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

Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

electrek.co

Post reply on HN
Print view View original

141–150 of 174 posts

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#141

Post by argonaut »

ChuckMcM wrote: post #63
mattnewton wrote: post #58

Earlier quoted context omitted.

Why not shoot for better than human performance and "cheat" any way possible along the way? To paraphrase a quote I can't remember by who, do we care if a submarine "swims"? Besides, with even with lidar, the problem is hard enough.

I agree, being better than human is a sales point that I expect to see in brochures. One of the ways I would expect that plays out is self driving transport cars for high value targets like world leaders and drug lords. "This car will respond faster, and more accurately, to get you to safety before a human driver even knew there was a problem." That said, John stated that without LIDAR you couldn't adequately meet th…

There is only a little evidence current image classification models outperform humans. The 5.1% number is just the number from one grad student who went through some ImageNet images himself - e.g. a single blog post (http://karpathy.github.io/2014/09/02/what-i-learned-from-com...). There really hasn't been a concerted effort to see how humans actually do on ImageNet.

I am willing to believe that a group of humans trained on ImageNet and without time constraints would be able to outperform the state of the art neural net models.

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#142

Post by argonaut »

ChuckMcM wrote: post #45
Animats wrote: post #20

I'm still not happy with self-driving on vision alone, or vision augmented with radar. There are too many hard cases for vision. Everybody who has good self-driving right now - Google, Otto, Volvo, GM - uses LIDAR. Self-driving is coming to the first end users in 2017, in Volvo's test of 100 vehicles. Volvo has multiple LIDARs, multiple radars, multiple cameras, redundant computers, and redundant actuators. They're b…

The argument reasoning I've heard goes like this; People drive reasonably well using vision primarily and with imperfect visibility of their environment. Computer learning networks can classify imagery at least as accurately as humans and sometimes more so. A computer using imagery that is well classified from an array of visual sensors with near perfect visibility should be able to drive as well, or better, than a h…

Driving has almost nothing to do with image classification. *

Humans implicitly perform SLAM (simulataneous localization and mapping). What do I mean? Look around your room. Close your eyes. Visualize the room. As a human, you've built a rough 3D model of the room. And if you keep your eyes open and walk through the room, that map is pretty fine-grained/detailed too and humans can keep track of where they are in the map.

The state of the art in visual SLAM (visual SLAM = SLAM from just images, nothing else) is not deep learning. It's actually still linear-algebra/geometric/keyframe based traditional computer vision (including variants that incorporate GPS/accelerometer info). There are all sorts of limitations, but the biggest is the current algos don't work when the environment is moving (!!!).

SLAM from LIDAR is solved. That's why people use LIDAR.

You might argue, that perfect SLAM is overkill for driving. And I agree. Humans rely on being able to do lots of things that are "theoretically overkill" for any given task - and maybe that's exactly why, so far, humans can drive and computer can't.

* It bears noting that even in domains like image segmentation, humans still do better than neural nets. (Group pixels in an image into different categories - this is still a caricature of "vision," but still far more representative of real vision than simply giving a global label to an image).

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#143

Post by argonaut »

dave_sullivan wrote: post #109
Hydraulix989 wrote: post #95

Earlier quoted context omitted.

Well, not with traditional feedforward networks (LeNet, etc.). You can't run the classifier and find tires, then wheels, and then a car; but you do get composition of features.

> not with traditional feedforward networks (LeNet, etc.) I'd argue they are implicitly doing this. > You can't run the classifier and find tires, then wheels, and then a car; Why can't you run a classifier for tires, one for wheels, one for cars, then combine their outputs for a final classifier maybe based on a decision tree? You can train all the networks at the same time and it will give you a probability distrib…

That would just be your opinion. It has not been shown. It's still an open research question over what neural nets are actually learning in their intermediate layers.

You're going to need large amounts of fine-grained labeled data for each category. You've also just manually determined some sort of (brittle) object ontology. What if there are only 3 tires? What if there are four tires on the road but no car? All sorts of edge cases, and all you've done is train a classifier for cars, not actually solved driving in any meaningful way.

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#144

Post by georgespencer »

argonaut wrote: post #139
visarga wrote: post #73

Earlier quoted context omitted.

> Humans may not always see a white truck in a snowstorm, but is computer vision going to see it either? So you put in your training and test dataset a bunch of such situations. At some point you've covered enough cases to extrapolate the rest. Good testing is going to hunt for these blind spots and fix them. Fact is that it's already safer than humans, even with all its hidden imperfections.

What if that point is 20 years from now? What if every time Ford/GM/Toyota substantially changes the look of their cars, your classifier no longer recognizes them because all your data only has the old models in it. That's what people are driving at. Simply collecting more data is not enough to solve this problem.

At a certain point it's just about recognising an object which shares broad characteristics with a car rather than aesthetics. Eg it moves at the speed a car moves at, it's in the road, it's overtaking on the right hand lane. I would expect any autonomous car to be able to fail over to "this object is likely a vehicle I haven't seen before" given a strange car-like object being detected.

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#145

Post by argonaut »

georgespencer wrote: post #144
argonaut wrote: post #139

Earlier quoted context omitted.

What if that point is 20 years from now? What if every time Ford/GM/Toyota substantially changes the look of their cars, your classifier no longer recognizes them because all your data only has the old models in it. That's what people are driving at. Simply collecting more data is not enough to solve this problem.

