Mark Rober just set up one of the most interesting self-driving tests of 2025, and he did it by imitating Looney Tunes. The former NASA engineer and current YouTube mad scientist recreated the classic gag where Wile E. Coyote paints a tunnel onto a wall to fool the Road Runner.
Only this time, the test subject wasn’t a cartoon bird… it was a self-driving Tesla Model Y.
The result? A full-speed, 40 MPH impact straight into the wall. Watch the video and tell us what you think!
So to stop robotaxis, all we have to do is paint a fake road directly into a rock wall with a painted on tunnel.
Even a few non-robotaxi people.
If the roadrunner cartoons taught me anything, it’s that no matter what happens, whether you’ve been blown to smithereens or fell off a cliff and subsequently flattened by a boulder, you’ll be good as now in the next scene.
To be fair, I’d be surprised if half the humans driving didn’t do the same.
this. watching the video, I had some trouble telling the difference. sure, from some angles it is obvious, but from others it is not.
That said, other cars, with more types of sensors, would probably have “seen” the obstruction on the road.
I think the human brain hasthe edge in processing visuals since out brains are so much better at adapting than any computer system. We can improvise much better since we have our whole life experience to draw on.
That said, other cars, with more types of sensors, would probably have “seen” the obstruction on the road.
Well yeah, that’s sort of the entire point of the video. He ran the test with a lidar-equipped vehicle, and it saw the wall right away. Hell, a radar-equipped car (like early teslas) probably would have seen the “kid” behind the wall as well. But since Musk has decided that cars should be able to self-drive with only cameras, the newer teslas will just plow straight into the wall without braking.
I would have liked to see how a more typical car with automatic cruise control /braking functioned. I think they use ultra sonic sensors and would have done better than the Tesla.
I mean you’re watching from a recorded video. I really doubt that it wouldn’t be anything but obvious to actual humans eyes. i mean our depth perception alone would tell us something is wrong. You’re just not watching this in 3D.
Maybe at 55 or 65 mph on a foggy day. But I doubt any person paying attention isn’t seeing the obvious anchors holding the wall up and the incorrect perspective at 40 mph.
paying attention
That’s doing a lot of heavy lifting
You’re right. I miss the days when it was just “these damn kids” on their cellphones. Now, more often than not, its a boomer on their cellphone. At the end of the day fuckcars.
Soccer mom yelling at the kids and trying to text at the same time.
This is like the crash on a San Francisco bridge that happened because of a Tesla that went into a tunnel and it wasn’t sure what to do since it went from bright daylight to darkness. In this case the Tesla just suddenly merged lanes and then immediately stopped and caused a multi car pile up.
You’d think they have cameras with higher dynamic range and faster auto exposure in their cars by now. Nope, still penny pinching.
The cameras that do what is needed are 10’s of thousands of dollars.
If only elon hadn’t insisted on not using lidar or anything other than just visible light cameras
Yeah, pulling radar from the cars was the beginning of the end. Early teslas had radar, and that was what led to all of the “car sees something three vehicles ahead and brakes to avoid a pileup that hasn’t even started yet” type of collision avoidance videos. First, pulling radar was a cost cutting thing. Then Elon demanded that they pull out the lidar too, and that’s when their crash numbers skyrocketed.
They never had lidar, in addition to radar they removed the ultrasound sensors for parking, which is stupid because they cost like $2 and for parking they’re much better than cameras. Same for the rain sensor. Why use a $1 rain sensor that always works reliably all the time in any visibility when you can do that with cameras and complex algorithms?..
It’s been about 7 years of model 3 on the market, maybe 8, and the rain detection still doesn’t work reliably. Or the traffic sign recognition (in Europe). My car fortunately still has the ultrasound sensors. Phantom braking is still an issue, too. Thank God for stocks for blinkers and drive/reverse.
I like the car in general, but it has the dumbest fails, things everyone else seems to have figured out.
Other cars also have dumb mistakes, like electric cars with no frunk. Literally bolted down hoods. Looking at you, German auto industry…
They never had lidar, as far as I know.
The video literally shows it having lidar tho.
