Chris Urmson: How a driverless car sees the road

So in 1885, Karl Benz
invented the automobile. Later that year, he took it out
for the first public test drive, and — true story —
crashed into a wall. For the last 130 years, we’ve been working around that least
reliable part of the car, the driver. We’ve made the car stronger. We’ve added seat belts,
we’ve added air bags, and in the last decade, we’ve actually
started trying to make the car smarter to fix that bug, the driver. Now, today I’m going to talk to you
a little bit about the difference between patching around the problem
with driver assistance systems and actually having fully
self-driving cars and what they can do for the world. I’m also going to talk to you
a little bit about our car and allow you to see how it sees the world
and how it reacts and what it does, but first I’m going to talk
a little bit about the problem. And it’s a big problem: 1.2 million people are killed
on the world’s roads every year. In America alone, 33,000 people
are killed each year. To put that in perspective, that’s the same as a 737
falling out of the sky every working day. It’s kind of unbelievable. Cars are sold to us like this, but really, this is what driving’s like. Right? It’s not sunny, it’s rainy, and you want to do anything
other than drive. And the reason why is this: Traffic is getting worse. In America, between 1990 and 2010, the vehicle miles traveled
increased by 38 percent. We grew by six percent of roads, so it’s not in your brains. Traffic really is substantially worse
than it was not very long ago. And all of this has a very human cost. So if you take the average commute time
in America, which is about 50 minutes, you multiply that by the 120 million
workers we have, that turns out to be
about six billion minutes wasted in commuting every day. Now, that’s a big number,
so let’s put it in perspective. You take that six billion minutes and you divide it by the average
life expectancy of a person, that turns out to be 162 lifetimes spent every day, wasted, just getting from A to B. It’s unbelievable. And then, there are those of us
who don’t have the privilege of sitting in traffic. So this is Steve. He’s an incredibly capable guy, but he just happens to be blind, and that means instead of a 30-minute
drive to work in the morning, it’s a two-hour ordeal
of piecing together bits of public transit or asking friends and family for a ride. He doesn’t have that same freedom
that you and I have to get around. We should do something about that. Now, conventional wisdom would say that we’ll just take
these driver assistance systems and we’ll kind of push them
and incrementally improve them, and over time, they’ll turn
into self-driving cars. Well, I’m here to tell you
that’s like me saying that if I work really hard at jumping,
one day I’ll be able to fly. We actually need to do
something a little different. And so I’m going to talk to you
about three different ways that self-driving systems are different
than driver assistance systems. And I’m going to start
with some of our own experience. So back in 2013, we had the first test
of a self-driving car where we let regular people use it. Well, almost regular —
they were 100 Googlers, but they weren’t working on the project. And we gave them the car and we allowed
them to use it in their daily lives. But unlike a real self-driving car,
this one had a big asterisk with it: They had to pay attention, because this was an experimental vehicle. We tested it a lot,
but it could still fail. And so we gave them two hours of training, we put them in the car,
we let them use it, and what we heard back
was something awesome, as someone trying
to bring a product into the world. Every one of them told us they loved it. In fact, we had a Porsche driver
who came in and told us on the first day, “This is completely stupid.
What are we thinking?” But at the end of it, he said,
“Not only should I have it, everyone else should have it,
because people are terrible drivers.” So this was music to our ears, but then we started to look at what
the people inside the car were doing, and this was eye-opening. Now, my favorite story is this gentleman who looks down at his phone
and realizes the battery is low, so he turns around like this in the car
and digs around in his backpack, pulls out his laptop, puts it on the seat, goes in the back again, digs around, pulls out
the charging cable for his phone, futzes around, puts it into the laptop,
puts it on the phone. Sure enough, the phone is charging. All the time he’s been doing
65 miles per hour down the freeway. Right? Unbelievable. So we thought about this and we said,
it’s kind of obvious, right? The better the technology gets, the less reliable
the driver is going to get. So by just making the cars
incrementally smarter, we’re probably not going to see
the wins we really need. Let me talk about something
a little technical for a moment here. So we’re looking at this graph,
and along the bottom is how often does the car
apply the brakes when it shouldn’t. You can ignore most of that axis, because if you’re driving around town,
and the car starts stopping randomly, you’re never going to buy that car. And the vertical axis is how often
the car is going to apply the brakes when it’s supposed to
to help you avoid an accident. Now, if we look at
the bottom left corner here, this is your classic car. It doesn’t apply the brakes for you,
it doesn’t do anything goofy, but it also doesn’t get you
