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

61–70 of 102 posts

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

#61

Post by dkarapetyan »

argonaut wrote: post #54
dkarapetyan wrote: post #53

Earlier quoted context omitted.

Wait? That's exactly what it means. Since the networks are not "continuous" you can't reason about how the system will behave in actual real world conditions because any random fluctuations can cause the whole thing to malfunction. I put continuous in quotes because it's not the real definition of continuous like in real analysis but a good enough analogy as in small variations in input should not lead to wildly diff…

To be fair, you should be more precise. The attacks are specifically calculated. The combinatorial space of possible inputs is so massive that I'm sure it is extremely unlikely for a malicious input to occur randomly.

I don't think it has to do with the combinatorics of the input space. Adversarial inputs are hard to generate until someone figures how to point a set of laser pointers at exactly the right spots on a truck on a highway to get it to swerve out of control.

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

#62

Post by argonaut »

dkarapetyan wrote: post #61
argonaut wrote: post #54

Earlier quoted context omitted.

To be fair, you should be more precise. The attacks are specifically calculated. The combinatorial space of possible inputs is so massive that I'm sure it is extremely unlikely for a malicious input to occur randomly.

I don't think it has to do with the combinatorics of the input space. Adversarial inputs are hard to generate until someone figures how to point a set of laser pointers at exactly the right spots on a truck on a highway to get it to swerve out of control.

> because any random fluctuations can cause the whole thing to malfunction

You made a very specific claim that random fluctuations could have the same effect as adversarial examples. I was addressing that.

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

#63

Post by dkarapetyan »

argonaut wrote: post #62
dkarapetyan wrote: post #61

Earlier quoted context omitted.

I don't think it has to do with the combinatorics of the input space. Adversarial inputs are hard to generate until someone figures how to point a set of laser pointers at exactly the right spots on a truck on a highway to get it to swerve out of control.

> because any random fluctuations can cause the whole thing to malfunction You made a very specific claim that random fluctuations could have the same effect as adversarial examples. I was addressing that.

Yes, that makes sense and you're right. I don't have a proper definition of randomness and I wouldn't expect generic noise to cause issues.

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

#64

Post by ilyaeck »

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 replace things by reducing the degrees of freedom - it's the ABC of engineering even in much less sensitive industries. So while N2N is going to be very useful for rapid prototyping, and perhaps setting the performance bar for other method, I doubt it will ever be used in production.

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

#65

Post by Animats »

The machine learning, no model approach is kind of scary. It's likely to do the right thing most of the time, and something really bogus on rare occasions. There needs to be more than just a model trained from successful driving. Some kind of recognition of "this is bad" is needed.

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

#66

Post by rdabane »

Animats wrote: post #65

The machine learning, no model approach is kind of scary. It's likely to do the right thing most of the time, and something really bogus on rare occasions. There needs to be more than just a model trained from successful driving. Some kind of recognition of "this is bad" is needed.

Yup, like a near collision scenario to teach it to drive off the road instead of head on collision ...

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

#67

Post by Consultant32452 »

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.

I suspect that it won't take long for people to come to terms with it in the same way we now "accept" industrial accidents. "Accept" in this case simply means that the industry in question is allowed to continue doing business.

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

#68

Post by EugeneOZ »

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.

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

#69

Post by sgk284 »

dkarapetyan wrote: post #61
argonaut wrote: post #54

Earlier quoted context omitted.

To be fair, you should be more precise. The attacks are specifically calculated. The combinatorial space of possible inputs is so massive that I'm sure it is extremely unlikely for a malicious input to occur randomly.

I don't think it has to do with the combinatorics of the input space. Adversarial inputs are hard to generate until someone figures how to point a set of laser pointers at exactly the right spots on a truck on a highway to get it to swerve out of control.

How is that different than today with human drivers? A laser to the eye will cause lots of swerving.

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

#70

Post by argonaut »

greeneggs wrote: post #57
EmployedRussian wrote: post #43

Earlier quoted context omitted.

"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.

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-drivin…

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.

Post reply on HN