Chris Urmson: How a driverless car sees the road

Prevoditelj: Stjepan Mateljan Recezent: Ivan Stamenković

So in 1885, Karl Benz invented the automobile.

Dakle 1885, Karl Benz izumio je automobil.

Later that year, he took it out for the first public test drive,

Kasnije te godine, izveo ga je na prvu javnu probnu vožnju,

and -- true story -- crashed into a wall.

i -- istinita priča -- zabio se u zid.

For the last 130 years,

Kroz zadnjih 130 godina,

we've been working around that least reliable part of the car, the driver.

radili smo oko najmanje pouzdanog dijela auta, vozača.

We've made the car stronger.

Napravili smo aute jačim.

We've added seat belts, we've added air bags,

Dodali smo sigurnosne pojase, dodali smo zračne jastuke,

and in the last decade, we've actually started trying to make the car smarter

a u zadnjem desetljeću, zapravo smo počeli činiti aute pametnijima

to fix that bug, the driver.

da popravimo taj bug, vozača.

Now, today I'm going to talk to you a little bit about the difference

Sad, danas ću vam pričati nešto malo o razlici

between patching around the problem with driver assistance systems

između krpanja oko problema sa sustavima pomoći vozaču

and actually having fully self-driving cars

i imanja pravih posve samovozećih automobila.

and what they can do for the world.

te što oni mogu učiniti za svijet.

I'm also going to talk to you a little bit about our car

Također ću vam pričati malo i o našem autu

and allow you to see how it sees the world and how it reacts and what it does,

i dozvoliti vam da vidite kako on vidi svijet te kako reagira i što čini,

but first I'm going to talk a little bit about the problem.

ali prvo ću malo pričati o problemu.

And it's a big problem:

A to je veliki problem:

1.2 million people are killed on the world's roads every year.

1,2 milijuna ljudi je ubijeno na svjetskim cestama svake godine.

In America alone, 33,000 people are killed each year.

Samo u Americi, 33.000 ljudi je ubijeno svake godine.

To put that in perspective,

Da to stavimo u perspektivu,

that's the same as a 737 falling out of the sky every working day.

to je jednako kao da 737 padne s neba svaki radni dan.

It's kind of unbelievable.

Na neki je način nevjerojatno.

Cars are sold to us like this,

Aute nam prodaju ovako,

but really, this is what driving's like.

ali zapravo, ovo je kako izgleda vožnja.

Right? It's not sunny, it's rainy,

Je li tako? Nije sunčano, pada kiša,

and you want to do anything other than drive.

i želite raditi bilo što drugo, samo ne voziti.

And the reason why is this:

A razlog zašto je ovaj:

Traffic is getting worse.

Promet postaje gori.

In America, between 1990 and 2010,

U Americi, od 1990 do 2010,

the vehicle miles traveled increased by 38 percent.

milje proputovane vozilima su porasle 38 posto.

We grew by six percent of roads,

Porasli smo za šest posto u cestama,

so it's not in your brains.

tako da vam to nije u glavama.

Traffic really is substantially worse than it was not very long ago.

Promet je zbilja bitno gori nego što je bio ne tako davno.

And all of this has a very human cost.

A sve to ima vrlo ljudsku cijenu.

So if you take the average commute time in America, which is about 50 minutes,

Pa ako uzmete prosječno vrijeme dnevne vožnje koje je pedesetak minuta,

you multiply that by the 120 million workers we have,

pomnožite to sa 120 milijuna radnika koliko ih imamo,

that turns out to be about six billion minutes

ispadne da je to otprilike šest milijardi minuta

wasted in commuting every day.

potrošenih u prometu svaki dan.

Now, that's a big number, so let's put it in perspective.

Sad, to je velik broj, pa ajmo ga staviti u perspektivu.

You take that six billion minutes

Uzmete tih šest milijardi minuta

and you divide it by the average life expectancy of a person,

i podijelite ih sa prosječnim očekivanim životnim vijekom osobe,

that turns out to be 162 lifetimes

ispadne 162 životna vijeka

spent every day, wasted,

potrošenih svaki dan, bačenih

just getting from A to B.

samo na prelazak od A do B.

