Tempe Police Release Video of Uber Accident • Hacker News Board

Re: Tempe Police Release Video of Uber Accident

#411

Post by adamweld » Thu, Mar 22, 2018, 1:22 AM UTC

maxerickson wrote: post #105

chrsstrm wrote: post #16

The description given before the video was released painted a picture in my mind that the woman was on the median and "suddenly" entered the roadway in front of the vehicle. I pictured someone darting across the road directly in front of the car, with no way to stop in time. This video shows a completely different scenario. The woman started on the median, but the vehicle was in the #2 lane. She wasn't visible to the…

I think this seems like exactly the scenario that autonomous driving vehicles are intended to prevent. may be optimistic. Lots of people are hoping they will prevent such scenarios, the motivation for fielding them is more related to making lots of money.

I disagree, if you look at any of the Waymo videos you can see they have great recognition of every car, pedestrian, and obstacle within 100 meters of the car, and most of that data (point cloud lidar/radar at the very least) would work in pitch black without even headlights. Thus it's extremely reasonable to expect that autonomous vehicles will easily prevent scenarios like this.

Inclement conditions, defensive driving, etc. are much harder to work with but this should have been cake.

Re: Tempe Police Release Video of Uber Accident

#412

Post by aerovistae » Thu, Mar 22, 2018, 1:22 AM UTC

atonse wrote: post #25

How did LIDAR and IR not catch that? That seems like a pretty serious problem. It's clear from the video that a human driver actually would've had more trouble since the pedestrian showed up in the field of view right before the collision, yet that's in the visible spectrum. When I argue for automated driving (as a casual observer), I tell people about exactly this sort of stuff (a computer can look in 20 places at t…

> Yet this crash proves that all the equipment in the world didn't catch a very obvious obstruction.

Because the software is still critically flawed, of course...this only represents a present-day failing, not some sort of permanent obstacle for the future.

Re: Tempe Police Release Video of Uber Accident

#413

Post by pdonis » Thu, Mar 22, 2018, 1:23 AM UTC

chillwaves wrote: post #359

pdonis wrote: post #195

Earlier quoted context omitted.

> I think it's important as a driver to hit the brakes as hard as you can even if you don't think you'll be able to avoid collision It's good to hit the brakes, yes, but the best way to avoid almost all collisions is to steer, not just to brake. Braking combined with steering sharply to the left (since the pedestrian was moving to the right) would have been the best response to this situation. (Note that, before anti…

Depending on your speed, that is very bad advice. Sounds like a recipe for losing traction and fish tailing (potentially into other cars or people or even stationary objects). There is only so much traction afforded by the contact patch on your tires. You can brake, you can turn, you can speed up but I would not recommend doing more than one at a time.

> There is only so much traction afforded by the contact patch on your tires

If you have anti-lock brakes, they are designed and calibrated to know how much to brake to be just short of losing traction. That's what they're for--to allow you to brake and steer at the same time without having to have special training to know exactly how to balance the two.

If you don't have anti-lock brakes (but it's very rare now not to have them in a car of recent manufacture), then it's still possible to brake and steer at the same time, but it's not easy or intuitive to balance the two to maintain control. It can be done, but you basically have to be a professional driver.

Re: Tempe Police Release Video of Uber Accident

#414

Post by ScottBurson » Thu, Mar 22, 2018, 1:23 AM UTC

erobbins wrote: post #220

A straight road, in dry conditions, obstructed by an entire person and a bicycle with REFLECTORS on it, and the car doesn't see her? I think whoever wrote this code should be in prison, quite honestly, along with their entire management chain. I suspect many people will feel the same way. This is a really really bad look for automated vehicles in general. It also backs up my contention that anything less than full 10…

I don't see any reflectors in the video. The wheels and something in the vicinity of the handlebars are the brightest objects I see.

