Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Delirium on March 22, 2018, 09:42:34 AM
That is funny, because when cars were released these early drivers were also told to buy horses.
Self driving cars will become the norm, no one will be able to stop the tide of technology. However, I do wish additional sensors would be installed in roadways as part of an approach to make them safer.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Skuzzy on March 22, 2018, 10:11:02 AM
It will be a while before autonomous cars are the norm.
You want electric cars? Or do you want autonomous cars? Today, you cannot have both. Well you can, but according to Bosch, who makes most of the autonomous sensor equipment, your useable driving range, in an electric car, will drop about 90% when fitted with everything to make it autonomous.
Personally, I see advantages of it on the open Interstates/Freeways, but in town and residential areas, no way.
If a car has to decide whether to hit a pole or run over a baby, it will run over the baby as the primary concern is the safety of the occupants and running over a baby will serve to protect the occupants of the car. Cars lack moral judgement.
If I am driving, I hit the pole. I am in a better position to survive that, than a baby is if I run over it.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Maverick on March 22, 2018, 10:38:28 AM
The car / truck can be autonomous but until you fix the people issue (other drivers and pedestrians) there will always be a tremendous number of unknown factors for the machinery to deal with. Machines and software are predictable, peepuls are stupid too much of the time. ANYONE who has studied traffic or had to direct traffic knows that first hand.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Skuzzy on March 22, 2018, 10:40:32 AM
The car failed, in this case. The lady had to cross an open lane before entering the lane the car was traveling in. There is no way that car should not have detected her.
It does not appear to make any changes at all, in speed or direction.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: pembquist on March 22, 2018, 10:54:15 AM
I'm not going to watch the video as I have enough stuff I can't un-see already. What Skuzzy said about the pedestrian having to cross a lane before getting into the lane the car was in reminded me of the crosswalks here. The law here is that every corner crossing is a cross walk whether marked or not and the rules are the same as when a cross walk is marked with broad white stripes and flashing yellow caution signals. The rule is if a pedestrian steps out traffic has to stop. Unfortunately knowledge of this law is not consistent across drivers ranging from puzzlement to rage in the reactions of the drivers when pedestrians use even the emphatically marked cross walks in a way that causes the cars to have to stop. At least the autonomous cars aren't supposed to get angry that they have to follow the law, or will they?
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Skuzzy on March 22, 2018, 11:06:24 AM
The safety driver also failed.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Devil 505 on March 22, 2018, 11:40:34 AM
Looks like they were surfing on their phone or device - out of view of the internal camera on purpose...you can tell by watching the video and see them smiling for a moment because they were using a smart device.
That said, I'm not sure the outcome would of been any different if they had been watching the road as they were alert and looking forward just prior to the accident. And had Volvo's own safety system been turned on, I'm not sure if the outcome would of been different. I have a similar system on my Sube Forester (Eyesight) and it relies on visibility to brake.
In this case, the poor lady jay-walked across a fast multi-lane road at night - I'm not sure if anyone else had been driving the outcome would of been different. The time from being visible in the vehicle lights to impact as just a tad under 1 second. The average reaction rate for a 30 year old driver is 1 second.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Skuzzy on March 22, 2018, 12:34:13 PM
You cannot go by what you see in that video. The camera may have poor low light support to begin with.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: 100Coogn on March 22, 2018, 12:56:39 PM
I wonder how these autonomous vehicles will deal with snow & ice. We can get 6-8 inches if snow easily overnight, here in Michigan. How are those sensors going to negate the edge of the road in that stuff? I've been driving for 35 years here and every year can be an adventure in the winter.
Coogan
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Wiley on March 22, 2018, 01:06:03 PM
I was under the impression the whole point of the autonomous systems was it was way better at detection and reaction than people, therefore a Kobayashi Maru scenario where you've got not choice but to hit *something* wouldn't occur.
Once they get it reasonably debugged, I'm sure they'll hit a point where they're statistically safer than people. We'll just have to put up with the occasional incident where a human that was paying attention might've made another decision.