At a certain point it's just about recognising an object which shares broad characteristics with a car rather than aesthetics. Eg it moves at the speed a car moves at, it's in the road, it's overtaking on the right hand lane. I would expect any autonomous car to be able to fail over to "this object is likely a vehicle I haven't seen before" given a strange car-like object being detected.

Great. Now the problem you've posed is no longer image classification. It's more like video classification or zero-shot classification! (neither of which are close to solved)

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#146

Post by frik »

Animats wrote: post #20

I'm still not happy with self-driving on vision alone, or vision augmented with radar. There are too many hard cases for vision. Everybody who has good self-driving right now - Google, Otto, Volvo, GM - uses LIDAR. Self-driving is coming to the first end users in 2017, in Volvo's test of 100 vehicles. Volvo has multiple LIDARs, multiple radars, multiple cameras, redundant computers, and redundant actuators. They're b…

I agree, everyone is using LIDAR in the sensor mix but Tesla. Cameras simple don't work in certain weather conditions like direct low sun light rays eg in the evening.

Ford, Volvo and others are using two (or more) smaller cheaper ($6k) LIDAR instead of the single big $70k one that everyone remembers from Google cars. And smaller cheaper LIDAR are around the corner. It seems Telsa isn't going the full self-driving long way at the moment but offers some package that doesn't fully deliver and is a risk on the road if the driver uses it in condititions outside of it's limited designated highway-style roads, but in inner cities or country side roads. I am surprised that Google doesn't deliver something or Mercedes who did research since the 1980s and if the other companies take that long, Volvo and other chinese owned car manufacturers will take the lead in the next years.

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#147

Post by Animats »

sliken wrote: post #107
Animats wrote: post #20

I'm still not happy with self-driving on vision alone, or vision augmented with radar. There are too many hard cases for vision. Everybody who has good self-driving right now - Google, Otto, Volvo, GM - uses LIDAR. Self-driving is coming to the first end users in 2017, in Volvo's test of 100 vehicles. Volvo has multiple LIDARs, multiple radars, multiple cameras, redundant computers, and redundant actuators. They're b…

Tesla is going a different way with radar+cameras. Lidar TODAY is too expensive for normal priced vehicles, google's solution is very expensive, volvo seems to be targeting large trucks which are less price sensitive. The price of the future volvo passenger cars hasn't been announced, has it? Society seems hyper sensitive to different risks, even if lower than existing risks. Thus a tesla fire is big news, even if th…

Reference for the 3 rammed cars "at speed"?

Sideswipe of car stopped at inner edge of roadway in China: https://www.youtube.com/watch?v=rJ7vqAUJdbE

Rammed stopped or slow moving street sweeper at inner edge of roadway in China. Driver killed: https://www.youtube.com/watch?v=xoSNw_n1Xgk

Rammed stopped van at inner edge of roadway in Germany: https://www.youtube.com/watch?v=qQkx-4pFjus

Those are all the same design flaw - a big solid obstacle partly blocking the lane was hit.

These all have dashcam video on Youtube. One wonders how many more times this has happened without a dashcam.

This list doesn't include ramming the semitrailer in Florida, another fatal event. (Ref NSTB investigation HWY16FH018).

(There's some denial from Tesla fans, and Musk, about this.)

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#148

Post by kybernetikos »

onion2k wrote: post #87
TaylorAlexander wrote: post #54

Earlier quoted context omitted.

Humans don't use accurate depth maps to drive. Machine learning is great at complex algorithms if done well.

Humans don't use accurate depth maps to drive. Humans are very good at estimating distance from a combination parallax visual cues and experience. We don't need to have seen a specific model of car before to judge how far away it is with a high level of accuracy.

Humans can drive well with vision in only one eye, so it seems like even binocular vision isn't necessarily as important as some of those cues and experience.

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#149

Post by 2bitencryption »

argonaut wrote: post #142
ChuckMcM wrote: post #45

Earlier quoted context omitted.

The argument reasoning I've heard goes like this; People drive reasonably well using vision primarily and with imperfect visibility of their environment. Computer learning networks can classify imagery at least as accurately as humans and sometimes more so. A computer using imagery that is well classified from an array of visual sensors with near perfect visibility should be able to drive as well, or better, than a h…

Driving has almost nothing to do with image classification. * Humans implicitly perform SLAM (simulataneous localization and mapping). What do I mean? Look around your room. Close your eyes. Visualize the room. As a human, you've built a rough 3D model of the room. And if you keep your eyes open and walk through the room, that map is pretty fine-grained/detailed too and humans can keep track of where they are in the…

Let me make sure I get this:

When a Tesla (or other non-LIDAR) vehicle is driving, it is not continuously building a 3D model of its environment. Instead, it is matching patterns on the road, and "understanding" based off what it sees in an otherwise flat image.

Whereas LIDAR vehicles use the LIDAR technology to develop a map of the world around them, for additional understanding?

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#150

Post by frik »

mrfusion wrote: post #123

How well would a modern car do in the darpa grand challenge? I'm curious how far we've come.

I doubt a self-driving car without a LIDAR would make it - on the same "test road" as in 2006. But it shouldn't be a problem for others like Google, Volvo, Ford, etc

We need an independent review of self-driving cars in a few years. It will be quite interesting how good they really are in different driving situations like different road and weather conditions. Say good buy to only-camera+radar based cars on a snowy road with bright winter sun (low sun rays) or heavy rain in a dark foggy night.

Post reply on HN