Chris Urmson: How a driverless car sees the road

譯者: Kenny Lo 審譯者: Yamei Huang

So in 1885, Karl Benz invented the automobile.

1885年，卡爾·賓士發明汽車。

Later that year, he took it out for the first public test drive,

那年底， 他開著那台車做了第一次公開試駕，

and -- true story -- crashed into a wall.

結果，撞毀了。

For the last 130 years,

過去 130 年來，

we've been working around that least reliable part of the car, the driver.

我們一直致力於改進 車裡最不可靠的部分，駕駛。

We've made the car stronger.

我們讓車子更堅固。

We've added seat belts, we've added air bags,

我們加上安全帶和安全氣囊，

and in the last decade, we've actually started trying to make the car smarter

過去十年， 我們想辦法讓車子變得更聰明

to fix that bug, the driver.

來修正駕駛這個問題。

Now, today I'm going to talk to you a little bit about the difference

現在，我要告訴你

between patching around the problem with driver assistance systems

使用駕駛輔助系統來修正這問題，

and actually having fully self-driving cars

和完全自動化駕駛其中的差異

and what they can do for the world.

以及在世界上所產生的影響。

I'm also going to talk to you a little bit about our car

我也將告訴你 關於我們車子的一些細節

and allow you to see how it sees the world and how it reacts and what it does,

讓你可以了解它所看到的世界 以及如何對外界做出反應，

but first I'm going to talk a little bit about the problem.

首先我先來探討一個問題。

And it's a big problem:

是一個大問題：

1.2 million people are killed on the world's roads every year.

全世界每年有 120 萬人 死於交通事故。

In America alone, 33,000 people are killed each year.

僅僅美國， 每年就佔了 33,000 人。

To put that in perspective,

依此數據與飛機事故比較，

that's the same as a 737 falling out of the sky every working day.

等於每個上班日， 都有一台 737 從空中掉下。

It's kind of unbelievable.

有點讓人無法置信。

Cars are sold to us like this,

車輛以這種模式賣給我們，

but really, this is what driving's like.

但實際上， 這才是我們開車所遇到的狀況，

Right? It's not sunny, it's rainy,

對吧？不是晴天，而是雨天，

and you want to do anything other than drive.

除了開車外你還想要做其他事。

And the reason why is this:

就是這個原因：

Traffic is getting worse.

交通變得更糟糕了。

In America, between 1990 and 2010,

在美國，1990 年到 2010 年間，

the vehicle miles traveled increased by 38 percent.

汽車行駛哩程數增加百分之三十八，

We grew by six percent of roads,

但是道路只增加百分之六，

so it's not in your brains.

所以不是錯覺。

Traffic really is substantially worse than it was not very long ago.

跟幾年前比起來 交通其實是變差。

And all of this has a very human cost.

所有這一切都代表大量的人力成本。

So if you take the average commute time in America, which is about 50 minutes,

以美國平均通勤時間來看， 大約 50 分鐘，

you multiply that by the 120 million workers we have,

乘以目前約一億兩千萬工作人口，

that turns out to be about six billion minutes

將會是六十億分鐘的時間

wasted in commuting every day.

浪費在每天的通勤上。

Now, that's a big number, so let's put it in perspective.

這是個很大的數值， 這個數據，相當於

You take that six billion minutes

把六十億分鐘的時間

and you divide it by the average life expectancy of a person,

除以一般人的平均壽命，

that turns out to be 162 lifetimes

將會是 162 個人一生的時間

spent every day, wasted,

每天浪費在這交通上面，

just getting from A to B.

只是要從 Ａ 點移動到 B 點。

It's unbelievable.

讓人無法置信。

And then, there are those of us who don't have the privilege

而且，有些在交通上

of sitting in traffic.

弱勢的人，

So this is Steve.

這是史蒂夫。

He's an incredibly capable guy,

一個非常有才能力的人，

but he just happens to be blind,

但是他卻是眼睛失明，

and that means instead of a 30-minute drive to work in the morning,

他不是每天早上 花 30 分鐘開車上班，

it's a two-hour ordeal of piecing together bits of public transit

而是要痛苦的花兩個時 轉搭大眾運輸工具

or asking friends and family for a ride.