The thing is, very few people treat driving as a skill anymore so regardless of what a good driver would do, the average morning commute zombie is as likely to freeze or make the wrong choice as they are to make the right one.
I don't like the idea of putting my life completely in the hands of a software engineer just on principle, but I agree that seems to be the way we're headed.
As to the snow and ice, I really wonder about that too. I recall one time driving a highway at 4 AM that had gotten about 2 inches of fresh snow overnight, and the plows hadn't been down it. The ditches were full to be level with the road and there was one set of tracks that had gone down it. I spent most of the 20 mile drive just praying that guy hadn't hit the ditch or I was going to be right behind him.
On an average plowed city street though I think the snow might actually help it delineate the road a little better.
Wiley.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: bustr on March 22, 2018, 01:22:21 PM
Here in california black and dark coats\shirts are the norm year round. At night even on well lit roads and your lights on, at times it can get dicey seeing pedestrians. In cities you are habituated to looking for them becasue they are a constant in the environment. Once you leave urban areas, you don't expect to see a person walking across the road and this can have unfortunate consequences. It's how the brain works.
Looking at the video, the human passenger aside, I have to wonder if our eyes and brains process a bit differently than a digital camera shows under low light conditions. There was a left road fork that she came out of while being already on the road bed, not darting from one shoulder to the other. The dash cam appears to be kind of binary in showing dark and light areas versus our eyes and brain has more spectrum which the street light may have been enough for our peripheral vision to be tickled which works better in dark conditions to sense motion. That doesn't account for the passenger's reflexes or lack of in the equation. A younger more alert passenger may have still hit the pedestrian or rolled the car in a reflexive evasion panic killing both people. One will never know.
It appears the sensors are not scanning wide enough nor did they resolve the image outline of a combined human pushing a bicycle from its huge database of possible collision image outlines. And her reflective white shoes, the sensors may have thought they were a road bed painted reflection device for human drivers to see. The industry that is moving autonomous vehicles along had to accept things like this would happen during the formative years while the sensory equipment was being refined. Otherwise, they would never have started down this path to one day replacing human drivers with AI.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Wiley on March 22, 2018, 01:39:31 PM
That is funny, because when cars were released these early drivers were also told to buy horses.
Self driving cars will become the norm, no one will be able to stop the tide of technology. However, I do wish additional sensors would be installed in roadways as part of an approach to make them safer.
Personally I am not really keen on external sensors. They seem to me like a target for vandals/hackers. If they can't make it work self-contained in the vehicle, I don't think they should do it.
Wiley.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: zack1234 on March 22, 2018, 02:03:38 PM
Why will no one answer the flipper question every time this comes up?.
What is the point of driverless cars?.
And why dont they put railway track on the freeways?.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Skuzzy on March 22, 2018, 02:38:02 PM
According to Uber, here are the sensor layouts and types. (http://bbs.hitechcreations.com/smf/index.php?action=dlattach;topic=392309.0;attach=29445)
If they are being truthful about the sensor package, there is no way that lady could have gotten in front of that car without it knowing about long before she got there.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Wiley on March 22, 2018, 03:56:01 PM
According to Uber, here are the sensor layouts and types. (http://bbs.hitechcreations.com/smf/index.php?action=dlattach;topic=392309.0;attach=29445)
If they are being truthful about the sensor package, there is no way that lady could have gotten in front of that car without it knowing about long before she got there.
I'd be curious to see the recording of what the system thought was going on there.
Although I just noticed this was in the Daily Fail, so I now doubt the existence of Arizona and pedestrians...
I just saw the part of the video showing the driver. Kind of illustrates the problem with an autonomous system. If you're paying enough attention to be effective in that role, what's the point of not being in control? I've often wondered why they don't do up some kind of system that basically does augmented reality through some kind of HUD on the windshield. Infrared and/or night vision to improve the driver's awareness type stuff.
Wiley.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Vulcan on March 22, 2018, 08:24:41 PM
If they are being truthful about the sensor package, there is no way that lady could have gotten in front of that car without it knowing about long before she got there.
