Live data from Hacker News

Uber vehicle reportedly saw but ignored woman it struck

techcrunch.com

51–60 of 445 posts

Re: Uber vehicle reportedly saw but ignored woman it struck

#51

Earlier quoted context omitted.

As long as Uber's system logged which automatic brake was triggered - or simply failed to log that its own braking system stepped in - it could have saved a life without impacting the data gathered. They didn't put a tarp over the windshield; why get rid of other proven safety features?

You don't generally want multiple autonomous control systems in a single vehicle competing with each other for control. There are scenarios where the less-sophisticated collision avoidance radar could do the unsafe thing where the self-driving system has a more holistic plan. Basically, there's no reason the self-driving tech shouldn't have been way more effective than the collision avoidance radar other than Uber ro…

> There are scenarios where the less-sophisticated collision avoidance radar could do the unsafe thing where the self-driving system has a more holistic plan.

Like, for example, this plan? https://www.youtube.com/watch?v=od5YG6kBrJs

I believe the whole thing will require better conceptualization of something that we call crew resource management for human teams. That is, how do you respond if you have conflicting information?

Re: Uber vehicle reportedly saw but ignored woman it struck

#52

The question I want to know is: Did Uber doctor the camera video to make the road seem darker than it actually was? If you recall, there was initially a doubt that Uber was at fault because the streets appeared extremely dark, but I think they were buying time to delay the outage at incompetent Uber. The police initially didn't fault Uber based on this video.

It shouldn't matter at all how dark the roads were, the vehicle was equipped with LIDAR.

Re: Uber vehicle reportedly saw but ignored woman it struck

#53

I'm curious what degree of "cultural context" is built into automated cars - I feel that there has to be a lot of locale-specific techniques for driving. For example, in NYC, there's nothing at all uncommon about a pedestrian beginning to cross the street in front of you and approaching the area of your lane where you will shortly be. Pedestrians typically then stop about a foot away from your lane, let you drive pas…

There's a road near the University of Waterloo where students get hit, some killed, on pretty much an annual basis. Often it boils down to the large number of foreign students who come from a part of the world where for one reason or another, you just don't need to bother looking before crossing, so they don't and walk right in front of cars (and in one case a city bus).

To me this is an example of the overwhelming importance of locale-specific context. When I'm near UW, my driving behaviour changes significantly even though the laws do not.

Re: Uber vehicle reportedly saw but ignored woman it struck

#54

The question I want to know is: Did Uber doctor the camera video to make the road seem darker than it actually was? If you recall, there was initially a doubt that Uber was at fault because the streets appeared extremely dark, but I think they were buying time to delay the outage at incompetent Uber. The police initially didn't fault Uber based on this video.

The cameras used in applications like these are not like your typical 24-bit RGB cameras in phones or webcams that need gain adjustment: their sensors support a very high range of brightness values (like "high dynamic range") - but the video released to the public and the media would be MPEG/H.26x/etc which do not support HDR - or at least most video players wouldn't. The police probably lacked the expertise to know to demand the raw high-range camera data but instead just asked for "the video" and it's possible Uber deliberately took advantage of their ignorance to release a video that mitigates their culpability.

Re: Uber vehicle reportedly saw but ignored woman it struck

#55
post #17

Earlier quoted context omitted.

I highly doubt it, considering the video came from Tempe police, not Uber. Regardless, does it matter at this point? Uber is basically saying here that the sensors did detect the pedestrian but the issue was that the software to ignore false positives was tuned incorrectly.

Tempe police obtained the video from Uber, Uber could have easily altered it before handing it over. Uber has behaved badly in the past, and they had the motivation and past experience to do what it takes to advance their agenda. Remember, Uber terminated its autonomous driving testing as a result of this preventable tragedy.

> Tempe police obtained the video from Uber

If by "from Uber", you mean they popped the SD card from the Uber-owner car's dashcam, sure.

