News for hackers. Stuff that matters.
Re:End to End Learning for Self-Driving Cars [pdf] by birdmanjeremy on Monday May 09, 2016 @06:30PM (#11663744)
This is really interesting, but I'd want autonomous cars to be better than humans at driving, not to emulate them.
Re:End to End Learning for Self-Driving Cars [pdf] by elihu on Monday May 09, 2016 @07:24PM (#11664083)
I've read that one of the problems with Google's self-driving cars has been that other cars tend to run into them because the self-driving cars drive extremely conservatively and violate other driver's expectations of how a typical California driver is expected to behave.

I think this sort of thing is something developers are going to have to find ways of dealing with; a car can be technically driving in a safe, legal way but if it's too different from how a human would drive, they are going to be a safety hazard.

Of course, standard driving behavior varies dramatically from place to place. For instance, in the United States, everyone is expected to get out of the way of whichever car has the right-of-way in that situation. In Indonesia, the car that has the right-of-way is expected to slow down, stop, or move over to accommodate other cars that do things like pull out in front of them in an intersection or pass on a two-lane road with oncoming traffic. A self-driving car in Jakarta would need to be trained very differently than a self-driving car in Seattle or Paris. Not just because the traffic laws are different, but because drivers have very different expectations about what is normal behavior.

Re:End to End Learning for Self-Driving Cars [pdf] by bduerst on Monday May 09, 2016 @07:46PM (#11664204)
>problems with Google's self-driving cars has been that other cars tend to run into them

I feel like this is already an urban myth, given the small amount of people who have actually been driving around the cars. And won't some of the people at fault for hitting them try to put the blame on the robot anyways?

Is there even a credible source for what you read?

Re:End to End Learning for Self-Driving Cars [pdf] by teraflop on Monday May 09, 2016 @08:12PM (#11664320)
Maybe you wouldn't consider this "credible", but Google publishes a monthly report listing every collision their autonomous cars have been involved in. [1]

I was curious, so I went through the whole list. By my count, in the history of the program they've been involved in 19 accidents during autonomous operation, and the car was only at fault in one of those. [2] The majority of the other crashes were caused by other drivers rear-ending the car while it was stopped.

[1]: https://www.google.com/selfdrivingcar/reports/

[2]: http://www.theverge.com/2016/3/9/11186072/google-self-drivin...

Re:End to End Learning for Self-Driving Cars [pdf] by EmployedRussian on Monday May 09, 2016 @09:25PM (#11664620)
"While it was stopped" is the key.

It's hard to argue that a car stopped at red light violates anyone's expectation of how a human would drive.

Re:End to End Learning for Self-Driving Cars [pdf] by greeneggs on Monday May 09, 2016 @11:19PM (#11664956)
That's a misleading phrase. A number of the accidents have occurred because the Google car abruptly came to a stop in a situation where a human driver would not have stopped. Slamming on the brakes is dangerous.

Here is one example. It is hard to be sure exactly what happened, because Google obviously phrases its accident reports to put its cars in as favorable light as possible.

"April 28, 2016: A Google self-driving prototype vehicle travelling westbound in autonomous mode on Nita Avenue in Palo Alto was involved in an accident. The prototype vehicle came to a stop at the intersection of San Antonio Road, then, prior to making a right turn on San Antonio Road, began to gradually advance forward in order to get a better view of traffic approaching from the left on San Antonio Road. When the prototype vehicle stopped in order to yield to traffic approaching from the left on San Antonio Road, a vehicle approaching at approximately 9 mph from behind the prototype collided with the rear bumper of the prototype vehicle."

http://static.googleusercontent.com/media/www.google.com/en/...

Re:End to End Learning for Self-Driving Cars [pdf] by argonaut on Tuesday May 10, 2016 @01:32AM (#11665329)
Obviously the textual description is limited (e.g. a video would settle this question), but that description alone is hardly unnatural. The behavior of the Google car is behavior I make all the time, and one I see drivers making all the time: inching forwards in the right-hand lane to look at the traffic on the left, then stopping because you've decided not to go for it.

The fact is: slow speed rear ends are really common. I've had them happen to me several times during one year where I commuted every day. I've done it myself on another car.

I would not be surprised if over the course of the next few years Google cars get rear-ended at light to moderate speeds hundreds of times.

Re:End to End Learning for Self-Driving Cars [pdf] by bduerst on Tuesday May 10, 2016 @01:38AM (#11665346)
That says nothing about driver expectations, and is a poor interpretation of statistics.

About 23-30% of human accidents are rear end collisions. It is entirely possible that the car drives so well that other types of collisions are minimized.