It's unbelievable.

Nevjerojatno.

And then, there are those of us who don't have the privilege

A potom, ima ih među nama koji nemaju povlasticu

of sitting in traffic.

sudjelovanja u prometu.

So this is Steve.

Dakle ovo je Steve.

He's an incredibly capable guy,

On je nevjerojatno sposoban tip,

but he just happens to be blind,

samo što je slijep,

and that means instead of a 30-minute drive to work in the morning,

a to znači kako umjesto 30 minutne vožnje do posla ujutro,

it's a two-hour ordeal of piecing together bits of public transit

to je dvosatno iskušenje sastavljanja djelića javnog prijevoza

or asking friends and family for a ride.

ili molba prijateljima i obitelji za prijevoz.

He doesn't have that same freedom that you and I have to get around.

On nema istu slobodu kao vi i ja glede kretanja uokolo.

We should do something about that.

Trebali bismo učiniti nešto u vezi toga.

Now, conventional wisdom would say

Sad, uobičajena bi mudrost rekla

that we'll just take these driver assistance systems

neka samo uzmemo te sustave pomoći vozaču

and we'll kind of push them and incrementally improve them,

pa ćemo ih onda gurati i postepeno usavršavati

and over time, they'll turn into self-driving cars.

te će se tijekom vremena premetnuti u samovozeće aute.

Well, I'm here to tell you that's like me saying

Dobro, ovdje sam kako bih vam rekao da je to nalik izjavi

that if I work really hard at jumping, one day I'll be able to fly.

kako ću ako jako uporno radim na skakanju, jednoga dana moći letjeti.

We actually need to do something a little different.

Zapravo trebamo napraviti nešto malo drugačije.

And so I'm going to talk to you about three different ways

Pa ću vam pričati o tri različita načina

that self-driving systems are different than driver assistance systems.

na koji su samovozeći sustavi drugačiji od sustava pomoći vozaču.

And I'm going to start with some of our own experience.

A započeti ću sa nekim od naših vlastitih iskustava.

So back in 2013,

Dakle natrag u 2013.

we had the first test of a self-driving car

imali smo prvi ispit samovozećeg auta

where we let regular people use it.

gdje smo ga prepustili na korištenje običnim ljudima.

Well, almost regular -- they were 100 Googlers,

Pa, gotovo običnim -- bilo je to 100 Googlovaca,

but they weren't working on the project.

ali nisu radili na projektu.

And we gave them the car and we allowed them to use it in their daily lives.

Dali smo im auto i dopustili im koristiti ga u svakodnevnom životu.

But unlike a real self-driving car, this one had a big asterisk with it:

Ali za razliku od pravog samovozećeg auta, ovaj je dolazio sa velikom zvjezdicom:

They had to pay attention,

Morali su obraćati pažnju,

because this was an experimental vehicle.

stoga što je ovo bilo pokusno vozilo.

We tested it a lot, but it could still fail.

Puno smo ga iskušavali, ali i dalje je mogao iznevjeriti.

And so we gave them two hours of training,

Pa smo im dali dva sata obuke,

we put them in the car, we let them use it,

smjestili u auto, dali im koristiti ga,

and what we heard back was something awesome,

a što smo čuli zauzvrat je bilo nešto odlično,

as someone trying to bring a product into the world.

nekome tko pokušava donijeti proizvod na svijet.

Every one of them told us they loved it.

Svaki od njih nam je rekao kako ga vole.

In fact, we had a Porsche driver who came in and told us on the first day,

Zapravo, imalo smo vozača Poršea koji je došao i rekao nam prvi dan:

"This is completely stupid. What are we thinking?"

"Ovo je skroz glupo. Što nam pada na pamet?"

But at the end of it, he said, "Not only should I have it,

Ali na kraju, rekao je: "Ne samo da bih ga ja trebao imati,

everyone else should have it, because people are terrible drivers."

svi bi ga drugi trebali imati, jer ljudi su užasni vozači."