out of an accident. Now, if we want to bring
a driver assistance system into a car, say with collision mitigation braking, we’re going to put some package
of technology on there, and that’s this curve, and it’s going
to have some operating properties, but it’s never going to avoid
all of the accidents, because it doesn’t have that capability. But we’ll pick some place
along the curve here, and maybe it avoids half of accidents
that the human driver misses, and that’s amazing, right? We just reduced accidents on our roads
by a factor of two. There are now 17,000 less people
dying every year in America. But if we want a self-driving car, we need a technology curve
that looks like this. We’re going to have to put
more sensors in the vehicle, and we’ll pick some
operating point up here where it basically never
gets into a crash. They’ll happen, but very low frequency. Now you and I could look at this
and we could argue about whether it’s incremental, and
I could say something like “80-20 rule,” and it’s really hard to move up
to that new curve. But let’s look at it
from a different direction for a moment. So let’s look at how often
the technology has to do the right thing. And so this green dot up here
is a driver assistance system. It turns out that human drivers make mistakes that lead
to traffic accidents about once every 100,000 miles in America. In contrast, a self-driving system
is probably making decisions about 10 times per second, so order of magnitude, that’s about 1,000 times per mile. So if you compare the distance
between these two, it’s about 10 to the eighth, right? Eight orders of magnitude. That’s like comparing how fast I run to the speed of light. It doesn’t matter how hard I train,
I’m never actually going to get there. So there’s a pretty big gap there. And then finally, there’s how
the system can handle uncertainty. So this pedestrian here might be
stepping into the road, might not be. I can’t tell,
nor can any of our algorithms, but in the case of
a driver assistance system, that means it can’t take action,
because again, if it presses the brakes unexpectedly,
that’s completely unacceptable. Whereas a self-driving system
can look at that pedestrian and say, I don’t know what they’re about to do, slow down, take a better look,
and then react appropriately after that. So it can be much safer than
a driver assistance system can ever be. So that’s enough about
the differences between the two. Let’s spend some time talking about
how the car sees the world. So this is our vehicle. It starts by understanding
where it is in the world, by taking a map and its sensor data
and aligning the two, and then we layer on top of that
what it sees in the moment. So here, all the purple boxes you can see
are other vehicles on the road, and the red thing on the side
over there is a cyclist, and up in the distance,
if you look really closely, you can see some cones. Then we know where the car
is in the moment, but we have to do better than that:
we have to predict what’s going to happen. So here the pickup truck in top right
is about to make a left lane change because the road in front of it is closed, so it needs to get out of the way. Knowing that one pickup truck is great, but we really need to know
what everybody’s thinking, so it becomes quite a complicated problem. And then given that, we can figure out
how the car should respond in the moment, so what trajectory it should follow, how
quickly it should slow down or speed up. And then that all turns into
just following a path: turning the steering wheel left or right,
pressing the brake or gas. It’s really just two numbers
at the end of the day. So how hard can it really be? Back when we started in 2009, this is what our system looked like. So you can see our car in the middle
and the other boxes on the road, driving down the highway. The car needs to understand where it is
and roughly where the other vehicles are. It’s really a geometric
understanding of the world. Once we started driving
on neighborhood and city streets, the problem becomes a whole
new level of difficulty. You see pedestrians crossing in front
of us, cars crossing in front of us, going every which way, the traffic lights, crosswalks. It’s an incredibly complicated
problem by comparison. And then once you have
that problem solved, the vehicle has to be able
to deal with construction. So here are the cones on the left
forcing it to drive to the right, but not just construction
in isolation, of course. It has to deal with other people moving
through that construction zone as well. And of course, if anyone’s
breaking the rules, the police are there and the car has to understand that
that flashing light on the top of the car means that it’s not just a car,
it’s actually a police officer. Similarly, the orange box
on the side here, it’s a school bus, and we have to treat that
differently as well. When we’re out on the road,
other people have expectations: So, when a cyclist puts up their arm, it means they’re expecting the car
to yield to them and make room for them to make a lane change. And when a police officer
stood in the road, our vehicle should understand
that this means stop, and when they signal to go,
we should continue. Now, the way we accomplish this
is by sharing data between the vehicles. The first, most crude model of this is when one vehicle
sees a construction zone, having another know about it
so it can be in the correct lane to avoid some of the difficulty. But we actually have a much
