Jennifer Healey: If cars could talk, accidents might be avoidable

47,932 views ・ 2013-04-25

TED


请双击下面的英文字幕来播放视频。

00:00
Translator: Joseph Geni Reviewer: Morton Bast
0
0
7000
翻译人员: Catelyn Zhu 校对人员: June He
00:12
Let's face it:
1
12703
1914
让我们来面对一桩事实吧
00:14
Driving is dangerous.
2
14617
2445
开车是一件危险的事
00:17
It's one of the things that we don't like to think about,
3
17062
3098
它是我们不愿意去想的事物之一
00:20
but the fact that religious icons and good luck charms
4
20160
3652
但事实上那些神像和平安符
00:23
show up on dashboards around the world
5
23812
4790
世界各地都有人把它们摆在仪表盘的上方
00:28
betrays the fact that we know this to be true.
6
28602
4137
这就无意中透露出一个我们都心知肚明的事实
00:32
Car accidents are the leading cause of death
7
32739
3594
车祸是死亡的主因
00:36
in people ages 16 to 19 in the United States --
8
36333
4170
尤其在美国16到19岁的美国人群中
00:40
leading cause of death --
9
40503
2843
死亡的主因
00:43
and 75 percent of these accidents have nothing to do
10
43346
3863
并且百分之七十五的车祸
00:47
with drugs or alcohol.
11
47209
2285
都与毒品和酒精无关
00:49
So what happens?
12
49494
2261
那么 究竟发生了什么
00:51
No one can say for sure, but I remember my first accident.
13
51755
4219
没人能给出确切答案 但我记得我第一次出车祸
00:55
I was a young driver out on the highway,
14
55974
3803
我当时还是个开车的新手,当时正在外面高速路上开着车。
00:59
and the car in front of me, I saw the brake lights go on.
15
59777
2258
我突然看见我前面汽车的刹车灯亮了
01:02
I'm like, "Okay, all right, this guy is slowing down,
16
62035
1800
我当时想 好吧 他减速了
01:03
I'll slow down too."
17
63835
1282
那我也减速好了
01:05
I step on the brake.
18
65117
1926
我踩了刹车
01:07
But no, this guy isn't slowing down.
19
67043
2254
但是 我前面那个人并不是在减速
01:09
This guy is stopping, dead stop, dead stop on the highway.
20
69297
3178
他(竟然)停车了 突然停车—— 在高速路上突然停车
01:12
It was just going 65 -- to zero?
21
72475
2540
速度从65迈瞬降到0
01:15
I slammed on the brakes.
22
75015
1520
我猛踩刹车
01:16
I felt the ABS kick in, and the car is still going,
23
76535
3059
我当时感觉到我的车的防抱死系统启动了 但车还在行驶
01:19
and it's not going to stop, and I know it's not going to stop,
24
79594
2696
并没停下来的意思 我也知道我的车停不了了
01:22
and the air bag deploys, the car is totaled,
25
82290
2939
安全气囊也鼓了起来 车报废了
01:25
and fortunately, no one was hurt.
26
85229
3557
但幸运的是 没有人受伤
01:28
But I had no idea that car was stopping,
27
88786
4211
但我根本不知道我前面那辆车要停
01:32
and I think we can do a lot better than that.
28
92997
3645
而且我想我们可以比那做得更好
01:36
I think we can transform the driving experience
29
96642
4145
我想我们通过实现“让汽车之间对话”——
01:40
by letting our cars talk to each other.
30
100787
3879
来改变我们的驾驶体验
01:44
I just want you to think a little bit
31
104666
1424
我希望你们能思考片刻
01:46
about what the experience of driving is like now.
32
106090
2888
思考一下现在的驾驶体验是怎么样的
01:48
Get into your car. Close the door. You're in a glass bubble.
33
108978
4028
坐进车里 关上车门 你就已经置身在一个玻璃气泡中
01:53
You can't really directly sense the world around you.
34
113006
2916
你不能直接感受到你周围的世界
01:55
You're in this extended body.
