out of it.
251
755000
3000
馬上調整得到結果
12:50
At the moment, doing something like this by hand
252
758000
2000
如果手動調動畫
12:52
would take you probably a couple of days.
253
760000
2000
大概會花去好幾天
12:55
This is another behavior they requested.
254
763000
3000
他們還要求另一個動作
12:58
I'm not quite sure why, but we've done it anyway.
255
766000
2000
不知道為什麼但我們還要做了
13:00
It's a very simple behavior that shows you the power of this approach.
256
768000
2000
它是很簡單的動作
13:02
In this case, the character's hands
257
770000
2000
這個角色的手
13:04
are fixed to a particular point in space,
258
772000
2000
被固定在一個地方
13:06
and all we've told the character to do is to struggle.
259
774000
3000
可以看出角色在掙扎
13:09
And it looks organic. It looks realistic.
260
777000
3000
看起來不生硬還令人有點不舒服
13:12
You feel kind of sorry for the guy.
261
780000
2000
如果你們為他感到同情
13:14
It's even worse -- and that is another video I just got last night --
262
782000
3000
接下來的畫面更糟，這是我昨晚拿到的片段
13:17
if you render that a bit more realistically.
263
785000
2000
算圖之後看來更真實了
13:23
Now, I'm showing this to you just to show you
264
791000
2000
只是想讓你們看看
13:25
how organic it actually can feel, how realistic it can look.
265
793000
2000
它多麼地寫實
13:27
And this is all a physical simulation of the body,
266
795000
3000
這全是真實模擬的結果
13:30
using AI to drive virtual muscles in that body.
267
798000
3000
用人工智慧驅動虛擬的肌肉
13:35
Now, one thing which we did for a laugh was
268
803000
3000
最後要介紹的是較複雜的特技
13:38
to create a slightly more complex stunt scene,
269
806000
2000
一個最有名的特技鏡頭是
13:40
and one of the most famous stunts is the one where James Bond
270
808000
3000
007的腳被彈力繩綁住
13:43
jumps off a dam in Switzerland and then is caught by a bungee.
271
811000
4000
從瑞士一個水壩一躍而下
13:48
Got a very short clip here.
272
816000
2000
這裡有一個簡短的片段
13:54
Yes, you can just about see it here.
273
822000
2000
就如同你看到的一樣
13:56
In this case, they were using a real stunt man. It was a very dangerous stunt.
274
824000
3000
當時用真人演出十分危險
13:59
It was just voted, I think in the Sunday Times, as one of the most impressive stunts.
275
827000
3000
它被週日時報票選為最令人印象深刻的特技
14:02
Now, we've just tried and -- looked at our character and asked ourselves,
276
830000
3000
我看到這一幕時自問
14:05
"Can we do that ourselves as well?"
277
833000
2000
能不能做到
14:07
Can we use the physical simulation of the character,
278
835000
2000
實際模擬身體
14:09
use artificial intelligence,
279
837000
2000
利用人工智慧
14:11
put that artificial intelligence into the character,
280
839000
2000
並且放入人工智慧
14:13
drive virtual muscles, simulate the way he jumps off the dam,
281
841000
4000
模擬它綁著彈跳繩
14:17
and then skydive afterwards,
282
845000
2000
高空跳下水壩
14:19
and have him caught by a bungee afterwards?
283
847000
2000
捕捉它跳下的畫面
14:21
We did that. It took about altogether just two hours,
284
849000
3000
總共花了二個小時產生模擬
14:24
pretty much, to create the simulation.
285
852000
2000
接近真實創造了模擬
14:26
And that's what it looks like, here.
286
854000
2000
結果看起來是這樣的
14:37
Now, this could do with a bit more work. It's still very early stages,
287
865000
3000
它只是初步階段還需要一些調整
14:40
and we pretty much just did this for a laugh,
288
868000
2000
我們會這樣握只是要讓大家笑一笑
14:42
just to see what we'd get out of it.
289
870000
2000
看看到底可以得到什麼東西
14:44
But what we found over the past few months
290
872000
2000
過去幾個月來
14:46
is that this approach -- that we're pretty much standard upon --
291
874000
3000
我們發現這個方法
14:49
is incredibly powerful.
292
877000
2000
非常強大
14:51
We are ourselves surprised what you actually get out of the simulations.
293
879000
4000
對於模擬的結果令人感到吃驚
14:55
There's very often very surprising behavior that you didn't predict before.
294
883000
4000
有些結果是我們沒有預期的
14:59
There's so many things we can do with this right now.
295
887000
2000
現在它可以做很多事
15:01
The first thing, as I said, is going to be virtual stuntmen.