So this was music to our ears,

To je bila muzika za naše uši,

but then we started to look at what the people inside the car were doing,

ali tada smo počeli gledati što su ljudi u autu radili,

and this was eye-opening.

i to nam je otvorilo oči.

Now, my favorite story is this gentleman

Sad, moja je omiljena priča ovaj gospodin

who looks down at his phone and realizes the battery is low,

koji gleda svoj telefon i vidi da mu je baterija slaba,

so he turns around like this in the car and digs around in his backpack,

pa se okreće ovako u autu i kopa okolo po svojoj naprtnjači,

pulls out his laptop,

vadi svoj laptop,

puts it on the seat,

stavlja ga na sjedište,

goes in the back again,

ide nazad ponovo,,

digs around, pulls out the charging cable for his phone,

kopa okolo, vadi kabel za napajanje telefona,

futzes around, puts it into the laptop, puts it on the phone.

raspliće ga, ukapča ga u laptop, ukapča ga u telefon.

Sure enough, the phone is charging.

Sigurno, telefon se puni.

All the time he's been doing 65 miles per hour down the freeway.

Svo je to vrijeme vozio 100 km na sat po autocesti.

Right? Unbelievable.

Jel tako? Nevjerojatno.

So we thought about this and we said, it's kind of obvious, right?

Porazmislili smo o ovome i rekosmo, zapravo je na neki način očito, ne?

The better the technology gets,

Što će tehnologija postajati bolja,

the less reliable the driver is going to get.

to će manje pouzdan postajati vozač.

So by just making the cars incrementally smarter,

Tako da samo praveći aute postepeno pametnijima,

we're probably not going to see the wins we really need.

vjerojatno nećemo vidjeti pobjede koje zbilja trebamo.

Let me talk about something a little technical for a moment here.

Dajte da malo pričam o nečemu malo tehničkom na trenutak.

So we're looking at this graph, and along the bottom

Dakle gledamo ovaj grafikon, a po njegovom dnu je

is how often does the car apply the brakes when it shouldn't.

koliko često auto koči kada ne bi trebao.

You can ignore most of that axis,

Možete ignorirati većinu te osi,

because if you're driving around town, and the car starts stopping randomly,

jer ako vozite po gradu, a auto se počne nasumično zaustavljati,

you're never going to buy that car.

nikad nećete kupiti takav auto.

And the vertical axis is how often the car is going to apply the brakes

A vertikalna je os koliko će često auto pritisnuti kočnicu

when it's supposed to to help you avoid an accident.

kada bi i trebao kako bi vam pomogao izbjeći nezgodu.

Now, if we look at the bottom left corner here,

Sad, ako pogledamo u donji lijevi ugao,

this is your classic car.

ovo je vaš klasični auto.

It doesn't apply the brakes for you, it doesn't do anything goofy,

Ne pritišće kočnice umjesto vas, ne čini ništa šašavo,

but it also doesn't get you out of an accident.

ali vas također niti ne izvlači iz nezgoda.

Now, if we want to bring a driver assistance system into a car,

Sad, ako želimo dovesti sustav za pomoć vozaču u auto,

say with collision mitigation braking,

recimo kroz kočenje radi izbjegavanja sudara,

we're going to put some package of technology on there,

ubacit ćemo u njega neki paket tehnologije,

and that's this curve, and it's going to have some operating properties,

a to je ova krivulja, i imat će neka operativna svojstva,

but it's never going to avoid all of the accidents,

ali nikad neće izbjeći baš sve nezgode,

because it doesn't have that capability.

jer nema te sposobnosti.

But we'll pick some place along the curve here,

Ali odabrat ćemo neko mjesto na ovoj krivulji,

and maybe it avoids half of accidents that the human driver misses,

te možda izbjegava polovicu nezgoda koje čovjek ne bi,

and that's amazing, right?

i to je zapanjujuće, ne?

We just reduced accidents on our roads by a factor of two.

Upravo smo smanjili nezgode na našim cestama za duplo.

There are now 17,000 less people dying every year in America.

Sad 17.000 manje ljudi umire svake godine u Americi.

