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

91–100 of 174 posts

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

#91

Post by closeparen »

guiambros wrote: post #86
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…

> ... humans don't need LIDAR to drive, why should computers? That being the case, wouldn't we be limiting self-driving technology to the same traffic-related death rates as humans? Maybe 10, 20% better, but still fundamentally close. For self-driving cars to be truly successful, the death rates will need to be an order of magnitude better. An incremental improvement won't convince governments and the public at large…

>Maybe 10, 20% better, but still fundamentally close.

You are asserting that human drivers are essentially perfect, because in 80-90% of their crashes, the information necessary to avoid the collision just isn't available visually.

That seems like an incredibly optimistic view of human drivers.

Collisions happen because a driver does not look at, see, understand, or act appropriately on available visual signals. Or they are going too fast / following too closely for their actions to be effective.

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

#92

Post by sushirain »

ilaksh wrote: post #41
60654 wrote: post #15

Earlier quoted context omitted.

This exactly. I did robotics in the late 90's and it's interesting to see how many fundamental problems still remain unsolved. And the trajectory of tech advancement is positive for sure, but not _nearly_ as fast as popsci and marketing articles suggest.

What fundamental problems remain to be solved for self driving cars?

Vehicle detection: detect any vehicle, even from the side, even if its shape is rare, even at dark, etc. This could be solved with data.

Control: when to yield, without watching the face of the other driver, etc.

Edge cases: obeying a police officer, yielding to an ambulance, cooperating with other cars.

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

#93

Post by sangnoir »

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…

> The argument against LIDAR is just this in reverse, humans don't need LIDAR to drive, why should computers?

That is a terrible argument: birds don't need ailerons either.

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

#94

Post by dave_sullivan »

Cybiote wrote: post #85
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…

> People drive reasonably well using vision primarily This is not accurate however. Other important senses in use include proprioceptive, hearing and tactile feedback from wheels. In addition to vision and the improved dynamic range of eyes, there is the important fact that human vision integrates a world model into expectations. Human vision also models time and motion which help manage where to focus attention. Hum…

> The key difference is learning in animals occurs by breaking things down in terms of modular concepts, so even when things are not recognized new things can be labeled as a composition of smaller nearby concepts. Machines cannot yet do this well at all and certainly not as flexibly.

Actually, that's pretty much what deep learning is doing. For instance: https://papers.nips.cc/paper/5027-zero-shot-learning-through...

That paper was from a few years ago, I think the state of the art is better now, but it's trying to do exactly what you're talking about. More broadly, what you're talking about falls under the umbrella of transfer learning (that is, a model's ability to learn helpful information about task Y by training on related task X, preferably by learning and sharing useful features.)

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

#95

Post by Hydraulix989 »

dave_sullivan wrote: post #94
Cybiote wrote: post #85

Earlier quoted context omitted.

> People drive reasonably well using vision primarily This is not accurate however. Other important senses in use include proprioceptive, hearing and tactile feedback from wheels. In addition to vision and the improved dynamic range of eyes, there is the important fact that human vision integrates a world model into expectations. Human vision also models time and motion which help manage where to focus attention. Hum…

> The key difference is learning in animals occurs by breaking things down in terms of modular concepts, so even when things are not recognized new things can be labeled as a composition of smaller nearby concepts. Machines cannot yet do this well at all and certainly not as flexibly. Actually, that's pretty much what deep learning is doing. For instance: https://papers.nips.cc/paper/5027-zero-shot-learning-through..…

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.

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

#96

Post by ChuckMcM »

sangnoir wrote: post #93
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…

> The argument against LIDAR is just this in reverse, humans don't need LIDAR to drive, why should computers? That is a terrible argument: birds don't need ailerons either.

I think you meant to say that birds don't need a vertical stabilizer to change direction. Bird wings have pretty awesome ailerons built into them.

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

#97

Post by tim333 »

The PX 2 is kind of a cool computer. 8 teraflops, 250W, liquid cooled. I imagine it would run a good bit less than that most of the time. 8 teraflops is about 8% of Moravecs estimate of brain equivalence so assuming you use ~8% of your brain driving it may be about right.

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

#98

Post by cambion »

dogma1138 wrote: post #72
mattnewton wrote: post #59

Earlier quoted context omitted.

I don't understand your argument, so maybe this is off base, but if you are saying people in industry aren't replacing their supercomputers with commodity gpu's, you're wrong; both apple and google have massive purchase orders for commodity nvidia gpus because they aren't just cheaper, they are better at this application. And I imagine other companies are as well. Edit: "replace" is probably not the right word, this…

They aren't buying consumer GPU's they aren't buying the NVIDIA dedicated servers, but they aren't running Geforce chips either. If nothing else is that because you cannot virtualize Geforce line GPU's, there is no CUDA Direct or NVLINK support etc. If you are telling me that Google is buying Geforce GPU's and flashing the bios with a custom bios ripped off a Quadro card so they can do PCIe passthrough in a hyperviso…

While I agree that Google is not buying GeForce GPUs, their general use-case for GPUs does not require virtualization.

They use containers to isolate and throttle different tasks/jobs running on the same hardware.

At their scale, virtualization would be significantly wasteful in terms of manageability and overhead.

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

#99

Post by qq66 »

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…

The problem is that humans do primarily (not solely) use vision to drive, but they have mental models about the other driver. I remember once I was at a red light and when it turned green, I looked at the oncoming driver (far away) and thought, "that guy is too into his music" and didn't accelerate. Sure enough, he goes right through the red and slams his brakes halfway through the intersection.

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

#100

Post by maxerickson »

vectorjohn wrote: post #81
maxerickson wrote: post #51

Earlier quoted context omitted.

Yeah, I screwed up the math. Point stands though.

I don't think it does still stand when you were off by an order of magnitude.

Yeah, in the wrong direction, I underestimated the powertrain consumption, so the power cost of the computer is relatively even smaller.

The point I made missed the point though, it apparently isn't the energy consumption they are concerned with, other people in the thread are pointing to limiting/getting rid of the heat being the main concern.

Post reply on HN