296
889000
3000
第一虛擬特技演員
15:04
Several studios are using this software now to produce virtual stuntmen,
297
892000
4000
有7家公司已經開始使用這套軟體做數位替身
15:08
and they're going to hit the screen quite soon, actually,
298
896000
2000
很快會在大銀幕上看到
15:10
for some major productions.
299
898000
2000
為知名的產品做模擬
15:12
The second thing is video games.
300
900000
3000
第二電玩
15:15
With this technology, video games will look different and they will feel very different.
301
903000
4000
用這項科技會使電玩看起來大不同
15:19
For the first time, you'll have actors that really feel very interactive,
302
907000
3000
將是第一次角色具有互動感
15:22
that have real bodies that really react.
303
910000
2000
它們有真實的身體對周遭做出反應
15:24
I think that's going to be incredibly exciting.
304
912000
3000
我覺得這真的令人興奮
15:27
Probably starting with sports games,
305
915000
2000
或許從運動遊戲開始
15:29
which are going to become much more interactive.
306
917000
2000
將變得更有互動感
15:31
But I particularly am really excited
307
919000
1000
特別希望看到這科技
15:32
about using this technology in online worlds,
308
920000
3000
用在線上世界
15:35
like there, for example, that Tom Melcher has shown us.
309
923000
3000
像是剛才看到的"There"
15:38
The degree of interactivity you're going to get
310
926000
2000
互動程度將會和現在的遊戲
15:40
is totally different, I think, from what you're getting right now.
311
928000
3000
大不同
15:44
A third thing we are looking at and very interested in is simulation.
312
932000
4000
第三是模擬
15:49
We've been approached by several simulation companies,
313
937000
2000
我們接到很多模擬公司的詢問
15:51
but one project we're particularly excited about, which we're starting next month,
314
939000
3000
其中一項計畫特別令我感到興趣，這個計畫下個月就要開始
15:54
is to use our technology -- and in particular, the walking technology --
315
942000
4000
它將使用我們行走的技術
15:58
to help aid surgeons who work on children with cerebral palsy,
316
946000
4000
幫助兒童腦性麻痺開刀的外科醫生
16:02
to predict the outcome of operations on these children.
317
950000
3000
預測孩子手術的結果
16:05
As you probably know,
318
953000
2000
你們知道
16:07
it's very difficult to predict what the outcome of an operation is
319
955000
3000
矯正腦性麻痺患者的行走的手術結果
16:10
if you try and correct the gait.
320
958000
2000
是很難預測的
16:12
The classic quote is, I think, it's unpredictable at best,
321
960000
3000
我覺得這是現下最難的
16:15
is what people think right now, is the outcome.
322
963000
3000
是人們的想法
16:18
Now, what we want to do with our software is allow our surgeons to have a tool.
323
966000
4000
我們會提供醫師另一套工具
16:22
We're going to simulate the gait of a particular child
324
970000
3000
模擬小朋友的步行
16:25
and the surgeon can then work on that simulation
325
973000
3000
手術可以依照模擬的結果去進行
16:28
and try out different ways to improve that gait,
326
976000
2000
所以他可以在手術之前進行模擬
16:30
before he actually commits to an actual surgery.
327
978000
3000
從不同的矯正結果中找出最好的，再進行手術
16:33
That's one project we're particularly excited about,
328
981000
2000
這就是我們特別興奮的計劃
16:35
and that's going to start next month.
329
983000
2000
它下個月就會開始
16:39
Just finally, this is only just the beginning.
330
987000
3000
最後，這只是一開始的結果
16:42
We can only do several behaviors right now.
331
990000
2000
我們現在只能做出幾個行為模式
16:44
The AI isn't good enough to simulate a full human body.
332
992000
3000
現在它的人工智慧還無法模擬全身
16:47
The body yes, but not all the motor skills that we have.
333
995000
3000
可以做出軀體但是還沒能做出所有動作
16:50
And, I think, we're only there if we can have something like ballet dancing.
334
998000
3000
不過很快它就能做出芭蕾的動作
16:53
Right now, we don't have that
335
1001000
2000
雖然現在我們沒有芭蕾舞動作
16:55
but I'm very sure that we will be able to do that at some stage.
336
1003000
2000
但是我知道總有一天我們可以做出來的
16:57
We do have one unintentional dancer actually,
337
1005000
3000
事實上我們不小心模擬出芭蕾舞蹈
17:00
the last thing I'm going to show you.
338
1008000
2000
這裡有一個偶然的成果是我最後想展示給大家看的
17:02
This was an AI contour that was produced and evolved --
339
1010000
3000
這個角色被創造時有加入人工智慧
17:05
half-evolved, I should say -- to produce balance, basically.
340
1013000
3000
來創造平衡
17:08
So, you kick the guy and the guy's supposed to counter-balance.
341
1016000
3000
當你踢它的時候它會去取得平衡
17:11
That's what we thought was going to come out of this.
