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

391–400 of 550 posts

Re: Tesla Live Stream – Autonomy Day [video]

#391

Post by selectodude »

outworlder wrote: post #239
selectodude wrote: post #112

Earlier quoted context omitted.

Which might explain why he's a crummy CEO. If your job is to strategize for the entire company and you're busy learning the minutiae that you spend a lot of money for other people to worry about, maybe you need to consider using your time a little better. If you want to build neural nets, keep your stock, fire yourself and go build neural nets.

> If your job is to strategize for the entire company and you're busy learning the minutiae that you spend a lot of money for other people to worry about, maybe you need to consider using your time a little better This is what everyone that is not Tesla or SpaceX are doing. And have been doing for a long time. If the CEO is not an engineer at heart, what are they? I seriously doubt Elon Musk has more engineering know…

>That's quite debatable, I'd say. Isn't he getting results?

Sure, if you call burning billions of dollars a result.

Re: Tesla Live Stream – Autonomy Day [video]

#392

Post by Fricken »

penny45 wrote: post #353
Fricken wrote: post #240

Earlier quoted context omitted.

Musk would have you think it's a Lidar vs. cameras debate. It's not. It's a Lidar + cameras vs. just cameras debate. Lidar has significant shortcomings. So do cameras. But together they make for a decent perception system. With regards to fleet learning, Tesla has been going on about it for years, but more data is not better. Better data is better. Clifornia's disengagement reports have seen criticism because they pl…

It's a radar + cameras vs lidar + cameras debate. It sounds like radar + cameras > lidar + cameras

Well technically it's Lidar + Cameras + inertial measurement units + GPS + ultrasonic proximity sensors + Radar vs. all those things minus that one sensor that costs too much.

Re: Tesla Live Stream – Autonomy Day [video]

#393

Post by tomjakubowski »

slg wrote: post #321
RivieraKid wrote: post #301

Earlier quoted context omitted.

Waymo operates the first autonomous taxi service in Phoenix with plans to expand geographically, no info about the others.

Phoenix basically provides perfect conditions for self driving cars. There is very little precipitation. It gets more daylight and sunlight than any other major city in the US. There is little to no vehicle endangering wildlife. The city was mostly designed post-cars meaning there are lots of big newish straight roads and there isn't much pedestrian culture. To put it simply there is a lot of "reality" that exists in…

> It gets more daylight and sunlight than any other major city in the US.

I think every place on Earth gets just about the same amount, ~182.5 days, of daylight in a year, right? (Not accounting for solar eclipses, or that the earth's spin is slowing)

Phoenix having relatively sunny and dry weather is a point taken though.

Re: Tesla Live Stream – Autonomy Day [video]

#394

Post by leesec »

whamlastxmas wrote: post #294
dforrestwilson wrote: post #15

Earlier quoted context omitted.

Hmmm so then why is Tesla ranked last for autonomous driving by third party researchers? https://www.google.com/url?sa=i&source=web&cd=&ved=2ahUKEwiR... And Elon has a long history of making false claims about Tesla’s progress. For example in 2015 and 2016 he claimed that Teslas would be fully self-driving by 2018. So why shouldn’t we be skeptical? https://arstechnica.com/cars/2019/03/teslas-self-driving-str...

What other major manufacturer has anything close to Tesla's autopilot in a car I can buy today? As far as I know, no one.

Only really GM with Supercruise on one of their cars, the CT6. And it is not advanced as Autopilot.

Re: Tesla Live Stream – Autonomy Day [video]

#395

Post by mirimir »

toomuchtodo wrote: post #354
mirimir wrote: post #352

Earlier quoted context omitted.

I wonder if Tesla is getting subpoenaed for video clips. Other than for accidents, the SEC investigation, etc.

My FOIA requests say no, but lots of blind spots. I'm not operating "at scale" due to the cost involved with non-electronic FOIA requests.

Thanks.

I can imagine that police could mine this just like they're doing with Google geolocation data.

Re: Tesla Live Stream – Autonomy Day [video]

#396

Post by salty_biscuits »

Fricken wrote: post #173
sairahul82 wrote: post #148

Earlier quoted context omitted.

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.

Vision is probablistic. You can improve your probabilities with more data and deeper nets, but the probability is never 100%. Inferring depth using triangulation of extracted features using vision is also probabilistic. Lidar gives you very rudimentary depth and positional data, but it is precise, and reliable, and the false positives are low. Lidar is not seeing the world as a series of probabilistic phantasms that…

"Lidar is not seeing the world as a series of probabilistic phantasms that may or may not be a pedestrian, or a jersey barrier, or whatever"

Lidar is inherently probabilistic too,like every sensor is. Just because the photomultiplier voltage rises and some peak detection hardware can correlate it with a transmit pulse, it does not mean that there is a "point" at that position in 3d space. It has different error characteristics to vision sure, but it is still an inference problem with corresponding artifacts to deal with. In fact I would say that the different error characteristics actually make them ideal for sensor fusion, i.e. Lidar for initial depth and vision for filling in the details.

