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

Tesla AI Day [video]

livestream.tesla.com

Post reply on HN
Print view View original

111–120 of 187 posts

Re: Tesla AI Day [video]

#111

Post by shkkmo »

lttlrck wrote: post #91
abc_lisper wrote: post #74

Earlier quoted context omitted.

Idk.. animals seem to do fine without a lidar

If Tesla switches to stereoscopic vision with fully articulated cameras that can move independently of the vehicle (not fully independent, but limited 3 degrees of motion), and then they manage to integrate the output into something meaningful then maybe it would be comparable.

Animals tend to use a combination of four tools to detect distance. Stereo vision, parallax, focus detection and scene context. Independent movement is not required for any of these (though it can help generate parallax.) Humans (and other animals) can learn to do pretty well with one eye and no head movement given the appropriate training regime.

It makes the software problem harder but it certainly is possible.

Re: Tesla AI Day [video]

#113

Post by panick21 »

joshuamorton wrote: post #65
panick21 wrote: post #63

Earlier quoted context omitted.

Lidar might have dropped in price, but please show me the Lidar that can produce that quality output, is incredibly cheap, easy to manufacture and integrate into the car and available millions of time by next year. And it would be great if it something that almost never broke as things that move a lot tend to. As far as I know static lidar are nowhere near as good. Then if the difference in quality is not actually th…

> And it would be great if it something that almost never broke as things that move a lot tend to. As far as I know static lidar are nowhere near as good. Keep in mind you're saying this about something that attaches to a car, which already has dozens or hundreds of parts that rotate at hundreds or thousands of RPM. > Then if the difference in quality is not actually that great, doing the development effort once will…

Adding more rotating parts is exactly what you are trying to avoid. For example, go look at how Tesla designed the heating and cooling system. The integrated all the different streams of hot and cold in one system duplicate these parts that can break easily.

In some cases it can simply not be avoided of course but you better make sure that you really need it if you are gone add it to millions of cars.

> cruise and waymo and co have multiple units per vehicle and collectively hundreds of thousands of vehicles

Waymo has vehicle count of a few 1000s as far as I know. I don't know about cruise but I don't think the have even 100k vehicles. Please show me a source.

And even if that were the case, the build those fleets of quite a long time and the cost per vehicle they currently have is nowhere near close to what would be possible for a car like the Model 3 or future cheaper models.

Margins in car industry are incredibly tight, car companies invest gigantic amount of capital to remove a few $ per car. These vehicles need to be able to be produced at a run rate of millions per year. If you are proposing to add something that cost 100-1000$ that is a absolute killer.

In addition its an additional part that can hold up your production. This current chip shortage is a perfect example where having a Lidar would just introduce a whole host of new chips that might be in a shortage.

Re: Tesla AI Day [video]

#114

Post by cmrdporcupine »

rnaud wrote: post #36
tru3_power wrote: post #34

Earlier quoted context omitted.

What was their reasoning for not using Lidar?

Too expensive + Your eyes already do the distance estimation and they are basically cameras so we can do this just as well or better.

My eyes don't get covered in salt and mud while driving down the highway.

But people in California probably don't get this.

Re: Tesla AI Day [video]

#115

Post by panick21 »

itsoktocry wrote: post #70
xibalba wrote: post #11

Thus far, this is all information Andrej has presented elsewhere. Edit: Wow, Ashok's section was amazing. It does seems as though their ability to simulate (on top of their fleet's data collection advantage) could allow them to rapidly accelerate toward true FSD. I really like that they capture real world failures and simulate many realizations of them.

> could allow them to rapidly accelerate toward true FSD Every year a little BS is added, and the faithful believe this. There is zero evidence they collect the data they claim to.

You think they are fake collecting data? I suppose they wrote code to create fake uploads from peoples cars. How deep is this conspiracy going.

How does the FSD Beta work? Do they buy data from somewhere else? Or are all the people who have the FSD Beta paid by Tesla to create fake content.

True conspiracy theory you have unraveled here.

Re: Tesla AI Day [video]

#116

Post by shkkmo »

ModernMech wrote: post #106
cycrutchfield wrote: post #103

Earlier quoted context omitted.

Are humans animals?