342
1019000
3000
這是我們想像會是這樣的結果
17:14
But this is what emerged out of it, in the end.
343
1022000
2000
但是最後卻得到這樣的結果
17:17
(Music)
344
1025000
10000
(音樂)
17:27
Bizarrely, this thing doesn't have a head. I'm not quite sure why.
345
1035000
3000
我也不知道為什麼沒有把頭放進去
17:31
So, this was not something we actually put in there.
346
1039000
2000
這不是我們設定的
17:33
He just started to create that dance himself.
347
1041000
4000
這些動作都是自己發生的
17:37
He's actually a better dancer than I am, I have to say.
348
1045000
3000
他比我還會跳舞, 我必須承認
17:41
And what you see after a while --
349
1049000
2000
如同你所看到的
17:43
I think he even goes into a climax right at the end.
350
1051000
2000
最後的動作是最精彩的部份
17:49
And I think -- there you go.
351
1057000
3000
然後, 你看
17:52
(Laughter)
352
1060000
2000
(笑聲)
17:54
So, that all happened automatically. We didn't put that in there.
353
1062000
2000
這不是我們有意設計的動作
17:56
That's just the simulation creating this itself, basically.
354
1064000
3000
它完全是模擬的成果
17:59
So it's just --
355
1067000
2000
所以這是--
18:01
(Applause)
356
1069000
1000
(掌聲)
18:02
Thanks.
357
1070000
2000
謝謝
18:05
Not quite John Travolta yet, but we're working on that as well,
358
1073000
3000
還不能像John Travolta那麼厲害, 但是我們會繼續努力
18:08
so thanks very much for your time.
359
1076000
2000
謝謝大家的時間
18:10
Thanks.
360
1078000
1000
謝謝
18:11
(Applause)
361
1079000
1000
(掌聲)
18:12
CA: Incredible. That was really incredible.
362
1080000
2000
Chris Anderson: 真的是很令人驚嘆
18:14
TR: Thanks.
363
1082000
1000
Torsten Reil：謝謝
ABOUT THE SPEAKER
Torsten Reil - Animating neurobiologistBy coding computer simulations with biologically modeled nervous systems, Torsten Reil and his company NaturalMotion breathe life into the animated characters inhabiting the most eye-poppingly realistic games and movies around.
Why you should listen
From modeling the mayhem of equine combat in Lord of the Rings: Return of the King to animating Liberty City gun battles in Grand Theft Auto IV, Torsten Reil's achievements are all over the map these days. Software that he helped create (with NaturalMotion, the imaging company he co-founded) has revolutionized computer animation of human and animal avatars, giving rise to some of the most breathtakingly real sequences in the virtual world of video games and movies- and along the way given valuable insight into the way human beings move their bodies.
Reil was a neural researcher working on his Masters at Oxford, developing computer simulations of nervous systems based on genetic algorithms- programs that actually used natural selection to evolve their own means of locomotion. It didn't take long until he realized the commercial potential of these lifelike characters. In 2001 he capitalized on this lucrative adjunct to his research, and cofounded NaturalMotion. Since then the company has produced motion simulation programs like Euphoria and Morpheme, state of the art packages designed to drastically cut the time and expense of game development, and create animated worlds as real as the one outside your front door. Animation and special effects created with Endorphin (NaturalMotion's first animation toolkit) have lent explosive action to films such as Troy and Poseidon, and NaturalMotion's software is also being used by LucasArts in video games such as the hotly anticipated Indiana Jones.
But there are serious applications aside from the big screen and the XBox console: NaturalMotion has also worked under a grant from the British government to study the motion of a cerebral palsy patient, in hopes of finding therapies and surgeries that dovetail with the way her nervous system is functioning.
More profile about the speakerReil was a neural researcher working on his Masters at Oxford, developing computer simulations of nervous systems based on genetic algorithms- programs that actually used natural selection to evolve their own means of locomotion. It didn't take long until he realized the commercial potential of these lifelike characters. In 2001 he capitalized on this lucrative adjunct to his research, and cofounded NaturalMotion. Since then the company has produced motion simulation programs like Euphoria and Morpheme, state of the art packages designed to drastically cut the time and expense of game development, and create animated worlds as real as the one outside your front door. Animation and special effects created with Endorphin (NaturalMotion's first animation toolkit) have lent explosive action to films such as Troy and Poseidon, and NaturalMotion's software is also being used by LucasArts in video games such as the hotly anticipated Indiana Jones.
But there are serious applications aside from the big screen and the XBox console: NaturalMotion has also worked under a grant from the British government to study the motion of a cerebral palsy patient, in hopes of finding therapies and surgeries that dovetail with the way her nervous system is functioning.
Torsten Reil | Speaker | TED.com