×
INTELLIGENT WORK FORUMS
FOR ENGINEERING PROFESSIONALS

Log In

Come Join Us!

Are you an
Engineering professional?
Join Eng-Tips Forums!
  • Talk With Other Members
  • Be Notified Of Responses
    To Your Posts
  • Keyword Search
  • One-Click Access To Your
    Favorite Forums
  • Automated Signatures
    On Your Posts
  • Best Of All, It's Free!
  • Students Click Here

*Eng-Tips's functionality depends on members receiving e-mail. By joining you are opting in to receive e-mail.

Posting Guidelines

Promoting, selling, recruiting, coursework and thesis posting is forbidden.

Students Click Here

Jobs

Self Driving Uber Fatality
11

Self Driving Uber Fatality

Self Driving Uber Fatality

(OP)
San Francisco Chronicle

As noted in the article, this was inevitable. We do not yet know the cause. It raises questions.

It is claimed that 95% of accidents are caused by driver error. Are accidents spread fairly evenly across the driver community, or are a few drivers responsible for most accidents? If the latter is true, it creates the possibility that there is a large group of human drivers who are better than a robot can ever be. If you see a pedestrian or cyclist moving erratically along the side of your road, do you slow to pass them? I am very cautious when I pass a stopped bus because I cannot see what is going on in front. We can see patterns, and anticipate outcomes.

Are we all going to have to be taught how to behave when approached by a robot car. Bright clothing at night helps human drivers. Perhaps tiny retro-reflectors sewn to our clothing will help robot LiDARs see us. Can we add codes to erratic, unpredictable things like children andd pets? Pedestrians and bicycles eliminate any possibility that the robots can operate on their own right of way.

Who is responsible if the robot car you are in causes a serious accident? If the robot car manufacturer is responsible, you will not be permitted to own or maintain the car. This is a very different eco-system from what we have now, which is not necessarily a bad thing. Personal automobiles spend about 95% (quick guesstimate on my part) parked. This is not a good use of thousands of dollars of capital.

--
JHG

RE: Self Driving Uber Fatality

Well, somebody had to be first :)

The problem with sloppy work is that the supply FAR EXCEEDS the demand

RE: Self Driving Uber Fatality

"Are accidents spread fairly evenly across the driver community, or are a few drivers responsible for most accidents?"

Accident rates per mile driven are biased highly towards new drivers (the stats are complex), young drivers, and old drivers. Men are about 50% more likely to crash than women.




"Perhaps tiny retro-reflectors sewn to our clothing will help robot LiDARs see us."

Perhaps, a more promising path is to detect your cell phone.

"Who is responsible if the robot car you are in causes a serious accident? If the robot car manufacturer is responsible, you will not be permitted to own or maintain the car. "

All the main manufacturers for L4 cars have announced they are liable and will self insure, and that current legislation is adequate. I suspect your second sentence is wrong in detail (somebody somewhere will buy an L4 AV) but going in the right direction.

Cheers

Greg Locock


New here? Try reading these, they might help FAQ731-376: Eng-Tips.com Forum Policies http://eng-tips.com/market.cfm?

RE: Self Driving Uber Fatality

Without regard to this crash, there are cases where people try to beat locomotives around crossing arms. There are cases where the driver has limited options. Unlike most accidents, autonomous vehicles are most likely to gather all critical information leading to the crash.

RE: Self Driving Uber Fatality

The graph that Greg posted doesn't even attempt to consider other factors. Within drivers of the same age group, there are some that are highly skilled and others who are scatterbrained and un-co-ordinated, and others that are risk-takers (some intentional, others just unaware of their surroundings). Some are courteous, others are not. There's probably still an order of magnitude between the best and worst even within the same age group.

We all know someone that we don't want to be in the same vehicle with ...

I suspect that automated drivers may be better than the worst drivers, possibly even at today's technology level, but are not even remotely close to the best drivers and may never be.

RE: Self Driving Uber Fatality

I heard, but don't have backup evidence, that the person killed stepped onto a 75 km/hr road from a median and not at a crosswalk. Self-driving car, or human-operated may not have mattered.

RE: Self Driving Uber Fatality

That's what the initial reports are saying. It also appears that both the victim, and the person that Uber had hired to operate the vehicle, had backgrounds that were ... interesting.

RE: Self Driving Uber Fatality

The police comment saying the video made it clear the accident would have been hard to avoid in any kind of mode is rather false for the autonomous mode. Darkness should have little bearing on the car's ability to have detected her. A self driving car could conceivably drive in complete darkness so what a video camera saw really means little on what the car can detect and be capable of reacting to.

To me, it seems that these autonomous cars do fairly well when reacting to something that is going to collide with them or they are going to collide into. But, they seem to be missing some or all of the "this could become dangerous so I should proceed with caution" programming. You could call it lacking prudence maybe? From what the reports have said so far, it sounds like the car decided to proceed at full speed close enough to this woman that it could not react when she changed paths towards it. The Tesla death demonstrated this as one of the faults too, trying to shoot the space between the truck and trailer wheels at full speed.

The car should have slowed and/or moved further away from the woman, even if she was proceeding in a direction that did not indicate she was going to cross into the path of the car.

RE: Self Driving Uber Fatality

Self-driving technology may never be better than the best drivers, but...

It won't get tired, bored, distracted, angry, aggressive, in a hurry, or any of the hundred other things ordinary drivers do. Probably already better than, say, 50% of drivers out there now.

The problem with sloppy work is that the supply FAR EXCEEDS the demand

RE: Self Driving Uber Fatality

Yes, Brian but posting an analysis that shows how good good drivers are and how bad the bad drivers are doesn't really help, I think. Here's the best I could find, I don't know what the source data is, or even what is really being plotted, probably crashes of any type in the last year on the x axis, and the proportion of drivers on the y axis.



The Luck curve is if you just take the average crash rate (20.3%) and do the usual probability on it. Not a whole lot different to the underlying data.

Obviously many meat drivers never have an (injury/fatality) accident in their half a million miles of driving in their lifetime. So accident free meat drivers are a hard target to beat, since they have a perfect record.

So I'd rather look at averages.

Cheers

Greg Locock


New here? Try reading these, they might help FAQ731-376: Eng-Tips.com Forum Policies http://eng-tips.com/market.cfm?

RE: Self Driving Uber Fatality

https://search.proquest.com/openview/5809c2c3cb007...

also has some interesting stuff



I like this graph. What it is saying is that if you have had 0 or 1 crashes in the previous 6 years, there is a 5% chance of having a crash in the next year. If you've had 5 crashes in the previous 6 years, there's a 25% chance you'll have another crash in the next year.

Cheers

Greg Locock


New here? Try reading these, they might help FAQ731-376: Eng-Tips.com Forum Policies http://eng-tips.com/market.cfm?

RE: Self Driving Uber Fatality

Quote (LionelHutz)

The police comment saying the video made it clear the accident would have been hard to avoid in any kind of mode is rather false for the autonomous mode. Darkness should have little bearing on the car's ability to have detected her. A self driving car could conceivably drive in complete darkness so what a video camera saw really means little on what the car can detect and be capable of reacting to.

I know the area in question and it's quite possible that she emerged from the median from behind brush or trees leaving little or no time for a driver (human or not) to react.

Link

RE: Self Driving Uber Fatality

I'd ride a bicycle in a hailstorm before I'd ever get in of those things. Can you imagine? Haven't paid your property taxes? The doors would lock and straight to City Hall you'd go. Say something politically incorrect inside the cab? It'd Mary Jo Kopechne you off the nearest bridge. No thanks.

RE: Self Driving Uber Fatality

Further to Lionel's statement, I think the autonomous systems are lacking in situational awareness in general.

Hmmm. The lane to my right is ending (or is obstructed up ahead). I should allow for vehicles in that lane to merge with the lane that I'm in, by matching speed with them and aligning myself with a space between those vehicles so that the merge can be done without conflict.

Hmmm. I'm approaching a traffic signal. It just turned yellow. My rear view mirror is filled with dump truck. I'm going through this intersection even if it's a wee smidge into the red by the time I get there.

RE: Self Driving Uber Fatality

Quote:

a median and not at a crosswalk

I've heard this defense several times and I really really don't like it. Yes if the person jumped out in front of the car from behind a bush that's one thing, but this suggestion that autonomous cars can't be expected to stop for pedestrians who aren't at cross-walks does the case for autonomous vehicles no favours.

RE: Self Driving Uber Fatality

(OP)
Tomfh,

We do not understand the algorithms used with these autonomous cars. We anticipate that people will cross at crosswalks. We anticipate they will be less likely to cross elsewhere.

A big advantage of LiDAR is that it provides its own light source and ought to detect stuff even in complete darkness. I wonder just how rapidly LiDAR detects everything. I have over thirty years experience with LiDAR. It does a finite number of scans per second. Will it detect and make sense of an object moving somewhere other than along the anticipated track?

Dodging a LiDAR equipped vehicle is not the same thing as dodging a vehicle driven by a human.

I slow right down when I pass groups of pedestrians, especially children, when I drive down narrow lanes and in parking lots. How will a robot anticipate threats like this, and how well behaved will humans be when they are following this robot as it tries to interpret threats?

--
JHG

RE: Self Driving Uber Fatality

Quote (drawoh)

I slow right down when I pass groups of pedestrians, especially children, when I drive down narrow lanes and in parking lots.