But if we want a self-driving car,

Ali ako želimo samovozeći auto,

we need a technology curve that looks like this.

trebamo tehnološku krivulju koja izgleda ovako.

We're going to have to put more sensors in the vehicle,

Morat ćemo stavljati više senzora u vozilo,

and we'll pick some operating point up here

i odabrat ćemo neku operativnu točku ovdje

where it basically never gets into a crash.

gdje zapravo nikad ne dolazi do sudara.

They'll happen, but very low frequency.

Događat će se, ali vrlo rijetko.

Now you and I could look at this and we could argue

Sad bismo vi i ja mogli gledati ovo i raspravljati

about whether it's incremental, and I could say something like "80-20 rule,"

Raste li postupno, a ja bih mogao spomenuti nešto poput pravila 80-20,

and it's really hard to move up to that new curve.

a zbilja je teško popeti se do te nove krivulje.

But let's look at it from a different direction for a moment.

Ali pogledajmo na to iz drugog smjera na trenutak.

So let's look at how often the technology has to do the right thing.

Pogledajmo koliko često tehnologija mora učiniti pravu stvar.

And so this green dot up here is a driver assistance system.

Tako je ova zelena točka gore sustav pomoći vozaču.

It turns out that human drivers

Ispada da ljudski vozači

make mistakes that lead to traffic accidents

čine greške koje dovode do prometnih nesreća

about once every 100,000 miles in America.

otprilike jednom svakih 100.000 milja u Americi.

In contrast, a self-driving system is probably making decisions

Za usporedbu, samovozeći sustav vjerojatno donosi odluke

about 10 times per second,

oko 10 puta po sekundi,

so order of magnitude,

dakle red veličina,

that's about 1,000 times per mile.

to je oko 1000 puta po milji.

So if you compare the distance between these two,

Pa ako usporedite udaljenost između to dvoje,

it's about 10 to the eighth, right?

to je otprilike 10^8, jel tako?

Eight orders of magnitude.

Osam redova veličine.

That's like comparing how fast I run

To je kao usporediti koliko brzo trčim

to the speed of light.

sa brzinom svjetlosti.

It doesn't matter how hard I train, I'm never actually going to get there.

Nema veze koliko teško treniram, nikad zbilja neću stići tamo.

So there's a pretty big gap there.

Dakle tu je poprilično velik jaz.

And then finally, there's how the system can handle uncertainty.

I konačno, tu je i kako se sustav može nositi sa nesigurnošću.

So this pedestrian here might be stepping into the road, might not be.

Primjerice ovaj pješak će možda stati na cestu, a možda i neće.

I can't tell, nor can any of our algorithms,

Ne mogu reći, niti to može ikoji od naših algoritama,

but in the case of a driver assistance system,

ali u slučaju sustava pomoći vozaču,

that means it can't take action, because again,

to znači kako ne može poduzeti akciju, jer ponovo

if it presses the brakes unexpectedly, that's completely unacceptable.

ako stisne kočnicu neočekivano, to je posve neprihvatljivo.

Whereas a self-driving system can look at that pedestrian and say,

Dok samovozeći sustav može osmotriti pješaka i reći,

I don't know what they're about to do,

Ne znam što se sprema učiniti,

slow down, take a better look, and then react appropriately after that.

uspori, bolje osmotri, a tada se ponesi prikladno.

So it can be much safer than a driver assistance system can ever be.

Dakle može biti puno sigurniji nego što sustav pomoći vozaču može biti ikad .

So that's enough about the differences between the two.

No to je dovoljno o razlikama između to dvoje.

Let's spend some time talking about how the car sees the world.

Hajdemo potrošiti neko vrijeme pričajući o tome kako auto vidi svijet.

So this is our vehicle.

Dakle ovo je naše vozilo.

It starts by understanding where it is in the world,

Počinje od razumijevanja gdje se nalazi u svijetu,

by taking a map and its sensor data and aligning the two,

uzimajući mapu i svoje podatke iz senzora te ih usklađuje

and then we layer on top of that what it sees in the moment.

a potom stavljamo povrh toga ono što vidi u trenutku.

