Dennis Hong: My 7 species of robot

譯者: Cherie Yip 審譯者: Bill Hsiung

我們首先談到的機器人叫 STriDER，

So the first robot to talk about is called STriDER.

它的意思是

It stands for Self-excited Tripedal Dynamic Experimental Robot.

三腳動力實驗性機器人。

It's a robot that has three legs, which is inspired by nature.

這是一個有三隻腳的機器人，

它的靈感是從自然界中所獲得的。

But have you seen anything in nature, an animal that has three legs?

但是，你可曾看過自然界中

有三隻腳的生物嗎？

Probably not. So why do I call this a biologically inspired robot?

大概沒有，那爲什麽我稱這機器人為

被生物所啓發的機器人？這機器人是怎麼運作的呢？

How would it work?

在我解釋之前，讓我們先來看看流行文化，

But before that, let's look at pop culture.

So, you know H.G. Wells's "War of the Worlds," novel and movie.

都聽過 H.G.Wells 的世界大戰小說和電影吧。

And what you see over here is a very popular video game,

你們現在在這邊所看到的是一個很熱門的

電腦遊戲。

and in this fiction, they describe these alien creatures and robots

在小說裏面，他們把這些襲擊地球的

外星生物描述成有三隻腳的機器人。

that have three legs that terrorize Earth.

但是我的機器人 STriDER，不是這樣移動的。

But my robot, STriDER, does not move like this.

This is an actual dynamic simulation animation.

這是一個真正的動力學模擬動畫。

I'm going to show you how the robot works.

我將會向你們展示這個機器人是如何運作的。

它把自己翻了180度，

It flips its body 180 degrees

and it swings its leg between the two legs

它通過甩動兩條腿中間的腿來防止自己跌倒。

and catches the fall.

So that's how it walks.

看，它就是這樣走路的。但是，我們再看看自己，

But when you look at us human beings, bipedal walking,

人類 — 靠雙腿行走的生物，

what you're doing is,

我們並沒有用肌肉

you're not really using muscle to lift your leg and walk like a robot.

抬起自己的腿，然後走得像個機器人，對吧？

What you're doing is, you swing your leg and catch the fall,

你做的實際上是甩開你的腿來止住自己跌倒的趨勢，

重新站穩，并再次甩開腿。

stand up again, swing your leg and catch the fall.

You're using your built-in dynamics, the physics of your body,

通過運用我們身體內置的動力機制 — 身體的物理構造，

just like a pendulum.

就像個鐘擺一般，

We call that the concept of passive dynamic locomotion.

我們把這概念叫做消極動力運動。

What you're doing is, when you stand up,

你做的是，當你站立的時候，

potential energy to kinetic energy,

位能轉化

potential energy to kinetic energy.

為動能，

It's a constantly falling process.

這是一個普通的下落過程。

So even though there is nothing in nature that looks like this,

所以，儘管自然界中沒有生物長成這樣，

really, we're inspired by biology and applying the principles of walking

我們仍然從生物學中受到啓發，

并製造出機器人的這種行走模式。

to this robot.

所以，這是一個受生物所啓發的機器人。

Thus, it's a biologically inspired robot.

What you see here, this is what we want to do next.

你們現在所看到的這個，則是我們接下來想要做的。

我們想把腿折起來，然後把它射出去以做長距離的移動。

We want to fold up the legs and shoot it up for long-range motion.

And it deploys legs -- it looks almost like "Star Wars" --

它叉開它的腿，這讓它看起來像電影星際大戰裡面的角色。

so when it lands, it absorbs the shock and starts walking.

當它降落的時候，它能吸收震盪，并開始行走。

What you see over here, this yellow thing, this is not a death ray.

你們在這邊所看到的這個，這黃色的東西，這不是死光。

(Laughter)

這只是用來告訴你，機器人上是否具備相機，

This is just to show you

that if you have cameras or different types of sensors,

或別種感測器，

因為它很高，它有 1.8 公尺高，

because it's 1.8 meters tall,

所以你可以穿過像灌木叢這樣的障礙物來觀察前方。

you can see over obstacles like bushes and those kinds of things.

