Torsten Reil: Using biology to make better animation

譯者: Dxm Online大小媒體 審譯者: Ang-Yu, Debra Chiang

I'm going to talk about a technology that we're developing at Oxford now,

我將向各位介紹一項目前我們正在牛津研究發展的科技

that we think is going to change the way that

我們認為它將改變

computer games and Hollywood movies are being made.

電玩和好萊塢電影的製作方式。

That technology is simulating humans.

這一項科技就是模擬人類，

It's simulated humans with a simulated body

它以模擬的人類身體

and a simulated nervous system to control that body.

及用以控制那身體的模擬神經系統來模擬人類。

Now, before I talk more about that technology,

在往下介紹這項科技之前，

let's have a quick look at what human characters look like

先讓我們看一下現在電玩裡頭

at the moment in computer games.

人物運動的樣子。

This is a clip from a game called "Grand Theft Auto 3."

這是俠盜獵車手 3 的片段，

We already saw that briefly yesterday.

昨天我們有稍微看了一些。

And what you can see is -- it is actually a very good game.

就如你看到的, 它是一個非常棒的遊戲。

It's one of the most successful games of all time.

所有最成功遊戲的其中一個。

But what you'll see is that all the animations in this game are very repetitive.

不過你可以看出遊戲中動畫人物的動作不斷地重覆，

They pretty much look the same.

它們看起來都一樣。

I've made him run into a wall here, over and over again.

這個角色撞上牆之後，

And you can see he looks always the same.

一直重覆一樣的動作。

The reason for that is that these characters

主要的原因是這些角色

are actually not real characters.

並不是真實的人物。

They are a graphical visualization of a character.

他們是一個角色的圖像視覺呈現結果。

To produce these animations, an animator at a studio has to anticipate

遊戲公司裡的動畫師必需先預測

what's going to happen in the actual game,

遊戲中的情節，

and then has to animate that particular sequence.

並針對特定橋段繪製，才能製作出這些動畫。

So, he or she sits down, animates it, and tries to anticipate what's going to happen,

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，

and then these particular animations are just played back

而這些動畫成果會在遊戲的

at appropriate times in the computer game.

適當時候播放。

Now, the result of that is that you can't have real interactivity.

但這麼做的結果是玩家無法擁有真實的互動。

All you have is animations that are played back

你只能不斷看到

at more or less the appropriate times.

相同的動作

It also means that games aren't really going to be as surprising as they could be,

這也表示遊戲中不會發生驚喜角色

because you only get out of it, at least in terms of the character,

只能做預設的內容

what you actually put into it.

你當時放了什麼在裡面

There's no real emergence there.

因為裡面沒有真實的結合

And thirdly, as I said, most of the animations are very repetitive because of that.

所以大部份的動作只能反覆

Now, the only way to get around that

避免的唯一方法就是實際地

is to actually simulate the human body

模擬人體

and to simulate that bit of the nervous system of the brain that controls that body.

模擬控制的神經系統

And maybe, if I could have you for a quick demonstration

可以請你上來做個簡單示範嗎

to show what the difference is --

看看哪裡不一樣

because, I mean, it's very, very trivial.

這是一個微不足道的現象

If I push Chris a bit, like this, for example, he'll react to it.

如果我推Chris一下，他會產生反應

If I push him from a different angle, he'll react to it differently,

如果我從另一個角度推，他會有不同反應

and that's because he has a physical body,

這是因為他有一個真實的身體

and because he has the motor skills to control that body.

和控制身體的能力

It's a very trivial thing.

這是一個微不足道的

It's not something you get in computer games at the moment, at all.

這是一個與電玩無關的小事

Thank you very much. Chris Anderson: That's it?

謝謝你就這樣。就這樣嗎？

Torsten Reil: That's it, yes.

是的

So, that's what we're trying to simulate --

卻正是我們要模擬的

not Chris specifically, I should say, but humans in general.

不是模擬Chris 而是模擬人體

Now, we started working on this a while ago at Oxford University,

我們在牛津大學開始一段時間了

and we tried to start very simply.

一切從最簡單的事開始

What we tried to do was teach a stick figure how to walk.

也就是教這個火柴人走路

That stick figure is physically stimulated. You can see it here on the screen.

它已經完全地模擬人體

So, it's subject to gravity, has joints, etc.

會受到地心引力影響也有關節

If you just run the simulation, it will just collapse, like this.