Unless they have reached true autonomy and the cars - like the rest of us drivers - hate cyclists.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: ToeTag on March 22, 2018, 09:29:04 PM
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Skuzzy on March 23, 2018, 05:44:20 AM
There is always that. This could be the first robot kill we have witnessed as they grow tired of their human overlords.
That sounds entirely too plausible. I know I've read in the past how the vehicles were having trouble with cyclists due to unpredictability. This incident paints that in a completely different light.
Wiley.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: SysError on March 23, 2018, 10:10:09 AM
Decide who lives and who dies. The Moral Machineacademic
"A platform for public participation in and discussion of the human perspective on machine-made moral decisions"
http://moralmachine.mit.edu/
Some of the results I got (from a few years ago.. Perhaps I should take it again to see changes....)
Most Saved Character: Reg guy Most Killed Character: Fat Guy Saving More Lives: Matter a Lot (to me) Protecting Passengers: almost 50 - 50 Upholding the Law: A little less than other people Avoiding Intervention: A less than other people Gender Preference: Females by a bit (i think it means preferr to save save females more than males.)
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Volron on March 23, 2018, 10:55:59 AM
So no one is going to question the fact that that *ahem* "person" was crossing in the middle of nowhere IN THE DARK while wearing DARK clothing, with NO reflectors that I could see on the bike or on her person, AND taking her sweet time in a 45MPH zone???
Yeah, no. Scratch one stupid. I see this a LOT in my line of work, and quite frankly, I have no sympathy for that cyclist/pedestrian.
THAT being said, I would've thought they would have something better to work with on that vehicle. If the car is operating off of a camera like the one used in the dash cam, it's a surprise this hasn't happened sooner. You don't see her till she's practically under the car. You'd think they would have much better camera's and/or THERMAL camera's for situations like this. Still needs work, as what is provided to us shows me that left lane was clear, so car could've evaded.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Wiley on March 23, 2018, 11:10:41 AM
So no one is going to question the fact that that *ahem* "person" was crossing in the middle of nowhere IN THE DARK while wearing DARK clothing, with NO reflectors that I could see on the bike or on her person, AND taking her sweet time in a 45MPH zone???
Yeah, no. Scratch one stupid. I see this a LOT in my line of work, and quite frankly, I have no sympathy for that cyclist/pedestrian.
THAT being said, I would've thought they would have something better to work with on that vehicle. If the car is operating off of a camera like the one used in the dash cam, it's a surprise this hasn't happened sooner. You don't see her till she's practically under the car. You'd think they would have much better camera's and/or THERMAL camera's for situations like this. Still needs work, as what is provided to us shows me that left lane was clear, so car could've evaded.
Well, that's kind of the point isn't it? An autonomous vehicle is relatively easy as long as nothing unexpected happens. People and animals do stupid things. Sometimes, there's just a large hunk of metal in the middle of the road for no good reason.
I agree with you that if what was on that camera was what the vehicle was able to see, then it's not a good system but per Skuzzy's picture upthread, that shouldn't be the case.
I sure wouldn't want to be the driver though.
Wiley.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Volron on March 23, 2018, 11:22:19 AM
The fact they are bringing the driver's past into this just shows that they really have nothing. Sadly, there are enough stupid out there that will take that bait. Yeah, I feel bad for the driver.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Wiley on March 23, 2018, 11:47:48 AM
The fact they are bringing the driver's past into this just shows that they really have nothing. Sadly, there are enough stupid out there that will take that bait. Yeah, I feel bad for the driver.
IMO the video's pretty damning with her having her eyes down like they were.
Depending on what was actually visible in the headlights though, if what the dashcam captured actually was what was visible it changes things a lot. The vehicle was over driving the headlights and there wasn't a thing the driver could've done, even if they had F1 driver reflexes. I doubt people will see that though and nobody will ever know.
Wiley.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: 100Coogn on March 23, 2018, 11:49:01 AM
So no one is going to question the fact that that *ahem* "person" was crossing in the middle of nowhere IN THE DARK while wearing DARK clothing, with NO reflectors that I could see on the bike or on her person, AND taking her sweet time in a 45MPH zone???
