←back to thread

65 points doener | 1 comments | | HN request time: 0.217s | source
Show context
rmu09 ◴[] No.45345721[source]
US made cars had the reputation of being low quality, too big, too heavy and too inefficient for european cities.

Tesla was somewhat different. People bought Teslas not for their promised "self driving" capabilities (I know no Tesla driver that took those promises at face value or got the FSD option FWIW), but one motivation was to "stick it" to snobbish arrogant european manufacturers wanting to develop "clean" ICEs with "green fuels" or other non-sensical crimes against thermodynamics like H2-cars.

Now, Tesla (and the US in general) has a brand toxicity problem, and it is worsening. People I know that would consider a Tesla some years ago now drive electric VWs or BWMs or KIAs, often times much more expensive cars than the comparable Tesla 3 / Y model.

This trend will probably continue the next years, and I don't see a way for Tesla to repair the brand image.

replies(6): >>45345771 #>>45345851 #>>45345901 #>>45345908 #>>45346627 #>>45346875 #
bayindirh ◴[] No.45345851[source]
Tesla killed its brand reputation thrice.

- First they went "camera only", alienating people who knows the tech.

- Then they mocked car industry for so long. It was a necessary poke at first, but they didn't get prepared, and the elephant proved that it can run.

- Then Elon's Trump affair and all the shebang happened.

The broken FSD promises, using non-auto rated parts (and related failures), being negligent of their own errors and acting like they are deaf to the criticism is the cement between the layers.

replies(2): >>45345963 #>>45346605 #
storus ◴[] No.45345963[source]
They had camera-only tech employing multiple 4k cameras running at over 2000fps. Not your grandma's 480p/25fps webcam many car manufacturers use as parking cameras. 2000fps gives you enormous safety margin even in case of individual frame misdetection. The long-tail issues they hit are present on LiDAR vehicles as well but LiDAR is much slower, more difficult to process and sensor fusion adds its own errors.
replies(8): >>45346032 #>>45346086 #>>45346115 #>>45346268 #>>45346460 #>>45349033 #>>45350326 #>>45353213 #
rich_sasha ◴[] No.45346115[source]
Why 2k FPS? I'm not being facetious; human eye sees, apparently, at around 25fps, which is why this is what TVs and cinemas used to use. At that rate, and 144kph, say, the car moves 1.4m between frames.

Fine, so maybe you think this is too much. But 10x this still gives you 14cm between frames, at what is already speeding in most jurisdictions I know of.

2000 FPS seems to my untrained eye like a problem, not a feature.

replies(3): >>45346446 #>>45346615 #>>45354933 #
1. storus ◴[] No.45346446[source]
Because you are processing a sequence of a fixed length in deep learning models and the more frames you have, the more accurate your FSD output is. Driving 1.4m between the frames with single-frame accuracy of 80% is quite risky and input correction quite discrete; 14cm is still risky for a proper trajectory planning. Now make it in millimeters and suddenly your trajectory is nearly perfect with only little noise.