ABOUT THE SPEAKER
Chris Gerdes - Mechanical engineer
An autonomous car may seem like a thing of the distant future, but mechanical engineer Chris Gerdes is racing to make it a reality today.

Why you should listen

Imagine a car that can drive itself -- that with the push of a button can get you home safely when you’re too tired to drive or have had a night of one too many drinks. Dr. Chris Gerdes , the Director of the Center for Automotive Research at Stanford (conveniently acronymed CARS), and his team are developing a robotic race car, capable of driving at outrageous speeds while avoiding every possible accident. Gerdes’ research focuses on the development of driver assistance systems for collision avoidance, as well as on new combustion processes for engines.

Prior to teaching at Stanford, Gerdes was the project leader for vehicle dynamics at the Vehicle Systems Technology Center of Daimler-Benz Research and Technology North America. His work at Daimler focused on safety analysis.

More profile about the speaker
Chris Gerdes | Speaker | TED.com
TEDxStanford

Chris Gerdes: The future race car -- 150mph, and no driver

克里斯·格迪斯: 未来的赛车 -- 每公里150英里, 并且没有司机

Filmed:
806,444 views

无人驾驶汽车正向我们走来-它们的开车技术会比你们好。克里斯·格迪斯透露了他和他的队伍怎么样研制每小时能开150英里并可以避免所有可能的交通事故的机器赛车。而且,在了解专业赛车手的脑电波时候,格迪斯说他获得了一个对专业赛车手本能的新的认识。(在斯坦福大学拍摄的)
- Mechanical engineer
An autonomous car may seem like a thing of the distant future, but mechanical engineer Chris Gerdes is racing to make it a reality today. Full bio

Double-click the English transcript below to play the video.