When we're talking about the brain and its processing, planning, and decision-making abilities exhibited during driving, no. We are distinct from animals. We have the technology to build robots that mimic the capabilities of animals, from birds to fish to snakes, and now approaching dogs. Trying to do what humans do while driving with binocular cameras is far beyond our capabilities. Like I said, if you want to drive…

Animals do just fine with more complex navigation challenges than driving a car. While we can 'mimic' various animal capabilities, I don't believe we are anywhere close to AGI with either a dog's level of intelligence, motor control or sensory integration.

Re: Tesla AI Day [video]

#117

Post by oliv__ »

TheDong wrote: post #21
Invictus0 wrote: post #15

I like Andrej and I think he's a brilliant guy. At the end of the day though, there is no way for me or anyone to audit the neural networks or their training data. How can anyone trust them? I think this is really a fundamental problem with using neural networks in self-driving cars--I don't want to put my life in the hands of a fragile system that I, and no one alive, can understand. We are being asked to close our…

> I don't want to put my life in the hands of a fragile system that I, and no one alive, can understand. [...] just hope nothing out of the ordinary will ever happen while we're in the car. This honestly sounds pretty similar to the current state of affairs. Currently, there are 0 people that fully understand the human brain. If you're driving, and someone turns in front of you suddenly, you can ask "why did they do…

The main difference is you have knowledge of how your own brain operates in reality, what kind of actions you might take in a given situation (and by extension the same can be said of other humans), whereas most (if not all?) people have no clue how neural nets operate, so all bets are off when it comes to predicting what the computer could/will do.

Contrast that with a human: you know the subset of possible actions a human would likely take. Even when you see a car swerving and acting like the driver is drunk, you have a mental model of the set of actions to expect from such a car (you might add more distance between you and that driver for example).

Re: Tesla AI Day [video]

#118

Post by pyinstallwoes »

lttlrck wrote: post #91
abc_lisper wrote: post #74

Earlier quoted context omitted.

Idk.. animals seem to do fine without a lidar

If Tesla switches to stereoscopic vision with fully articulated cameras that can move independently of the vehicle (not fully independent, but limited 3 degrees of motion), and then they manage to integrate the output into something meaningful then maybe it would be comparable.

Maybe it's more like spider eyes that see a blended vectorspace of reality with less movement?

Re: Tesla AI Day [video]

#119

Post by ctdonath »

mdorazio wrote: post #51
rnaud wrote: post #36

Earlier quoted context omitted.

Too expensive + Your eyes already do the distance estimation and they are basically cameras so we can do this just as well or better.

> Your eyes already do the distance estimation and they are basically cameras so we can do this just as well or better. This is not really accurate. Our brains do the distance estimation, and they use all kinds of tricks and contextual clues to do it, not just parallax (~2.5 inch parallax for objects more than ~100ft away isn't all that helpful). And this is the whole problem with vision-only autonomous driving - ML…

That’s exactly what Tesla described tonight. 8 video cameras on a moving platform provide enough eyes, parallax, context, etc to build accurate 4D (!) models in real time.

Re: Tesla AI Day [video]

#120

Post by AlotOfReading »

ajross wrote: post #26
Invictus0 wrote: post #15

I like Andrej and I think he's a brilliant guy. At the end of the day though, there is no way for me or anyone to audit the neural networks or their training data. How can anyone trust them? I think this is really a fundamental problem with using neural networks in self-driving cars--I don't want to put my life in the hands of a fragile system that I, and no one alive, can understand. We are being asked to close our…

> At the end of the day though, there is no way for me or anyone to audit the neural networks or their training data. How can anyone trust them? By external measurements and statistics. You measure an ML engine by performance. Literally no one anywhere knows how to debug these things by looking inside the model. If it's a "fragile system" then it will be shown to be so in data. At the end of the data, either cars cra…

How can you measure the performance of an ML engine in untested conditions? Tesla's whole goal is to achieve L5 capabilities. That means anywhere in any conditions, which is clearly impossible to comprehensively validate with a finite test set. It's plausible that we could get a long period of acceptable safety before a black swan event suddenly causes deaths because it can't handle smoke, heavy rain/fog, or blizzards.
Post reply on HN