我們做了兩個原型機，

So we have two prototypes.

The first version, in the back, that's STriDER I.

第一版，後面的那個，這是 STriDER I，

The one in front, the smaller, is STriDER II.

這在前面的，更小的，是 STriDER II.

The problem we had with STriDER I is, it was just too heavy in the body.

STriDER I 的問題是

身體過重。因為你知道，我們要

We had so many motors aligning the joints

連接許多關節，所以安裝上很多馬達一類的東西。

and those kinds of things.

所以，我們決定想出一種機械原理，

So we decided to synthesize a mechanical mechanism

so we could get rid of all the motors, and with a single motor,

以擺脫所有的馬達，只需使用單一馬達，

we can coordinate all the motions.

我們就可以連貫所有動作。

It's a mechanical solution to a problem, instead of using mechatronics.

我們運用了機械原理來解決問題，而不是使用電子機械。

So with this, now the top body is lighted up; it's walking in our lab.

現在，機器人的上身輕得足夠讓它在實驗室行走。

這只是邁向成功的第一步。

This was the very first successful step.

It's still not perfected, its coffee falls down,

它仍然是不完美的。它拿著的咖啡掉了，

so we still have a lot of work to do.

所以，我們仍然有很多工作要做。

The second robot I want to talk about is called IMPASS.

我要介紹的第二個機器人叫 IMPASS。

It stands for Intelligent Mobility Platform with Actuated Spoke System.

它的意思是輪輻驅動系統的智慧型移動平臺，

It's a wheel-leg hybrid robot.

這是個輪、腳混合的機器人。

So think of a rimless wheel or a spoke wheel,

試著想像一個沒輪框的輪子，

或者一個有輻條的輪子，

but the spokes individually move in and out of the hub;

但是輪輻獨立地在輪軸裡外運動，

so, it's a wheel-leg hybrid.

所以就成了輪、腳混合，

We're literally reinventing the wheel here.

事實上，我們相當於重新發明了一種輪子。

Let me demonstrate how it works.

讓我來示範一下它是如何運作的。

So in this video we're using an approach called the reactive approach.

在這個影片裡，我們用了一種方法，

叫反應途徑。

Just simply using the tactile sensors on the feet,

只要運用它腳上的觸覺感應器，

it's trying to walk over a changing terrain,

它正嘗試穿過一個不停改變的地形，

a soft terrain where it pushes down and changes.

一個柔軟的地形，它會受壓變形。

And just by the tactile information,

僅憑藉它的觸覺訊息，

it successfully crosses over these types of terrains.

它成功地穿越了這些地形。

But, when it encounters a very extreme terrain --

但，當它遭遇了一個十分嚴峻的地形，比如說：

in this case, this obstacle is more than three times the height

在它前面的障礙是

它身高的3倍多，

of the robot --

then it switches to a deliberate mode,

它就會轉到一種思考模式，

where it uses a laser range finder and camera systems

這個模式使用一種鐳射找尋器，

以及相機系統，來確定障礙和它的體積，

to identify the obstacle and the size.

然後它會做計劃，小心的計劃它輪輻的移動，

And it carefully plans the motion of the spokes

並協調其移動，因此，它就能夠做出這些

and coordinates it so it can show this very impressive mobility.

十分讓人驚歎的移動能力。

You probably haven't seen anything like this out there.

你可能在外頭從沒看過類似這樣的東西。

這是我們所開發的一種有

This is a very high-mobility robot that we developed called IMPASS.

很高移動能力的機器人，叫做 IMPASS。

Ah, isn't that cool?

啊...這不是很酷嗎？

When you drive your car,

當你開車的時候，

當你駕駛你的汽車的時候，你用一種

when you steer your car, you use a method called Ackermann steering.