00:16
So, how many许多 of you have ever
0
506
1407
你们当中有多少人
00:17
gotten得到 behind背后 the wheel of a car汽车
1
1913
1655
当你不应该开车的时候
00:19
when you really shouldn't不能 have been driving主动?
2
3568
5687
还开车跟在另一部车后面?
00:25
Maybe you're out on the road for a long day,
3
9255
1905
有可能你已经开了一整天的车
00:27
and you just wanted to get home.
4
11160
1490
心里只想回家
00:28
You were tired, but you felt you could drive驾驶 a few少数 more miles英里.
5
12650
2647
你已经身心疲惫了,但你感觉还能再驾驶多几英里
00:31
Maybe you thought,
6
15297
1199
大概你有想过
00:32
I've had less to drink than everybody每个人 else其他,
7
16496
2017
我喝得没有其他人多
00:34
I should be the one to go home.
8
18513
1736
我可以驾车回家
00:36
Or maybe your mind心神 was just entirely完全 elsewhere别处.
9
20249
4591
或者也许你的大脑已经在神游
00:40
Does this sound声音 familiar to you?
10
24840
1454
这些你们听起来有点熟悉吧?
00:42
Now, in those situations情况, wouldn't不会 it be great
11
26294
2898
现在,在这些情况下
00:45
if there was a button按键 on your dashboard仪表板
12
29192
1593
如果仪表盘上有一个按钮
00:46
that you could push, and the car汽车 would get you home safely安然?
13
30785
6343
你按一下,车就可以带你安安全全地回家,会不会很棒
00:53
Now, that's been the promise诺言 of the self-driving自驾车 car汽车,
14
37128
2293
如今,这些都是自动汽车能做到的
00:55
the autonomous自主性 vehicle车辆, and it's been the dream梦想
15
39421
2627
自动汽车从 1939 年通用汽车公司在世
00:57
since以来 at least最小 1939, when General一般 Motors汽车 showcased展出
16
42048
3249
通用汽车公司在世界展销会上展示他们未来汽车的的理念
01:01
this idea理念 at their Futurama飞出个未来 booth at the World's世界 Fair公平.
17
45297
3302
就一直是一个梦想
01:04
Now, it's been one of those dreams
18
48599
1943
现在,它已成为那些看起来
01:06
that's always seemed似乎 about 20 years年份 in the future未来.
19
50542
4214
总是还要再等20年的梦想之一
01:10
Now, two weeks ago, that dream梦想 took a step forward前锋,
20
54756
2683
两个星期前,这个梦想有了突破
01:13
when the state of Nevada内华达 granted理所当然 Google's谷歌的 self-driving自驾车 car汽车
21
57439
3265
当内华达州授予谷歌的自驾汽车
01:16
the very first license执照 for an autonomous自主性 vehicle车辆,
22
60704
3600
第一个无人驾驶的上路许可证,
01:20
clearly明确地 establishing建立 that it's legal法律 for them
23
64304
2245
明确地表示他们在内华达州道路上
01:22
to test测试 it on the roads道路 in Nevada内华达.
24
66549
1810
测试是合法的
01:24
Now, California's加州 considering考虑 similar类似 legislation立法,
25
68359
3727
现在,加州的也正在考虑类似的立法,
01:27
and this would make sure that the autonomous自主性 car汽车
26
72086
2408
这将确保无人驾驶汽车
01:30
is not one of those things that has to stay in Vegas拉斯维加斯.
27
74494
2977
不会像赌博这类事一样只会发生在拉斯维加斯。
01:33
(Laughter笑声)
28
77471
2096
(笑声)
01:35
Now, in my lab实验室 at Stanford斯坦福, we've我们已经 been working加工 on
29
79567
3784
现在,在我在斯坦福大学的实验室里,我们也一直在
01:39
autonomous自主性 cars汽车 too, but with a slightly different不同 spin
30
83351
3487
研究无人驾驶汽车,但在对事物研究的理念上略有不同
01:42
on things. You see, we've我们已经 been developing发展 robotic机器人 race种族 cars汽车,
31
86838
4248
我们一直在开发机器人赛车
01:46
cars汽车 that can actually其实 push themselves他们自己 to the very limits范围
32
91086
4120
它们在性能上可以
01:51
of physical物理 performance性能.
33
95206
2240
到达其物理极限
01:53
