Chris Urmson: How a driverless car sees the road

863,108 views ・ 2015-06-26

TED


Dvaput kliknite na engleske titlove ispod za reprodukciju videozapisa.

Prevoditelj: Stjepan Mateljan Recezent: Ivan Stamenković
00:12
So in 1885, Karl Benz invented the automobile.
0
12528
3949
Dakle 1885, Karl Benz izumio je automobil.
00:16
Later that year, he took it out for the first public test drive,
1
16707
3762
Kasnije te godine, izveo ga je na prvu javnu probnu vožnju,
00:20
and -- true story -- crashed into a wall.
2
20469
3375
i -- istinita priča -- zabio se u zid.
00:24
For the last 130 years,
3
24184
2043
Kroz zadnjih 130 godina,
00:26
we've been working around that least reliable part of the car, the driver.
4
26227
4319
radili smo oko najmanje pouzdanog dijela auta, vozača.
00:30
We've made the car stronger.
5
30546
1354
Napravili smo aute jačim.
00:32
We've added seat belts, we've added air bags,
6
32200
2548
Dodali smo sigurnosne pojase, dodali smo zračne jastuke,
00:34
and in the last decade, we've actually started trying to make the car smarter
7
34748
3971
a u zadnjem desetljeću, zapravo smo počeli činiti aute pametnijima
00:38
to fix that bug, the driver.
8
38719
2938
da popravimo taj bug, vozača.
00:41
Now, today I'm going to talk to you a little bit about the difference
9
41657
3261
Sad, danas ću vam pričati nešto malo o razlici
00:44
between patching around the problem with driver assistance systems
10
44918
3808
između krpanja oko problema sa sustavima pomoći vozaču
00:48
and actually having fully self-driving cars
11
48726
2564
i imanja pravih posve samovozećih automobila.
00:51
and what they can do for the world.
12
51290
1880
te što oni mogu učiniti za svijet.
00:53
I'm also going to talk to you a little bit about our car
13
53170
2995
Također ću vam pričati malo i o našem autu
00:56
and allow you to see how it sees the world and how it reacts and what it does,
14
56165
3999
i dozvoliti vam da vidite kako on vidi svijet te kako reagira i što čini,
01:00
but first I'm going to talk a little bit about the problem.
15
60164
3187
ali prvo ću malo pričati o problemu.
01:03
And it's a big problem:
16
63651
1648
A to je veliki problem:
01:05
1.2 million people are killed on the world's roads every year.
17
65299
3089
1,2 milijuna ljudi je ubijeno na svjetskim cestama svake godine.
01:08
In America alone, 33,000 people are killed each year.
18
68388
3784
Samo u Americi, 33.000 ljudi je ubijeno svake godine.
01:12
To put that in perspective,
19
72172
2028
Da to stavimo u perspektivu,
01:14
that's the same as a 737 falling out of the sky every working day.
20
74200
4797
to je jednako kao da 737 padne s neba svaki radni dan.
01:19
It's kind of unbelievable.
21
79342
1786
Na neki je način nevjerojatno.
01:21
Cars are sold to us like this,
22
81548
2298
Aute nam prodaju ovako,
01:23
but really, this is what driving's like.
23
83846
2717
ali zapravo, ovo je kako izgleda vožnja.
01:26
Right? It's not sunny, it's rainy,
24
86563
2159
Je li tako? Nije sunčano, pada kiša,
01:28
and you want to do anything other than drive.
25
88722
2488
i želite raditi bilo što drugo, samo ne voziti.
01:31
And the reason why is this:
26
91210
1622
A razlog zašto je ovaj:
01:32
Traffic is getting worse.
27
92832
1858
Promet postaje gori.
01:34
In America, between 1990 and 2010,
28
94690
3506
U Americi, od 1990 do 2010,
01:38
the vehicle miles traveled increased by 38 percent.
29
98196
3504
milje proputovane vozilima su porasle 38 posto.
01:42
We grew by six percent of roads,
30
102213
2749
Porasli smo za šest posto u cestama,
01:44
so it's not in your brains.
31
104962
1602
tako da vam to nije u glavama.
01:46
Traffic really is substantially worse than it was not very long ago.
32
106564
4276
Promet je zbilja bitno gori nego što je bio ne tako davno.
01:50
And all of this has a very human cost.
33
110840
2409
A sve to ima vrlo ljudsku cijenu.
01:53
So if you take the average commute time in America, which is about 50 minutes,
34
113529
3948
Pa ako uzmete prosječno vrijeme dnevne vožnje koje je pedesetak minuta,
01:57
you multiply that by the 120 million workers we have,
35
117477
3649
pomnožite to sa 120 milijuna radnika koliko ih imamo,
02:01
that turns out to be about six billion minutes
36
121126
2225
ispadne da je to otprilike šest milijardi minuta
02:03
wasted in commuting every day.
37
123351
2026
potrošenih u prometu svaki dan.
02:05
Now, that's a big number, so let's put it in perspective.
38
125377
2827
Sad, to je velik broj, pa ajmo ga staviti u perspektivu.
