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

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

images.nvidia.com

Post reply on HN
Print view View original

71–80 of 102 posts

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

#71

Post by bduerst »

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…

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]

#72

Post by andrewchambers »

jonny_eh wrote: post #11
andrewchambers wrote: post #9

Earlier quoted context omitted.

They need some sort of prefilter to remove any bad driving habits before training begins I suppose.

I imagine with enough training data from enough drivers that bad habits will disappear as noise.

wouldn't it just converge on an average driver? not even a good one.

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

#73

Post by ksml »

EugeneOZ wrote: post #68
ilyaeck wrote: post #64

With just 72 hours of training data, this is an extremely impressive result, scientifically speaking. However, in terms of quality control/best practices in automotive, it's simply unacceptable to trust human lives with a monolithic black-box system. The reason to have modular building blocks in a production system is not necessarily better performance, but the must-have ability to test, troubleshoot, debug, fix and…

Can be used as additional system for taking decisions.

This is a great point. Reminds me of how airplanes have redundant flight computers and compare the outputs of the computers to determine if one might be faulty. https://en.wikipedia.org/wiki/Fly-by-wire#Redundancy The output of different self driving models could be compared to handle more difficult driving situations -- I never thought of that.

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

#74

Post by kabouseng »

rdabane wrote: post #48
rawnlq wrote: post #45

Earlier quoted context omitted.

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.

That's an unattainable high acceptance bar. A more reasonable one would be to have mass adoption of self driving cars as soon as self driving cars cause less accidents than human drivers.

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

#75

Post by drewm1980 »

brianchu wrote: post #46

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 hel…

Engineers are going to break down the problem into many subsystems and test the heck out of them.

Maybe the system can still be globally optimized, though, as long as individual subsystems are still verifiably correctly trained. i.e. lane detection, pedestrian detection could share some of the same convolutional layers and still be tested separately.

My personal prediction is that all of this 2D convolutional network stuff will be extended to 3D within a few years. The front-end will do a full 3D scene reconstruction from first principles, and then some sort of 3D features will be learned on ~that data.

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

#76

Post by ta7552 »

argonaut wrote: post #59
aab0 wrote: post #55

Earlier quoted context omitted.

The adversarial examples are so weak that they disappear if you give the CNN even some attention or foveation mechanisms (that is, they work only on a single pass). How much effect are they going to have on a CNN being used at 30FPS+ to do lane following under constantly varying lighting and appearances and position? None.

Are you referring to this foveation paper ( http://arxiv.org/abs/1511.06292 )? I'm quite skeptical of the claims in that paper; upon closer reading their experiments are problematic. Also, it appears the paper was rejected. I can elaborate if that is indeed the case.

> I can elaborate if that is indeed the case.

Please do anyway.

I'm wondering whether adversarial examples can also be found for autoencoders to the same extent. It seems very intuitive that you can overstep the decision boundary that a discriminatory network learns by slightly shifting the input into the direction of a different, nearby label.

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

#77

Post by RobertoG »

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…

Is not this the problem of induction in Philosophy?

Are not all the minds subjected to the same limitation?

(https://en.wikipedia.org/wiki/Problem_of_induction)

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

#78

Post by arthur_pryor »

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

i agree that it doesn't have to be perfect, but the standard should be higher than "doesn't fail in common scenarios." we should also expect graceful handling of many uncommon but plausible scenarios. we expect human drivers to handle more than just common scenarios, and human drivers are pretty bad.

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

#79

Post by Joeri »

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…

You use a test set of scenario's on which you don't train but only measure effectiveness. When accuracy on the test set exceeds your chosen threshold, that is good enough.

What is the accuracy of the human brain in recognizing traffic situations? It is probably not that hard to get a NN to do better, even if periodically it still causes an accident. This is the uncanny valley effect for self-driving cars. It's not enough to be better than average humans at driving, which i think they already are, they have to be perfect at driving for people to trust them.

Post reply on HN