Yeah, you do, I do, but plenty of people don't. Don't get me wrong, the tech has got a ways to go. It'll get better, human drivers will not. My experience is, the cars get better and better, the drivers get worse and worse.

The problem with sloppy work is that the supply FAR EXCEEDS the demand

RE: Self Driving Uber Fatality

For those who are statistically minded-
There are a certain number of pedestrians killed each year.
And various autonomous cars get in a certain number of miles each year.
Just based on the miles, how many pedestrians would expect to have been killed by autonomous cars?

By the way, how do we know this was an accident, anyway? Isn't that car "autonomous"? It could very well have been intentional.

RE: Self Driving Uber Fatality

Given that link to the location, comparing video from the scene and the Google street view shows the car was on Mill Ave travelling north.

The news reports say she was walking and pushing the bike, and if that is true then she wasn't travelling particularly fast.

The right side of the SUV has the damage so the woman most likely came from the right side into the path of the SUV. If she came from the median on the left then she crossed almost 4 traffic lanes before the SUV hit her which certainly goes against any claims that she suddenly stepped in front of the SUV.

It also appears the accident occurred across from the second leg of the X in the median just past the road drains in the right side curb. Since the ground is rough and hilly past the sidewalk in that area, I find it hard to believe the woman was travelling perpendicular to the roadway or outside the sidewalk before entering the roadway. That location also has a sidewalk and a bike lane between any vegetation and any excuse saying she jumped out from behind a bush doesn't hold much water.

My expectation is that she was travelling southbound on the sidewalk or in the bike lane and then turned to her right to cross to that X path going across the median. Crossing Mill Ave completely and heading into the parking lots or below the overpass on the west side would be as likely a general direction of travel as any.

An alert and aware driver would know the path of someone coming southbound on that sidewalk might turn towards that path through the median.

How much foot and bike traffic is in that area? Would regular drivers of that section of roadway specifically watch for bikes or people on foot crossing at the ends of those X paths?

On another note, that X path "to nowhere" through the median appears to be one dumb road feature. It has no useful function except to dangerously tempt people to shortcut across Mill Ave.

RE: Self Driving Uber Fatality

The statistical angle is the entire point of the graphs I found. The best human drivers have perfect records. The worst human drivers smash into things quite often. Whether AVs are worth having very much boils down to where, within those extremes, on average, AVs fall out. My guess is that from say 1 pedestrian death in (WAG) 10 million miles that they are doing worse than the average driver. But according to the first graph I posted, in 10 million miles even the best cohort of drivers would expect 4 crashes per million miles, or 40 crashes in 10 million miles.

I don't know what proportion of crashes result in pedestrian deaths, I don't know how much that 4 per million has changed since 1990 (quite a lot actually), but what I do see is that the numbers aren't immediately screaming that prototype AVs are just randomly mowing down people right, left and centre.

Cheers

Greg Locock


New here? Try reading these, they might help FAQ731-376: Eng-Tips.com Forum Policies http://eng-tips.com/market.cfm?

RE: Self Driving Uber Fatality

I have read some interesting commentaries that basically stated the "AI" in these cars is doing a lot of learning by example and a huge amount of data processing. Together, this makes it impossible to log the details of the object processing and subsequent step by step decision making. In other words, it's difficult to figure out exactly why the car did something.


Greg - No the cars are not displaying any signs of being particularly dangerous. But they should do much better than a human, especially in conditions that make driving more difficult. We'll likely never see the detailed report on the accident, but from what I have see so far it appears this accident could have been avoided if the right precautions were taken as the car approached the woman.


From the video in the news reports, belongings were on the ground approximately above the "N Mill Ave" in this street view

RE: Self Driving Uber Fatality

Wouldn't the more sophisticated control system be expected to be more responsible for avoiding the collision? For certain we don't have a handle on how the non-AI works.

RE: Self Driving Uber Fatality

News: "...10PM... Pushing a bicycle laden with plastic shopping bags, a woman abruptly walked from a center median into a lane of traffic..."

Assume for a moment that the pedestrian in this case was visible, while still walking on the median.

A human driver might have been able to make some assumptions about those circumstances - seeing what is probably a homeless person, in the median, at 10PM, and therefore assume that they're perhaps somewhat less predictable than normal. So an attentive and cautious human driver might either slow down or perhaps even change lanes if possible. Mental alarm bells should be ringing, because of the context.

To help make this point crystal clear: an attentive human driver would certainly take extreme caution if they saw a toddler or small child wandering around in the center median, within a few steps of the lane, not firmly holding hands with a parent. In such an extreme example, one would probably even turn on the 4-way flashers, stop, rescue the child, call the police, etc. Would an autonomous vehicle have any such inkling of the increased risks? Do autonomous vehicles understand 'children', 'holding hands with a parent' and 'not trying to wriggle away', or 'the homeless' yet? It seems not.

It's going to be a very long time before autonomous vehicles have any common sense about the real world. And without such common sense, they'll inevitably get them themselves into accidents of a different sort than would a cautious human driver.

At this point the proponents are forced to abandon any overhyped claims about an AI-driven "Accident-Free" Utopia. (Yes, such ridiculous claims have been made; perhaps from the sidelines and/or marketing departments.)

The more rational proponents can retreat to statistical comparisons, and claim autonomous superiority once the lines cross. While such a comparison is reasonable, it still leaves a vast legal and regulatory quagmire to be sorted out.

RE: Self Driving Uber Fatality

(OP)
3DDave,

Your link explicitly describes the problem I was noting. The LiDAR's range and resolution are not sufficient for cars travelling at highway speeds. Think through what the LiDAR or video camera has to do. It has to recognize the object. It has to recognize that this is the same object it saw 100ms ago and that it has moved. If the object is moving steadily, the robot can conclude it will continue to move steadily. Can the robot detect erratic movement or even someone's head turning to indicate a sudden change of direction, possibly in front of the robot?

--
JHG

RE: Self Driving Uber Fatality

Quote (JHG)

Personal automobiles spend about 95% (quick guesstimate on my part) parked. This is not a good use of thousands of dollars of capital.

Autonomous Cars may indeed lead to much more Car Sharing, so these quite separate and distinct topics are related.

[To be clear, referring here to Car Sharing (alone, one by one) not Ride Sharing (i.e. car pool).]

It's worth noting that Car Sharing inherently increases total distance driven, road usage, traffic, energy (fuel) expended, and wear and tear. Applies to Taxicabs, Uber services, or any future autonomous fleets wandering around.

Because (A-to-B) + (C-to-D) < (A-to-B) + (B-to-C) + (C-to-D), where (B-to-C) is the 'extra' movement.

Nobody ever seems to think about that. Which is annoying considering how obvious it is. At best, there's some hand waving about future efficiencies somehow compensating for the extra distance.

The distance ratio could probably be determined by asking Taxi or Uber drivers about their total working mileage per year versus how much of that is 'paid' mileage. It would presumably vary by location. Hopefully it's more efficient than 50%, and it can't be 100%; so I'd guess it's about 75%.

Yes, there are many obvious upsides of Car Sharing; but they're well known.

RE: Self Driving Uber Fatality

Most drivers currently cannot accurately detect that. At least not so as to take evasive action. Instead they usually just hit the horn and expect the other person to cope. The benefit of AI cars will be that they behave uniformly.

RE: Self Driving Uber Fatality

(OP)
VE1BLL,

I also did not account for heavy usage of automobiles at rush hour, when maybe half of them are on the road.

--
JHG

RE: Self Driving Uber Fatality

As in the case of the Tesla accident, it's likely that the AI is simply maintaining context information. In the Tesla case, the truck that was hit had to have been detectable prior to it turning across the road, but it's likely the Tesla had essentially "forgotten" that there was even a truck in the vicinity.

Likewise, it's likely the LIDAR on the Uber detected the victim well before the impact, but essentially forgot the detection once a new set of detections were acquired.

We used to have a guy that worked on tracking algorithms, and when queried about why the tracker had clearly ignored a previous detected target, he stated, "Oh, I only use data from the current frame for detections."

A human driver, having detected a pedestrian might pay more attention than normal to insure that the they can avoid the consequences of the pedestrian doing something silly, which the victim did. If I see a pedestrian too close to the road edge, I will sometimes change lanes to be further away, just in case.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

Quote (GregLocock)

Accident rates per mile driven are biased highly towards new drivers (the stats are complex), young drivers, and old drivers
.

Does this account for young drivers doing most of the driving?

Dik

RE: Self Driving Uber Fatality

(OP)
IRstuff,

If the robot cannot maintain context information, then it cannot determine the direction and velocity of whatever object it sees. I noticed this this morning with my car GPS. It does not know what direction I am pointed in until I start moving.

--
JHG

RE: Self Driving Uber Fatality

"...the Tesla had essentially 'forgotten' [about the] ...truck..."

Based on the reports, I thought that the Tesla had failed to even see the truck due to a lack of contrast against the sky. It had been mentioned that the Tesla had utterly failed to brake before, during, and even after the crash. It was a fairly comprehensive failure, seeming to do precisely nothing correctly.

Perhaps the findings have changed since I last saw it.

Old curse: "May you live during interesting times."

RE: Self Driving Uber Fatality

I have a rental car for the week. It has lane-departure warning that's supposed to beep at you when you go out of your lane. The display also indicates whether it is currently recognizing the lane.