35
115922
2181
因为你坐在车这样一个不小的空间里
01:58
You're tasked with navigating it down
36
118103
2163
你的任务就是导航
02:00
partially-seen roadways,
37
120266
2056
你只能看见道路的一部分
02:02
in and amongst other metal giants, at super-human speeds.
38
122322
4424
并且以超人类的速度行驶在其他的“金属巨人”间
02:06
Okay? And all you have to guide you are your two eyes.
39
126746
4480
对吧? 你只能靠双眼来导航
02:11
Okay, so that's all you have,
40
131226
1762
对 你别无他法
02:12
eyes that weren't really designed for this task,
41
132988
1735
(但其实)眼睛并非是用来干着活儿的
02:14
but then people ask you to do things like,
42
134723
3751
但是有些事情你就必须得做,比方说,
02:18
you want to make a lane change,
43
138474
1549
你想换个车道
02:20
what's the first thing they ask you do?
44
140023
2321
那你第一件要做的事是什么
02:22
Take your eyes off the road. That's right.
45
142344
3095
将眼睛从车道上移开 对
02:25
Stop looking where you're going, turn,
46
145439
2096
将目光从你前进的方向移开 转弯
02:27
check your blind spot,
47
147535
2018
检查一下盲点
02:29
and drive down the road without looking where you're going.
48
149553
3471
然后就一直开 根本不注意自己在往哪里开
02:33
You and everyone else. This is the safe way to drive.
49
153024
3135
所有人都这么做 这是安全的驾驶方式
02:36
Why do we do this? Because we have to,
50
156159
2241
我们为什么这么做? 因为我们别无选择
02:38
we have to make a choice, do I look here or do I look here?
51
158400
2579
我们必须作出一个抉择 是朝这儿看 还是朝那儿看
02:40
What's more important?
52
160979
1521
更重要的一点是什么呢
02:42
And usually we do a fantastic job
53
162500
2711
我们通常都做得很好
02:45
picking and choosing what we attend to on the road.
54
165211
3769
能够很好的选择我们要往哪个方向开
02:48
But occasionally we miss something.
55
168980
3650
但是偶然 我们也会忘记一些事情
02:52
Occasionally we sense something wrong or too late.
56
172630
4461
有时 当我们发觉有些东西出了问题的时候 已经为时过晚。
02:57
In countless accidents, the driver says,
57
177091
1988
在无数的车祸中 司机都会说
02:59
"I didn't see it coming."
58
179079
2308
“我没想到会这样。”
03:01
And I believe that. I believe that.
59
181387
3281
我相信他们的话 我相信
03:04
We can only watch so much.
60
184668
2925
我们看到的只有这么多而已
03:07
But the technology exists now that can help us improve that.
61
187593
5144
但是现存的科技可以帮我们改善这一点
03:12
In the future, with cars exchanging data with each other,
62
192737
4296
在未来 车与车之间可以交换数据
03:17
we will be able to see not just three cars ahead
63
197033
3928
我们就不仅只能看见前面的三台车了
03:20
and three cars behind, to the right and left,
64
200961
1594
还能看见后面的三台车,左边的,以及右边车。
03:22
all at the same time, bird's eye view,
65
202555
3166
同时看见 鸟瞰视野
03:25
we will actually be able to see into those cars.
66
205721
3128
我们可以看见这些车的内部
03:28
We will be able to see the velocity of the car in front of us,
67
208849
2371
我们可以看到我们前面那辆车的速度
03:31
to see how fast that guy's going or stopping.
68
211220
3240
看看前面那位什么时候会启动或停下
03:34
If that guy's going down to zero, I'll know.
69
214460
4510
假如那人的速度突然降到零,我就能知道了。
03:38
And with computation and algorithms and predictive models,
70
218970
3859
利用运算 代数以及预测模型
03:42
we will be able to see the future.
71
222829
3273
我们能看见未来
03:46
You may think that's impossible.
72
226102
1556
你可能会觉得这是不可能的
03:47
How can you predict the future? That's really hard.
73
227658
2731
你怎么能预测未来呢 太难了
03:50
Actually, no. With cars, it's not impossible.
