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

Tesla Autopilot

tesla.com

Post reply on HN
Print view View original

221–230 of 347 posts

Re: Tesla Autopilot

#221

Post by nkozyra »

TeMPOraL wrote: post #189
keymone wrote: post #188

Earlier quoted context omitted.

> You don't switch from seeing cars to seeing nothing to seeing an elephant just because the input got a little noisy yeah, instead you get hallucinations, muscle twitches, seizures, mental breaks and many more ways a brain can fail to do it's job.

Sure, but a) we have thousands of years of experience with those, and b) none of those are caused by little random noise in the visual input. Brains are incredibly robust against noisy data.

Robustness is a key property of the methods and models used in self driving cars.

For a human, the noise isn't bad recognition, it's corrupted sensor data via distraction. It's one of the most common causes of accidents. For the AI agent an elephant will never appear unless it's been trained to be recognized. More likely it's recognized as an obstacle, which is ok. But keep in mind that years of Google's autonomous vehicle success make this pretty improbable, certainly less than in the average driver.

Much of the fear here is irrational and natural when humans lose control.

Re: Tesla Autopilot

#222

Post by eddyg »

willvarfar wrote: post #160
the_rosentotter wrote: post #152

Earlier quoted context omitted.

It terrifies me to think of relying on image recognition software to correctly determine an upcoming crossing road (with cars zipping across) so it can properly slow down, rather than get broadsided at full speed. Or a number of other life-and-death situations (which are common during driving). It just seems fragile (what if the 'vision' is somehow impaired, f.ex. blinded by sunlight, or the road markings are wrong o…

> It terrifies me to think of relying on image recognition software to correctly determine (... snip) Do you not drive using only your eyes? If you are not terrified of the sensors, then software? Turing's central belief was that the human brain was 'just' a computer. Regards doing things like embedding reflectors in roads and other ways to simplify lane holding, completely agree. But we can't forego the cameras etc…

Is the "computer vision" on Tesla good enough to ignore this false "lane marker" and use the actual yellow lane marker, not the "fake" one caused by the sun/shadow/pavement interaction?

http://i.imgur.com/fk3OvEW.jpg

This situation generated constant lane departure warnings for the driver.

Re: Tesla Autopilot

#223

Post by TeMPOraL »

RobertoG wrote: post #213
TeMPOraL wrote: post #204

Earlier quoted context omitted.

It's not. When you're being blinded by sun, you don't suddenly see elephants or spaceships or comic books. You also don't think the world just disappeared - you know to just ignore the visual input. Also, I'm more worried about temporary, unexpected configuration of things that suddenly make a NN see something weird.

That doesn't sound as an insurmountable problem. Humans don't see elephants suddenly because a prior is telling them that an elephant is improbable in that context. Something like that in a computer system shouldn't be above the current capabilities.

I agree it shouldn't be above current capabilities. But I'm yet to see anyone doing something like this. And I'm definitely wary about taking the results of toying with "deep learning" and saying we've can put that on a car and expect good results - which is an impression I sometimes get in articles about those topics.

Re: Tesla Autopilot

#224

Post by baby »

_ph_ wrote: post #111
madengr wrote: post #36

Will I get a DUI if I'm drunk and my car drives me home? Say I'm in the back seat.

That question only becomes relevant when it would be considered legal to have the car drive without a licensed driver in control. As long a driver with a license is required, you have of course to be fit for driving.

This is really interesting to me as I do not have a driver's license and I am not intending to get one.

Re: Tesla Autopilot

#225

Post by philippoi »

obastani wrote: post #203
Daviey wrote: post #193

Earlier quoted context omitted.

You've never been temporary blinded by a low-sun? Never sneezed and had your eyes closed at the wrong moment? This is the same thing..

Humans know when they can't see properly. The problem with adversarial examples is that the neural net thinks it's doing great. You have to manually specify every possible failure mode for the neural net before hand -- if you miss one, you might have an accident.

Usually. Drunk and sleepy drivers blur this distinction, but you still make a good point.