deeper understanding of this. We could take all of the data
that the cars have seen over time, the hundreds of thousands
of pedestrians, cyclists, and vehicles that have been out there and understand what they look like and use that to infer
what other vehicles should look like and other pedestrians should look like. And then, even more importantly,
we could take from that a model of how we expect them
to move through the world. So here the yellow box is a pedestrian
crossing in front of us. Here the blue box is a cyclist
and we anticipate that they’re going to nudge out
and around the car to the right. Here there’s a cyclist
coming down the road and we know they’re going to continue
to drive down the shape of the road. Here somebody makes a right turn, and in a moment here, somebody’s
going to make a U-turn in front of us, and we can anticipate that behavior
and respond safely. Now, that’s all well and good
for things that we’ve seen, but of course, you encounter
lots of things that you haven’t seen in the world before. And so just a couple of months ago, our vehicles were driving
through Mountain View, and this is what we encountered. This is a woman in an electric wheelchair chasing a duck in circles on the road.
(Laughter) Now it turns out, there is nowhere
in the DMV handbook that tells you how to deal with that, but our vehicles were able
to encounter that, slow down, and drive safely. Now, we don’t have to deal
with just ducks. Watch this bird fly across in front of us.
The car reacts to that. Here we’re dealing with a cyclist that you would never expect to see
anywhere other than Mountain View. And of course, we have
to deal with drivers, even the very small ones. Watch to the right as someone
jumps out of this truck at us. And now, watch the left as the car
with the green box decides he needs to make a right turn
at the last possible moment. Here, as we make a lane change,
the car to our left decides it wants to as well. And here, we watch a car
blow through a red light and yield to it. And similarly, here, a cyclist
blowing through that light as well. And of course,
the vehicle responds safely. And of course, we have people
who do I don’t know what sometimes on the road, like this guy
pulling out between two self-driving cars. You have to ask, “What are you thinking?” (Laughter) Now, I just fire-hosed you
with a lot of stuff there, so I’m going to break one of these
down pretty quickly. So what we’re looking at is the scene
with the cyclist again, and you might notice in the bottom,
we can’t actually see the cyclist yet, but the car can: it’s that little
blue box up there, and that comes from the laser data. And that’s not actually
really easy to understand, so what I’m going to do is I’m going
to turn that laser data and look at it, and if you’re really good at looking
at laser data, you can see a few dots on the curve there, right there, and that blue box
is that cyclist. Now as our light is red, the cyclist’s light
has turned yellow already, and if you squint, you can see that
in the imagery. But the cyclist, we see, is going
to proceed through the intersection. Our light has now turned green,
his is solidly red, and we now anticipate that this bike
is going to come all the way across. Unfortunately the other drivers next to us
were not paying as much attention. They started to pull forward,
and fortunately for everyone, this cyclists reacts, avoids, and makes it through the intersection. And off we go. Now, as you can see, we’ve made
some pretty exciting progress, and at this point we’re pretty convinced this technology is going
to come to market. We do three million miles of testing
in our simulators every single day, so you can imagine the experience
that our vehicles have. We are looking forward to having
this technology on the road, and we think the right path
is to go through the self-driving rather than driver assistance approach because the urgency is so large. In the time I have given this talk today, 34 people have died on America’s roads. How soon can we bring it out? Well, it’s hard to say because
it’s a really complicated problem, but these are my two boys. My oldest son is 11, and that means
in four and a half years, he’s going to be able
to get his driver’s license. My team and I are committed
to making sure that doesn’t happen. Thank you. (Laughter) (Applause) Chris Anderson: Chris,
I’ve got a question for you. Chris Urmson: Sure. CA: So certainly, the mind of your cars
is pretty mind-boggling. On this debate between
driver-assisted and fully driverless — I mean, there’s a real debate
going on out there right now. So some of the companies,
for example, Tesla, are going the driver-assisted route. What you’re saying is that
that’s kind of going to be a dead end because you can’t just keep improving
that route and get to fully driverless at some point, and then a driver
is going to say, “This feels safe,” and climb into the back,
and something ugly will happen. CU: Right. No, that’s exactly right,
and it’s not to say that the driver assistance systems
aren’t going to be incredibly valuable. They can save a lot of lives
in the interim, but to see the transformative opportunity
to help someone like Steve get around, to really get to the end case in safety, to have the opportunity
to change our cities and move parking out and get rid of
these urban craters we call parking lots, it’s the only way to go. CA: We will be tracking your progress
with huge interest. Thanks so much, Chris.
CU: Thank you. (Applause)