74
230389
3619
事实上 不难 对于汽车来说 这并非不可能
03:54
Cars are three-dimensional objects
75
234008
2732
汽车是三维物体
03:56
that have a fixed position and velocity.
76
236740
2332
位置速度都是固定的
03:59
They travel down roads.
77
239072
1631
行使在路上的时候
04:00
Often they travel on pre-published routes.
78
240703
2412
它们通常都是按照预先规划好的道路行驶
04:03
It's really not that hard to make reasonable predictions
79
243115
3938
未来 想要预测汽车将要驶向什么方向
04:07
about where a car's going to be in the near future.
80
247053
2864
对之作出合理的预测并不困难
04:09
Even if, when you're in your car
81
249917
2002
即使你在自己的车里
04:11
and some motorcyclist comes -- bshoom! --
82
251919
1994
突然出现了一个开着摩托的人 砰!
04:13
85 miles an hour down, lane-splitting --
83
253913
2296
时速85英里,跟你抢车道
04:16
I know you've had this experience --
84
256209
2547
我知道你们曾经有过这样的经历
04:18
that guy didn't "just come out of nowhere."
85
258756
2603
那个开摩托的并非凭空出现
04:21
That guy's been on the road probably for the last half hour.
86
261359
3643
他可能之前的半小时就一直在路上开着吧
04:25
(Laughter)
87
265002
1190
(笑声)
04:26
Right? I mean, somebody's seen him.
88
266192
3589
对吧?我的意思是,有人看见过他
04:29
Ten, 20, 30 miles back, someone's seen that guy,
89
269781
2768
在10,20,30英里前,有人看见过他,
04:32
and as soon as one car sees that guy
90
272549
2384
只要一辆车看见那个人
04:34
and puts him on the map, he's on the map --
91
274933
2231
将他的信息置入地图中,他的位置就会显示在地图上了
04:37
position, velocity,
92
277164
2176
位置,速度
04:39
good estimate he'll continue going 85 miles an hour.
93
279340
2321
预测他将保持85英里的时速
04:41
You'll know, because your car will know, because
94
281661
2184
那你就知道了,因为你的车就会知道了,因为
04:43
that other car will have whispered something in his ear,
95
283845
2275
其他的车已经悄悄把这件事告诉它了
04:46
like, "By the way, five minutes,
96
286120
1923
打个比方,“告诉你一声,五分钟之后
04:48
motorcyclist, watch out."
97
288043
2775
会出现个开摩托的,注意。”
04:50
You can make reasonable predictions about how cars behave.
98
290818
2703
你可以对汽车的运动作出合理的预测。
04:53
I mean, they're Newtonian objects.
99
293521
1365
它们可是遵从牛顿力学的物体
04:54
That's very nice about them.
100
294886
2909
这是它们的优点
04:57
So how do we get there?
101
297795
3034
那么我们怎么样才能做到这一点呢
05:00
We can start with something as simple
102
300829
2266
我们可以从简单的开始
05:03
as sharing our position data between cars,
103
303095
2870
比如在车辆间共享位置数据
05:05
just sharing GPS.
104
305965
1892
只需要共享GPS
05:07
If I have a GPS and a camera in my car,
105
307857
2444
假如我的车内装有GPS和摄像头
05:10
I have a pretty precise idea of where I am
106
310301
2231
我就能清楚地知道自己的位置
05:12
and how fast I'm going.
107
312532
1732
自己的速度
05:14
With computer vision, I can estimate where
108
314264
1657
那么利用电脑视野,我就可以预测
05:15
the cars around me are, sort of, and where they're going.
109
315921
3537
我周围的车大概在哪里,他们在向哪个方向前进
05:19
And same with the other cars.
110
319458
970
其他的车也是一样
05:20
They can have a precise idea of where they are,
111
320428
1814
他们也能知道自己的准确位置
05:22
and sort of a vague idea of where the other cars are.
112
322242
2146
并且大致知道其他车的位置
05:24
What happens if two cars share that data,
113
324388
3231
假如两车共享数据的话会发生什么呢?
05:27
if they talk to each other?