It only works with painted lane markings that are clearly visible.

It doesn't recognize guardrails, unmarked roadways, painted lines that are worn down or obscured by dust or dirt or damaged/repaired pavement. If there is a visible transition in the pavement that is separate from the painted lane marking (e.g. in construction zones where the temporary lane position doesn't correspond with what it's meant to be by design) it sometimes sees the wrong one and false-triggers. It gets confused on curves. It gets confused in roundabouts. If I intentionally shift to the side of a clearly marked lane for a rational purpose - e.g. to be further away from a vehicle that appears errant or is throwing off wind-buffeting, or to smooth out an errant lane marking - it beeps because it doesn't realize that what I'm doing has a purpose. I haven't tried it in rain at night when the shine from the rain makes lane markings hard to distinguish.

In other words, it works only in situations where it isn't needed, and it hardly ever works in situations where it might serve some purpose.

I've had other rental cars that have blind-spot warning systems (this one doesn't have that) and they don't detect something coming up from behind in the adjacent lane at a significant speed difference. They don't look far enough behind. IIRC the Germans criticised Tesla's autopilot for that ... and in a situation where you're doing 130 km/h and the car coming up from behind is legally doing 230 km/h, that's pretty important.

RE: Self Driving Uber Fatality

"Based on the reports, I thought that the Tesla had failed to even see the truck due to a lack of contrast against the sky. It had been mentioned that the Tesla had utterly failed to brake before, during, and even after the crash. It was a fairly comprehensive failure, seeming to do precisely nothing correctly."

The claim was that the sides of the trailer were white, and confused the image processor. But, it order for the side of the trailer to get that far into the field of view of the camera, the tractor had to have passed through the field of view, so the image processor must have "seen" the tractor, but didn't worry that it couldn't see the trailer.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

The Tesla could 'see' that the road was continuous under the trailer, just the same as it can 'see' the road is continuous under overpasses and overhead signs. It did not matter that it could see the tractor leave the path; not all tractors have trailers.

Look at 11foot8.com. Which just nailed a 'secret military' truck. Even humans stink at this and that's with warning signs, flashing lights, and every other option available to deflect the stupid from hitting a bridge that is older than most people. And people wonder why military equipment costs so much.

RE: Self Driving Uber Fatality

The object of issue, the tractor, had passed out of the collision zone. If the car doesn't recognize the invisible trailer that no-longer-dangerous tractor is hauling, we're still back to the fact that the software did not recognize a secondary danger. The tractor is no different than another car... so we we write the algorithm to more fully recognize a tractor and expect a trailer might be attached, no matter the color?

Dan - Owner
http://www.Hi-TecDesigns.com

RE: Self Driving Uber Fatality

"...must have 'seen' the tractor, but didn't worry that it couldn't see the trailer."

A.I. sometimes means Artificial Imbecile. smile

We'd all be safer if the decision makers kept this in mind.

RE: Self Driving Uber Fatality

For the Tesla accident, forget for a moment that it failed to identify the trailer. What I consider the second and worse failure of the Tesla goes like this. It should have detecting the wheels of the trailer moving towards it's path. So, a truck (or big car) had just crossed it's path and another object was moving towards it's path. I have no idea what it thought the trailer wheels were, but if a vehicle had just crossed your path and there was another "thing" moving in that same direction then wouldn't you proceed with caution instead of trying to blast through the gap at full speed???

RE: Self Driving Uber Fatality

The Google street view of the Tesla accident location shows it was a quite flat stretch of road. The wheels would not have been hidden as the car was approaching.

RE: Self Driving Uber Fatality

The police released the video. Two things stand out. One is that all reflectors look to have been removed from the bicycle, including the critical ones on the wheels. The other is that the 'projector' head lamps produce such a sharp cut-off that no light is above the cut-off, meaning the contrast is extreme. Frankly, I would place a lot of blame on the head lamp design, which puts far too much light close up and produces so much contrast that anything outside the beam is practically invisible.

I think that the woman would have been more visible if the headlamps were off and the amplification of the image higher.

Not helping is what looks like a black jacket and low levels of lighting from local streetlamps. Also it's not helping that neither the driver nor the pedestrian seems engaged with the situation.

I don't know if an alert driver would have done much better. Even though I know where the victim will be, until less than 1/2 second from impact I can't make out any evidence of her. There was no lighting behind her that was being eclipsed as she went across the road; not even from retro-reflective striping paint on the road.

I expect the NTSB will be interested in this and I look forward to a report as to why the Lidar and radar sensors specifically failed to detect her. There should have been plenty of time for several cycles. It wouldn't even require target path prediction.

RE: Self Driving Uber Fatality

(OP)
Slate magazine has linked the video (warning, warning, etc.). In the video, she was not visible until the last split second. I assume the headlights were dimmed, but I would think there should have been more forward visibility than what we see.

It looks like she crossed between areas lit by streetlights. I wonder how well cameras respond to changes in light level. Our (human) eyes cope way better at changing light levels than digital cameras. This may be part of learning to walk in the vicinity of robot vehicles.

--
JHG

RE: Self Driving Uber Fatality

Quote (SnTMan)

My experience is, the cars get better and better, the drivers get worse and worse.
A Truism if there ever was one!! thumbsup2

"Schiefgehen wird, was schiefgehen kann" - das Murphygesetz

RE: Self Driving Uber Fatality

That's a very bad video for UBER. When driving at night you can see objects in adjacent lanes ahead. Combined with the LIDAR there is no excuse for the car's object avoidance to have failed so badly. It didn't even attempt to slow down.

RE: Self Driving Uber Fatality

I agree it's bad. They're not showing the LIDAR data, which should have detected the person well before they show up in the video.

The LIDAR should be able to detect obstacles out to well past 200 ft, so it had to have detected the person at least 2.5 seconds before the person was visible in the video. This is a major fubar in the systems engineering.

The Uber should also have a radar, which should also have detected the person.

This is again a context issue, since even a non-moving obstacle in what should have been an unoccupied lane is a major deviation from normality. Moreover, given the range and the obvious motion of the person, the sensors should have been able to easily determine that there was going to be an intersection in trajectories.

The Uber supposedly has a "camera array," and at least some of them should have been configured for low-light.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

(OP)
IRstuff,

The LiDAR does not require ambient light. Then again, there is a huge confict between resolution and scan rate. I think Elon Musk may be right about LiDAR.

--
JHG

RE: Self Driving Uber Fatality

Didn't say it did. The Uber has at least one camera as evidenced by the video, but there are also other cameras angled to the side. One would think there would also be low-light cameras as well.

Below is something like what the lidar should have seen. I think Musk is crazy. Humans get into accidents precisely because they don't have enough bandwidth and detection capability; this is where lidar or radar could trivially provide additional sensing and processing capability. Hypothetically, the video is what a human driver might have been able to see, but lidar would have and should have detected the pedestrian and provided warning that something was in the adjacent lane coming up. Had it been working correctly, it should have also determined that the anomaly was moving toward the car's own lane.




TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

We were flying a helicopter obstacle avoidance lidar in 1994 with only about 100 kHz pulse rate. We weren't trying to detect collisions against movers, though, but today's processors are more than capable of doing so. And, today, at least 10x higher pulse rate should be possible, particularly for only 1/4 of the range that we were achieving.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

She did cross from the path in the center meaning she did cross about 3.5 lanes width of open road before getting hit. That was nothing abrupt about her movement despite what the news reports claim.

That video makes the incident very damning against uber. The car totally failed in detecting an object that was clear visible to it's sensors and was crossing into it's path for some time before the impact occurred. I'd guess she would have been on the road and easily detectable for 4-5 seconds before the impact happened which is lots of time for the car to react.

Feet appear in the video maybe 1.5 seconds before the collision. At 38mph, that is about 85 feet. I've never been in a Volvo with HID projector lights, but I've been in other cars with them and the low beams project enough light to make objects in front of the car visible to a distance that is much greater than 85'. So, I would say the camera taking that video suffers from a contrast limitation limiting the visible distance compared to what a human could see.

I'd bet a driver who was paying attention and is capable of steering avoidance instead of just freaking out and slamming on the brakes could have avoided her. The autonomous driving system should have easily avoided her too.

Blaming the sensors is a non-starter. If that accident was caused by sensor limitations, then better sensing must be developed for these cars.

Musk's argument is hinged on that fact that it's an expensive sensor so the system will be much cheaper without it.

RE: Self Driving Uber Fatality

Not blaming the sensors; blaming the processing of the data.

Just because it could be cheaper doesn't mean that it's the right answer, particularly if it winds up being no better than a human with terrible night vision.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

@dik, "Does this account for young drivers doing most of the driving?"

The first graph is per million miles so yes I think that it does account for the higher annual mileage of younger drivers.

Cheers

Greg Locock


New here? Try reading these, they might help FAQ731-376: Eng-Tips.com Forum Policies http://eng-tips.com/market.cfm?

RE: Self Driving Uber Fatality

One of the factors in driving statistics is that they become heavily skewed with highway miles. There are fewer chances for interactions between pedestrians and vehicles on interstates and rural highways. Even with the following breakdown, a critical segment of information that is missing are the primary and secondary opportunities for collision. For example, this collision was a primary opportunity, where a pedestrian has a clear view and probably can hear the oncoming vehicle and positions themselves in the lane. Secondary opportunities are when pedestrians are on the edge of the lane or on the sidewalk in a location that requires a vehicle to leave it's position in the lane to strike them.

