Chris Urmson: How a driverless car sees the road

862,221 views ・ 2015-06-26

TED


Please double-click on the English subtitles below to play the video.

Prevodilac: Aleksandar Korom Lektor: Ivana Korom
00:12
So in 1885, Karl Benz invented the automobile.
0
12528
3949
Godine 1885. Karl Benc izumeo je automobil.
00:16
Later that year, he took it out for the first public test drive,
1
16707
3762
Kasnije, u toku godine, izveo ga je na prvu javnu test vožnju
00:20
and -- true story -- crashed into a wall.
2
20469
3375
i, ovo se zaista dogodilo, udario ga u zid.
00:24
For the last 130 years,
3
24184
2043
U poslednjih 130 godina
00:26
we've been working around that least reliable part of the car, the driver.
4
26227
4319
radili smo na tom, najmanje pouzdanom, delu automobila - vozaču.
00:30
We've made the car stronger.
5
30546
1354
Ojačali smo sam automobil.
00:32
We've added seat belts, we've added air bags,
6
32200
2548
Dodali smo pojaseve za sedišta, vazdušne jastuke,
00:34
and in the last decade, we've actually started trying to make the car smarter
7
34748
3971
i, u poslednjoj deceniji, počeli smo čak i da činimo auto pametnijim
00:38
to fix that bug, the driver.
8
38719
2938
kako bismo ispravili tu grešku - vozača.
00:41
Now, today I'm going to talk to you a little bit about the difference
9
41657
3261
Danas ću govoriti malo o razlici
00:44
between patching around the problem with driver assistance systems
10
44918
3808
između rešavanja problema sistema asistencije vozaču
00:48
and actually having fully self-driving cars
11
48726
2564
i zapravo, potpuno samoupravljajućih automobila
00:51
and what they can do for the world.
12
51290
1880
i šta oni mogu da učine za svet.
00:53
I'm also going to talk to you a little bit about our car
13
53170
2995
Takođe ću govoriti ponešto i o našem automobilu
00:56
and allow you to see how it sees the world and how it reacts and what it does,
14
56165
3999
i prikazati vam kako on vidi svet, kako reaguje i šta radi,
01:00
but first I'm going to talk a little bit about the problem.
15
60164
3187
ali prvo moram da kažem nešto i o jednom problemu.
01:03
And it's a big problem:
16
63651
1648
A problem je velik:
01:05
1.2 million people are killed on the world's roads every year.
17
65299
3089
svake godine, na putevima širom sveta, 1,2 miliona ljudi pogine.
01:08
In America alone, 33,000 people are killed each year.
18
68388
3784
Samo u Americi svake godine pogine 33 000 ljudi.
01:12
To put that in perspective,
19
72172
2028
Stavimo to u ovakvu perspektivu:
01:14
that's the same as a 737 falling out of the sky every working day.
20
74200
4797
to je kao da se svakog radnog dana 737 sruši iz vazduha.
01:19
It's kind of unbelievable.
21
79342
1786
To je neverovatno.
01:21
Cars are sold to us like this,
22
81548
2298
Automobili nam se prodaju na ovakav način
01:23
but really, this is what driving's like.
23
83846
2717
ali, zapravo, ovo predstavlja vožnju, zar ne?
01:26
Right? It's not sunny, it's rainy,
24
86563
2159
Nema sunca nego kiše
01:28
and you want to do anything other than drive.
25
88722
2488
i radije biste radili bilo šta drugo, osim vožnje.
01:31
And the reason why is this:
26
91210
1622
A razlog tome je sledeći:
01:32
Traffic is getting worse.
27
92832
1858
saobraćaj postaje sve gori.
01:34
In America, between 1990 and 2010,
28
94690
3506
U Americi, u periodu između 1990. i 2010,
01:38
the vehicle miles traveled increased by 38 percent.
29
98196
3504
milje koje su vozila prelazila
se uvećao za 38%.
01:42
We grew by six percent of roads,
30
102213
2749
Procenat naših puteva se uvećao za 6%.
01:44
so it's not in your brains.
31
104962
1602
To nije samo u našim glavama,
01:46
Traffic really is substantially worse than it was not very long ago.
32
106564
4276
saobraćaj se zaista znatno pogoršao u skorije vreme.
01:50
And all of this has a very human cost.
33
110840
2409
I sve to ima veliku cenu po čoveka.
01:53
So if you take the average commute time in America, which is about 50 minutes,
34
113529
3948
Ako uzmete prosečno vreme transporta, u Americi, koje iznosi oko 50 minuta
01:57
you multiply that by the 120 million workers we have,
35
117477
3649
i pomnožite ga sa 120 miliona radnika koje imamo,
02:01
that turns out to be about six billion minutes
36
121126
2225
dobijete negde oko šest milijardi minuta
02:03
wasted in commuting every day.
37
123351
2026
protraćenih tokom transporta svakog dana.
02:05
Now, that's a big number, so let's put it in perspective.
38
125377
2827
To je velika cifra pa sagledajmo to na sledeći način:
02:08
You take that six billion minutes
39
128204
1774
uzmite tih šest milijardi minuta
02:09
and you divide it by the average life expectancy of a person,
40
129978
3784
i podelite ih sa prosečnim životnim vekom jedne osobe
02:13
that turns out to be 162 lifetimes
41
133762
3135
i dobićete 162 života
02:16
spent every day, wasted,
42
136897
2925
uzaludno utrošenih svakog dana,
02:19
just getting from A to B.
