Dennis Hong: My 7 species of robot

翻译人员: dahong zhang 校对人员: Angelia King

第一个要介绍的机器人叫STriDER(Stride迈大步，Strider迈大步者)。

So the first robot to talk about is called STriDER.

全称是自激式三足动态实验机器人

It stands for Self-excited Tripedal Dynamic Experimental Robot.

(Self-excited Tripedal Dynamic Experimental Robot)。

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

这种机器人

受自然界的启发有三条腿。

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

不过您在自然界中

见过三条腿的动物吗？

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

应该没有。

那我们为什么要称其为仿生机器人呢？运作原理是什么呢？

How would it work?

说之前，先看看当下流行文化。

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

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

您应该知道赫伯特·乔治·威尔斯（H.G. Wells）的小说《世界大战》，以及由此改编的电影。

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

您现在看到的是一款流行

视频游戏。

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

在小说里，威胁地球的外星生物

被描述成三足机器人。

that have three legs that terrorize Earth.

不过我的机器人，STriDER，不是这样移动的。

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

This is an actual dynamic simulation animation.

这是一段真实的动态仿真动画。

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

我要展示的是机器人是如何移动行走的。

空中转体180度。

It flips its body 180 degrees

and it swings its leg between the two legs

其中一条腿，在另两条腿中间荡秋千。

and catches the fall.

So that's how it walks.

这是他的行走方式。不过研究一下

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

我们人类的两足行走，

what you're doing is,

人类不是用肌肉

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

提起一条腿迈出去，像机器人那样。对吧？

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

我们实际上是把一条腿荡出去，然后落地，

站稳，然后再荡腿...落地...。

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

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

使用您的身体内置动力，身体动力

just like a pendulum.

就像一个钟摆。

We call that the concept of passive dynamic locomotion.

我们称之为被动动力运动概念。

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

身体直立情况下，您所做的就是

potential energy to kinetic energy,

把势能转变

potential energy to kinetic energy.

为动能。

It's a constantly falling process.

这是一个不断下落的过程。

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

所以，虽然自然界中没有三足动物，

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

实际上我们还是受到了生物的启发

把这套原理运用于这种机器人，

to this robot.

所以它是仿生机器人。

Thus, it's a biologically inspired robot.

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

您这里所见的就是我们下一步的目标。

我们要让机器人把腿像弹簧一样折叠起来，然后弹射出去，做长距离运动。

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" --

然后展开腿，就像星球大战一样。

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

落地有，机器人的三条腿吸收落地震动，然后开始步行。

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

这里面黄色的区域，不是死光。

(Laughter)

这演示的是装有一部摄像机

This is just to show you

that if you have cameras or different types of sensors,

或者其他类型的传感器，

因为机器人个高，有1.8米高，

because it's 1.8 meters tall,

可以从灌木丛之类的障碍物上方露出头观察。

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

我们有两种型号的原型机。

So we have two prototypes.

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

第一个型号，在后面，那是STriDER I型。

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

前面那个，小一点儿的，是STriDER II型。

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

STriDER I型遇到的问题是

机器人太重了。我们装了太多的马达，

We had so many motors aligning the joints

诸如调整关节之类的东西。

and those kinds of things.

所以，我们决定综合成一个机械机构，

So we decided to synthesize a mechanical mechanism

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

我们就可以用一部马达，代替所有的马达，

we can coordinate all the motions.

我们就可以协调所有的动作。

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

这是用机械解决办法，代替机电一体化。

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

所以现在机器人上部机体就够轻巧了，可以在实验室内走路。

这是向成功迈出第一步。

This was the very first successful step.

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

还不完美。这个实验机器人摔倒了，

so we still have a lot of work to do.

所以后面还有我们忙的。

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

第二个要介绍的机器人缩写是IMPASS。

It stands for Intelligent Mobility Platform with Actuated Spoke System.

它带有驱动辐条系统的智能移动平台（Intelligent Mobility Platform with Actuated Spoke System）。

It's a wheel-leg hybrid robot.