Now, why would we want to do such这样 a thing?
34
97446
2613
那么为什么我们想要做这样的事呢?
01:55
Well, there's two really good reasons原因 for this.
35
100059
2100
嗯,有两个好的理由来解释
01:58
First, we believe that before people turn over control控制
36
102159
3959
第一,我们认为在人完全将控制交给
02:02
to an autonomous自主性 car汽车, that autonomous自主性 car汽车 should be
37
106118
2834
一部无人驾驶汽车之前,这部无人驾驶汽车
02:04
at least最小 as good as the very best最好 human人的 drivers司机.
38
108952
3254
至少得运行得像一位好的驾驶员一样
02:08
Now, if you're like me, and the other 70 percent百分 of the population人口
39
112206
3305
那么,如果你像我,还有那其他70%的人一样
02:11
who know that we are above-average高于平均水平 drivers司机,
40
115511
2193
认为我们是高于平均水平的司机
02:13
you understand理解 that's a very high bar酒吧.
41
117704
3175
你明白我们高估了自己
02:16
There's another另一个 reason原因 as well.
42
120879
2392
同时还有另一个原因
02:19
Just like race种族 car汽车 drivers司机 can use all of the friction摩擦
43
123271
3576
就像赛车手可以利用
02:22
between之间 the tire and the road,
44
126847
1280
车胎和路面间所有的摩擦
02:24
all of the car's汽车 capabilities功能 to go as fast快速 as possible可能,
45
128127
3177
还有汽车的最大性能来尽可能快的开一样
02:27
we want to use all of those capabilities功能 to avoid避免
46
131304
3345
我们想用这些性能来避免
02:30
any accident事故 we can.
47
134649
1588
任何我们可以避免的交通事故
02:32
Now, you may可能 push the car汽车 to the limits范围
48
136237
2050
现在,你可能把车开到极限
02:34
not because you're driving主动 too fast快速,
49
138287
1967
并不是说你开得太快
02:36
but because you've hit击中 an icy冷冰冰 patch补丁 of road,
50
140254
2160
而是说你开到有冰的路面上了
02:38
conditions条件 have changed.
51
142414
1704
路况变了
02:40
In those situations情况, we want a car汽车
52
144118
2761
在这些情况下,我们希望这部汽车
02:42
that is capable enough足够 to avoid避免 any accident事故
53
146879
3720
有能力避免任何那些
02:46
that can physically物理 be avoided避免.
54
150599
2678
人工可以避免的意外
02:49
I must必须 confess承认, there's kind of a third第三 motivation动机 as well.
55
153277
4267
我必须承认,还有第三个理由
02:53
You see, I have a passion for racing赛跑.
56
157544
2256
你瞧,我对赛车很痴迷
02:55
In the past过去, I've been a race种族 car汽车 owner所有者,
57
159800
2764
过去,我曾拥有一部赛车
02:58
a crew船员 chief首席 and a driving主动 coach教练,
58
162564
2555
是一个车队的头,也是驾校教练
03:01
although虽然 maybe not at the level水平 that you're currently目前 expecting期待.
59
165119
3855
虽然也许水平没有你期待得那么高
03:04
One of the things that we've我们已经 developed发达 in the lab实验室 --
60
168974
2704
我们在实验室中做的几件事中的一件--
03:07
we've我们已经 developed发达 several一些 vehicles汽车 --
61
171678
1704
就是我们开发了几部车--
03:09
is what we believe is the world's世界 first
62
173382
2235
我们相信他们是世界上
03:11
autonomously自主 drifting漂流 car汽车.
63
175617
2365
第一步无人漂移汽车
03:13
It's another另一个 one of those categories类别
64
177982
2513
它是无人车中新的分类
03:16
where maybe there's not a lot of competition竞争.
65
180495
2423
也许它还没有竞争对手
03:18
(Laughter笑声)
66
182918
1408
(笑声)
03:20
But this is P1. It's an entirely完全 student-built学生建 electric电动 vehicle车辆,
67
184326
3822
我们叫它P1。它是一部完全由学生设计的
03:24
which哪一个 through通过 using运用 its rear-wheel后轮 drive驾驶
68
188148
2078
后轮驱动电动车
03:26
and front-wheel前轮 steer-by-wire转向的线控