The lidar car in the video is a modified Lexus prototype (came with radar from factory, modified by a third party, with Lexus branding blacked out and replaced with the third party name)
Afaik at the moment there are no cars in the market that have lidar (waymo is adding lidar to cars that have only radar as stock)
I think some Chinese ones do (nio?), but definitely not tesla
Ah, gotcha, I was only half watching so I misunderstood. Thanks for the clarification.
Im glad Luigi & Wile are on the same side.
I saw the video pop up in my Youtube recommended, but didn’t bother watching because I just assumed that any cars tested would be using LIDAR and thus would ignore the fake road just fine. I had no idea Tesla a) was still using basic cameras for this and b) actually had sophisticated enough “self driving” capabilities that this could be tested on them safely.
They are not still using cameras but removed LIDAR and radar from their cars during the chip shortage 2020/21. The story they were telling was “humans don’t have LIDAR but can drive cars as well, so the cars also only need ‘eyes’ like humans”.
Humans cannot, in fact, drive cars well. Humans kill tens of thousands of other humans with cars every year in the US alone.
Yup, cameras and humans share various exploits. Self-driving is going to work better than humans once every car has it and communicates with each other, allowing for minimal gaps even at high speeds, once roads are all very standardized and in a database, and-
Wait, that’s trains
Fucking build more electrified high-speed rail and forget tech bros’ shitty promises
I was getting mildly outraged and ready to comment how you were re-deriving the train at first. Well played.
They really had me in the first half, not gonna lie
Trains don’t go from my driveway to my destination exactly when I feel like going there, while carrying all my luggage.
I get that it’s fun to be smug on the Internet, but private vehicles aren’t going away any time soon.
It’s not a binary decision between all cars and no cars. If trains and public transit have enough capacity and convenience to make most trips feasible by them, car infrastructure will no longer have to be added (in fact can be converted into bus and bike lanes) while shortening trip duration (less cars = less jams) and improving safety.
Also, you barely have luggage for most trips. 99% of my trips are made with luggage I can carry to the nearest stop and board the bus with.
Yeah it’s not a binary decision, but trains are almost never the answer for a lot of people. If I’m going less than a couple hours, then I’m driving that distance. If I’m going much further than that, I’m flying. If I need to move a ton of stuff, I’m either taking my car or renting a uhaul. If I’m taking a lot of people, I’m taking my car. Trains never enter the picture unless I’m looking for variety in my mode of transport.
And trains do not shorten the trip duratiion, not without absolutely kneecapping the roads. And over long distances, they’re absolutely slow compared to planes. In the short distance, they’re slow compared to cars.
Depends on where you live. In most of Europe, trains are frequent and direct between city centers.
My parents tend to prefer the car for the 3-hour trip (also 3 hours by train and bus) to Grandma’s when at least 3 people go because it’s cheaper. A higher toll on the highway could change the threshold, and we’d go more comfortably. Politicians can smoothly adjust the number of people for which public transport wins out with taxes and investments. You’re more likely to cling to the car and they’ve accounted for that in their models, maybe making you switch for a specific kind of trip is not worth the investment. There are lots of factors, such as political alignment, culture, wealth distribution, existing infrastructure etc. that make some jurisdictions able to move the threshold faster than others. Still, the majority of people using cars is unsustainable for lots of reasons:
- noise, smoke, particulate matter pollution
- high energy use per unit of distance per person regardless of drivetrain and resulting climate change
- cost of road maintenance
- waste of space for parking, resulting in poor land use and sprawl
- accident fatalities
- unwalkable areas ruin business opportunities, resulting in towns that simply go broke
so there is an obligation to eventually push the threshold in favor of public transit for most trips.
I have a van load of tools to transport most of the trips I make.
So you’ll keep using it. And enjoy narrow but way less jammed streets. Maybe you’ll be incentivized/required to join the self-driving network, but in decades, not years, after positioning markers have been added to every road in the last repaving, while infrastructure funds have been directed towards making the city traversible for non-drivers.
That should tell you just how vastly complicated driving is.
There are plenty of uncomplicated things that humans do poorly, too.
Walking up and down stairs, not that I’d know.
