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

Scenarios in which Tesla FSD Beta 9.0 fails

twitter.com

Post reply on HN
Print view View original

251–260 of 502 posts

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#251

Post by enahs-sf »

bob1029 wrote: post #119
serverholic wrote: post #72

Earlier quoted context omitted.

We are going to need a fundamental breakthrough in AI to achieve the level of FSD that people expect. Like a convolutional neural network level breakthrough.

I think we should first start with a fundamental breakthrough in our willingness as engineers to admit defeat in the face of underestimated complexity. Once we take proper inventory of where we are at, we may find that we are still so far off the mark that we would be inclined to throw away all of our current designs and start over again from (new) first principles. The notion that you can iteratively solve the full-…

I think we're beginning to see the true endgame to Tesla's strategy. Elon initially said first you build the prototype to raise the capital to finance the expensive car which you build to fund the mid-priced car which you scale to build the cheap car. In reality, we're still at step two which is the expensive car and the R&D to build the real thing.

As a model Y owner, I'm quite skeptical about this generation of vehicles being able to truly hit the mark on FSD.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#252

Post by brianwawok »

flowerlad wrote: post #222
BugsJustFindMe wrote: post #186

Earlier quoted context omitted.

They should be trivially handled by stereopsis and structure from motion as well. Stereo+time photogrammetry has been solved well enough to not steer directly towards large obstacles for decades. Overreliance on machine learning pixel models to classify everything in view is the real problem.

Why not have redundant sensors and crosscheck them? Boeing 737 Max had only one AOA sensor [1], and that wasn't a great idea. https://www.cnn.com/2019/04/30/politics/boeing-sensor-737-ma...

Right, so what happens when one says wall, and one says clear air? You brake? That is what happens now with phantom braking. Approaching a bridge? camera sees air, radar sees wall, slam on brakes.

You want the best sensor type over a high-fidelity sensor and a lower fidelity sensor. The Tesla system has 8 cameras (3 forward), so they def have overlap between what they are considering better cameras.

Time will prove which approach wins.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#253

Post by steelframe »

cs702 wrote: post #235
rhinoceraptor wrote: post #136

Earlier quoted context omitted.

The fact that it 'only' requires human intervention so rarely is still incredibly dangerous. You can't ask a human to have complete focus for hours on end when they're not making any inputs, and then require them to intervene at a moment's notice. That's not how humans work. Also, the fact that they're distributing safety critical software to the public as a 'beta' is just insanity. How many more people need to die a…

> You can't ask a human to have complete focus for hours on end when they're not making any inputs, and then require them to intervene at a moment's notice. That's not how humans work. I agree. Everyone agrees. That's why FSD Beta 9 is closed to the public. My understanding is that only a few thousand approved drivers can use it. > Also, the fact that they're distributing safety critical software to the public as a '…

What are the qualifications of the people selected to participate in the Beta? Do they have any particular experience or receive special training that would set them apart from the general public?

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#254

Post by matz1 »

foepys wrote: post #226
matz1 wrote: post #202

Earlier quoted context omitted.

>Mandatory breathalyzer tests before every engine start We don't do that today and we are still allowing people to drive on the road today.

Exactly. That's why Tesla's approach is bad. There is no rush to let this technology out on the streets before testing it rigorously for flaws. But Tesla promised FSD for all current models with FSD hardware, so they have to move or they will potentially be on the hook for fraud. I call this irresponsible and dangerous.

Disagree, Tesla approach is the right approach. You want to test the technology as early as possible in real situation as much as possible.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#255

Post by yawaworht1978 »

Any human driver driving like that would have his driver's licence revoked, might risk prison for endangerment of society and perhaps be subject to a psychological evaluation (not joking, this stuff happens in Germany). Why are there no consequences for neither Tesla nor the lawmakers who are looking away?