02:08
You take that six billion minutes
39
128204
1774
Uzmete tih šest milijardi minuta
02:09
and you divide it by the average life expectancy of a person,
40
129978
3784
i podijelite ih sa prosječnim očekivanim životnim vijekom osobe,
02:13
that turns out to be 162 lifetimes
41
133762
3135
ispadne 162 životna vijeka
02:16
spent every day, wasted,
42
136897
2925
potrošenih svaki dan, bačenih
02:19
just getting from A to B.
43
139822
2044
samo na prelazak od A do B.
02:21
It's unbelievable.
44
141866
1730
Nevjerojatno.
02:23
And then, there are those of us who don't have the privilege
45
143596
2844
A potom, ima ih među nama koji nemaju povlasticu
02:26
of sitting in traffic.
46
146440
1672
sudjelovanja u prometu.
02:28
So this is Steve.
47
148112
1578
Dakle ovo je Steve.
02:29
He's an incredibly capable guy,
48
149690
1765
On je nevjerojatno sposoban tip,
02:31
but he just happens to be blind,
49
151455
2516
samo što je slijep,
02:33
and that means instead of a 30-minute drive to work in the morning,
50
153971
3217
a to znači kako umjesto 30 minutne vožnje do posla ujutro,
02:37
it's a two-hour ordeal of piecing together bits of public transit
51
157188
3979
to je dvosatno iskušenje sastavljanja djelića javnog prijevoza
02:41
or asking friends and family for a ride.
52
161167
2385
ili molba prijateljima i obitelji za prijevoz.
02:43
He doesn't have that same freedom that you and I have to get around.
53
163552
3669
On nema istu slobodu kao vi i ja glede kretanja uokolo.
02:47
We should do something about that.
54
167221
2460
Trebali bismo učiniti nešto u vezi toga.
02:49
Now, conventional wisdom would say
55
169891
1757
Sad, uobičajena bi mudrost rekla
02:51
that we'll just take these driver assistance systems
56
171648
2492
neka samo uzmemo te sustave pomoći vozaču
02:54
and we'll kind of push them and incrementally improve them,
57
174140
3750
pa ćemo ih onda gurati i postepeno usavršavati
02:57
and over time, they'll turn into self-driving cars.
58
177890
2542
te će se tijekom vremena premetnuti u samovozeće aute.
03:00
Well, I'm here to tell you that's like me saying
59
180432
2409
Dobro, ovdje sam kako bih vam rekao da je to nalik izjavi
03:02
that if I work really hard at jumping, one day I'll be able to fly.
60
182841
4057
kako ću ako jako uporno radim na skakanju, jednoga dana moći letjeti.
03:06
We actually need to do something a little different.
61
186898
2728
Zapravo trebamo napraviti nešto malo drugačije.
03:09
And so I'm going to talk to you about three different ways
62
189626
2711
Pa ću vam pričati o tri različita načina
03:12
that self-driving systems are different than driver assistance systems.
63
192337
3346
na koji su samovozeći sustavi drugačiji od sustava pomoći vozaču.
03:15
And I'm going to start with some of our own experience.
64
195683
2651
A započeti ću sa nekim od naših vlastitih iskustava.
03:18
So back in 2013,
65
198334
2253
Dakle natrag u 2013.
03:20
we had the first test of a self-driving car
66
200587
2663
imali smo prvi ispit samovozećeg auta
03:23
where we let regular people use it.
67
203250
2027
gdje smo ga prepustili na korištenje običnim ljudima.
03:25
Well, almost regular -- they were 100 Googlers,
68
205277
2202
Pa, gotovo običnim -- bilo je to 100 Googlovaca,
03:27
but they weren't working on the project.
69
207479
2003
ali 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 auto i dopustili im koristiti ga u svakodnevnom životu.
03:33
But unlike a real self-driving car, this one had a big asterisk with it:
71
213103
3719
Ali za razliku od pravog samovozećeg auta, ovaj je dolazio sa velikom zvjezdicom:
03:36
They had to pay attention,
72
216822
1504
Morali su obraćati pažnju,
03:38
because this was an experimental vehicle.
73
218326
2633
stoga što je ovo bilo pokusno vozilo.
03:40
We tested it a lot, but it could still fail.
74
220959
3525
Puno smo ga iskušavali, ali i dalje je mogao iznevjeriti.
03:44
And so we gave them two hours of training,
75
224484
2059
Pa smo im dali dva sata obuke,
03:46
we put them in the car, we let them use it,
76
226543
2092
smjestili u auto, dali im koristiti ga,
03:48
and what we heard back was something awesome,
77
228635
2127
a što smo čuli zauzvrat je bilo nešto odlično,
03:50
as someone trying to bring a product into the world.
78
230762
2524
nekome tko pokušava donijeti proizvod na svijet.
03:53
Every one of them told us they loved it.
79
233286
1925
Svaki od njih nam je rekao kako ga vole.
03:55
In fact, we had a Porsche driver who came in and told us on the first day,
80
235211
3566
Zapravo, imalo smo vozača Poršea koji je došao i rekao nam prvi dan:
03:58
"This is completely stupid. What are we thinking?"
81
238777
2663
"Ovo je skroz glupo. Što nam pada na pamet?"
04:01
But at the end of it, he said, "Not only should I have it,
82
241850
2840
Ali na kraju, rekao je: "Ne samo da bih ga ja trebao imati,
04:04
everyone else should have it, because people are terrible drivers."