43
139822
2044
prelazeći samo od tačke A do B.
02:21
It's unbelievable.
44
141866
1730
To je neverovatno.
02:23
And then, there are those of us who don't have the privilege
45
143596
2844
Zatim, imamo i one koji nemaju tu privilegiju
02:26
of sitting in traffic.
46
146440
1672
da sede u saobraćaju.
02:28
So this is Steve.
47
148112
1578
Ovo je Stiv.
02:29
He's an incredibly capable guy,
48
149690
1765
On je neverovatno sposoban muškarac
02:31
but he just happens to be blind,
49
151455
2516
ali je, pri tom, i slep.
02:33
and that means instead of a 30-minute drive to work in the morning,
50
153971
3217
A to znači da umesto tridesetominutne jutarnje vožnje do posla,
02:37
it's a two-hour ordeal of piecing together bits of public transit
51
157188
3979
to je iskušenje od dva sata spajajući delove javnog prevoza
02:41
or asking friends and family for a ride.
52
161167
2385
ili moljakanje prijatelja i porodice za prevoz.
02:43
He doesn't have that same freedom that you and I have to get around.
53
163552
3669
On nema tu istu slobodu kretanja koju vi i ja imamo.
02:47
We should do something about that.
54
167221
2460
Trebalo bi da uradimo nešto po tom pitanju.
02:49
Now, conventional wisdom would say
55
169891
1757
Konvencionalno razmišljanje bi bilo
02:51
that we'll just take these driver assistance systems
56
171648
2492
da uzmemo te sisteme asistencije vozača,
02:54
and we'll kind of push them and incrementally improve them,
57
174140
3750
da ih guramo, postepeno unapređujemo i da će se oni vremenom
02:57
and over time, they'll turn into self-driving cars.
58
177890
2542
pretvoriti u samoupravljajuće automobile.
03:00
Well, I'm here to tell you that's like me saying
59
180432
2409
Međutim, to je kao kada bih vam ja sada rekao da
03:02
that if I work really hard at jumping, one day I'll be able to fly.
60
182841
4057
ako bih se mnogo trudio da skačem, da bih jednog dana mogao i da poletim.
03:06
We actually need to do something a little different.
61
186898
2728
Morali bismo ipak da uradimo nešto drugačije.
03:09
And so I'm going to talk to you about three different ways
62
189626
2711
Zato ću vam pričati o tri glavne razlike
03:12
that self-driving systems are different than driver assistance systems.
63
192337
3346
između samoupravljajućih automobila i sistema asistencije vozaču.
03:15
And I'm going to start with some of our own experience.
64
195683
2651
I počeću sa nekim od naših iskustava.
03:18
So back in 2013,
65
198334
2253
Godine 2013.
03:20
we had the first test of a self-driving car
66
200587
2663
imali smo prvi test samoupravljajućih automobila
03:23
where we let regular people use it.
67
203250
2027
i dozvolili običnim ljudima da ga koriste.
03:25
Well, almost regular -- they were 100 Googlers,
68
205277
2202
Dobro, delimično običnim - to je bilo 100 Guglovih radnika
03:27
but they weren't working on the project.
69
207479
2003
međutim, oni nisu radili na projektu.
03:29
And we gave them the car and we allowed them to use it in their daily lives.
70
209482
3621
Dali smo im taj automobil i dozvolili im da ga koriste u svakodnevnom životu.
03:33
But unlike a real self-driving car, this one had a big asterisk with it:
71
213103
3719
U odnosu na druge samoupravljajuće automobile
ovaj je imao jednu veliku začkoljicu:
03:36
They had to pay attention,
72
216822
1504
morali su da vode računa
03:38
because this was an experimental vehicle.
73
218326
2633
jer je ovo bilo eksperimentalno vozilo.
03:40
We tested it a lot, but it could still fail.
74
220959
3525
Mi smo ga dosta testirali, ali je i dalje moglo da se pokvari.
03:44
And so we gave them two hours of training,
75
224484
2059
Dva sata smo ih obučavali,
03:46
we put them in the car, we let them use it,
76
226543
2092
stavili smo ih u auto, dali im da ga koriste,
03:48
and what we heard back was something awesome,
77
228635
2127
i šta smo naknadno čuli je bilo fenomenalno
03:50
as someone trying to bring a product into the world.
78
230762
2524
za nekoga ko pokušava da uvede proizvod u svet.
03:53
Every one of them told us they loved it.
79
233286
1925
Svi ponaosob su rekli da im se svideo.
03:55
In fact, we had a Porsche driver who came in and told us on the first day,
80
235211
3566
Zapravo, imali smo jednog vozača Poršea koji nam je prvog dana rekao:
03:58
"This is completely stupid. What are we thinking?"
81
238777
2663
"Ovo je potpuno glupo. O čemu uopšte razmišljamo?"
04:01
But at the end of it, he said, "Not only should I have it,
82
241850
2840
Ali je, na kraju, rekao: "Ne samo da je meni potreban,
04:04
everyone else should have it, because people are terrible drivers."
83
244690
3175
potreban je svima, jer su ljudi očajni vozači."