69
190226
1565
线控方向盘
03:27
can drift漂移 around corners角落.
70
191791
2067
可以在拐角漂移
03:29
It can get sideways侧身 like a rally团结 car汽车 driver司机,
71
193858
2200
它能像一个汽车拉力赛选手一样从路边过
03:31
always able能够 to take the tightest严格的 curve曲线,
72
196058
1715
也从能转过急弯
03:33
even on slippery, changing改变 surfaces,
73
197773
3304
即使在湿滑,不断变化的路面
03:36
never spinning纺织 out.
74
201077
1616
也从来不会打滑被甩出去
03:38
We've我们已经 also worked工作 with Volkswagen大众汽车 Oracle神谕,
75
202693
2368
我们也曾与大众 Oracle合作出研发
03:40
on Shelley雪莱, an autonomous自主性 race种族 car汽车 that has raced赛跑
76
205061
3424
一部叫” 谢莉“的无人驾驶赛车
03:44
at 150 miles英里 an hour小时 through通过 the Bonneville博纳维尔 Salt Flats公寓,
77
208485
3070
它能用每小时 150 英里的速度沿着邦纳维尔盐滩行驶
03:47
gone走了 around ThunderhillThunderhill Raceway赛道 Park公园 in the sun太阳,
78
211555
4471
能在阳关明媚时,能在大风大雨天
03:51
the wind and the rain,
79
216026
2639
跑在 Thunderhill 赛车跑道上
03:54
and navigated导航 the 153 turns and 12.4 miles英里
80
218665
5018
并在Pikes Peak Hill Climb 线路上
03:59
of the Pikes派克 Peak Hill爬坡道 Climb route路线
81
223683
1562
开12.4英里,通过153拐弯处
04:01
in Colorado科罗拉多州 with nobody没有人 at the wheel.
82
225245
3473
这是在科罗拉多州,真的一个人都没在车上
04:04
(Laughter笑声)
83
228718
1448
(笑声)
04:06
(Applause掌声)
84
230166
5566
(掌声)
04:11
I guess猜测 it goes without saying that we've我们已经 had a lot of fun开玩笑
85
235732
3279
我想我们不用说
04:14
doing this.
86
239011
1304
这样做真的有很多乐趣
04:16
But in fact事实, there's something else其他 that we've我们已经 developed发达
87
240315
3657
但事实上,我们还研发了一些其它的东西
04:19
in the process处理 of developing发展 these autonomous自主性 cars汽车.
88
243972
3055
在这个研发无人驾驶汽车的过程中
04:22
We have developed发达 a tremendous巨大 appreciation升值
89
247027
3871
我们对人类赛车手的能力
04:26
for the capabilities功能 of human人的 race种族 car汽车 drivers司机.
90
250898
3817
变的更加的的钦佩
04:30
As we've我们已经 looked看着 at the question of how well do these cars汽车 perform演出,
91
254715
4345
当我们想这些车可以运作的多好时候
04:34
we wanted to compare比较 them to our human人的 counterparts同行.
92
259060
3279
我们想把无人驾驶车和人类驾驶的操作做一个比较
04:38
And we discovered发现 their human人的 counterparts同行 are amazing惊人.
93
262339
5680
我们发现执行任务的人类是不可思议的
04:43
Now, we can take a map地图 of a race种族 track跟踪,
94
268019
4023
现在,我们可以拿一张赛车跑道图
04:47
we can take a mathematical数学的 model模型 of a car汽车,
95
272042
2370
我们可以做一个数字模型车
04:50
and with some iteration迭代, we can actually其实 find
96
274412
2903
加上一些迭代,我们可以找到
04:53
the fastest最快的 way around that track跟踪.
97
277315
1625
整个跑道的最快路径
04:54
We line线 that up with data数据 that we record记录
98
278940
2533
我们把一个职业赛车手开车数据记录下来
04:57
from a professional专业的 driver司机,
99
281473
1433
进行直线图表分析
04:58
and the resemblance相似 is absolutely绝对 remarkable卓越.
100
282906
4107
相似度是那样的惊人
05:02
Yes, there are subtle微妙 differences分歧 here,
101
287013
3212
是的,这里还是有细微的差别的
05:06
but the human人的 race种族 car汽车 driver司机 is able能够 to go out
102
290225
3127
赛车手能够在户外
05:09
and drive驾驶 an amazingly令人惊讶 fast快速 line线,
103
293352
2335
开到最快的那条线路
05:11
without the benefit效益 of an algorithm算法 that compares比较