83
244690
3175
svi bi ga drugi trebali imati, jer ljudi su užasni 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
ali tada smo počeli gledati što su ljudi u autu radili,
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
Sad, moja je omiljena priča ovaj gospodin
04:18
who looks down at his phone and realizes the battery is low,
88
258690
3829
koji gleda svoj telefon i vidi da mu je baterija slaba,
04:22
so he turns around like this in the car and digs around in his backpack,
89
262519
4548
pa se okreće ovako u autu i kopa okolo po svojoj naprtnjači,
04:27
pulls out his laptop,
90
267067
2153
vadi svoj laptop,
04:29
puts it on the seat,
91
269220
1567
stavlja ga na sjedište,
04:30
goes in the back again,
92
270787
1764
ide nazad ponovo,,
04:32
digs around, pulls out the charging cable for his phone,
93
272551
3367
kopa okolo, vadi kabel za napajanje telefona,
04:35
futzes around, puts it into the laptop, puts it on the phone.
94
275918
3367
raspliće ga, ukapča ga u laptop, ukapča ga u telefon.
04:39
Sure enough, the phone is charging.
95
279285
2043
Sigurno, telefon se puni.
04:41
All the time he's been doing 65 miles per hour down the freeway.
96
281328
3994
Svo je to vrijeme vozio 100 km na sat po autocesti.
04:45
Right? Unbelievable.
97
285322
2484
Jel tako? Nevjerojatno.
04:47
So we thought about this and we said, it's kind of obvious, right?
98
287806
3121
Porazmislili smo o ovome i rekosmo, zapravo je na neki način očito, ne?
04:50
The better the technology gets,
99
290927
2263
Što će tehnologija postajati bolja,
04:53
the less reliable the driver is going to get.
100
293190
2121
to će manje pouzdan postajati vozač.
04:55
So by just making the cars incrementally smarter,
101
295311
2396
Tako da samo praveći aute postepeno pametnijima,
04:57
we're probably not going to see the wins we really need.
102
297707
2902
vjerojatno nećemo vidjeti pobjede koje zbilja trebamo.
05:00
Let me talk about something a little technical for a moment here.
103
300609
3901
Dajte da malo pričam o nečemu malo tehničkom na trenutak.
05:04
So we're looking at this graph, and along the bottom
104
304510
2438
Dakle gledamo ovaj grafikon, a po njegovom dnu je
05:06
is how often does the car apply the brakes when it shouldn't.
105
306948
3051
koliko često auto koči kada ne bi trebao.
05:09
You can ignore most of that axis,
106
309999
1621
Možete ignorirati većinu te osi,
05:11
because if you're driving around town, and the car starts stopping randomly,
107
311620
3719
jer ako vozite po gradu, a auto se počne nasumično zaustavljati,
05:15
you're never going to buy that car.
108
315339
1701
nikad nećete kupiti takav auto.
05:17
And the vertical axis is how often the car is going to apply the brakes
109
317040
3375
A vertikalna je os koliko će često auto pritisnuti kočnicu
05:20
when it's supposed to to help you avoid an accident.
110
320415
3049
kada bi i trebao kako bi vam pomogao izbjeći nezgodu.
05:23
Now, if we look at the bottom left corner here,
111
323464
2221
Sad, ako pogledamo u donji lijevi ugao,
05:25
this is your classic car.
112
325685
1845
ovo je vaš klasični auto.
05:27
It doesn't apply the brakes for you, it doesn't do anything goofy,
113
327530
3133
Ne pritišće kočnice umjesto vas, ne čini ništa šašavo,
05:30
but it also doesn't get you out of an accident.
114
330663
2779
ali vas također niti ne izvlači iz nezgoda.
05:33
Now, if we want to bring a driver assistance system into a car,
115
333442
3018
Sad, ako želimo dovesti sustav za pomoć vozaču u auto,
05:36
say with collision mitigation braking,
116
336460
1828
recimo kroz kočenje radi izbjegavanja sudara,
05:38
we're going to put some package of technology on there,
117
338288
2612
ubacit ćemo u njega neki paket tehnologije,
05:40
and that's this curve, and it's going to have some operating properties,
118
340900
3418
a to je ova krivulja, i imat će neka operativna svojstva,
05:44
but it's never going to avoid all of the accidents,
119
344318
2490
ali nikad neće izbjeći baš sve nezgode,
05:46
because it doesn't have that capability.
120
346808
2059
jer nema te sposobnosti.
05:48
But we'll pick some place along the curve here,
121
348867
2249
Ali odabrat ćemo neko mjesto na ovoj krivulji,
05:51
and maybe it avoids half of accidents that the human driver misses,
122
351116
3254
te možda izbjegava polovicu nezgoda koje čovjek ne bi,
05:54
and that's amazing, right?
123
354370
1297
i to je zapanjujuće, ne?
05:55
We just reduced accidents on our roads by a factor of two.
124
355667
2727
Upravo smo smanjili nezgode na našim cestama za duplo.
05:58
There are now 17,000 less people dying every year in America.
125
358394
3987
Sad 17.000 manje ljudi umire svake godine u Americi.
06:02
But if we want a self-driving car,
126
362381
2020
Ali ako želimo samovozeći auto,
06:04
we need a technology curve that looks like this.