114
327619
1955
假如他们实现彼此对话又会发生什么呢?
05:29
I can tell you exactly what happens.
115
329574
2778
我可以很明确的告诉你答案
05:32
Both models improve.
116
332352
2339
这两种模型都会进步
05:34
Everybody wins.
117
334691
2055
共赢
05:36
Professor Bob Wang and his team
118
336746
2577
王鲍勃教授和他的团队
05:39
have done computer simulations of what happens
119
339323
2738
做了个电脑模拟系统
05:42
when fuzzy estimates combine, even in light traffic,
120
342061
3431
来研究 当我们结合不同的模糊预测的时候会发生什么 即使只是在交通情况通畅、
05:45
when cars just share GPS data,
121
345492
2624
汽车仅仅共享GPS数据时
05:48
and we've moved this research out of the computer simulation
122
348116
2513
之后 我们让这项研究不仅限于电脑模拟
05:50
and into robot test beds that have the actual sensors
123
350629
3027
我们还用机器人测试床 它们用到的传感器
05:53
that are in cars now on these robots:
124
353656
3133
正是当下汽车里真正在用到的传感器 在这些机器人上有
05:56
stereo cameras, GPS,
125
356789
1838
立体相机 GPS
05:58
and the two-dimensional laser range finders
126
358627
1874
二位激光测距仪
06:00
that are common in backup systems.
127
360501
2240
这些(也)都是备用系统中非常常见的
06:02
We also attach a discrete short-range communication radio,
128
362741
4484
我们再安装一个离散短距离无线电
06:07
and the robots talk to each other.
129
367225
1909
实现机器人间的通话
06:09
When these robots come at each other,
130
369134
1539
当这些机器人遇见彼此时
06:10
they track each other's position precisely,
131
370673
2971
它们能够准确地追踪彼此的位置
06:13
and they can avoid each other.
132
373644
2737
并可躲避彼此
06:16
We're now adding more and more robots into the mix,
133
376381
3226
我们现在正在向这样的混合系统中 添加更多的机器人
06:19
and we encountered some problems.
134
379607
1471
我们也遇到了一些问题
06:21
One of the problems, when you get too much chatter,
135
381078
2359
问题之一就是 当(汽车间的)“悄悄话”太泛滥
06:23
it's hard to process all the packets, so you have to prioritize,
136
383437
3728
就很难处理所有的信息 所以你必须抓重点
06:27
and that's where the predictive model helps you.
137
387165
2357
在这样的情况下预测模型就可以派上用场了
06:29
If your robot cars are all tracking the predicted trajectories,
138
389522
4372
假如你的机器人机器正在追踪所有已预测的轨迹
06:33
you don't pay as much attention to those packets.
139
393894
1767
那么你就不用花费太多的精力去关注那些了
06:35
You prioritize the one guy
140
395661
1703
你可以将重心放在某台
06:37
who seems to be going a little off course.
141
397364
1333
看上去有些偏离航向的车上
06:38
That guy could be a problem.
142
398697
2526
那台车可能是一个隐患
06:41
And you can predict the new trajectory.
143
401223
3002
那你就可以预测新的路线
06:44
So you don't only know that he's going off course, you know how.
144
404225
2763
这样你不仅知道了它正在偏离航向 你还知道了它是怎样偏离的
06:46
And you know which drivers you need to alert to get out of the way.
145
406988
3725
而且你还能知道你该提醒哪些司机注意躲避
06:50
And we wanted to do -- how can we best alert everyone?
146
410713
2633
我们一直也想这么做 可是怎样提醒他人才好呢
06:53
How can these cars whisper, "You need to get out of the way?"
147
413346
3183
车怎么可能悄悄给彼此送信 说“你得躲一躲”
06:56
Well, it depends on two things:
148
416529
1517
这个取决于两件事
06:58
one, the ability of the car,
149
418046
2169
第一 汽车的能力
07:00
and second the ability of the driver.