Re: Tesla Autopilot

#226

Post by baby »

cwp wrote: post #49
mcbutterbunz wrote: post #39

Earlier quoted context omitted.

I would guess that if you gave the command to drive home, you would be seen as the operator of the vehicle and would probably receive a DUI. If there is an emergency and the automobile needs human intervention, then you would be responsible.

Yeah. When I was in J-school, I covered a court case where a man was convicted of DUI when the cops found him asleep in the back seat of a car with the engine running. He knew he was too drunk to drive and decided to sleep it off in the back. It was a cold winter night so he turned on the engine to run the heater. He got convicted because being inside the vehicle with the engine running met the definition of "operati…

That is a pretty bad judge, one quality for judging cases is to also be human and flexible.

Re: Tesla Autopilot

#227

Post by baby »

sshanky wrote: post #10
jshap70 wrote: post #7

I love watching videos like the one they have on there. theres something almost hypnotic about it

The car seems to stop for no apparent reason. I noticed it once next to two pedestrians just off the road, and again after turning right at a stop sign. I wonder if that is why they are showing it in a sped up format -- it certainly makes it harder to notice.

I wonder how fast the car is going as well.

Re: Tesla Autopilot

#228

Post by TeMPOraL »

nkozyra wrote: post #221
TeMPOraL wrote: post #189

Earlier quoted context omitted.

Sure, but a) we have thousands of years of experience with those, and b) none of those are caused by little random noise in the visual input. Brains are incredibly robust against noisy data.

Robustness is a key property of the methods and models used in self driving cars. For a human, the noise isn't bad recognition, it's corrupted sensor data via distraction. It's one of the most common causes of accidents. For the AI agent an elephant will never appear unless it's been trained to be recognized. More likely it's recognized as an obstacle, which is ok. But keep in mind that years of Google's autonomous v…

I'm not trying to express a fear that comes from humans losing control. I don't fear that - in fact, I can't wait until the day comes no humans are allowed to drive on public roads.

I was just answering about the concerns of self-driving systems relying solely (or primarily) on visual data from cameras. It's true this is how humans drive, but human visual system is much more complicated than what the current (published) state of the art in image processing seems to be. I do not trust visual-only systems today (especially if they employ deep learning shenanigans).

I know those problems aren't insurmountable, but I'd feel much safer if they threw in a LIDAR there too.

Re: Tesla Autopilot

#229

Post by Tharkun »

TeMPOraL wrote: post #180
willvarfar wrote: post #160

Earlier quoted context omitted.

> It terrifies me to think of relying on image recognition software to correctly determine (... snip) Do you not drive using only your eyes? If you are not terrified of the sensors, then software? Turing's central belief was that the human brain was 'just' a computer. Regards doing things like embedding reflectors in roads and other ways to simplify lane holding, completely agree. But we can't forego the cameras etc…

The thing is, human "machine vision" has graceful failure modes. You don't switch from seeing cars to seeing nothing to seeing an elephant just because the input got a little noisy. The same cannot be said about current ML demonstrations - because they operate on just vision. Humans continuously reconcile visual input with their model of the world and with other inputs, to the point of overriding visual data if neede…

> You don't switch from seeing cars to seeing nothing to seeing an elephant just because the input got a little noisy.

You'd be surprised. All kinds of conditions can do really weird things to your vision. Migraine auras probably being the most common.

Re: Tesla Autopilot

#230

Post by Retric »

obastani wrote: post #203
Daviey wrote: post #193

Earlier quoted context omitted.

You've never been temporary blinded by a low-sun? Never sneezed and had your eyes closed at the wrong moment? This is the same thing..

Humans know when they can't see properly. The problem with adversarial examples is that the neural net thinks it's doing great. You have to manually specify every possible failure mode for the neural net before hand -- if you miss one, you might have an accident.

The real world is not filled with adversarial examples. Further, NN often does not think it's doing great when providing off the wall examples. Further this is a car, with GPS, where simply stopping is a completely viable option 99% of the time.

The truth is people really really stuck a driving, but it's easy enough that the vast majority of mistakes don't result in any problems.

Post reply on HN