, , , , , , , , , , ,

Post navigation

100 thoughts on “Chris Urmson: How a driverless car sees the road

  1. There will not be self driving cars wide spread for 50 years. We just don't have the tech. to do it safely and wont for a long time. Get over it.

  2. Benjamin Franklin once said: "Those who would give up essential Liberty, to purchase a little temporary Safety, deserve neither Liberty nor Safety." This is NOT really about keeping people safe – that's the tag line Big Brother ALWAYS uses to implement tyranny! It's really about controlling you, & where you go. It's also about making people stupider & less responsible for themselves & their actions. Google is an elitist globalist collectivist monster that wants to eliminate much of humanity & have ultimate control over those who are left – like much of TED's cast of characters. Plenty of views of them saying they want to greatly reduce world population – so why would they be sooo concerned about our safety?? TO CONTROL YOU IN THEIR GLOBALIST "SUSTAINABLE" ANTHILLS!!!! WAKE UP, PEOPLE!!!!!!!!! You will have to pry my steering wheel out of my COLD DEAD HANDS, JUST LIKE MY GUNS!!!!!!!!!!

  3. AND … can you say SOLAR FLARES? Wait till you see what happens to ALL your electronic crap – computers, Stupid, oops, I mean "Smart" phones, etc. WHEN, not if, the next round of major solar flares begin!!! Whee! I can't wait! No electronic banking or digital money; hospital electronic equipment, GPS, NOTHIN' electrical working!! What will your autoNOmus vehicles do then??!! Stupid sheeple; electronic dependency is for kids!

  4. "Imagine a future where everything's perfect. Humans will no longer have to use their arms or legs to do anything. No more having to set foot outside and risk endangering ourselves or others. Robots will do all of the work, while A.I. will do all of the thinking for us. We could have telepathic chips implanted into our brains when we're born so we could do all of our learning via software updates (no more money wasted on schools [public or private]), not to mention those even entertaining any type of criminal thought would immediately be detained by the "state". But the best part is people will share identical thoughts because of said chips, which means no more debating or critiquing progress or innovation. Everything will go according to plan. Perfection."

    Nah…screw that! I enjoy being "imperfect" and having my freedom.

  5. Can these work on India, there are bad roads full with potholes,open drain holes in middle of road, with jam pack traffic, Animals like cows, buffalos, donkeys, goats, stray dogs and cats all using the road as resting and living spaces. People living in shacks made on the side of road. people sleeping on roads at night time.

  6. Sorry Taxi drivers, you are about to lose your jobs and soon it will be delivery drivers, HGV Drivers, FLT drivers etc. What a bunch of fuckwits we are. We need to be creating jobs for everyone, not taking them away on a global scale, which is exactly what will happen.

  7. "…Carl Benz invented the automobile. Later that year, he took it out for the first public test drive, and true story, crashed into a wall."

    Right, because no autonomous vehicle has ever crashed on its "maiden voyage". *rolls eyes*

  8. hmmm not sure how i feel about the car stopping when it sees someone holding their hand out in front of them. That's going to get abused by people who aren't police. Like myself hehe

  9. A driverless car can't see the road, and it is just an Illusion, the last few percentages of human-like visual perception and driving confidence are impossible to achieve. Believe me.

  10. Every single driverless car would have to work perfectly all the time. I do not see that happening. Then there is how long will they work perfectly? Their computers and all the connections would have to be flawless, and so would their repairmen. I don't think that will happen.

    They might be able to do this for 18 wheeler commercial applications on highways, but you would still need a driver to be awake at the wheel. There would need to be redundant backup control. There is still an unanswered question of liability, and I would bet it will not be the manufacturer somehow.