127
364401
2307
trebamo tehnološku krivulju koja izgleda ovako.
06:06
We're going to have to put more sensors in the vehicle,
128
366708
2599
Morat ćemo stavljati više senzora u vozilo,
06:09
and we'll pick some operating point up here
129
369307
2021
i odabrat ćemo neku operativnu točku ovdje
06:11
where it basically never gets into a crash.
130
371328
2019
gdje zapravo nikad ne dolazi do sudara.
06:13
They'll happen, but very low frequency.
131
373347
2443
Događat će se, ali vrlo rijetko.
06:15
Now you and I could look at this and we could argue
132
375790
2461
Sad bismo vi i ja mogli gledati ovo i raspravljati
06:18
about whether it's incremental, and I could say something like "80-20 rule,"
133
378251
3605
Raste li postupno, a ja bih mogao spomenuti nešto poput pravila 80-20,
06:21
and it's really hard to move up to that new curve.
134
381856
2568
a zbilja je teško popeti se do te nove krivulje.
06:24
But let's look at it from a different direction for a moment.
135
384424
2934
Ali pogledajmo na to iz drugog smjera na trenutak.
06:27
So let's look at how often the technology has to do the right thing.
136
387358
3512
Pogledajmo koliko često tehnologija mora učiniti pravu stvar.
06:30
And so this green dot up here is a driver assistance system.
137
390870
3506
Tako je ova zelena točka gore sustav pomoći vozaču.
06:34
It turns out that human drivers
138
394376
2485
Ispada da ljudski vozači
06:36
make mistakes that lead to traffic accidents
139
396861
2647
čine greške koje dovode do prometnih nesreća
06:39
about once every 100,000 miles in America.
140
399508
3172
otprilike jednom svakih 100.000 milja u Americi.
06:42
In contrast, a self-driving system is probably making decisions
141
402680
3167
Za usporedbu, samovozeći sustav vjerojatno donosi odluke
06:45
about 10 times per second,
142
405847
3663
oko 10 puta po sekundi,
06:49
so order of magnitude,
143
409510
1422
dakle red veličina,
06:50
that's about 1,000 times per mile.
144
410932
2832
to je oko 1000 puta po milji.
06:53
So if you compare the distance between these two,
145
413764
2485
Pa ako usporedite udaljenost između to dvoje,
06:56
it's about 10 to the eighth, right?
146
416249
2600
to je otprilike 10^8, jel tako?
06:58
Eight orders of magnitude.
147
418849
1765
Osam redova veličine.
07:00
That's like comparing how fast I run
148
420614
2809
To je kao usporediti koliko brzo trčim
07:03
to the speed of light.
149
423423
2206
sa brzinom svjetlosti.
07:05
It doesn't matter how hard I train, I'm never actually going to get there.
150
425629
3785
Nema veze koliko teško treniram, nikad zbilja neću stići tamo.
07:09
So there's a pretty big gap there.
151
429414
2438
Dakle tu je poprilično velik jaz.
07:11
And then finally, there's how the system can handle uncertainty.
152
431852
3729
I konačno, tu je i kako se sustav može nositi sa nesigurnošću.
07:15
So this pedestrian here might be stepping into the road, might not be.
153
435581
3323
Primjerice ovaj pješak će možda stati na cestu, a možda i neće.
07:18
I can't tell, nor can any of our algorithms,
154
438904
3395
Ne mogu reći, niti to može ikoji od naših algoritama,
07:22
but in the case of a driver assistance system,
155
442310
2284
ali u slučaju sustava pomoći vozaču,
07:24
that means it can't take action, because again,
156
444594
2806
to znači kako ne može poduzeti akciju, jer ponovo
07:27
if it presses the brakes unexpectedly, that's completely unacceptable.
157
447400
3339
ako stisne kočnicu neočekivano, to je posve neprihvatljivo.
07:30
Whereas a self-driving system can look at that pedestrian and say,
158
450739
3133
Dok samovozeći sustav može osmotriti pješaka i reći,
07:33
I don't know what they're about to do,
159
453872
1890
Ne znam što se sprema učiniti,
07:35
slow down, take a better look, and then react appropriately after that.
160
455762
3762
uspori, bolje osmotri, a tada se ponesi prikladno.
07:39
So it can be much safer than a driver assistance system can ever be.
161
459524
3702
Dakle može biti puno sigurniji nego što sustav pomoći vozaču može biti ikad .
07:43
So that's enough about the differences between the two.
162
463226
2730
No to je dovoljno o razlikama između to dvoje.
07:45
Let's spend some time talking about how the car sees the world.
163
465956
3484
Hajdemo potrošiti neko vrijeme pričajući o tome kako auto vidi svijet.
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
Počinje od razumijevanja gdje se nalazi u svijetu,
07:53
by taking a map and its sensor data and aligning the two,
166
473130
2787
uzimajući mapu i svoje podatke iz senzora te ih usklađuje
07:55
and then we layer on top of that what it sees in the moment.
167
475917
2948
a potom stavljamo povrh toga ono što vidi u trenutku.
07:58
So here, all the purple boxes you can see are other vehicles on the road,
168
478865
3655
Pa ovdje, sve ljubičaste kutije koje možete vidjeti su druga vozila.
