Hacker News Reader

Comment by anonu | Hacker News Reader

I'm still amazed Tesla has decided not to use lidar and instead just stick with cheap cameras. Better sensors are there, they're available, they're cheap and they can probably "see" better than plain old cameras... it doesn't make too much sense not to use them IMHO. But then again, I am not coding NNs for Tesla...

View on HN

I think they advertised self-driving as a future feature of the Model 3, so I think they are limited to whatever Model 3's currently have.

While LIDAR's are certainly 'better' from a technological standpoint than not having anything, from a business standpoint it's less clear.

LIDAR's are cheap, but not cheap enough yet to not seriously affect the bottom line if you put them into every car. It also will kill the resale price of cars without it, which in turn hurts the companies image and stock price.

If you are first to market with a level 4 autonomous taxi, unit economics will likely be great regardless of whether you put LIDAR or cameras in.

Yes, but the current reality is they need to pay for the hardware, and still make a profit, without any guarantee of that autonomous taxi market.

It all depends what you see are the chances of the autonomous taxi market developing within the lifetime of these cars.

Musk doesn't like it:

>“Lidar is a fool’s errand,” Elon Musk said. “Anyone relying on lidar is doomed. Doomed! [They are] expensive sensors that are unnecessary. It’s like having a whole bunch of expensive appendices. Like, one appendix is bad, well now you have a whole bunch of them, it’s ridiculous, you’ll see.” https://techcrunch.com/2019/04/22/anyone-relying-on-lidar-is...

I recommend watching George Hotz's take on this: https://www.youtube.com/watch?v=IxuU5L2MEII

You're underestimating the cost issue. Obviously if it was literally 0% extra cost they would have a value benefit. The problem is making a great and cheap and profitable electric vehicle.

lidars are used to generate humongous amounts of labeled training data for depth perception networks so that you don’t have to use them during inference

Kaparthy has a good presentation outlining why they aren’t focused on lidar.. it’s pretty compelling logic.

Do you have a link handy? I couldn't find it with a quick google.

It’s addressed in the autonomy day presentation if I’m not mistaken.

It’s not like they decided not to use it just because. Here is an interesting breakdown:

https://cleantechnica.com/2016/07/29/tesla-google-disagree-l...

Reply on news.ycombinator.com