或請求朋友或親人接送。

He doesn't have that same freedom that you and I have to get around.

他無法像你我一樣 有到處走動的自由。

We should do something about that.

我們應該做一些事情。

Now, conventional wisdom would say

在現在傳統的思慮會提到

that we'll just take these driver assistance systems

我們可以使用一些駕駛輔助系統

and we'll kind of push them and incrementally improve them,

我們則持續的推動及改善整個系統，

and over time, they'll turn into self-driving cars.

隨著時間演進， 轉變為自動駕駛系統。

Well, I'm here to tell you that's like me saying

在這我要告訴你們就像我所說的

that if I work really hard at jumping, one day I'll be able to fly.

如果我可以很努力的跳躍， 有一天我可以飛上天

We actually need to do something a little different.

我們確實需要 用一些不同的方式去做事情。

And so I'm going to talk to you about three different ways

我將告訴你 在自動駕駛系統

that self-driving systems are different than driver assistance systems.

與駕駛輔助系統之間， 有三個不同點。

And I'm going to start with some of our own experience.

從我們本身的經驗開始談起。

So back in 2013,

2013 年。

we had the first test of a self-driving car

我們第一次做自動駕駛車的測試

where we let regular people use it.

我們讓一般大眾人去開它。

Well, almost regular -- they were 100 Googlers,

嗯，幾乎算是 -- 他們是 100 位谷歌的員工，

but they weren't working on the project.

但他們的工作都不屬於這個專案，

And we gave them the car and we allowed them to use it in their daily lives.

我們提供車輛 並允許在每天的日常生活中使用。

But unlike a real self-driving car, this one had a big asterisk with it:

但這不像是自動駕駛的車， 上頭有一個大大的星號在車上，

They had to pay attention,

他們必須集中注意力開車，

because this was an experimental vehicle.

因為這些只是實驗車輛。

We tested it a lot, but it could still fail.

我們測試很多， 但仍有失敗狀況發生。

And so we gave them two hours of training,

所以我們給車主 2 個小時的訓練，

we put them in the car, we let them use it,

再讓他們進入車內使用它，

and what we heard back was something awesome,

我們所收到的回覆讓人感到驚訝，

as someone trying to bring a product into the world.

當一個新產品嘗試進入這個世界。

Every one of them told us they loved it.

每一個人都跟我們說他們愛上了它。

In fact, we had a Porsche driver who came in and told us on the first day,

事實上，第一天有一個 開保時捷的駕駛跟我們說，

"This is completely stupid. What are we thinking?"

「這完全是件愚蠢的事情， 不知道我們在想些什麼？」

But at the end of it, he said, "Not only should I have it,

但是在他測試結束後，他說 「不該只有我可以使用它，

everyone else should have it, because people are terrible drivers."

每個人都該使用它， 因為許多人都是個糟糕的駕駛。」

So this was music to our ears,

這對我們來說有很大的鼓勵，

but then we started to look at what the people inside the car were doing,

然後我們開始研究 人們在車裡做些什麼，

and this was eye-opening.

真讓人大開眼界。

Now, my favorite story is this gentleman

我最喜歡的故事裡有一位男士

who looks down at his phone and realizes the battery is low,

他低頭看手機 發現電池快沒電了，

so he turns around like this in the car and digs around in his backpack,

然後在車裡像這樣轉過身來， 並且在背包裡找尋東西，

pulls out his laptop,

拿出一台筆記型電腦，

puts it on the seat,

放在前座，

goes in the back again,

再回頭一次，

digs around, pulls out the charging cable for his phone,

繼續搜尋，拿出手機的充電線，

futzes around, puts it into the laptop, puts it on the phone.

轉身回來， 把電源線接上筆電跟手機。

Sure enough, the phone is charging.

當然他的手機已經開始充電了。

All the time he's been doing 65 miles per hour down the freeway.