一旦啟動模擬它就會像這樣跌倒，就像這樣

The tricky bit is now to put an AI controller in it

困難的部份是加入控制

that actually makes it work.

也就是人工智慧讓它動起來

And for that, we use the neural network, which we based on

我們用在神經系統上的是

that part of the nervous system that we have in our spine

脊椎上控制走路的

that controls walking in humans.

神經網絡

It's called the central pattern generator.

叫中樞模式產生器

So, we simulated that as well, and then the really tricky bit

我們同樣模擬了這套網絡，但真正困難的是

is to teach that network how to walk.

訓練網絡走路

For that we used artificial evolution -- genetic algorithms.

為此我們使用人工演化以取得自然的演算法

We heard about those already yesterday,

我們昨天已聽過這個主題演講

and I suppose that most of you are familiar with that already.

我想大部份的人都蠻熟悉了

But, just briefly, the concept is that

但是，簡單地來說， 它的概念

you create a large number of different individuals --

就是要產生大量不同的個體

neural networks, in this case --

以這個例子來說

all of which are random at the beginning.

起初所有個體都是亂數產生

You hook these up -- in this case, to the virtual muscles

再將它們連結火柴人的虛擬肌肉

of that two-legged creature here --

火柴人的虛擬肌肉

and hope that it does something interesting.

希望它可以做出有趣的事

At the beginning, they're all going to be very boring.

一開始挺無聊的

Most of them won't move at all,

大部份火柴人不會動

but some of them might make a tiny step.

但有些會走小步路

Those are then selected by the algorithm,

這些演算法就會被選用

reproduced with mutation and recombinations to introduce sex as well.

加上突變和重組之後進行繁殖

And you repeat that process over and over again,

接下來不斷重覆這些步驟

until you have something that walks --

直到它能像這樣走直線

in this case, in a straight line, like this.

這就是它背後的概念

So that was the idea behind this.

現在我們開始示範

When we started this, I set up the simulation one evening.

我在前一天晚上設定完畢

It took about three to four hours to run the simulation.

花幾個小時執行模擬運算

I got up the next morning, went to the computer and looked at the results,

隔天早晨回來檢查成果

and was hoping for something that walked in a straight line,

我希望能看到它走直線

like I've just demonstrated,

就像我所證明的一樣

and this is what I got instead.

但這卻是我得到的

(Laughter)

(笑聲)

So, it was back to the drawing board for us.

結果它變成關節

We did get it to work eventually,

所以我們做了些許調整

after tweaking a bit here and there.

最後還是成功了

And this is an example of a successful evolutionary run.

人工演化成功地運行

So, what you'll see in a moment is a very simple biped

待會將看到一個簡易的雙足生物

that's learning how to walk using artificial evolution.

藉由人工演化學習如何走路

At the beginning, it can't walk at all,

一開始它完全不會走路

but it will get better and better over time.

但是有愈來愈進步

So, this is the one that can't walk at all.

這個完全不能走路

(Laughter)

(笑聲)

Now, after five generations of applying evolutionary process,

然後我們改變演算法

the genetic algorithm is getting a tiny bit better.

在演化的第五次演算它有點好轉

(Laughter)

(笑聲)

Generation 10 and it'll take a few steps more --

第十次演算能夠往前走幾步

still not quite there.

但還是沒有成功

But now, after generation 20, it actually walks in a straight line without falling over.

到了第二十次演算它完全成功，不但能走直線也不會跌倒

That was the real breakthrough for us.

對我們來說是一個突破

It was, academically, quite a challenging project,

這是一個很有挑戰性的計劃

and once we had reached that stage, we were quite confident

一旦發展到下個階段，我們相當有信心

that we could try and do other things as well with this approach --

我們相信能以同樣的方法，讓它做其他事

actually simulating the body

模擬人體

and simulating that part of the nervous system that controls it.

及其控制神經系統

Now, at this stage, it also became clear that this could be very exciting

到了這個階段對電玩和線上遊戲

for things like computer games or online worlds.

無疑地是一個興奮的消息

What you see here is the character standing there,

你們可以看到一個角色站在那兒

and there's an obstacle that we put in its way.

在那裡我們放了一個障礙物

And what you see is, it's going to fall over the obstacle.

它會在絆到障礙物時跌倒

Now, the interesting bit is, if I move the obstacle a tiny bit to the right,

現在有趣的是，如果現在我把障礙物挪右邊一點

which is what I'm doing now, here,

就跟我現在做的一樣

it will fall over it in a completely different way.