So here, all the purple boxes you can see are other vehicles on the road,

Pa ovdje, sve ljubičaste kutije koje možete vidjeti su druga vozila.

and the red thing on the side over there is a cyclist,

A crvena stvar tamo sa strane je biciklist,

and up in the distance, if you look really closely,

a gore u daljini, ako gledate zbilja pažljivo,

you can see some cones.

možete vidjeti neke čunjiće.

Then we know where the car is in the moment,

Tada znamo gdje se auto nalazi u nekom trenutku,

but we have to do better than that: we have to predict what's going to happen.

Ali moramo napraviti bolje od tog: moramo predvidjeti što će se dogoditi.

So here the pickup truck in top right is about to make a left lane change

Pa se ovdje auto gore desno baš sprema prestrojiti u traku lijevo

because the road in front of it is closed,

jer je cesta ispred njega zatvorena,

so it needs to get out of the way.

pa se treba maknuti s puta.

Knowing that one pickup truck is great,

Znati o tom jednom autu je odlično,

but we really need to know what everybody's thinking,

ali mi zapravo trebamo znati što svi razmišljaju,

so it becomes quite a complicated problem.

pa to postaje priično složen problem.

And then given that, we can figure out how the car should respond in the moment,

A potom bismo mogli shvatiti kako bi auto trebao odgovarati u trenutku,

so what trajectory it should follow, how quickly it should slow down or speed up.

dakle koju putanju bi trebao slijediti, koliko bi trebao usporiti ili ubrzati.

And then that all turns into just following a path:

A potom se to sve svodi samo na slijeđenje uputa:

turning the steering wheel left or right, pressing the brake or gas.

okretanje volana lijevo ili desno, pritiskanje gasa ili kočnice.

It's really just two numbers at the end of the day.

To su zapravo samo dva broja na kraju dana.

So how hard can it really be?

Pa koliko to teško zapravo može biti?

Back when we started in 2009,

Kad smo tek počinjali 2009.

this is what our system looked like.

ovo je kako je naš sustav izgledao.

So you can see our car in the middle and the other boxes on the road,

Možete vidjeti naš auto u sredini te druge kutije na cesti,

driving down the highway.

kako se voze autoputom.

The car needs to understand where it is and roughly where the other vehicles are.

Auto mora razumjeti gdje je te ugrubo gdje su ostala vozila.

It's really a geometric understanding of the world.

To je zapravo geometrijsko razumijevanje svijeta.

Once we started driving on neighborhood and city streets,

Jednom kad smo krenuli voziti po ulicama susjedstva i grada,

the problem becomes a whole new level of difficulty.

problem doseže posve novu razinu teškoće.

You see pedestrians crossing in front of us, cars crossing in front of us,

Vidite pješake kako prolaze ispred nas, aute kako prolaze ispred nas,

going every which way,

u svakakvim smjerovima,

the traffic lights, crosswalks.

semafore, pješačke prijelaze.

It's an incredibly complicated problem by comparison.

To je nevjerojatno složen problem u usporedbi.

And then once you have that problem solved,

A onda jednom kad taj problem imate riješen,

the vehicle has to be able to deal with construction.

Vozilo mora biti u stanju nositi se sa radovima na cesti

So here are the cones on the left forcing it to drive to the right,

Pa su ovdje čunjići s lijeva koji ga prisiljavaju na vožnju po desnoj strani,

but not just construction in isolation, of course.

ali ne samo radovi na cesti u izolaciji, naravno.

It has to deal with other people moving through that construction zone as well.

Mora se nositi i sa drugim ljudima koji se kreću kroz tu zonu radova.

And of course, if anyone's breaking the rules, the police are there

Te naravno, ako netko krši pravila, postoji policija

and the car has to understand that that flashing light on the top of the car

a auto mora razumjeti kako rotirka na krovu tog auta

means that it's not just a car, it's actually a police officer.

znači kako to nije samo auto, već zapravo policijski dužnosnik.

Similarly, the orange box on the side here,

Slično tome, narančasta kutija tu sa strane,

it's a school bus,

je školski autobus,

and we have to treat that differently as well.

i njega također trebamo tretirati drugačije.