104
295687
2330
而不用计算程序去比较
05:13
the trade-off交易 between之间 going as fast快速 as possible可能
105
298017
2608
是该在这个拐弯出开快点
05:16
in this corner, and shaving a little bit of time
106
300625
2037
还是应该在开过这个
05:18
off of the straight直行 over here.
107
302662
1902
直线的时候减点速
05:20
Not only that, they're able能够 to do it lap膝部
108
304564
3457
不但如此,他们能如此地开一圈
05:23
after lap膝部 after lap膝部.
109
308021
2375
一圈又一圈
05:26
They're able能够 to go out and consistently始终如一 do this,
110
310396
2912
他们能在户外,持续地这么做
05:29
pushing推动 the car汽车 to the limits范围 every一切 single time.
111
313308
4128
每一次都把车用到极限
05:33
It's extraordinary非凡 to watch.
112
317436
3169
看起来真的不可思议
05:36
You put them in a new car汽车,
113
320605
2066
你给他们换部车
05:38
and after a few少数 laps, they've他们已经 found发现 the fastest最快的 line线 in that car汽车,
114
322671
3902
在跑几个圈后他们就已经能找到适合车的最快的路线
05:42
and they're off to the races比赛.
115
326573
3877
接着,他们就可以比赛了
05:46
It really makes品牌 you think,
116
330450
1146
这不禁使你想
05:47
we'd星期三 love to know what's going on inside their brain.
117
331596
4871
我们真的很想知道他们大脑里究竟发生了什么
05:52
So as researchers研究人员, that's what we decided决定 to find out.
118
336467
4541
作为研究人员说,这就是我们决定要挖据的
05:56
We decided决定 to instrument仪器 not only the car汽车,
119
341008
1812
我们决定测量不仅仅是车
05:58
but also the race种族 car汽车 driver司机,
120
342820
2495
还有赛车手
06:01
to try to get a glimpse一瞥 into what was going on
121
345315
2769
尝试去了解在他们赛车时候
06:03
in their head as they were doing this.
122
348084
2186
他们大脑的变化
06:06
Now, this is Dr博士. Lene琳恩 HarbottHarbott applying应用 electrodes电极
123
350270
3950
现在,这是 琳恩·哈博特博士把电极片
06:10
to the head of John约翰 Morton莫顿.
124
354220
1232
放在约翰 · 莫顿的头上的照片
06:11
John约翰 Morton莫顿 is a former前任的 Can-Am能是 and IMSAIMSA driver司机,
125
355452
2989
约翰 · 莫顿是前Can-Am 和IMSA的赛车手
06:14
who's谁是 also a class champion冠军 at Le Mans.
126
358441
1800
他也是勒芒赛事上出类拔萃的冠军
06:16
Fantastic奇妙 driver司机, and very willing愿意 to put up with graduate毕业 students学生们
127
360241
3496
极棒的赛车手,并且愿意忍受研究生
06:19
and this sort分类 of research研究.
128
363737
1855
和这类的研究
06:21
She's putting electrodes电极 on his head
129
365592
2672
她把电极片放在他的头上
06:24
so that we can monitor监控 the electrical电动 activity活动
130
368264
2112
这样,我们可以监测当约翰绕着轨道飚车时候
06:26
in John's约翰 brain as he races比赛 around the track跟踪.
131
370376
2832
他大脑电波的活动
06:29
Now, clearly明确地 we're not going to put a couple一对 of electrodes电极 on his head
132
373208
3195
显然我们不是放一对电极片在他头上
06:32
and understand理解 exactly究竟 what all of his thoughts思念 are on the track跟踪.
133
376403
3270
就可以准确的了解到他在跑道上飚车时候所有的想法
06:35
However然而, neuroscientists神经学家 have identified确定 certain某些 patterns模式
134
379673
3407
然而,神经学家已经可以识别了一定的模式
06:38
that let us tease out some very important重要 aspects方面 of this.
135
383080
3761
让我们对这个研究中一些非常重要的因素能理出头绪
06:42
For instance, the resting休息 brain
136
386841
1847
例如,休息中的大脑
06:44
tends趋向 to generate生成 a lot of alphaα waves波浪.
137
388688
2155
往往会产生大量的α波
06:46