08:02
and the red thing on the side over there is a cyclist,
169
482520
2528
A crvena stvar tamo sa strane je biciklist,
08:05
and up in the distance, if you look really closely,
170
485048
2402
a gore u daljini, ako gledate zbilja pažljivo,
08:07
you can see some cones.
171
487450
1794
možete vidjeti neke čunjiće.
08:09
Then we know where the car is in the moment,
172
489244
2773
Tada znamo gdje se auto nalazi u nekom trenutku,
08:12
but we have to do better than that: we have to predict what's going to happen.
173
492017
3833
Ali moramo napraviti bolje od tog: moramo predvidjeti što će se dogoditi.
08:15
So here the pickup truck in top right is about to make a left lane change
174
495850
3488
Pa se ovdje auto gore desno baš sprema prestrojiti u traku lijevo
08:19
because the road in front of it is closed,
175
499338
2223
jer je cesta ispred njega zatvorena,
08:21
so it needs to get out of the way.
176
501561
1731
pa se treba maknuti s puta.
08:23
Knowing that one pickup truck is great,
177
503292
1863
Znati o tom jednom autu je odlično,
08:25
but we really need to know what everybody's thinking,
178
505155
2479
ali mi zapravo trebamo znati što svi razmišljaju,
08:27
so it becomes quite a complicated problem.
179
507634
2507
pa to postaje priično složen problem.
08:30
And then given that, we can figure out how the car should respond in the moment,
180
510141
4749
A potom bismo mogli shvatiti kako bi auto trebao odgovarati u trenutku,
08:34
so what trajectory it should follow, how quickly it should slow down or speed up.
181
514890
3866
dakle koju putanju bi trebao slijediti, koliko bi trebao usporiti ili ubrzati.
08:38
And then that all turns into just following a path:
182
518756
3065
A potom se to sve svodi samo na slijeđenje uputa:
08:41
turning the steering wheel left or right, pressing the brake or gas.
183
521821
3197
okretanje volana lijevo ili desno, pritiskanje gasa ili kočnice.
08:45
It's really just two numbers at the end of the day.
184
525018
2464
To su zapravo samo dva broja na kraju dana.
08:47
So how hard can it really be?
185
527482
2241
Pa koliko to teško zapravo može biti?
08:50
Back when we started in 2009,
186
530433
1952
Kad smo tek počinjali 2009.
08:52
this is what our system looked like.
187
532385
1798
ovo je kako je naš sustav izgledao.
08:54
So you can see our car in the middle and the other boxes on the road,
188
534183
3391
Možete vidjeti naš auto u sredini te druge kutije na cesti,
08:57
driving down the highway.
189
537574
1271
kako se voze autoputom.
08:58
The car needs to understand where it is and roughly where the other vehicles are.
190
538845
3818
Auto mora razumjeti gdje je te ugrubo gdje su ostala vozila.
09:02
It's really a geometric understanding of the world.
191
542663
2429
To je zapravo geometrijsko razumijevanje svijeta.
09:05
Once we started driving on neighborhood and city streets,
192
545092
2948
Jednom kad smo krenuli voziti po ulicama susjedstva i grada,
09:08
the problem becomes a whole new level of difficulty.
193
548040
2445
problem doseže posve novu razinu teškoće.
09:10
You see pedestrians crossing in front of us, cars crossing in front of us,
194
550485
3494
Vidite pješake kako prolaze ispred nas, aute kako prolaze ispred nas,
09:13
going every which way,
195
553979
1811
u svakakvim smjerovima,
09:15
the traffic lights, crosswalks.
196
555790
1527
semafore, pješačke prijelaze.
09:17
It's an incredibly complicated problem by comparison.
197
557317
2797
To je nevjerojatno složen problem u usporedbi.
09:20
And then once you have that problem solved,
198
560114
2103
A onda jednom kad taj problem imate riješen,
09:22
the vehicle has to be able to deal with construction.
199
562217
2512
Vozilo mora biti u stanju nositi se sa radovima na cesti
09:24
So here are the cones on the left forcing it to drive to the right,
200
564729
3151
Pa su ovdje čunjići s lijeva koji ga prisiljavaju na vožnju po desnoj strani,
09:27
but not just construction in isolation, of course.
201
567880
2402
ali ne samo radovi na cesti u izolaciji, naravno.
09:30
It has to deal with other people moving through that construction zone as well.
202
570282
3723
Mora se nositi i sa drugim ljudima koji se kreću kroz tu zonu radova.
09:34
And of course, if anyone's breaking the rules, the police are there
203
574005
3263
Te naravno, ako netko krši pravila, postoji policija
09:37
and the car has to understand that that flashing light on the top of the car
204
577268
3622
a auto mora razumjeti kako rotirka na krovu tog auta
09:40
means that it's not just a car, it's actually a police officer.
205
580890
3105
znači kako to nije samo auto, već zapravo policijski dužnosnik.
09:43
Similarly, the orange box on the side here,
206
583995
2032
Slično tome, narančasta kutija tu 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 njega također trebamo tretirati drugačije.