Re: Tesla Live Stream – Autonomy Day [video]

#397

Post by Klathmon »

maccam94 wrote: post #183
Fricken wrote: post #173

Earlier quoted context omitted.

Vision is probablistic. You can improve your probabilities with more data and deeper nets, but the probability is never 100%. Inferring depth using triangulation of extracted features using vision is also probabilistic. Lidar gives you very rudimentary depth and positional data, but it is precise, and reliable, and the false positives are low. Lidar is not seeing the world as a series of probabilistic phantasms that…

I believe he claimed that they did have all of the sensors they need with hardware v2, and they had no need for LIDAR. We'll see if that's true. One thing that stood out to me is that he said they only need radar in front because you're only moving fast in that direction. Does that mean the cars will be susceptible to T-bone accidents?

>Does that mean the cars will be susceptible to T-bone accidents?

Is there much of anything a car can do to prevent being T-Boned?

And even if there is, I don't really see it being something that radar would help much with. If you and another car are approaching perpendicularly, you'll have an almost perfect situation to get positioning and speed information over a pretty short amount of time.

Of course I've never done anything even resembling any kind of work in this space, and I don't want to pretend to know the answer, but the claims of side radar not being necessary seems to pass a smoke test.

Re: Tesla Live Stream – Autonomy Day [video]

#398

Post by xkcd-sucks »

monk_e_boy wrote: post #382
alyx wrote: post #375

Earlier quoted context omitted.

Good overview, I share your opinion. Tesla is betting BIG on NNs. In the presentation they say that we have NNs in our brain. Which is why we can look at one photo of a dog, and distill enough identifying information in order to spot the breed from then on. Training sample of 1. Curiously though, they than say that NNs don't work like our brains do, and require A LOT of training data from all angles, etc. Training sa…

> require A LOT of training data from all angles Also, we learn things outside of our cars. I ride a bike, this gives me insight into what bike riders will do on the road. I have kids, so I know a kid on the pavement will be more risky / unpredictable than an adult. I drove down a single track road today and met another car coming towards me. We stopped, then he started to reverse, there was a passing place behind hi…

Hmm maybe the problem is actually interacting with humans naturally, on the road, so self-driving is really human-style general AI

Re: Tesla Live Stream – Autonomy Day [video]

#399

Post by gjm11 »

bogomipz wrote: post #317
threeseed wrote: post #285

Earlier quoted context omitted.

That people drive vision is so idiotic. Humans have far higher resolution sensors and the most advanced computer ever seen behind them. And even that fails at a far higher rate than we want self driving cars to be.

>"And even that fails at a far higher rate than we want self driving cars to be." Thanks, but did you mean to say that people fail at a far lower rate that we want self driving cars to have? Maybe I misunderstood your point?

I'm not threeseed, but I'm pretty sure they meant what they said.

Expanded version of the argument: "Karpathy says 'people drive vision-only' and apparently intends that to convince us that vision-only is good enough. But (1) those people driving vision-only are using human brains, whose abilities we have not yet come close to duplicating, and (2) even with the astonishing abilities of the human brain, those people driving vision-only make a lot of mistakes and have a lot of accidents, and we want self-driving cars to be much safer than that. So the fact that people drive vision-only is no reason to think that self-driving cars should do likewise. They're trying to be safer than people, with less computing power; why shouldn't we make up for that by giving them extra sensors?"

Re: Tesla Live Stream – Autonomy Day [video]

#400

Post by mrep »

slg wrote: post #390
mrep wrote: post #383

Earlier quoted context omitted.

Is tesla able to perform at Waymos level in phoenix because I would expect them to be showing that off if they could? Let's be real, there has got to be some teslas with autopilot in Phoenix and the fact that they aren't trying to upshow Waymo with their Phoenix autopilot stats shows they cannot beat Waymo.

Autopilot isn't trying to compete with Waymo and therefore any comparison there is irrelevant. Tesla hasn't rolled out FSD publicly so it is unclear whether Tesla would have any data about it performs in Phoenix.

> Autopilot isn't trying to compete with Waymo and therefore any comparison there is irrelevant

So their autopilot sensors, disengagement data, and algorithms from their autopilot cars aren't being used at all for their FSD program whatsoever?

> Tesla hasn't rolled out FSD publicly so it is unclear whether Tesla would have any data about it performs in Phoenix.

Isn't that because they are using their autopilot program + the people who upgraded to the FSD tech sensors to train their FSD tech under the previously mentioned autopilot program?

Post reply on HN