  11. What part of dehumanization didn't you understand?
    How many lives will be saved? And how many lives will be shot be unemployed hungry desperate people?
    Will it be a crime to fake crossing a road just to make a self-driving vehicle slow down or stop?
    By By jobs hello future?
    Get real, quickly, please!

  12. well that similar system did not pickup the uber fatal incident in march 2018… far from being safe even after 3+ years of acumulating more data… that system isn't perfect…

  13. 1.2million road deaths, 55million deaths each year globally, so only 2% of deaths from road vehicle accidents. It's actually not a big problem, compared to other causes of death (which aren't even being addressed).

  14. Must read , self driving cars … 60 accidents that were not the self driving car's fault??

    2018-03-28 07:00 by Karl Denninger 
    in Technology , 252 references

    The Real Issue With Self-Driving Cars

    [Comments enabled]

    It's not that the car apparently didn't "see" a pedestrian walking a bicycle and hit her. At least we think it didn't see her. We actually don't know that yet, just that she was struck.

    But you better start thinking about the realregulatory issue, and one that had better get center-stage right damn now and be part of the debate and requirements if these things are going to run around on our roads.

    It's this:

    The car is on a two-lane road with a hard and fixed barrier on the right side, and on-coming traffic on the other side. A child runs out in front of the vehicle inside of the stopping distance. The car detects the child instantly, but is unable to stop.

    The vehicle is able to compute the probability of your death (and everyone else in your vehicle) with a fair degree of certainty if it intentionally crashes into the fixed object to avoid the child. If the oncoming vehicle is also self-driving it may also be able to compute the risk of death or serious injury for those occupants if it hits that car intentionally since the vehicles are probably communicating. If it hits the child it also probably can compute the odds (very high, perhaps 100%) that the child will die as well.

    The vehicle must strike something due to the physics of the situation.

    What decision does the car make and who or what does it hit?

    If you are in this situation as a human driver you cannot compute the risk of death for various parties, since you don't have the mass of the vehicles, the energy each carriers, the presence or absence of wearing seat belts, where the impact will be taken, etc. The car can make that computation in the milliseconds available, you cannot.

    However, you still can choose to intentionally decide to hit the solid abutment, or the oncoming car to avoid hitting the child.

    You as someone buying or riding in a self-driving vehicle must be able to know the decision tree on this situation in advance because it does happen.

    Now let's take another example. Uber is claimed to have something like 2 million road miles on its self-driving cars but there have been ~60 accidents, most minor and nearly all the fault of the other driver. This may sound to you like a good record.

    It's not. It in fact sucks big fat donkey balls; a human driver with that record would be considered a terrible risk (and pay an astronomical insurance premium) no matter who was technically "at fault."

    I have well over 750,000 lifetime miles on the road by my best guess. My current car has 130,000. The truck in the driveway has about 60,000. My Jetta, which my kid now has, was given to her just short of 200,000. That's nearly 400,000 miles just between these last three vehicles, and there were years when I lived in Chicago where I put 50k on a car because I was doing contract work and in the damn thing all the time.

    My lifetime accident record on the road? Zero.

    But I have, several times (including fairly recently) intentionally violating a traffic law to avoid an accident, the most-common incident being intentionally running a light that has either just turned red or is about to and I detect that the vehicle behind me is not going to stop before striking me, yet the crossing road is clear. The law says I must stop if I can do so safely. I will take and fight any ticket ever given to me where I run such a light for that reason, because if I'm about to be hit then "stopping safely" isn't going to occur. I've yet to be ticketed for this but I've avoided several accidents this way — none of which would have been "my fault", but all of which would have damaged my car and maybe myself or others in the car.

    How are these self-driving cars programmed and why would anyone get into one without knowing that first — or buy one, for that matter?

    You have every right to know if the vehicle will obey traffic laws even if it means getting struckand you potentially being injured or worse as a result, and you also have the right to know if the vehicle will kill or injure you preferentially and intentionally to avoid killing someone else who is not in the car. Since you are not driving you are never "at fault" for hitting someone else, which means you personally will never be tagged in such a lawsuit — the company that made the car will be!

    This provides a powerful incentive for the vehicle designer to avoid hitting the other party even if they have to injure or kill you in order to do so since you have some contractual relationship with said firm (in which they might, and probably will, try to limit their liability) but the other party does not and thus can't be bound by same.

