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.
I saw the video and I have two points:
- Yes it plays like an infomercial for lidar. So take that portion with some skepticism. I can think of some issues exclusive to lidar like 2+ lidar cars blinding each other which needs to be solved, e.g. some kind of light pattern encoding to mask out unwanted signals.
- It absolutely 100% demonstrates the issue with camera-only technology in Tesla vehicles.
Teslas used to have cameras + radar but they cheaped out and removed the radar. I think it would have passed all the tests if they still had the front facing radar but they don’t. The problem with cameras alone is obvious - they can’t see what they can’t see and probably don’t have an innate sense to slow down if there is rain, fog, ice or whatever else that might cause a human to.
I can’t wait for all this brand loyalty and fan people culture to end. Why is this even a thing? Like talking about box office results, companies financials and stocks…. If you’re not an investor of theirs, just stop. It sounds like you’re working for free for them.
Of course it disengages self driving modes before an impact. Why would they want to be liable for absolutely anything?
How are there still tesla fans?
Does anyone else get the heebies with Mark Rober? There’s something a little off about his smile and overall presence.
Man these cars don`t have a Radar ? Only eyes like most of the animals? Not even as a backup ? Not talking about Lasers, but Radar? Truck drivers, better not paint a scenery on the back of your truck.
Mark Rober did a follow up interview here: https://youtu.be/W1htfqXyX6M
I hope some of you actually skimmed the article and got to the “disengaging” part.
As Electrek points out, Autopilot has a well-documented tendency to disengage right before a crash. Regulators have previously found that the advanced driver assistance software shuts off a fraction of a second before making impact.
It’s a highly questionable approach that has raised concerns over Tesla trying to evade guilt by automatically turning off any possibly incriminating driver assistance features before a crash.
It’s a highly questionable approach that has raised concerns over Tesla trying to evade guilt by automatically turning off any possibly incriminating driver assistance features before a crash.
That is like writing musk made an awkward, confused gesture during a time a few people might call questionable timing and place.
Yeah but that’s milliseconds. Ergo, the crash was already going to happen.
In any case, the problem with Tesla autopilot is that it doesn’t have radar. It can’t see objects and there have been many instances where a Tesla crashed into a large visible object.
That’s what’s confusing me. Rober’s hypothesis is without lidar the Tesla couldn’t detect the wall. But to claim that autopilot shut itself off before impact means that the Tesla detected the wall and decided impact was imminent, which disproves his point.
If you watch the in car footage, autopilot is on for all of three seconds and by the time its on impact was already going to happen. That said, teslas should have lidar and probably do something other than disengage before hitting the wall but I suspect their cameras were good enough to detect the wall through lack of parallax or something like that.
Or it still may have short distance sensors for parking and that if it sees something solid on those it disables autopilot?
That’s so wrong holy shit
Don’t get me wrong, autopilot turning itself off right before a crash is sus and I wouldn’t put it past Tesla to do something like that (I mean come on, why don’t they use lidar) but maybe it’s so the car doesn’t try to power the wheels or something after impact which could potentially worsen the event.
On the other hand, they’re POS cars and the autopilot probably just shuts off cause of poor assembly, standards, and design resulting from cutting corners.
if it can actually sense a crash is imminent, why wouldn’t it be programmed to slam the brakes instead of just turning off?
Do they have a problem with false positives?
if it was european made, it would slam the brakes or swerve in order to at least try and save lives since governments attempt to regulate companies to not do evil shit. Since it american made it is designed to maximise profit for shareholders.
I don’t believe automatic swerving is a good idea, depending on what’s off to the side it has the potential to make a bad situation much worse.
I’m thinking like, kid runs into the street, car swerves and mows down a crowd on the sidewalk
Its the cars job to swerve into a less dangerous place.
Can’t do that? Oops, no self-driving for you.
I’ve been wondering this for years now. Do we need intelligence in crashes, or do we just need vehicles to stop? I think you’re right, it must have been slamming the brakes on at unexpected times, which is unnerving when driving I’m sure.
So they had an issue with the car slamming on the brakes at unexpected times, caused by misidentifying cracks in the road or glare or weird lighting or w/e. The solution was to make the cameras ignore anything they can’t recognize at high speeds. This resulted in Teslas plowing into the back of firetrucks.