04:09
So this was music to our ears,
84
249135
1735
To je bila muzika za naše uši.
04:10
but then we started to look at what the people inside the car were doing,
85
250870
3803
A onda smo počeli da gledamo šta ljudi unutar automobila rade
04:14
and this was eye-opening.
86
254673
1579
i to nam je otvorilo oči.
04:16
Now, my favorite story is this gentleman
87
256252
2438
A meni je omiljena priča jednog gospodina
04:18
who looks down at his phone and realizes the battery is low,
88
258690
3829
koji gleda u svoj telefon i shvati da mu se baterija istrošila.
04:22
so he turns around like this in the car and digs around in his backpack,
89
262519
4548
On se ovako okrenuo, u autu, čeprkao po svom rancu,
04:27
pulls out his laptop,
90
267067
2153
izvukao svoj laptop,
04:29
puts it on the seat,
91
269220
1567
stavio ga na sedište,
04:30
goes in the back again,
92
270787
1764
opet se okrenuo nazad,
04:32
digs around, pulls out the charging cable for his phone,
93
272551
3367
opet čeprkao i izvukao kabl za punjenje za svoj telefon,
04:35
futzes around, puts it into the laptop, puts it on the phone.
94
275918
3367
vrpoljio se, uključio kabl u laptop i u telefon.
04:39
Sure enough, the phone is charging.
95
279285
2043
Zasigurno, telefon se puni
04:41
All the time he's been doing 65 miles per hour down the freeway.
96
281328
3994
a svo to vreme on se vozio brzinom od 100 km na sat, po autoputu.
04:45
Right? Unbelievable.
97
285322
2484
Zaista neverovatno.
04:47
So we thought about this and we said, it's kind of obvious, right?
98
287806
3121
Razmišljali smo o ovome i rekli smo da je to nekako očigledno.
04:50
The better the technology gets,
99
290927
2263
Što više tehnologija napreduje
04:53
the less reliable the driver is going to get.
100
293190
2121
vozač postaje sve manje pouzdan.
04:55
So by just making the cars incrementally smarter,
101
295311
2396
Samim tim što automobil postepeno postaje pametan
04:57
we're probably not going to see the wins we really need.
102
297707
2902
verovatno više nećemo videti pobede koje smo nekada želeli.
05:00
Let me talk about something a little technical for a moment here.
103
300609
3901
Dozvolite mi da vam se obratim tehničkim jezikom, na trenutak.
05:04
So we're looking at this graph, and along the bottom
104
304510
2438
Gledajući ovaj grafik, na dnu primećujemo
05:06
is how often does the car apply the brakes when it shouldn't.
105
306948
3051
koliko često automobil primenjuje kočnice kada ne bi trebalo.
05:09
You can ignore most of that axis,
106
309999
1621
Ignorišite veći deo ove ose
05:11
because if you're driving around town, and the car starts stopping randomly,
107
311620
3719
jer ako se vozite gradom i automobil iz nekog razloga stane,
05:15
you're never going to buy that car.
108
315339
1701
vi nikada nećete kupiti taj auto.
05:17
And the vertical axis is how often the car is going to apply the brakes
109
317040
3375
Vertikalna osa prikazuje koliko često će auto primeniti kočnice,
05:20
when it's supposed to to help you avoid an accident.
110
320415
3049
kada je to potrebno, da bi vam pomogao da izbegnete nesreću.
05:23
Now, if we look at the bottom left corner here,
111
323464
2221
Ako sada pogledamo u ovaj donji levi ugao
05:25
this is your classic car.
112
325685
1845
- to je vaš klasičan automobil.
05:27
It doesn't apply the brakes for you, it doesn't do anything goofy,
113
327530
3133
On ne primenjuje kočnice umesto vas, ne radi ništa šašavo
05:30
but it also doesn't get you out of an accident.
114
330663
2779
ali isto tako vas i ne čuva od nesreće.
05:33
Now, if we want to bring a driver assistance system into a car,
115
333442
3018
Ako sada želimo u auto da uvedemo sistem asistencije vozaču
05:36
say with collision mitigation braking,
116
336460
1828
recimo za kočenje za ublažavanje sudara
05:38
we're going to put some package of technology on there,
117
338288
2612
ubacićemo neki paket tehnologije tu
05:40
and that's this curve, and it's going to have some operating properties,
118
340900
3418
i to je ova kriva ovde i sistem će imati neka upravljačka svojstva
05:44
but it's never going to avoid all of the accidents,
119
344318
2490
ali nikada neće izbeći sve nesreće
05:46
because it doesn't have that capability.
120
346808
2059
jer nema takve sposobnosti.
05:48
But we'll pick some place along the curve here,
121
348867
2249
Ali izabraćemo neku poziciju na krivi ovde
05:51
and maybe it avoids half of accidents that the human driver misses,
122
351116
3254
pa možda izbegava polovinu nesreća koja ljudima vozačima promakne
05:54
and that's amazing, right?
123
354370
1297
neverovatno, zar ne?
05:55
We just reduced accidents on our roads by a factor of two.
124
355667
2727
Upravo smo duplo smanjili nesreće na našim putevima.
05:58
There are now 17,000 less people dying every year in America.
125
358394
3987
Sada 17 000 ljudi manje pogine u Americi svake godine.