Yeah, no. Scratch one stupid. I see this a LOT in my line of work, and quite frankly, I have no sympathy for that cyclist/pedestrian.
THAT being said, I would've thought they would have something better to work with on that vehicle. If the car is operating off of a camera like the one used in the dash cam, it's a surprise this hasn't happened sooner. You don't see her till she's practically under the car. You'd think they would have much better camera's and/or THERMAL camera's for situations like this. Still needs work, as what is provided to us shows me that left lane was clear, so car could've evaded.
So the penalty for jaywalking goes from a misdemeanor to insta-death.. :headscratch:
Coogan
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Volron on March 23, 2018, 11:57:43 AM
As a guy who has written a lot of machine-control software, I would not want a driverless car.
It can take a lot of time before obscure bugs show themselves and get fixed.
And that's in a relatively controlled environment I'm assuming? With driving and streets, you run into dozens, maybe hundreds of obscure scenarios every day. So in that aspect, maybe the iterations will be very rapid due to the amount of data they're given to work with.
The sad thing is, even taking that into account it likely won't take much for them to become statistically better than humans, the bar is so low.
Wiley.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Vraciu on March 23, 2018, 12:49:13 PM
And that's in a relatively controlled environment I'm assuming? With driving and streets, you run into dozens, maybe hundreds of obscure scenarios every day. So in that aspect, maybe the iterations will be very rapid due to the amount of data they're given to work with.
The sad thing is, even taking that into account it likely won't take much for them to become statistically better than humans, the bar is so low.
Wiley.
I mean statistically, they already are.
Sure, an alert human drive absolutely has an advantage when it comes to the "what the hell?" moments, but enough people are bad enough at driving that they're already safer overall.
At this point, it's a trade off of hitting a few more pedestrians for hitting a LOT fewer cars.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: bustr on March 23, 2018, 02:43:03 PM
In 2016 a survey was performed to see how people felt about driver-less cars hitting people. You cannot reject the idea that the programing for the Uber AI had a survival threshold for the passenger versus external objects at different speeds.
And that's in a relatively controlled environment I'm assuming?
Yep -- way, way more controlled than driving on streets. That's why, to me, I wouldn't trust it for a long time. It would take a much longer time to see the low-probability occurrences that could trigger a bug.
Quote
The sad thing is, even taking that into account it likely won't take much for them to become statistically better than humans, the bar is so low.
That's the other side of the coin -- that the software (even with bugs) might be better than the bottom portion of human drivers and that it might, overall, still be an improvement.
For example, it might increase some accidents but vastly reduce drunk-driving accidents and thus overall lower the accident rate.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Brooke on March 23, 2018, 05:03:51 PM
Do you mean currently, or completely? Currently, I'd agree completely. The tech really isn't up to snuff for it in my opinion.
Eventually, software-controlled cars will, I think, be superior to human drivers in just about all ways.
But, currently, I would not want one. I think it will take a lot of them driving around trouble free in lots of different conditions for a substantial time before I would trust it.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: ghi on March 23, 2018, 05:44:02 PM
They really are -in a sense- already here. https://www.technologyreview.com/s/603170/mining-24-hours-a-day-with-robots/
Shipyards are next is my guess.
And we are only making it easier for this all to happen (40 miles at a time I guess). https://www.npr.org/2018/03/06/591266949/georgia-transportation-officials-plan-to-build-a-1-8-billion-truck-only-highway
It will not be long before everyone comes up with their own spin on the Luddite movement https://en.wikipedia.org/wiki/Luddite
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: eagl on March 23, 2018, 06:00:14 PM
So the penalty for jaywalking goes from a misdemeanor to insta-death.. :headscratch:
Coogan
Well, yea, if you step in front of a car. Duh. Vegas has a huge number of pedestrian deaths and almost all of them are idiots committing "misdemeanor" offenses and getting the death penalty for it. Cross in the middle of a high speed multi-lane street wearing no lights and dark clothing, and you get what you get.