As the article mentioned, other self-driving cars solved that with lidar, which elon himself is against because he says AI will just get so good and 2d cameras are cheaper.
This is from 6 years ago. I haven’t heard of the issue more recently
https://www.washingtonpost.com/technology/interactive/2023/tesla-autopilot-crash-analysis/
The tesla did not consistently detect that the thing infront of it was a truck, so it didn’t brake. Also, this describes a lot of similar cases.
I remember a youtuber doing similar tests, where they’d try to run over a fake pedestrian crossing or standing in the road at low speed, and then high speed. It would often stop at low speed, but very rarely stopped or swerved at high speed.
Wouldn’t it make more sense for autopilot to brake and try to stop the car instead of just turning off and letting the car roll? If it’s certain enough that there will be an accident, just applying the brakes until there’s user override would make much more sense…
False positives. Most like it detected something was off (parking sensor detected something for example) but doesn’t have high confidence it isn’t an erroneous sensor reading. You don’t want the car slamming on brakes at highway speed for no reason and causing a multi car pileup.
Normal cars do whatever is in their power to cease movement while facing upright. In a wreck, the safest state for a car is to cease moving.
I see your point, and it makes sense, but I would be very surprised if Tesla did this. I think the best option would be to turn off the features once an impact is detected. It shutting off before hand feels like a cheap ploy to avoid guilt
… It shutting off before hand feels like a cheap ploy to avoid guilt
that’s exactly what it is.
Rober seems to think so, since he says in the video that it’s likely disengaging because the parking sensors detect that it’s parked because of the object in front, and it shuts off the cruise control.
It always is that way; fuck the consumer, its all about making a buck
I’ve heard that too, and I don’t doubt it, but watching Mark Rober’s video, it seems like he’s deathgripping the wheel pretty hard before the impact which seems more likely to be disengaging. Each time, you can see the wheel tug slightly to the left, but his deathgrip pulls it back to the right.
Beep beep
E. Lon Musk. Supah. Geenius.
My 500$ robot vacuum has LiDAR, meanwhile these 50k pieces of shit don’t 😂
I think it was a guess 🤷♂️ or maybe it’s a different currency?
Holy shit, I knew I’d heard this word before. My Chinese robot vacuum cleaner has more technology than a tesla hahahahaha
Vacuum doesn’t run outdoors and accidentally running into a wall doesn’t generate lawsuits.
But, yes, any self-driving cars should absolutely be required to have lidar. I don’t think you could find any professional in the field that would argue that lidar is the proper tool for this.
…what is your point here, exactly? The stakes might be lower for a vacuum cleaner, sure, but lidar - or a similar time-of-flight system - is the only consistent way of mapping environmental geometry. It doesn’t matter if that’s a dining room full of tables and chairs, or a pedestrian crossing full of children.
I think you’re suffering from not knowing what you don’t know.
Let me make it a but clearer for you to make a fair answer.
Take a .25mw lidar sensor off a vacuum, take it outdoors and scan an intersection.
Will that laser be visible to the sensor?
is it spinning fast enough to track a kid moving in to an intersection when you’re traveling at 73 feet per second?
The price of lidar sensors has dropped by like 50 times since musk decided to cut costs by eliminating theny from their cars.
Yeah looks like it, chinese sensors are down to 700 a pop. Even if it’s a few grand, it’s decent, looks like chevy offers it on 7 models.
You’re mischaracterizing their point. Nobody is saying take the exact piece of equipment, put it in the vehicle and PRESTO. That’d be like asking why the vacuum battery can’t power the car. Because duh.
The point is if such a novelty, inconsequential item that doesn’t have any kind of life safety requirements can employ a class of technology that would prevent adverse effects, why the fuck doesn’t the vehicle? This is a design flaw of Teslas, pure and simple.
Older teslas HAD lidar. They were removed on newer models to cut costs.
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
Prices tend to come down on these things simply because the car industry widely adopts them. For example, accelerometers became cheap because they were needed for air bags. LIDAR might not come down as much as those have, but it won’t be tens of thousands of dollars.
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.
Stop being deliberately dense.
Its weaponized incompetence.
I bet they do the same shit with their partner when it comes to dishes, laundry, and the garbage.
You’re either taking to a fanboy or Elon on ket. You ain’t gettin’ through.