09:50
When we're out on the road, other people have expectations:
209
590576
2793
Kad izađemo na cestu, drugi ljudi imaju očekivanja:
09:53
So, when a cyclist puts up their arm,
210
593369
1780
tako, kad biciklist 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 kako očekuju da ih auto propusti i napravi im mjesta
09:58
to make a lane change.
212
598667
2053
kako bi promijenili traku.
10:01
And when a police officer stood in the road,
213
601030
2173
A kad policajac stoji na cesti,
10:03
our vehicle should understand that this means stop,
214
603203
2740
naš bi auto trebao razumjeti kako to znači zaustavljanje,
10:05
and when they signal to go, we should continue.
215
605943
3506
a kad nam signaliziraju pokret, trebali bismo nastaviti.
10:09
Now, the way we accomplish this is by sharing data between the vehicles.
216
609449
3761
Sad, način na koji to postižemo je dijeleći podatke među vozilima.
10:13
The first, most crude model of this
217
613210
1696
Prvi, najsiroviji model toga
10:14
is when one vehicle sees a construction zone,
218
614906
2113
je kad jedno vozilo vidi zonu radova na cesti,
10:17
having another know about it so it can be in the correct lane
219
617019
3062
da obavijesti drugo kako bi to znalo biti u pravoj traci
10:20
to avoid some of the difficulty.
220
620081
1570
kako bi izbjeglo poteškoće.
10:21
But we actually have a much deeper understanding of this.
221
621651
2664
Ali mi zapravo imamo puno dublje razumijevanje ovoga.
10:24
We could take all of the data that the cars have seen over time,
222
624315
3009
Mogli bismo uzeti sve podatke koje su auti prikupili tijekom vremena
10:27
the hundreds of thousands of pedestrians, cyclists,
223
627324
2376
stotine tisuća pješaka, biciklista,
10:29
and vehicles that have been out there
224
629700
1787
i vozila koja su bila tamo
10:31
and understand what they look like
225
631487
1695
te razumjeti kako izgledaju
10:33
and use that to infer what other vehicles should look like
226
633182
2831
a potom to iskoristiti kako bi zaključili kako bi druga vozila trebala izgledati
10:36
and other pedestrians should look like.
227
636013
1926
i kako bi trebali izgledati drugi pješaci.
10:37
And then, even more importantly, we could take from that a model
228
637939
3021
A tad, čak i važnije, mogli bismo iz toga izvesti model
10:40
of how we expect them to move through the world.
229
640960
2330
toga kako od njih očekujemo da se kreću kroz svijet.
10:43
So here the yellow box is a pedestrian crossing in front of us.
230
643290
2963
Tako je ovdje žuta kutija pješak koji prelazi cestu ispred nas.
10:46
Here the blue box is a cyclist and we anticipate
231
646253
2250
Ovdje je plava kutija biciklist a mi očekujemo
10:48
that they're going to nudge out and around the car to the right.
232
648503
3312
da će se progurati van i oko auta s desne strane.
10:52
Here there's a cyclist coming down the road
233
652115
2092
Ovdje imamo biciklista koji se kreće cestom
10:54
and we know they're going to continue to drive down the shape of the road.
234
654207
3486
a mi znamo kako će se nastaviti kretati slijedeći oblik ceste.
10:57
Here somebody makes a right turn,
235
657693
1867
Ovdje netko skreće desno,
10:59
and in a moment here, somebody's going to make a U-turn in front of us,
236
659560
3360
a za trenutak ovdje, netko će skrenuti polukružno ispred nas,
11:02
and we can anticipate that behavior and respond safely.
237
662920
2614
i mi možemo predvidjeti to ponašanje te mu odgovoriti sigurno.
11:05
Now, that's all well and good for things that we've seen,
238
665534
2728
Sad, sve je to lijepo i krasno za stvari koje smo vidjeli,
11:08
but of course, you encounter lots of things that you haven't
239
668262
2865
ali naravno, srećete puno stvari koje niste
11:11
seen in the world before.
240
671127
1231
ranije vidjeli u svijetu.
11:12
And so just a couple of months ago,
241
672358
1741
I tako baš prije par mjeseci,
11:14
our vehicles were driving through Mountain View,
242
674099
2235
naša su vozila bila vozila kroz Mountain View,
11:16
and this is what we encountered.
243
676334
1644
a ovo je što smo 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 ganja patku u krugovima po cesti. (Smijeh)
11:22
Now it turns out, there is nowhere in the DMV handbook
246
682677
3111
Ispada kako nigdje u priručniku za vožnju ne piše
11:25
that tells you how to deal with that,
247
685788
2245
kako se nositi s time,
11:28
but our vehicles were able to encounter that,
248
688033
2143
ali naša su vozila bila u stanju nabasati na to,
11:30
slow down, and drive safely.
249
690176
2255
usporiti, te voziti sigurno.
11:32
Now, we don't have to deal with just ducks.
250
692431
2041
Sad, ne moramo raditi samo sa patkama.
11:34
Watch this bird fly across in front of us. The car reacts to that.
251
694472
3708
Pogledajte ovu pticu kako prolijeće ispred nas. Auto reagira na to.
11:38
Here we're dealing with a cyclist
252
698180
1615
Ovdje imamo posla s biciklistom
11:39
that you would never expect to see anywhere other than Mountain View.
