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

Tesla Live Stream – Autonomy Day [video]

livestream.tesla.com

Post reply on HN
Print view View original

331–340 of 550 posts

Re: Tesla Live Stream – Autonomy Day [video]

#331

Post by justapassenger »

sharadov wrote: post #205
grecy wrote: post #184

Holy cow Elon said a lot of things that will drastically change the world in the next 2-3-5 years. I think it's very, very clear they've been doing a lot of stuff behind that scenes that nobody has given them credit for over these last 5 years. Everyone thought they were just throwing everything at the Model 3 ramp and doing nothing else, but it turns out the opposite is true. At the end Elon said autonomy is basical…

And I think they are far ahead of the game compared to anyone else w.r.t autonomous driving, they have a fleet sending them data back real time.

Quick look at their earnings shows it's not true. With amount of cars they have, even sending tiny % of it back home would require Tesla to spend billions on datacetners.

Re: Tesla Live Stream – Autonomy Day [video]

#332

Post by derpherp »

slg wrote: post #248
semi-extrinsic wrote: post #212

Earlier quoted context omitted.

It kinda is though. Snow deposition is a function of surface temperature, which is uniform across the sensor. Hit the wrong initial temp when you enter a blizzard, and deposition takes your vision in seconds. It can be hard enough to see out the windshield which has heating, wipers and anti-freeze wiper fluid fighting for it.

Do you realize how far you have moved the goalposts during this conversation? You started out with the suggestion that they "fully disable autonomy in September and enable it again in late April" and now you are talking about situations with "the wrong initial temp when you enter a blizzard". I will simply refer back to my initial comment in this thread: "there is going to be a decent amount of time between when a se…

I don't think OP has moved the goalposts at all. LIDAR can work in snow but cameras get covered. And yes you are right, there will be a decent time between testing in some basic scenarios and testing in all scenarios. But I do not understand why Mr. Musk is trying to reinvent the wheel and rely only on vision when LIDAR has already shown that it works better.

https://www.cambridge.org/core/journals/journal-of-glaciolog...

Re: Tesla Live Stream – Autonomy Day [video]

#333

Post by andbberger »

cromwellian wrote: post #275

Seems to me that relying too much on Machine Learning for this is actually the real risk, not LIDAR. Tesla's competitors are using ML, but combining it with sensor fused data from LIDAR, Radar, accurate maps, and visual data. In other words, they're starting from a view of the world with super-human sensing. Starting from a purely visual domain likely dooms your system to making the same types of mistakes that humans…

Indeed, Tesla is on the wrong side of history in sticking to their guns on pure vision autonomy.

And they're going to kill people.

It's hard enough already to communicate to the public in any meaningful sense ML results without #SKYNET brigading, Tesla is going to make it 100x harder dragging us all through their mud.

I think at this point (of having been a matrix boi long enough) I am allowed to publicly state my belief that we are very very very far away from human-level visual perception. Just staggeringly, incomprehensibly far. We've just barely started to be able to do the most basic things, sometimes.

Is it an incredible amount of collective dunning-kruger that is blinding tesla? Or perhaps willful ignorance?

Re: Tesla Live Stream – Autonomy Day [video]

#334

Post by salty_biscuits »

torpfactory wrote: post #150
sairahul82 wrote: post #114

Karpathy's presentation is really good. Watch it later if you get some time. The key points are - Telsa is using fleet for learning (Fleet learning). This has 3 components, a. Trigger infrasture that collects the kind of data telsa is looking for training. The rational here is we don't need massive amounts of same kind of data but needs right kind of data for training neural networks correctly. b. Data Engine which l…

Does anyone know how Lidar would work in the future when many other vehicles are also using lidar? From working with some different types of photo sensors (CCD, avalanche photodiodes, photomultiplier tubes), you might imagine that incident light from another car's emitter would be much brighter than the reflected light the lidar sensors are reading and cause saturation.

I've only got experience with aerial survey lidar, but "blinding" the photomultiplier with your own transmit pulse is pretty common, e.g. hitting something retroreflective like a cats eye marker or a street sign. Even the sun off a puddle can do it too. It is a pretty obvious artifact to recognize and remove. I guess it would depend on the mechanism of the lidar (i.e. if it is scanning then what is the probability that the different cars are scanning at each other at the same time, probably low). Might be a problem if they use flash or geiger mode lidar. But then the pulse rate would be lower. Interesting to think about. I'm sure the people working on it would have an answer.

Re: Tesla Live Stream – Autonomy Day [video]

#335

Post by justapassenger »

xedeon wrote: post #105
JustSomeNobody wrote: post #63

Earlier quoted context omitted.

> The thing I don't get about Tesla is why they keep heaping more on their plate... Musk's ego plays a lot into this for better or worse.