06:02
But if we want a self-driving car,
126
362381
2020
Ali ako želimo samoupravljajući automobil,
06:04
we need a technology curve that looks like this.
127
364401
2307
potrebna nam je kriva koja izgleda ovako.
06:06
We're going to have to put more sensors in the vehicle,
128
366708
2599
Morali bismo da postavimo više senzora u vozilo
06:09
and we'll pick some operating point up here
129
369307
2021
i izabraćemo jednu tačku korišćenja ovde
06:11
where it basically never gets into a crash.
130
371328
2019
gde, zapravo, nikada ne dolazi do sudara.
06:13
They'll happen, but very low frequency.
131
373347
2443
Dešavaće se, ali sa vrlo malom učestalošću.
06:15
Now you and I could look at this and we could argue
132
375790
2461
Mogli bismo ovo da gledamo i da polemišemo o tome
06:18
about whether it's incremental, and I could say something like "80-20 rule,"
133
378251
3605
da li je ovo postepeno i ja bih rekao da je to "pravilo 80-20"
06:21
and it's really hard to move up to that new curve.
134
381856
2568
i da je veoma teško da se podigne na tu novu krivu.
06:24
But let's look at it from a different direction for a moment.
135
384424
2934
Ali hajde na trenutak da to sagledamo iz drugačijeg ugla.
06:27
So let's look at how often the technology has to do the right thing.
136
387358
3512
Hajde da vidimo koliko često tehnologija postupi na ispravan način.
06:30
And so this green dot up here is a driver assistance system.
137
390870
3506
Ova zelena tačka ovde predstavlja sistem asistencije vozaču.
06:34
It turns out that human drivers
138
394376
2485
Ispostavilo se da ljudi vozači
06:36
make mistakes that lead to traffic accidents
139
396861
2647
prave greške koje dovode do saobraćajnih nesreća
06:39
about once every 100,000 miles in America.
140
399508
3172
jednom u 161 000 km, u Americi.
06:42
In contrast, a self-driving system is probably making decisions
141
402680
3167
Nasuprot tome, sistem asistencije vozaču verovatno donosi odluke
06:45
about 10 times per second,
142
405847
3663
oko 10 puta u sekundi,
06:49
so order of magnitude,
143
409510
1422
a to je red veličine
06:50
that's about 1,000 times per mile.
144
410932
2832
oko 1000 puta u toku 1,5 kilometra.
06:53
So if you compare the distance between these two,
145
413764
2485
Ako uporedite razdaljinu između ove dve veličine,
06:56
it's about 10 to the eighth, right?
146
416249
2600
to je oko 10 na osmu, zar ne?
06:58
Eight orders of magnitude.
147
418849
1765
Osam puta više.
07:00
That's like comparing how fast I run
148
420614
2809
To je kao kada bi poredili koliko brzo ja trčim
07:03
to the speed of light.
149
423423
2206
u odnosu na brzinu svetlosti.
07:05
It doesn't matter how hard I train, I'm never actually going to get there.
150
425629
3785
Nije bitno koliko naporno treniram kada zapravo, nikada neću moći to da stignem.
07:09
So there's a pretty big gap there.
151
429414
2438
Prema tome, to je vrlo velik procep.
07:11
And then finally, there's how the system can handle uncertainty.
152
431852
3729
I na kraju, naravno, imamo i to kako sistem podnosi nesigurnosti.
07:15
So this pedestrian here might be stepping into the road, might not be.
153
435581
3323
Ovaj pešak ovde možda iskorači na put, a možda i ne.
07:18
I can't tell, nor can any of our algorithms,
154
438904
3395
Ja ne mogu to da znam, niti bilo koji naš algoritam
07:22
but in the case of a driver assistance system,
155
442310
2284
ali u slučaju sistema asistencije vozaču
07:24
that means it can't take action, because again,
156
444594
2806
to znači da ne može nešto da preduzme opet iz razloga što
07:27
if it presses the brakes unexpectedly, that's completely unacceptable.
157
447400
3339
ako nenadano pritisne kočnice to je potpuno neprihvatljivo.
07:30
Whereas a self-driving system can look at that pedestrian and say,
158
450739
3133
Dok samoupravljajući sistem može da prepozna pešaka i kaže
07:33
I don't know what they're about to do,
159
453872
1890
"Ne znam šta će da uradi,
07:35
slow down, take a better look, and then react appropriately after that.
160
455762
3762
uspori, pogledaj bolje i nakon toga reaguj adekvatno."
07:39
So it can be much safer than a driver assistance system can ever be.
161
459524
3702
Tako da je mnogo bezbedniji nego što će sistem asistencije vozaču ikad biti.
07:43
So that's enough about the differences between the two.
162
463226
2730
Toliko o razlikama između ova dva sistema.
07:45
Let's spend some time talking about how the car sees the world.
163
465956
3484
Hajde da sada razgovaramo o tome kako automobil vidi svet.
07:49
So this is our vehicle.
164
469440
1252
Dakle, ovo je naše vozilo.
07:50
It starts by understanding where it is in the world,
165
470692
2438
Kreće tako što prepoznaje gde se nalazi, na svetu,
07:53
by taking a map and its sensor data and aligning the two,
166
473130
2787
tako što koristi podatke sa mape i senzora i upoređuje ih
07:55
and then we layer on top of that what it sees in the moment.