它會以完全不同的方式跌倒

And again, if you move the obstacle a tiny bit, it'll again fall differently.

再把障礙物挪右邊一點，它還是會以不同的方式跌倒

(Laughter)

(笑聲)

Now, what you see, by the way, at the top there,

對了，畫面上方顯示的是

are some of the neural activations being fed into the virtual muscles.

虛擬肌肉系統的神經運動

Okay. That's the video. Thanks.

以上就是我的示範影片。謝謝

Now, this might look kind of trivial, but it's actually very important

這或許微不足道但卻很重要

because this is not something you get at the moment

現在的虛擬的世界

in any interactive or any virtual worlds.

並沒有達到互動

Now, at this stage, we decided to start a company and move this further,

發展到這個階段，我們決定要開一家公司繼續發展下去

because obviously this was just a very simple, blocky biped.

這不過是一個簡單的雙足生物

What we really wanted was a full human body.

我們的目標要模擬人體全身

So we started the company.

所以我們開了一家公司

We hired a team of physicists, software engineers and biologists

聘了物理學家軟體工程師生物學家

to work on this, and the first thing we had to work on

第一個任務就是

was to create the human body, basically.

建造一個人體

It's got to be relatively fast, so you can run it on a normal machine,

它得輕巧以便在一般機器上執行

but it's got to be accurate enough, so it looks good enough, basically.

外觀也要準確好看

So we put quite a bit of biomechanical knowledge into this thing,

我們也加了不少生化科技進去

and tried to make it as realistic as possible.

盡力把它做得精巧

What you see here on the screen right now

你們現在看到的是

is a very simple visualization of that body.

簡易的外型可以輕易地加上頭髮衣物等

I should add that it's very simple to add things like hair, clothes, etc.,

我應該要加一些簡單的東西，如頭髮、衣服等等

but what we've done here is use a very simple visualization,

我們現在只是用簡單的方式

so you can concentrate on the movement.

所以你們可以專注在它的動作

Now, what I'm going to do right now, in a moment,

我們現在要做的是

is just push this character a tiny bit and we'll see what happens.

輕推它一下，看看會怎麼樣

Nothing really interesting, basically.

沒什麼有趣的事發生

It falls over, but it falls over like a rag doll, basically.

它像個布娃娃一樣跌倒

The reason for that is that there's no intelligence in it.

因為還沒有為它加入人工智慧

It becomes interesting when you put artificial intelligence into it.

如果加上會產生有趣的結果

So, this character now has motor skills in the upper body --

現在它的上半身可以做很多動作

nothing in the legs yet, in this particular one.

下半身則未放入任何東西

But what it will do -- I'm going to push it again.

我現在再次推倒它

It will realize autonomously that it's being pushed.

它知道自己被推了

It's going to stick out its hands.

它會伸出手

It's going to turn around into the fall, and try and catch the fall.

轉身試圖不摔倒

So that's what you see here.

就像這樣

Now, it gets really interesting

把人工智慧加到下半身

if you then add the AI for the lower part of the body as well.

會更有趣

So here, we've got the same character.

現在使用同一個角色

I'm going to push it a bit harder now,

當我更用力地推它

harder than I just pushed Chris.

就像我推Chris一樣

But what you'll see is -- it's going to receive a push now from the left.

它會試圖抵抗左邊來的力量

What you see is it takes steps backwards,

你們可以看到它先退了一步

it tries to counter-balance,

試著保持平衡

it tries to look at the place where it thinks it's going to land.

眼睛還會看向

I'll show you this again.

我再播一次

And then, finally hits the floor.

最後它才跌倒

Now, this becomes really exciting

這是非常有趣的

when you push that character in different directions, again, just as I've done.

如果你把它推向不同的方向，就像我剛剛做的一樣

That's something that you cannot do right now.

這是現在的遊戲做不到的

At the moment, you only have empty computer graphics in games.

這裡頭可沒有預設動作

What this is now is a real simulation. That's what I want to show you now.

這才是真實的模擬，也就是我現在要展示的

So, here's the same character with the same behavior I've just shown you,

再次現在使用同一個角色

but now I'm just going to push it from different directions.

我把它推到不同方向

First, starting with a push from the right.

第一次是往右推

This is all slow motion, by the way, so we can see what's going on.