叫做 Ackermann 的方法，

The front wheels rotate like this.

來做前輪驅動，像這樣。

For most small-wheeled robots,

對於大多數的小輪子機器人，

they use a method called differential steering

它們用一種叫差速齒輪方法，

where the left and right wheel turn the opposite direction.

即左右兩個輪分別轉向相反方向。

For IMPASS, we can do many, many different types of motion.

對於 IMPASS 來說，我們可以做很多不同類型的動作。

For example, in this case,

舉例來說，在這裡，儘管左輪和右輪通過

even though the left and right wheels are connected

單一輪軸相連，以相同的角速度在旋轉，

with a single axle rotating at the same angle of velocity,

我們只要簡單的改變輪輻的長度，

we simply change the length of the spoke, it affects the diameter,

它影響了直徑，然後它就會向左轉，再向右轉。

then can turn to the left and to the right.

所以，這只是一些 IMPASS

These are just some examples of the neat things we can do with IMPASS.

可以做到的美妙的例子。

This robot is called CLIMBeR:

這個機器人叫 CLIMBeR，

Cable-suspended Limbed Intelligent Matching Behavior Robot.

吊索智能行為協調機器人。

I've been talking to a lot of NASA JPL scientists --

我曾和很多 NASA JPL 的科學家交談過，

at JPL, they are famous for the Mars rovers --

他們是 JPL 登月機器人的專家。

這些科學家，地理學家總是告訴我，

and the scientists, geologists always tell me

真正有趣的科學研究，

that the real interesting science, the science-rich sites,

富有研究價值的地點，總是在懸崖邊緣才能發現。

are always at the cliffs.

But the current rovers cannot get there.

但是，現在的登月機器人到不了那些地方。

So, inspired by that, we wanted to build a robot

因此，受到這對話的啟發，我們想建一個機器人，

that can climb a structured cliff environment.

能夠攀爬懸崖峭壁，

So this is CLIMBeR.

於是，我們有了 CLIMBeR。

It has three legs.

來看看它是如何做到的，它有三條腿，這大概很難看到，

It's probably difficult to see, but it has a winch and a cable at the top.

它有個絞盤和繩索在頂部，

It tries to figure out the best place to put its foot.

它會嘗試找到最好的地方落腳。

And then once it figures that out,

一旦找到了這地方，

in real time, it calculates the force distribution:

它即時計算力量的分佈。

how much force it needs to exert to the surface

它需要多大的力氣才能在表面站穩，

so it doesn't tip and doesn't slip.

而不至於會摔倒或者滑到。

Once it stabilizes that, it lifts a foot,

一旦它穩定後，就會抬起一條腿，

and then with the winch, it can climb up these kinds of cliffs.

然後，使用絞盤，它可以爬上這種東西。

Also for search and rescue applications as well.

這種技術用於搜索和救難同樣有用。

Five years ago, I actually worked at NASA JPL

五年前的一個夏天我在 NASA JPL

兼任暑期教職。

during the summer as a faculty fellow.

他們已經有一個六支腳的機器人，叫 LEMUR。

And they already had a six-legged robot called LEMUR.

So this is actually based on that.

這機器人其實是以 LEMUR 為基礎的，它叫 MARS，

This robot is called MARS:

Multi-Appendage Robotic System.

多附加機器人工程系統。是的，這是個六足機器人，

It's a hexapod robot.

We developed our adaptive gait planner.

我們開發了自己的適應性步伐平台，

We actually have a very interesting payload on there.

實際上，我們放了一個很有趣的貨物在它上面。

The students like to have fun.

學生們喜歡有趣的東西。這裡你可以看到它

And here you can see that it's walking over unstructured terrain.