150
420215
3217
第二 司机的能力
07:03
If one guy has a really great car,
151
423432
1505
假如一个人的车超棒
07:04
but they're on their phone or, you know, doing something,
152
424937
2925
但他在打电话或者,你懂得,开开小差
07:07
they're not probably in the best position
153
427862
1930
那他可能状态不佳
07:09
to react in an emergency.
154
429792
2970
在面对紧急情况的时候措手不及
07:12
So we started a separate line of research
155
432762
1665
所以我们开展了一条独立的研究线路
07:14
doing driver state modeling.
156
434427
2551
司机状态模型
07:16
And now, using a series of three cameras,
157
436978
2329
我们利用一系列三个摄像头
07:19
we can detect if a driver is looking forward,
158
439307
2270
我们可以监测这个司机是在向前看
07:21
looking away, looking down, on the phone,
159
441577
2860
向边上看 向下看 打电话
07:24
or having a cup of coffee.
160
444437
3061
还是喝咖啡
07:27
We can predict the accident
161
447498
2070
我们能预测车祸
07:29
and we can predict who, which cars,
162
449568
3651
我们可以预测哪些司机 哪些车
07:33
are in the best position to move out of the way
163
453219
3486
能够最快的离开将要出现事故的路线
07:36
to calculate the safest route for everyone.
164
456705
3009
为每个人算出最安全的线路
07:39
Fundamentally, these technologies exist today.
165
459714
4635
最根本的一点 这些技术现在已经成为了现实
07:44
I think the biggest problem that we face
166
464349
2824
我认为我们面临的最大的问题
07:47
is our own willingness to share our data.
167
467173
3013
就是我们自己是否愿意分享自己的数据
07:50
I think it's a very disconcerting notion,
168
470186
2631
我认为这是一个非常令人不安的想法
07:52
this idea that our cars will be watching us,
169
472817
2386
设想我们自己的车将要监视着我们
07:55
talking about us to other cars,
170
475203
3371
跟其他的车分享我们的一举一动
07:58
that we'll be going down the road in a sea of gossip.
171
478574
3427
那样我们就像开车穿过 对我们指指点点的人群
08:02
But I believe it can be done in a way that protects our privacy,
172
482001
3897
但我想这件事可以在保护我们隐私的情况下成功
08:05
just like right now, when I look at your car from the outside,
173
485898
3741
就像现在一样 当我在外面看向你的车的时候
08:09
I don't really know about you.
174
489639
2363
我并不能真正的了解你
08:12
If I look at your license plate number,
175
492002
1137
当我看你的车牌号码时
08:13
I don't really know who you are.
176
493139
1886
我并不能知道你是谁
08:15
I believe our cars can talk about us behind our backs.
177
495025
4249
我觉得我们的车完全能在我们的背后谈论我们
08:19
(Laughter)
178
499274
2975
(笑声)
08:22
And I think it's going to be a great thing.
179
502249
3185
而且 我认为这是一件非常好的事
08:25
I want you to consider for a moment
180
505434
1650
我希望你们能思考片刻
08:27
if you really don't want the distracted teenager behind you
181
507084
4118
假如你真心不想让 开在你后面的心不在焉的年轻人
08:31
to know that you're braking,
182
511202
2120
知道你要停车
08:33
that you're coming to a dead stop.
183
513322
2924
你要突然刹车的话
08:36
By sharing our data willingly,
184
516246
2741
通过自愿分享我们的数据
08:38
we can do what's best for everyone.
185
518987
2812
我们可以实现人人共赢
08:41
So let your car gossip about you.
186
521799
3076
所以让你的车“八卦”你吧
08:44
It's going to make the roads a lot safer.
187
524875
3038
这会让我们的道路更安全
08:47
Thank you.
188
527913
1791
谢谢大家
08:49
(Applause)
189
529704
4985
(鼓掌)
关于本网站

这个网站将向你介绍对学习英语有用的YouTube视频。你将看到来自世界各地的一流教师教授的英语课程。双击每个视频页面上显示的英文字幕,即可从那里播放视频。字幕会随着视频的播放而同步滚动。如果你有任何意见或要求,请使用此联系表与我们联系。

https://forms.gle/WvT1wiN1qDtmnspy7