I’m not being deliberately dense it just a seriously incomplete analogy. At worst I’m being pedantic. And if that’s the case I apologize.
I agree with the premise that the cars need lidar radar whatever the f*** they can get.
Saying if a vacuum company can see that a vacuum needs lidar (which is a flawed premise because half the f****** vacuums use vslam/cameras) then why doesn’t my car have lidar, none of the consumer car companies are using it (yet anyway). It’s great to get the rabble up and say why are vacuum companies doing it when car companies can’t but when nobody’s doing it there are reasons. Ford Chevy BMW f***, what about Audi what about Porsche? What about these luxury brands that cost an arm and three fucking legs.
Let’s turn this on its head, why do people think they’re not including it in cars. And let’s discount musk for the moment because we already know he’s a fucking idiot that never had an original idea in his life and answer why it isn’t in any other brand.
Is it just that none of these companies thought about it? Is it a conspiracy? What do people think here. If I’m being so dense tell me why the companies aren’t using it.
It’s a cost-benefit calculation.
- For a vacuum at the speeds they travel and the range it needs to go, LiDAR is cheap, worth doing. Meanwhile computing power is limited.
- my phone is much more expensive than the robot vacuum, and its LiDAR can range to about a room, at speeds humans normally travel. It works great for almost instant autofocus and a passable measurement tool.
- For a car, at the speeds they travel and range it needs to go, LiDAR is expensive, large and ugly. Meanwhile the car already needs substantial computing power
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
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.
You’re bending over backwards to miss the point huh
So be clear about the point.
https://techcrunch.com/2019/03/06/waymo-to-start-selling-standalone-lidar-sensors/
Waymo’s top-of-range LiDAR cost about $7,500… Insiders say those costs have fallen further thanks to continuous advances by the team. And considering that this short-range LiDAR is cheaper than the top-of-range product, the price is likely under $5,000 a unit.
This article is six years old, so I wouldn’t be surprised if they’re even cheaper now.
10 - 30 grand
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
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 $10k worth of sensors.
But to be clear, I don’t think camera only systems are viable or safe. They should at minimum be forced to use radar in combination with their cameras. In fact I actually trust radar more than lidar because it’s much less susceptible to heavy snow or rain.
Shit that’s pretty decent. That looks like a ready fit car part, I wonder what vehicle it’s for. Kind of sucks that it only faces One direction but at that price four them would not be a big deal
Only Tesla does not use radar with their control systems. Every single other manufacturer uses radar control mixed with the camera system. The Tesla system is garbage.
The self driving system uber was working on also went downhill after they went full visual only.
yeah, you’d think they’d at least use radar. That’s cheap AF. It’s like someone there said I have this hill to die on, I bet we can do it all with cameras.
I think you’re suffering from not knowing what you don’t know.
and I think you’re suffering from being an arrogant sack of dicks who doesn’t like being called out on their poor communication skills and, through either a lack of self-awareness or an unwarranted overabundance of self-confidence, projects their own flaws on others. But for the more receptive types who want to learn more, here’s Syed Saad ul Hassan’s very well-written 2022 paper on practical applications, titled Lidar Sensor in Autonomous Vehicles which I found also serves as neat primer of lidar in general..
Wow, what’s with all the hostility against him.
It’s maybe because i also know a bit about lidars that his comment was clear to me (“ha, try putting a vacuum lidar in a car and see if it can do anything useful outside at the speeds & range a car needs”).
Is it that much of an issue if someone is a bit snarky when pointing out the false equivalence of “my 500$ vacuum has a lidar, but a tesla doesn’t? harharhar”.
(“ha, try putting a vacuum lidar in a car and see if it can do anything useful outside at the speeds & range a car needs”).
Because no one suggested that.
So someone saying “why does my 500$ vacuum have a lidar but not the car” isn’t suggesting that?
I guess in some technical way you’re right, but it for sure is the implication…
But, yes, any self-driving cars should absolutely be required to have lidar.
So they think self-driving cars should have lidar, like a vacuum cleaner. They agree, and think it’s a good idea, right?
I don’t think you could find any professional in the field that would argue that lidar is the proper tool for this.
…then in the next sentence goes on to say that lidar is not the correct tool. In the space of a paragraph they make two points which directly contradict one-another. Hence my response:
What is your point here, exactly?