走過沒有結構可言的地形。

(Motor sound)

它正嘗試穿過這粗糙的地形，

It's trying to walk on the coastal terrain, a sandy area,

沙地，

but depending on the moisture content or the grain size of the sand,

根據濕度大小或者沙子顆粒大小，

the foot's soil sinkage model changes, so it tries to adapt its gait

它腳的泥土陷入模式會改變，

所以，它嘗試把它的步伐調整到能成功地穿過這些地方。

to successfully cross over these kind of things.

It also does some fun stuff.

因此，可以想像，它會做出一些有趣的動作，

As you can imagine, we get so many visitors visiting our lab.

很多人會到我們的實驗室參觀，

So when the visitors come, MARS walks up to the computer,

當有參觀者來的時候，MARS 會走到電腦前，

開始打字：「嗨，我叫 MARS。」

starts typing, "Hello, my name is MARS.

歡迎來到 RoMeLa，

Welcome to RoMeLa,

the Robotics Mechanisms Laboratory at Virginia Tech."

在維吉尼亞理工的機器人工程實驗室。

(Laughter)

This robot is an amoeba robot.

這是個阿米巴機器人，

Now, we don't have enough time to go into technical details,

們沒有時間詳細討論技術細節，

I'll just show you some of the experiments.

我將直接展示一些實驗給你們看。

These are some of the early feasibility experiments.

這是我們一些早期的可行性實驗。

我們在它的彈性皮膚上儲存位能用以驅動它。

We store potential energy to the elastic skin to make it move,

or use active tension cords to make it move forward and backward.

或者用一個彈簧索來讓它

向前或者向後移動。它叫做 ChiMERA.

It's called ChIMERA.

We also have been working with some scientists and engineers

我們也曾和一些來自賓大的

科學家和工程師合作

from UPenn

to come up with a chemically actuated version of this amoeba robot.

開發了一個這阿米巴機器人的

化學能驅動版本。

We do something to something,

我們這兒加點，那兒也加點。

and just like magic, it moves.

就像魔術一樣，結果，它動了，這小圓塊。

"The Blob."

This robot is a very recent project.

這機器人是一個非常新的計畫，叫 RAPHaEL，

It's called RAPHaEL:

有彈性韌帶的空氣驅動手機器人。

Robotic Air-Powered Hand with Elastic Ligaments.

There are a lot of really neat, very good robotic hands

市面上有很多很好，很巧妙地機械手，

out there on the market.

問題是，它們都過於昂貴，每個需要成千上萬的美金。

The problem is, they're just too expensive --

tens of thousands of dollars.

So for prosthesis applications it's probably not too practical,

所以，應用在義肢上可能並不會太實用，

因為大多數人負擔不起。

because it's not affordable.

我們希望能從一個十分不同的角度來解決這個問題，

We wanted to tackle this problem in a very different direction.

Instead of using electrical motors, electromechanical actuators,

我們不再用電動馬達和其它的機電驅動，

we're using compressed air.

我們使用壓縮空氣，

We developed these novel actuators for the joints, so it's compliant.

我們開發了這些新型的關節驅動器，

它的兼容性很高。你可以簡單地

You can actually change the force,

simply just changing the air pressure.

通過改變氣壓改變力度，

And it can actually crush an empty soda can.

它可以壓扁空的易開罐。

It can pick up very delicate objects like a raw egg,

也可以撿起像生雞蛋這樣易碎的物體。

or in this case, a lightbulb.

或像這邊，一個燈泡。

The best part: it took only 200 dollars to make the first prototype.

最妙的是，它只需要二百美金，就能做出第一台原型機。

這機器人其實屬於蛇形機器人系列，

This robot is actually a family of snake robots

that we call HyDRAS,

我們稱它為 HyDRAS，

Hyper Degrees-of-freedom Robotic Articulated Serpentine.

蛇形高自由度機器人。

這機器人可以攀爬。

This is a robot that can climb structures.

This is a HyDRAS's arm.

這是 HyDRAS 的手臂，

It's a 12-degrees-of-freedom robotic arm.

這是有 12 個自由度的機械手臂。

But the cool part is the user interface.