My supposition is that most miles driven have either no pedestrians present at all or have only secondary opportunities. One might argue about places like downtown Manhattan where in some areas and times pedestrians would be trapped if they were to never step into traffic lanes, but they are cognizant that drivers are less likely to yield, but that is more of a parking lot situation than a driving one.

In the following it seems to me that the largest factor is pedestrian behavior. Buses are probably very high because they are attractants and dispersants of pedestrians; lots of people on foot nearby and operate in the lane alongside sidewalks. Heavy trucks are probably low because they don't operate near pedestrians (example: fewer people near warehouses) and pedestrians can easily identify them.

(reformatted from http://injuryprevention.bmj.com/content/11/4/232 , says is based on 2002 US DOT statistics)
(Edit: RR = Relative Rate)

Passenger cars and light trucks (vans, pickups, and sport utility vehicles) accounted for 46.1% and 39.1%, respectively, of the 4875 deaths, with the remainder split among motorcycles, buses, and heavy trucks.

Compared with cars, the RR of killing a pedestrian per vehicle mile was
7.97 (95% CI 6.33 to 10.04) for buses;
1.93 (95% CI 1.30 to 2.86) for motorcycles;
1.45 (95% CI 1.37 to 1.55) for light trucks, and
0.96 (95% CI 0.79 to 1.18) for heavy trucks.

Compared with cars,
buses were 11.85 times (95% CI 6.07 to 23.12) and
motorcycles were 3.77 times (95% CI 1.40 to 10.20)
more likely per mile to kill children 0–14 years old.

Buses were 16.70 times (95% CI 7.30 to 38.19) more likely to kill adults age 85 or older than were cars.

The risk of killing a pedestrian per vehicle mile traveled in an urban area was 1.57 times (95% CI 1.47 to 1.67) the risk in a rural area.

RE: Self Driving Uber Fatality

It's taken a long time to get to something that even remotely resembles a true AI, and it's still got a long way to go. AIs are going to get drunk, and aren't going to fall asleep, and that latter feature would have been a godsend back when I was driving back home from college after pulling a week of all-nighters. Micronaps at 90 mph was scary. But, clearly, the Tesla and Uber incidents show that the AIs still have a long way to go before they're as robust as I think they should be. Neither of those two accidents seem to be a fault of the sensor technology; they seem to be a fault of the systems engineering or the programming, as both look to be well within the possible use cases.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

(OP)
IRstuff,

Take your digital camera out and try shooting in limited light. Film emulsion, CCDs, and CMOSs do not have the bandwidth of a human eye. That woman was invisible to the camera until the last split second. She would not have been invisible to the driver if he had kept his head up.

--
JHG

RE: Self Driving Uber Fatality

IRstuff, and they don't take their eyes off the road to text either.
Just this morning, I was on the same road where this accident happened- the car in front of me drifted over the lane divider line and stayed there for close to a quarter mile. Too busy texting to even realize that they were taking up 2 lanes.

I have been driving in the area they have been testing these vehicles for many months. I was skeptical when they started doing this, but I have never seen one make what I would consider a dangerous maneuver.

The more we hear about the Tempe accident, the more it sounds like it was probably the pedestrian's fault. There are many large bushes along this stretch of road, it seems likely that the sensors didn't even know the pedestrian was there until it was too late. One of the scariest moment I had while diving (only a couple miles from this site), was when a mountain biker darted out from behind some bushes while I was driving the speed limit. He came to a quick stop and almost went over his handle bars just a few feet in front of me. There was no warning that he was approaching (he was not on a trail)- and I would have had no chance of stopping if he had continued into traffic.

RE: Self Driving Uber Fatality

"Take your digital camera out and try shooting in limited light. Film emulsion, CCDs, and CMOSs do not have the bandwidth of a human eye. That woman was invisible to the camera until the last split second. She would not have been invisible to the driver if he had kept his head up."

btw, the safety driver was a woman. But, this is not your, or my, digital camera; any intensified camera with IR cut filter removed can see in starlight alone. Moreover, even the tiny bit of light from the headlights would be more than enough for even a moderately intensified camera, or even an HDR camera. It's unimaginable that the engineers wouldn't have at least run HDR, which is even available on cell phones, specifically for this type of use case. HDR, when properly implemented, substantially outperforms the instantaneous dynamic range of the human eyeball. The headlights could clearly illuminate adjacent lanes out to at least 100 ft, so HDR should have picked up the pedestrian in video camera.

And, since this is NOT a Tesla, the lidar, as was pointed out earlier, doesn't need any ambient light. If Uber had depended on using just that video for collision avoidance, they should have never gotten authorization for full autonomous driving, and they should be rightly sued for every penny a good lawyer can get from them.
I'm not even sure what you mean by bandwidth; the human eyeball has about a 150 millisecond averaging time, which is why it's typically happy with 24-fps imagery, while even a cheap Epson camera can do 200 frames a second. The pedestrian was WALKING, not running, not riding, a bicycle across the road, so bandwidth isn't even that relevant.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

"The more we hear about the Tempe accident, the more it sounds like it was probably the pedestrian's fault. There are many large bushes along this stretch of road, it seems likely that the sensors didn't even know the pedestrian was there until it was too late. "

The pedestrian is clearly not looking, so to that extent, they could have avoided the incident, but, again, the pedestrian wasn't moving fast, and the only issue, aside from not paying attention, is that they crossed in the worst possible spot in the section of the road, right past where the street light actually lights the pavement. Moreover, they were in the left hand lane, not hiding behind bushes. The car failed miserably in a number of ways in a foreseeable use-case. The pedestrian's feet are clearly visible within the car's lane at about 50 ft from the point of impact. The car should have been braking or swerving well before the impact. Had the car reacted at all in the half-second before the impact, there might a reasonable argument, but it didn't react, even when the pedestrian was fully illuminated by the headlights.

btw, video such as what is posed on the web, doesn't come close to displaying the true dynamic range of even the cheapest camera. There's almost nothing on the market that doesn't digitize at least 12 bits/color, but most video formats are 8-bit/color. And not to mention that display video uses AGC, which suppresses detail that might otherwise be clearly visible. It's certainly in Uber's financial interest to NOT show what the cameras probably did see.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

Clearly a pedestrian bridge over Mill at this location is needed.

RE: Self Driving Uber Fatality

Quote (drawoh)

IRstuff,

Take your digital camera out and try shooting in limited light. Film emulsion, CCDs, and CMOSs do not have the bandwidth of a human eye. That woman was invisible to the camera until the last split second. She would not have been invisible to the driver if he had kept his head up.

That vehicle had LIDAR. It should have seen the bike and person regardless. But anything reflective like those shoes or bicycle reflectors would have been screaming at that sensor.

It most likely is a breakdown in processing and programming. Even with our limited vision relative to LIDAR, we can differentiate between a couple of mylar potato chip bags blowing across the road and a pair of tennis shoes. Good drivers even have muscle memory that automatically takes over to avoid those collisions. We can't see animals for anything at night. But those that drive amongst them know that two beady little specs of light low to the shoulder mean to focus our attention if we don't want want to kill someone's pet; and that two beady specs of light at chest height mean to slow down immediately if we don't want to wind up in the body shop.

RE: Self Driving Uber Fatality

"Clearly a pedestrian bridge over Mill at this location is needed."

So long as it's not the one in Florida.

As an example of what HDR can do, right now, the first image is comparable to what's in the video, but the camera probably saw something like the second image, and this is without headlights. Note that the second image specifically remaps the dynamic range of the HDR into a standard display dynamic range. I think the Uber's cameras should have seen what this second image looks like, and not what's in the video on YouTube.



TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

I just saw the dash cam video from the Uber car- I retract my previous statement. The car was in the right lane, and the pedestrian was traveling left to right. She did not come out from behind bushes.
I now agree that the lidar should have seen her.

RE: Self Driving Uber Fatality

Pedestrian behavior is decidedly irrational. I have to pass a church every day on my way home. It's a large church and they must be bad sinners because they have to attend multiple nights of the week. Their parking is on the other side of the street from the church. There are two cross walks at a traffic light complete with push to walk buttons and complete stoppage of traffic for crossing that are almost completely ignored. There are two more cross walks in the middle of the block with signs in the middle of the road and a cop directing traffic. Never the less, the vast majority choose to jay walk. They step out of clusters of pedestrians on the sidewalk or from between parked cars and just head into the middle of the lanes expecting divine protection from the almighty to keep them safe.

----------------------------------------

The Help for this program was created in Windows Help format, which depends on a feature that isn't included in this version of Windows.

RE: Self Driving Uber Fatality

I'm actually surprised there isn't an infrared camera incorporated into their sensors. It would seems that it could easily augment the visual light sensors and associated programming, and would have the benefit of cutting through fog and darkness. Finally, it would highlight cars, deer, and people and allow easy recognition by the computer.

Professional Engineer (ME, NH, MA) Structural Engineer (IL)
American Concrete Industries
https://www.facebook.com/AmericanConcrete/

RE: Self Driving Uber Fatality

Uber uses LIDAR and radar sensors that don't depend on visible light. It's most likely that the suite of sensors did detect the pedestrian and bicycle (they should have been able to), or at least detected "something there", but chose to ignore them.