In contrast对比, thetaTHETA waves波浪 are associated相关 with
138
390843
3752
与此相反,θ波与大量认知活动
06:50
a lot of cognitive认知 activity活动, like visual视觉 processing处理,
139
394595
3184
相关联,如视觉处理
06:53
things where the driver司机 is thinking思维 quite相当 a bit.
140
397779
3048
赛车手正在想的事,很多
06:56
Now, we can measure测量 this,
141
400827
1663
现在,我们可以测量这一点
06:58
and we can look at the relative相对的 power功率
142
402490
1985
我们可以看到
07:00
between之间 the thetaTHETA waves波浪 and the alphaα waves波浪.
143
404475
2200
θ波与α波之间的相对动力
07:02
This gives us a measure测量 of mental心理 workload工作量,
144
406675
2442
这给我们了脑力负荷的一个测试
07:05
how much the driver司机 is actually其实 challenged挑战 cognitively认知
145
409117
3567
在轨道上任何一个地方,赛车手实际上
07:08
at any point along沿 the track跟踪.
146
412684
1786
需要接受多少认知上的挑战
07:10
Now, we wanted to see if we could actually其实 record记录 this
147
414470
2942
现在,我们想看看我们是否能真实地在跑道上
07:13
on the track跟踪, so we headed当家 down south to Laguna拉古纳 Seca塞卡.
148
417412
3038
记录这点,所以我们向南出发去卡赛道
07:16
Laguna拉古纳 Seca塞卡 is a legendary传奇的 raceway滚道
149
420450
2016
卡赛道是有传奇色彩的赛道
07:18
about halfway between之间 Salinas萨利纳斯 and Monterey蒙特雷.
150
422466
2301
大约在萨利纳斯和蒙特雷的中间
07:20
It has a curve曲线 there called the Corkscrew螺旋形的.
151
424767
2087
它有一道弯被称为瓶塞钻
07:22
Now, the Corkscrew螺旋形的 is a chicane强辩, followed其次 by a quick
152
426854
2717
现在,这个瓶塞钻是一个S 形弯道
07:25
right-handed右手 turn as the road drops滴剂 three stories故事.
153
429571
2746
接下来是一个很急的右转弯与此同时路面好像下陷3层楼那么高
07:28
Now, the strategy战略 for driving主动 this as explained解释 to me was,
154
432317
3766
现在,可以理解这个驾驶的策略为
07:31
you aim目标 for the bush衬套 in the distance距离,
155
436083
2022
你以远处的灌木丛为目标
07:34
and as the road falls下降 away, you realize实现 it was actually其实 the top最佳 of a tree.
156
438105
3025
当你感到跑道向下落的时候,你才意识到你其实是在树尖上
07:37
All right, so thanks谢谢 to the Revs转速 Program程序 at Stanford斯坦福,
157
441130
3304
很好,非常感谢斯坦福大学的自驾车研究项目
07:40
we were able能够 to take John约翰 there
158
444434
1473
我们把约翰带到哪里了
07:41
and put him behind背后 the wheel
159
445907
964
让他 主宰1960年
07:42
of a 1960 Porsche保时捷 Abarth阿巴特 Carrera卡雷拉.
160
446871
2439
保时捷的阿巴特卡雷拉的方向盘
07:45
Life is way too short for boring无聊 cars汽车.
161
449310
3698
大家对一般的车的喜好就像昙花一现一样
07:48
So, here you see John约翰 on the track跟踪,
162
453008
1759
所以,在这里你看到约翰在赛道上
07:50
he's going up the hill爬坡道 -- Oh! Somebody liked喜欢 that --
163
454767
2184
他在爬坡, 哦 !有人也喜欢来这里飚车 — —
07:52
and you can see, actually其实, his mental心理 workload工作量
164
456951
2465
实际上,你可以看到一条红的长方形条
07:55
-- measuring测量 here in the red bar酒吧 --
165
459416
2153
正在监测他的脑力负荷--
07:57
you can see his actions行动 as he approaches方法.
166
461569
2343
随着他的移动,你可以看到他的反映
07:59
Now watch, he has to downshift降档.
167
463912
3230
现在看看,他不得不换到低档。
08:03
And then he has to turn left.
168
467142
761
然后他必须左转。
08:03
Look for the tree, and down.
169
467903
3993
看清楚路旁的树,然后下坡。
08:07
Not surprisingly出奇, you can see this is a pretty漂亮 challenging具有挑战性的 task任务.
170
471896
2838
没什么可大惊小怪的,您可以看到这是一个非常有挑战性的任务
