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

Tesla bought over $2M worth of Lidar from Luminar

theverge.com

Post reply on HN
Print view View original

21–30 of 44 posts

Re: Tesla bought over $2M worth of Lidar from Luminar

#21

Post by grecy »

tensor wrote: post #20
amadeuspagel wrote: post #11

Musk used to argue that since humans can drive without Lidar, cars could as well.

That must clearly be true, but I'd like cars to driver better than humans and make use of all the tech that we can't. Academically vision only is an interesting feat, and as a backup mode for when sensors fail it makes sense to pursue vision only operation, but it seems to me that having more sensors should be superior.

> but it seems to me that having more sensors should be superior.

What do you do when the sensors disagree?

Re: Tesla bought over $2M worth of Lidar from Luminar

#25

Post by darby_eight »

ljlolel wrote: post #6

In order to make vision-only depth sensing work well, you need ground-truth data. Buying a few thousand lidar to get a ton of ground-truth training data for the NN to learn distance on its own from vision is an obvious move. They're not switching to Lidar. source: i debugged lidar and built localization and behavioral planning algorithms for self driving cars

Why would they not simply use lidar in the cars themselves?

Besides, I imagine many of the issues with vision (e.g. adverse weather) could not be addressed with training-time data.

Re: Tesla bought over $2M worth of Lidar from Luminar

#26

Post by neom »

amadeuspagel wrote: post #11

Musk used to argue that since humans can drive without Lidar, cars could as well.

It's an interesting argument, I'm sure there are lots of reasons why it's a bad argument, but the one I think about is that depth perception isn't actually fully understood, mostly, but not fully, and, an important system that is always overlooked in that argument is that the vestibular system (among others) is also involved in depth perception. You can say binocular vision is just LIDAR, but that's not the whole story.

Re: Tesla bought over $2M worth of Lidar from Luminar

#27

Post by ripjaygn »

darby_eight wrote: post #25
ljlolel wrote: post #6

In order to make vision-only depth sensing work well, you need ground-truth data. Buying a few thousand lidar to get a ton of ground-truth training data for the NN to learn distance on its own from vision is an obvious move. They're not switching to Lidar. source: i debugged lidar and built localization and behavioral planning algorithms for self driving cars

Why would they not simply use lidar in the cars themselves? Besides, I imagine many of the issues with vision (e.g. adverse weather) could not be addressed with training-time data.

> Besides, I imagine many of the issues with vision (e.g. adverse weather)

LIDAR is bad in rain, fog and snow.

Re: Tesla bought over $2M worth of Lidar from Luminar

#28

Post by stetrain »

darby_eight wrote: post #25
ljlolel wrote: post #6

In order to make vision-only depth sensing work well, you need ground-truth data. Buying a few thousand lidar to get a ton of ground-truth training data for the NN to learn distance on its own from vision is an obvious move. They're not switching to Lidar. source: i debugged lidar and built localization and behavioral planning algorithms for self driving cars

Why would they not simply use lidar in the cars themselves? Besides, I imagine many of the issues with vision (e.g. adverse weather) could not be addressed with training-time data.

Because $1000 of Lidar hardware per car would be $1.85 billion per year.

Re: Tesla bought over $2M worth of Lidar from Luminar

#30

Post by stetrain »

stefan_ wrote: post #15
ljlolel wrote: post #6

In order to make vision-only depth sensing work well, you need ground-truth data. Buying a few thousand lidar to get a ton of ground-truth training data for the NN to learn distance on its own from vision is an obvious move. They're not switching to Lidar. source: i debugged lidar and built localization and behavioral planning algorithms for self driving cars

Yes, 10 years after the initial announcement, Tesla has just now got around to ordering some LIDARs for capturing ground-truth training data. They then went out of their way to get the one LIDAR made to look palatable to end customers instead of the superior industrial ones everyone puts 8 of on their recording cars. Not very credible.

> Tesla has just now got around to

What's the source that they haven't ordered from Luminar previously? They have definitely used Lidar test rigs for years.

Post reply on HN