RE: Self Driving Uber Fatality

2
JHG mentioned, "Film emulsion, CCDs, and CMOSs do not have the bandwidth of a human eye."

The issue here might be the maximum effective contrast ratio.

The human eye is typically much better than cameras to start, *and* can also dart about and quickly peek into the shadows. In the real world, I sometimes hold my hand up to block an overly-bright street lamp, so I can better see into a dark area.

The regulators may have to impose some basic Vision Tests on new self-driving vehicles.

Investigators should consider this when reviewing the video. They might need to ask the next questions:
  • How come your cameras couldn't see the pedestrian?
  • Who specified the inappropriate cameras?
  • Who is your System Safety Engineer?
edit: But if "Uber uses LIDAR and radar sensors...", then it may not be a primary issue.

RE: Self Driving Uber Fatality

I think a vision test is a good idea for a self driving car, as they are required of humans.

I have to ask, would this type of car drive at full speed in fog? Most sane humans would not drive full speed if their vision was impaired.

Also are there any tests of these cars in areas where the roads may not be in the best conditions?

It appears the driving might only be in good conditions, so as to improve reliability numbers.

RE: Self Driving Uber Fatality

The vision test for drivers is more about being able to read signs, as people are often distracted trying to figure out signs. The lighting is a slight dim office ambient, which no way resembles the nighttime ambient of the Uber accident. There are lots of people with odd vision artifacts at night, which aren't tested by the DMV. I don't recall if they even still do the depth perception test.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

(OP)
IRstuff,

Another problem with LiDAR is that when there are a lot of them, they will be seeing each other's signals. This would not have been a problem with this accident on a fairly lonely road, but imagine moving through a downtown intersection.

--
JHG

RE: Self Driving Uber Fatality

Re drawoh's video link: Interesting footage of the safety driver, or whatever they're called...

The problem with sloppy work is that the supply FAR EXCEEDS the demand

RE: Self Driving Uber Fatality

I'll never understand the appeal of those things. I don't even like to have my gears shifted for me.

RE: Self Driving Uber Fatality

Archie264, I kind of look at them the way I do busses. A great thing for other people :)

The problem with sloppy work is that the supply FAR EXCEEDS the demand

RE: Self Driving Uber Fatality

With my deteriorating vision and limbs I'm actually hoping they get these things working by the time I'm no longer able to drive myself. They've got about a dozen years (I hope).

----------------------------------------

The Help for this program was created in Windows Help format, which depends on a feature that isn't included in this version of Windows.

RE: Self Driving Uber Fatality

"Basic vision tests" will result in the programmers gaming the test. Designs are tweaked to pass specific tests all the time ... sometimes legally/legitimately, sometimes not.

I have a feeling, but nothing more, that the issue here wasn't whether the pedestrian and bicycle were detected, but that the underlying logic chose to ignore it.

If there is a pothole, or a bump, or a painted road marking, or a small piece of debris, lying on the road directly in front of the car, you don't want the self-driving logic to slam on the brakes or take drastic evasive action.

Somehow the system has to distinguish between something it needs to avoid, and something it can safely ignore and drive over or through.

Select wrongly ... and a situation like this one happens.

RE: Self Driving Uber Fatality

(OP)
VE1BLL,

Thanks. That was the term I was looking for.

--
JHG

RE: Self Driving Uber Fatality

She was probably classified as an inanimate fixed object, like a bush. Inanimate fixed objects stay on the side of the road and don't end up in the vehicle lane so they're not a threat. Sure, it was an oddly moving bush, but still a bush is nothing to be concerned about.

IRstuff - I didn't say you were blaming the sensors. I was just making a general observation that that any excuse about her not being detectable is complete BS. You and I are both on the same page believing this was a complete and utter fail for the AI system.

As I already pointed out, the distance where she becomes visible is much closer than the distance I can see when behind the wheel. So the camera that was filming that video definitely had a contrast issue and did not show what a human could see. It very much works in Uber's favor, at least for the people who are clueless about the capabilities of the camera used to film that video and/or the capabilities of the sensor package being used by the AI driving the car.

RE: Self Driving Uber Fatality

As I said before, I don't believe that the video that was posted is a reasonable rendering of the actual video data that resides in the car. The actual navigation video is probably as damning as the lidar and radar data.

The issue with the bush theory is that it's in the car's lane for at least one second (from the time the feet are visible to the time of impact), and no warnings, no detections, and no braking occurs.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

Regarding the bush theory, not only is she in the travel lane in which she was hit for nearly 2 seconds (4 steps), she had crossed some 35+' of paved travel lanes to get there. Kind of ironic that there is a "BEGIN RIGHT TURN LANE - YIELD TO BIKES" sign right there.

Here is the link to where she was hit. https://goo.gl/maps/9qhLm8pJhcE2

She had the potential to be seen for over 300' from where the Volvo came out from under the overpass. The second picture is the streetview from that vantage point.


RE: Self Driving Uber Fatality

Quote (drawoh)

Another problem with LiDAR is that when there are a lot of them, they will be seeing each other's signals.

Oh will they end up scrambling each other's vision? Like everyone shinign torches in each otehrs face?

RE: Self Driving Uber Fatality

There are potential ways to avoid interference, such as the protocols used by GPS to avoid interference between satellite signals. One of the reasons cold boot takes a long time is that the channel receivers have to decode the sequences and then verify that that all the signals being received are consistent with the receivers decoding of the signals.

Alternately, one could imagine using something like programmable quantum cascade lasers with unique wavelengths.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

I presume these cars must have some kind of "decision log" .. "I have detected XYZ therefore I shall do ABC in response".

I wonder what this log would show in this case? I would be willing to bet that the woman + bike was detected by the sensors, but for whatever reason was not attributed to be a threat to be avoided? Perhaps she looked like a motorbike merging from the left into the lane in front of the car, and thus did not need to be avoided?

I wonder what decision is made when it is 'too late' to avoid a threat in a safe manner? Do you prioritise occupant safety (e.g. avoid sudden / dangerous braking which might result in a pile up) or do you prioritise pedestrian safety (and do absolutely anything possible to slow down before hitting them, even if this might escalate into a pileup)?

The video of the 'person behind the wheel' is shocking. The amount of inattention she is paying is criminal.

RE: Self Driving Uber Fatality

Don't like bush. Tumbleweed???

The Tesla decided the truck trailer which was in the path of it's windshield was not a concern since it was classified as an overhead sign and signs don't move and cars are supposed to be able to drive under them....

The most likely cause was her being classified wrong caused the "AI" to decide she wasn't a threat the car could hit. Being classified as a motorcycle travelling the same direction and changing into the same lane doesn't make much sense from the point that the car was rapidly approaching it, and it should brake or otherwise to try to avoid any another vehicle it is rapidly approaching. Being classified as an object that the car is not supposed to be able to hit makes more sense than a wrong one that moves and that it could hit.

The weather report for Tempe last Sunday says the winds were gusting to 26 mph. Was the foliage on the sides of the road blowing around enough to confuse the "AI"?

We can all speculate, but we'll only find out what really went wrong if/when Uber releases any findings on the accident.

Spartan5 - yes, I already posted a link to the street view pretty much pointing out the spot it happened even before the video was released. So, I'm quite aware of the location and street configuration. The evidence so far makes it quite clear there was lots of time for detection and she didn't abruptly dart into the cars path, so something else went wrong.

RE: Self Driving Uber Fatality

Is it possible to incorporate all LiDAR data to give a better 3D layout of the area?

Dik

RE: Self Driving Uber Fatality

(OP)
Tomfh,

LiDAR fires a laser. A few micronanoseconds after the laser fires, the receiver sees what is called the t0 blast. The LiDAR electronics start counting, waiting for the signal to bounce off something and reflect back into the receiver lens. The receiver probably will have a narrow band interference filter that excludes all light that is not within say 2nm of the laser signal. LiDARs now are fairly rare. That 905nm signal you are detecting almost certainly is yours. If fifty cars all have LiDAR, that signal almost certainly is not yours. You have no way to make sense of the other signals. There is not enough bandwidth to give each vehicle its own laser wavelength, even if this were practical in cost sensitive production.

The company I worked for was developing airborne LiDARs that flew high enough, and ran at high enough laser pulse rates that the lasers were firing before the previous pulse came back from the ground. There were all sorts of tricky electronics for dealing with that. Of course, this would not be a problem for a car approaching woman pushing a bicycle across the highway. LiDAR scanners are a whole lot of fun

--
JHG

RE: Self Driving Uber Fatality

drawoh: Thanks... didn't realise that the pulse it sends out is for timing and distance.

Dik

RE: Self Driving Uber Fatality

lidars measure distance using their time of flight (TOF) [TOF/(2*c) = distance]. Typical pulse widths are on the order of nanoseconds, as are the times of flight; for 100-m radius coverage, TOF is 667 ns.

The design beamwidth of a lidar might be on the order of 1.5 mrad, which is less than 0.1 deg. lidars need to be scanned to cover the 50 deg or so of frontage, so the receivers are aligned with and have fields of view (5 mrad-ish) comparable to the beamwidths. There needs to be a larger receiver FOV than beamwidth to allow for physical misalignment and TOF during the scan. Opposing lidar beam on own receiver will be very, given the small beamwidths and FOVs, and masking by other cars. But, such events are essentially non-events in the sense that the strength of the signals are likely to saturate the receivers.

