Autonomous Cars

[strad]

Look Greg this idiot came to a stop and like the guy that pulls out in front of motorcycles after stopping, pulled out into my lane and stopped leaving me maybe 30 feet to react. I was doing nothing even vaguely wrong. I was not going too fast for conditions I was not, not paying attention. For all your assumptions you're wrong on every count. Full Stop.
IF he had not panicked and stopped and been smart enough to get back on the gas there would have been no situation at all.

[Just_a_fan]

Let's keep it civil, everyone. Please and thank you.

Boo, I was just getting my popcorn!

[AJI]

"An accident involving a driverless car and a motorcyclist has provided an insight into a major factor holding back the burgeoning technology....
...Waymo has analysed what caused the crash and company chief John Krafcik has detailed what went wrong. It was human error."

"According to Krafcik, the accident occurred during a fairly commonplace road manoeuvre when a car merged abruptly into the lane of the driverless vehicle. At that point the test driver, who has the ability to take over controls at any time, moved the car manually into the next lane to avoid the car.

He failed to see the motorcycle that had moved from behind the autonomous car and was in the process of overtaking."


https://amp.news.com.au/technology/inno ... 9641093d8e

[Phil]

And this is an argument for AVs how exactly?

If anything, the fact that the “test driver” felt he needed to intervene to be quite telling about how mature the tech is and how much faith he put into his cars “A.I.”.

Also, one wonders how well the stats of the pro AV PR machine backs up. “No accidents in how many million miles of driving”? Sure. Are there also statistics how many times the test-driver needed to intervene like in the above case? I’m guessing not.

[Big Tea]

And this is an argument for AVs how exactly?

If anything, the fact that the “test driver” felt he needed to intervene to be quite telling about how mature the tech is and how much faith he put into his cars “A.I.”.

Also, one wonders how well the stats of the pro AV PR machine backs up. “No accidents in how many million miles of driving”? Sure. Are there also statistics how many times the test-driver needed to intervene like in the above case? I’m guessing not.

It does not have to be perfect, just better than sole human driven, and I do not think that is ever going to be in question. I had the bad luck (or timing) to have to drive in the motorway at 'rush hour' (every hour is rush there) today and people are either 50% idiots or just do not know the rules.

[strad]

Boeing 737 crashes because the anti stall sensor sends false information and the computerized rudder control has caused crashes and you think A/Vs will be safe?

[AJI]

...Are there also statistics how many times the test-driver needed to intervene like in the above case? I’m guessing not.

I'm guessing yes. With the admittance from manufacturers that they will ultimately have to accept responsibility, there would be reams of data on that very question. It's an actuaries wet dream...

[subcritical71]

And this is an argument for AVs how exactly?

If anything, the fact that the “test driver” felt he needed to intervene to be quite telling about how mature the tech is and how much faith he put into his cars “A.I.”.

Also, one wonders how well the stats of the pro AV PR machine backs up. “No accidents in how many million miles of driving”? Sure. Are there also statistics how many times the test-driver needed to intervene like in the above case? I’m guessing not.

For over-regulation California takes first place, but some of these regulations are good. In the AV space manufacturers are required to report just the data you mention. These are for manufacturers whom test their vehicles on California roads.

Here is a summary report on the AV accidents;
https://www.axios.com/california-people ... bc936.html

Here are all the reports on AV accidents;
https://www.dmv.ca.gov/portal/dmv/detai ... veh_ol316+

Here is a report on all the disengagements;
https://www.dmv.ca.gov/portal/dmv/detai ... eport_2017
https://www.dmv.ca.gov/portal/dmv/detai ... eport_2016
https://www.dmv.ca.gov/portal/dmv/detai ... eport_2015

[subcritical71]

Boeing 737 crashes because the anti stall sensor sends false information and the computerized rudder control has caused crashes and you think A/Vs will be safe?

Are you mentioning the Lion Air flight? That one looks to be the result of shitty maintenance practices more than an automation problem. Anyway, there have been numerous studies that show it is safer and more economical to have a computer fly the plane than to have their pilots hand fly them.

However, if every car accident was handled the way every AV or Aviation accident were handled we would probably have much safer drivers/pilots (or rules/regulations). But also think we would get tired of the nightly news and news outlets only covering car accidents.

[Big Tea]

I know it is a good comparison to planes as they are on the leading edge of self driving, but remember cars are in 2 dimensions only, and can slow or stop without falling.

I am not making light of it, but it has to be far easier to handle if the 'object' can stop in a couple of seconds and stay there on a plane that will not change.