253
699795
3290
kojeg ne biste očekivali vidjeti nigdje drugdje nego u Mountain Viewu.
11:43
And of course, we have to deal with drivers,
254
703085
2068
Te naravno, imamo posla i sa biciklistima,
11:45
even the very small ones.
255
705153
3715
čak i vrlo malenima.
11:48
Watch to the right as someone jumps out of this truck at us.
256
708868
4131
Gledajte desno dok netko iskače iz kamiona točno pred nas
11:54
And now, watch the left as the car with the green box decides
257
714460
2929
a sad, gledajte lijevo dok auto sa zelenom kutijom odlučuje
11:57
he needs to make a right turn at the last possible moment.
258
717389
3325
kako mora skrenuti desno u zadnji mogući trenutak.
12:00
Here, as we make a lane change, the car to our left decides
259
720714
2851
Ovdje, dok mijenjamo trake auto nama slijeva odlučuje
12:03
it wants to as well.
260
723565
3553
kako želi to isto.
12:07
And here, we watch a car blow through a red light
261
727118
2693
A ovdje, gledamo auto kako prolazi kroz crveno
12:09
and yield to it.
262
729811
2090
te potom u tome ustraje.
12:11
And similarly, here, a cyclist blowing through that light as well.
263
731901
3854
A također, ovdje, biciklist također prolazi kroz to svjetlo.
12:15
And of course, the vehicle responds safely.
264
735755
2746
Te naravno, vozilo odgovara sigurno.
12:18
And of course, we have people who do I don't know what
265
738501
2601
Te naravno, imamo ljude koji čine ne znam što
12:21
sometimes on the road, like this guy pulling out between two self-driving cars.
266
741102
3823
ponekad na cesti, poput ovog lika koji radi škarice između dva samovozeća auta.
12:24
You have to ask, "What are you thinking?"
267
744925
2045
Morate se zapitati: "što im je u glavi?"
12:26
(Laughter)
268
746970
1212
(Smijeh)
12:28
Now, I just fire-hosed you with a lot of stuff there,
269
748182
2521
Sad, zatrpao sam vas ovdje sa puno toga,
12:30
so I'm going to break one of these down pretty quickly.
270
750703
2650
Pa ću preći preko slijedećeg poprilično brzo,
12:33
So what we're looking at is the scene with the cyclist again,
271
753353
2940
dakle ovdje vidimo scenu sa biciklistom ponovno,
12:36
and you might notice in the bottom, we can't actually see the cyclist yet,
272
756293
3491
a mogli biste primijetiti na dnu, mi zapravo još ne vidimo biciklista
12:39
but the car can: it's that little blue box up there,
273
759784
2504
Ali auto može: to je ta malena plava kutija tamo,
12:42
and that comes from the laser data.
274
762288
2081
a to dolazi od laserskih podataka.
12:44
And that's not actually really easy to understand,
275
764369
2418
A to zapravo baš i nije jednostavno shvatiti,
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 je ono što ću učiniti je uključiti te podatke i pogledati ih,
12:50
and if you're really good at looking at laser data, you can see
277
770371
3029
a ako ste zbilja dobri sa gledanjem u laserske podatke, možete vidjeti
12:53
a few dots on the curve there,
278
773400
1487
nekoliko točaka na krivulji ovdje,
12:54
right there, and that blue box is that cyclist.
279
774887
2372
točno ovdje, a ta je plava kutija taj biciklist.
12:57
Now as our light is red,
280
777259
1149
sad kako je naše svjetlo crveno,
12:58
the cyclist's light has turned yellow already,
281
778408
2192
biciklistu se već upalilo žuto.
13:00
and if you squint, you can see that in the imagery.
282
780600
2438
A ako zaškiljite, možete to i vidjeti u slikama.
13:03
But the cyclist, we see, is going to proceed through the intersection.
283
783038
3286
Ali biciklist, vidimo, će nastaviti kroz križanje.
13:06
Our light has now turned green, his is solidly red,
284
786324
2394
Nama se sada upalilo zeleno, njegovo je čisto crveno,
13:08
and we now anticipate that this bike is going to come all the way across.
285
788718
4292
te mi sad predviđamo kako će taj bicikl proći sasvim preko križanja.
13:13
Unfortunately the other drivers next to us were not paying as much attention.
286
793010
3742
Na nesreću ostali vozači pored nas ne obraćaju baš toliko pažnje.
13:16
They started to pull forward, and fortunately for everyone,
287
796752
3157
Počinju se kretati, te na sreću za sve,
13:19
this cyclists reacts, avoids,
288
799909
3011
biciklist reagira, izbjegava,
13:22
and makes it through the intersection.
289
802920
2191
te prolazi kroz križanje.
13:25
And off we go.
290
805111
1568
I eto ga.
13:26
Now, as you can see, we've made some pretty exciting progress,
291
806679
2948
Sad, kako možete vidjeti, napravili smo prilično uzbudljiv napredak,
13:29
and at this point we're pretty convinced
292
809627
1902
te smo u ovom trenutku prilično uvjereni
13:31
this technology is going to come to market.
293
811529
2010
kako će ova tehnologija dospjeti na tržište.
13:33
We do three million miles of testing in our simulators every single day,
294
813539
4783
Radimo tri milijuna milja testova u našim simulatorima svakog dana,
13:38
so you can imagine the experience that our vehicles have.