167
475917
2948
i na to dodaje šta vidi u konkretnom trenutku.
07:58
So here, all the purple boxes you can see are other vehicles on the road,
168
478865
3655
Tako da ove ljubičaste kutije koje vidite predstavljaju druga vozila na putu.
08:02
and the red thing on the side over there is a cyclist,
169
482520
2528
Ove crvene stvari, sa strane, su biciklisti,
08:05
and up in the distance, if you look really closely,
170
485048
2402
a tamo u daljini, ako bolje pogledate,
08:07
you can see some cones.
171
487450
1794
možete videti čunjeve.
08:09
Then we know where the car is in the moment,
172
489244
2773
Sad, pošto znamo gde se auto nalazi u datom trenutku
08:12
but we have to do better than that: we have to predict what's going to happen.
173
492017
3833
moramo da uradimo i bolje od toga: moramo da predvidimo šta će se desiti.
08:15
So here the pickup truck in top right is about to make a left lane change
174
495850
3488
Ovaj pikap kamion, gore desno, će da izvrši prestrojavanje u levu traku
08:19
because the road in front of it is closed,
175
499338
2223
zato što je napred put zatvoren
08:21
so it needs to get out of the way.
176
501561
1731
pa on mora da se skloni sa puta.
08:23
Knowing that one pickup truck is great,
177
503292
1863
Poznajemo taj jedan pikap i to je super
08:25
but we really need to know what everybody's thinking,
178
505155
2479
ali moramo da znamo i o čemu svi ostali misle
08:27
so it becomes quite a complicated problem.
179
507634
2507
pa to sad postaje vrlo komplikovan problem.
08:30
And then given that, we can figure out how the car should respond in the moment,
180
510141
4749
Ako sad to znamo, možemo da smislimo kako bi auto trebalo da reaguje u trenutku
08:34
so what trajectory it should follow, how quickly it should slow down or speed up.
181
514890
3866
koju putanju bi trebalo da sledi, koliko brzo bi trebalo da uspori ili ubrza.
08:38
And then that all turns into just following a path:
182
518756
3065
I sve to postaje samo praćenje putanje:
08:41
turning the steering wheel left or right, pressing the brake or gas.
183
521821
3197
skretanje levo ili desno, pritiskanje kočnice ili gasa.
08:45
It's really just two numbers at the end of the day.
184
525018
2464
Na kraju se sve svodi na dva broja, zapravo.
08:47
So how hard can it really be?
185
527482
2241
Koliko teško to može da bude?
08:50
Back when we started in 2009,
186
530433
1952
Kada smo počinjali u 2009,
08:52
this is what our system looked like.
187
532385
1798
ovako je izgledao naš sistem.
08:54
So you can see our car in the middle and the other boxes on the road,
188
534183
3391
Možete videti naš automobil u sredini i ostale kocke na putu
08:57
driving down the highway.
189
537574
1271
kako se voze po autoputu.
08:58
The car needs to understand where it is and roughly where the other vehicles are.
190
538845
3818
Auto mora da prepozna gde se nalazi i gde se otprilike nalaze i ostala vozila.
09:02
It's really a geometric understanding of the world.
191
542663
2429
To je zapravo geometrijsko razumevanje sveta.
09:05
Once we started driving on neighborhood and city streets,
192
545092
2948
Kada smo počeli da vozimo po komšiluku i gradskim ulicama,
09:08
the problem becomes a whole new level of difficulty.
193
548040
2445
pojavile su se poteškoće na potpuno novom nivou.
09:10
You see pedestrians crossing in front of us, cars crossing in front of us,
194
550485
3494
Vidimo pešake koji prelaze ispred nas, automobile koji prelaze ispred nas
09:13
going every which way,
195
553979
1811
koji idu u svim smerovima,
09:15
the traffic lights, crosswalks.
196
555790
1527
semafori, pešački prelazi.
09:17
It's an incredibly complicated problem by comparison.
197
557317
2797
To je neverovatno složen problem u odnosu na prethodni.
09:20
And then once you have that problem solved,
198
560114
2103
Jednom kada je taj problem rešen,
09:22
the vehicle has to be able to deal with construction.
199
562217
2512
vozilo mora da se nosi sa radovima na putu.
09:24
So here are the cones on the left forcing it to drive to the right,
200
564729
3151
Ovde su čunjevi sa leve strane koji ga primoravaju da ide na desnu
09:27
but not just construction in isolation, of course.
201
567880
2402
ali ne samo sa radovima, naravno.
09:30
It has to deal with other people moving through that construction zone as well.
202
570282
3723
Mora da se nosi sa ostalim ljudima koji se kreću oko tih radova, takođe.
09:34
And of course, if anyone's breaking the rules, the police are there
203
574005
3263
I, naravno, ako neko krši pravila, policija je tu
09:37
and the car has to understand that that flashing light on the top of the car
204
577268
3622
i auto mora da prepozna rotaciono svetlo na krovu auta
09:40
means that it's not just a car, it's actually a police officer.
205
580890
3105
koje znači da to nije običan auto, nego policijac.
09:43
Similarly, the orange box on the side here,
206
583995
2032
Slično, ova narandžasta kutija sa strane
09:46
it's a school bus,
207
586027
1109
je školski autobus
09:47
and we have to treat that differently as well.