And the really dumb thing is that lots of modern non-selfdriving cars now have lidar sensors to help the humans not crash into things. Musk apparently wants the AI to be working at a disadvantage.
He just wants people to buy his junk, and doesn’t care how many people would have to die as collateral damage.
That statement of him is not entirely wrong. But we humans have a very powerful bio computer that is perfectly tuned to process those visual inputs in realtime. Until a comparable performance is possible, removing LIDAR is very stupid.
Besides that, in the fog and rain tests a human likely would have killed a kid anyway, and why settle for human limitations when you could be safer?
We absolutely should also have lidar or analogous tech as part of a solution here, even if cameras did manage to get to human level safety.
The child dummy was clearly visible through the water in the rain test. Tesla’s systems just suck.
Also competent drivers generally know to slow down during rain. Hell I was literally taught to drive some roads like its a speedway and even I drop below the speed limit during the rain if visuals are bad enough, especially first rain pulls oils out of the road makes it slippery and may cause hydroplaning.
I’ll add that every other self driving car company has a pretty good safety record, specifically because they do use LIDAR and RADAR so they can see better than humans.
IIRC Musk said it would rely on AI using the footage from all the Teslas and it’s better than LiDAR. That idiot was proven wrong once again.
Small correction here: they never had LIDAR. Cars with LIDAR have big racks on top with a spinny thing measuring the surroundings. Teslas had radar but removed during the chip shortage (and disabled it on existing cars) and acted like it was an improvement. The radar was used for distance keeping on cars and could actually detect the car in front of the car by bouncing signals off the ground, it was really slick.
Spinny thing is just when you mount one ontop. It doesn’t have to be. The example in the video appears to use a forward facing cone LIDAR. Presumably in addition to other sensors.
It’s still a spinny thing with a laser in it. That’s fundamentally how lidar works. The outside shell can look however they want it to look.
And let me just add, Musk ordered the LIDAR removed against the engineers better judgement.
Did he have lidar removed? I thought it was radar. I didn’t think any Tesla vehicle ever took on the cost of lidar.
This is true. There never was LIDAR.
They tested a LiDAR rigged car, and it stopped just like you predicted. As of 2021, Tesla uses only cameras for FSD, and not even radar (which my stupid fine Toyota truck has).
They tested the idea safely by building the wall out of styrofoam, or at least that’s what it looks like when it blows apart :)
Front-facing radar is the bare minimum needed to pass the test given (fake-road wall). Many vehicles use it for adaptive cruise control, and radar is even faster than either cameras or lidar for figuring out the range to an object. 1000 Hz measuring distance to an object is enough to find both the relative velocity and the acceleration of another object. This provides enough time to apply the brakes safely when approaching a vehicle or obstacle
LIDAR is even better, and also more compute intensive and expensive to install.
I think Tesla was very short-sighted in removing radar sensors, certainly. If they hadn’t, they could’ve spent more of their energy on making the FSD cars better instead of just making them sufficiently safe with insufficient sensors
Forget lidar, they don’t even have mature tech like radar for emergency braking. Edit: +even
Why do you think lidar is not mature? It is radar, except it uses light and can get much more resolution than an RF radar. Or was that a joke… That was probably a joke… if it was then nm.
Lidar is mature but its automotive application is not. Radar is basic by now in comparison.
That comment just missed the word ‘even’ - as in they don’t even have radar, and that’s on regular non-self-driving cars, and lidar would be a step above that.
Not a joke, lidar struggles with fog/rain, which radar can handle much better.
You know what struggles even more in fog and rain? Camera only systems 😄
And ?most? humans. 😉
As far as I’ve seen, any system would be additive. If it has lidar, it would also have cameras and radar. So that you get the best of all the technologies (e.g cameras are the only only of the three that can follow lane markings)
I am a bit disappointed to not see the Tesla crash into a real wall. I feel a bit click baited here.
Also, they prepared the polystyrene wall to break this cartoonishly, but still played on being surprised.
The purpose of the video is to test a hypothesis, not to total a car.
Mark Rober is a youtuber sure, and some of the stuff he does is to feed the algorithm. But he’s also an engineer, and that involves experimentation and a good dose of science.
