this post was submitted on 02 Nov 2024
229 points (96.4% liked)
Technology
59133 readers
2259 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Even worse, LIDAR isn't even that expensive. Musky just thought they should be able to do without it because, "humans do it with just eyes."
Just so no one mistakes the above as hyperbolic, musk actually said this during an engineering meeting. His engineers kept telling him why Tesla needed the extra sensors, and he replied "people just have eyes and they can drive."
Anytime someone tries to play him off an engineer or anything but a lucky gambler and flim flam man, just remember the above.
People also have a brain. Most of them even use it when driving.
Ah, an optimist!
Absolutely.
And then the car mistook the side of a white semi for the sky and plowed full speed into the semi, decapitating the driver. These systems see, but don't really understand what they see.
Self driving doesn't need to be perfect it only needs to be better than humans.
Examples like this are kind of pointless because humans are incredibly bad drivers statistically.
It needs to be quite a bit better than humans to actually take off. The difference between a person driving and anything else is who is in control, and therefore to blame. Just being statistically better than the average person isn’t good enough, imho.
An order of magnitude better would give trust. Slightly better doesn´t convince people.
I still think the technology would be getting pushed forward even if it was only slightly better than humans. However it is far safer than humans which is why its growing rapidly in application.
However humans may also be getting better via self driving tools such as radar cruise control. So you’d need to compare to a human with access to these tools.
Thats a good point. I cant wait for that stuff to become more widely available so we can see how that impacts things.
I'm pretty sure we're a human would not have made that mistake though so it's already not better than humans.
Human eyes are far better than cameras at real time adaptation to varied lighting conditions though.
And we can predict what will happen pretty well and adapt to the situation dynamically. Our only weakness is that we do stupid shit like drunk driving, speeding and not paying attention.
Of course humans also have a brain whereas computers don't exactly think about things. Perhaps we should have given them a competitive advantage
Also it's such a shit excuse anyway, I am perfectly capable of driving a car myself, but I would like it to drive itself so I don't have to, so clearly just because humans do it without additional aid does not mean the additional aid is not warranted or desired.
Not a fan of Musk at all, but Lidar is quite expensive. A 64 line lidar with 100m+ range was about 30k+ a few years ago (not sure how prices have changed now). The long range lidar on the top of the Waymo car is probably even higher resolution than this. It's likely that the sensor suite + compute platform on the waymo car costs way more than the actual Jaguar base vehicle itself, though waymo manufactures it's own lidars. I think it would have been impossible to keep the costs of Teslas within the general public's reach if they had done that. Of course, deploying a self driving/L2+ solution without this sensor fidelity is also questionable.
I agree that perception models will not be able deal with this well for a while. They are just not good enough at estimating depth information. That being said, a few other companies also attempted "vision-only" solutions. TuSimple (the autonomous trucking company) argued at some point that lidar didn't offer enough range for their solution since semi trucks need a lot more time to slow down/react to events ahead because of their massive inertia.
Yeah we used to joke that if you wanted to sell a car with high-resolution LiDAR, the LiDAR sensor would cost as much as the car. I think others in this thread are conflating the price of other forms of LiDAR (usually sparse and low resolution, like that on 3D printers) with that of dense, high resolution LiDAR. However, the cost has definitely still come down.
I agree that perception models aren't great at this task yet. IMO monodepth never produces reliable 3D point clouds, even though the depth maps and metrics look reasonable. MVS does better but is still prone to errors. I do wonder if any companies are considering depth completion with sparse LiDAR instead. The papers I've seen on this topic usually produce much more convincing pointclouds.
Even my cheap chinese vacuum cleaner has it.
I bet it's got 'vacuum-grade' granularity, and not '2 tons at 50mph approaching some trick-or-treaters' kind of granularity required.
More money tho.