They could have said “oops, typo!” or something but, no, instead they went full on-condescending:
I think you’re suffering from not knowing what you don’t know.
I stand by my response:
arrogant sack of dicks
And while I’m not naive enough to believe that upvotes and downvotes are any kind of arbiter of objective truth, they at least seem to suggest, in this case, that my interpretation is broadly in line with the majority.
Well look at you being adult and using big words instead of just insulting people. Not even going to wastime on people like you, I’m going to block you and move on and hope that everyone else does the same so you can sit in your own quiet little world wondering why no one likes you.
You’re an idiot.
jesus man, how many alts do you have?
It’s a highly questionable approach that has raised concerns over Tesla trying to evade guilt by automatically turning off any possibly incriminating driver assistance features before a crash.
So, who’s the YouTuber that’s gonna test this out? Since Elmo has pushed his way into the government in order to quash any investigation into it.
It basically already happened in the Mark Rober video, it turns off by itself less than a second before hitting
He needs to post footage of it turning off as he drives. An uninterrupted one-camera take from start to crash to finish.
He did, I don’t have the link unfortunately but he did post the unedited take from inside the car where you can see it turn off
It’s from the Philip DeFranco interview he did after the weekend it was released.
Right yeah that’s the one I was referring to
To be fair, if you were to construct a wall and paint it exactly like the road, people will run into it as well. That being said, tesla shouldn’t rely on cameras
Edit: having just watched the video, that was a very obvious fake wall. You can see the outlines of it pretty well. I’m also surprised it failed other tests when not on autopilot, seems pretty fucking dangerous.
Watch the video it’s extremely obvious to a human driver that there is something wrong with that view ahead. It’s even pointed out in the video that humans use additional visual clues when a situation is ambiguous.
The cars don’t have deduction and reasoning capabilities so they need additional sensors to give them more information to compensate due to their lack of brains. So it’s not really sensible to compare self-driving systems to humans. Humans have limited sensory input but it’s compensated for by reasoning abilities, Self-Driving cars do not have reasoning abilities but it’s compensated for by enhanced sensory input.
Wonder if stereoscopic cameras would figure it out.
Huh, I thought the exact opposite. The clues were small. While they were sufficient for a focussed driver at slow speeds, it also looked like something that would fool a human at typical speeds and attention span.
Painting exactly like the road is a gimmick that really doesn’t demonstrate anything.
Personally I wished they went full looney tunes to better entertain us and to demonstrate that even significant clues may not be enough
To be fair, if you were to construct a wall and paint it exactly like the road, people will run into it as well.
this isn’t being fair. It’s being compared to the other- better- autopilot systems that use both LIDAR and radar in addition to daylight and infrared optical to sense the world around them.
Teslas only use daylight and infrared. LIDAR and radar systems both would not have been deceived.
So out of interest I looked it up.
The new BYD cars that are coming out also have self-driving probably to directly compete with Tesla.
However they do use lidar, and radar, and cameras, and infrared cameras, and ultrasonic sensors. All have to be working or the car won’t go into self-drive. So other companies consider even one of their sensors failing to be enough to disable self-driving capabilities yet Tesla are claiming that it’s perfectly safe to drive around with those features not even installed let alone functional.
So yeah that’s a real bad look.
I don’t see how this test demonstrates anything is better. It is a gimmick designed for a specific sensor to get an intended result. Show me a realistic test if they want to be useful, or go full looney tunes if they want to be entertaining
The cartoon wall is just an exagerated illustration of why a vision only system sucks compared to other systems.
If you watch the rest of the video, you’d see Tesla’s vision only system is inferior to cars using radar/lidar in other, more realistic situations like heavy rain and fog.
I’d take that bet. I imagine at least some drivers would notice something sus’ (due to depth perception, which should be striking as you get close, or lack of ANY movement or some kind of reflection) and either
- slow down
- use a trick, e.g. flicking lights or driving a bit to the sides and back, to try to see what’s off
or probably both, but anyway as other already said, it’s being compared to other autopilot systems, not human drivers.
The video does bring up human ability too with the fog test (“Optically, with my own eyes, I can no longer see there’s a kid through this fog. The lidar has no issue.”) But, as they show, this wall is extremely obvious to the driver.