這些是慢動作影片讓你們能看清楚

Now, the angle will have changed a tiny bit,

現在角度變了

so you can see that the reaction is different.

它倒下的方向也變了

Again, a push, now this time from the front.

下一次我從前面推

And you see it falls differently.

看它跌倒的方式不一樣

And now from the left --

從左邊推

and it falls differently.

它跌倒的方式也不同

That was really exciting for us to see that.

我們對此結果感到十分高興

That was the first time we've seen that.

這是本計畫結果第一次公開

This is the first time the public sees this as well,

我們還沒有讓任何人看過

because we have been in stealth mode.

因為我們是祕密進行的

I haven't shown this to anybody yet.

我還沒有把這個給任何人看過

Now, just a fun thing:

現在來點有趣的

what happens if you put that character --

它會發生的事是

this is now a wooden version of it, but it's got the same AI in it --

這是木頭人的版本有相同的智慧

but if you put that character on a slippery surface, like ice.

如果把它放到平滑的冰面

We just did that for a laugh, just to see what happens.

我們這麼試只想看點滑稽的東西

(Laughter)

(笑聲)

And this is what happens.

而結果是這樣

(Laughter)

(笑聲)

(Applause)

(掌聲)

It's nothing we had to do about this.

我們不需要在它身上做什麼

We just took this character that I just talked about,

只是把它

put it on a slippery surface, and this is what you get out of it.

放在平滑表面就能得到這個結果

And that's a really fascinating thing about this approach.

這就是我們的模擬方法神奇之處

Now, when we went to film studios and games developers

當這項技術介紹給電玩公司時

and showed them that technology, we got a very good response.

介紹給電玩公司時，我們得到很好的回應

And what they said was, the first thing they need immediately is virtual stuntmen.

他們的第一個反應是用在特技演員

Because stunts are obviously very dangerous, they're very expensive,

因為特技很危險很貴

and there are a lot of stunt scenes that you cannot do, obviously,

還有更多的特技鏡頭是做不到的

because you can't really allow the stuntman to be seriously hurt.

因為不能讓特技演員受傷

So, they wanted to have a digital version of a stuntman

所以他們想要數位的特技演員

and that's what we've been working on for the past few months.

這正是我們過去幾個月來的工作

And that's our first product that we're going to release in a couple of weeks.

我們很榮幸能在幾個星期內發表

So, here are just a few very simple scenes of the guy just being kicked.

這裡有幾個簡單的鏡頭，一個傢伙被踢

That's what people want. That's what we're giving them.

那是他們要的，這是我們給的

(Laughter)

(笑聲)

You can see, it's always reacting.

你們可以看到不停地表演

This is not a dead body. This is a body who basically, in this particular case,

一點都不僵硬，在這個鏡頭

feels the force and tries to protect its head.

他試著平衡也會保護自己的頭

Only, I think it's quite a big blow again.

另一個鏡頭又是一記重擊

You feel kind of sorry for that thing,

你們或許為木頭人感到難過

and we've seen it so many times now that

但我們已經看了太多遍了

we don't really care any more.

現在可是一點感覺也沒有

(Laughter)

(笑聲)

There are much worse videos than this, by the way, which I have taken out, but ...

後面還有很多更痛的鏡頭我得拿掉

Now, here's another one.

另一個

What people wanted as a behavior was to have an explosion,

人們想要的是在爆炸之後

a strong force applied to the character,

角色在空中

and have the character react to it in midair.

如何反應強大的力量

So that you don't have a character that looks limp,

它看起來不可以軟綿綿的

but actually a character that you can use in an action film straight away,

它得是可以用在電影裡的角色

that looks kind of alive in midair as well.

能飛在空中看起來有活力

So this character is going to be hit by a force,

現在這個角色會被用力一擊

it's going to realize it's in the air,

它會發現自己在空中

and it's going to try and, well,

而試著抓住些什麼

stick out its arm in the direction where it's landing.

它被推出去然後著地

That's one angle; here's another angle.

這是一個拍攝角度，還有另一個角度

We now think that the realism we're achieving with this

我們認為達到這個程度

is good enough to be used in films.

就已經可以用在電影上

And let's just have a look at a slightly different visualization.

現在我們來看點不一樣的的圖像

This is something I just got last night

這是我昨天拿到的影片

from an animation studio in London, who are using our software

一家倫敦動畫公司正在試用我們軟體

and experimenting with it right now.