它是一种“轮-腿“混合机器人。

So think of a rimless wheel or a spoke wheel,

无框轮，

或者叫辐条轮。

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

每个辐条都可以缩进缩出轮毂。

so, it's a wheel-leg hybrid.

所以它是”轮腿”混合机器人。

We're literally reinventing the wheel here.

我们又重新发明了一种轮子。

Let me demonstrate how it works.

让我演示一下工作原理。

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

这段视频中我们用了一种方法

被称为响应式方法。

Just simply using the tactile sensors on the feet,

只在利用足部的触觉传感器，

it's trying to walk over a changing terrain,

这机器人在崎岖不平的地形行走，

a soft terrain where it pushes down and changes.

地面柔软，随着它的下压而改变。

And just by the tactile information,

仅依靠足部传感器的信息，

it successfully crosses over these types of terrains.

它成功的跨越了这些地形。

But, when it encounters a very extreme terrain --

不过，它遇到极端地形时，

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

如视频中显示的，一个三倍于

机器人高度的障碍物，

of the robot --

then it switches to a deliberate mode,

它会切换到谨慎模式，

where it uses a laser range finder and camera systems

这里机器人利用激光测距仪，

和摄像系统，来找出障碍和测量大小，

to identify the obstacle and the size.

作出相应的对策，仔细的策划辐条的动作，

And it carefully plans the motion of the spokes

同时协调好各部分动作，这样显示出

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

令人惊讶的机动性。

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

你可能从来没有见过这样的机器人。

这是一部机动性很高的机器人

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

这就是我们开发的，叫做IMPASS的机器人。

Ah, isn't that cool?

很酷吧？

When you drive your car,

您开车的时候，

转动方向盘，这种方式

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

叫阿克曼转向。

The front wheels rotate like this.

前轮像这样转动。

For most small-wheeled robots,

对于那些小型轮式机器人，

they use a method called differential steering

它们一般采用差速转向，

where the left and right wheel turn the opposite direction.

也就是左轮和右轮向相反方向转动。

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

对于IMPASS机器人，我们可以采用不同方式的转向运动。

For example, in this case,

如视频中演示的那样，它的左右轮连接在一个轴上，

even though the left and right wheels are connected

以同样的转速转动。

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

不同的是，我们依靠调解辐条的长度实现转向。

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

辐条长度的变化改变了辐条轮的直径大小，以此实现左右转弯。

then can turn to the left and to the right.

这些只是一些IMPASS可以做的巧妙动作

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

的事例。

This robot is called CLIMBeR:

这个机器人叫CLIMBeR(攀登者)，

Cable-suspended Limbed Intelligent Matching Behavior Robot.

全称是：钢缆吊肢智能匹配行为机器人(Cable-suspended Limbed Intelligent Matching Behavior Robot.)。

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

我曾和许多NASA喷气推进实验室的科学家们聊过，

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

在喷气推进实验室，最出名的就是火星车。

科学家们和地质学家们经常告诉我，

and the scientists, geologists always tell me

真正有趣的科学、

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

富含科学知识的地点就是在悬崖峭壁上。

are always at the cliffs.

But the current rovers cannot get there.

不过目前火星车还探测不了峭壁。

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

受此启发，我们要建造一台

that can climb a structured cliff environment.

攀登峭壁的机器人。

So this is CLIMBeR.

那就是CLIMBeR机器人。

It has three legs.

它有三条腿。可能很难看到，

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

但它顶部有一个绞盘，一条钢缆。

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

它正在测算最好的立足点。

And then once it figures that out,

一旦测算好，

in real time, it calculates the force distribution:

它会实时计算出力的分布。

how much force it needs to exert to the surface

计算出需要施加多大的力，

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

确保不翻下来，不打滑。

Once it stabilizes that, it lifts a foot,

一旦稳定下来，抬起一条腿，

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

然后利用绞盘，可以向上爬一点点。

Also for search and rescue applications as well.