Sure, test autonomous driving off the roads or on dedicated test environments, but do not permit this on public roads, i do not wanna be part of any beta test.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#256

Post by EForEndeavour »

manmal wrote: post #159

Is FSD still operating on a frame-by-frame basis? I remember it was discussed on Autonomy day that the ideal implementation would operate on video feeds, and not just the last frame, to improve accuracy. When you look at the dashboard visualizations of the cars‘ surroundings, the model that is built up looks quirky and inconsistent. Other cars flicker into view for one frame and disappear again; lane markings come an…

You've nicely articulated what was bothering me about the jittery dashboard visualizations. Why on earth is everything flickering in and out of existence, and why is the car's own planned trajectory also flickering with discontinuities?? It seems like they aren't modeling the dimension of time, thus throwing away crucial information about speed and needlessly re-fitting the model to static snapshots of dynamic scenes.

It's like the ML system needs its inferences constrained by rules like "objects don't teleport" or "acceleration is never infinite."

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#257

Post by olyjohn »

emodendroket wrote: post #228
toomuchtodo wrote: post #15

Earlier quoted context omitted.

> I don't understand how something this broken is allowed to operate on public roads. Also out in a rural area. Running out to pickup lunch a few minutes ago, a young man flipped their old pickup truck on its side in an intersection, having hit the median for some reason. I too don't understand how humans are allowed to operate on public roads. Most of them are terrible at it. About 35k people a year die in motor veh…

> I believe the argument is the software will improve to eventually be as good or better than humans, and I have a hard time not believing that, not because the software is good but because we are very bad in aggregate. But logically this doesn't really follow, does it? That because humans are not capable of doing something without errors a machine is necessarily capable of doing it better? Your argument would be mor…

Yeah in the parent post, how many miles did that guy drive before flipping his truck? In all of these videos, we are seeing it disengage multiple times within a couple of miles. Nobody is that bad of a driver that they crash every time they go out and drive.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#258

Post by BugsJustFindMe »

wiz21c wrote: post #239
BugsJustFindMe wrote: post #215

Earlier quoted context omitted.

They probably would be if they stopped using such shitty cameras. It always blows my mind that the cameras they use appear to be quite bad for the job. > in the night Purpose-built cameras can see better in the dark than humans can.

But we have a working brain to interpret those images.

Your brain helps you with all kinds of things, but fundamental geometry is not magic. Reconstructing scene geometry from high quality binocular video is an extremely well developed field and has been for decades. The problem seems to be that Tesla overrelies on ML-based instantaneous pixel classification when you don't actually need to know what a large thing moving toward you is in order to not run into it.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#259

Post by moralestapia »

wiz21c wrote: post #239
BugsJustFindMe wrote: post #215

Earlier quoted context omitted.

They probably would be if they stopped using such shitty cameras. It always blows my mind that the cameras they use appear to be quite bad for the job. > in the night Purpose-built cameras can see better in the dark than humans can.

But we have a working brain to interpret those images.

And this is supposed to imply what exactly?

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#260

Post by Arch-TK »

toomuchtodo wrote: post #35
Syonyk wrote: post #27

Earlier quoted context omitted.

Could have been equipment failure on the truck - a tie rod end failing or such will create some interesting behaviors. > I believe the argument is the software will improve to eventually be as good or better than humans, and I have a hard time not believing that. I find it easy to believe that software won't manage to deal well with all the weird things that reality can throw at a car, because we suck at software as…

Is flying a helicopter on Mars arrogance? Launching reusable space launch vehicles that boost back to the landing site arrogance? I don't believe so. These are engineering challenges to be surmounted, just as safe robotic vehicles are a challenge, and its reasonable (I'd argue) for us as a species to drive towards solutions (no pun intended). Silicon Valley isn't going to suddenly become less arrogant, but that doesn…

>Is flying a helicopter on Mars arrogance?

No, but I am not so sure it's anything more than a stunt with a high chance of failure.

>Launching reusable space launch vehicles that boost back to the landing site arrogance?

Maybe, but it's mostly a PR stunt from my point of view.

Just my 2 cents.

Post reply on HN