但最酷的還是使用者界面。

The cable over there, that's an optical fiber.

電纜在那兒，這是一條光纖，

This student, it's probably her first time using it,

而這學生，大概是第一次用，

but she can articulate it in many different ways.

但她可以通過不同方式清楚傳達她的意思。

舉個例子，在伊拉克，你知道，是個戰場，

So, for example, in Iraq, the war zone, there are roadside bombs.

那裡路邊有炸彈。 目前你可以派這

Currently, you send these remotely controlled vehicles that are armed.

武裝的遙控載具過去，

It takes really a lot of time and it's expensive to train the operator

這真的會花費很多時間和金錢

去訓練操縱員操作這複雜的機械手臂，

to operate this complex arm.

In this case, it's very intuitive;

而這邊則是十分直覺的。

this student, probably his first time using it,

這學生，大概是第一次用，正在進行十分複雜的操縱任務，

is doing very complex manipulation tasks,

picking up objects and doing manipulation, just like that.

撿起物體，並進行操控，

像這樣，非常直觀。

Very intuitive.

Now, this robot is currently our star robot.

這個機器人是我們的明星級機器人。

We actually have a fan club for the robot, DARwIn:

我們的 DARwin 機器人有一個粉絲團，

Dynamic Anthropomorphic Robot with Intelligence.

人形動力智能機器人。

As you know, we're very interested in human walking,

如你所知，我們對人形機器人，

以及人類行走非常感興趣，

so we decided to build a small humanoid robot.

所以，我們打算做一個小型的人形機器人。

This was in 2004; at that time,

那是在 2004 年，

this was something really, really revolutionary.

在當時，這計畫非常、非常的有革命性。

This was more of a feasibility study:

這更像是一項可行性研究，

What kind of motors should we use? Is it even possible?

我們應該用怎麼樣的馬達呢？

這真的可行嗎？我們要如何控制呢？

What kinds of controls should we do?

沒有任何的感應器，

This does not have any sensors, so it's an open-loop control.

開環控制，

For those who probably know, if you don't have any sensors

你們中一些人可能會知道，如果你沒有任何感應器，

而同時又有干擾的時候，會有什麽事情發生。

and there's any disturbances, you know what happens.

(Laughter)

（笑聲）

Based on that success, the following year we did the proper mechanical design,

所以，基於這些成就，後面一年

我們做了適當的機械設計，

starting from kinematics.

從運動學開始。

And thus, DARwIn I was born in 2005.

最後，DARwin 一代在 2005 年誕生。

It stands up, it walks -- very impressive.

它站起來了，還能走了，十分讓人震驚。

However, still, as you can see, it has a cord, an umbilical cord.

儘管如此，你還是能看到，

它有條電線，臍帶，我們仍然使用外部電源

So we're still using an external power source

and external computation.

和外部的計算。

所以，到了 2006 年，是時候來點有趣的了。

So in 2006, now it's really time to have fun.

Let's give it intelligence.

我們給了它智能，我們給了它所有它需要的計算能力，

We give it all the computing power it needs:

a 1.5 gigahertz Pentium M chip, two FireWire cameras,

1.5千兆赫的奔騰M晶片，

兩個火線攝影機，八個陀螺儀，加速度計，

rate gyros, accelerometers, four forced sensors on the foot,

四個腳上的扭矩感應器，鋰電池。

lithium polymer batteries --

and now DARwIn II is completely autonomous.

現在的 DARwin 二代完全自動化了，

It is not remote controlled. There's no tethers.

它不再是遙控的了。

沒有外部繫繩。看，它朝四處看，尋找那個球，

It looks around, searches for the ball ... looks around, searches for the ball,

不停地看，搜索那個球，而且它嘗試著去踢足球，

and it tries to play a game of soccer autonomously -- artificial intelligence.

這就是自動化的，人工智能。

Let's see how it does.

讓我們來看它是怎樣做到的。這是我們第一次的嘗試，

This was our very first trial, and ...