That leaves rear-end collisions - the type the car can't control - misleadingly seeming to be abnormally high.

Re:End to End Learning for Self-Driving Cars [pdf] by fizixer on Monday May 09, 2016 @09:08PM (#11664560)
So if a conservative human driver from a peaceful low-traffic part of the country goes to California and drives there, and an aggressive Californian causes the accident between the two cars, the conservative driver is to be blamed?

Sounds like a textbook example of blaming the victim.

Re:End to End Learning for Self-Driving Cars [pdf] by blazespin on Monday May 09, 2016 @07:27PM (#11664098)
Self driving cars must do significantly better safety wise otherwise the adoption will be hampered.

Plus, the whole point here I think is to save lives. Google self driving cars arent really a hazard they're more just very annoying because they are overly cautious.

Re:End to End Learning for Self-Driving Cars [pdf] by mechanon05 on Monday May 09, 2016 @07:34PM (#11664144)
I feel like people just assume that they are annoying to drive around, but very few people actually have experience driving around google's cars. The times that I'm around them (a few mornings a week), they are never in any way weird or annoying. In fact, they are extremely predictable, and therefor, if anything, less annoying to drive around.
Re:End to End Learning for Self-Driving Cars [pdf] by mikeyouse on Monday May 09, 2016 @07:47PM (#11664207)
I agree -- they never encroach in your lane, they signal with plenty of room to spare, they don't threaten to pull out in front of you, in many different ways, they're preferable to human (Californian) drivers.
Re:End to End Learning for Self-Driving Cars [pdf] by Diederich on Monday May 09, 2016 @09:57PM (#11664712)
Right. I see them a couple times a week, and once in a while, they pass me while I am on my bicycle.

I will admit that once I became aware of a Google car coming up to pass me on my left, and I did a little jink toward it on my bicycle. It reacted conservatively but decisively. It didn't jump into another lane or slam on its breaks. It just quickly gave me some more room and gently passed.

Kind of creepy, but very cool.

Re:End to End Learning for Self-Driving Cars [pdf] by ktRolster on Monday May 09, 2016 @08:31PM (#11664399)
I think the fear is that they'll drive the speed limit on the freeway, even when no one else is.
Re:End to End Learning for Self-Driving Cars [pdf] by danieltillett on Monday May 09, 2016 @08:38PM (#11664428)
Actually what would speed up adoption would be if they were able to drive over the speed limit legally. If they are significantly safer then this should be a win-win for everyone other than those issuing speeding tickets.
Re:End to End Learning for Self-Driving Cars [pdf] by grkvlt on Tuesday May 10, 2016 @06:41AM (#11666207)
People are afraid the cars will follow traffic laws, and drive legally, even when no one else is? And, I find it hard to believe that everyone disobeys the posted speed limits on freeways. For example, trucks with speed-limiters, people who don't want to break the law, buses, etc.
Re:End to End Learning for Self-Driving Cars [pdf] by mac01021 on Monday May 09, 2016 @09:35PM (#11664659)
Certainly not the whole point. An autonomous vehicle that can drive me around exactly as safely as I can drive myself is a vast improvement over the status quo, in which commuting is a significant waste of my time.
Re:End to End Learning for Self-Driving Cars [pdf] by jonny_eh on Monday May 09, 2016 @07:03PM (#11663954)
Even if it was trained to drive like a human, it'd be better in many ways: It never gets drunk, doesn't get tired, doesn't get distracted, can drive old people (or anyone) around who shouldn't be driving anymore, etc.
Re:End to End Learning for Self-Driving Cars [pdf] by jfoutz on Monday May 09, 2016 @07:46PM (#11664200)
I couldn't find the article, but i remember a project learning from remote control plane pilots. People mess up all the time. It's not even drunk or tired, there's just errors every so often, it's almost statistical. The little errors people make wash out as noise.
Re:End to End Learning for Self-Driving Cars [pdf] by taf2 on Monday May 09, 2016 @07:24PM (#11664082)
This almost sounds like the line from terminator two.

"It can't be bargained with. It can't be reasoned with It doesn't feel pity, or remorse, or fear. And it absolutely will not stop, ..."

Re:End to End Learning for Self-Driving Cars [pdf] by smackmybishop on Tuesday May 10, 2016 @09:04AM (#11666842)
That's the first Terminator. Terminator 2 would be:

It would never leave him, and it would never hurt him, never shout at him, or get drunk and hit him, or say it was too busy to spend time with him. It would always be there. And it would die, to protect him.