The tesla would lose its shit if it sees this
They already have trouble enough with trucks carrying traffic lights, or with speed limit drivers on them.
and fire trucks. and little kids. and, uh, lots of things really.
I have seen trucks with landscape scenes painted on the side and I’ve never crashed into one of those thinking that it was a portal to a random sunlit field.
see, that’s what you’re supposed to think. because you’re not special. but really, it’s a secret portal to a magical world, a world that’s very exciting for a few seconds.
Yeah, the Roadrunner could easily skip by such barriers, frustrating the Coyote to no end. Tesla is not a Roadrunner.
in the world of coyotes, be a roadrunner.
MEEP MEEP.
And the president is driving one of these?
Maybe we should be purchasing lots of paint and cement blockades…
When he was in the Tesla asking if he should go for a ride I was screaming “Yes! Yes Mr. President! Please! Elon, show him full self driving on the interstate! Show him full self driving mode!”
The president can’t drive by law unless on the grounds of the White House and maybe Camp David. At least while in office. They might be allowed to drive after leaving office…
This isn’t true at all. I can’t tell if you’re being serious or incredibly sarcastic, though.
The reason presidents (and generally ex presidents, too) don’t drive themselves is because the kind of driving to escape an assassination attempt is a higher level of driving and training than what the vast majority of people ever have. There’s no law saying presidents are forbidden from driving.
In any case, I would be perfectly happy if they let him drive a CT and it caught fire. I’d do a little jib, and I wouldn’t care who sees that.
deleted by creator
I never that proud of a french president than when I read this comment 😎
Current and past presidents are prohibited from driving.
you’re gonna have to drop a source for that.
because, no, they’re not. the Secret Service provides a driver specially trained for the risks a president might face, and very strongly insists, but they’re not “prohibited” from driving simply because they’re presidents.
to be clear, the secret service cannot prohibit the president from doing anything they really want to do. Even if it’s totally stupid for them to do that. (This includes, for example, Trump’s routine weekend round of golf at Turd-o-Lardo)
You’re technically correct, there is no law prohibiting a current or former president from driving, but there is a policy preventing it and it is enforced by the secret service (who follow them around for the rest of their life). Many former presidents have gone on the record that the lose of their driving privileges really sucks (Bush 43, Clinton, and Obama have all discussed it on camera during various interviews). It’s been a policy since Kennedy was assassinated, lots of other policy changes too, but one was the no driving bit.
Random sources: https://www.smh.com.au/world/us-presidents-can-have-everything--except-the-car-keys-20140506-zr5we.html
https://www.cnbc.com/2017/06/28/presidents-arent-allowed-to-drive.html
And one just about some times they drove anyway:
https://www.motorbiscuit.com/3-u-s-presidents-got-around-no-driving-rule/
Policy can be changed. Quite easily.
Especially by the president, when it’s about the president.
Obama, Clinton, others, they don’t really lose their driving privileges. Effectively, they do, sure. But that’s because they’re not utter morons.
Even trump has yet to prove himself that stupid. He probably is that stupid, but he likes the pomp and circumstance, don’t get me wrong.
Other policies include screening people for firearms at rallies- trump over ruled that one, that day, too.
to be clear, the secret service cannot prohibit the president from doing anything they really want to do
Was Trump lying when he said the SS wouldn’t take him back to the capital on Jan 6?
I could definitely see him lying about that so he doesn’t look like he abandoned his supporters during the coup, but I could also see the driver being like “I can’t endanger you, mr president” and ignoring his requests.
Was Trump lying when he said the SS wouldn’t take him back to the capital on Jan 6?
Definitely not. There is no way in hell the secret service would have taken the president to that shit show. Doesn’t mean that they would have physically arrested him if he insisted going on his own, however.
I don’t think Trump can drive. As in, he doesn’t even know what the pedals do.
clearly knows what he is doing
He looks like he’s making the siren sounds and having a great time
He would be a much funnier person if he weren’t in a position of power (and thus didn’t have the ability to affect people), especially one as terrifying as being the leader of one of the most powerful nations in the world.
deleted by creator
I imagine when he’s driving around his golf course he makes voom voom noises
He’s going to fall out of the cab on the next right turn.
Are his hands even big enough to hold the wheel?
The real question is, in a truly self-driving car, (not a tesla) are you actually driving?
deleted by creator