Re: Tempe Police Release Video of Uber Accident

#415

Post by zerostar07 » Thu, Mar 22, 2018, 1:25 AM UTC

ajross wrote: post #92

TrainedMonkey wrote: post #53

There was almost a second where the woman was clearly visible and yet the car did not attempt to emergency break. I would not expect the vehicle to safely stop, but it could have definitely slowed down and reduce the energy of the collision. This is not criticism against self-driving tech, I would not expect alert human driver to avoid collision either due to limited reaction time. With technology however, we should…

Do we know the vehicle didn't brake? There's no audio to tell us anything, and a car takes "almost a second" to rock forward on its suspension when reacting to brake input too. FWIW, I think I might see the nose bobbing a bit just before the collision, but honestly can't tell. I certainly don't think you can say "did not attempt to brake" based on the evidence at hand, basically.

from the interior view it doesnt look like the car braked abrubtly

Re: Tempe Police Release Video of Uber Accident

#416

Post by chrsstrm » Thu, Mar 22, 2018, 1:25 AM UTC

maxerickson wrote: post #105

chrsstrm wrote: post #16

The description given before the video was released painted a picture in my mind that the woman was on the median and "suddenly" entered the roadway in front of the vehicle. I pictured someone darting across the road directly in front of the car, with no way to stop in time. This video shows a completely different scenario. The woman started on the median, but the vehicle was in the #2 lane. She wasn't visible to the…

I think this seems like exactly the scenario that autonomous driving vehicles are intended to prevent. may be optimistic. Lots of people are hoping they will prevent such scenarios, the motivation for fielding them is more related to making lots of money.

Go to [0] and [1] and count how many times they use the word "safe." We're not hoping autonomous vehicles are safer, we're being sold on them as the safer alternative. So yes, this type of close call situation is exactly where these vehicles are supposed to be superior.

[0] https://waymo.com/

[1] https://www.uber.com/info/atg/

Re: Tempe Police Release Video of Uber Accident

#417

Post by sitkack » Thu, Mar 22, 2018, 1:25 AM UTC

fudged71 wrote: post #251

I do wonder if perhaps Uber made the video darker before releasing. Or used a camera that is not the main sensing camera. Because I would hope the cars are smart enough to increase ISO to get more detail at night time.

1) It does NOT show what the LIDAR sees.

2) They should be using a dark adapted / night vision camera and probably are, the video feed presented is just that, the best one that "presents".

3) They should be using thermal infrared to spot living things

4) They were severely over driving their headlights if what we are seeing is "reality" as seen by the onboard computer.

I want to know how much access to the hardware Uber had after the accident, including physical and remote. I also want to see the streaming logs and full provenance.

Re: Tempe Police Release Video of Uber Accident

#418

Post by pdonis » Thu, Mar 22, 2018, 1:26 AM UTC

imh wrote: post #305

pdonis wrote: post #168

Earlier quoted context omitted.

> I have better night vision than this camera, I feel as a human I would have seen the bike. I'm not so sure. Under conditions where there is low light everywhere, so the eye has time to adapt, human low light vision is very good. But under the conditions shown in the video, where there are street lights present and the pedestrian comes out from a gap between the street lights, your eye won't be dark adapted and you…

It's not a function of seeing it the dark, it's that human eyeballs have really good dynamic range, which is exactly why they'd beat cameras in those conditions.

> human eyeballs have really good dynamic range

Not if they're not given time to dark adapt. As I've posted elsewhere in this thread, human vision would still be better than that of a video camera using visible light, but that still wouldn't be very good under variable lighting conditions.

Re: Tempe Police Release Video of Uber Accident

#419

Post by vlozko » Thu, Mar 22, 2018, 1:27 AM UTC

munk-a wrote: post #288

atonse wrote: post #25

How did LIDAR and IR not catch that? That seems like a pretty serious problem. It's clear from the video that a human driver actually would've had more trouble since the pedestrian showed up in the field of view right before the collision, yet that's in the visible spectrum. When I argue for automated driving (as a casual observer), I tell people about exactly this sort of stuff (a computer can look in 20 places at t…

It strikes me as extremely disingenuous if this is all Uber gave to the police. They should be making as much raw data as possible available. At the very least it'd let other companies test their AIs against the scenario and see if they would catch sight of and be able to avoid the pedestrian, if not then this is one more data point to train them on so it doesn't happen again.

The NTSB is also involved and I’m sure they’ll have more than than video to go by.

Re: Tempe Police Release Video of Uber Accident

#420

Post by acdha » Thu, Mar 22, 2018, 1:27 AM UTC

mehrdadn wrote: post #339

blurbleblurble wrote: post #273

Earlier quoted context omitted.

I wouldn't be one bit surprised. The antics of this company are well known. This incident has my wondering: of all the companies working on this, why is Uber trusted to be testing this technology?

> I wouldn't be one bit surprised. The antics of this company are well known. I would be surprised under the new CEO.

Culture takes time to change and we don’t know how hard they’re trying. A new CEO matters long-term but lower level management matters more in the short-term.