Returns from cars going in the same direction are likewise relatively rare, as there also masking by other cars, and the limited time and angles over which a Lambertian return can actually get into the FOV of a receiver. Nevertheless, the interference can be mitigated by a pulse-coding scheme with a matched filter receiver. Additional mitigators could be varying the pulse energy as a function of traffic congestion, since having a car 20 ft in front of you means that firing the lidar to find a 100-m distant target is not realistic.

Additionally, the collision avoidance processor needs to maintain a 3D database of detected objects, and generate trajectories as required, and apply a fading memory to kill of older and no longer relevant objects.



TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

Haven't dealt with LiDAR, but I have to wonder what techniques they use that are similar to spread spectrum stuff... Gold Codes and the like. Something along those lines would improve the cross-correlation of "your" signal versus those of the other 500 cars in visible range, but would require a bit more computation.

Also found this interesting snippet:
https://spectrum.ieee.org/cars-that-think/transpor...

Dan - Owner
http://www.Hi-TecDesigns.com

RE: Self Driving Uber Fatality

The victim was walking her bicycle across the road. She was already in the left lane for an extended period. She did not dart out of the shadows; the Uber's headlights eventually reached her. The Uber drove past its headlights range, and its Lidar obviously failed to help.

It's a comprehensive failure.

IEEE Spectrum

Screen capture cropped:

RE: Self Driving Uber Fatality

IEEE Spectrum, "Although the video shows the pedestrian appearing almost out of thin air, she would have, in fact, crossed two turn lanes, a through lane, and half of the Uber car’s lane before being struck—that’s roughly 42 feet. Walking at a speed of 3.5 feet per second, the design walking speed for traffic light 'walk' signals, she would have been on the road for more than 10 seconds before impact."

RE: Self Driving Uber Fatality

Maybe a dumb question, but who called this in?
Would the car automatically do this? Or would it have kept on going?
Can an AI be ticketed for hit and run?

RE: Self Driving Uber Fatality

Daytime view of that location attached. The accident would have been approximately where the car in the right lane is located in the picture.
Note the pavers in the median on the left side. Just off the picture is a no walking sign the city posted in that area. I gather this must have been a problem even before this incident.

RE: Self Driving Uber Fatality

Regarding “coming out of the shadows;” locals are starting to draw attention to just how poor the quality of the video that has been released is relative to what it is actually like at night there.

Another dash cam still from that exact spot:

RE: Self Driving Uber Fatality

The police essentially aided and abetted Uber in potentially steering public opinion about their culpability in the accident. This is a huge fail, particularly given the example dashcam image with decent histogram equalization.

Uber shot themselves in the foot with their video, because the better video shows that TWO sensor systems failed to operate correctly; the video cameras should have been capable of seeing the pedestrian, and simple change detection would have detected the lateral motion into the car's lane and the lidar likewise should have detected the pedestrian from double or triple that distance.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

Incidentally here's a video of a LiDAR system in action https://youtu.be/_EMAoiqLq9Y

Eyeballing the resolution and range the LiDAR was functioning it seems hard to believe that it would not have picked up a pedestrian several seconds before impact.

Here however is an old blog on the subject https://recast.ai/blog/the-era-of-smart-cars-focus...

"The most common errors for detectors are:

detecting tree leaves or traffic lights in background as pedestrian
detecting the same person twice
not detecting small persons
not detecting cyclists"

oo er.

Cheers

Greg Locock


New here? Try reading these, they might help FAQ731-376: Eng-Tips.com Forum Policies http://eng-tips.com/market.cfm?

RE: Self Driving Uber Fatality

Seems like all those issues are not the "detector's" issues, per se, assuming we define detector as the transmitter and receiver. The issue is what to do with the detections that must obviously have occurred, which is a processing problem. The target trackers for ballistic missile defense were capable of tracking hundreds of targets simultaneously, and the trick is to figure out trajectories of the targets and whether the trajectories will cross into the car's lane.

US football receivers running at their fastest would seem to be a plausible upper bound for "pedestrians" at about 28 ft/s. This would suggest that the lidar needs to have a frame rate on the order of 5 to 10 Hz to be able to correlate runners as single targets moving at a high rate. Slow targets might be the senior citizen in front of me in the supermarket, moving at about 0.5 ft/s. Usually, the big challenge isn't the targets, it's the obscurations, such as when a slow moving target walks behind a wall or billboard. A conventional tracker might get fooled into thinking the target came to stop at the leading edge of the obscuration and decide not to look for the target to re-emerge on the far side of the obscuration. Faster targets are less problematic with obscurations, but they aren't problem free.

Lidars have one serious limitation that makes the processing so difficult, and that's shadows, i.e., the areas behind objects that block further transmission of the laser and where pedestrians tend to suddenly emerge into traffic.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

I've seen suggestions that target /recognition/ might have been more difficult because she was behind the bike. Does this mean that Uber cars will intentionally run into things 1.5m tall and 2 m wide simply because it can't recognise them? I'd have thought not hitting large objects was pretty much AV 101.

This is different to the Tesla invisible truck problem because the Tesla system lacks a LiDAR, so it has to have good visual analysis.

Cheers

Greg Locock


New here? Try reading these, they might help FAQ731-376: Eng-Tips.com Forum Policies http://eng-tips.com/market.cfm?

RE: Self Driving Uber Fatality

The bike was behind her. The only thing that would explain the behavior is if the AI classified the inputs as a vapor cloud. I would say that adding a thermal camera would be the best discriminator for such an event.

RE: Self Driving Uber Fatality

"This is different to the Tesla invisible truck problem because the Tesla system lacks a LiDAR, so it has to have good visual analysis."

And it failed miserably at that. Change detection should have detected the sudden presence of a "overhead sign," and that alone should have been an issue. The fact that the "overhead sign" went below the clearance level of the car and it didn't conclude that was a problem, is a problem. The fact that it failed to detect the wheels and undercarriage of the truck as anomalies is also a problem.


TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

Quote (IRstuff)

The police essentially aided and abetted Uber in potentially steering public opinion...

At least we can be thankful that Uber is such a model corporate citizen with no history of ethical misfires. They've always acted in accordance with only the highest moral principles. So we can rest assured that they'll fully cooperate, honestly and openly.

--

One of the mistakes that newbie or bad drivers can make is looking for obstacles ahead. The correct logic is to look for empty road ahead. (The wording here is a simplification, but I trust that the point is clear.)

Perhaps autonomous vehicles should be subjected to a blinding Sudden Fog Bank Test. Or a Blind Curve (with too generous speed limit) Test. Such testing should be complete with a brick wall final exam.

I'm not sure that this 'safe driving logic' point is related to what happened here. Although it seems to have driven straight into a non-empty road.

So far this accident seems inexplicable. Explanations offered so far are not merely 'lessons learned', but massive failures.

RE: Self Driving Uber Fatality

I don't disagree that some sort of testing to verify a minimum threshold of capability needs to be performed, particularly after this.

However, I'm struggling with how trivial this scenario ought to have been. This is like worrying about a kindergartener running well, when they seem to have failed to tie their shoelaces.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

Capability tests will be "gamed". The systems will be programmed to pass them. The problem is for the systems to react properly to situations that they were not explicitly programmed for, and those will be the situations that for whatever reason (sometimes seemingly inexplicable to humans) fell through the cracks. Situations like, oh, driving underneath an overhead sign board through the gap between the back of a truck and some other unknown moving object about 40 feet behind it, or failing to recognize a bicycle that is being pushed rather than ridden as something that perhaps shouldn't be hit.

The above statement that drivers (whether human or otherwise) should be aiming for empty road is an extremely important one. It's still not without its share of headaches.

Does a pothole disqualify empty road? A little pothole? A big one? A sinkhole? Where's the threshold between stopping/swerving and driving over or through it?

Does a piece of paper ahead disqualify empty road? A small piece of debris? A truck tire tread? A squirrel? A cat? A dog? A small deer? A moose? A small human? A big one? Where's the threshold? You do not want self driving cars dodging a plastic bag or stopping in a traffic lane of a motorway.

RE: Self Driving Uber Fatality

"Capability tests will be "gamed". "

But, now that you know that they're going to want to game the system, there are other approaches to the problem, such as demanding source code and program memory inspection, or randomly selected scenarios. Even now, we demand that we can arbitrarily build executables in a traceable fashion, simply so that we can avoid other silly problems like repeatable builds.


The smog tests are absurdly simple compared the tests required of a target detection and tracking system.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

With the disclaimer "I Am Not A Software Guy" ... I cannot begin to imagine how complex and abstract the relationship is between the executable machine code and what the user sees. To debug that by looking at source code would be a herculean task at minimum.

It's one thing to look for a logic fault when a programmed system has a repeatable flaw and you have a clue where to look. "Oh crap, we have an OR rather than an AND between these two logic rungs." (been there!) It's quite another to have millions, possibly billions, of lines of code laid out with the task "Find all the problems with this."

How many times do you get "Windows Update" ...

Random test scenarios would have to be part of the picture, but it is the nature of statistics that they will not find every flaw.

Self-driving cars are essentially going through random test scenarios right now. This random test scenario found a bug.

And for those saying "this shouldn't be happening in public", I don't disagree, but at the same time, in controlled test scenarios, probably that pedestrian wouldn't have pushed that bicycle across the road in that manner under those lighting conditions.