208
587136
2520
i time moramo, takođe, drugačije da se pozabavimo.
09:50
When we're out on the road, other people have expectations:
209
590576
2793
Kada se nalazimo na putu, drugi ljudi imaju očekivanja.
09:53
So, when a cyclist puts up their arm,
210
593369
1780
Tako da kada biciklista ispruži ruku
09:55
it means they're expecting the car to yield to them and make room for them
211
595149
3518
to znači da očekuje od auta da mu da prednost i napravi mesta za njega
09:58
to make a lane change.
212
598667
2053
da bi se prestrojio.
10:01
And when a police officer stood in the road,
213
601030
2173
I kada se policijski auto nalazi na putu
10:03
our vehicle should understand that this means stop,
214
603203
2740
naše vozilo mora da prepozna da to znači da stanemo,
10:05
and when they signal to go, we should continue.
215
605943
3506
i kada nam signaliziraiju da krenemo da mi nastavimo dalje.
10:09
Now, the way we accomplish this is by sharing data between the vehicles.
216
609449
3761
Način na koji ovo postižemo jeste deljenjem podataka između vozila.
10:13
The first, most crude model of this
217
613210
1696
Prvi, grub model ovoga
10:14
is when one vehicle sees a construction zone,
218
614906
2113
je kada vozilo vidi radove,
10:17
having another know about it so it can be in the correct lane
219
617019
3062
i daje drugom to do znanja da bi moglo da bude u pravilnoj traci
10:20
to avoid some of the difficulty.
220
620081
1570
kako bi izbeglo poteškoće.
10:21
But we actually have a much deeper understanding of this.
221
621651
2664
Ovo zapravo mnogo dublje razumemo.
10:24
We could take all of the data that the cars have seen over time,
222
624315
3009
Mogli bismo da uzmemo sve podatke koje auto prima u toku vremena
10:27
the hundreds of thousands of pedestrians, cyclists,
223
627324
2376
stotine hiljada pešaka, motociklista,
10:29
and vehicles that have been out there
224
629700
1787
i vozila koje se tamo nalaze
10:31
and understand what they look like
225
631487
1695
i da prepoznamo kako izgledaju
10:33
and use that to infer what other vehicles should look like
226
633182
2831
i to upotrebimo da zaključimo kako bi druga vozila
10:36
and other pedestrians should look like.
227
636013
1926
i drugi pešaci mogli da izgledaju.
10:37
And then, even more importantly, we could take from that a model
228
637939
3021
I onda, još važnije, iz toga bismo mogli da izvučemo model
10:40
of how we expect them to move through the world.
229
640960
2330
kako očekujemo da se oni ponašaju u svetu.
10:43
So here the yellow box is a pedestrian crossing in front of us.
230
643290
2963
Ovde žuta kocka predstavlja pešaka koji prelazi ispred nas.
10:46
Here the blue box is a cyclist and we anticipate
231
646253
2250
Ovde je plava kocka biciklista i predviđamo
10:48
that they're going to nudge out and around the car to the right.
232
648503
3312
da će da se pomeri iza automobila desno.
10:52
Here there's a cyclist coming down the road
233
652115
2092
Ovde nam biciklista ide u susret
10:54
and we know they're going to continue to drive down the shape of the road.
234
654207
3486
i znamo da će nastaviti da vozi po obliku puta.
10:57
Here somebody makes a right turn,
235
657693
1867
Ovde neko skreće desno,
10:59
and in a moment here, somebody's going to make a U-turn in front of us,
236
659560
3360
i ubrzo vidimo ovde nekog ko će da napravi polukružno ispred nas
11:02
and we can anticipate that behavior and respond safely.
237
662920
2614
pa možemo da predvidimo to i da reagujemo bezbedno.
11:05
Now, that's all well and good for things that we've seen,
238
665534
2728
Sad, sve je to dobro za ove stvari koje smo videli.
11:08
but of course, you encounter lots of things that you haven't
239
668262
2865
Ali, naravno, dešavaće se gomila stvari
koje pre toga niste videli.
11:11
seen in the world before.
240
671127
1231
11:12
And so just a couple of months ago,
241
672358
1741
Pre nekoliko meseci,
11:14
our vehicles were driving through Mountain View,
242
674099
2235
naša vozila su se kretala kroz Mauntin Vju
11:16
and this is what we encountered.
243
676334
1644
i evo sa čim smo se susreli.
11:17
This is a woman in an electric wheelchair
244
677978
2082
Ovo je žena u električnim kolicima
11:20
chasing a duck in circles on the road. (Laughter)
245
680060
2617
koja juri patku u krug, po putu. (Smeh)
11:22
Now it turns out, there is nowhere in the DMV handbook
246
682677
3111
Međutim, nigde u uputstvu o ponašanju u saobraćaju
11:25
that tells you how to deal with that,
247
685788
2245
ne piše kako to da rešite.
11:28
but our vehicles were able to encounter that,
248
688033
2143
Ali naša vozila su mogla to da prepoznaju,
11:30
slow down, and drive safely.
249
690176
2255
uspore i nastave bezbedno.
11:32
Now, we don't have to deal with just ducks.
250
692431
2041
Nećemo se nositi samo sa patkama.