(Video) Spectators: Goal!

影片：進了！

Dennis Hong: There is actually a competition called RoboCup.

這其實是一個叫作 RoboCup 的比賽。

I don't know how many of you have heard about RoboCup.

我不知道你們有多少人聽過 RoboCup，

這是一個國際性的自動化機器人足球比賽。

It's an international autonomous robot soccer competition.

And the actual goal of RoboCup is,

RoboCup 真正的目標是，

by the year 2050,

到 2050 年，

we want to have full-size, autonomous humanoid robots

我們會有全尺寸、自動化的人形機器人

足球隊與人類世界杯冠軍對壘，

play soccer against the human World Cup champions

and win.

而且，還要打贏人類。

(Laughter)

It's a true, actual goal.

這是個千真萬確的目標，也是個十分有野心的目標，

It's a very ambitious goal, but we truly believe we can do it.

但我們確信，我們可以做到。

這是去年在中國，

This is last year in China.

We were the very first team in the United States that qualified

我們是美國第一個獲得

人形機器人競賽參賽資格的隊伍。

in the humanoid RoboCup competition.

而今年，在奧地利。

This is this year in Austria.

You're going to see the action is three against three,

你們即將看到這比賽，是三對三，

完全地自動化。

completely autonomous.

(Video) (Crowd groans)

進了！耶！

DH: There you go. Yes!

The robots track and they team-play amongst themselves.

機器人跟著球跑，而且它們能有組織地踢，

完全由它們自己組織。

It's very impressive.

這讓人十分驚訝。這其實是一個包裝在

It's really a research event,

packaged in a more exciting competition event.

讓人興奮地比賽活動裡的研究項目。

你在這裡看到的，真是漂亮，

What you see here is the beautiful Louis Vuitton Cup trophy.

Louis Vuitton Cup 獎盃。

This is for the best humanoid.

這是給最佳人形機器人的，

We'd like to bring this, for the first time, to the United States next year,

我們很高興能將這個獎盃首次捧回美國，

下一年，希望我們也能夠如此幸運。

so wish us luck.

謝謝。

(Applause)

Thank you.

（掌聲）

(Applause)

DARwIn also has a lot of other talents.

DARwin 還有很多其它技能。

Last year, it actually conducted the Roanoke Symphony Orchestra

去年，在假日音樂會上，

它指揮了 Roanoke 交響樂團。

for the holiday concert.

This is the next generation robot, DARwIn IV,

這是下一代機器人，DARwin 四代，

much smarter, faster, stronger.

更聰明，更快，更強。

And it's trying to show off its ability:

它正炫耀它的本領。

"I'm macho, I'm strong."

「看我強壯又威武。」

(Laughter)

"I can also do some Jackie Chan-motion, martial art movements."

「我也可以做一些成龍

電影裡的武術動作啊」

(Laughter)

（笑聲）

And it walks away. So this is DARwIn IV.

然後，它走掉了，這，就是 DARwin 四代,

Again, you'll be able to see it in the lobby.

你們會有機會在門廳再一次看到它的。

We truly believe this will be the very first running humanoid robot

我們真的相信這會是美國第一個

能奔跑的人型機器人，所以拭目以待吧。

in the United States.

So stay tuned.

我已經展示一些我們工作上所製作的激動人心的機器人。

All right. So I showed you some of our exciting robots at work.

那麼我們成功的秘密是什麽呢?

So, what is the secret of our success?

Where do we come up with these ideas?

我們這些創意從哪兒來的呢?

How do we develop these kinds of ideas?

我們是如何開發這些創意的呢？

We have a fully autonomous vehicle

我們有一輛全自動的車，

that can drive into urban environments.

這車可以開到城市里。結果我們在 DARPA

We won a half a million dollars in the DARPA Urban Challenge.

城市挑戰賽中贏了 50 萬美金。

我們也研發了世界上首台

We also have the world's very first vehicle that can be driven by the blind.

