Tempe Police Release Video of Uber Accident • Hacker News Board

Re: Tempe Police Release Video of Uber Accident

#481

Post by kappi » Thu, Mar 22, 2018, 1:53 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…

check the below article and embedded video, talks about the Uber ADAS https://www.buzzfeed.com/nicolenguyen/not-too-fast-not-too-f...

Re: Tempe Police Release Video of Uber Accident

#482

Post by cjensen » Thu, Mar 22, 2018, 1:53 AM UTC

Driver was obviously on cell phone.

Since this is still in development, Uber should have assumed that the self driving software would fail unexpectedly.

If a human sees something work 1000 times, they will expect it to work every time. Uber should have anticipated overconfidence in the software. They should have coached the driver on this. They should have reviewed footage of safety drivers to ensure that safety drivers are complying with instruction.

This was not an accident. This was carelessness. I blame Uber. Uber's "just get it done" cultural attitude is incompatible with developing safe self-driving software. There's a reason that Google, with 10X the number of miles on the road, have not killed anyone.

Re: Tempe Police Release Video of Uber Accident

#483

Post by buvanshak » Thu, Mar 22, 2018, 1:53 AM UTC

jeffmould wrote: post #135

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…

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…

> clear the driver was looking at his phone or doing something ...

Seriously, what else can you expect. These companies who do put these things on the road with the justification that "There is a human behind the wheel" should be taken out back and shot in the head...Just pull the plug. No more self driving cars for them. Those are just the kind of tech companies we don't want around...

See, it is not a mistake that they are making. They know well enough that this human behind this wheel is a useless as a dummy. But they do it any way. What does it say about them?

Re: Tempe Police Release Video of Uber Accident

#484

Post by neom » Thu, Mar 22, 2018, 1:54 AM UTC

For reference, here is a marketing video of Ford self driving at night: https://www.washingtonpost.com/video/business/technology/pro...

Re: Tempe Police Release Video of Uber Accident

#485

Post by throwaway010718 » Thu, Mar 22, 2018, 1:54 AM UTC

mehrdadn wrote: post #332

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…

> apply the brakes Or swerve out of the way.

Or flick your high beams, quick beeps, adjust speed... I do all these things if I see anything on a collision course with my vehicle.

It is surprising to learn that these vehicles are operating at night. To collect training data, since nighttime driving is inevitable, perhaps there are ways to simulate night to the computer vision systems during daytime so the human supervisor can still see clearly.

Re: Tempe Police Release Video of Uber Accident

#486

Post by URSpider94 » Thu, Mar 22, 2018, 1:55 AM UTC

dylan-m wrote: post #387

This is such a blatant attempt to manipulate public opinion before the actual data appears. Even if Uber's software is ridiculously using visible light for its decision-making, it should definitely be taking into account what it doesn't know. A system like this should not be guessing. There is a giant swath of black in the video; the camera doesn't know what's there. So, the car should be moving so it has a short eno…

The police department released the video, not Uber.

Re: Tempe Police Release Video of Uber Accident

#487

Post by JshWright » Thu, Mar 22, 2018, 1:58 AM UTC

TylerE wrote: post #444

sitkack wrote: post #417

Earlier quoted context omitted.

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 U…

It's Arizona. I just checked. The high today was 92F. Pavement would almost certainly be warmer than that. How's a thermal camera supposed to detect 98F on a background that is proably +/- 5 degrees of that?

Thermal cameras care about more than just the absolute temperature of an object. The emissive and reflective properties of the material (in infrared) also matter significantly. A human being would almost certainly be visible in a thermal imaging view of that scene.

When you walk outside in the daytime, everything is bathed in a uniform light from the sun, but you have no trouble distinguishing between objects, as they emit and reflect light differently.

Re: Tempe Police Release Video of Uber Accident

#488

Post by seanmcdirmid » Thu, Mar 22, 2018, 1:58 AM UTC

adamweld wrote: post #411

maxerickson wrote: post #105

Earlier quoted context omitted.

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 driv…

If you turn your headlights off on a dark country road, your sight capabilities actually go up, not down. The problem is: most roads are lit or you st least have to compete with other headlights, and it would make you harder to see.

Re: Tempe Police Release Video of Uber Accident

#489

Post by grizzles » Thu, Mar 22, 2018, 1:58 AM UTC

It strikes me that a good way to test self driving cars would be to simulate people doing random dangerous things like walking in front of the car and seeing how good the car is at avoiding an accident. Then you give the car less and less time to see how well it can eg. respond to a giant mannequin being thrown in front of it.

Following that train of thought, an accident like this could have been caused by fear of corporate liability.

Because you would eventually have to set some threshold where the car would not respond to an errant pedestrian for the safety of the occupants. Especially in wet weather. A good lawyer could argue that is when the car software decided to kill the pedestrian. So, Uber's AV team might have just said "she was jaywalking" to avoid writing code that dealt with situations outside of the rules of the road because it might in the future look controversial, even if the addition of that code may have the effect of sparing more lives than it takes.

Re: Tempe Police Release Video of Uber Accident

#490

Post by darklajid » Thu, Mar 22, 2018, 2:00 AM UTC

ineedasername wrote: post #292

jerf wrote: post #197

Earlier quoted context omitted.

"The driver specially selected and trained for exactly this job, does not look at the road!" Humans gonna human. Our brains are trained by millions of years to not pay attention to things not directly important. It's hard enough sometimes to keep our attention on the road when we're doing the driving and the driving is too easy, like being alone on a highway at night. Expecting humans to passively observe driving whi…

Yeah, there's that videogame about driving a bus constantly, on an empty road, for hours and hours. It occasionally veers off, so you have to pay attention, but that's all. That game should be a minimum "driving" test for safety drivers. (Not really, but something like that)

Desert Bus. Not quite Twitch stream material..

I agree that it's an apt comparison, except Uber seems a worse experience. In Desert Bus you have to correct the bus.. Stupid work, but something necessary - boring - to do or you fail.

There seems to be nothing at all to do in that Uber?