I watched the video. I think a regular car and driver probably would have hit her even harder since most drivers drive well over the speed limit. No lights, crossing in a very dark area of a high speed multi-lane road, stepping out right in front of a moving car... Yea, you get death for that pretty much everywhere. MANY fatalities every year in Vegas for that exact same situation, with regular alert drivers behind the wheel.
Sure, a "good" autodrive system should have seen that person, but was there even an IR signature from the pedestrian? Wearing enough clothes and pushing a cold bike, she might have not even shown up in an IR scene. Visible light... no way. Lidar? The pedestrian was hustling so she may have been just outside the left edge of the critical area in a frontal collision avoidance area, until she ran right in front of the car. So... Yea, a better system maybe could have used multi-spectral imagery or radar/lidar to see and avoid a pedestrian doing her best to run in front of a moving car, but I think it's a stretch to blame the car here since I highly doubt a regular driver could have done anything different.
I think the lesson I'm taking away is to not run across the middle of a dark high speed multi-lane road right in front of a car.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Karnak on March 23, 2018, 06:44:22 PM
And that's in a relatively controlled environment I'm assuming? With driving and streets, you run into dozens, maybe hundreds of obscure scenarios every day. So in that aspect, maybe the iterations will be very rapid due to the amount of data they're given to work with.
The sad thing is, even taking that into account it likely won't take much for them to become statistically better than humans, the bar is so low.
Wiley.
That is why Waymo is testing in San Francisco instead of the relatively simple Arizona that Uber is in. San Francisco provides a better real world environment that self driving cars need to be able to handle. If they can handle San Francisco, Arizona is no problem, but the reverse does not hold true.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: 100Coogn on March 23, 2018, 08:46:44 PM
Well, yea, if you step in front of a car. Duh. Vegas has a huge number of pedestrian deaths and almost all of them are idiots committing "misdemeanor" offenses and getting the death penalty for it. Cross in the middle of a high speed multi-lane street wearing no lights and dark clothing, and you get what you get.
I watched the video. I think a regular car and driver probably would have hit her even harder since most drivers drive well over the speed limit. No lights, crossing in a very dark area of a high speed multi-lane road, stepping out right in front of a moving car... Yea, you get death for that pretty much everywhere. MANY fatalities every year in Vegas for that exact same situation, with regular alert drivers behind the wheel.
Sure, a "good" autodrive system should have seen that person, but was there even an IR signature from the pedestrian? Wearing enough clothes and pushing a cold bike, she might have not even shown up in an IR scene. Visible light... no way. Lidar? The pedestrian was hustling so she may have been just outside the left edge of the critical area in a frontal collision avoidance area, until she ran right in front of the car. So... Yea, a better system maybe could have used multi-spectral imagery or radar/lidar to see and avoid a pedestrian doing her best to run in front of a moving car, but I think it's a stretch to blame the car here since I highly doubt a regular driver could have done anything different.
I think the lesson I'm taking away is to not run across the middle of a dark high speed multi-lane road right in front of a car.
At least a pedestrian would have a chance with human driver. Some may stop some may not. All of these automated cars will be programmed the same. 'Run em all down!' Now what if it's a dog/deer or your child in the road?
Coogan
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Skuzzy on March 23, 2018, 10:06:34 PM
eagl, you missed a couple of points.
1) She did not just step in front of the car. She crossed one empty lane before getting to the lane the car was in, then crossed left to right, getting hit by the right front fender. The camera footage has already been proven to be artificially darker than the real scene was, by several factors. Was she wrong? Sure, but she did not need to die because of that mistake.
2) The LIDAR system Uber is claiming to use has a range of 500m and a 360 degree sweep.
Both the car and the safety driver failed. A needless death was the result.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Wiley on March 23, 2018, 11:11:24 PM
1) She did not just step in front of the car. She crossed one empty lane before getting to the lane the car was in, then crossed left to right, getting hit by the right front fender. The camera footage has already been proven to be artificially darker than the real scene was, by several factors. Was she wrong? Sure, but she did not need to die because of that mistake.