能被盲人駕駛的汽車。

We call it the Blind Driver Challenge, very exciting.

我們叫這做盲人司機挑戰賽，非常好玩，

還有很多很多其它我想介紹的機器人計畫。

And many, many other robotics projects I want to talk about.

These are just the awards that we won in 2007 fall

這些只是我們在 2007 年秋天贏得的獎項，

是機器人比賽之類的。

from robotics competitions and those kinds of things.

So really, we have five secrets.

我們有五個秘訣。

First is: Where do we get inspiration?

首先是我們的啓發從哪兒來？

我們從哪兒得到靈機一動的瞬間？

Where do we get this spark of imagination?

這是一個真實的故事，我自己的故事。

This is a true story, my personal story.

At night, when I go to bed, at three, four in the morning,

當我晚上上床時，凌晨三、四點吧，

我躺在床上，閤上眼睛，我看到這些線條和圓圈，

I lie down, close my eyes, and I see these lines and circles

and different shapes floating around.

還有其它的形狀一直在周圍浮動，

And they assemble, and they form these kinds of mechanisms.

然後，它們組合起來，形成這樣的機械組件。

And I think, "Ah, this is cool."

我覺得，「啊，這超酷的。」

So right next to my bed I keep a notebook, a journal,

我一般都在我床頭準備一本筆記本，

一個有著一支帶 LED 燈的筆在上面的筆記本，

with a special pen that has an LED light on it,

because I don't want to turn on the light and wake up my wife.

因為我不想打開燈吵醒我妻子。

就這樣，我記下所有東西，畫好它，

So I see this, scribble everything down, draw things, and go to bed.

再上床睡覺。

Every day in the morning, the first thing I do,

每天早晨

我做的第一件事，不是給自己倒杯咖啡，

before my first cup of coffee, before I brush my teeth,

不是刷牙，而是打開我的筆記本。

I open my notebook.

很多時候，它是空的，

Many times it's empty; sometimes I have something there.

有時候，有東西了，卻是垃圾，

If something's there, sometimes it's junk.

更多時候，我不能看懂我自己寫的東西。

But most of the time, I can't read my handwriting.

而且，凌晨四點，你還能要求什麽呢？對吧？

Four in the morning -- what do you expect, right?

So I need to decipher what I wrote.

所以，我需要幫我所寫的東西解碼。

But sometimes I see this ingenious idea in there,

但是，有時候，我能看到一些絕妙的主意在這裡面，

and I have this eureka moment.

於是，靈光一閃，

I directly run to my home office, sit at my computer,

我直接跑到我家裡的辦公室，坐在我電腦旁，

I type in the ideas, I sketch things out

把這些想法打進電腦，把它們理清楚，

and I keep a database of ideas.

我有個點子資料庫。

So when we have these calls for proposals,

所以，當我們有提案的需求時，

I try to find a match between my potential ideas

我會嘗試在我的資料庫裡

找到匹配的可能想法

and the problem.

和問題，如果我們找到匹配的，我們會寫個研究提案，

If there's a match, we write a research proposal,

找到研究資金，然後開始我們的研究項目。

get the research funding in,

and that's how we start our research programs.

但只有靈機一動時候的創意是不足夠的。

But just a spark of imagination is not good enough.

How do we develop these kinds of ideas?

我們怎樣改進這些創意呢？

At our lab RoMeLa, the Robotics and Mechanisms Laboratory,

在我們的 RoMeLa，機器人機械實驗室，

we have these fantastic brainstorming sessions.

我們有超棒的腦力激盪時間，

So we gather around, we discuss problems and solutions and talk about it.

我們會聚在一起，討論有關問題

和社會問題，並分析它們。

But before we start, we set this golden rule.

在我們開始之前，我們定下了鐵則，

The rule is:

規則是：

nobody criticizes anybody's ideas.

不可以批評別人的想法、

Nobody criticizes any opinion.

