I don’t think they can, because they’re suffering so much from the rectal-cranial inversion that Musk started with his FSD.

Muskrat insists on using computer vision entirely, and building it in-house. Tesla (probably EM) as I recall also insulted MobilEye so they refuse to do business with them. Mind you, I think lane keeping is generally a computer vision problem.

I rode in a 2019 Subaru Ascent (like a big Outback) a few years ago, the lane keep assist was great even back then, not to mention the blind spot monitoring and all that. and it was all included. wtf is Tesla even doing with all that time and money??

I love mine. Combined with adaptive cruise, it’s amazing for slowly rolling traffic, longer journeys, and stop-and-go traffic. I’m under no impression the car is ‘driving’ but having a machine take over the mental load is great and frees up that capacity for other driving tasks and/or awareness of the road.

Tesla calling that technology “Auto” anything without it being genuinely 100% autonomous should have landed someone a fat fine or jail time

The actual answer: It should be Level 4 autonomy. It is capable of full self driving, but only in certain conditions.

Do note that Tesla autopilot is actually only SAE level 2, so it's just a straight up lie

FSD has lane-keeping in it. It’s not up for debate if they can do it or not, because they’ve been doing it for years.

Also I’m not sure what other technology you think they would use for lane-keeping other than cameras and “computer vision”? Things like Lidar don’t work for this because lidar can’t see lane markers. The only way to do it is with cameras.

Come on now, why the stupid hot takes like this?

Without Tesla electric vehicles would still be in the dark ages. Think whatever you want about Musk, but what he did for electric vehicles with Tesla cannot be understated or taken away. He revolutionised the entire industry and kickstarted the EV path we’re on.

No it’s not.

It fully drives itself, but legally you need to “supervise” it. It’s called that because of the laws around driving a car.

Both. You can use both LiDAR and optical teaming, the technologies complement each other so you don’t fall for a Looney-Tunes ass painted wall, while the camera covers the one-dimensional recognition that LiDAR can’t.

[Tesla] removed radars from its vehicle lineup and even deactivated already installed radars in existing vehicles. This strategy has not yet been worth it since Tesla’s systems are still stuck at level 2 driver assist systems.

Lidar does not help with seeing lane markers. At all. Radar can’t see painted lines on a road.

That looney tunes wall “test” was ridiculous and Rober was rightly raked over the coals and lost a lot of respect over it. It was basically a marketing stunt by his friends LiDAR company, and was full of dishonesty such as poorly photoshopped phones and lies such as not even using the self driving while smashing into the wall. These glaring flaws have been covered extensively.

what he did for electric vehicles with Tesla cannot be understated

I think you meant to say “cannot be overstated.” “Cannot be understated” means the opposite of the point you’re trying to make.

He definitely lit a fire under the asses of the traditional automakers, no doubt. But then he consistently threw away every advantage his company had, one after another.

Had they developed a normal-ass pickup truck they could’ve beaten the Lightning F-150 to market. But no, because Musk wanted to make a car as stupid and ill-advised as the DeLorean DMC-12 it resembles, design time took so long that by the time the thing hit the streets it wasn’t what truck owners wanted or what Tesla owners wanted. There was already an EV version of the best-selling pickup truck in the world. And he had, by that point, thoroughly torched his image among the people most likely to buy his cars.

Tesla definitely accelerated the development of EV models and infrastructure, but I personally think it’s easy to overstate Elon’s impact.

Honestly, while not a scientifically rigerous test, it does demonstrate through absurdity the real risks of computer vision only for driver assist features.

Real world examples including of course the Tesla that plowed into a white truck on a foggy day because it mistook the truck for absolutely nothing among too many others

Elon Musk clearly has enourmous skillset at managing startups from their early stages though their explosive growth stages. He's successfully done so both with Tesla and SpaceX. Unfortunately his management skills are clearly incompatible with running a large company that makes up a notable portion of a market. He should have stepped away from Tesla about a decade ago (possibly as much as 15 years ago). He should have stepped away from SpaceX about 5 years ago. He should be known for growing a promising disruptive startup into a true market player then immediately handing the reigns away and moving onto the next startup, but his ego is simply too big for that, and he doesn't seem to have the introspection to see the damage he's doing to the companies he built up

If only they didn’t fake it to get their desired result, then maybe it could have been useful.

I agree that LiDAR and other technologies should be used in conjunction with regular cameras. I don’t know why anyone would be against that unless they have vested interests. For various reasons though I understand that it isn’t always possible - price being a big one.