Failure all around in my opinion. It's sad, but crossing a highway at night you should see vehicles for miles.
But the vehicle appeared to not react in any way, not good.
Wiley.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Karnak on March 24, 2018, 09:01:09 AM
It is even worse than I stated previously. Even though Uber is using comparatively easy Arizona they average a safety driver intervention once every 13 miles. Waymo, in comparison, is averaging a safety driver intervention once every 5600 miles in California and GM's Cruise program (the one actually bragging about using San Francisco, my bad) averages 1250 miles per intervention.
Uber is literally years behind Waymo and GM.
Also, remember the reason Uber is using Arizona and not California. California required permits and data reporting, Uber said they didn't need permits, California put their foot down and Arizona told Uber to come do the testing in Arizona where they wouldn't be held back by bureaucracy. It seems that Waymo and GM don't find California's permits excessively burdensome. I suspect it wasn't the permits that Uber was trying to avoid, but rather the public reporting of data. The 5600 mile per intervention and 1250 mile per intervention are publicly available data points, the 13 miles per intervention comes from leaked documents.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Lusche on March 24, 2018, 10:20:59 AM
I am still waiting for the promised arrival of the atomic car! :old:
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: icepac on March 25, 2018, 09:07:16 PM
There wasn't even any sidewalk or road from where she was coming.
Did she just walk that bike right out of that park on the left?
It reminds me of when Donte Stallworth got pounded for hitting a guy who was walking across the lanes of this causeway.
Sure, stallworth deserved partial blame since he would not have hit the guy if he weren't driving (he was buzzed) but who knows if a designated driver wouldn't have hit the guy if you put the car and pedestrian into the same sequence of events.
There wasn't even any sidewalk or road from where she was coming.
Did she just walk that bike right out of that park on the left?
It reminds me of when Donte Stallworth got pounded for hitting a guy who was walking across the lanes of this causeway.
Sure, stallworth deserved partial blame since he would not have hit the guy if he weren't driving (he was buzzed) but who knows if a designated driver wouldn't have hit the guy if you put the car and pedestrian into the same sequence of events.
I think the main problem people are having with it is it seems like exactly the kind of thing an autonomous vehicle should be great at detecting. As Skuzzy said upthread, the LIDAR theoretically has a range of 500 yards.
A human might've been looking the wrong way at the moment the pedestrian became visible or been slow to react. The way AVs have been sold to the public is that it won't get distracted, its reaction times are way better than human, and blahblahblah. Then you see what should be a basic, incredibly simple part of the program "If there's something in the road, avoid it." and it failed spectacularly.
It doesn't matter what crosswalk was where. The fact that there was a living obstacle in the road and the car didn't even seem to twitch is the issue.
Wiley.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Delirium on March 26, 2018, 10:41:48 AM
The populace said cars were too dangerous when they started to appear on the streets in the early 20th century. Some states required someone to walk in front of the car with a red flag for safety reasons. Eventually, people accepted the change and cars began to travel ever faster on improved roads.
Driverless cars will come onto the scene in much the same way. Sure, avoid it as long as you can much like the populace avoided elevators and opted to take the stairs, but no one will be able to stop the flood of technology (short of a nuclear war).
I don't know about the rest of the group here, but I'm looking forward to taking a road trip in a camper one day without actually having to drive the trip itself! (I know we are many years from that)
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Wiley on March 26, 2018, 11:14:32 AM
I don't know about the rest of the group here, but I'm looking forward to taking a road trip in a camper one day without actually having to drive the trip itself! (I know we are many years from that)
It'll be swell when it works. The way there is going to have bumps though.
My main problem with the above footage and the stuff Karnak posted is it appears their product isn't up to snuff, but they're basically gambling with peoples' lives in the meantime.
Wiley.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Karnak on March 26, 2018, 10:43:12 PM
Update:
Arizona tells Uber they can no longer test autonomous cars in the state:
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: FBKampfer on March 28, 2018, 01:16:38 PM
Get em Google, they're vulnerable :old:!