不可以批評任何觀點、

This is important, because many times, students fear or feel uncomfortable

這很重要，因為很多時候，學生們會因為在乎

別人對自己的觀點和思想的想法

about how others might think about their opinions and thoughts.

而害怕或者感到不舒服

So once you do this, it is amazing how the students open up.

當我們實施了這措施以後，我們很驚訝地發現

學生們開始暢所欲言了。

They have these wacky, cool, crazy, brilliant ideas,

他們有很多怪誕的，但是很酷很瘋狂的妙點子，

and the whole room is just electrified with creative energy.

整個房間都被創意能量激發了，

這就是我們改進想法的方法。

And this is how we develop our ideas.

Well, we're running out of time.

我們的時間不多了，我還想說的一件事就是

One more thing I want to talk about is,

你知道，只有瞬間的靈光一閃和改進是不夠的。

you know, just a spark of idea and development is not good enough.

There was a great TED moment -- I think it was Sir Ken Robinson, was it?

曾有一個很好的 TED 演講，

是 Ken Robinson 爵士，對吧？

He gave a talk about how education and school kill creativity.

他的演講是有關教育和學校

如何扼殺創意。

Well, actually, there's two sides to the story.

其實這個故事有兩面，

So there is only so much one can do with just ingenious ideas

對於直率的想法、

創造力和好的工程直覺

and creativity and good engineering intuition.

一個人能做的就這麼點兒。

If you want to go beyond a tinkering,

如果你不只想做個貪玩的孩子，

if you want to go beyond a hobby of robotics

如果你不只想讓機器人成為你的興趣，

and really tackle the grand challenges of robotics

而是真的想在這方面通過進行精確的

研究來挑戰自我

through rigorous research,

we need more than that.

我們需要更多，這才是學校的目的。

This is where school comes in.

Batman, fighting against the bad guys,

蝙蝠俠，和壞人鬥爭，

he has his utility belt, he has his grappling hook,

他有實用的皮帶，有強大抓力的攀牆鉤，

he has all different kinds of gadgets.

有各種不同的小配件。

For us roboticists, engineers and scientists,

對於我們機器人學家，工程師和科學家，

這些工具就是你在課堂上學的課程，

these tools are the courses and classes you take in class.

Math, differential equations.

數學、微分方程、

I have linear algebra, science, physics --

線性代數、科學、物理，

今天還有，化學和生物。

even, nowadays, chemistry and biology, as you've seen.

這些就是我們需要的工具。

These are all the tools we need.

So the more tools you have, for Batman,

對於蝙蝠俠來說，有更多的工具

more effective at fighting the bad guys,

對付壞人的時候會更有效，

for us, more tools to attack these kinds of big problems.

對於我們，就是用更多的工具對付這些大難題。

So education is very important.

所以教育十分重要。

Also -- it's not only about that.

當然也不止這麼簡單，

最重要的，還是要努力學習。

You also have to work really, really hard.

我經常告訴我的學生

So I always tell my students,

先求明智地工作，再認真地工作，

"Work smart, then work hard."

這後面的照片是在凌晨三點拍的。

This picture in the back -- this is three in the morning.

I guarantee if you come to our lab at 3, 4am,

我能保證如果你凌晨三、四點來我們實驗室，

還能看到有學生在那工作，

we have students working there,

not because I tell them to, but because we are having too much fun.

不是因為我叫他們這樣，而是他們覺得這樣很好玩。

這就把我們帶到最後一個話題，

Which leads to the last topic:

do not forget to have fun.

不要忘記給自己點樂趣，

That's really the secret of our success, we're having too much fun.

這是我們成功最重要的秘密，我們真的覺得很好玩，

I truly believe that highest productivity comes when you're having fun,

我真的相信最高的效率來自於當你找到樂趣的時候。

這就是我們所做的成果。

and that's what we're doing.

And there you go.

謝謝。

Thank you so much.

（掌聲）

(Applause)