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

471–480 of 550 posts

Re: Tesla Live Stream – Autonomy Day [video]

#471

Post by unityByFreedom »

ehmish wrote: post #155
Traster wrote: post #125

I'm sorry but I'm finding it really difficult to watch this and match up what the engineer is saying to what Elon Musk is saying. For example, the engineer says the custom ASIC does 144 TOps for 2 chips vs the NVidia drive Xavier - does 21 TOps. Okay, well yeah I expect your custom ASIC does have a nice performance advantage over the equivalent GPU. at 3.5x advantage probably seems reasonable. Cue Elon Musk: "At firs…

This doesn't seem wildly inconsistent with my understanding of Elon musk, in that he has a higher level of confidence of his understanding of the world than others would, and in a "you don't know what you don't know " way it seems he didn't know about custom how custom ASICs are much more efficient at specific tasks than a general purpose computer. Doesn't make him a bad person, and in fact something like that is exa…

I don't understand this response to the above comment. You write,

> it seems he didn't know about custom how custom ASICs are much more efficient at specific tasks than a general purpose computer

Yet, Musk is clearly stating his new chip is state-of-the-art. He is not underselling it.

> something like that is exactly who you want leading a company trying to change the rules of the industry they're in

You want someone in charge who does not understand the hardware he's touting?

> it's the job of the boots on the ground to exercise due diligence here

Who are you referring to? Employees and investors?

What, then, do you consider are the responsibilities of the CEO, if due diligence is not part of the job?

Re: Tesla Live Stream – Autonomy Day [video]

#472

Post by monk_e_boy »

zaroth wrote: post #436
threeseed wrote: post #430

Earlier quoted context omitted.

This is actually the aspect that really doesn't get discussed enough. Imagine these scenarios: a) Roadworks and a guy tells you to stop or waves you through. Or asks you to drive slowly. Or points to a direction that he wants you to go. b) Woman on the side of the road is waving their arms about because her small child is crawling on the road trying to chase a toy. If self driving cars can't look another person in th…

What's the more interesting question is not whether there will be corner cases where self-driving fails, but when the average performance is so much better than humans that AI saves 10s if not 100s of lives every day, but that's still a reality where AI driving software could be actively out there involved in the deaths of a single digit number of different people a day or week. Do you deploy that build or not?

For sure deploy if the numbers are right. It's the edge cases that are interesting.

Cameras are fine in the day, but when I struggle to see at night, in the rain, with spray from cars, glare from on coming traffic... that's where I would LOVE to have a lidar assisted heads up display. How Tesla think they can do better with just cameras compared to another car with cameras AND lidar just baffles the mind.

Re: Tesla Live Stream – Autonomy Day [video]

#473

Post by hellllllllooo »

robterrell wrote: post #73
grey-area wrote: post #47

“Anyone using Lidar is doomed” Strong words from Musk about sticking with video only. Later on in the software talk: “Lidar is really a shortcut which sidesteps the fundamental problems...and gives us a false sense of progress”

I wonder if he's going to explain this position at all? Or if it's just posturing against Waymo et al. Seems like more data is always better than less data for this application?

Yeah it's nonsense. It's an after the fact reframing of a decision that was made for other reasons. Lidar + camera is better for this kind of problem. It's because current lidar are too expensive and too fragile (1-2year life) to put in a production car, not because they aren't much better. If this wasn't the case he'd definitely be using them. Elon cannot use a lidar in a Tesla even if he wants too so he's coming up with some FUD to dismiss any completely reasonable questions in advance.

Re: Tesla Live Stream – Autonomy Day [video]

#474

Post by cromwellian »

salty_biscuits wrote: post #447
cromwellian wrote: post #439

Earlier quoted context omitted.

That's not how maps are used, and the map can be used as purely negative signal if you want, as in "no go" areas instead of "yes, this is safe". As it stands, Tesla's vision only system has no other backup system to tell us what is off limits.

Can you elaborate a little about how the maps are used? The "go/no go" is basically the sort of thing I mean by "high level navigation", the sort of thing a satnav system would provide help with. If they have nothing like that it seems insane. I guess there is an ambiguity around how high detail is "high detail".