    In short you have every right to know what the vehicle's "prime directive" is but we're not even talking about this!

    This is the issue with these self-driving cars. The machine may have limitations on what it can see and sense but it is always faster in making the decision and acting on it than you can be. The question here first is did the car see the woman but second, if it did then the next question is "did it deliberately hit her because the other options were worse?"

    If that's not the case here it will be in the future and in fact it has already happened with less-dire consequences, it would appear, if these vehicles have managed to rack up 60 accidents in 2 million miles where I, as a human, have yet to have one in more than 25% of that mileage — but I have had to break traffic laws and take anticipatory actions for that to be the case.

    These self-driving cars clearly are doing neither and you have every right to know what their decision matrix is and what preference it will take both in the event that a traffic law conflicts with an impending accident (that is otherwise avoidable) and what it will do in a "no-win" scenario — before you get into one.

    Never mind the data security and spying that willgo on, with every trip you take in one of these things being data that does not belong to you.

  15. Great. So what part of Uber's system failed in Tempe? I can't be the only night cyclocommuter who wants to know.

  16. I think it is very innovative and good technology. But I think it is very dangerous because of this uber car.

  17. There isn't enough bandwidth available to support all of the data needed for intelligent highways used by smart cars.

  18. Bad news for autonomous vehicles….take a look at just a couple of the many informative Youtube videos on the subject…."The driverless car scam" & "The terrifying truth about self-driving vehicles"

  19. In the near future, there will be an overwhelming need for a paradigm shift. AV's will enable people to forego owning a car. Picture this if you will! You want to go to work, you call up an AV and it comes to your door. You get in the AV and tell it where you want to go. The AV sets out for your destination and you check your email, the news or start work on your computer. Shorty you arrive, release the AV. You then schedule an AV to pick you up at the end of your workday.
    Think about it; no cash outlay, no insurance, no fuel cost and no parking fees.
    The future will be stress free.

  20. I wonder how many human drivers have had zero accidents through all their driving years. How many careless drivers and how many careful drivers do we have? The above talk is quite leading with untested claims. The end result is that humans will be prevented from driving. The Porche driver 'story' was a clear giveaway, right away. The videos of self-drive cars show cars moving in highly controlled surroundings. If your self-drive car manages to move more than a few meters in the Bombay traffic then it can be said to have replaced human drivers.

  21. I wonder here in the US, we blame traffic and drivers for the road accidents. This is while ignoring the fact that many people spend an hour just to drive their workplace 15miles away from their house. Public transportation as better connected local trains could save more time, money and pollution. But no, that’s against the capitalism I believe.
    I mean self driving could actually increase the safety on the streets, but does it solve the traffic problems?

  22. At 7:20, the driver will make a visual contact with the pedestrian to make sure that he saw him. The pedestrian can even wave to the driver to show him to pass, An autonomous car will never understand that.

  23. Why are you comparing the difference "distance" between human error rate (errors/mile), and vehicle assist decision rate at 6:59? Your argument about running and the speed of light seemed deceptive. You lost credibility with me sir.

  24. 7:33, a driver assist system could issue an alert to notify driver of uncertainty. I remain skeptical that any system will attain full autonomy without mass adoption.

  25. Ansys a major player in engineering simulation systems has released a new video showcasing "System Simulation for Autonomous Vehicle Development"

  26. I want to see it drive in the snow with snow drifts all over that the snow plows put there. I want to see it park in field that is a temporary parking lot for a big event like a concert, Renaissance Fair, or State Fair. I want too see how it handles while a police chase is zooming by.

  27. Fine, but does not describe the problem autonomous cars keep failing to handle (crashing): when you are in the lane on a highway following another car, which suddenly changes lanes to avoid a stationary or very slow car or object. Under such circumstances, the autonomous system ignores the stationary car/object because it is programmed to ignore various stationary objects such as parked cars, etc. Waymo (Google) has, no doubt, the most advanced system but still can not solve this problem, which remains​ a serious flaw for use of AV at highway speeds. Others, such as Tesla have even more scenarios where stationary objects confuse the systems and cause wrong responses. This is why more experienced automotive companies such as Benz, BMW, GM, etc. are taking the incremental approach and considering the need for greater vehicle-to-vehicle communication before full autonomy is realized (road-mapped mid-2020's).