也可以应用在搜索和救援工作上。

Five years ago, I actually worked at NASA JPL

五年前，我夏季在NASA喷气推进实验室

做教员研究员。

during the summer as a faculty fellow.

他们有个六足机器人，称作LEMUR。

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

So this is actually based on that.

基于此我们开发一台机器人，称作MARS(Mars, 火星)

This robot is called MARS:

Multi-Appendage Robotic System.

多附体机器人系统（Multi-Appendage Robotic System）。它是一种六足机器人。

It's a hexapod robot.

We developed our adaptive gait planner.

我们开发了自适应步态规划软件。

We actually have a very interesting payload on there.

我们放了一个十分有趣的有效载荷。

The students like to have fun.

学生们喜欢有趣的机器人。您可以看到

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

机器人在不规则地形上行走。

(Motor sound)

它试图在粗糙地形上行走，

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

沙地上，

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

取决于水分含量或沙粒大小的

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

脚下的泥土下沉模式变化。

机器人自适应的调整步态以便成功翻越这类地形。

to successfully cross over these kind of things.

It also does some fun stuff.

除此之外，它还可以做出一些搞笑的事。

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

我们的实验室有很多参观者。

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

有参观者来的时候，MARS机器人会走到计算机旁边，

并输入“你好！我叫MARS。”

starts typing, "Hello, my name is MARS.

欢迎来到RoMeLa，

Welcome to RoMeLa,

the Robotics Mechanisms Laboratory at Virginia Tech."

弗吉尼亚理工大学的“机器人技术与机械实验室（RoMeLa）。

(Laughter)

This robot is an amoeba robot.

这个机器人是一个变形虫机器人。

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

我们没有时间讲述技术细节，

I'll just show you some of the experiments.

我将展示些实验。

These are some of the early feasibility experiments.

这是一些早期的可行性实验。

弹性表皮上存有势能，使之移动。

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

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

利用一个有张力绳子

使之前进和后退。它被称为嵌合体(ChIMERA)。

It's called ChIMERA.

We also have been working with some scientists and engineers

我们还和来自宾州大学的科学家

和工程师合作，

from UPenn

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

开发出化学驱动版本的

变形虫机器人。

We do something to something,

我们鼓捣一下，

and just like magic, it moves.

然后，就像变魔术，它移动了。就像科幻电影The Blob。

"The Blob."

This robot is a very recent project.

这个机器人是最近的项目。它叫RAPHaEL

It's called RAPHaEL:

带有弹性韧带的气压机器手臂 (Robotic Air Powered Hand with Elastic Ligaments)。

Robotic Air-Powered Hand with Elastic Ligaments.

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

市面上有不少不错的机器手臂。

out there on the market.

不过动辄就要几万美元太贵了。

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

tens of thousands of dollars.

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

对于假肢应用可能不太现实，

因为太贵了。

because it's not affordable.

我们想到一个非常不同的方法去解决这个问题。

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

Instead of using electrical motors, electromechanical actuators,

不使用电动马达，机电执行器，

we're using compressed air.

而是用压缩空气作动力。

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

我们开发这些新型驱动器的关节。

它是兼容的。你其实可以通过调节气压

You can actually change the force,

simply just changing the air pressure.

就很容易地来改变驱动力的大小。

And it can actually crush an empty soda can.

它的力气可以压扁一个空可乐罐。

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

也可以握住易碎的物体，如生鸡蛋

or in this case, a lightbulb.

或如这展示的电灯泡。

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

最棒的是，这个原型机仅花费200美元。

这部机器人实际上是一系列蛇形机器人，

This robot is actually a family of snake robots

that we call HyDRAS,

我们称之为HyDRAS，

Hyper Degrees-of-freedom Robotic Articulated Serpentine.

高自由度铰接式蛇形机器人（Hyper Degrees-of-freedom Robotic Articulated Serpentine）。

这是一个可以攀爬的机器人。

This is a robot that can climb structures.