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: ToeTag on March 28, 2018, 08:08:56 PM
If this is ever going to work pedestrian traffic and autonomous traffic has to be seperated. Much like the road system had to be completely redone for interstate travel by modern cars vs carriages, foot traffic and sleighs. Decades away from working.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: 100Coogn on March 28, 2018, 08:21:19 PM
I see some similarities here..
(https://i.imgur.com/2vD20aE.png)
Coogan
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Karnak on March 29, 2018, 12:45:50 AM
If this is ever going to work pedestrian traffic and autonomous traffic has to be seperated. Much like the road system had to be completely redone for interstate travel by modern cars vs carriages, foot traffic and sleighs. Decades away from working.
GM and Waymo are testing them in San Francisco and other California locations. There are lots of pedestrians there. Pedestrians don't seem to be an issue for them, just Uber. With proper programming the autonomous cars should be much safer than a human driver as they don't get distracted and lidar/IR sensors work regardless of illumination.
I doubt we are decades away. We may not even be 5 years away. It just won't be Uber's system that triumphs.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: save on March 29, 2018, 03:12:15 AM
GM and Waymo are testing them in San Francisco and other California locations. There are lots of pedestrians there. Pedestrians don't seem to be an issue for them, just Uber. With proper programming the autonomous cars should be much safer than a human driver as they don't get distracted and lidar/IR sensors work regardless of illumination.
I doubt we are decades away. We may not even be 5 years away. It just won't be Uber's system that triumphs.
I'll bet you my pile of dirt vs. yours. Don't forget this maybe the first tests of AI vs. the public pr machine just to see how we react to "mistakes" which really means deaths...wait it is. OOOps you killed somebody..lets figure out whats wrong with you.....but many people are jailed with no hope of figuring out whats wrong with them....I guess machines are easier to train and the programmers have no death and/or dismemberment issues with the law. Somebody died and somebody needs to be held liable for an ability (they programmed it) to drive a vehicle that they were not actually driving. So in short they said " We got this"...and then.... :devil"My Bad! Sorry fat guy texting! You're Screwed for the rest of your life too!"
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: icepac on April 01, 2018, 10:02:07 AM
Did she walk that bike right out of the grassy knoll on the left?
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: bustr on April 02, 2018, 02:30:33 PM
You watch the dash cam from this article of the moment the driver first looked up, the expression on his face is a good indicator if he was acting as the driver and not a distracted passenger he would have seen the woman. Each of you can identify with his look by remembering how much trouble mentally it is for you to ride in the passenger seat while another person drives. It does not turn off your automated muscle memory reactions from years behind the wheel paying attention as a driver. The film clips of the area after the accident shows the area well lit enough that a "driver" would have seen the woman.
A whole lot of people have egg on their face and how this is being reported to the news outlets is to CYA first. As they show more film, as experienced drivers it looks like a situation a person driving that car would not have hit the woman as the available light at the accident scene is more accurately shown post accident. There is enough ambient lighting that her "pink" bicycle frame would have caught a driver's eye along with the reflective spots on her shoes that showed up brightly in the very first dash cam video. I wondered if the dash cam video chip was not showing the full extent of the surround light. Ever noticed your smartphone chip does not see as much nighttime ambient light and resolve objects in shadow as your eyes? But a $15,000 news camera will becasue that is what $15,000 is paying for.
Wonder if NTSB will require the state police to rerun this with a person at the wheel to determine how much a person would really have seen versus that crappy dash cam video? All they will need is a person with a dark T-shirt and jeans to hold that bike frame at the victim's left hand starting spot while an officer and an observer drives past at the same speed after dark. Bet no one wants that test to happen.
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: SPKmes on April 02, 2018, 03:25:08 PM
That safety driver looks asleep to me.....
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Brooke on April 02, 2018, 04:02:06 PM
Some more autonomous driving for you:
Title: Re: Dashcam footage released Uber Volvo XC accident in AZ
Post by: Wiley on April 02, 2018, 04:05:18 PM
Something something eggs something omelette.
Sad thing is they're likely already statistically better than humans.