現在正在試驗中

So this is exactly the same behavior that you saw,

它會做一樣的動作

but in a slightly better rendered version.

算圖看起來比較漂亮

So if you look at the character carefully,

仔細看身體每一部份

you see there are lots of body movements going on,

都有反應動作

none of which you have to animate like in the old days.

不再像以往得親自調動畫

Animators had to actually animate them.

現在動作

This is all happening automatically in the simulation.

都能自動模擬出來

This is a slightly different angle,

從不同角度看

and again a slow motion version of this.

用慢動作再看一次

This is incredibly quick. This is happening in real time.

這非常快即時運算馬上就能看到

You can run this simulation in real time, in front of your eyes,

你可以執行模擬

change it, if you want to, and you get the animation straight out of it.

馬上調整得到結果

At the moment, doing something like this by hand

如果手動調動畫

would take you probably a couple of days.

大概會花去好幾天

This is another behavior they requested.

他們還要求另一個動作

I'm not quite sure why, but we've done it anyway.

不知道為什麼但我們還要做了

It's a very simple behavior that shows you the power of this approach.

它是很簡單的動作

In this case, the character's hands

這個角色的手

are fixed to a particular point in space,

被固定在一個地方

and all we've told the character to do is to struggle.

可以看出角色在掙扎

And it looks organic. It looks realistic.

看起來不生硬還令人有點不舒服

You feel kind of sorry for the guy.

如果你們為他感到同情

It's even worse -- and that is another video I just got last night --

接下來的畫面更糟，這是我昨晚拿到的片段

if you render that a bit more realistically.

算圖之後看來更真實了

Now, I'm showing this to you just to show you

只是想讓你們看看

how organic it actually can feel, how realistic it can look.

它多麼地寫實

And this is all a physical simulation of the body,

這全是真實模擬的結果

using AI to drive virtual muscles in that body.

用人工智慧驅動虛擬的肌肉

Now, one thing which we did for a laugh was

最後要介紹的是較複雜的特技

to create a slightly more complex stunt scene,

一個最有名的特技鏡頭是

and one of the most famous stunts is the one where James Bond

007的腳被彈力繩綁住

jumps off a dam in Switzerland and then is caught by a bungee.

從瑞士一個水壩一躍而下

Got a very short clip here.

這裡有一個簡短的片段

Yes, you can just about see it here.

就如同你看到的一樣

In this case, they were using a real stunt man. It was a very dangerous stunt.

當時用真人演出十分危險

It was just voted, I think in the Sunday Times, as one of the most impressive stunts.

它被週日時報票選為最令人印象深刻的特技

Now, we've just tried and -- looked at our character and asked ourselves,

我看到這一幕時自問

"Can we do that ourselves as well?"

能不能做到

Can we use the physical simulation of the character,

實際模擬身體

use artificial intelligence,

利用人工智慧

put that artificial intelligence into the character,

並且放入人工智慧

drive virtual muscles, simulate the way he jumps off the dam,

模擬它綁著彈跳繩

and then skydive afterwards,

高空跳下水壩

and have him caught by a bungee afterwards?

捕捉它跳下的畫面

We did that. It took about altogether just two hours,

總共花了二個小時產生模擬

pretty much, to create the simulation.

接近真實創造了模擬

And that's what it looks like, here.

結果看起來是這樣的

Now, this could do with a bit more work. It's still very early stages,

它只是初步階段還需要一些調整

and we pretty much just did this for a laugh,

我們會這樣握只是要讓大家笑一笑

just to see what we'd get out of it.

看看到底可以得到什麼東西

But what we found over the past few months

過去幾個月來

is that this approach -- that we're pretty much standard upon --

我們發現這個方法

is incredibly powerful.

非常強大

We are ourselves surprised what you actually get out of the simulations.

對於模擬的結果令人感到吃驚

There's very often very surprising behavior that you didn't predict before.

有些結果是我們沒有預期的

There's so many things we can do with this right now.

現在它可以做很多事

The first thing, as I said, is going to be virtual stuntmen.

第一虛擬特技演員

Several studios are using this software now to produce virtual stuntmen,

有7家公司已經開始使用這套軟體做數位替身

and they're going to hit the screen quite soon, actually,

很快會在大銀幕上看到

for some major productions.

為知名的產品做模擬

The second thing is video games.

第二電玩

With this technology, video games will look different and they will feel very different.

