Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Google Cars Drive Themselves, in Traffic

nytimes.com

Post reply on HN
Print view View original

161–170 of 216 posts

Re: Google Cars Drive Themselves, in Traffic

#161

Post by Naga »

scotty79 wrote: post #152
cletus wrote: post #111

Earlier quoted context omitted.

I walk a lot and the times where I've been nearly hit by a car have ALWAYS been at crosswalks and traffic lights (where the pedestrian light is green and cars should be stopping). Crosswalks are a problem because you can't predict car behaviour: some will stop. Some will completely ignore them (for reasons unknown). If there were no crosswalk you know exactly what cars will do. That's much safer for both parties. The…

That http://en.wikipedia.org/wiki/Right_turn_on_red is the source of almost all dangerous situations I had on the roads as pedestrian. The one single time when cause was different that I can remember was when somebody drove in one way street in wrong direction and I was crossing the road assuming that this was impossible.

Where I recently moved to there are a lot of one way streets. I feel stupid looking to see if anyone is turning down the wrong way, but what you described is exactly why I do.

Re: Google Cars Drive Themselves, in Traffic

#162

Post by dedward »

cletus wrote: post #111
dandelany wrote: post #13

Very cool, but I sometimes worry that the illusion of safety is more dangerous than the original danger itself. In Boulder, where I live, several crosswalks were identified as being particularly dangerous for pedestrians, and pedestrian crossing signs with big flashing lights were installed at these locations over the past 5 years. This spring, a report was released[1] that showed accidents at many of these crosswalk…

I walk a lot and the times where I've been nearly hit by a car have ALWAYS been at crosswalks and traffic lights (where the pedestrian light is green and cars should be stopping). Crosswalks are a problem because you can't predict car behaviour: some will stop. Some will completely ignore them (for reasons unknown). If there were no crosswalk you know exactly what cars will do. That's much safer for both parties. The…

WHere I live the govenrment is putting up big fences in the middle of the road to prevent jaywalking, because people sprint across roads at night, even the highway, and there are lots, lots, lots of car -vs- pedestrian accidents because of people running across the street to catch a bus instead of using hte pedestrian bridge or crosswalk not far away. At night. Wearking dark clothing. (No, I'm not making any of this up)

Re: Google Cars Drive Themselves, in Traffic

#163

Post by neilc »

asr wrote: post #154
Groxx wrote: post #18

Earlier quoted context omitted.

> they cannot be perfect Two things: 1) neither are people; far from it. (you already knew this though, so...) 2) I wholly agree... as long as other people are driving . Get rid of people's irrationality / drunken behavior on the road, and automated car driving becomes a much easier problem. A computer can take more into account than a human, and decide faster. The transition is almost guaranteed to occur at some poi…

I agree computers will be able to drive much better than humans, and this transition will occur at some point--the question is, when? Is the 8 years mentioned in the article anywhere close to realistic? I don't think so. Not only does the technology have to become better in the aggregate than humans, it has to become so much better there's aren't any crash situations where human drivers perform better. There also can…

Keep in mind that there are already millions of lines of code running in modern cars. The worst-case failure mode of all that code would certainly result in loss of life, and legal liability on the part of the manufacturer/insurer/etc. So really the question is just how much automation we'll see in automobiles in the future, not if.

Re: Google Cars Drive Themselves, in Traffic

#164

Post by skorgu »

mdwrigh2 wrote: post #129
ph0rque wrote: post #120

Earlier quoted context omitted.

You mean thinking it, right? ;~)

Didn't Eric Schmidt say they'd know what you want even before you did? So no thinking required!

I know you were joking but you're also right.

I go food shopping every week at about the same time. I email trip plans between friends and schedule them. I don't drive to work but certainly if I did that's an obviously predictable event.

Between synergy among the various google properties and good pattern-recognition in the google cars (or whatever) system itself I'd be surprised if predicted trips didn't hugely overwhelm explicitly-ordered ones.

Re: Google Cars Drive Themselves, in Traffic

#165

Post by skorgu »

olefoo wrote: post #34
borism wrote: post #27

Earlier quoted context omitted.

> The insurance company, just like today. Possibly paid for by the manufacturer and entirely included in the sales price, or possibly paid for by the driver/owner like today. duh, of course! The question is - at what premium? Because you know, actually it's customer in the end who pays the price.

