The real problem here is not that the tech is imperfect, I'd actually expect it to be imperfect given it's not been even a decade for this tech. The real problem is that this imperfect tech is on public roads. How do they even get the permission to test drive on public roads?
Tempe Police Release Video of Uber Accident
941–950 of 1001 posts
Re: Tempe Police Release Video of Uber Accident
#942It appears that UBER may have disabled/overridden Volvo's built-in safety platform, "City Safety". City safety automatically brakes for obstructions, up to 50MPH.
https://www.youtube.com/watch?v=gcqktnqlf10&feature=youtu.be...
https://support.volvocars.com/en-CA/cars/Pages/owners-manual...
Re: Tempe Police Release Video of Uber Accident
#943Why are safety drivers not: - working in pairs, so there is social pressure, conversation, and two pairs of eyes to increase alertness and safety? - doing shifts of 30 - 45 minutes at most [1] (although they could potentially swap back and forth with a co-driver) - issued a dumb-phone for emergencies and searched for entertainment devices (it's good enough for Amazon warehouse staff) - being monitored by the driver-f…
I think these are sensible approaches to try and mitigate the problem.
Still, I'm not sure this is a problem that can be effectively mitigated. I've been _extremely_ suspicious of any AV system that requires a human to be attentive, alert, and ready to take over at a moment's notice.
Humans are just _so bad_ at that kind of task. Since we're apparently making people do that job anyway, I'm all for the mitigations you've outlined. But I think it's absolutely crazy that we have humans doing a job that we're just _really really_ bad at, and then making that the critical safety element of the testing.
Re: Tempe Police Release Video of Uber Accident
#944Earlier quoted context omitted.
I wonder if the moon phase or clouds had anything to do with the lighting conditions.
Don't know why this is being downvoted, it's an interesting point. There's a significant difference in lighting between a night with a clear sky and full moon versus an overcast night and new moon. Not saying that's the case here, but it's not a valueless comment.
My guess would be because there’s already been pictures shown that show the street has pretty good street lamps.
Re: Tempe Police Release Video of Uber Accident
#945It looks to me that the car's lights are too low. Probably if you are not 100% driving you don't feel like you need to adjust the lights.
Re: Tempe Police Release Video of Uber Accident
#946Earlier quoted context omitted.
> there is no such thing as a too reflective vest for bicyclists And to not jaywalk a bike across a street in the dark!
Since I've seen this be a very controversial statement here in the past, I'd just like to point out to everyone that American drivers on four lane roads are not expecting pedestrians to be in the middle of the road and not at a crosswalk. That is not a normal thing to happen in America, and no one expects it to happen. It is a very rare situation. --edit: okay guys... no where did anyone argue that you shouldn't be w…
Do you realize how much of a sociopath you sound like? A person died.
Re: Tempe Police Release Video of Uber Accident
#947Earlier quoted context omitted.
> You'd have to see someone crossing the road like that. You could say the same thing about a car with headlights on coming towards you... From the little evidence we have it seems like the pedestrian, driver/monitor and the car all should have done better.
It is not uncommon for pedestrian to notice in coming traffic, and still cross the road, in the expectation that the car ll just slow down for them to cross..A human driver, without exception, will slow down in this case. Sadly the same thing might have happened here. The lady took one look before crossing, and expected the car to slow down..
> It is not uncommon for pedestrian to notice in coming traffic, and still cross the road, in the expectation that the car ll just slow down for them to cross..
Where do you live because I never see this. That is just asking to get hit by a car.
> A human driver, without exception, will slow down in this case.
Goverment statistics show this is clearly not the case: https://crashstats.nhtsa.dot.gov/Api/Public/ViewPublication/...
Re: Tempe Police Release Video of Uber Accident
#948Earlier quoted context omitted.
Indeed! To LIDAR, she was basically standing in the lane, with a bulky bicycle. To visible light, including the driver, who was apparently half asleep or watching the dashboard, she was in shadow until just before the collision. So yes, LIDAR should have caught this. Easily. So something was clearly misconfigured. And even if the driver had been carefully watching the road, he probably wouldn't have seen her in time.…
Probably the LIDAR did catch it. Probably the algorithm (neural network) that takes in LIDAR data and outputs whether there is a object in front failed or gave a really low probability which was less than the threshold specified. This happens all the time with deep neural networks. In any case technology is to blame and self driving should be banned until these issues are resolved.
> self driving should be banned until these issues are resolved
_Ubers'_ self driving trials should be banned since they don't seem to exercise enough caution. That shouldn't hold the progress of competitors back.
Re: Tempe Police Release Video of Uber Accident
#949One thing that I haven't seen a whole lot of commenting on is how distracted the safety driver appears to be in the interior shots. He looks bored, and his attention seems to be directed everywhere but the roadway.
This raises some serious concerns about the extent to which "safety drivers" actually increase the safety of self-driving car tests. If that's how they normally behave when a car's in self-driving mode, then it seems to me more like they are creating a false sense of security that mostly just serves to make the public feel better about the risk of half-baked self-driving equipment being tested on the public roadways.
Re: Tempe Police Release Video of Uber Accident
#950How 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…
Regarding how the LIDAR did not catch that, there are 4 possibilities I can think of: 1. A software bug failed to recognize the obstacles, or misclassified them, or it fell below some probability threshold. 2. LIDAR didn’t work at the time, and the car did not shutdown. 3. The victim‘s clothing absorbs the LIDAR‘s wavelength pretty much completely, such that it appeared as a „black hole“ and was ignored by the algori…
Another option (related to your #1) could be disagreement between the visual field cameras and the LIDAR. Which could result in a lower confidence of an object being a pedestrian.