Tempe Police Release Video of Uber Accident • Hacker News Board

Re: Tempe Police Release Video of Uber Accident

#691

Post by voussoir » Thu, Mar 22, 2018, 5:04 AM UTC

burke wrote: post #285

ars wrote: post #74

Direct link: https://twitter.com/TempePolice/status/976585098542833664 The interior view tells you everything you need to know about why anything except perfection in self driving cars will lead to more accidents. The driver specially selected and trained for exactly this job, does not look at the road! If someone specially trained for that won't do it, the general public certainly will not. Also, in the video you ca…

> anything except perfection in self driving cars will lead to more accidents. Only if perfection is defined as "statistically better than humans". I do agree that these "assistive" technologies have the potential to do more harm than good, but the bar is actually far lower than "perfection".

There was an excellent comment by curveship on the thread the other day [0] that really stuck with me so I want to parrot it a bit:

> Our car-based transportation system is far and away the most dangerous thing any of us accept doing on a daily basis ... everyone on the jury has in the back of their mind "that could have been me"

> drivers don't get punished for doing something dangerous, ... They get punished for doing something more dangerous than the norm.

> self-driving cars don't just have to be safer than human drivers to be free of liability, they need to be safe period. In a trial, they don't benefit from the default "could have been me" defense.

You are obviously correct that a "statistically better than humans" vehicle is an improvement over what we currently have. But this is the kind of technically correct answer that doesn't actually resonate with people, especially those outside of tech.

[0] https://news.ycombinator.com/reply?id=16624910

Re: Tempe Police Release Video of Uber Accident

#692

Post by visarga » Thu, Mar 22, 2018, 5:04 AM UTC

jcfrei wrote: post #144

chrsstrm wrote: post #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…

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.

Maybe it detected her but failed at predicting her path.

Re: Tempe Police Release Video of Uber Accident

#693

Post by lovelearning » Thu, Mar 22, 2018, 5:04 AM UTC

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.

Those cars have multiple sensor feeds, many of which are far better than human vision. I have experience with off-the-shelf IR illuminators, and even an array of half a dozen of cheapo ones improve low light object detection at distances of upto 40-50m by orders of magnitude.

So I feel Uber would have selected whichever feed best supported the explanation that it was "impossible" to avoid such an accident, and handed it to investigators. Given the number of people agreeing with the "impossible to avoid" explanation even in a tech-savvy crowd like HN, I'd say the PR strategy's worked well and saved Uber some more bad press.

Re: Tempe Police Release Video of Uber Accident

#694

Post by galdosdi » Thu, Mar 22, 2018, 5:05 AM UTC

smogcutter wrote: post #242

darkerside wrote: post #79

Earlier quoted context omitted.

I wonder if this was affected by the fact that the pedestrian was in another lane up until the very last second. Perhaps the car detected the pedestrian but failed to consider it an obstacle since it wasn't in its direct path. It could be unexpectedly difficult to account for pedestrian crossing speed if it caused automated cars to stop when a car in the next lane happened to "wobble" towards the automated car's lane…

I dunno, if it decided to ignore the pedestrian because she was in the other lane that's extremely troubling. The pedestrian was moving laterally across the road. If the car has detected that, it should infer that she might become an obstacle very shortly. Driving is all about predicting the future. Think of every time you've been able to tell that someone is going to change lanes even though their blinker is off, or…

What's most troubling is it doesn't even matter if the uber car thought the slow object in the other lane was a pedestrian, a car, a tree, whatever. Even if it thought the object was say, the most "normal" thing it could be, another car, this would still be a special situation requiring action. Without knowing the objects classification the estimated speed is enough to decide. Why would a car be stopped in the middle of a lane on a fast road? It should be treated as an obstacle that could grow to the side. After all it could be a police, tow, construction, or disabled vehicle, and a cop or tow worker might be about to walk to the side.

Actually many states now require by law that you get as far as possible from a lane with a disabled vehicle, as many human accidents have happened.

I am convinced uber has been basically pretending to do the mountains of careful and sophisticated crap waymo actually has gone to great lengths to do, and is just racing to put anything out so they can keep stringing investors along as far as they can before the jig is up. Well the jig is up now.

Re: Tempe Police Release Video of Uber Accident

#695

Post by Tempest1981 » Thu, Mar 22, 2018, 5:05 AM UTC

buvanshak wrote: post #483

jeffmould wrote: post #135

Earlier quoted context omitted.

I have to agree. Just like a normal camera has issues in low-light, it is clear that this camera is diminishing exactly how light the road ahead was. While I can't say confidently that I would have been able to stop to prevent hitting them, watching the video in full screen does lead me to believe that I would have seen them and been able to apply the brakes at least enough to reduce the impact. Also, watching the vi…

> clear the driver was looking at his phone or doing something ... Seriously, what else can you expect. These companies who do put these things on the road with the justification that "There is a human behind the wheel" should be taken out back and shot in the head...Just pull the plug. No more self driving cars for them. Those are just the kind of tech companies we don't want around... See, it is not a mistake that…

There are other cases where having a backup-driver might help: mechanical malfunction, sabotage, or a more obvious un-sensed danger.