[strad]

That one looks to be the result of shitty maintenance practices more than an automation problem

Nope.. Boeing has warned pilots and there are lots of other cases...Just they didn't kill over a hundred people.
As for the aviation comparison just a few posts back I was told how planes had triple redundancy and were safer than A/Vs..
What about the computer controlled rudder problems?
You can't just brush aside stuff that doesn't fit with your argument.
some of you take this thread too serious.

[subcritical71]

That one looks to be the result of shitty maintenance practices more than an automation problem

Nope.. Boeing has warned pilots and there are lots of other cases...Just they didn't kill over a hundred people.
As for the aviation comparison just a few posts back I was told how planes had triple redundancy and were safer than A/Vs..
What about the computer controlled rudder problems?
You can't just brush aside stuff that doesn't fit with your argument.
some of you take this thread too serious.

I’m not trying to brush it aside, I’ll have to look into that as I’ve only seen some comments about the improper maintenance from others on the investigation (airliners.net) which like this site does have some experts which post. I know there was an emergency airworthiness bulletin issued but I don’t know it’s contents, yet. It’s a bit morbid to some, but as a pilot myself I like to know why others have died so I might save my own ass someday.

And to be clear, I don’t think AVs are ready for prime time yet, I give it another 3-5 years before it’s more than a novelty. I’ve made the comment before that I think they feel like your on the car ride at Disneyland, the one that bounces back and forth between the rails where you can’t steer at all, but in this case the rails are the white lines in the road. I do keep an open mind, the first link in my post above was from a group who are obviously against AVs also.

I read Tesla just updated their autopilot software so I’m going to drop into the local showroom and take one for another test drive. If you have a showroom around you give it a try, they are extremely low pressure and it’s worth checking out the (limitations) of the technology. The most pressure I’ve had is, you can go on our website and order a car anytime!

[Phil]

And this is an argument for AVs how exactly?

If anything, the fact that the “test driver” felt he needed to intervene to be quite telling about how mature the tech is and how much faith he put into his cars “A.I.”.

Also, one wonders how well the stats of the pro AV PR machine backs up. “No accidents in how many million miles of driving”? Sure. Are there also statistics how many times the test-driver needed to intervene like in the above case? I’m guessing not.

For over-regulation California takes first place, but some of these regulations are good. In the AV space manufacturers are required to report just the data you mention. These are for manufacturers whom test their vehicles on California roads.

I think you misread what i was asking for. I did not ask for statistics when an accident/collision took place, who was at fault.

I was specifically asking who keeps note on how many times a test-driver intervened to prevent a collision from happening.

Obviously, that these “interventions” exist, is denonstrated by the article above when there was an actual collision because of it. Obviously, if there is a collision, you cant hide it and there is obviously an investigation of sorts, as the links you supplied nicely demonstrate. What about the cases where nothing happened? How are these logged? I would think that data is just as relevant in determining how safe these AVs would be without supervision, wouldnt you agree?

[subcritical71]

And this is an argument for AVs how exactly?

If anything, the fact that the “test driver” felt he needed to intervene to be quite telling about how mature the tech is and how much faith he put into his cars “A.I.”.

Also, one wonders how well the stats of the pro AV PR machine backs up. “No accidents in how many million miles of driving”? Sure. Are there also statistics how many times the test-driver needed to intervene like in the above case? I’m guessing not.

For over-regulation California takes first place, but some of these regulations are good. In the AV space manufacturers are required to report just the data you mention. These are for manufacturers whom test their vehicles on California roads.

I think you misread what i was asking for. I did not ask for statistics when an accident/collision took place, who was at fault.

I was specifically asking who keeps note on how many times a test-driver intervened to prevent a collision from happening.

Obviously, that these “interventions” exist, is denonstrated by the article above when there was an actual collision because of it. Obviously, if there is a collision, you cant hide it and there is obviously an investigation of sorts, as the links you supplied nicely demonstrate. What about the cases where nothing happened? How are these logged? I would think that data is just as relevant in determining how safe these AVs would be without supervision, wouldnt you agree?

Take a look at the last 3 links, I should have put those first. Those are the reports of whenever the autonomous system has automatically deactivated as well as when a human driver had to take control. This is the raw report so it’s a bit of a lookup session but I’m sure some group has mined the data out of them for their own statistics.

[AJI]

...
I was specifically asking who keeps note on how many times a test-driver intervened to prevent a collision from happening.
...

Surely this data would be easy to acquire as a log? If you're asking whether a human being is trustworthy enough to report honestly on the situation then I'd have to say no way, but I trust logged data.