同時他以 65 英哩的速度 在高速公路上行駛。

Right? Unbelievable.

讓人無法置信。

So we thought about this and we said, it's kind of obvious, right?

我們思考這整件事情， 有明顯的結論

The better the technology gets,

有更好的科技輔助，

the less reliable the driver is going to get.

駕駛就越不可靠。

So by just making the cars incrementally smarter,

若只讓車子變得更聰明，

we're probably not going to see the wins we really need.

那就和我們希望達到的結果不同。

Let me talk about something a little technical for a moment here.

讓我來談論有關技術的部分。

So we're looking at this graph, and along the bottom

我們來看這圖型，底部的部分，

is how often does the car apply the brakes when it shouldn't.

是在不該踩煞車的情況下 卻踩煞車的頻率，

You can ignore most of that axis,

你可以忽略大部分的 X 軸，

because if you're driving around town, and the car starts stopping randomly,

因為如果在你開車到鎮上的路程中， 隨時煞車的話，

you're never going to buy that car.

你將不會買這部車。

And the vertical axis is how often the car is going to apply the brakes

從垂直軸上 可以看到當車輛踩煞車後

when it's supposed to to help you avoid an accident.

可以幫助你避免意外的頻率。

Now, if we look at the bottom left corner here,

現在，我們看到左下角這個點，

this is your classic car.

這是我們一般的車輛。

It doesn't apply the brakes for you, it doesn't do anything goofy,

他不會幫忙煞車 傻傻的也不會幫忙任何事，

but it also doesn't get you out of an accident.

當然也無法幫你避免意外。

Now, if we want to bring a driver assistance system into a car,

現在， 如果我們想要引進駕駛輔助系統，

say with collision mitigation braking,

如碰撞減輕煞車系統。

we're going to put some package of technology on there,

我們將在這上面導入一些技術方案，

and that's this curve, and it's going to have some operating properties,

由這個曲線得知， 這系統可以發揮一些功效，

but it's never going to avoid all of the accidents,

但仍不可能避免所有的意外，

because it doesn't have that capability.

因為尚未有足夠的能力。

But we'll pick some place along the curve here,

但我們可以在這個曲線中挑一點，

and maybe it avoids half of accidents that the human driver misses,

它也許就足夠避免掉一半 人為疏失所造成的意外，

and that's amazing, right?

非常神奇，對吧？

We just reduced accidents on our roads by a factor of two.

我們改變一、兩個因素 就可以把路上的意外事故減少一半。

There are now 17,000 less people dying every year in America.

在美國每年有接近 一萬七千人 死於交通事故。

But if we want a self-driving car,

但如果我們想要有自動駕駛車輛，

we need a technology curve that looks like this.

我們需要像這條的技術曲線。

We're going to have to put more sensors in the vehicle,

需要將更多的感測器放在車上，

and we'll pick some operating point up here

將功能調整在曲線上這一點

where it basically never gets into a crash.

基本上這點不會導致車禍發生。

They'll happen, but very low frequency.

就算是有，也是個很低的機率。

Now you and I could look at this and we could argue

當然你可以跟我辯論這一部分

about whether it's incremental, and I could say something like "80-20 rule,"

曲線是否有增量性，我只能說 有些事情就像「80-20 法則」，

and it's really hard to move up to that new curve.

向上移動成為一個新的曲線 是非常困難的。

But let's look at it from a different direction for a moment.

我們暫時由另一個方向來看這件事。

So let's look at how often the technology has to do the right thing.

可以發現科技 做正出確的判斷有多高。

And so this green dot up here is a driver assistance system.

這條綠線代表的是駕駛輔助系統。

It turns out that human drivers

結果說明了一般駕駛

make mistakes that lead to traffic accidents

的錯誤行為而導致意外發生

about once every 100,000 miles in America.

在美國約每十萬英哩發生一次。

In contrast, a self-driving system is probably making decisions

相對的，自動駕駛系統做出決定

about 10 times per second,

每秒大約 10 次，

so order of magnitude,

在這個數量級，

that's about 1,000 times per mile.