Re: Tempe Police Release Video of Uber Accident

#696

Post by dfee » Thu, Mar 22, 2018, 5:06 AM UTC

What no one seems to be talking about is that a person was walking their bike across a divided 4 lane road that in many places would be called a highway. This is not a pedestrian friendly crosswalk, and it’s not high noon.

You can tell by the tail lights of the car in front (first second of video) that a pedestrian would be able to see a car coming.

Which begs the question - why did the human step out in front of the car? Is there culpability there, too? If a person intentionally puts themselves into a deadly situation, how should AI handle this?

We’re all looking at the cars, but let’s keep in mind that crossing a dark divided highway in front of a car you can see coming is a really really bad idea.

Re: Tempe Police Release Video of Uber Accident

#697

Post by ajross » Thu, Mar 22, 2018, 5:07 AM UTC

hcknwscommenter wrote: post #599

ajross wrote: post #590

Earlier quoted context omitted.

You can't increase ISO without washing out the areas in the street lights. One of the difficulties not being discussed here is that this is a terribly lit road, with large dark voids between the street lights. And the biker was crossing in the void.

It is not a terribly lit road. You cannot increase ISO, but you CAN increase dynamic range. The human eye, as an example or as another example a much better camera, can easily see those seemingly large dark voids between street lights.

This is a common theme to all the luddits and uber haters, and I don't get it.

The video doesn't show the rider until less than a second before the collision. Yet it's an article of faith among you guys that this video which does not show an easy path to avoidance actually does, due to various magic incantations:

+ The road lighting wasn't bad. A real eye would have shown something different that the camera can't[1], therefore the video proves what it doesn't show.

+ LIDAR and IR should have shown that, therefore Uber is hiding something because the video doesn't show data that must have been present.

I just don't get it. I'm watching this video and seeing what is clearly a huge tragedy and a near-unavoidable collision.

[1] This is not at all true in the real world, by the way. But I see little value in arguing what is clearly a point of faith and not reason.

Re: Tempe Police Release Video of Uber Accident

#698

Post by gugagore » Thu, Mar 22, 2018, 5:07 AM UTC

cmurf wrote: post #467

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 think it's possible to look at the video file and find markers for modification. Certainly this is the case for JPEG, TIFF, PSD, vs Raw files. It's not impossible but very impractical to render a Raw file, edit it, and then unrender it back into a Raw file. It's also pretty malicious and I think it would show a corrupt intent to modify a Raw image in this manner. There are Raw equivalents for video, but consumer ca…

Is there any modern digital video that is "raw"? Without any lossy compression?

Re: Tempe Police Release Video of Uber Accident

#699

Post by voxadam » Thu, Mar 22, 2018, 5:14 AM UTC

stuartgm wrote: post #388

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.

The issue is more with the dynamic range of the sensor than the ISO. Increasing the ISO would blow out the highlights long before providing sufficient detail of the shadows (not to mention the increased noise). Regardless of this camera's performance the LIDAR and other sensors should have picked this up.

Is there any reason it wouldn't be possible to employ multiple cameras each with varying gain/ISO/aperture/exposure/shutter-speed to combat the narrow dynamic range of the individual sensors? Basically create an HDR stream in parallel instead of in series by varying the settings from frame to frame.

Disclaimer: I have a frustratingly poor understanding of this subject, something I desperately need to remedy.

Re: Tempe Police Release Video of Uber Accident

#700

Post by aecs99 » Thu, Mar 22, 2018, 5:16 AM UTC

I currently work full-time in the self-driving vehicle industry. I am part of a team that builds perception algorithms for autonomous navigation. I have been working exclusively with LiDAR systems for over 1.5 years.

Like a lot of folks here, my first question was: "How did the LiDAR not spot this?". I have been extremely interested in this and kept observing images and videos from Uber to understand what could be the issue.

To reliably sense a moving object is a challenging task. To understand/perceive that object (i.e., shape, size, classification, position estimate, etc.) is even more challenging. Take a look at this video (set the playback speed to 0.25): https://youtu.be/WCkkhlxYNwE?t=191

Observe the pedestrian on the sidewalk to the left. And keep a close eye on the laptop screen (held by the passenger on right) at the bottom right. Observe these two locations by moving back and forth +/- 3 seconds. You'll notice that the height of the pedestrian varies quite a bit.

This variation in pedestrian height and bounding box happens at different locations within the same video. For example, at 3:45 mark, the height of human on right wearing brown hoodie, keeps varying. At 2:04 mark, the bounding box estimate for pedestrian on right side appears to be unreliable. At 1:39 mark, the estimate for the blue (Chrysler?) car turning right jumps quite a bit.

This makes me believe that their perception software isn't as robust to handle the exact scenario in which the accident occurred in Tempe, AZ.

I think we'll know more technical details in the upcoming days/weeks. These are merely my observations.