11:34
Watch this bird fly across in front of us. The car reacts to that.
251
694472
3708
Vidite kako ova ptica izleće ispred nas.
Auto reaguje na to.
11:38
Here we're dealing with a cyclist
252
698180
1615
Ovde se suočavamo sa biciklistom
11:39
that you would never expect to see anywhere other than Mountain View.
253
699795
3290
kojeg ne biste očekivali da vidite nigde drugde osim u Mauntin Vjuu.
11:43
And of course, we have to deal with drivers,
254
703085
2068
I, naravno, moramo da se suočavamo
11:45
even the very small ones.
255
705153
3715
čak i sa veoma malim vozačima.
11:48
Watch to the right as someone jumps out of this truck at us.
256
708868
4131
Pogledajte desno ovde kako neko iskače iz ovog kamiona ispred nas.
11:54
And now, watch the left as the car with the green box decides
257
714460
2929
I ovde sa leve strane, auto sa zelenom kutijom koji je odlučio
11:57
he needs to make a right turn at the last possible moment.
258
717389
3325
da mora da skrene desno u poslednjem mogućem trenutku.
12:00
Here, as we make a lane change, the car to our left decides
259
720714
2851
Ovde, dok se prestrojavamo, auto sa naše leve strane
12:03
it wants to as well.
260
723565
3553
želi isto to.
12:07
And here, we watch a car blow through a red light
261
727118
2693
A ovde vidimo auto koji jurca kroz crveno svetlo
12:09
and yield to it.
262
729811
2090
i propuštamo ga.
12:11
And similarly, here, a cyclist blowing through that light as well.
263
731901
3854
Slično tome, ovde biciklista isto jurca kroz crveno svetlo.
12:15
And of course, the vehicle responds safely.
264
735755
2746
I, naravno, vozilo reaguje bezbedno.
12:18
And of course, we have people who do I don't know what
265
738501
2601
Takođe imamo ljude koji rade ne-znam-ni-ja-šta na putu
12:21
sometimes on the road, like this guy pulling out between two self-driving cars.
266
741102
3823
kao ovaj koji se zaustavlja između dva samoupravljajuće automobila.
12:24
You have to ask, "What are you thinking?"
267
744925
2045
Zapitate se: "O čemu ti razmišljaš?"
12:26
(Laughter)
268
746970
1212
(Smeh)
12:28
Now, I just fire-hosed you with a lot of stuff there,
269
748182
2521
Obasuo sam vas sa dosta stvari
12:30
so I'm going to break one of these down pretty quickly.
270
750703
2650
i sada ću samo na brzinu analizirati jednu od njih.
12:33
So what we're looking at is the scene with the cyclist again,
271
753353
2940
Sada gledamo situaciju, opet sa biciklistom,
12:36
and you might notice in the bottom, we can't actually see the cyclist yet,
272
756293
3491
i na dnu možete da primetite da još uvek ne možemo da ga vidimo
12:39
but the car can: it's that little blue box up there,
273
759784
2504
ali auto može: to je ona mala plava kocka tamo,
12:42
and that comes from the laser data.
274
762288
2081
i to je podatak koji se očitao laserski.
12:44
And that's not actually really easy to understand,
275
764369
2418
To nije baš tako lako da se razume
12:46
so what I'm going to do is I'm going to turn that laser data and look at it,
276
766787
3584
pa ću ih sada uključiti da vidimo te laserske podatke
pa ako ste veoma dobri u gledanju laserskih podataka,
12:50
and if you're really good at looking at laser data, you can see
277
770371
3029
možete uočiti ove tačke na bankini
12:53
a few dots on the curve there,
278
773400
1487
12:54
right there, and that blue box is that cyclist.
279
774887
2372
ovde, a ona plava kocka je taj biciklista.
Pošto je nama sada crveno svetlo,
12:57
Now as our light is red,
280
777259
1149
12:58
the cyclist's light has turned yellow already,
281
778408
2192
biciklisti se već upalilo žuto,
13:00
and if you squint, you can see that in the imagery.
282
780600
2438
i ako škiljite, možete da vidite to ovde na slici.
13:03
But the cyclist, we see, is going to proceed through the intersection.
283
783038
3286
Ali biciklista, kako vidimo, će nastaviti pravo na raskrsnici.
13:06
Our light has now turned green, his is solidly red,
284
786324
2394
Nama je sada zeleno svetlo, njegovo je crveno,
13:08
and we now anticipate that this bike is going to come all the way across.
285
788718
4292
i mi sada predviđamo da će taj bajs da pređe preko.
13:13
Unfortunately the other drivers next to us were not paying as much attention.
286
793010
3742
Nažalost, ostali vozači pored nas nisu obratili dovoljno pažnje.
13:16
They started to pull forward, and fortunately for everyone,
287
796752
3157
Počeli su da se pomeraju unapred i na svu sreću,
13:19
this cyclists reacts, avoids,
288
799909
3011
biciklista je reagovao, izbegao,
13:22
and makes it through the intersection.
289
802920
2191
i prošao kroz raskrsnicu.
13:25
And off we go.
290
805111
1568
I krećemo.
13:26
Now, as you can see, we've made some pretty exciting progress,
291
806679
2948
Kao što vidite, napravili smo prilično uzbudljiv napredak
13:29
and at this point we're pretty convinced
292
809627
1902
i u ovom trenutku smo prilično ubeđeni
13:31
this technology is going to come to market.