  28. We have driverless cars. They are called trains…… Betterthan clogging up the road with people who dont qualify for a licence to drive.

  29. Sure driverless cars make you tons of money…. Nobody cares about your money because you obviously dont care about the rights of others.

  30. The first "fact" he stated is wrong. With 120M people driving an average of 50 min/day is still 50 min of driving everyday, not 6B minutes and not 162 lifetimes wasted on driving…

  31. Stop overengineering it! All the car has to do is: not crash. Apply an uncertainty margin to other vehicles. Drive like the cars behave as expected, but drive in a way that you could still stop safely, if harshly, if anything within the uncertainty margin happens. It's still too complex to fully describe it in a youtube comment, but it isn't very hard to understand.

  32. All we need to do really would be to put the cell phone for map viewing and it will capture images with camera and give feed back to the engine control unit by the cigarette lighter charging cable. Every car can have an auto pilot in the future

  33. Another case of not addressing the root problem. Self-driving cars will only cause more problems. How about figuring out overpopulation, housing prices, spreading economic centers across the country more?

    Why are people willing to give the government and big corporations control over their mobility? I'm not afraid of change, in fact, I welcome it, but why isn't anyone answering the tough questions? Hackers anyone?

  34. Oh they blind have the privilege of sitting in traffic they just don't drive in that traffic. Also in all those yellow dot pictures I do not see for 1 a person with a service animal, and 2 a person in a wheelchair or power chair other then the lady casing a duck they show later.

  35. I can't be bothered watching this extended Google advert, but I wonder if he mentioned the people driverless cars have killed so far, or the fact that most testing has been *simulated*, or that the idea is to have monopolies in cities whereby the residents will be forced to rent cars form the monopoly holder, which naturally he hopes would be Google. Mr Ford has been honest enough about the real reasons for driverless cars, but everyone else prattles on about safety, when in fact the complete lack of real data means that claiming these awful machines would be safer than humans is, to put it nicely, simply conjecture.

    Did he say that the idea is to put smart phone zombies in driverless death traps and have them see adverts and make purchases instead of driving?

    I could go on, so I will. I wonder if he mentioned what happens after flooding or hurricanes have ripped up roads and blown down signs, or when someone needs to go offroad across the desert, or lives on a large farm which isn't mapped, or needs to park in a certain place, or is a sole trader with a van full of tools.

    Still, why let irritating things such as questions or facts get in the way of profit?

  36. I rarely apply the breaks while on the freeway, while I see some cars spend more time on the breaks then off the breaks.
    Don't tailgate and look past the car in front of you and it is possible to have the need to break less.

  37. Why does everyone assume you'll need to worry about licenses, insurance and gas prices? It seems likely to me that when this becomes the norm you wont own a driverless car, you'll order it like Uber, be collected and dropped off and pay for your trip. Then off it goes to pick up the next fellow. Also it would likely evolve to not even look like a traditional car. See the bigger picture folks!

  38. 13:51 Umm, no. 33,000 American fatalities per year / 365 days / 24 hours per day / 60 minutes per hour = 0.063 fatalities per minute. Rounding up, Urmson has been talking for 14 minutes at this point. So 14 x 0.063 = … yeah, not quite there yet. He'd have to talk for another two minutes to reach a single fatality. Still tragic to be sure, but nowhere near 34 as he claims. Now using the 1.2 million worldwide number does work out to 34 for the entirety of his speech. But I'm sure he just accidentally conflated the two statistics, and really didn't intend to manipulate anyone to his point of view through the use of scare tactics.

    Then again, he does resemble Al Gore a little.

  39. If you have this kind of car, does it mean that you don't need a drivers license? Because blind person can drive using driver less car.

  40. KJV Bible says we humans will definitely eliminate all cars.
    Car crashes are the 8th leading cause of death for all ages.
    So: I Corinthians 15:26
    “The last enemy that shall be destroyed is death,” so there won’t be any vehicles, which means that all nations will someday (soon I hope) eliminate all vehicles and build only Tower cities connected to maglev Trains, so some generation will do it. We could and should, but not many want to do it. Maybe this generation doesn’t care that 50,000 Americans die every year in cars (but I say more), and maybe that’s because our population loves their cars more than life. But God is life. Satan is death.