08:10
You can see his mental心理 workload工作量 spike as he goes through通过 this,
171
474734
2976
你可以看到当他经历这一切的时候,他的大脑负荷增加了
08:13
as you would expect期望 with something that requires要求
172
477710
2064
你会预测到
08:15
this level水平 of complexity复杂.
173
479774
2809
这种复杂程度会产生的事
08:18
But what's really interesting有趣 is to look at areas of the track跟踪
174
482583
3416
但是真正有趣的事是看
08:21
where his mental心理 workload工作量 doesn't increase增加.
175
485999
2846
不会使他脑力负荷增加的一些赛道的区域
08:24
I'm going to take you around now
176
488845
1495
我将带你绕到
08:26
to the other side of the track跟踪.
177
490340
1089
赛道的另外一半
08:27
Turn three. And John's约翰 going to go into that corner
178
491429
2336
数三下,约翰将开到拐角
08:29
and the rear end结束 of the car汽车 is going to begin开始 to slide滑动 out.
179
493765
2551
汽车的尾部将会滑出轨道
08:32
He's going to have to correct正确 for that with steering操舵.
180
496316
2017
他将不得不打方向盘使车回到轨道
08:34
So watch as John约翰 does this here.
181
498333
2231
所以看好约翰是怎么操作的
08:36
Watch the mental心理 workload工作量, and watch the steering操舵.
182
500564
2322
看看他的脑负荷,和方向盘
08:38
The car汽车 begins开始 to slide滑动 out, dramatic戏剧性 maneuver演习 to correct正确 it,
183
502886
3672
赛车开始滑出去了,戏剧性的操作使它回到轨道上了,
08:42
and no change更改 whatsoever任何 in the mental心理 workload工作量.
184
506558
3523
而大脑负荷却丝毫没有变化
08:45
Not a challenging具有挑战性的 task任务.
185
510081
2832
这不是一个具有挑战性的任务
08:48
In fact事实, entirely完全 reflexive反思.
186
512913
3200
实际上,完全是条件的放射
08:52
Now, our data数据 processing处理 on this is still preliminary初步,
187
516113
3643
现在,我们对此的数据处理仍是初步的阶段
08:55
but it really seems似乎 that these phenomenal非凡的 feats功勋
188
519756
2672
但这现象明显表明
08:58
that the race种族 car汽车 drivers司机 are performing执行
189
522428
1610
这些赛车手表现出来的惊人水平
08:59
are instinctive直觉的.
190
524038
1910
是其本能
09:01
They are things that they have simply只是 learned学到了 to do.
191
525948
3390
这些事对他们来说孰能生巧了
09:05
It requires要求 very little mental心理 workload工作量
192
529338
2282
对他们来说完成这样了不起的事
09:07
for them to perform演出 these amazing惊人 feats功勋.
193
531620
2824
只需要很少的大脑负荷。
09:10
And their actions行动 are fantastic奇妙.
194
534444
3135
他们表现真的很棒
09:13
This is exactly究竟 what you want to do on the steering操舵 wheel
195
537579
2611
当车遇到这种情况时候
09:16
to catch抓住 the car汽车 in this situation情况.
196
540190
3337
你想做到的就是去控制好车
09:19
Now, this has given特定 us tremendous巨大 insight眼光
197
543527
3445
现在,这给我们的无人驾驶汽车的研究
09:22
and inspiration灵感 for our own拥有 autonomous自主性 vehicles汽车.
198
546972
3122
有了巨大的启示和灵感
09:25
We've我们已经 started开始 to ask the question:
199
550094
1928
我们已经开始问自己
09:27
Can we make them a little less algorithmic算法
200
552022
2253
我们可以使我们的自驾车少一点计算程序
09:30
and a little more intuitive直观的?
201
554275
2449
而多一点直觉性的东西吗?
09:32
Can we take this reflexive反思 action行动
202
556724
2281
我们能借助
09:34
that we see from the very best最好 race种族 car汽车 drivers司机,
203
559005
2287
我们现在从最好赛车手身上看到的这种对条件反射的反应
09:37
introduce介绍 it to our cars汽车,
204
561292
1649
从而把它运用到我们的车上吗
09:38
and maybe even into a system系统 that could