293
811529
2010
da će se ova tehnologija naći na tržištu.
13:33
We do three million miles of testing in our simulators every single day,
294
813539
4783
U našim simulatorima testiramo skoro 5 miliona kilometara svakog dana
13:38
so you can imagine the experience that our vehicles have.
295
818322
2689
pa možete zamisliti kakvo iskustvo naša vozila imaju.
13:41
We are looking forward to having this technology on the road,
296
821011
2864
Radujemo se što će ova tehnologija biti na putu,
13:43
and we think the right path is to go through the self-driving
297
823875
2890
i mislimo da su samoupravljajući automobili pravi put
13:46
rather than driver assistance approach
298
826765
1844
u odnosu na sistem asistencije vozaču
13:48
because the urgency is so large.
299
828609
2621
zato što je pravovremenost veoma značajna.
13:51
In the time I have given this talk today,
300
831230
2393
U toku ovog mog današnjeg govora
13:53
34 people have died on America's roads.
301
833623
3135
34 ljudi je poginulo na američkim putevima.
13:56
How soon can we bring it out?
302
836758
2368
Koliko brzo možemo izneti ovu tehnologiju?
13:59
Well, it's hard to say because it's a really complicated problem,
303
839126
3832
Teško je to reći jer je to zaista komplikovan problem.
14:02
but these are my two boys.
304
842958
2214
Ovo su moja dva dečaka.
14:05
My oldest son is 11, and that means in four and a half years,
305
845172
3623
Stariji ima 11 godina a to znači da će za četiri ipo godine
14:08
he's going to be able to get his driver's license.
306
848795
2577
moći da dobije vozačku dozvolu.
14:11
My team and I are committed to making sure that doesn't happen.
307
851372
3204
Moj tim i ja smo posvećeni tome da se to ne desi.
14:14
Thank you.
308
854576
1904
Hvala vam.
14:16
(Laughter) (Applause)
309
856480
3667
(Smeh) (Aplauz)
14:21
Chris Anderson: Chris, I've got a question for you.
310
861110
2568
Kris Anderson: Kris, imam pitanje za tebe.
14:23
Chris Urmson: Sure.
311
863678
2809
Kris Urmson: Svakako.
14:26
CA: So certainly, the mind of your cars is pretty mind-boggling.
312
866487
3924
KA: Zasigurno, svest vaših automobila je prilično zapanjujuća.
14:30
On this debate between driver-assisted and fully driverless --
313
870411
4459
Na debatu između asistencije vozaču i potpuno bezvozača -
14:34
I mean, there's a real debate going on out there right now.
314
874870
3041
Mislim, dešava se prava debata o tome sada.
14:37
So some of the companies, for example, Tesla,
315
877911
2833
Pa neke kompanije, kao što je, na primer, Tesla
14:40
are going the driver-assisted route.
316
880744
2159
idu putem asistencije vozaču.
14:42
What you're saying is that that's kind of going to be a dead end
317
882903
5248
Ti govoriš da će to biti ćorsokak
14:48
because you can't just keep improving that route and get to fully driverless
318
888151
5456
jer ne može samo unapređivanjem te putanje
da se dođe do potpunog samoupravljanja
14:53
at some point, and then a driver is going to say, "This feels safe,"
319
893607
3530
u jednom trenutku i da onda vozač kaže: "Osećam da je ovo sigurno"
14:57
and climb into the back, and something ugly will happen.
320
897137
2647
i onda se prebaci nazad i nešto ružno se desi.
14:59
CU: Right. No, that's exactly right, and it's not to say
321
899784
2676
KU: Tako je. To je potpuno tačno i ne možemo da kažemo
15:02
that the driver assistance systems aren't going to be incredibly valuable.
322
902460
3537
da sistemi asistencije vozaču neće biti neverovatno značajni.
15:05
They can save a lot of lives in the interim,
323
905997
2058
Mogu da spasu mnogo života u međuvremenu,
15:08
but to see the transformative opportunity to help someone like Steve get around,
324
908055
3833
ali da imaju priliku da se transformišu i pomognu ljudima kao što je Stiv
15:11
to really get to the end case in safety,
325
911888
1969
da zaista dođu do kraja bezbedno,
15:13
to have the opportunity to change our cities
326
913857
2479
da imaju mogućnost da promene naše gradove
15:16
and move parking out and get rid of these urban craters we call parking lots,
327
916336
4204
i da se otarase urbanih kratera koje zovemo parking mestima,
15:20
it's the only way to go.
328
920540
1240
ovo je jedini put.
15:21
CA: We will be tracking your progress with huge interest.
329
921780
2718
KA: Pratićemo vaš napredak sa velikim interesovanjem.
15:24
Thanks so much, Chris. CU: Thank you. (Applause)
330
924498
4232
Hvala puno, Kris. KU: Hvala vama. (Aplauz)
About this website

This site will introduce you to YouTube videos that are useful for learning English. You will see English lessons taught by top-notch teachers from around the world. Double-click on the English subtitles displayed on each video page to play the video from there. The subtitles scroll in sync with the video playback. If you have any comments or requests, please contact us using this contact form.

https://forms.gle/WvT1wiN1qDtmnspy7