大約每英哩 1,000 次。

So if you compare the distance between these two,

所以如果你比較這兩個的距離，

it's about 10 to the eighth, right?

大約是 10 的 8 次方，對吧？

Eight orders of magnitude.

8 次方的數量級。

That's like comparing how fast I run

這個對比有點像是 以我跑步的速度

to the speed of light.

與光速作比較。

It doesn't matter how hard I train, I'm never actually going to get there.

所以不管我如何努力訓練， 都不可能實際達到那個程度。

So there's a pretty big gap there.

他們之間有一個很大的差距。

And then finally, there's how the system can handle uncertainty.

最後的部分， 這個系統可以處理一些突發狀況。

So this pedestrian here might be stepping into the road, might not be.

這個人有可能是走在馬路上， 也有可能不是。

I can't tell, nor can any of our algorithms,

我不能預測， 我們的演算法也無法預測，

but in the case of a driver assistance system,

但是駕駛輔助系統在這情況下，

that means it can't take action, because again,

無法採取任何行動，

if it presses the brakes unexpectedly, that's completely unacceptable.

如果無預期的踩煞車 是完全無法被接受的。

Whereas a self-driving system can look at that pedestrian and say,

當自動駕駛系統發現這位行人會說，

I don't know what they're about to do,

我不知道他們打算做什麼，

slow down, take a better look, and then react appropriately after that.

減慢速度，仔細觀察， 之後再採取更適當的回應。

So it can be much safer than a driver assistance system can ever be.

比起駕駛輔助系統它將會更為安全。

So that's enough about the differences between the two.

這是兩個不同系統之間的差別。

Let's spend some time talking about how the car sees the world.

我們花點時間來探討 車輛所看到的世界。

So this is our vehicle.

這是我們的測試車。

It starts by understanding where it is in the world,

從理解目前所在的位置開始，

by taking a map and its sensor data and aligning the two,

比對地圖與感應到的訊息，

and then we layer on top of that what it sees in the moment.

然後把當下所看到的訊息 再加上另一訊息。

So here, all the purple boxes you can see are other vehicles on the road,

在裏頭，你所看到的所有紫色方框 都是路上的其他車輛，

and the red thing on the side over there is a cyclist,

旁邊的紅色部分則是自行車，

and up in the distance, if you look really closely,

如果你仔細看 上方較遠處，

you can see some cones.

可以看到一些三角錐。

Then we know where the car is in the moment,

然後就可以知道車輛當時的位置，

but we have to do better than that: we have to predict what's going to happen.

但是我們需要做得更好： 要能夠預測出將會發生的事情，

So here the pickup truck in top right is about to make a left lane change

右上角有一輛小貨卡 將會切換到左邊車道

because the road in front of it is closed,

因為前方的路段將會關閉，

so it needs to get out of the way.

所以需要變更車道

Knowing that one pickup truck is great,

可以預測小貨車的行徑 是件很棒的事，

but we really need to know what everybody's thinking,

但我們還需要知道每個人的想法，

so it becomes quite a complicated problem.

這變成一個非常複雜的問題。

And then given that, we can figure out how the car should respond in the moment,

有了這資訊後，我們便可以 推測出當下車輛該如何反應。

so what trajectory it should follow, how quickly it should slow down or speed up.

該跟隨哪一條路線， 該多快反應減速或加速。

And then that all turns into just following a path:

匯集所有項目後 只要跟隨著路線，

turning the steering wheel left or right, pressing the brake or gas.

向左或向右轉動方向盤， 加速或踩油門。

It's really just two numbers at the end of the day.

只要這兩個數值 就可以持續到一天結束。

So how hard can it really be?

所以會有多難呢？

Back when we started in 2009,

在 2009 年我們剛開始時，

this is what our system looked like.

我的系統看起來像這樣。

So you can see our car in the middle and the other boxes on the road,

你可以看到在中心有我們的車輛， 路上還有其他小方框，

driving down the highway.

行駛在高速公路上。

The car needs to understand where it is and roughly where the other vehicles are.