RE: Self Driving Uber Fatality

It's essentially an AI problem; at least the tricky bits are. Famously, "AI is hard", where 'hard' is a computer science keyword that isn't very distant from 'impossible'. This conclusion goes back decades.

Historically, AI has been 'an indoor cat', assigned to finite problems within defined problem spaces. Now it's being taken outdoors, where the problem space is unbounded. I expect that it will soon be realized that "AI Outdoors is VERY hard."

There's also the issue of sensors. It's hard to appear intelligent if you're oblivious to what's going on around you. Autonomous vehicles should have microphones to hear the sirens of emergency vehicles, but nobody seems to have thought of even that obvious example. Smoke, vibrations, sudden banging noises, screams of terror from the passengers, etc.; all should be inputs. Successful AI Outdoors will need a large range of sensors.

Given the wildly optimistic naivety, these sorts of accidents are not surprising. They'll continue, and lives and billions will be lost.

I expect that it'll be a bit like Fermat's Last Theorem. Yes, Wiles' [edited] 129-page solution certainly would not fit in the margin. When Autonomous Vehicles are finally fully sorted out (10+ years from now), they'll look back and then realize how the problem was so much bigger than they expected.

RE: Self Driving Uber Fatality

I just saw that the LiDAR manufacturer introduced a new model late last year with 0.1 degree resolution and 300m range. It seems likely that the Uber would have had the previous generation model, at 0.4 degrees and 120m range. That means that 6 seconds from impact the woman with the bike would come into range and be a blob about 2 pixels by 2 pixels, in a picture 900 pixels wide. Braking time from 40 mph is about 2 seconds. The blob would be persistent and therefore easy to track. How on earth the software copes with blobs that move fast enough to have distinctly separate images in each frame I don't know. Obviously there's no hope of doing image recognition on a 2 pixel by 2 pixel blob (you could get fancy and use lots of frames of data to give better resolution).






Cheers

Greg Locock


New here? Try reading these, they might help FAQ731-376: Eng-Tips.com Forum Policies http://eng-tips.com/market.cfm?

RE: Self Driving Uber Fatality

"...consecutive frames..."

I wonder what the frame rate of Lidar is? Being mechanically scanned (laser and spinning mirrors), I assume it's slow.

RE: Self Driving Uber Fatality

The Velodyne 64E has a complex relationship between the upper and lower banks of lasers and the rotation rate. The elevation increment of approx. 0.4 degrees is constant; nothing else is except sample rate. Higher rate = lower resolution. It also seems to depend on which data is being accessed. I've only given it a cursory reading, but one thing that stands out is the sensitivity to reflectance; the spec indicates the limit for pavement might be only 50m based on a reflectance of 0.1.

See www.velodynelidar.com/lidar/products/manual/HDL-64...

One characteristic that I expected but did not find is the beam divergence.

RE: Self Driving Uber Fatality

The angular resolution depends on the LiDAR's rps, it can scan at 5 10 or 15 rps. Long range resolution is then set out in Appendix B of that manual, and is substantially better than 0.4 degrees, at the lowest speed it is 0.1152 degrees and is proportional to the rps. So you can have 15 frames per second at 0.34 degrees resolution, or 5 frames per second at 0.12.

Cheers

Greg Locock


New here? Try reading these, they might help FAQ731-376: Eng-Tips.com Forum Policies http://eng-tips.com/market.cfm?

RE: Self Driving Uber Fatality

The apparent movement is tangential from any viewpoint in the vehicle except the point(s) of collision. It will have a tangential component if either member to the collision is on a non-linear path or has a non-linear velocity regardless of view point.

RE: Self Driving Uber Fatality

IRstuff, I think your IRstuff (Aerospace)22 Mar 18 02:16 image is misleading, I don't see any sign of vertical scanning as such in that manual, just an upper and lower bank with different fields of view. So the LiDAR map would just be a set of distances at the two different heights at the angular resolution? Am I missing something?

Cheers

Greg Locock


New here? Try reading these, they might help FAQ731-376: Eng-Tips.com Forum Policies http://eng-tips.com/market.cfm?

RE: Self Driving Uber Fatality

There are 64 individual lasers in the scanner; 32 upper and 32 lower, spread to cover a range of angles.

RE: Self Driving Uber Fatality

3DDave beat me to it. Most commercial lidars are scanning in azimuth only, and use either an array of transmitters and receivers or a single fan-shaped transmitter beam and an array of receivers. An array of transmitters AND array of receivers seems way more complicated than I would hope for, but that does help out on the pulse repetition rate, which is the limit of the frame rate vs. resolution problem.

"To debug that by looking at source code would be a herculean task at minimum."
The first thing to do is to start with the recorded data and processor logs. Since they are in the testing phase, there should be copious amounts of both. If the data log is empty, heads will roll.

Note that we were referring to acceptance tests, not engineering tests. The engineering tests are performed by the supplier, and should involve a progression of tests starting at the smallest software module, and then progressing to ensembles of modules. Acceptance tests are not intended to exhaustively test functionality, just like IIHS or DOT tests only test specific things, which were gamed by VW and others. But, one can demand, justifiably, that a testing authority have access to the code, and witness the programming of such code, and tested with a series of random scenarios.

The HDL-64 has 0.4-deg vertical resolution and almost exactly 2-mrad horizontal resolution at 5-Hz frame rate, so at 20-m range, it would have 0.04-m horizontal resolution, which means there were something like 205 lidar returns from the pedestrian every 0.2 seconds at the instant her feet were visibly illuminated by the headlights. At that frame rate, even if she were moving at 4 mph, there would have been minimal horizontal separation between successive lidar return clusters. It should have been trivial for the object processor to determine that there was a moving object about to get hit by the car. Consider that in the 1.2 seconds from that point, there should have been at least 6 complete frames, and more than 1230 lidar returns from the pedestrian (actually way more, since the range was decreasing), it should have been impossible for the object processor to ignore that pedestrian.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

Quote (3DDave)

It will have a tangential component if either member to the collision is on a non-linear path or has a non-linear velocity regardless of view point.

In this case, for a vision based system, given that we're apparently talking about a time interval of only about 2 or 3 seconds and neither was obviously turning, both motions are going to be effectively linear.

And the scale of the "point of impact" doesn't really help much except in the final too-late fraction of a second.

Greg touched on an interesting point for vision systems. A lack of apparent relative motion for objects on a collision course. At least until it's perhaps too late.

Vision systems would perhaps benefit from widely spaced cameras, indicating placement on the outside mirror housings.


RE: Self Driving Uber Fatality

Oh, and if the sensors only have a range of 50m sometimes, the braking distance from 70 mph is 75m, in other words the 50m range lidar is unfit for purpose at 70 mph, even if the car can immediately recognise a problem. The more sensible alternative, swerving, may need less distance, but of course requires more situational awareness and skill. I guess this speed limit is why the L4 testing is being done in urban areas.

Cheers

Greg Locock


New here? Try reading these, they might help FAQ731-376: Eng-Tips.com Forum Policies http://eng-tips.com/market.cfm?

RE: Self Driving Uber Fatality

A human wouldn't be issued a license (based on poor vision) if they couldn't see an obstacle (or better: lack of empty road) beyond 50 or 75 m.

RE: Self Driving Uber Fatality

50m is for an asphalt type surface at a guess. I wonder where wool or other natural fabrics in a dark color fall?

Next cab off the rank (haha) is the radar system. Do these vehicles have them and what is the spec?

Cheers

Greg Locock


New here? Try reading these, they might help FAQ731-376: Eng-Tips.com Forum Policies http://eng-tips.com/market.cfm?

RE: Self Driving Uber Fatality

It will be interesting to read the NTSB report once it is released. What I am missing in all the information that has been published is simple things such as how many sensor are there of each kind, are we looking at 2 out 3 systems, what determines if a sensor is not working correctly? Is there a safety system / computer that monitors the computer that operates the car? What kind of redundant power supply exist for the computer(s)?

Many other questions but did the Uber stop and call 911 after running over the pedestrian?

It is hard enough to make chemical plants safe but at least they are not moving down the road at 70 mph. On the other, I think there are many things from the various safety analysis that are done in chemical plants that could be applied to these robot cars.

RE: Self Driving Uber Fatality

Doing a bit of reading here.

A couple of quotes from this article: http://www.latimes.com/business/la-fi-uber-pedestr...
"Also on Monday, the auto-parts maker that supplied the radar and camera on the Volvo SUV that struck and killed the woman last week said Uber had disabled the standard collision-avoidance technology in the vehicle.
"'We don't want people to be confused or think it was a failure of the technology that we supply for Volvo, because that's not the case,' Zach Peterson, a spokesman for Aptiv, said by phone. The Volvo XC90's standard advanced driver-assistance system 'has nothing to do' with the Uber test vehicle's autonomous driving system, he said.
"Aptiv is speaking up for its technology to avoid being tainted by the fatality involving Uber, which may have been following standard practice by disabling other tech as it develops and tests its own autonomous driving system. Experts who saw video of the Uber crash pointed to apparent failures in Uber's sensor system, which failed to stop or slow the car as 49-year-old Elaine Herzberg crossed a street pushing a bicycle."
And
"Meanwhile, a top executive for the maker of sensors used on the self-driving Uber vehicle said she was 'baffled' as to why the tech-outfitted vehicle failed to recognize a pedestrian crossing the street and hit the brakes.
"Marta Thoma Hall, president of Velodyne Lidar Inc., maker of the special laser radar that helps an autonomous car "see" its surroundings, said the company doesn't believe its technology failed. But she's surprised the car didn't detect Herzberg.
"'Certainly, our Lidar is capable of clearly imaging Elaine and her bicycle in this situation,' Thoma Hall wrote in an email. 'However, our Lidar doesn't make the decision to put on the brakes or get out of her way.
"'In addition to Lidar, autonomous systems typically have several sensors, including camera and radar to make decisions," she wrote. "We don't know what sensors were on the Uber car that evening, if they were working, or how they were being used.'"

