Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Tempe Police Release Video of Uber Accident

twitter.com

Post reply on HN
Print view View original

771–780 of 1001 posts

Re: Tempe Police Release Video of Uber Accident

#771

Post by confiscate »

itronitron wrote: post #425
confiscate wrote: post #185

Wow, the pedestrian just walked onto the road without so much of a glance at the direction of incoming cars. Sure, it's the car's responsibility to stop. But still--it's almost like the pedestrian didn't care at all. She never saw the car throughout the entire incident. She never saw it coming. She didn't cared to.

it's almost as if she has done this many times before and never been hit by cars being driven by real people

yes, that's why she should keep doing it and not expect anything to ever happen! Who cares? Not her. She doesn't care.

Re: Tempe Police Release Video of Uber Accident

#772

Post by Tossrock »

tbabb wrote: post #556
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…

IIRC IR is ITAR controlled and not available above abysmal resolution. I am curious if this limitation applies to self-driving cars, too. If so, then it's really time to do what was done for GPS and declassify it for use by the general public. It's a public safety/public good issue.

You can get 320x240 60hz for $2000 as a consumer[1]. On the one hand I wonder what kind of resolution the military grade version is, but I also wonder if the bandwidth/dollar is actually better. I imagine Raytheon basically just makes up a number when they're setting the price of a helicopter gun cam.

[1]: eg https://www.amazon.com/FLIR-Systems-III-320-Thermal-Detector...

Re: Tempe Police Release Video of Uber Accident

#773

Post by bambax »

Animats wrote: post #496
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…

How did LIDAR and IR (?) not catch that? That seems like a pretty serious problem. Something is badly wrong there. That should have been detected by LIDAR, radar, and vision. Yes, they need a wide dynamic range camera for night driving, but such things exist.[1][2] They're available as low-end dashcams; it's not expensive military night vision technology. Radar should pick up a bicycle at that range. The old Eaton VO…

Probably the only explanation was that LIDAR was off, either on purpose (for testing?) or because it broke and there was no safety mechanism to prevent the car from operating if/when LIDAR is off.

Re: Tempe Police Release Video of Uber Accident

#774

Post by noobermin »

hiisukun wrote: post #769

Since I didn't find it in a Ctrl+F, I'll chime in to say that one of the advantages of self-driving cars is the scrutiny that accidents will come under, and how the results of that investigation can improve the driving of all other self-driving cars. While many fatal car accidents are scrutinized to an appropriate level throughout the various countries across the world, many are not. And when they are examined in det…

Your reasoning sounds a lot like the broken window fallacy.

Re: Tempe Police Release Video of Uber Accident

#775

Post by usgroup »

hiisukun wrote: post #769

Since I didn't find it in a Ctrl+F, I'll chime in to say that one of the advantages of self-driving cars is the scrutiny that accidents will come under, and how the results of that investigation can improve the driving of all other self-driving cars. While many fatal car accidents are scrutinized to an appropriate level throughout the various countries across the world, many are not. And when they are examined in det…

Typically models don’t work like that... i.e changing the model or its training alters it’s behaviour generally and needs to be tested against its overall performance. So whilst crash data may go toward a dataset which is then used to better evaluate or train different aspects of a system, it has none of the luster of the learning from every accident being maximised.

The human mind is a quite unique in its ability to decide where one model stops and another one starts.

Re: Tempe Police Release Video of Uber Accident

#776

Post by InclinedPlane »

noobermin wrote: post #707
aecs99 wrote: post #700

I currently work full-time in the self-driving vehicle industry. I am part of a team that builds perception algorithms for autonomous navigation. I have been working exclusively with LiDAR systems for over 1.5 years. Like a lot of folks here, my first question was: "How did the LiDAR not spot this?". I have been extremely interested in this and kept observing images and videos from Uber to understand what could be th…

Alright, so given your observations, which I don't doubt, here's a question I have: why have a pilot on public roads? If uber's software wasn't robust, why "test in production" when production could kill people?

Because Uber wanted that.

Other self-driving car companies (like Google (or whatever they renamed it)) have put a lot more work into their systems and done a much greater degree of due diligence in proving their systems are safe enough to drive on public roads. Uber has not, which is why they've been kicked out of several cities where they were trying to run tests. But Tempe and Arizona is practically a lawless wasteland in this regard and is willing to let Uber run amok on their roads in the hopes that it'll help out the city financially somehow.

Re: Tempe Police Release Video of Uber Accident

#777

Post by jakeogh »

ajross wrote: post #590
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.

You can't increase ISO without washing out the areas in the street lights. One of the difficulties not being discussed here is that this is a terribly lit road, with large dark voids between the street lights. And the biker was crossing in the void.

Street lighting is a side issue, and the lack of street lighting is AZ is a feature. It's awesome, I get to keep my night vision, and we have the stars:) Making things worse to accommodate confusion about what computers are capable of is a bad idea, and the correct sensors don't care anyway.

http://darksky.org

Re: Tempe Police Release Video of Uber Accident

#778

Post by askvictor »

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…

Indeed; I'm wondering why the police were so fast to say that the woman suddenly entered to road, when the video shows this clearly isn't the case.

Re: Tempe Police Release Video of Uber Accident

#779

Post by martin_bech »

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…

Im conviced 99-100% that the Automatic Emergency Brakeing (AEB) on my Tesla would have braked for that. The promise of these systems, as you also point out, is that they can see things, humans cant. The "real" cameras on this car (not this dashcam footage), and the LIDAR, should be fine with it beeing near pitch black.

Re: Tempe Police Release Video of Uber Accident

#780

Post by thesumofall »

I really hope this will be looked at professionally and unbiased. The initial statement of the police sounded anything but. If they looked at the same evidence as we do now, it would indicate a severe lack of understanding of the difference between camera pictures and human vision. Plus, who spread the rumor on the very first day that the victim was a homeless person? What does that have to do with anything?
Post reply on HN