When we're out on the road, other people have expectations:

Kad izađemo na cestu, drugi ljudi imaju očekivanja:

So, when a cyclist puts up their arm,

tako, kad biciklist ispruži ruku,

it means they're expecting the car to yield to them and make room for them

to znači kako očekuju da ih auto propusti i napravi im mjesta

to make a lane change.

kako bi promijenili traku.

And when a police officer stood in the road,

A kad policajac stoji na cesti,

our vehicle should understand that this means stop,

naš bi auto trebao razumjeti kako to znači zaustavljanje,

and when they signal to go, we should continue.

a kad nam signaliziraju pokret, trebali bismo nastaviti.

Now, the way we accomplish this is by sharing data between the vehicles.

Sad, način na koji to postižemo je dijeleći podatke među vozilima.

The first, most crude model of this

Prvi, najsiroviji model toga

is when one vehicle sees a construction zone,

je kad jedno vozilo vidi zonu radova na cesti,

having another know about it so it can be in the correct lane

da obavijesti drugo kako bi to znalo biti u pravoj traci

to avoid some of the difficulty.

kako bi izbjeglo poteškoće.

But we actually have a much deeper understanding of this.

Ali mi zapravo imamo puno dublje razumijevanje ovoga.

We could take all of the data that the cars have seen over time,

Mogli bismo uzeti sve podatke koje su auti prikupili tijekom vremena

the hundreds of thousands of pedestrians, cyclists,

stotine tisuća pješaka, biciklista,

and vehicles that have been out there

i vozila koja su bila tamo

and understand what they look like

te razumjeti kako izgledaju

and use that to infer what other vehicles should look like

a potom to iskoristiti kako bi zaključili kako bi druga vozila trebala izgledati

and other pedestrians should look like.

i kako bi trebali izgledati drugi pješaci.

And then, even more importantly, we could take from that a model

A tad, čak i važnije, mogli bismo iz toga izvesti model

of how we expect them to move through the world.

toga kako od njih očekujemo da se kreću kroz svijet.

So here the yellow box is a pedestrian crossing in front of us.

Tako je ovdje žuta kutija pješak koji prelazi cestu ispred nas.

Here the blue box is a cyclist and we anticipate

Ovdje je plava kutija biciklist a mi očekujemo

that they're going to nudge out and around the car to the right.

da će se progurati van i oko auta s desne strane.

Here there's a cyclist coming down the road

Ovdje imamo biciklista koji se kreće cestom

and we know they're going to continue to drive down the shape of the road.

a mi znamo kako će se nastaviti kretati slijedeći oblik ceste.

Here somebody makes a right turn,

Ovdje netko skreće desno,

and in a moment here, somebody's going to make a U-turn in front of us,

a za trenutak ovdje, netko će skrenuti polukružno ispred nas,

and we can anticipate that behavior and respond safely.

i mi možemo predvidjeti to ponašanje te mu odgovoriti sigurno.

Now, that's all well and good for things that we've seen,

Sad, sve je to lijepo i krasno za stvari koje smo vidjeli,

but of course, you encounter lots of things that you haven't

ali naravno, srećete puno stvari koje niste

seen in the world before.

ranije vidjeli u svijetu.

And so just a couple of months ago,

I tako baš prije par mjeseci,

our vehicles were driving through Mountain View,

naša su vozila bila vozila kroz Mountain View,

and this is what we encountered.

a ovo je što smo susreli.

This is a woman in an electric wheelchair

Ovo je žena u električnim kolicima

chasing a duck in circles on the road. (Laughter)

koja ganja patku u krugovima po cesti. (Smijeh)

Now it turns out, there is nowhere in the DMV handbook

Ispada kako nigdje u priručniku za vožnju ne piše

that tells you how to deal with that,

kako se nositi s time,

but our vehicles were able to encounter that,

ali naša su vozila bila u stanju nabasati na to,

slow down, and drive safely.

usporiti, te voziti sigurno.

Now, we don't have to deal with just ducks.