205
562941
1984
再或者运用到你们
09:40
get onto your car汽车 in the future未来?
206
564925
1968
未来车子的系统里?
09:42
That would take us a long step
207
566893
1611
我们还需要很大的努力
09:44
along沿 the road to autonomous自主性 vehicles汽车
208
568504
2509
来研制出和最棒的车手一样的
09:46
that drive驾驶 as well as the best最好 humans人类.
209
571013
1912
无人驾驶汽车
09:48
But it's made制作 us think a little bit more deeply as well.
210
572925
3440
它同时使我们从更深的层面去思考
09:52
Do we want something more from our car汽车
211
576365
2968
我们想让我们的车为我们做得更多
09:55
than to simply只是 be a chauffeur司机?
212
579333
1840
而不是简简单单地一个驾驶员吗?
09:57
Do we want our car汽车 to perhaps也许 be a partner伙伴, a coach教练,
213
581173
4235
我们想让我们的车成我们的伙伴,教练
10:01
someone有人 that can use their understanding理解 of the situation情况
214
585408
3087
或者是能了解到周围环境的那个人
10:04
to help us reach达到 our potential潜在?
215
588495
4256
从而帮助我们发挥我们的潜力吗?
10:08
Can, in fact事实, the technology技术 not simply只是 replace更换 humans人类,
216
592751
2273
那么科技能不能不只是简单的取代人类
10:10
but allow允许 us to reach达到 the level水平 of reflex反射 and intuition直觉
217
595024
4575
而且可以让我们达到
10:15
that we're all capable of?
218
599599
3425
我们都能达到的直觉的反应水平?
10:18
So, as we move移动 forward前锋 into this technological技术性 future未来,
219
603024
1923
所以,当我们向这个科技时代迈进的时候
10:20
I want you to just pause暂停 and think of that for a moment时刻.
220
604947
2821
我想你停下来思考一会
10:23
What is the ideal理想 balance平衡 of human人的 and machine?
221
607768
3775
什么是人类和机器之间最理想的平衡
10:27
And as we think about that,
222
611543
1709
当我们思考时候
10:29
let's take inspiration灵感
223
613252
1731
让我们用
10:30
from the absolutely绝对 amazing惊人 capabilities功能
224
614983
3329
人类身体和大脑的
10:34
of the human人的 body身体 and the human人的 mind心神.
225
618312
2816
了不起的能力来激发自己
10:37
Thank you.
226
621128
1736
谢谢
10:38
(Applause掌声)
227
622864
4604
(掌声)
Translated by Ling Jin
Reviewed by Kelvin Wang

▲Back to top

ABOUT THE SPEAKER
Chris Gerdes - Mechanical engineer
An autonomous car may seem like a thing of the distant future, but mechanical engineer Chris Gerdes is racing to make it a reality today.

Why you should listen

Imagine a car that can drive itself -- that with the push of a button can get you home safely when you’re too tired to drive or have had a night of one too many drinks. Dr. Chris Gerdes , the Director of the Center for Automotive Research at Stanford (conveniently acronymed CARS), and his team are developing a robotic race car, capable of driving at outrageous speeds while avoiding every possible accident. Gerdes’ research focuses on the development of driver assistance systems for collision avoidance, as well as on new combustion processes for engines.

Prior to teaching at Stanford, Gerdes was the project leader for vehicle dynamics at the Vehicle Systems Technology Center of Daimler-Benz Research and Technology North America. His work at Daimler focused on safety analysis.

More profile about the speaker
Chris Gerdes | Speaker | TED.com