> Uber could have easily altered it before handing it over

See my comment from the last time someone had suggested the idea of doctored videos: https://news.ycombinator.com/item?id=16644663

Re: Uber vehicle reportedly saw but ignored woman it struck

#56

I'm curious what degree of "cultural context" is built into automated cars - I feel that there has to be a lot of locale-specific techniques for driving. For example, in NYC, there's nothing at all uncommon about a pedestrian beginning to cross the street in front of you and approaching the area of your lane where you will shortly be. Pedestrians typically then stop about a foot away from your lane, let you drive pas…

I think you're overselling the extent of the difficulty here. People from out of state usually manage to get through New York, pedestrians and all, without getting into an accident.

A car won't get through a block as quickly as it could if it merely obeys the laws makes sure it doesn't run into anybody. I'm sure this will cause great joy among people crossing the street and consternation among other drivers but the problem isn't a blocking one as long as the car can actually avoid hitting people - even if it's more cautious than it needs to be.

Re: Uber vehicle reportedly saw but ignored woman it struck

#57
post #24

> We’re actively cooperating with the NTSB in their investigation. Out of respect for that process and the trust we’ve built with NTSB, we can’t comment on the specifics of the incident. Hey look, somebody knows how to follow the script! Uber may be grossly negligent, but at least they respect the process unlike Tesla.

It's actually the rest of that statement which shocks me a bit:

> In the meantime, we have initiated a top-to-bottom safety review of our self-driving vehicles program,

So they actually think they can continue to work on self-driving vehicles after this, and not scrap the program entirely. That's...not what I expected. No municipality in the country should allow Uber to test on their streets after they killed someone, almost certainly because of their recklessly fast development. That's not something you come back from by promising to Do Better, especially not when there are more than a few competitors already way ahead of you.

Re: Uber vehicle reportedly saw but ignored woman it struck

#58
post #42

Earlier quoted context omitted.

Unfortunately I think it's one of those things that is both inexcusable and guaranteed to happen. It absolutely makes sense to put a human in a car you're testing and don't have full confidence in yet but are sending into real traffic. Not doing so would be ludicrously negligent. However, humans simply don't maintain focus for a long period of time without some sort of extreme, years-long training. The ability of mon…

I think there's some room for improvement though. Instead of "just one human in there", they could put them out in teams of two, and have periodic "awareness checks" that you have to respond to by pressing a driving-irrelevant button.

Dead-man switches do not work.

Re: Uber vehicle reportedly saw but ignored woman it struck

#59

I'm curious what degree of "cultural context" is built into automated cars - I feel that there has to be a lot of locale-specific techniques for driving. For example, in NYC, there's nothing at all uncommon about a pedestrian beginning to cross the street in front of you and approaching the area of your lane where you will shortly be. Pedestrians typically then stop about a foot away from your lane, let you drive pas…

This really speaks to other cues that we use while driving that are more complex that just the location and velocity of objects/people. In this case: attention and gaze. I sometimes do the "walk up to the lane and wait" thing, but I always look up and make eye contact with the driver to communicate that I know they exist and I'm not walking out in front of them. And when I'm driving and someone is walking up to my la…

I think body language might be more important, and seems to me should be harder to detect. Eye's are pretty easy to detect because of the contrast between the whites and iris, and, of course they reflect light.

Detecting the difference between a hustle, a saunter, and a day dream might be a tad more difficult.

Re: Uber vehicle reportedly saw but ignored woman it struck

#60

Earlier quoted context omitted.

And welcome to why self-driving cars will always be 3 years away. I think we should be targeting self driving for long-haul freeway scenarios where the rules are relatively simple and predictable. Trying to control for the infinite number of scenarios in cities is a nightmare which will ultimately bog down the development of any company which makes that its goal.

This is already happening in the trucking industry. Self-driving trucks are being developed to be able to drive 99% of the trip that's on highways and then human drivers take over for the local 1%. To make it easier, transfer hubs are being built near cities off major highways to make everything easier and non-disruptive. The same thing could be done with cars without the need for the transfer hubs and it basically i…

I can't beleive they would do a trail run with an automous truck weighing 80,000lbs barreling down the freeway.

This revolution should have started with mundane tasks, such as city street sweepers and perhaps garbage trucks. Vehicles that move slow on a predefined path in the night. Then advance to faster moving objects like taxis.

Just like the DARPA Grand Challenge that started this mess. Many of those vehicles were industrial usage, not consumer.

Post reply on HN