Sad, ne moramo raditi samo sa patkama.

Watch this bird fly across in front of us. The car reacts to that.

Pogledajte ovu pticu kako prolijeće ispred nas. Auto reagira na to.

Here we're dealing with a cyclist

Ovdje imamo posla s biciklistom

that you would never expect to see anywhere other than Mountain View.

kojeg ne biste očekivali vidjeti nigdje drugdje nego u Mountain Viewu.

And of course, we have to deal with drivers,

Te naravno, imamo posla i sa biciklistima,

even the very small ones.

čak i vrlo malenima.

Watch to the right as someone jumps out of this truck at us.

Gledajte desno dok netko iskače iz kamiona točno pred nas

And now, watch the left as the car with the green box decides

a sad, gledajte lijevo dok auto sa zelenom kutijom odlučuje

he needs to make a right turn at the last possible moment.

kako mora skrenuti desno u zadnji mogući trenutak.

Here, as we make a lane change, the car to our left decides

Ovdje, dok mijenjamo trake auto nama slijeva odlučuje

it wants to as well.

kako želi to isto.

And here, we watch a car blow through a red light

A ovdje, gledamo auto kako prolazi kroz crveno

and yield to it.

te potom u tome ustraje.

And similarly, here, a cyclist blowing through that light as well.

A također, ovdje, biciklist također prolazi kroz to svjetlo.

And of course, the vehicle responds safely.

Te naravno, vozilo odgovara sigurno.

And of course, we have people who do I don't know what

Te naravno, imamo ljude koji čine ne znam što

sometimes on the road, like this guy pulling out between two self-driving cars.

ponekad na cesti, poput ovog lika koji radi škarice između dva samovozeća auta.

You have to ask, "What are you thinking?"

Morate se zapitati: "što im je u glavi?"

(Laughter)

(Smijeh)

Now, I just fire-hosed you with a lot of stuff there,

Sad, zatrpao sam vas ovdje sa puno toga,

so I'm going to break one of these down pretty quickly.

Pa ću preći preko slijedećeg poprilično brzo,

So what we're looking at is the scene with the cyclist again,

dakle ovdje vidimo scenu sa biciklistom ponovno,

and you might notice in the bottom, we can't actually see the cyclist yet,

a mogli biste primijetiti na dnu, mi zapravo još ne vidimo biciklista

but the car can: it's that little blue box up there,

Ali auto može: to je ta malena plava kutija tamo,

and that comes from the laser data.

a to dolazi od laserskih podataka.

And that's not actually really easy to understand,

A to zapravo baš i nije jednostavno shvatiti,

so what I'm going to do is I'm going to turn that laser data and look at it,

pa je ono što ću učiniti je uključiti te podatke i pogledati ih,

and if you're really good at looking at laser data, you can see

a ako ste zbilja dobri sa gledanjem u laserske podatke, možete vidjeti

a few dots on the curve there,

nekoliko točaka na krivulji ovdje,

right there, and that blue box is that cyclist.

točno ovdje, a ta je plava kutija taj biciklist.

Now as our light is red,

sad kako je naše svjetlo crveno,

the cyclist's light has turned yellow already,

biciklistu se već upalilo žuto.

and if you squint, you can see that in the imagery.

A ako zaškiljite, možete to i vidjeti u slikama.

But the cyclist, we see, is going to proceed through the intersection.

Ali biciklist, vidimo, će nastaviti kroz križanje.

Our light has now turned green, his is solidly red,

Nama se sada upalilo zeleno, njegovo je čisto crveno,

and we now anticipate that this bike is going to come all the way across.

te mi sad predviđamo kako će taj bicikl proći sasvim preko križanja.

Unfortunately the other drivers next to us were not paying as much attention.

Na nesreću ostali vozači pored nas ne obraćaju baš toliko pažnje.

They started to pull forward, and fortunately for everyone,

Počinju se kretati, te na sreću za sve,

this cyclists reacts, avoids,

biciklist reagira, izbjegava,

and makes it through the intersection.

te prolazi kroz križanje.

And off we go.

I eto ga.