Engineers won’t set up tests that intentionally destroy their expensive test equipment if they can conduct an equivalent test non-destructively.
Did anyone seriously expect it to be a real wall with Rober sitting in the driver’s seat?
Apparently, yes.
deleted by creator
The title of this post is “Self-Driving Tesla Crashes into Wall Painted to Look Like a Road… Just Months Before Planned Robotaxi Launch”. In order to know that someone was sitting in the car, you have to watch the video.
I was expecting they’d rig it with a dummy sitting
Yeah, do YTers not have the money to kill one Tesla?
That seemed like an expensive production, sadly one totaled car couldn’t make it.Should’ve let WhistlinDiesel “test” it.
For environmental reasons I’m glad they’re not just destroying whatever they can afford to
Yes, you are very right.
I’m a bit disappointed they painted identical to the actual road. Probably a lot of humans will get fooled by that one. We should send a challenge back: how looney toons can you get? Will something more cartoonish fool it? Will a different landscape fool it? How about drawing an oncoming train?
Haha, oncoming train? You’d be lucky to avoid a slow-rolling freight train at a clearly lit crossing in a Tesla using FSD.
Case in point:
Is such depressing cynicism fun for you?
I would say that it’s a good idea to paint more tunnels on walls, but then I remember how dumb human drivers are too
You’d be horrified how many people drive off a bridge that has collapsed, it’s happened multiple times in multiple different incidents.
I’d be horrified that physical barriers with bright reflectors weren’t put up before the bridge that was out.
This has typically been seconds after the bridge collapsed, before emergency services could reach the site.
Did you really think someone just demolished a bridge without putting up a sign?
I love that one of the largest YouTubers is the one that did this. Surely, somebody near our federal government will throw a hissy fit if he hears about this but Mark’s audience is ginormous
Honestly I think Mark should be more scared of Disney coming after him for mapping out their space mountain ride.
He probably just made Disney admissions and security even more annoying for everyone else.
Judging by the fact that he has an imagineer-video out (effectively) at the same time as the space-mountain mapping, I’d expect that Disney was fully aware of what he was doing, and the whole sneaky-thing was just to make it more appealing to viewers.
To be fair, the roadrunner it was following somehow successfully ran into the painting.
All these years, I always thought all self driving cars used LiDAR or something to see in 3D/through fog. How was this allowed on the roads for so long?
Money.
I remember reading that tesla only uses cameras for it’s self driving. My 2018 Honda uses radar for the adaptive cruise so the technology exists, musk is just an idiot.
Radar would not detect a Styrofoam wall either the return from Styrofoam is extremely low. Radar also can not distinguish elevation differences very well so an overhead road sign can be mistaken for a stopped vehicle or a stopped vehicle mistaken for an overhead road sign.
Does it? My 2023 model throws a shit fit if it’s cold and I assume the camera covers are iced over.
It probably has cameras as well, for lane guidance etc.
My Mazda complains if the windscreen is dirty for the same reason.
Radar doesn’t detect stopped objects at high speed. It’d hit the wall too on radar alone.
This has to be solved by vision and or lidar.
Unless your car is traveling faster than the speed of light, radar will detect objects in front of it. But yeah, I was trying to imply that for a complex system like self driving musk is a buffoon for relying on a single system instead of creating a more robust package of sensors.
They get filtered out and the car will not act on it because there is so much noise from stationary objects all around you. The car essentially wouldn’t drive at all if it didn’t filter them out.
At high speeds, the radar in all cars is used to detect moving objects and the change in velocity of those objects.
Radar will not prevent running into this wall at 40mph.
People can downvote me all they want, but that doesn’t change anything.
Only vison and / or lidar would stop for that wall at 40mph.
Edit: aside from clarity on the above this is the expected outcomes
Radar in cars today: hit the wall
Vision: probably all hit the wall but could be sufficiently programmed to not if they trained on it.
Lidar: would not hit the wall.
You’re partially right, stationary objects on the side of the road will have a different Doppler shift than a stationary object in front of the vehicle, items on the side of the road can be filtered. Cheap radars with low sampling rates will not be able to distinguish as their Doppler bins are fairly large.
