Tempe Police Release Video of Uber Accident • Hacker News Board

Re: Tempe Police Release Video of Uber Accident

#721

Post by 6841iam » Thu, Mar 22, 2018, 5:40 AM UTC

sydd wrote: post #267

jeffmould wrote: post #135

Earlier quoted context omitted.

I have to agree. Just like a normal camera has issues in low-light, it is clear that this camera is diminishing exactly how light the road ahead was. While I can't say confidently that I would have been able to stop to prevent hitting them, watching the video in full screen does lead me to believe that I would have seen them and been able to apply the brakes at least enough to reduce the impact. Also, watching the vi…

The footage from a normal camera should not matter, a self driving car is equipped with stuff that works regardless of light conditions like LIDAR oor IR cameras. This looks to me like a software failure.

why havent they released the Infra Red footage? that will be less deceiving

Re: Tempe Police Release Video of Uber Accident

#722

Post by Scoundreller » Thu, Mar 22, 2018, 5:40 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…

And this is why I have retroreflective tape on my bike’s forks. It’s legally required while riding at night too.

Re: Tempe Police Release Video of Uber Accident

#723

Post by zachrip » Thu, Mar 22, 2018, 5:41 AM UTC

aecs99 wrote: post #712

noobermin wrote: post #707

Earlier quoted context omitted.

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?

I have the same questions as well. But my best guess is that they probably have permission to drive at non-highway speeds at late nights/early mornings (which is when this accident occurred, at 10 PM). My first reaction when I watched that video was that my Subaru with EyeSight+RADAR would have stopped/swerved. Even the news articles state something similar (from this article: https://www.forbes.com/sites/samabuelsam…

I live here and they drive around at all times of the day and don't seem to have any limitations. They've been extremely prevalent and increasing in frequency over the past year. In fact, it's unusual _not_ to see them on my morning commute.

Re: Tempe Police Release Video of Uber Accident

#724

Post by Scoundreller » Thu, Mar 22, 2018, 5:44 AM UTC

walrus01 wrote: post #356

jeffmould wrote: post #135

Earlier quoted context omitted.

I have to agree. Just like a normal camera has issues in low-light, it is clear that this camera is diminishing exactly how light the road ahead was. While I can't say confidently that I would have been able to stop to prevent hitting them, watching the video in full screen does lead me to believe that I would have seen them and been able to apply the brakes at least enough to reduce the impact. Also, watching the vi…

This is pretty much the experience I have with my dash cam, a Yi. In its recorded video, its automatic exposure control make it look like everything outside of the headline cone is pitch black, but it is actually not. I have seen deer and possums by the side of the road, and debris etc, that did not show up when I later checked the video for the same period. There is enough spillover light from modern headlights that…

IR can help with that. Headlights are limited by the disincentive of blinding oncoming drivers...

Now that I think about it, self driving cars may be paralyzed by other self driving cars running IR boosted headlights.

Re: Tempe Police Release Video of Uber Accident

#725

Post by gowld » Thu, Mar 22, 2018, 5:46 AM UTC

Focusing on the car-automation and driver may be missing the point in this scenario.

@jedweeks: Nearly 2 miles between crosswalks, that's why. Street was designed to kill pedestrians.

Re: Tempe Police Release Video of Uber Accident

#726

Post by vinniejames » Thu, Mar 22, 2018, 5:46 AM UTC

I'm more than a little disappointed to see the victim walked all the way across the left-side lane, unnoticed, before being struck. While the monitor appeared to be more interested in her phone, or whatever she was continually looking down at, instead of keeping an eye on the road and vehicle performance which I imagine was what she was being payed to do

Re: Tempe Police Release Video of Uber Accident

#727

Post by triggercut » Thu, Mar 22, 2018, 5:48 AM UTC

There are a lot of questions around the vision side of this, but I have slightly different question, the answer which probably points to greater systemic issue in the overall solution.

Why is a car, the speed of which is regulated by the autonomous driving system, breaking the legal speed limit?

Even accounting for errors/accuracy of odometers/speed cameras, this car was traveling at a speed in excess of the legal speed limit for that section of road, increasing both all the underlying risks of operating a 1-2t motor vehicle at 60+km/hr, and the material impacts from those risks.

In a relatively new technology, why is the decision to trade safety for speed being made?

In any technology where safety (and ultimately human life) is concerned, why are we testing in production?

Re: Tempe Police Release Video of Uber Accident

#728

Post by vowelless » Thu, Mar 22, 2018, 5:50 AM UTC

schreiaj wrote: post #651

Animats wrote: post #496

Earlier quoted context omitted.

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…

LIDAR also has limitations on angular resolution just as a function of how the sensor works. It's entirely possible that the size of the person/bike on LIDAR was just too small until it was too late to stop. Why it didn't even appear to try to stop? You got me, refresh rate on the LIDAR? LIDAR flat out being mounted to high and relying on optical sensors instead for collision avoidance of small targets (like a human…

> LIDAR also has limitations on angular resolution just as a function of how the sensor works. It's entirely possible that the size of the person/bike on LIDAR was just too small until it was too late to stop.

I highly doubt this is the issue. I am not sure what Ubers setup is, but even a standard velodyne should have been able to pick that up based on angular resolution.

Re: Tempe Police Release Video of Uber Accident

#729

Post by gowld » Thu, Mar 22, 2018, 5:50 AM UTC

Twisell wrote: post #593

jackpirate wrote: post #78

Earlier quoted context omitted.

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. That's not at all clear to me. I don't know too much about cameras, but it looks to me like the camera is making the scene appear much darker than it actually is. In the video, you can see many street lights projecting down…

Also even if the camera was perfectly accurate about human field of view, no human driver in his right mind would drive so fast with such a poor visibility. Any judge would qualify this as reckless driving. So either way the software failed: -If AI misjudged Lidar information and didn’t compute the slow moving pedestrian it’s a fail -If it didn’t have enough computer vision space it should have slowed down Possibly i…

Is a driver ever at fault when a pedestrian is in the road at night without a crosswalk nor lights nor reflective gear?

Re: Tempe Police Release Video of Uber Accident

#730

Post by austenallred » Thu, Mar 22, 2018, 5:54 AM UTC

dfee wrote: post #696

What no one seems to be talking about is that a person was walking their bike across a divided 4 lane road that in many places would be called a highway. This is not a pedestrian friendly crosswalk, and it’s not high noon. You can tell by the tail lights of the car in front (first second of video) that a pedestrian would be able to see a car coming. Which begs the question - why did the human step out in front of the…

I think we could all agree that:

1. The pedestrian should not have been there

2. The car should not have hit/killed him/her.

Those points needn't be mutually exclusive.