Uber vehicle reportedly saw but ignored woman it struck
331–340 of 445 posts
Re: Uber vehicle reportedly saw but ignored woman it struck
#332Earlier quoted context omitted.
> And welcome to why self-driving cars will always be 3 years away. It's also possible that human/pedestrian behavior will adapt to the consistent behavior of driverless cars.
Or jaywalking will become more strictly enforced with policing or physical barriers. https://www.strongtowns.org/journal/2018/4/2/automated-vehic...
The scenario you're describing, OTOH, feels even more alienating than what we're already suffering. What in the hell gives you, sitting on a seat in a car, more right to travel through a space than a walking human being?
Re: Uber vehicle reportedly saw but ignored woman it struck
#333Earlier quoted context omitted.
That was a bad call on the part of the police. You're only allowed to drive as fast as conditions permit. If it's dark enough that you can't avoid an obstacle by the time your headlights illuminate it, you need to slow down .
That's not really true. Thousands of deer get killed on the road every year, because deer aren't smart enough not to be an obstacle when it's dark. Do we therefore change all the speed limits at night? No. It's a driving risk taken, just like any other.
Re: Uber vehicle reportedly saw but ignored woman it struck
#334I'm looking forward to seeing the full NTSB report. This hints that Uber's mindset is focused on "obstacles", not "flat road". The first job of automated driving is to drive only on flat surfaces. Doesn't matter why it's not flat. Then you worry about where to go. That's how the off-road DARPA Grand Challenge vehicles had to work. "Flat road" is a pure geometry thing. Not much AI needed. On road, non-flat road is rar…
The old adage applies. Aviate, Navigate, Communicate. In that order.
Re: Uber vehicle reportedly saw but ignored woman it struck
#335I'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…
Humans have that awareness and lack on visibility (you can't see 360degrees, you can't see a wide range, you can't see beyond your car Caracas...). The awareness was enough to let us move but the lack of visibility did certainly kill people.
The best we could have done today was a system that helps human visually. Then the system reports back how human interacted with that particular situation (ignore, brake, etc...) Then maybe 5 years later of work we could have had something.
Re: Uber vehicle reportedly saw but ignored woman it struck
#336Earlier quoted context omitted.
This makes no sense to me even after assuming you are from a country that drives on the left and reading the Wikipedia page.
Ok, let's use normal right-sided driving method. Imagine you're vulnerable (on a bike, or worse: on an electric scooter), and you want to turn left. You were going northbound and want to go westbound. In "normal" fashion, you'd have to stay on the left of your lane, and wait for the traffic coming in front of you to die down before you can cross. That puts you straight in the middle of the intersection for some time,…
Re: Uber vehicle reportedly saw but ignored woman it struck
#337Earlier quoted context omitted.
Which law is violated if you enter the intersection when the light is green and exit it when the light is red?
In many places it's illegal to enter the intersection (even if the light is green) if you're unable to immediately leave it, mainly to ensure that intersections don't get blocked if there's a traffic jam in the direction you want to go; and this rule also prohibits (not everywhere) to enter the intersection for a left turn if you can't complete the turn right now because there's still oncoming traffic.
Then the laws in Pittsburgh are just bad. Not a design question at all.
Here you oull into the intersection on green, turn slightly ti a big white cross on the road for exactly this purpose and go when it is clear. This happens when the oncoming side has red, but before the crossing cars have green. The time between red and green is long enough for all two or three cars to clear the intersection.
Get better laws i guess?
Re: Uber vehicle reportedly saw but ignored woman it struck
#338Earlier quoted context omitted.
However, if the car saw the pedestrian, even as a false positive (presumably from far enough away to have enough time to brake/avoid it), I think it should’ve alerted the driver. The driver would’ve most likely started paying attention and avoided the crash.
> I think it should’ve alerted the driver. I like the idea, and if these pruned false positives are rare enough I think it would be a great safety measure - you could even have the driver verbally label things, which might have both training (in the AI sense) and awareness (for the humans) benefits ( https://en.wikipedia.org/wiki/Pointing_and_calling ). Note that "rare enough" needn't be all that rare, just that if i…
> I like the idea
I'm not sure how well I would respond to a sudden alarm when everything has been deemed safe until a moment ago. I'd potentially need several seconds to figure out what is going on.
I would hazard a guess that an approach that might be more fruitful be to have a meter that dynamically adjusts the "riskiness" of the situation between a yellow, orange, and red zone, so that the driver (a) has to pay attention constantly, (b) gets information constantly, and hence (c) has a better chance to react earlier. I know if I see a "danger meter" getting into the orange zone, I'm not going to wait until it goes into the red before I start paying attention.
Re: Uber vehicle reportedly saw but ignored woman it struck
#339Should a autonomous vehicle also prioritise it's own passenger over the safety of others, aka head on collision with a people carrier.