They do.
But “all self driving cars” are practically only from waymo.
Level 4 Autonomy is the point at which it’s not required that a human can intercede at any moment, and as such has to be actively paying attention and be sober.
Tesla is not there yet.On the other hand, this is an active attack against the technology.
Mirrors or any super-absorber (possibly vantablack or similar) would fuck up LIDAR. Which is a good reason for diversifying the Sensors.On the other hand I can understand Tesla going “Humans use visible light only, in principle that has to be sufficient for a self driving car as well”, because, in principle I agree. In practice… well, while this seems much more click-bait than an actual issue for a self-driving taxi, diversifying your Input chain makes a lot of sense in my book. On the other hand, if it would cost me 20k more down the road, and Cameras would reach the same safety, I’d be a bit pissed.
they generally do
They originally the model S had front facing radar and ultrasonic sensors all round, the car combined the information to corroborate it’s visual interpretation.
According to reports years ago the radar saved Tesla’s from multiple pileups when it detected crashes multiple cars ahead (that the driver couldn’t see).
Elmo in his infinite ego demanded both the radar and ultrasonics be removed, since he could drive with out that input so the car should be able to… also it is cheaper.I’d be very curious to know how much cheaper it is. Sure, there’s R&D to integrate that with everything, but that cost is split across all units sold. It feels like the actual sensors, at this scale, can’t add a significant amount to the final price.
Exactly, my previous car (BMW) once saved me in the fog by emergency braking for something I wasn’t able to see yet. My current car (Tesla) shuts down almost all safety features when the camera’s can’t see anything, so I doubt it will help me in such situations. The only time my Tesla works well is in perfect conditions, but I don’t live in California.
Exactly, my previous car (BMW) once saved me in the fog by emergency braking for something I wasn’t able to see yet.
If you were driving at a speed at which the low visibility would have gotten you into into an accident due to some obstable you weren’t able to see yet, you were driving too fast. Simple, isn’t it?
While true, it’s still nice that super-human senses are looking out for the driver on their behalf. Also it’s nice if super-human senses allow for braking earlier and closer to graceful rather than standing hard on the brakes because of late notice.
Fog is one example, but sudden blinding glare could be another situation that could be mitigated by things like radar and lidar. Human driver may unexpectedly be blinded and operating at unsafe speed without any way of knowing that glare was coming in advance.
tesla uses cameras only, i think waymo uses lidar.
Most non Tesla brands that have some sort of self-driving functionality use lidar and/or radar. I’ve got a BMW iX and as far as I know it uses cameras, radar, lidar, and ultrasonic sensors.
It’s the only sensible approach. Not just is the notion that “humans use just their eyes too” completely wrong (otherwise how would be able to tell that something is off with the car “with our butt”?), computers are not even remotely close to our understanding and rapid interpretation of the world around us or cooperation beyond of what’s pre-programmed, which is necessary to deal with unforeseen circumstances. Cars must offset this somehow, and the simplest way to do so is with vast sensor suites that give them as much information as possible. Of course many humans also utterly fail at cooperation and defensive driving, but that’s another problem.
Honestly all the fails with the kid dummy were a way bigger deal than the wall test. The kid ones will happen a hundred times more than the wall scenario.
Some sort of radar or lidar should 100% be required on autonomous cars.
I think insurances will require that is it comes to self driving at least here in Europe.
EU leading the world in consumer protection laws yet again
I fully agree, but sadly, investors likely care more about their cars hitting walls than hitting kids. Killing a kid or pedestrian in the US is often a very cheap fine. When my uncle was run over on a sidewalk next to his son, the police ruled it an accident and the city refused to do anything. Same thing happened when my friend was ran over in a bike lane… So killing humans is probably cheaper than hitting a wall.
Interesting that in the most consumerist nation on earth, objects have more value than people.
They should just program it to drive through the painted tunnel but when another driver comes behind you they crash into it.
Tesla is trash.
Fuck Elon musk.
They sound like they’re perfect for red states
It got fucking wile e coyoted
The scientists in Ireland calling their data set to prevent this exact fucking thing “Coyote” sent me over the moon.
