Live data from Hacker News

Tempe Police Release Video of Uber Accident

twitter.com

81–90 of 1001 posts

Re: Tempe Police Release Video of Uber Accident

#81

She crossed at a spot that was pitch black. Sneakers come into view maybe 40 feet away. Clearly visible at 20. Is that enough time to stop at that speed? Not sure I would have stopped in time.

You don’t need to stop. Slowing from 40 to 30mph decreases the fatality rate by an order of magnitude. Maybe the car shouldn’t have been going above the speed limit if the conditions were so poor that it couldn’t plausibly see humans walking right in front of it.

Re: Tempe Police Release Video of Uber Accident

#82

Two obvious things from the footages: the pedestrian is invisible until the last moment, and the "driver" is focused on something else, probably a smartphone. Given of how little time there was between the hitted woman became visible and the impact, a driver action may not have been able to avoid it, but what will be interesting is how his responsability will be engaged or not. Anyway one advantage of automous car is…

> the pedestrian is invisible until the last moment

In this crappy video, yes. Maybe it was scaled down massively before handing to the police or made darker, we don't know. It might have been visible for a normal person.

Re: Tempe Police Release Video of Uber Accident

#83
That is utterly terrible. The car should have reacted to the pedestrian comfortably. I think something in the change in lighting confused the sensors (the road appears to go from having street lights to not having them at the point of contact).

Re: Tempe Police Release Video of Uber Accident

#84
post #37

However bad the car was or wasn't at detecting the victim, it's nothing compared to how bad the human victim was at detecting the car (which presumably had its lights on coming down an empty street at night). Imagine if the victim was driving a car...

Are these cars electric? They can be pretty quiet, even at high speeds.

Re: Tempe Police Release Video of Uber Accident

#85

Two obvious things from the footages: the pedestrian is invisible until the last moment, and the "driver" is focused on something else, probably a smartphone. Given of how little time there was between the hitted woman became visible and the impact, a driver action may not have been able to avoid it, but what will be interesting is how his responsability will be engaged or not. Anyway one advantage of automous car is…

I believe in reality the pedestrian would have been much more visible than this to a human.

When I watch night videos from my dashcam, they look similar to this but in reality my night vision is much better.

I believe I would have had time to slow down significantly in this situation.

That car supposedly had LIDAR and whatever else, so WTF wasn't it able to at least slow down?

Re: Tempe Police Release Video of Uber Accident

#86
It's incredible how bad the self-driving system failed in this instance; it's clear that any self-driving system (Uber or any other) -including any update/change to its software- should be audited by the government AND all major tech universities (e.g. MIT) before a single one of those cars go into the public streets.

Re: Tempe Police Release Video of Uber Accident

#87
post #40

While I'm surprised the sensors on the car didn't catch the cyclist, I pretty sure if I had been driving and paying full attention I would have hit the bike too. Personally, given this video, I'd still be totally comfortable with a self driving car on the road with no safety driver (who clearly didn't make a difference here anyway, not that they could have).

Yeah, but you don’t operate an automobile by looking at a video display.

Re: Tempe Police Release Video of Uber Accident

#89
post #10

When I cross-reference the lane lines at 0:03 with google maps[1], I get an estimate of the car being about 60ft-70ft away from the victim when I was first able to spot her shoe in the video. Some googling[2] says human reaction at 40mph would've taken 59ft, with an additional 80ft of actual stopping time. This seems in line with the police report that "it would have been difficult to avoid this collision in any kind…

The speed limit is only 35 not 40 on that road unless we're looking at different roads? If the driver is paying attention they could turn the wheel a bit and split the left lane (there doesn't appear to be anyone else on the road) and avoid the person who was half way through the lane at time of impact. Might not clear the person but clipping the back of the bike would certainly be better than a direct impact. You wouldn't even have to jerk the wheel and swerve at such a slow speed and on a dry road with modern tcs even over-correcting is handled by tcs to limit what your input does. Of course all this is just playing arm chair quarterback so who knows if someone including myself would have been able to react in time. More of a thought experiment to how an alternative could have occurred.

I'm curious how the visibility differs between what we see on this camera and what a human actually sees in person.

Re: Tempe Police Release Video of Uber Accident

#90
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…

This is exactly it. I see people mentioning seeing the victim at the last second but these vehicles are supposed to be better. They scan in non visible spectrums with LIDAR. Lack of safety vest, lack of headlights, none of it is supposed to matter... or at least it shouldn't completely compromise the vehicle's systems. Camera's may not work as well but an obstacle directly in the path should still be detected. Especially an obstacle that would reflect LIDAR and give off a very obvious infrared signature.

This video also shows another point I made recently in a conversation. People need stimulus to keep them alert and focused. I don't think it's at all reasonable to expect someone to sit idly with almost no interaction or responsibility and expect them to stay alert. The human brain doesn't function that way.

Post reply on HN