這輛測試車需要知道它現在位置 以及其他車輛大約位置。

It's really a geometric understanding of the world.

用幾何方式來理解這個世界。

Once we started driving on neighborhood and city streets,

當開始行駛在近郊及街道中時，

the problem becomes a whole new level of difficulty.

這問題又變為更複雜的層次。

You see pedestrians crossing in front of us, cars crossing in front of us,

可以看到行人及車輛 都會在我們前面穿過，

going every which way,

往各個方向移動，

the traffic lights, crosswalks.

紅綠燈，行人穿越道。

It's an incredibly complicated problem by comparison.

相對而言 這是個相當複雜的問題。

And then once you have that problem solved,

一旦這問題可以被解決掉，

the vehicle has to be able to deal with construction.

車輛就有辦法去處理 這建構出來的環境。

So here are the cones on the left forcing it to drive to the right,

如果左邊有三角錐 它就會要求往右邊開，

but not just construction in isolation, of course.

當然不只是個封閉的施工環境。

It has to deal with other people moving through that construction zone as well.

它也還必須去處理 有人走在施工區的路段。

And of course, if anyone's breaking the rules, the police are there

當然，如果有人違規，警察在場

and the car has to understand that that flashing light on the top of the car

車輛必須知道車頂上有閃著燈的車輛

means that it's not just a car, it's actually a police officer.

代表的是警車而不是一般車輛。

Similarly, the orange box on the side here,

相似的情況下， 在路旁的橘色小方框，

it's a school bus,

是一輛校車，

and we have to treat that differently as well.

我們也必需對它做出不同的回應。

When we're out on the road, other people have expectations:

當車輛在行駛的時候， 有些人會預期，

So, when a cyclist puts up their arm,

當自行車騎士舉起他們的手臂，

it means they're expecting the car to yield to them and make room for them

是預期汽車可以注意到他們 並且挪出空間

to make a lane change.

讓他們可以變換車道。

And when a police officer stood in the road,

當一位警察站在路上，

our vehicle should understand that this means stop,

測試車輛必須了解要停下來，

and when they signal to go, we should continue.

如果手勢指揮通行的話， 則要繼續走。

Now, the way we accomplish this is by sharing data between the vehicles.

經由交通工具資料共享 我們完成這個成就。

The first, most crude model of this

首先，最原始的模型

is when one vehicle sees a construction zone,

當車輛遇到施工區域，

having another know about it so it can be in the correct lane

讓其他人收到這個訊息 然後它會選擇正確的車道

to avoid some of the difficulty.

而避開施工的地方。

But we actually have a much deeper understanding of this.

但我們對這狀況有更進一步的了解。

We could take all of the data that the cars have seen over time,

取得車子所看到的歷史資料，

the hundreds of thousands of pedestrians, cyclists,

數十萬的行人，自行車，

and vehicles that have been out there

以及視線內的車輛

and understand what they look like

理解他們看起來像什麼

and use that to infer what other vehicles should look like

再用來推斷其他車輛的樣式

and other pedestrians should look like.

及其他行人的長相。

And then, even more importantly, we could take from that a model

最重要的是， 我們會依此作為模型

of how we expect them to move through the world.

以及預測他們是如何移動，

So here the yellow box is a pedestrian crossing in front of us.

黃色方框指的是 一位行人從我們面前穿越。

Here the blue box is a cyclist and we anticipate

藍色方框指的是自行車 而且我們預測

that they're going to nudge out and around the car to the right.

他們將會沿著車輛的右邊前行。 。

Here there's a cyclist coming down the road

這是另一輛自行車從對向而來

and we know they're going to continue to drive down the shape of the road.

而且我們知道他會沿著道路過來。

Here somebody makes a right turn,

另外有一個人要右轉，

and in a moment here, somebody's going to make a U-turn in front of us,

同時正前方有一個人 正準備要迴轉，

and we can anticipate that behavior and respond safely.

我們可以預測這個行為 並安全的反應。

Now, that's all well and good for things that we've seen,

這些是我們一般常見的好的狀況，

but of course, you encounter lots of things that you haven't

當然有時也會遇到一些事情

seen in the world before.

