In the piece — titled “Can You Fool a Self Driving Car?” — Rober found that a Tesla car on Autopilot was fooled by a Wile E. Coyote-style wall painted to look like the road ahead of it, with the electric vehicle plowing right through it instead of stopping.
The footage was damning enough, with slow-motion clips showing the car not only crashing through the styrofoam wall but also a mannequin of a child. The Tesla was also fooled by simulated rain and fog.
But they do, there are literally cars out there with lidar sensors.
The question was why can’t I have a lidar sensor on my car if my $150 vacuum has one. The lidar sensor for a car is more than $150.
You don’t have one because there are expensive at that size and update frequency. Sensors that are capable of outdoor mapping at high speed cost the price of a small car.
The manufacturers suspect and probably rightfully so that people don’t want to pay an extra 10 - 30 grand for an array of sensors.
The technology readily exists rober had one in his video that he used to scan a roller coaster. It’s not some conspiracy that you don’t have it on cars and it’s not like it’s not capable of being done because waymo does it all the time.
There’s a reason why waymo doesn’t use smaller sensors they use the minimum of what works well. Which is expensive, which people looking at a mid-range car don’t want to take on the extra cost, hence it’s not available
https://techcrunch.com/2019/03/06/waymo-to-start-selling-standalone-lidar-sensors/
This article is six years old, so I wouldn’t be surprised if they’re even cheaper now.
Good God it’s like you’re going out of the way to intentionally misunderstand the point.
Nobody is saying that the lidar on a car should cost the same as a lidar on a vacuum cleaner. What everyone is saying is that if the company that makes vacuum cleaners thinks it’s important enough to put lidar on, surely you’re not the company that makes cars should think that it’s important enough to put lidar on.
Stop being deliberately dense.
It’s a cost-benefit calculation.
So the question is whether they can achieve self-driving without it: humans rely on vision alone so maybe an ai can. I’m just happy someone is taking a different approach rather than the follow the pack mentality: we’re more likely to get something that works
Edit: everyone talks about the cost-benefit, but I imagine it makes things simpler for the ai when all sensors can be treated and weighted identically. Whether this is a benefit or disadvantage will eventually become clear
You’re either taking to a fanboy or Elon on ket. You ain’t gettin’ through.
Whether lidars are reliable enough to run on autonomous cars has nothing to do with whether they are cost efficient enough to run on vacuum cleaners though. The comparison is therefore completely irrelevant. Might as well complain that jet fighters don’t allow sharing on Instagram your location, because your much cheaper phone does.
Decent LIDAR sensors have gotten a lot cheaper in the last 5 years or so, here’s one that is used in commercial self-driving taxis: https://www.alibaba.com/product-detail/X01-36020021-Nev-Auto-Parts-for_1601252480285.html
Shit that’s pretty decent. That looks like a ready fit car part, I wonder what vehicle it’s for. Kind of sucks that it only faces One direction but at that price four them would not be a big deal
So that one sensor is $700. Waymo has 4 LIDAR sensors (all of which are physically larger and I would imagine fancier than the Alibaba ones, but that’s speculation), so just in the scanner hardware itself you’re looking at $2,800. Plus the computer to run it, plus the 6 radar receivers, and 13 cameras, I could absolutely see the price for the end user to be around $10k worth of sensors.
But to be clear, I don’t think camera only systems are viable or safe. They should at minimum be forced to use radar in combination with their cameras. In fact I actually trust radar more than lidar because it’s much less susceptible to heavy snow or rain.
Only Tesla does not use radar with their control systems. Every single other manufacturer uses radar control mixed with the camera system. The Tesla system is garbage.
The self driving system uber was working on also went downhill after they went full visual only.
yeah, you’d think they’d at least use radar. That’s cheap AF. It’s like someone there said I have this hill to die on, I bet we can do it all with cameras.
Yeahhh pretty sure I know who
Not sure it’s a him thing, though it definitely could be. An inexpensive Chinese radar element could have eliminated all these problems and they could still use cameras as the main system. It would have cost them dollars to add it to the parts list and it’s just a minor input to the collision avoidance stuff.
I would expect him to do a cost-savings thing and pull parts, but they’re not really all that cost adverse. ( until you get to QC )
Maybe it was a DOGE kid he hired to come up with ideas or something. Doing with cameras only is more like a technical challenge, nobody looks at that and goes, WOW they can just do that with cameras, they go wow, that’s a horrible idea full of dust, dirt and mud issues.
That said, he has made worse plans :)
How are people still giving this man a fucking pass on everything?
August 2019:
Elon Musk: “Anyone relying on lidar is doomed.” Experts: Maybe not
Jan 2025:
Tesla CEO Elon Musk Dismisses LiDAR Again: ‘Humans Drive Without Shooting Lasers Out Of Their Eyes’
It was Elon, he was very vocal about how Lidar was an expensive crutch and how machine learning would get so much better than human vision back around 2016ish.
And I can see the expense on lidar being a problem in 2016 but what about radar? You can get a 30 m radar/sonar element for dollars. Then they wouldn’t be crashing into walls and children and what have you.
Your perspective is very generous to Elon. “It’s a cheap part, why would they omit it? Probably it was some dumb kid working there”.
Usually cost-cutting measures that make significant compromises are top-down pushes, profit is their concern. Might not have been the CEO himself but, in my perspective, it would have been from the top levels.
No I’m not trying to be generous, If it were just a dumb decision it would totally have been his. This is like a recent graduate engineer vendetta kind of decision. I don’t think he’s actually smart enough to try to make this bad decision.
What’s the opposite of occam’s razor? The most convoluted, unbelievable answer full of assumptions is the correct one? Because it seems like rumba is operating from there.