Now, as you can see, we've made some pretty exciting progress,

Sad, kako možete vidjeti, napravili smo prilično uzbudljiv napredak,

and at this point we're pretty convinced

te smo u ovom trenutku prilično uvjereni

this technology is going to come to market.

kako će ova tehnologija dospjeti na tržište.

We do three million miles of testing in our simulators every single day,

Radimo tri milijuna milja testova u našim simulatorima svakog dana,

so you can imagine the experience that our vehicles have.

pa možete zamisliti iskustvo koje naša vozila imaju.

We are looking forward to having this technology on the road,

Radujemo se imati ovu tehnologiju na cesti,

and we think the right path is to go through the self-driving

te mislim kako ispravan put vodi kroz samovozeći

rather than driver assistance approach

prije nego kroz sustav pomoći vozaču

because the urgency is so large.

jer žurba je toliko velika.

In the time I have given this talk today,

U vremenu u kojem sam danas održao ovaj govor,

34 people have died on America's roads.

34 ljudi je poginulo na američkim cestama.

How soon can we bring it out?

Koliko brzo možemo ovo objelodaniti?

Well, it's hard to say because it's a really complicated problem,

Pa, teško je reći stoga što je to zbilja složen problem,

but these are my two boys.

ali ovo su moja dva klinca.

My oldest son is 11, and that means in four and a half years,

Starijem je 11, a to znači kako će za četiri i pol godine,

he's going to be able to get his driver's license.

biti u mogućnosti steći vlastitu vozačku dozvolu.

My team and I are committed to making sure that doesn't happen.

Moj tim i ja smo predani osigurati da se to ne dogodi.

Thank you.

Hvala vam.

(Laughter) (Applause)

(Smijeh) (Pljesak)

Chris Anderson: Chris, I've got a question for you.

Chris Anderson: Chris, imam pitanje za tebe.

Chris Urmson: Sure.

Chris Urmson: Naravno.

CA: So certainly, the mind of your cars is pretty mind-boggling.

CA: Sigurno, um tvojih autiju je poprilično zapanjujuć.

On this debate between driver-assisted and fully driverless --

U ovoj debati između pomoći vozaču i posve bez vozača --

I mean, there's a real debate going on out there right now.

Mislim, postoji prava debata koja se odvija upravo sada.

So some of the companies, for example, Tesla,

Dakle neke kompanije, na primjer, Tesla,

are going the driver-assisted route.

idu putem pomoći vozaču.

What you're saying is that that's kind of going to be a dead end

Što nam govoriš je kako će to na neki način biti slijepa ulica

because you can't just keep improving that route and get to fully driverless

stoga što ne možeš samo poboljšavati po tom putu i doći do rješenja posve bez vozača

at some point, and then a driver is going to say, "This feels safe,"

u nekom trenutku, te će onda vozač reći: "Ovo ulijeva sigurnost"

and climb into the back, and something ugly will happen.

i zavaliti se u naslon, a tad će se dogoditi nešto ružno.

CU: Right. No, that's exactly right, and it's not to say

CU: Tako je. Ne, to je upravo to, i nije kako

that the driver assistance systems aren't going to be incredibly valuable.

će sustavi pomoći vozaču biti od nevjerojatne vrijednosti.

They can save a lot of lives in the interim,

Oni mogu sačuvati puno života u međurazdoblju,

but to see the transformative opportunity to help someone like Steve get around,

ali za vidjeti preobražajne prilike za pomoć nekome poput Stevea da se kreće,

to really get to the end case in safety,

za stvarno doći do završetka priče o sigurnosti,

to have the opportunity to change our cities

za imati priliku promijeniti naše gradove

and move parking out and get rid of these urban craters we call parking lots,

i izbaciti parkirana vozila te se riješiti urbanih kratera - parkirališta,

it's the only way to go.

to je jedini pravi put.

CA: We will be tracking your progress with huge interest.

CA: Pratit ćemo vaš napredak s ogromnim zanimanjem.

Thanks so much, Chris. CU: Thank you. (Applause)

Hvala puno, Chris. CU: Hvala! (Pljesak)