是之前從不曾遇到過。

And so just a couple of months ago,

幾個月前，

our vehicles were driving through Mountain View,

測試車輛行經山景城時，

and this is what we encountered.

我們遇到一個狀況。

This is a woman in an electric wheelchair

一位坐著電動輪椅的女人

chasing a duck in circles on the road. (Laughter)

在路上追逐著繞圈圈鴨子。 （笑聲）

Now it turns out, there is nowhere in the DMV handbook

在加州管理局中的駕駛手冊中 找不到任何說明

that tells you how to deal with that,

告訴你如何處理以上狀況，

but our vehicles were able to encounter that,

但是我們測試車輛有辦法處理它。

slow down, and drive safely.

減速，安全地行駛而過。

Now, we don't have to deal with just ducks.

我們不只是要對付鴨子。

Watch this bird fly across in front of us. The car reacts to that.

看到一隻鳥在前方飛越而過 車子也對它們做出反應。

Here we're dealing with a cyclist

這裡我們正在應付一位自行車騎士

that you would never expect to see anywhere other than Mountain View.

除了在山景城外 你從來無法預期會遇到的。

And of course, we have to deal with drivers,

當然，我們還得應付一些駕駛，

even the very small ones.

甚至是很小事也要處理。

Watch to the right as someone jumps out of this truck at us.

注意右邊有一個人 在我們面前從卡車上跳下來。

And now, watch the left as the car with the green box decides

左邊有綠色方框所代表的車輛

he needs to make a right turn at the last possible moment.

在最後一個的關頭決定右轉。

Here, as we make a lane change, the car to our left decides

當我們決定要變換車道時， 左邊的車輛

it wants to as well.

也決定要變換車道。

And here, we watch a car blow through a red light

這邊我們看到一輛車子闖紅燈

and yield to it.

就讓他先過。

And similarly, here, a cyclist blowing through that light as well.

相同的情況， 則是另一輛自行車闖紅燈。

And of course, the vehicle responds safely.

當然測試車輛可以安全地回應。

And of course, we have people who do I don't know what

有時候人們會在路上 做一些無法理解的事

sometimes on the road, like this guy pulling out between two self-driving cars.

就像這位仁兄一樣，直接把車輛停在兩輛自動駕駛車之間。

You have to ask, "What are you thinking?"

你就會很想問，「你在想些什麼？」

(Laughter)

（笑聲）

Now, I just fire-hosed you with a lot of stuff there,

我剛才描述了許多狀況給大家，

so I'm going to break one of these down pretty quickly.

我將用很快的方式 來分析其中一個狀況。

So what we're looking at is the scene with the cyclist again,

我們再回到自行車這個例子，

and you might notice in the bottom, we can't actually see the cyclist yet,

可以注意到下方這部分， 我們還無法真正的看到自行車，

but the car can: it's that little blue box up there,

但是車輛可以： 是這個藍色小方框的部分，

and that comes from the laser data.

這資訊是由雷射所得來的。

And that's not actually really easy to understand,

確實無法很容易去理解，

so what I'm going to do is I'm going to turn that laser data and look at it,

我將要做的是轉換雷射資料 然後再來看，

and if you're really good at looking at laser data, you can see

如果你對分析雷射資料很拿手， 你將可以看到

a few dots on the curve there,

在曲線上面的一些小點，

right there, and that blue box is that cyclist.

就在這上面， 上面藍色的小方框就是自行車，

Now as our light is red,

這時我們是紅燈，

the cyclist's light has turned yellow already,

自行車這邊已經轉變為黃燈，

and if you squint, you can see that in the imagery.

如果你斜眼看的話， 可以從這張圖案看到。

But the cyclist, we see, is going to proceed through the intersection.

這輛我們所看到的自行車， 將打算穿越這個路口。

Our light has now turned green, his is solidly red,

我們的燈號已經轉為綠燈， 他的則是紅燈，

and we now anticipate that this bike is going to come all the way across.