Re:End to End Learning for Self-Driving Cars [pdf] by blazespin on Monday May 09, 2016 @07:21PM (#11664057)
Yeah, but if a computer screwed up like a human we'd never hear the end of it.
Re:End to End Learning for Self-Driving Cars [pdf] by dpflan on Monday May 09, 2016 @07:31PM (#11664127)
I think the trick is not to mix autonomous and non-autonomous. Cities delegate autonomous only zones where no non-autonomous cars can go; this creates a transportation circulatory system and safe experimental zone which can expand - which can include just making the area of city only for autonomous cars larger or gradual commingling with non-autonomous cars. Or again partial autonomy of cars on highways / more predictable driving scenarios, like we are already seeing.
Re:End to End Learning for Self-Driving Cars [pdf] by robbrown451 on Monday May 09, 2016 @11:20PM (#11664959)
That seems like the trick to making sure they are never adopted in a big way.

I mean sure, that's an easy problem to solve but in that case why use cars at all and not people movers or the like?

Re:End to End Learning for Self-Driving Cars [pdf] by sammyo on Monday May 09, 2016 @10:20PM (#11664779)
But this is just wrong. Virtually the only accidents were people rear ending a stopped car at a red light. The current google cars are probably improving the general driving safety.
Re:End to End Learning for Self-Driving Cars [pdf] by rdabane on Monday May 09, 2016 @06:43PM (#11663825)
Yeah,make sense. But this is the first example I've seen where the network is trained only with driver's input. Has anyone seen this kind of approach before?
Re:End to End Learning for Self-Driving Cars [pdf] by jonny_eh on Monday May 09, 2016 @07:02PM (#11663937)
Re:End to End Learning for Self-Driving Cars [pdf] by rdabane on Monday May 09, 2016 @07:22PM (#11664062)
Thanks for the reference.
Re:End to End Learning for Self-Driving Cars [pdf] by hedgehog on Monday May 09, 2016 @07:16PM (#11664026)
The neural net that accurately predicts human control inputs also extracts the relevant features you would want to build a more principled autopilot. For example you could take one of these nets and then for build a speed limit sign locator on top of it without training a whole net for that from scratch. Using that you could then hard code the rules for obeying the speed limit into a more traditional planner.
Re:End to End Learning for Self-Driving Cars [pdf] by cryptoz on Monday May 09, 2016 @06:45PM (#11663835)
There are real potential advantages to training networks using human behaviors. For example, the person-to-person communication that takes place while driving might be better understood by machines this way.

- Was that an obscene gesture or a thank you wave?

- Did the other driver suggest I go forward or tell me to stop?

- etc

Re:End to End Learning for Self-Driving Cars [pdf] by rdabane on Monday May 09, 2016 @07:19PM (#11664047)
Wondering if they have to create near collision scenarios in order to train the network :-)
Re:End to End Learning for Self-Driving Cars [pdf] by andrewchambers on Monday May 09, 2016 @07:03PM (#11663948)
They need some sort of prefilter to remove any bad driving habits before training begins I suppose.
Re:End to End Learning for Self-Driving Cars [pdf] by jonny_eh on Monday May 09, 2016 @07:04PM (#11663957)
I imagine with enough training data from enough drivers that bad habits will disappear as noise.
Re:End to End Learning for Self-Driving Cars [pdf] by msandford on Monday May 09, 2016 @07:11PM (#11663996)
Depends on the "bad habit". A huge number of people speed. How's that going to disappear as noise?
Re:End to End Learning for Self-Driving Cars [pdf] by andrewchambers on Tuesday May 10, 2016 @02:09AM (#11665431)
wouldn't it just converge on an average driver? not even a good one.
Re:End to End Learning for Self-Driving Cars [pdf] by cwe on Monday May 09, 2016 @07:11PM (#11663997)
I'd like to believe that would be the case, but I live in Seattle.
Re:End to End Learning for Self-Driving Cars [pdf] by johntb86 on Monday May 09, 2016 @08:56PM (#11664515)
From the paper:

To train a CNN to do lane following we only select data where the driver was staying in a lane and discard the rest.

Re:End to End Learning for Self-Driving Cars [pdf] by anonymfus on Monday May 09, 2016 @06:55PM (#11663896)
This technology is much more universal than just autonomous cars.
Re:End to End Learning for Self-Driving Cars [pdf] by blazespin on Monday May 09, 2016 @07:18PM (#11664041)
Good point. But there are a lot of things like self driving cars where emulating would be a quantum leap forward...
Re:End to End Learning for Self-Driving Cars [pdf] by marcosdumay on Monday May 09, 2016 @08:11PM (#11664316)
No problem in it driving like the best human drivers around.