Neural networks are probabilistic. They output predictions and are rarely 100% confident. So when Tesla's visual neutral networks are assigning inferred labels to things like cars, bikes, pedestrians, road barriers, etc, there is always some chance, say, 0.1% that it's wrong.

If you have other sensors, like LIDAR, radar, and high resolution maps, then you can corroborate your predictions, so for example, if the visual system predicts a 99.9% chance you can make a safe right turn, checking the LIDAR and map will provide additional checks, even if your map is out of date. Consider:

1) camera system predicts you can make a right turn. You have no map, so you make it. 2) camera system predicts you can make a right turn, you have a map, the map says there's a wall there. You don't make the turn. If the map is wrong, you're still safe, you just missed your turn off. 3) camera system predicts you can make a right turn, you have a map, the map is out of date and says there's no wall there, but a new barrier has been erected and the map doesn't contain it. This is equivalent to situation #1 4) Same as #3 but you have SIDE RADAR, so you sense the barrier 5) Same as #3, but you have SIDE LIDAR, so you sense the barrier

The problem is, Tesla is not only going "all in" with their "we only need video cameras", but Elon Musk was asked directly at intersections if the lack of side radar was a problem, and he again fell back on "video is all you need", but if that's the case, why even have front radar?

Clearly, video is not enough, and if you have front radar, there's no reason to argue against side or rear radar, and by proxy, against LIDAR.

All of this comes down to the Tesla is shipped with a cheap and fixed sensor suite, they can't change it now, it's too late, and so they are trying to justify their previous design decisions with overconfident sales tactics and PR, and I think this is somewhat reckless and dangerous to the entire AV industry because the more Tesla's that crash and kill people, the more all AVs will be tarnished as dangerous by the public.

Musk is acting like Tesla is SpaceX and they can afford to blow up rockets or astronauts during iteration, but these are consumer products. People will trust these things to be safe, not to be "beta"

Re: Tesla Live Stream – Autonomy Day [video]

#475

Post by kurtisc »

davej wrote: post #254
tomComb wrote: post #135

Earlier quoted context omitted.

I'm a fan of Tesla, but not Musk. You really can't believe much that comes out of his mouth. If you look at his past claims it becomes clear that he should just be ignored.

> If you look at his past claims it becomes clear that he should just be ignored. What's an example of this? His timelines are often much too aggressive for reality but he repeatedly delivers (eventually).

>he repeatedly delivers (eventually)

This is essentially unfalsifiable. In the case claims about FSD or a person on Mars are wrong then this statement can only be proven wrong when Elon Musk chooses to admit defeat - suffering a significant personal financial loss as a result - or when he retires.

Re: Tesla Live Stream – Autonomy Day [video]

#476

Post by jakobegger »

cma wrote: post #446
Traster wrote: post #125

I'm sorry but I'm finding it really difficult to watch this and match up what the engineer is saying to what Elon Musk is saying. For example, the engineer says the custom ASIC does 144 TOps for 2 chips vs the NVidia drive Xavier - does 21 TOps. Okay, well yeah I expect your custom ASIC does have a nice performance advantage over the equivalent GPU. at 3.5x advantage probably seems reasonable. Cue Elon Musk: "At firs…

Is it really an ASIC? I thought they said over and over it is full custom.

Definition from wikipedia:

> An application-specific integrated circuit (ASIC /ˈeɪsɪk/) is an integrated circuit (IC) customized for a particular use, rather than intended for general-purpose use.

Is there anything more "custom" than an ASIC?

Re: Tesla Live Stream – Autonomy Day [video]

#477

Post by lonnyk »

RivieraKid wrote: post #255
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…

It's so frustrating to see that people eat Elon's BS. Even after: - the Unsworth lie - the "zero concern and I mean zero about 10k Model 3s per week in Dec 2018" lie - the "funding secured" and "only uncertainty is shareholder approval" lies - the "short burn of the century" lies I mean, they were even wrong about Nvidia's chip today, Nvidia had to issue a statement: https://www.marketwatch.com/story/nvidia-says-tesl…

The tech specs of AGX Pegasus say they're 130 TOPS[1]. Or am I misunderstanding something?