用這項科技會使電玩看起來大不同

For the first time, you'll have actors that really feel very interactive,

將是第一次角色具有互動感

that have real bodies that really react.

它們有真實的身體對周遭做出反應

I think that's going to be incredibly exciting.

我覺得這真的令人興奮

Probably starting with sports games,

或許從運動遊戲開始

which are going to become much more interactive.

將變得更有互動感

But I particularly am really excited

特別希望看到這科技

about using this technology in online worlds,

用在線上世界

like there, for example, that Tom Melcher has shown us.

像是剛才看到的"There"

The degree of interactivity you're going to get

互動程度將會和現在的遊戲

is totally different, I think, from what you're getting right now.

大不同

A third thing we are looking at and very interested in is simulation.

第三是模擬

We've been approached by several simulation companies,

我們接到很多模擬公司的詢問

but one project we're particularly excited about, which we're starting next month,

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

is to use our technology -- and in particular, the walking technology --

它將使用我們行走的技術

to help aid surgeons who work on children with cerebral palsy,

幫助兒童腦性麻痺開刀的外科醫生

to predict the outcome of operations on these children.

預測孩子手術的結果

As you probably know,

你們知道

it's very difficult to predict what the outcome of an operation is

矯正腦性麻痺患者的行走的手術結果

if you try and correct the gait.

是很難預測的

The classic quote is, I think, it's unpredictable at best,

我覺得這是現下最難的

is what people think right now, is the outcome.

是人們的想法

Now, what we want to do with our software is allow our surgeons to have a tool.

我們會提供醫師另一套工具

We're going to simulate the gait of a particular child

模擬小朋友的步行

and the surgeon can then work on that simulation

手術可以依照模擬的結果去進行

and try out different ways to improve that gait,

所以他可以在手術之前進行模擬

before he actually commits to an actual surgery.

從不同的矯正結果中找出最好的，再進行手術

That's one project we're particularly excited about,

這就是我們特別興奮的計劃

and that's going to start next month.

它下個月就會開始

Just finally, this is only just the beginning.

最後，這只是一開始的結果

We can only do several behaviors right now.

我們現在只能做出幾個行為模式

The AI isn't good enough to simulate a full human body.

現在它的人工智慧還無法模擬全身

The body yes, but not all the motor skills that we have.

可以做出軀體但是還沒能做出所有動作

And, I think, we're only there if we can have something like ballet dancing.

不過很快它就能做出芭蕾的動作

Right now, we don't have that

雖然現在我們沒有芭蕾舞動作

but I'm very sure that we will be able to do that at some stage.

但是我知道總有一天我們可以做出來的

We do have one unintentional dancer actually,

事實上我們不小心模擬出芭蕾舞蹈

the last thing I'm going to show you.

這裡有一個偶然的成果是我最後想展示給大家看的

This was an AI contour that was produced and evolved --

這個角色被創造時有加入人工智慧

half-evolved, I should say -- to produce balance, basically.

來創造平衡

So, you kick the guy and the guy's supposed to counter-balance.

當你踢它的時候它會去取得平衡

That's what we thought was going to come out of this.

這是我們想像會是這樣的結果

But this is what emerged out of it, in the end.

但是最後卻得到這樣的結果

(Music)

(音樂)

Bizarrely, this thing doesn't have a head. I'm not quite sure why.

我也不知道為什麼沒有把頭放進去

So, this was not something we actually put in there.

這不是我們設定的

He just started to create that dance himself.

這些動作都是自己發生的

He's actually a better dancer than I am, I have to say.

他比我還會跳舞, 我必須承認

And what you see after a while --

如同你所看到的

I think he even goes into a climax right at the end.

最後的動作是最精彩的部份

And I think -- there you go.

然後, 你看

(Laughter)

(笑聲)

So, that all happened automatically. We didn't put that in there.

這不是我們有意設計的動作

That's just the simulation creating this itself, basically.

它完全是模擬的成果

So it's just --

所以這是--

(Applause)

(掌聲)

Thanks.

謝謝

Not quite John Travolta yet, but we're working on that as well,

還不能像John Travolta那麼厲害, 但是我們會繼續努力

so thanks very much for your time.

謝謝大家的時間

Thanks.

謝謝

(Applause)

(掌聲)

CA: Incredible. That was really incredible.

Chris Anderson: 真的是很令人驚嘆

TR: Thanks.

Torsten Reil：謝謝