This is a HyDRAS's arm.

这是一个HyDRAS型机器臂。

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

它有12个自由度的机器臂。

But the cool part is the user interface.

不过最酷的是用户接口。

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

这些电缆是光纤。

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

这名学生，可能是第一次使用，

but she can articulate it in many different ways.

她可以用很多不同的方法操作。

例如在伊拉克，在战区，

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

常有路边炸弹。

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

目前，派出的是遥控武装车辆。

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

它需要很多时间和花费

来培训控制这复杂武装车辆的操作员。

to operate this complex arm.

In this case, it's very intuitive;

在这种情况下，这个机器手臂很直观。

this student, probably his first time using it,

这名学生可能是第一次使用，就能完成复杂的操作任务，

is doing very complex manipulation tasks,

picking up objects and doing manipulation, just like that.

拾取物体，操作，

就像这样，非常直观。

Very intuitive.

Now, this robot is currently our star robot.

这部机器人，是我们的明星机器人。

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

我们有个DARwIn机器人兴趣小组，

Dynamic Anthropomorphic Robot with Intelligence.

智能动力人形机器人(Dynamic Anthropomorphic Robot With Intelligence)。

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

我们对人形机器人，

人类行走机器人，非常感兴趣，

so we decided to build a small humanoid robot.

我们决定造一个小型人形机器人。

This was in 2004; at that time,

在2004年，那时

this was something really, really revolutionary.

这是革命性的东西。

This was more of a feasibility study:

更多的是可行性研究，

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

应该选用什么样的马达？

可行吗？我们做什么样的控制？

What kinds of controls should we do?

这个机器人没有传感器。

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

它是开环控制。

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

如您所知，如果没有控制器

稍有扰动就会出问题。

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

(Laughter)

（笑声）

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

基于此，翌年，

我们做了正确的机械设计，

starting from kinematics.

从运动学开始。

And thus, DARwIn I was born in 2005.

2005年，DARwIn I型诞生。

It stands up, it walks -- very impressive.

站立，行走，令人印象深刻。

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

然而，如你所见

它是有线的，还有一条脐带。我们还是用的外部电源，

So we're still using an external power source

and external computation.

以及外部运算。

2006年，正是时候可以找乐子了。

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

Let's give it intelligence.

给他智能。我们给它所需的计算能力，

We give it all the computing power it needs:

a 1.5 gigahertz Pentium M chip, two FireWire cameras,

1.5GHz的Pentium M处理器，

两个火线（IEEE1394）摄像头,8个陀螺仪，一个加速度计，

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

足部四个力矩传感器，锂电池。

lithium polymer batteries --

and now DARwIn II is completely autonomous.

DARwIn II是全部自主式的。

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

不用远程遥控。

没有外接连线。它查看四周，寻找球，

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

再查看四周，寻找球，试着踢足球，

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

自主式的踢球，实现人工智能。

Let's see how it does.

看看它的能耐。这是我们第一次测试，

This was our very first trial, and ...

(Video) Spectators: Goal!

视频：进球了！

Dennis Hong: There is actually a competition called RoboCup.

有个竞赛叫机器人世界杯赛。

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

我不知道你们知不知道机器人世界杯赛。

机器人世界杯赛是自主式机器人足球赛事。

It's an international autonomous robot soccer competition.

And the actual goal of RoboCup is,

机器人世界杯赛的目标是，

by the year 2050,

到2050年

we want to have full-size, autonomous humanoid robots

我们有人类大小的自主式人形机器人

与人类的世界杯冠军队进行足球比赛

play soccer against the human World Cup champions

and win.

而且要胜利。

(Laughter)

It's a true, actual goal.

非常实际的目标。非常有野心的目标，

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

我们认为我们可以做到。

去年在中国。

This is last year in China.

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

我们是美国在人形机器人比赛获得比赛资格的

第一个团队。

in the humanoid RoboCup competition.

