Live data from Hacker News

Tempe Police Release Video of Uber Accident

twitter.com

141–150 of 1001 posts

Re: Tempe Police Release Video of Uber Accident

#141
post #92

There was almost a second where the woman was clearly visible and yet the car did not attempt to emergency break. I would not expect the vehicle to safely stop, but it could have definitely slowed down and reduce the energy of the collision. This is not criticism against self-driving tech, I would not expect alert human driver to avoid collision either due to limited reaction time. With technology however, we should…

Do we know the vehicle didn't brake? There's no audio to tell us anything, and a car takes "almost a second" to rock forward on its suspension when reacting to brake input too. FWIW, I think I might see the nose bobbing a bit just before the collision, but honestly can't tell. I certainly don't think you can say "did not attempt to brake" based on the evidence at hand, basically.

Yes, that was in the original announcement

Re: Tempe Police Release Video of Uber Accident

#143
post #33

I sure couldn't have reacted quickly enough to have prevented this collision. I'd expect the car to have better reflexes then I do, but given the little time from when the pedestrian first showed up on camera and the time when the collision occurred, I doubt that there was anything that the car could have done, regardless of the sophistication of its software.

An autonomous vehicle obviously shouldn't exceed a speed where it's stopping distance exceeds it's vision capabilities, since next time it might as well be a tree trunk. That's sometimes difficult for humans to gauge, but then we want autonomous cars so they can make these calculations (and they are much better equipped to).

That’s a good point. But in this situation I think we’d probably find that the driver wasn’t at fault.

Re: Tempe Police Release Video of Uber Accident

#144

The description given before the video was released painted a picture in my mind that the woman was on the median and "suddenly" entered the roadway in front of the vehicle. I pictured someone darting across the road directly in front of the car, with no way to stop in time. This video shows a completely different scenario. The woman started on the median, but the vehicle was in the #2 lane. She wasn't visible to the…

I would expect most autonomous systems to extrapolate the movements of anything in the vicinity and check whether it's going to cross paths with the vehicle. I would speculate that LIDAR (or whatever systems they use for object detection) simply failed to detect her.

Re: Tempe Police Release Video of Uber Accident

#145
post #62

Is it me or the street lighting is beyond mediocre? It is weak and alternate between a "lighted" portion and a literally black portion. But even then, the driver was busy with his cellphone. The accident might have happened nevertheless due to bad lighting. But this could have been avoided was the driver on alert.

The video makes the lighting look bad but most street lighting is very partial. When I drive home in the city—admittedly at somwhat lower speeds—the lighting is very patchy and all sorts of idiots in dark clothing are farting into traffic on foot and bikes. Lots of students. I pretty much expect people to be in the street but admittedly it’s a congested area compared to this.

Re: Tempe Police Release Video of Uber Accident

#147

An alert human driver would still have had a bad crash, but might not have killed the pedestrian. In a two-lane road, you cannot simply swerve to the other lane w/out checking. I (and many other?) drivers would have just slammed on the brakes. But at that road's speed limit, I believe the brakes wouldn't have stopped in time, and a collision would still have occurred. The pedestrian+bicycle was a direct obstacle, not…

Although a collision may still have occurred if a human slammed on the brakes immediately after seeing the pedestrian, even a 10mph slowdown may have mitigated the fatality into a minor injury. ProPublica has a graph showing the frequency of fatalities in crashes for different impact speeds, showing a more than halving in the occurrence of fatalities in crashes between 38mph and 28mph impacts: https://www.propublica.org/article/unsafe-at-many-speeds

The article says that the vehicle "doesn’t appear to slow down". If the data shows that it actually didn't slow down, it seems like there is a critical bug in Uber's software that has killed a pedestrian.

Re: Tempe Police Release Video of Uber Accident

#148
post #128

Is the video slowed down? Also they need to release a better quality. If I was behind that wheel, I don't think I would've seen that lady to be quite honest. The place where the lady was crossing the road was under a shadow of nearby trees or buildings. If one is going to cross a road like this, they should at least use a well lit part of the road. Also, why did she have her back turned to the traffic if she is jaywa…

1) I wouldn't be surprised if that is the "best quality" they have.

2) I also suspect that human eyeballs would have a different view of the light/dark portions of what's depicted there, and especially eyeballs would have probably had a much higher chance of detecting movement in peripheral vision than that video gives any hint of.

Re: Tempe Police Release Video of Uber Accident

#149

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 driver looked up a few seconds before the accident, though and didn't seem to notice anything on the road.

Re: Tempe Police Release Video of Uber Accident

#150

I feel like a human would've been able to at least brake a little or swerve in this situation? Not avoiding the collision but perhaps lessening the damage? It looks like the car doesn't even try to slow down.

How can you tell that from a dash cam video?
Post reply on HN