Tempe Police Release Video of Uber Accident • Hacker News Board

Re: Tempe Police Release Video of Uber Accident

#451

Post by cozzyd » Thu, Mar 22, 2018, 1:41 AM UTC

mehrdadn wrote: post #347

StavrosK wrote: post #329

Earlier quoted context omitted.

The cars don't have to increase ISO to get detail, that's for human eyes. Increasing ISO only works because we can't see details in shadows, but computers don't have that limitation. A neural network wouldn't have to add 100 to each pixel to make out detail, like a human would.

> The cars don't have to increase ISO to get detail, that's for human eyes. Increasing ISO only works because we can't see details in shadows, but computers don't have that limitation. A neural network wouldn't have to add 100 to each pixel to make out detail, like a human would. I'm not an expert on this stuff but I think you're misunderstanding or mixing up the ISO value with exposure compensation. The ISO value co…

Yes, the ISO is the amplifier gain, essentially.

Re: Tempe Police Release Video of Uber Accident

#452

Post by jonthepirate » Thu, Mar 22, 2018, 1:42 AM UTC

Does anybody really think its a good idea for Lyft, Uber, Tesla etc to develop safety systems for the open roads separately in isolation? Who benefits from that?!

I'll bet a Tesla would not have run this person over. This is where the Government should step in and force all of these AV manufacturers to implement a common safety system / protocol.

Re: Tempe Police Release Video of Uber Accident

#453

Post by solresident » Thu, Mar 22, 2018, 1:43 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…

The bike --rofl

Re: Tempe Police Release Video of Uber Accident

#454

Post by seanmcdirmid » Thu, Mar 22, 2018, 1:44 AM UTC

niftich wrote: post #243

pdonis wrote: post #136

Earlier quoted context omitted.

> The gap between street lights (and hence the person) was in the field of view of the camera the entire time But the gap between street lights is going to be very hard to see into. > I'm confident my eyes are good enough that I would have been able to see this person at night in these lighting conditions. I think you're overconfident. Human low light vision is very good if there is low light everywhere. But it is no…

FWIW the spot where the crash happened is in fact badly lit. I know this anecdotally from having been at the location for events -- it's right next to a concert venue -- but it can also be seen on other dashcam videos. In this video [1] driving northbound, same as the vehicle in the crash, the car first goes under AZ-202, emerges under a streetlight, goes through a darker spot, then another streetlight (as you see th…

Is Tempe like Tucson in explicitly aiming for low light pollution? It does make for some nice star gazing.

Re: Tempe Police Release Video of Uber Accident

#455

Post by cozzyd » Thu, Mar 22, 2018, 1:44 AM UTC

Balgair wrote: post #399

cozzyd wrote: post #342

Earlier quoted context omitted.

I suspect the raw output of their main sensing sensors is proprietary somehow.

Doubtful. There's no way they are making the CCDs/MOSFETS/etc. themselves, you'd need a heck of a chip fab and for almost no increase in usability. Most chips these days are very good at what they do. The main issue is what kind of sensor are they using. However, based on the compression that twitter is using to send you the video, we really don't have any way of knowing what the sensor is (bit-depth, frame-rate, dwe…

I don't mean they made their own CCD chips, (and I guess I didn't mean raw like what the voltages are at the digitizer), but the configuration and pre-processing prior to being fed into their algorithm probably is considered valuable enough that they wouldn't want to publicly display it.

Re: Tempe Police Release Video of Uber Accident

#456

Post by nickpsecurity » Thu, Mar 22, 2018, 1:45 AM UTC

ars wrote: post #74

Direct link: https://twitter.com/TempePolice/status/976585098542833664 The interior view tells you everything you need to know about why anything except perfection in self driving cars will lead to more accidents. The driver specially selected and trained for exactly this job, does not look at the road! If someone specially trained for that won't do it, the general public certainly will not. Also, in the video you ca…

The article below predicted a scenario much like this one. It made a point that putting a computer in control that works really well on average will make humans reaction worse in general and especially if it's a weird, emergency situation happening right as their attention is kicking in.

https://www.theguardian.com/technology/2016/oct/11/crash-how...

Re: Tempe Police Release Video of Uber Accident

#457

Post by kozikow » Thu, Mar 22, 2018, 1:45 AM UTC

The way I see it is that this fatality was a calculated risk for Uber. Uber realizes how much Waymo is ahead of them and decides to drop too many safety restraints in development of the self-driving technology.

The fatality is likely not cause big direct loses to Uber. Any safety regulations coming out of the result are going to hit Waymo just as much as Uber, slow them down and give uber time to catch up. Any financial fine would be tiny comparing to total money invested in self driving technology.

Re: Tempe Police Release Video of Uber Accident

#458

Post by JBlue42 » Thu, Mar 22, 2018, 1:45 AM UTC

niftich wrote: post #243

pdonis wrote: post #136

Earlier quoted context omitted.

> The gap between street lights (and hence the person) was in the field of view of the camera the entire time But the gap between street lights is going to be very hard to see into. > I'm confident my eyes are good enough that I would have been able to see this person at night in these lighting conditions. I think you're overconfident. Human low light vision is very good if there is low light everywhere. But it is no…

FWIW the spot where the crash happened is in fact badly lit. I know this anecdotally from having been at the location for events -- it's right next to a concert venue -- but it can also be seen on other dashcam videos. In this video [1] driving northbound, same as the vehicle in the crash, the car first goes under AZ-202, emerges under a streetlight, goes through a darker spot, then another streetlight (as you see th…

Thanks for the links.

Everyone is moaning and slicing and dicing what the self-driving vehicle did wrong but, since you're familiar with the area: are pedestrians typically expected to be crossing this road?

Seems like the accident has a lot of factors that might not only be the self-driving car's fault, nor even a human driver that was fully in control. Regardless of how well people may want self-driving cars to do, one thing that can actually exist in the present is to make sure that we are creating safe ways for pedestrians to cross a road.

Re: Tempe Police Release Video of Uber Accident

#459

Post by seanmcdirmid » Thu, Mar 22, 2018, 1:45 AM UTC

hcknwscommenter wrote: post #154

pdonis wrote: post #136

Earlier quoted context omitted.

> The gap between street lights (and hence the person) was in the field of view of the camera the entire time But the gap between street lights is going to be very hard to see into. > I'm confident my eyes are good enough that I would have been able to see this person at night in these lighting conditions. I think you're overconfident. Human low light vision is very good if there is low light everywhere. But it is no…

> But the gap between street lights is going to be very hard to see into. This wholly contradicts my experience driving at night on a street with street lights. I can't recall a time in my entire life I have had significant difficulty seeing into the gap between street lights. Keep in mind that the gap is not arbitrarily chosen. Edited to note that I have experienced difficulties in low-vis conditions such as snow st…

If Tempe is like Tuscon, they are using different kinds of street lighting from the rest of the country to minimize light pollution for star gazing reasons.

Re: Tempe Police Release Video of Uber Accident

#460

Post by vadimberman » Thu, Mar 22, 2018, 1:46 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…

In addition to that, even if we were limited to the "last moment", there was about half a second or a second time to react. Correct me if I'm wrong, but that should be enough for the car to at least try something.

Isn't the car supposed to brake to minimise the collision, if the swerving is too dangerous (and it wasn't in this case, as the road wasn't too busy)?