I loved cars.

孩提時

When I turned 18,

我就愛車

I lost my best friend to a car accident.

在我滿18歲時

Like this.

我最要好的朋友死於車禍

And then I decided I'd dedicate my life

就這樣

to saving one million people

我便決定要將我的人生

every year.

致力於挽救每年

Now I haven't succeeded, so this is just a progress report,

一百萬人的生命損失

but I'm here to tell you a little bit about self-driving cars.

我還沒成功, 所以這次只是個進度報告

I saw the concept first

今天我要介紹自動駕駛車輛

in the DARPA Grand Challenges

構想是來自於

where the U.S. government issued a prize

DARPA 的大挑戰

to build a self-driving car that could navigate a desert.

U.S. 政府提供一個獎項

And even though a hundred teams were there,

給能於沙漠中完成自動駕駛的團隊

these cars went nowhere.

即使有一百多隊參加

So we decided at Stanford to build a different self-driving car.

但這些車都沒能完成

We built the hardware and the software.

因此Standford 決定建構一個不同的自動駕駛車輛

We made it learn from us,

我們同時構造硬體與軟體

and we set it free in the desert.

我們使它能向人類學習

And the unimaginable happened:

我們把它放到沙漠中

it became the first car

想不到的事發生了:

to ever return from a DARPA Grand Challenge,

它竟成為第一部

winning Stanford 2 million dollars.

能完成 DARPA 大挑戰的車 --

Yet I still hadn't saved a single life.

為 Standford 贏得兩百萬美元

Since, our work has focused

但我還沒救到任何一條命

on building driving cars

一開始, 我們的設計就是

that can drive anywhere by themselves --

要建構一部車

any street in California.

能在任何路況作無人駕駛

We've driven 140,000 miles.

在加州的任何街道上

Our cars have sensors

我們已開了 14萬英哩

by which they magically can see

我們的車有許多感應器

everything around them

也就讓車子能看到

and make decisions

環繞車子四周的任何事物

about every aspect of driving.

作所有駕駛會遇到的

It's the perfect driving mechanism.

即時判斷

We've driven in cities,

堪稱是完美的駕駛機制

like in San Francisco here.

我們開過市區

We've driven from San Francisco to Los Angeles on Highway 1.

像這裡是舊金山

We've encountered joggers,

也開上從舊金山到洛杉磯的 1 號高速公路

busy highways, toll booths,

我們遇到過慢跑者

and this is without a person in the loop;

繁忙的高速公路，收費站

the car just drives itself.

這些都是無人控制的

In fact, while we drove 140,000 miles,

車子自動駕駛

people didn't even notice.

事實上呢, 這些14 萬英哩的測試

Mountain roads,

也多是無人察覺

day and night,

山路

and even crooked Lombard Street

日與夜

in San Francisco.

甚至是舊金山彎彎曲曲的

(Laughter)

Lombard 街

Sometimes our cars get so crazy,

(笑聲)

they even do little stunts.

有時 我們的車會玩瘋了

(Video) Man: Oh, my God.

也會做些電影特技駕駛

What?

(影片中對白) 甲: 哦! 天啊!

Second Man: It's driving itself.

什麼?

Sebastian Thrun: Now I can't get my friend Harold back to life,

乙: 是車子自己在開

but I can do something for all the people who died.

ST: 現在我雖不能救回我朋友 Harold 的命

Do you know that driving accidents

但我能為死於車禍的人盡些心力

are the number one cause of death for young people?

你們知道嗎: 車禍事故

And do you realize that almost all of those

是年輕人喪命的頭號殺手?

are due to human error

還有，你們知道嗎？

and not machine error,

那幾乎都是由於人為疏失

and can therefore be prevented by machines?

不是機器過失

Do you realize

所以由機器來替代人將有可能避免這些事故?

that we could change the capacity of highways

你們知道嗎:

by a factor of two or three

我們將能把高速公路的車輛容量

if we didn't rely on human precision

提高將近二到三倍

on staying in the lane --

將車輛開在車道内

improve body position

如果不依賴人為的控制的話

and therefore drive a little bit closer together

也就是說藉著自動駕駛能精準控制位置

on a little bit narrower lanes,

大家能開得靠近一些

and do away with all traffic jams on highways?

車道寬度縮減後

Do you realize that you, TED users,

就能改善高速公路的塞車

spend an average

TED 來賓, 你們知道嗎？

of 52 minutes per day

大家每天平均花費

in traffic,

52 分鐘

wasting your time

在交通中

on your daily commute?

你的時間

You could regain this time.

浪費在每天的通勤中

This is four billion hours

你可以再取回這些時間

wasted in this country alone.

對國家而言 這些是總共

And it's 2.4 billion gallons of gasoline wasted.

每年 40 億小時的浪費

Now I think there's a vision here, a new technology,

也是 24億加崙的汽油被浪費

and I'm really looking forward to a time

在這裡 我認為可以有個願景 有種新科技

when generations after us look back at us

我真的期待會有一天

and say how ridiculous it was that humans were driving cars.

當我們的後代 再回顧現在的時代

Thank you.

會說人們竟然需要開車 真是太好笑了

(Applause)

謝謝