Live data from Hacker News

Tempe Police Release Video of Uber Accident

twitter.com

11–20 of 1001 posts

Re: Tempe Police Release Video of Uber Accident

#11
post #8

Earlier quoted context omitted.

That’s only because there’s no light on her until the end. The car hardware should have seen her. If it doesn’t work in the dark it shouldn’t be on the road imho.

> That’s only because there’s no light on her until the end. Yes, quiet true. > The car hardware should have seen her. If it doesn’t work in the dark it shouldn’t be on the road imho. I tend to agree. I think unfortunately this video indicates that the car did not perform worse than a human. It's still valuable to have cars that perform better than humans, even if they aren't perfect.

What do you think based on this video:

https://twitter.com/brianawhitney/status/976591851384745984?...

The woman with the bike wasn’t moving fast at all. I dunno...

Re: Tempe Police Release Video of Uber Accident

#12
With all the logged sensor data this should be the best documented fatal collision in history and will be able to be replayed again and again with different software to see if it was avoidable with the current hardware configuration.

Obviously a sad situation, but it's reassuring that the knowledge from one crash can lead to all other autonomous vehicles learning to avoid it in the future.

Re: Tempe Police Release Video of Uber Accident

#13
I'm surprised the vehicle didn't detect an object moving into its field of view. What are the expectations from the driver under the terms of Arizona's self-driving car laws? Are they expected to remain engaged as a driver, or are they permitted to allow the car to perform all of the driving? It's impossible to say whether an attentive drive would have changed the outcome of this scenario -- largely because a highly compressed video doesn't really convey what the driver actually was capable of seeing, but it's very clear from the video that the driver was more focused on a phone (or some other device) and was not an active participant in driving the vehicle.

Re: Tempe Police Release Video of Uber Accident

#14
Wow, I had thought it impossible for the Uber AV to be in the right lane, and for the victim to be crossing left-to-right, for the police to claim that the victim couldn't be seen until it was too late. But I didn't expect the road to be so dark, given what we saw in the accident photos (which might have been over-exposed?) and Google Maps, which showed a lot of street/sidewalk lighting.

In the moment that we can fully see her, she does look unambiguously like a person walking a bike across the road (reports say there were plastic bags on the bike, but they weren't obvious/obstructive in the camera view). Is the AV's LIDAR expected to detect this kind of thing, even if it's too dark for human eyes?

The video of the Uber driver doesn't look great for the driver. I mean she doesn't look particularly engaged -- but I suspect that's what most of us would look like at the wheel. But she definitely seems to be looking downwards, right at the moment of impact.

Unless some other incriminating info is discovered, I hope that the driver isn't the sole focus of punishment (doesn't help that she's a convicted armed robber, albeit years ago). Being able to brake in time for the victim seems difficult even in most ideal and alert conditions. And I have to think human operators are going to suffer complacency when 95-99% of the time they never have to actually drive -- making that switch seems to be a situation ripe with problems.

I don't mean that Uber execs/testers/engineers (again, assuming there isn't other incriminating evidence) should be scapegoats. I hope the result involves regulations that add more transparency to reporting (especially in Arizona), and public debate about the expectations of AV and AI.

Re: Tempe Police Release Video of Uber Accident

#15
post #14

Wow, I had thought it impossible for the Uber AV to be in the right lane, and for the victim to be crossing left-to-right, for the police to claim that the victim couldn't be seen until it was too late. But I didn't expect the road to be so dark, given what we saw in the accident photos (which might have been over-exposed?) and Google Maps, which showed a lot of street/sidewalk lighting. In the moment that we can ful…

The dynamic range of small sensor digital cameras is so poor that it is impossible to judge whether or not she would have been visible to the naked eye based on the video.

Re: Tempe Police Release Video of Uber Accident

#16
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 naked eye but she also wasn't darting into traffic and had to cross the #1 lane before even being in the path of the vehicle. A human driver certainly would have difficulty stopping in time, but why did the sensor package not pick her up? This doesn't appear to be the close call we were told it was. To me, this seems like exactly the scenario that autonomous driving vehicles are intended to prevent.

Re: Tempe Police Release Video of Uber Accident

#18

Here’s a better video: https://twitter.com/brianawhitney/status/976591851384745984?... The car should have seen that.

How is this video "better?" This is clearly somebody holding a camera recording a screen and seems to have much more artifacting and brightness changes.

Re: Tempe Police Release Video of Uber Accident

#19
post #13

I'm surprised the vehicle didn't detect an object moving into its field of view. What are the expectations from the driver under the terms of Arizona's self-driving car laws? Are they expected to remain engaged as a driver, or are they permitted to allow the car to perform all of the driving? It's impossible to say whether an attentive drive would have changed the outcome of this scenario -- largely because a highly…

I'm definitely interested in the legal expectations too. If it turns out LIDAR completely dropped the ball here, it might not be the case (given AZ's lax rules) that Uber would be penalized for LIDAR that was substandard.

Presumably, there'd be regulations for software too, classifiers and AI decision making. Has any jurisdiction set standards in this?

Post reply on HN