And meanwhile, an interesting take on the whole situation:
https://jalopnik.com/uber-has-no-damn-business-tes...

RE: Self Driving Uber Fatality

This article contains the most detail about the car than anything else I've seen: https://techcrunch.com/2018/03/19/heres-how-ubers-... As has been mentioned a few times now, Uber had at least 3 sensor systems that should have detected the pedestrian. They are basically independent in their operation, and it's up the collision avoidance processor to make the decision about doing something, at which it failed miserable.

The jalopnik article is basically a rant, and however, or whatever, the writer feels about its business practice should not be confused with whether its technology is sound.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

Quote:

Uber had at least 3 sensor systems that should have detected the pedestrian.

It's hard to be enthusiastic about trusting my life to that.

RE: Self Driving Uber Fatality

I'm simply saying that there was nothing physically preventing the sensors from detecting the pedestrian at their maximum effective ranges. Since the car did not behave like it detected an obstacle at any time, I can't say for certain that all the sensors didn't fail simultaneously AND the processor failed to detect the fault condition.

Prior to this, I certainly would not have had any doubts about the performance of the sensors, given that scenario. Even a competitor was able use the crappy video released by the police to detect the pedestrian and the bicycle at the first instant they were fully within the headlight illumination; obviously, there could be gaming of that for other reasons.

I know what I would have flowed down as requirements for the sensors, and at that range, the probability of detection would be essentially be 99.9999%, since I would have required at least 99% probability of detection at 300 ft for a pedestrian. That would be 5 seconds for a car at 40 mph, and that would mean at least 25 frames in which the pedestrian was detected. The number of lidar pixels declaring detections would have been in the hundreds.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

Quote:

Marta Thoma Hall, president of Velodyne Lidar Inc., maker of the special laser radar that helps an autonomous car "see" its surroundings, said the company doesn't believe its technology failed. But she's surprised the car didn't detect Herzberg.
"Certainly, our Lidar is capable of clearly imaging Elaine and her bicycle in this situation," Thoma Hall wrote in an email. "However, our Lidar doesn't make the decision to put on the brakes or get out of her way. In addition to Lidar, autonomous systems typically have several sensors, including camera and radar to make decisions," she wrote. "We don't know what sensors were on the Uber car that evening, if they were working, or how they were being used."
Sometimes execs should just shut their mouths. One the one hand, she doesn't know what sensors were being used or if they were working. Yet she make the boneheaded move of stating "our Lidar doesn't make the decision to put on the brakes or get out of her way." That statement makes the assumption her system was in the loop (maybe it wasn't) and that it failed to do its job. Lawyers LOVE that kind of "self-incrimination".

EDIT: On second read, this could be an issue with the writer/editor. Perhaps what she meant was her system does not have the control (i.e., "say-so") to put on the brakes, rather than "my system didn't recognize the danger". Difficult to say the way the article is written.

Dan - Owner
http://www.Hi-TecDesigns.com

RE: Self Driving Uber Fatality

I interpreted her comment to be 'our systems send the information to the processor, which decides how to react'

The sensors are sensors, not processors.

RE: Self Driving Uber Fatality

Me too. Sensors just produce data. That data is just an input to the system making the decisions.

RE: Self Driving Uber Fatality

(OP)
MacGyverS2000,

An extreme case here is that Velodyne's LiDAR reported an image to the robot driver, and then reported a new image a tenth of a second later. The robot then identifies obstacles and moving objects. A LiDAR will have an on-board computer and should be possible to design one that identifies, tracks and reports objects. This may make it more difficult to integrate the output of multiple LiDARs and cameras.

--
JHG

RE: Self Driving Uber Fatality

"A LiDAR will have an on-board computer and should be possible to design one that identifies, tracks and reports objects. This may make it more difficult to integrate the output of multiple LiDARs and cameras."

Not by design. At the root, a lidar collects a cloud of returns that simply contain range, azimuth, and elevation. A processor might be included that places the returns in their proper place in the world. Almost no lidars do target recognition, that is the province of the system processor, that integrates the radar and video data into the decision making.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

That's not a theory. It's a smokescreen. The sensor, if mounted with the base level, has an ~25 degree down angle range. From a 5 foot altitude that would be about 12 feet to the pavement before a spot on the pavement disappeared. Anything taller would be proportionally visible closer. This is a better view than from the driver's seat as blocked by the hood.

RE: Self Driving Uber Fatality

Simple. They were ignored.

RE: Self Driving Uber Fatality

Uber has already settled with the family out of court.

https://www.reuters.com/article/us-autos-selfdrivi...

----------------------------------------

The Help for this program was created in Windows Help format, which depends on a feature that isn't included in this version of Windows.

RE: Self Driving Uber Fatality

This narrative that she "came out of the shadows" really bothers me. I heard it repeated on NPR today. That video has been a mixed blessing from a PR standpoint as it pertains to fault for this.

RE: Self Driving Uber Fatality

"That video has been a mixed blessing from a PR standpoint as it pertains to fault for this."

That's nonsense, I have no doubt that Uber allowed the police to have the video specifically to sway the public into thinking that the accident was unavoidable. The cited article about the settlement exactly describes what Uber had hoped people would think; "when the headlights suddenly illuminated Herzberg in front of the SUV." The person who was thinking on their feet and released that video is going to get a huge bonus at Christmas time.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

I just meant it was a mixed blessing in that it was pretty graphic and shows their product causing the end of someone's life. That, in and of itself, has some inherent downside to it. I agree that on the whole it has worked in their favor though.

RE: Self Driving Uber Fatality

(OP)
Spartan5,

One of my theories is that the camera contrast ratio was not sufficient to transition from dark areas to fully lit areas. People are posting stuff here that shows that cameras are available that have the contrast ratio. That is not good for Uber.

--
JHG

RE: Self Driving Uber Fatality

That assumes that:
a) it even needed a high contrast resolution
b) there was even a high contrast situation

The other dash cam videos show that a high contrast situation didn't even exist, so I'm tempted to think that Uber released video that was purposely altered in contrast to make it appear as it the accident was unavoidable. BUT, it wasn't because the radar and lidar which were supposedly installed on this car don't require ambient light at all, i.e., had there been total darkness, the pedestrian should still have been detectable. Had there been a searchlight blinding the camera, the accident ought not have occurred.

The fact that people are lamenting the video is a strong indication of how big a bonus the person at Uber who released the video will be getting this year.

The video is completely and totally irrelevant to the collision that the car ought to avoided with ease.

TTFN (ta ta for now)
I can do absolutely anything. I'm an expert! https://www.youtube.com/watch?v=BKorP55Aqvg
FAQ731-376: Eng-Tips.com Forum Policies forum1529: Translation Assistance for Engineers Entire Forum list http://www.eng-tips.com/forumlist.cfm

RE: Self Driving Uber Fatality

The video proves she was on the road and was travelling in a constant direction so the sensors had an unobstructed "view" of her for enough time that the accident should never have occurred.

It could be said the video shows the backup driver might not have been able to react, but I'm not buying that the backup driver could only we what that video shows. The glances the backup driver was giving might be indicative of how far she could see ahead, maybe not clearly but still with some visibility.

By the reports it didn't seem like much time elapsed between the crash and the police viewing the video.

RE: Self Driving Uber Fatality

So, the "design plan" of these self driving systems is not looking for physical objects in the path of the car but rather to only deal with things that are classified as objects that can be in the path of the car?

RE: Self Driving Uber Fatality

There needs to be a lot more development and testing before an AV is allowed on a public roadway. I think it will become very obvious in any remotely realistic "real world scenario" that the AI is no where near sophisticated enough to process the massive amount of input presented by the real world. I don't believe AI will ever be able to do the extrapolation required to drive as well as a human CAN. Obviously, even what's available now surpasses what human drivers sometimes DO, but "better than an oblivious idiot" is ridiculously low and unacceptable standard.

Rather than attempting the impossible with AI, if the the LIDAR, etc. were incorporated into regular automobiles, so that drivers could "see" what is not illuminated by the headlights,that would actually improve safety. Especially if such systems were incorporated as a heads-up display, showing the objects where they are from the driver's perspective. Some already have thermal imaging, but there is so much more that could be done.

Red Flag This Post

Please let us know here why this post is inappropriate. Reasons such as off-topic, duplicates, flames, illegal, vulgar, or students posting their homework.

Red Flag Submitted

Thank you for helping keep Eng-Tips Forums free from inappropriate posts.
The Eng-Tips staff will check this out and take appropriate action.

Reply To This Thread

Posting in the Eng-Tips forums is a member-only feature.

Click Here to join Eng-Tips and talk with other members!


Resources