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

Tesla's self driving algorithm's overlay [video]

tesla.com

Post reply on HN
Print view View original

501–510 of 658 posts

Re: Tesla's self driving algorithm's overlay [video]

#501

Post by eru »

mike_d wrote: post #468
grecy wrote: post #431

Earlier quoted context omitted.

There is speculation going around the "big rewrite" Elon mentioned last week is actually porting the code to run natively on the new hardware. Speculation says it's just been running in an emulation layer, but now they're about to unleash the full potential of the hardware. If true, it makes sense the video would also have been captured using this emulation layer, explaining why it's not latest-and-greatest-fast.

If that is true you should call in to question the integrity of a company that would run life-critical software on a non-RTOS.

Realtime has nothing to do with absolute performance. It's about meeting your deadlines.

And, of course, often real-time systems have much worse throughput performance than a non-real-time system on the same hardware. After all, latency guarantees are not free.

Re: Tesla's self driving algorithm's overlay [video]

#502

Post by eru »

platz wrote: post #401
iamaelephant wrote: post #399

Earlier quoted context omitted.

"Just". Pro tip, these guys work on these problems all day every day. If you think you've solved one of their major problems after 18 seconds of consideration then you're probably missing a large amount of context.

I was inviting you to tell me why

I do appreciate your intent, but I learned that to get the intended response you need to add way more humility into your provocative question. Especially in written communication amongst strangers, where there's a lot of contexts from body language etc missing.

Re: Tesla's self driving algorithm's overlay [video]

#503

Post by eru »

ajross wrote: post #423
platz wrote: post #393

Earlier quoted context omitted.

Why can't they just whack it with some kind of Bayesian latent space model. A big jump should have to require more evidence than the history of the previous posterior

Presumably that sort of thing does exist at some other layer. But the design goal here is, obviously, very much NOT to reduce the false positive rate via clever filtering, it's to reduce the rate of collisions with REAL OBJECTS IN THE ENVIRONMENT. Tolerating some false positives, and the phantom braking incidents that go with them, is going to be needed. Basically, no, you don't just throw it at some Bayesian math or…

Well, there's some trade-off between false positives and false negatives. Otherwise the optimal would be never to start the car.

But yeah, the scales are heavily tipped.

Re: Tesla's self driving algorithm's overlay [video]

#504

Post by eru »

01100011 wrote: post #490
FatalLogic wrote: post #440

Earlier quoted context omitted.

The raw sensory inputs to a human brain must also be jittery. Eyes apparently see highest definition detail only in a tiny area of the visual field, for example. The brain stitches it together, interpolates, tags features, and guesses. The preprocessing miraculously creates the impression of a big clear image out of a dirty data feed from two jello cameras that are swiveling around all the time. There's a lot a smoot…

There's smoothing, but maybe more importantly there is an expectation of continuity and a bias towards likely interpretations. The brain is trying to detect what it already thinks should be there, and not starting from scratch every millisecond. I'm not sure if anyone is doing that with neural nets, but I think we'll keep failing until we do that.

Yes, mostly. Your brain also cheats and adjusts your memory retrospectively to a certain degree.

Re: Tesla's self driving algorithm's overlay [video]

#505

Post by eru »

jacquesm wrote: post #138
agumonkey wrote: post #108

Earlier quoted context omitted.

I like to check for ranges and limits

Big fan of treating all inputs and outputs to and from functions as hostile. So parameters and return values as well. Always interesting how fast the bugs turn up once you start enforcing that.

Yes. See eg https://hillelwayne.com/talks/beyond-unit-tests/

Re: Tesla's self driving algorithm's overlay [video]

#506

Post by Veedrac »

Animats wrote: post #472

Compare Google's system from five years ago.[1] (at 7:42) This new video is at n00b level compared to that. [1] https://embed.ted.com/talks/chris_urmson_how_a_driverless_ca...

Note that Google's system operates in pre-mapped areas and uses lidar.

Re: Tesla's self driving algorithm's overlay [video]

#507

Post by yogrish »

Animats wrote: post #472

Compare Google's system from five years ago.[1] (at 7:42) This new video is at n00b level compared to that. [1] https://embed.ted.com/talks/chris_urmson_how_a_driverless_ca...

Please understand, Tesla works only with only Camera & Radars (at L2 level). Where as Google Waymo works with pretty expensive and lot of redundant sensors ie., 360degree LIDAR, cameras & Radars (at L4 level). Tesla sells vehicles in volumes, Waymo doesn't (as it is exhorbitant). Hence comparison is not apple to apple. I do agree Visualisation in the google video is more appealing. I assume Tesla also has state of art visualations for their algo development.

Re: Tesla's self driving algorithm's overlay [video]

#508

Post by axguscbklp »

xkjkls wrote: post #291
axguscbklp wrote: post #200

Earlier quoted context omitted.

The thing is, I see no way to have full self driving without AGI. And I don't think humanity is anywhere close to developing AGI. Without AGI you can have level 4++ self driving, maybe, but not level 5.

How much difference does 4++ vs 5 make for the predicted consequences of self-driving cars though? That's the important thing.

I would say that I would feel comfortable falling asleep in a 5 while it is driving nontrivial distance and/or road conditions, but I would not feel comfortable doing so in a 4++.

Re: Tesla's self driving algorithm's overlay [video]

#509

Post by torpfactory »

unityByFreedom wrote: post #475
Animats wrote: post #472

Compare Google's system from five years ago.[1] (at 7:42) This new video is at n00b level compared to that. [1] https://embed.ted.com/talks/chris_urmson_how_a_driverless_ca...

Plus Tesla still does not report disengagements to the CA dmv, right? It seems so strange to me that their HQ is there and they do not report any testing there.

Either Tesla: (1) Call it a 'driver assist system' and carry that definition beyond all reasonable bounds. I've read the regulation, I don't think that defense would stand up in court. (2) Does physical testing somewhere other than California. The testing regulation is fairly onerous, and I could see them saying 'nah' we'll do this in Arizona, Nevada, etc.

You're right they don't report disengagements, but they still maintain a autonomous test vehicle permit in the state, according to the DMV website. Very strange indeed. I think (2) is probably right.

Re: Tesla's self driving algorithm's overlay [video]

#510

Post by axguscbklp »

rifung wrote: post #453
axguscbklp wrote: post #200

Earlier quoted context omitted.

The thing is, I see no way to have full self driving without AGI. And I don't think humanity is anywhere close to developing AGI. Without AGI you can have level 4++ self driving, maybe, but not level 5.

> The thing is, I see no way to have full self driving without AGI. Why? AGI seems like a significantly harder problem than self driving cars (itself a hard problem admittedly). What I personally think will happen is we'll meet somewhere in the middle: we can redesign roads/cars to make solving the problem of self driving easier.

Because of all the edge cases that humans can handle a good amount of the time because we have a lot of intelligence compared to any computer.

But I agree with you that if we meet in the middle, that could actually work well.

Post reply on HN