  41. Driverless cars don't care about dogs, cats, stones, holes, animals, things, sudden rain or snow. If a person is not standing on the road, but lying down, driveless cars will step and go on it.

  42. So Cool ! Can't wait to see  / ride in one .  As long as they have a placard on the dash like  this I'm down with it  .  When will we have flying robo taxies based on say the hero Flyer ?

  43. Self-driving cars will be very confused in the UK. Cars parking all over the road and the entire road as wild as 1 lane in the USA. I can't wait to see how it will work out

  44. and all the roads in the world will have to become americanized if we want those cars to be purchasable worldwide within the next 100 years

  45. "We added seatbelts, we added airbags".. typical computer engineer. Thinks that the only thing happened in past 100 years in automobile.

  46. when every car is self driving they'll be able to communicate with eachother and it'll be much more effective

  47. Al this 5G, IoT, radar etc. will reduce human to no-thing – radiated out of existence. Not even capable of mastrubating while on the way to no-thing.

  48. I'm a huge supporter of self driving and i really hope they succeed.👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍

  49. You think the cancer rate is high now? Wait until everyone is getting hit by the radiation from the lidar systems. We're all going to be driving around in one big microwave. Maybe thats googles plan, give everyone cancer

  50. Honking Car Locking Wakes People Up and is VERY STRESSFUL. Especially for people with Ptsd. Cardiac Disease High Blood Pressure and Migraines.
    Noise Pollution Causes Serious Health Problems. Please Think of Your Neighbors. We hear the HONK from Behind the Walls of the Buildings You Park Next To.
    Please Use Light Flash Only. Please Break the HONK Habit. It is just a Habit. Thank You.

  51. Based on the first 5 min of his talk, I think we should inspect the driver rather than replacing the driver by machine. The former is realistic and the latter is a headache problem because the autonomous car can fail in an unpredictable way.


  53. Fixing the blind guy's problem is simple:

    better public transport.
    It should not take 2 hours by public transport if it takes 30 minutes by car.

  54. It is June, 2019. As the technology gets better, the challenge of self driving car continues to grow bigger.

  55. I assume they use Lidars. The ToF and reflection data provide histograms from which distances and geometries if objects seen along the roads are derived. This gives the point clouds. Do they use neural networks trained beforehand or some classical way to process the raw lidar data to do the perception (object detection)?

  56. Your son is going to have drive license, and Google still not yet announce their self-driving car to the market.

  57. The worst thing about a TED Talk is it's always informative and it always seems It's hard even put this into words but you have to have a good brain I guess to be able to see through it so it's hard to explain exactly what's wrong a person will come on we'll talk about some new age idea or how people got to love one another or in this case driverless cars and it's always in addition to what we have already in our existence so it seems like another step up never do they ever discuss what benefits or what reasons there are four why we are the way we are now it's just that were in a progression to another level and they're going to explain to us their version of the best way to get there. Such nonsense the fact is people do drive shity but what you could see by all of the technology he was having to have his driverless cars learn was how amazing people are they taking so many factors as they are driving that there's a billion cars on the road a day and there's only a few dozen people that died even with machines they give out and they'll still be people dying again this is the stupidity of a TED Talk they actually never covered the chance that even one in a million of those cars malfunctions I'm not talking about the ones that are hacked or anything else just breaks down healthy people dying no matter who drives us. Last I benefit a lot from the skills I got having done things mechanically in my life I've seen the Next Generation have other skills but completely lose the ability to do what I could do I've seen people literally asked me how to turn an LED light on I had to tell the person 20 of course I had to tell that twenty-year-old turn it clockwise they then asked how to turn it off see a bunch of mindless people and a Planet of the Apes scenario is not necessarily going to make us smarter in other ways Silgan stupid tedtalk hopes that you are new age and won't question what are the factors there are to consider perhaps the lack of skill motor skill pardon the pun that we lose as a result of this adds to our stupid decision making and lack of skill physically in some other area who knows whether we lose two dozen a day and some other area because we no longer have the skills from driving but again this isn't all about the skills of driving it's just to make a point that they always push a TED talk as if they were bringing you to the new age improved better human level and they never really discuss why we naturally all the way we are now it's just that we haven't gotten to some other stage yet we're just in a metamorphosis as if we're never meant to be where where are at the given moment

Leave a Reply

Your email address will not be published. Required fields are marked *