今年在奥地利举行。

This is this year in Austria.

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

三对三

完全自主的机器人。

completely autonomous.

(Video) (Crowd groans)

不错。很好！

DH: There you go. Yes!

The robots track and they team-play amongst themselves.

机器人跟踪，踢球，

组队对抗。

It's very impressive.

令人印象深刻。这实际上是

It's really a research event,

packaged in a more exciting competition event.

裹着竞赛外衣的科研工作。

这张照片是漂亮的

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

奖杯（Louis Vuitton Cup路易威登提供的奖杯）。

This is for the best humanoid.

这是颁发给最佳人形机器人的，

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

明年我们希望可以首次把它带回美国，

希望我们走运。

so wish us luck.

谢谢。

(Applause)

Thank you.

（掌声）

(Applause)

DARwIn also has a lot of other talents.

DARwIn还有其他的才能。

Last year, it actually conducted the Roanoke Symphony Orchestra

去年假日音乐会上，它实际指挥罗阿诺克

交响乐团。

for the holiday concert.

This is the next generation robot, DARwIn IV,

这是下一代，DARwIn四型，

much smarter, faster, stronger.

更小，更快，更有力。

And it's trying to show off its ability:

它正在展示它的能力。

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

“我是男子汉，我很结实。”

(Laughter)

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

我可以做些成龙式的

武术动作。

(Laughter)

（笑声）

And it walks away. So this is DARwIn IV.

它走开。这是DARwIn四型，

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

你可以在大厅里看到。

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

我们确信这将是第一个运行

在美国的人形机器人。因此，敬请关注。

in the United States.

So stay tuned.

好了，我展示给大家我们有趣的机器人。

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

那么我们成功的秘诀是什么呢？

So, what is the secret of our success?

Where do we come up with these ideas?

我们从哪里想出这些点子呢？

How do we develop these kinds of ideas?

我们如何发展这些点子呢？

We have a fully autonomous vehicle

我们有全自主式车辆

that can drive into urban environments.

可以穿行在城市里。我们赢了DARPA挑战赛的50万

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

美元。

我们有世界上第一辆

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

盲人驾驶汽车。

We call it the Blind Driver Challenge, very exciting.

我们称之为，盲人驾驶员的挑战，

还有许多其他的机器人项目。

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

These are just the awards that we won in 2007 fall

这些是2007年秋天我们赢得的奖项，

从机器人竞赛之类的活动中取得的。

from robotics competitions and those kinds of things.

So really, we have five secrets.

实际上我们有5个秘诀。

First is: Where do we get inspiration?

第一，我们从哪里得到的启发，

从哪里得到灵感的？

Where do we get this spark of imagination?

这是我个人切身经历的。

This is a true story, my personal story.

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

凌晨三四点钟的时候我上床睡觉，

我躺下，闭上眼睛，一些线环

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

and different shapes floating around.

和其他形状的东西浮现在脑海中，

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

拼凑起来，它们组成了一些机器。

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

然后我想，“这个很棒。”

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

就在我的床头有一个记事本，

日记，带有一个特殊的配有LED灯光的钢笔，

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.

因为我不想开灯弄醒我的妻子。

我看到这些绘图，涂鸦上我的想法，

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

然后睡觉。

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

每天早上，

喝咖啡刷牙之前的第一件事，

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

我打开笔记本。

I open my notebook.

通常是空的，

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

有时候，就是一些胡写乱画上去的，

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

有时候，我都看不懂我的笔迹。

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

凌晨4点写的东西，你说能好到哪里去？

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

So I need to decipher what I wrote.

我得辨识我的潦草字迹。

But sometimes I see this ingenious idea in there,

有时候，我会看到巧妙的点子，

and I have this eureka moment.

我就有了这种瞬间灵感Eureka。（Eureka阿基米德发现浮力后喊道的）

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

我直接跑到书房去，坐在计算机旁边，

I type in the ideas, I sketch things out

输入下我的点子，我勾画出来的东西，

and I keep a database of ideas.