Two words: Vertical Integration. Apple's work on developing their own SOC (A13) have paid dividends for them. The same legendary chip designer (Jim Keller) designed the new Tesla chip after working for Apple.

For vertical integration to work you need to have funds to support it long term. Apple has it. Tesla - not that much (at least not in the current state)

Re: Tesla Live Stream – Autonomy Day [video]

#336

Post by sytelus »

sairahul82 wrote: post #114

Karpathy's presentation is really good. Watch it later if you get some time. The key points are - Telsa is using fleet for learning (Fleet learning). This has 3 components, a. Trigger infrasture that collects the kind of data telsa is looking for training. The rational here is we don't need massive amounts of same kind of data but needs right kind of data for training neural networks correctly. b. Data Engine which l…

Karpathy is great at presenting executive-101. However self-driving is much much more than image classification. You have a time component, you need to integrate information as it comes in to meaningful state (aka SLAM) and make sequential decisions that has potential to kill people. This is still unsolved research problem unlike punny ImageNet classification. Karpathy could have easily spent entire day talking about current state of the art and how they have improved on it but instead we got Deep Learning 101. I hope he didn't intentionally used this tactic to avoid talking about the elephant in the room. It seems they are hell bent on vision-based end-to-end learning which vast majority of experts would agree that is far away in the future. So this whole thing is quite bold and if they really make this happen in 1yr3mo then I'd say you should dump your entire 401K in buying Tesla stock. Collecting data is actually more trivial part of this problem.

Re: Tesla Live Stream – Autonomy Day [video]

#337

Post by rohit2412 »

SheinhardtWigCo wrote: post #315
rohit2412 wrote: post #311

Earlier quoted context omitted.

So call them driver assists. I am tired of seeing driver assists being sold as driverless systems.

Do you think people buying cars with autopilot believe they are getting fully driverless systems?

People buying current cars were just told that their cars will earn them 30k$ a year. Is fsd driver assistance or driverless?

Re: Tesla Live Stream – Autonomy Day [video]

#338

Post by justapassenger »

gonehome wrote: post #88

Interesting pieces: - First principles hardware design of focused self driving computer (many times better than any competing existing hardware). Already shipping in all newly produced cars. Currently working on next gen that will be 3x better to ship in a couple years. - Lidar is an unnecessary mistake that competitors are making that won't succeed (too expensive, need too many, unnecessary). - Real world fleet test…

> Currently working on next gen that will be 3x better to ship in a couple years.

That's ... not great. If that was CPU type of unit, it'd be great. But TPU-type accelerators are growing at massive speed (as it's still pretty new and simple tech), where you're more looking for 10x type of gains.

Re: Tesla Live Stream – Autonomy Day [video]

#339

Post by Someone »

sairahul82 wrote: post #148
tjoff wrote: post #139

Earlier quoted context omitted.

Does anyone doing lidar not also do visual recognition?

I don't think any one is doing this. This is the point Karpathy is making. Vision is essential and needs to be perfect and also has all the information to recreate the 3d environment. That's why lidar is not required and is expensive.

I agree with the essential bit, but “has to be perfect”? Do you know how bad human vision is at estimating distances, speeds, angles, etc? I don’t think you need perfect vision to implement the first law of autonomous driving (“Avoid hitting stuff”)

It also doesn’t have all the information to recreate the 3d environment. There’s all kinds of inferences that human drivers make that require a good model of the world, to start with. For example, a car shouldn’t brake for a small object that moves with the wind, even if it looks like it’s made of concrete, or looks like a child.

Re: Tesla Live Stream – Autonomy Day [video]

#340

Post by dragonwriter »

derpherp wrote: post #332
slg wrote: post #248

Earlier quoted context omitted.

Do you realize how far you have moved the goalposts during this conversation? You started out with the suggestion that they "fully disable autonomy in September and enable it again in late April" and now you are talking about situations with "the wrong initial temp when you enter a blizzard". I will simply refer back to my initial comment in this thread: "there is going to be a decent amount of time between when a se…

I don't think OP has moved the goalposts at all. LIDAR can work in snow but cameras get covered. And yes you are right, there will be a decent time between testing in some basic scenarios and testing in all scenarios. But I do not understand why Mr. Musk is trying to reinvent the wheel and rely only on vision when LIDAR has already shown that it works better. https://www.cambridge.org/core/journals/journal-of-glaciol…

> But I do not understand why Mr. Musk is trying to reinvent the wheel and rely only on vision when LIDAR has already shown that it works better.

Because he's sold a bunch of cars (and a bunch of stock in the company selling the cars) without LIDAR with the explicit claim they are hardware-ready for full self-driving.

Post reply on HN