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

311–320 of 550 posts

Re: Tesla Live Stream – Autonomy Day [video]

#311

Post by rohit2412 »

gthtjtkt wrote: post #304
rohit2412 wrote: post #293

Earlier quoted context omitted.

I'm getting tired of saying this. Why is it one or the other? Why only a human driver or a robot driver? Could you have a human driver in charge with an accident preventing robot, getting the best of both worlds? If the human falls asleep, the robot can do trivial driving, and the human still makes the more difficult driving decisions. The question isn't if robot car is better than an average car being driven by a hu…

> Could you have a human driver in charge with an accident preventing robot, getting the best of both worlds? We already have this and we've had it for years. What do you think automatic emergency braking is? Adaptive cruise control? Lane keeping assist? > The question isn't if robot car is better than an average car being driven by a human. It's if the same robot car would be safer if the human was driving it, and t…

So call them driver assists.

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

Re: Tesla Live Stream – Autonomy Day [video]

#312

Post by derpherp »

XorNot wrote: post #295
threeseed wrote: post #280

Earlier quoted context omitted.

Vision is not perfect though. It is impaired during night time and difficult conditions and can be obscured if dust/dirt gets on the camera. And not sure who you are but I trust all of the other companies who are doing this a lot more. And they are all using LIDAR.

Dirt and dust can also impair LIDAR (it's just light, remember?) as can adverse weather (there's a big question over how well any California-based company will perform in a non-California climate. I suppose my country - Australia - is going to be a big beneficiary of all this). It's a mistake to think LIDAR doesn't have these drawbacks - its an optical system at its core.

Yes, LIDAR has drawbacks too. That's why almost all autonomous vehicle systems "fuse" LIDAR and vision data together. The debate here should be LIDAR + camera vs only camera. Musk has turned the conversation to LIDAR vs camera.

Re: Tesla Live Stream – Autonomy Day [video]

#313

Post by Maxious »

mzs wrote: post #210
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…

The livestream is gone though https://youtu.be/Ucp0TTmvqOE

Other channels have recorded it https://www.youtube.com/watch?v=tbgtGQIygZQ

Re: Tesla Live Stream – Autonomy Day [video]

#314

Post by SheinhardtWigCo »

michaelt wrote: post #279
SheinhardtWigCo wrote: post #259

Earlier quoted context omitted.

This argument misses the forest for the trees. Even level 5 autopilot will sometimes crash into objects that are clearly visible to most humans, as will lidar-based solutions. But if the robot fleet is an order of magnitude safer than the human fleet, then it makes rational sense to prefer a robot driver to a human.

I think you might have replied to the wrong post here? I didn't say anything about humans vs self-driving cars. I'm arguing about self-driving cars with LIDAR vs those without.

Your post suggested that missing any obvious obstacles casts doubt on Tesla's claim that lidar isn't necessary, but I'm saying their claim will indeed be proven true if the overall safety level of vision-and-radar autonomy is far better than that of humans, even if they sometimes crash in ways that seem obviously avoidable to humans.

Re: Tesla Live Stream – Autonomy Day [video]

#315

Post by SheinhardtWigCo »

rohit2412 wrote: post #311
gthtjtkt wrote: post #304

Earlier quoted context omitted.

> Could you have a human driver in charge with an accident preventing robot, getting the best of both worlds? We already have this and we've had it for years. What do you think automatic emergency braking is? Adaptive cruise control? Lane keeping assist? > The question isn't if robot car is better than an average car being driven by a human. It's if the same robot car would be safer if the human was driving it, and t…

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?

Re: Tesla Live Stream – Autonomy Day [video]

#316

Post by FireBeyond »

threeseed wrote: post #282
SheinhardtWigCo wrote: post #259

Earlier quoted context omitted.

This argument misses the forest for the trees. Even level 5 autopilot will sometimes crash into objects that are clearly visible to most humans, as will lidar-based solutions. But if the robot fleet is an order of magnitude safer than the human fleet, then it makes rational sense to prefer a robot driver to a human.

Problem with Tesla is that it is crashing into objects no human would crash into. And doing so at high speed.

If not actively accelerating at them, like it did in San Francisco.

Re: Tesla Live Stream – Autonomy Day [video]

#317

Post by bogomipz »

threeseed wrote: post #285
bogomipz wrote: post #265

Earlier quoted context omitted.

>"People drive vision only." Can you elaborate on what you mean here? Do you mean that Tesla will only be using Computer Vision for autonomy? Doesn't or wouldn't Lidar compliment CV? Or is there a practical design consideration that makes them mutual exclusive?

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?

Re: Tesla Live Stream – Autonomy Day [video]

#318

Post by gamblor956 »

dreaminvm wrote: post #243
gamblor956 wrote: post #215

Earlier quoted context omitted.

This is definitely not true. The engineer explicitly stated that Tesla only gets data when trigger conditions are met (and that this was in fact always the case), so most of the miles that Tesla drivers have been driving was actually never even sent back to the mothership for use in ML training. IOW, despite Elon claiming for years that they're ahead because of the "millions of miles" of free data collection by Tesla…

They cherry-pick rare cases and use their fleet to get more examples of these situations. This seems like the right approach given more miles following the same car in a straight line is pretty useless. My takeaway from the presentation is that Tesla will perform better than other companies in this space (although I don't know enough about Waymo to comment) due to the following: -You want a large dataset (Tesla and m…

My point was that it appears that Tesla doesn't have a large and varied dataset. It has a small and pre-selected data set, since the cars only transmit data when pre-determined triggers are fired. Thus, it doesn't matter how many 1000s of drivers Tesla "has" or how many "situations" they're in, since it's not actually collecting data from most of these situations.

And Autpilot's performance (including its numerous regressions) suggests very strongly either that it doesn't have a very large data set, or else that it has a large data set of everyone doing roughly the same thing almost all of the time. These are the two most logical explanations for Autopilot's tendency to veer toward freeway dividers even (especially?) after updates.

Re: Tesla Live Stream – Autonomy Day [video]

#319

Post by Joky »

dragontamer wrote: post #152
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…

> 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: Here's my issue with that. The on-chip SRAM is only 32MB, and the RAM is LPDDR4 rated at only 68GB/s. Assuming a dot-product (multiply +…

I think the key thing is that you assume a single dot-product per RAM load. In general you get higher compute performance by doing more than this. You load weights for a layer in the SRAM, then stream from RAM tiles of data that you can compute multiple operations on.

In the same way, to reach peak FLOPs on a GPU you better use the local/shared memory as much as possible.

Re: Tesla Live Stream – Autonomy Day [video]

#320

Post by karakot »

threeseed wrote: post #282
SheinhardtWigCo wrote: post #259

Earlier quoted context omitted.

This argument misses the forest for the trees. Even level 5 autopilot will sometimes crash into objects that are clearly visible to most humans, as will lidar-based solutions. But if the robot fleet is an order of magnitude safer than the human fleet, then it makes rational sense to prefer a robot driver to a human.

Problem with Tesla is that it is crashing into objects no human would crash into. And doing so at high speed.

really? just google/bing something like "car crashed into a wall/barrier"
Post reply on HN