[1] https://developer.nvidia.com/drive/drive-agx

Re: Tesla Live Stream – Autonomy Day [video]

#478

Post by salty_biscuits »

cromwellian wrote: post #474
salty_biscuits wrote: post #447

Earlier quoted context omitted.

Can you elaborate a little about how the maps are used? The "go/no go" is basically the sort of thing I mean by "high level navigation", the sort of thing a satnav system would provide help with. If they have nothing like that it seems insane. I guess there is an ambiguity around how high detail is "high detail".

Neural networks are probabilistic. They output predictions and are rarely 100% confident. So when Tesla's visual neutral networks are assigning inferred labels to things like cars, bikes, pedestrians, road barriers, etc, there is always some chance, say, 0.1% that it's wrong. If you have other sensors, like LIDAR, radar, and high resolution maps, then you can corroborate your predictions, so for example, if the visua…

Ok, lots of separate issues there. In terms of actually using a map I think my original point still stands. You need to use online navigation information to localize yourself within the map before you can use it. There is also the non trivial issue of actually doing a bayesian update of "can I go around this corner" given the error budget coming from how accurate is the map, how accurate is my position within the map and how accurate my other sensors are. Weighting all these probabilities and actually updating the state in a principled way is a bit of a nightmare (given the long tailed and multimodal distributions flying around). In a well principled controller the lack of certainty of the state should simply result in a more conservative control action. In your vision only scenario the correct control with high uncertainty is caution. i.e. slow down and don't turn until it can work out what is going on. This has nothing to do with sensors. It is possible to be safe with poor sensors but it will probably result in an unacceptable closed loop performance (will drive like grandpa). A big problem here is that it is really hard to get this stuff right. Probabilities will not be actual probabilities and solving the correct control problem is intractable in real time (i.e. actually solving the stochastic program for the optimal control action). Engineering problems always have constraints, I don't have a problem with a limited sensor set. Sure it is always better to add more sensors but money is a problem. So are logistics. I do have a problem with doing this hard problem badly and practicing in public. Really difficult problem to solve, being cavalier probably isn't the way to go.

Re: Tesla Live Stream – Autonomy Day [video]

#479

Post by cjhopman »

breakyerself wrote: post #455
cjhopman wrote: post #443

Earlier quoted context omitted.

> This is what everyone that is not Tesla or SpaceX are doing. If your goal is to make money, I'd follow anyone but Tesla or SpaceX's example.

How is SpaceX a bad example? They've managed to undercut everyone in the space launch sector while bringing in a larger profit per launch.

SpaceX isn't public or open about their financials, but there's a lot of evidence that they are simply losing money. Ex. they were raising a lot of money last year, profitable companies don't do that. Also read https://www.theverge.com/2018/12/7/18129539/spacex-falcon-9-...

Re: Tesla Live Stream – Autonomy Day [video]

#480

Post by Traster »

mrtron wrote: post #193
Traster wrote: post #125

I'm sorry but I'm finding it really difficult to watch this and match up what the engineer is saying to what Elon Musk is saying. For example, the engineer says the custom ASIC does 144 TOps for 2 chips vs the NVidia drive Xavier - does 21 TOps. Okay, well yeah I expect your custom ASIC does have a nice performance advantage over the equivalent GPU. at 3.5x advantage probably seems reasonable. Cue Elon Musk: "At firs…

I think the part that Elon, and the engineer, are trying to express that you are looking past is "A dot product with some memory attached" is what they need to do low latency image inference on the camera data. They don't need a multipurpose CPU/GPU, they have a single well defined task that dominates their compute needs. They built a chip to do this that is cost and power effective, and redundant for safety.

Right, but Nokia's 5G backhual infrastructure is far more capable of doing Mobile backhaul than a GPU, you don't get the head of Nokia standing up in a press conference telling everyone his team has designed the best chip in the world.
Post reply on HN