End to End Learning for Self-Driving Cars [pdf] • Hacker News Board

Re: End to End Learning for Self-Driving Cars [pdf]

#41

Post by fizixer » Tue, May 10, 2016, 1:08 AM UTC

elihu wrote: post #21

birdmanjeremy wrote: post #2

This is really interesting, but I'd want autonomous cars to be better than humans at driving, not to emulate them.

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, lega…

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]

#42

Post by euyyn » Tue, May 10, 2016, 1:08 AM UTC

Another obvious problem with having the neural network map from vision to steering is that you can't make it take decisions based on what it hasn't seen yet, but will see. E.g. changing lanes because to reach your destination you'll have to make a right turn. The authors note that E2E learning makes for a better smaller system, on account of being free from human-imposed concepts. That's fine if that's your only goal. But I think it's essential for autonomous cars to be able to reason in terms of those human concepts.

Re: End to End Learning for Self-Driving Cars [pdf]

#43

Post by EmployedRussian » Tue, May 10, 2016, 1:25 AM UTC

teraflop wrote: post #34

bduerst wrote: post #30

Earlier quoted context omitted.

>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?

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…

"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]

#44

Post by mac01021 » Tue, May 10, 2016, 1:35 AM UTC

blazespin wrote: post #23

elihu wrote: post #21

Earlier quoted context omitted.

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, lega…

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.

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]

#45

Post by rawnlq » Tue, May 10, 2016, 1:45 AM UTC

euyyn wrote: post #39

One problem with training a neural network end-to-end this way is that the system is susceptible to unpredictable glitches: The same principle that lets people trick a NN into [thinking a panda is a vulture]( https://codewords.recurse.com/issues/five/why-do-neural-netw... ) can happen randomly just by differing lighting/shadow conditions, sun glare, or who knows. One can always train the network with more and more sc…

For the "thinking a panda is a vulture" problem, don't humans fail in similar ways? The analogous examples for us are camouflage, optical illusions, logical fallacies, etc.

It doesn't really have to be perfect as long as it doesn't fail in common scenarios.

Re: End to End Learning for Self-Driving Cars [pdf]

#46

Post by brianchu » Tue, May 10, 2016, 1:50 AM UTC

Here is a great, very accessible video where the CTO of MobileEye (which provides some of the components for Tesla's "autopilot") explains his views on the challenges of end-to-end learning for autonomous vehicles, and why it's preferable to decompose the problem instead (still using deep learning for the decomposed modules). https://www.youtube.com/watch?v=GCMXXXmxG-I

I'm inclined to agree, especially because it helps in 1) providing diagnostic information (such as the great driving visualizations shown in the video), and 2) makes it easier to incorporate algorithms and sensors (like with Google's cars) as a redundancy in case the neural network hits a crazy edge case.

Re: End to End Learning for Self-Driving Cars [pdf]

#47

Post by Diederich » Tue, May 10, 2016, 1:57 AM UTC

mechanon05 wrote: post #28

blazespin wrote: post #23

Earlier quoted context omitted.

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.

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.

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]

#48

Post by rdabane » Tue, May 10, 2016, 2:16 AM UTC

rawnlq wrote: post #45

euyyn wrote: post #39

One problem with training a neural network end-to-end this way is that the system is susceptible to unpredictable glitches: The same principle that lets people trick a NN into [thinking a panda is a vulture]( https://codewords.recurse.com/issues/five/why-do-neural-netw... ) can happen randomly just by differing lighting/shadow conditions, sun glare, or who knows. One can always train the network with more and more sc…

For the "thinking a panda is a vulture" problem, don't humans fail in similar ways? The analogous examples for us are camouflage, optical illusions, logical fallacies, etc. It doesn't really have to be perfect as long as it doesn't fail in common scenarios.

It should never fail since any failure could potentially create a fatal scenario. People usually accept fatalities because of human error but they won't accept death because of algorithmic failure.

Re: End to End Learning for Self-Driving Cars [pdf]

#49

Post by sammyo » Tue, May 10, 2016, 2:20 AM UTC

dpflan wrote: post #26

birdmanjeremy wrote: post #2

This is really interesting, but I'd want autonomous cars to be better than humans at driving, not to emulate them.

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 predic…

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]

#50

Post by argonaut » Tue, May 10, 2016, 2:30 AM UTC

euyyn wrote: post #42

Another obvious problem with having the neural network map from vision to steering is that you can't make it take decisions based on what it hasn't seen yet, but will see. E.g. changing lanes because to reach your destination you'll have to make a right turn. The authors note that E2E learning makes for a better smaller system, on account of being free from human-imposed concepts. That's fine if that's your only goal…

This doesn't describe the (very basic prototype) system in the paper, but there is no theoretical reason there cannot be a recurrent net that plans ahead (obviously developing such a system is extremely difficult)