Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Tempe Police Release Video of Uber Accident

twitter.com

Post reply on HN
Print view View original

311–320 of 1001 posts

Re: Tempe Police Release Video of Uber Accident

#311

Post by taeric »

jonknee wrote: post #218
brokenmachine wrote: post #63

Wow, that self driving car is total crap if it can't pick up that obstacle. Doesn't get much more obvious than that. Slowly walking from the left lane into your lane on a fairly straight road. I bet it was more visible to the human eye than on that video as well. You'd have to see someone crossing the road like that. Of course the pedestrian wasn't doing the smartest thing but I believe a human driver would have at l…

> You'd have to see someone crossing the road like that. You could say the same thing about a car with headlights on coming towards you... From the little evidence we have it seems like the pedestrian, driver/monitor and the car all should have done better.

Agreed. Many of us are expecting the machines to do better, by design. Humans will make mistakes. Mistakes will be baked into the designs. Should be just once.

And it is surprising to see how limited this first run of sensors apparently is.

Re: Tempe Police Release Video of Uber Accident

#312

Post by arthurofbabylon »

I remain curious about the set of detection mechanisms in place - if this video is the only one, I’d say Uber is culpable (of course it’s not the only one), and if it’s not the only detection mechanism, then where’s the data from the others?

Another note: I haven’t heard criticism about the driver’s inattention...

Re: Tempe Police Release Video of Uber Accident

#314

Post by JustSomeNobody »

freehunter wrote: post #204
jonathanyc wrote: post #81

Earlier quoted context omitted.

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.

That's an argument intended only to shift blame and distract. The car was going 38 in a 35 which is well within the legal margin of error on a speedometer[1]. For all we know, the speedometer read exactly 35. There's enough blame to go around between the driver who was obviously texting and the woman illegally jaywalking, you don't need to invent a false controversy. [1] https://www.caranddriver.com/features/speedome…

Speed limits are for optimal conditions. Night driving is not optimal so the vehicle was going too fast.

Re: Tempe Police Release Video of Uber Accident

#315

Post by ttul »

fudged71 wrote: post #251

I do wonder if perhaps Uber made the video darker before releasing. Or used a camera that is not the main sensing camera. Because I would hope the cars are smart enough to increase ISO to get more detail at night time.

That would be criminal. Nobody at Uber would risk that.

Re: Tempe Police Release Video of Uber Accident

#316

Post by tachim »

manicdee wrote: post #262

To all the armchair experts: try recreating this accident scene in the real world. Sodium Vapour (monochromatic) lamps, then a large darker area with a pedestrian in dark clothing with car’s headlights dipped. You will be alarmed at how much stuff you can put on the road and not see it because the road has a lighting pattern that makes it less safe than no lights at all. With no lights at all, and a hedge between car…

Nope. That person + bike would have been completely trivial to detect with the LIDAR those cars have mounted on top.

Re: Tempe Police Release Video of Uber Accident

#318

Post by bigiain »

JustSomeNobody wrote: post #271
vkou wrote: post #158

Earlier quoted context omitted.

> 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. This was taken by a video camera - which has a much lower range of detectable brightness then the human eye. The pitch-black spots in the video are almost certainly not pitch-black if you were to look at them.

This car should have slowed down below the speed limit if it cannot safely stop or maneuver upon seeing something enter its field of view.

This is drummed into students during the motorcycle training syllabus here (Sydney Australia) - "Do not ride beyond your field of view. It you can't see beyond a curve, crest, fog, rainstorm, queue of traffic or whatever - make sure you're going slow enough that you can stop before you get to the end of where you can see".

I always explain it to friends starting out "you need to assume that just around every corner there's a stationary shipping container that's fallen off a truck. If you cant stop in time by the time you see it - it's your fault for going too fast."

Re: Tempe Police Release Video of Uber Accident

#319

Post by ashwinpp »

Apart from all the questions about the camera, resolution and culpability, we need to re-think what it means to be training and evaluation of autonomous cars with respect to the rare incidents.

Training the cars based on data collected from roads is heavily biased towards incident free conditions. This does not give any training or feedback on the rare occasions such as these. If there was a learning algorithm deciding what to do (assuming hand coded rules are brittle and hence one would want to learn handling these scenarios) then it perhaps has no training data.

Evaluating the cars based on incidents per million is fine but doesn't tell anything about how the incidents would have been handled if they had happened. There is no incentive for the learning algorithm to slow down the car to prevent fatality, if all it cares about is an incident happening and not the severity.

One possible solution, autonomous cars are trained in real life simulations (using realistic lighting conditions, dummies and what not) to be able to handle the rare incidents and they are also required to pass regulatory testing in similarly realistic conditions to test for their behavior in rare incidents, before they are allowed to drive on actual roads.

Re: Tempe Police Release Video of Uber Accident

#320

Post by fudged71 »

steve19 wrote: post #266
fudged71 wrote: post #251

I do wonder if perhaps Uber made the video darker before releasing. Or used a camera that is not the main sensing camera. Because I would hope the cars are smart enough to increase ISO to get more detail at night time.

I don't think Uber are stupid enough to doctor evidence before handing it to police.

Uber has built tools to track and avoid police. This is NOT below them.
Post reply on HN