295
818322
2689
pa možete zamisliti iskustvo koje naša vozila imaju.
13:41
We are looking forward to having this technology on the road,
296
821011
2864
Radujemo se imati ovu tehnologiju na cesti,
13:43
and we think the right path is to go through the self-driving
297
823875
2890
te mislim kako ispravan put vodi kroz samovozeći
13:46
rather than driver assistance approach
298
826765
1844
prije nego kroz sustav pomoći vozaču
13:48
because the urgency is so large.
299
828609
2621
jer žurba je toliko velika.
13:51
In the time I have given this talk today,
300
831230
2393
U vremenu u kojem sam danas održao ovaj govor,
13:53
34 people have died on America's roads.
301
833623
3135
34 ljudi je poginulo na američkim cestama.
13:56
How soon can we bring it out?
302
836758
2368
Koliko brzo možemo ovo objelodaniti?
13:59
Well, it's hard to say because it's a really complicated problem,
303
839126
3832
Pa, teško je reći stoga što je to zbilja složen problem,
14:02
but these are my two boys.
304
842958
2214
ali ovo su moja dva klinca.
14:05
My oldest son is 11, and that means in four and a half years,
305
845172
3623
Starijem je 11, a to znači kako će za četiri i pol godine,
14:08
he's going to be able to get his driver's license.
306
848795
2577
biti u mogućnosti steći vlastitu 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 predani osigurati da se to ne dogodi.
14:14
Thank you.
308
854576
1904
Hvala vam.
14:16
(Laughter) (Applause)
309
856480
3667
(Smijeh) (Pljesak)
14:21
Chris Anderson: Chris, I've got a question for you.
310
861110
2568
Chris Anderson: Chris, imam pitanje za tebe.
14:23
Chris Urmson: Sure.
311
863678
2809
Chris Urmson: Naravno.
14:26
CA: So certainly, the mind of your cars is pretty mind-boggling.
312
866487
3924
CA: Sigurno, um tvojih autiju je poprilično zapanjujuć.
14:30
On this debate between driver-assisted and fully driverless --
313
870411
4459
U ovoj debati između pomoći vozaču i posve bez vozača --
14:34
I mean, there's a real debate going on out there right now.
314
874870
3041
Mislim, postoji prava debata koja se odvija upravo sada.
14:37
So some of the companies, for example, Tesla,
315
877911
2833
Dakle neke kompanije, na primjer, Tesla,
14:40
are going the driver-assisted route.
316
880744
2159
idu putem pomoći vozaču.
14:42
What you're saying is that that's kind of going to be a dead end
317
882903
5248
Što nam govoriš je kako će to na neki način biti slijepa ulica
14:48
because you can't just keep improving that route and get to fully driverless
318
888151
5456
stoga što ne možeš samo poboljšavati po tom putu i doći do rješenja posve bez vozača
14:53
at some point, and then a driver is going to say, "This feels safe,"
319
893607
3530
u nekom trenutku, te će onda vozač reći: "Ovo ulijeva sigurnost"
14:57
and climb into the back, and something ugly will happen.
320
897137
2647
i zavaliti se u naslon, a tad će se dogoditi nešto ružno.
14:59
CU: Right. No, that's exactly right, and it's not to say
321
899784
2676
CU: Tako je. Ne, to je upravo to, i nije kako
15:02
that the driver assistance systems aren't going to be incredibly valuable.
322
902460
3537
će sustavi pomoći vozaču biti od nevjerojatne vrijednosti.
15:05
They can save a lot of lives in the interim,
323
905997
2058
Oni mogu sačuvati puno života u međurazdoblju,
15:08
but to see the transformative opportunity to help someone like Steve get around,
324
908055
3833
ali za vidjeti preobražajne prilike za pomoć nekome poput Stevea da se kreće,
15:11
to really get to the end case in safety,
325
911888
1969
za stvarno doći do završetka priče o sigurnosti,
15:13
to have the opportunity to change our cities
326
913857
2479
za imati priliku promijeniti naše gradove
15:16
and move parking out and get rid of these urban craters we call parking lots,
327
916336
4204
i izbaciti parkirana vozila te se riješiti urbanih kratera - parkirališta,
15:20
it's the only way to go.
328
920540
1240
to je jedini pravi put.
15:21
CA: We will be tracking your progress with huge interest.
329
921780
2718
CA: Pratit ćemo vaš napredak s ogromnim zanimanjem.
15:24
Thanks so much, Chris. CU: Thank you. (Applause)
330
924498
4232
Hvala puno, Chris. CU: Hvala! (Pljesak)
O ovoj web stranici

Ova stranica će vas upoznati s YouTube videozapisima koji su korisni za učenje engleskog jezika. Vidjet ćete lekcije engleskog koje vode vrhunski profesori iz cijelog svijeta. Dvaput kliknite na engleske titlove prikazane na svakoj video stranici da biste reproducirali video s tog mjesta. Titlovi se pomiču sinkronizirano s reprodukcijom videozapisa. Ako imate bilo kakvih komentara ili zahtjeva, obratite nam se putem ovog obrasca za kontakt.

https://forms.gle/WvT1wiN1qDtmnspy7