391–400 of 1001 posts
It's very disingenuous to release this video. This is not the picture the car saw nor the human. That coupled with the fact that no radar or lidar data was released makes me wonder why the police seem to be bending over backwards to absolve Uber.
What did the sensors register? Is their system using an ultrasonic sensor? Did this detect anything? Commercial ultrasonic sensors can detect something at least 15' away. So the software could have at least slowed down to minimize the collision impact.
What did the LIDAR see? Did their software detect an object?
This accident happened on a clear night. There was no rain. There was no snow. The pedestrian crossed the street in a perfect 90 degree angle to the sidewalk. The pedestrian did not jaywalk and cross diagonally. The pedestrian even walked the bike across the road. Thus, the pedestrian performed a legal road crossing.
I don't think a human driver would have made this same mistake. When I drive on a dark road, I occasionally flash my high beams to ensure that there is no obstacle in front of me for hundreds of feet. That is how I, as a human, can safely determine that the road is clear for me to proceed.
What's on trial here, is the safety of the software system developed by Uber. And on this instance, their system failed, and a human died.
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…
This is pretty much the experience I have with my dash cam, a Yi. In its recorded video, its automatic exposure control make it look like everything outside of the headline cone is pitch black, but it is actually not. I have seen deer and possums by the side of the road, and debris etc, that did not show up when I later checked the video for the same period. There is enough spillover light from modern headlights that…
Earlier quoted context omitted.
A theory that occurred to me last night is that if she was homeless, she may also have had an untreated eye condition such as myopia.
What about sound? Also, with myopia you should still be able to see a light source traveling towards you.
This woman's death will not be in vain. I did not expect such a terrible fuck up so early on, but I'm glad it clearly demonstrates how badly made autonomous vehicles are. They're not going to be ready to hit the streets for decades, unless of course we decide that Uber's profit margins are worth more than human life.
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…
Whether a human would've seen her or not is besides the point, really - the car is supposed to be fitted with sensors that don't rely on visible light, and this looks like the most basic test case you'd run on an AV - big empty road with an obstacle moving at constant speed into the path of the vehicle.
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".
Personally, I don't think that it's right to dismiss these systems entirely if they provide some level of safety benefit, are cheaper and easier than level 5 autonomous vehicles to develop and / or deploy.
> http://www.iihs.org/iihs/news/desktopnews/stay-within-the-li...
Earlier quoted context omitted.
This is exactly it. I see people mentioning seeing the victim at the last second but these vehicles are supposed to be better. They scan in non visible spectrums with LIDAR. Lack of safety vest, lack of headlights, none of it is supposed to matter... or at least it shouldn't completely compromise the vehicle's systems. Camera's may not work as well but an obstacle directly in the path should still be detected. Especi…
I watched the video a bunch of times and I'm not 100% sure how the vehicle could have reacted at the upper maximum of time where she would have been visible to LIDAR, and maybe for Radar, to make a significant difference. At least given the two options where it could have slowed maybe 10km/hr at most (from the 40mph aka 64km/hr speed limit) but that's still an if and I'm not sure it would have ensure the survivabilit…
The LIDAR sensor[1] being used here can pick up targets up to 120m away. I'm not sure about the RADAR or vision systems also in place, but even LIDAR alone should have been able to easily pick out the pedestrian with plenty of time to come to a full stop.
This is clearly poorly designed autonomous driving software, not a sensory deficiency.
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 suspect the raw output of their main sensing sensors is proprietary somehow.
exp: http://www.mssl.ucl.ac.uk/www_detector/ccdgroup/optheory/ccd...
Earlier quoted context omitted.
> 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".
I wonder what the "deaths per vehicle miles" stats for autonomous vs human-piloted cars look like right now? Humans kill, what, 30,000 other humans a year or so in The US? But there's a _lot_ of vehicle miles driven. My guess is this one incident has likely pushed the autonomous car death rate per vehicle mile way beyond the current human piloted death rate per vehicle mile... (Having said that, there's not much doub…
California .92 deaths per 100 million (human)vehicle miles traveled. There were only 500k autonomous miles driven in California last year.
I'd bet your guess about death rate per mile is right considering waymo which has largest and most advanced fleet only drove 2 million miles nationwide last year.