The first few years the premium would probably be much higher, especially since these would be luxury cars and you just know there would be attempts to fool the cars into compromising situations (or simply steal them). After the adoption curve hits the early majority the premium balance will shift the other direction (you'll pay more if your car doesn't have the safety feature of being able to drive itself). And at s…

Well the obvious solution is to make the cars paranoid.

http://www.vanemden.com/books/neals/jipi.html

Re: Google Cars Drive Themselves, in Traffic

#166

Post by stretchwithme »

dandelany wrote: post #13

Very cool, but I sometimes worry that the illusion of safety is more dangerous than the original danger itself. In Boulder, where I live, several crosswalks were identified as being particularly dangerous for pedestrians, and pedestrian crossing signs with big flashing lights were installed at these locations over the past 5 years. This spring, a report was released[1] that showed accidents at many of these crosswalk…

I agree. They'll have to accurately distinguish between toddlers walking into traffic and birds flying in front of cars.

One thing I read said the human driver had to take control because of a cyclist. Obviously there's more work to do.

But eventually these systems will get there. And they'll probably be able to share information with other vehicles too. So robotic vehicles will be able to see around corners. And tell each other exactly what they'll do before they start doing it.

Safety could wind up being 6 sigma instead whatever is currently. And we'll actually have the ability to measure it because collecting such statistics will be more feasible.

Right now, most of our screw ups don't end causing accidents and they never get recorded. And we prefer it that way! But we'll be able to do data mining on every little thing robotic cars do.

Re: Google Cars Drive Themselves, in Traffic

#168

Post by sukuriant »

Groxx wrote: post #127
rue wrote: post #125

Earlier quoted context omitted.

> They don't get "shocked", or hit the wrong pedal, and have faster reaction times. Yes they do. You could perhaps argue they do so less .

OK, kernel panics aside. Unless they're using a random number generator seeded with outside data, all computer operation can be called deterministic and 100% predictable. Because it's 100% repeatable given identical preconditions. People? Not so / not currently doable. If the wrong operation for a situation were performed, it'd be due to a higher-level decision going wrong, not the command. Meanwhile, people can "hit…

Even still, let's imagine they're performing using a pseudo-random number generator, and let's imagine they're using a trained neural network at some part of the program. The training (genetic or back-propagation based) didn't account for a very specific scenario, and the tool mis-classifies it, telling the computer to do the wrong thing.

If you're suggesting that we know what a computer will do on every single given input, we don't. That's in a class of unsolvable problems, as it requires the halting problem to be solved.

[Added the following section after being down-voted]

A "shock", in the deterministic computer world, could be an incorrect classification resulting in an incorrect action. The results are similar to when a human is shocked and doesn't act correctly.

Is the scenario I've painted limited to neural nets? No, any trained classifier, even any program at all may have "minor" slips like this. (When dealing with an analogue world, there's a ridiculously large number of situations that may exist). But you know what? Humans don't perform perfectly; and a computer that's been shown to perform the correct final* response 100% of the experimental time, and 99.9997% of the real time is competent at the activity, and trustworthy.

Disclaimer: I love machine learning, I love neural networks, and I see great usefulness for them in this world; however, I also believe that the perfect combination of variables could yield unusual results. Is it unlikely? Incredibly. Possible? yes.

* Consider a situation where a child is playing with a ball. The computer may not recognize that anomaly on the side of the road as the child and the ball, or even as something to be avoided. If the computer recognizes the anomaly as something that needs more information; then tells the car to slow down until it can acquire that information, then recognizes it as something that needs to be avoided and does so, successfully, safely, and with sufficient space for the conceivable outcomes that may have resulted with this child; then, while the computer couldn't discern the object at first, it did in the end and adapted to the situation appropriately. The "final response" was correct.

[edit: rather than simply down-vote me, please tell me where I'm wrong so I can learn.]

Re: Google Cars Drive Themselves, in Traffic

#170

Post by sukuriant »

dreeves wrote: post #138
Niten wrote: post #130

Earlier quoted context omitted.

This especially scares me as a cyclist. I'm sure they'll put a lot of effort into preventing automated cars from hitting other vehicles or slow-moving pedestrians. Now what about bicycles traveling around 20 mph in the right-hand side of the lane? Many people seem to neglect or completely fail to understand the risk of increased perception of safety leading to an overall decreased safety in these systems. We can't ha…

It does seem tricky for the car to properly account for the presence of a cyclist using just the cameras and radar and whatnot. What if as a cyclist you carried a special RFID that robot cars would all be programmed to recognize?

why? Have you seen lidar work? It's pretty effective. I understand lidar wouldn't be used, as it's dangerous (laser, yay!), but I imagine other radar is similarly effective
Post reply on HN