我有一个点子数据库。

So when we have these calls for proposals,

当我们需要建议的时候，

I try to find a match between my potential ideas

我就会在我的潜在点子库中找合适的

点子，

and the problem.

如果匹配我就写一个研究建议，

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

获得研究经费，这就是我们如何开始我们的研究计划。

get the research funding in,

and that's how we start our research programs.

仅仅是一丝灵感，还不够。

But just a spark of imagination is not good enough.

How do we develop these kinds of ideas?

我们如何发展这些点子呢？

At our lab RoMeLa, the Robotics and Mechanisms Laboratory,

在机器人技术与机械实验室（RoMeLa），

we have these fantastic brainstorming sessions.

我们有这个神奇的头脑风暴会议。

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

我们聚在一起讨论问题，

社会问题，诸如此类的。

But before we start, we set this golden rule.

讨论之前，我们设定一个规矩。

The rule is:

规矩是：

nobody criticizes anybody's ideas.

不准批评别人的点子。

Nobody criticizes any opinion.

不准指责任何意见。

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

这很重要，因为，很多时候，学生们

害怕别人

about how others might think about their opinions and thoughts.

批评他们的点子或主意。

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

一旦你这样做，

你就会惊异地发现学生们的创造力。

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

他们有光怪陆离的点子，

and the whole room is just electrified with creative energy.

整个房间里充满了创意能量。

这是我们如何发展这些点子的。

And this is how we develop our ideas.

Well, we're running out of time.

时间不够了，我再说一点

One more thing I want to talk about is,

只有点子和拓展是不够的。

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?

有一个TED瞬间，

我想他是Ken Robinson，对吗？

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

他在TED讲过

学校教育扼杀了创造力。

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

实际上，这是有正负两面性的。

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

人们只能做这么多，

非凡的点子

and creativity and good engineering intuition.

和有创造力的工程直觉。

If you want to go beyond a tinkering,

如果你想超越，

if you want to go beyond a hobby of robotics

超越机器人爱好

and really tackle the grand challenges of robotics

真正通过枯燥的研究应对机器人学的

巨大挑战，

through rigorous research,

we need more than that.

我们需要更多的东西。这些东西都是学校教的。

This is where school comes in.

Batman, fighting against the bad guys,

蝙蝠侠和坏人战斗，

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

蝙蝠侠有著名的万能腰带、绳钩，

he has all different kinds of gadgets.

还有其他的小玩意儿。

For us roboticists, engineers and scientists,

对于我们，机器人学家，工程师，科学家，

这些工具就是在教室里的课程。

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

Math, differential equations.

数学，微分方程。

I have linear algebra, science, physics --

线性代数，科学，物理，

更有，今天讲到的诸如化学，生物学。

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

这些都是我们需要的工具。

These are all the tools we need.

So the more tools you have, for Batman,

工具越多，

more effective at fighting the bad guys,

蝙蝠侠才能更有效的对抗坏人，

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

对于我们，工具越多就是解决问题的知识。

So education is very important.

所以教育至关重要。

Also -- it's not only about that.

不仅仅是这些，

你还要非常努力工作。

You also have to work really, really hard.

我常常告诫我的学生们

So I always tell my students,

学会聪明地工作，然后努力工作。

"Work smart, then work hard."

这张照片是凌晨三点拍的。

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

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

如果您凌晨3、4点来我们实验室，

您会看到学生们还在那里，

we have students working there,

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

不是我要求的，而是他们有兴趣做。

这就是最后一个主题。

Which leads to the last topic:

do not forget to have fun.

别忘了找乐子。

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

这是我们成功的秘诀，我们工作中充满了乐趣。

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

我认为人有多大乐，地有多大产。

这就是我们的工作。

and that's what we're doing.

And there you go.

就到这里吧。感谢各位听众。

Thank you so much.

（掌声）

(Applause)