I'm waiting for the 'grassroots' campaign to get every human and dog to wear locator beacons to make them easier to spot by self driving cars.
Maybe Cambridge Analytica is already working up a facebook campaign for it.
Tempe Police Release Video of Uber Accident
881–890 of 1001 posts
Re: Tempe Police Release Video of Uber Accident
#882In my mind this accident is on Uber no matter how you interpret the video. Scenario 1: Lets say the pedestrian was visible to the naked eye and sensors. The model and safety operator still didn't "see" her and act in time. Who to blame? Uber. Scenario 2: The lighting and environment was in a condition where neither the model nor the safety operator could see the road more than 10 feet in front of the car, yet neither…
This.
Many people comment that the lighting is poor and that a human might understand what's happening too late. This is debatable and misses the point: if visibility is bad, you (and it applies with full force to automated drivers) should reduce your speed accordingly, maybe with the exception of freeways where you are not expected to encounter pedestrians.
Re: Tempe Police Release Video of Uber Accident
#883Not to say there isn‘t a problem here... But walking across the street in dark clothes, without any light or reflectors, at a random spot does not seem like the best idea to me. If I have a picknick on the train tracks and get hit by a train, maybe you should consider my stupid decision as well when evaluating the security of trains.
People don't expect trains to avoid them if they step on the rails.
Recently I almost got hit by an electrical scooter. Ambient noise was very low, and I relied on sound alone until very late, and saw it at the very last moment.
I've learned, and I won't rely on sound anymore. If cars occasionally don't react to them, people will learn too, and completely stop jaywalking in unclear situations. It will also cost many lives before everyone has had a chance to adapt.
Re: Tempe Police Release Video of Uber Accident
#884They're trying pretty hard to keep the self-driving sham alive aren't they?
Re: Tempe Police Release Video of Uber Accident
#885How 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…
> 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.
Actually a human driver would be expected to have less visual trouble in this case. People's eyes are far more adaptable to low light conditions than a camera's video. If you've ever tried to take a picture on a visible night using your phone, you've seen this effect.
> 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 the same time, a human can't. a computer can see in the dark, a human can't).
Except that the computer did not do that in this case. This car also uses LIDAR and should have noticed the pedestrian long before the accident occurred.
> Yet this crash proves that all the equipment in the world didn't catch a very obvious obstruction.
Either the sensor equipment or the software was defective, otherwise the pedestrian would have been detected.
Re: Tempe Police Release Video of Uber Accident
#886Something that tickles my brain since yesterday: are their obstacle detection systems active or passive? In other words, do they emit IR to illuminate nearby obstacles or they rather rely exclusively on visible light projectors on board and street lights?
I ask because emitting IR would likely interfere or even blind speed cameras (which use IR themselves to take night photos), so I expect this to be either forbidden or strictly regulated. Which brings me to the question: if it uses IR, and therefore detects it, could a speed camera IR beam, or any other IR device, in vicinity have interfered with that car obstacle detection?
Re: Tempe Police Release Video of Uber Accident
#887The automotive cameras that I have worked on seemed to have a better low-light performance than this video suggests.
Some of the more recent OmniVision focal plane arrays (imagers) are really very good in low light conditions (for the price).
Of course, it is difficult to tell without a side-by-side comparison, but I would have thought that the equipment could/should have been better than this.
Who was the supplier of this camera?
Re: Tempe Police Release Video of Uber Accident
#888Earlier 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…
> it is clear that this camera is diminishing exactly how light the road ahead was Someone else thought the same thing and went to get their own footage of the road. https://www.youtube.com/watch?v=1XOVxSCG8u0
This shows how worrying is autonomous cars in a low-light environment. I suppose LIDAR should be able to pick that up, but sadly it failed miserably.
Re: Tempe Police Release Video of Uber Accident
#889Why did the pedestrian walk into the traffic? She should have seen the car. Probably she got used that the cars stop to let her cross the street.
Re: Tempe Police Release Video of Uber Accident
#890How 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…
Serious question: What is the argument for the need for autonomous driving? I haven't really pushed this question so figured I'd start here.