我們預測這輛自行車 將會穿越整個路口。

Unfortunately the other drivers next to us were not paying as much attention.

不巧的是旁邊的 其他司機並未注意到這點。

They started to pull forward, and fortunately for everyone,

他們開始往前移動， 不過很幸運的是，

this cyclists reacts, avoids,

自行車反應很快地避開，

and makes it through the intersection.

而且穿越了路口。

And off we go.

結束後我們才往前。

Now, as you can see, we've made some pretty exciting progress,

就如你所見的， 我們有了一些卓越的進展，

and at this point we're pretty convinced

在這個階段我們很有自信

this technology is going to come to market.

這個技術是可以上市的。

We do three million miles of testing in our simulators every single day,

在模擬系統下 我們每天做三百萬哩的測試，

so you can imagine the experience that our vehicles have.

你可以想像我們車輛的豐富經歷。

We are looking forward to having this technology on the road,

我們正設法把這技術 用於實際道路上，

and we think the right path is to go through the self-driving

我們認為正確的方向 應該是自動駕駛

rather than driver assistance approach

而不是駕駛輔助系統

because the urgency is so large.

因為有迫切的需求。

In the time I have given this talk today,

在我今天演說的同時，

34 people have died on America's roads.

有 34 個美國人死於交通事故。

How soon can we bring it out?

我們可以多快讓它上市？

Well, it's hard to say because it's a really complicated problem,

嗯，這很難說 因為這是一個很複雜的問題，

but these are my two boys.

這是我兩個兒子。

My oldest son is 11, and that means in four and a half years,

大的兒子 11 歲，表示再 4 年半，

he's going to be able to get his driver's license.

他就可以拿到駕照。

My team and I are committed to making sure that doesn't happen.

我跟我的團隊承諾 確保不會讓這件事情發生。

Thank you.

謝謝。

(Laughter) (Applause)

（笑聲）（掌聲）

Chris Anderson: Chris, I've got a question for you.

克里斯·安德森： 克里斯，我有一個問題。

Chris Urmson: Sure.

克里斯·厄姆森：好。

CA: So certainly, the mind of your cars is pretty mind-boggling.

克里斯·安德森： 的確，你車輛的智慧系統讓人驚訝。

On this debate between driver-assisted and fully driverless --

尤其在輔助駕駛與 自動駕駛的辯論中，

I mean, there's a real debate going on out there right now.

現在有一個真實的辯論就存在那邊。

So some of the companies, for example, Tesla,

有一些公司，如：特斯拉，

are going the driver-assisted route.

正在研究一些駕駛輔助系統。

What you're saying is that that's kind of going to be a dead end

根據你所說的 這個發展將會是個死胡同

because you can't just keep improving that route and get to fully driverless

因為無法藉由改善輔助系統 最後完全取代自動駕駛

at some point, and then a driver is going to say, "This feels safe,"

在某一點上，駕駛可能會說， 「這感覺到是安全的」，

and climb into the back, and something ugly will happen.

然後爬到後座去， 一些可怕的事情就可能會發生。

CU: Right. No, that's exactly right, and it's not to say

克里斯·厄姆森： 完全正確，現在還無法說

that the driver assistance systems aren't going to be incredibly valuable.

駕駛輔助系統不具有價值。

They can save a lot of lives in the interim,

在這段過渡期間 它們仍可挽救許多生命，

but to see the transformative opportunity to help someone like Steve get around,

但是看到這是一個改變的機會， 可以幫助像史蒂夫一樣的人，

to really get to the end case in safety,

而且最終是個安全的方案，

to have the opportunity to change our cities

去擁有這機會去改變我們的城市

and move parking out and get rid of these urban craters we call parking lots,

可以擺脫城市裡一個個的停車場，

it's the only way to go.

這是唯一的辦法。

CA: We will be tracking your progress with huge interest.

克里斯·安德森： 我們非常有興趣持續追蹤你的進度

Thanks so much, Chris. CU: Thank you. (Applause)

謝謝你，克里斯。 克里斯·厄姆森：謝謝。（掌聲）