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!
This would be hilarious if it weren’t for shitty cars causing deaths.
That said, I always wondered why we don’t find a system like RFID that could penetrate concrete and asphalt, and plant passive receivers in roads? We re-pave roads so damn often in this country (the U.S.) it seems like we could’ve knocked it out in the past couple of decades, minus our most rural areas.
I know RFID itself isn’t strong enough, but I imagine that would’ve been an easier problem than figuring our complete self driving. Not to mention making GPS a secondary system for U.S. road travel in most cases.
Maybe it’s just a dumb shower thought?
I have another idea: echolocation and laser measurement.
I don’t know the value of echolocation in this case, as I’m generally ignorant here, but it’s straight wild to me that they went purely on visuals.
Tesla used to also have radar (and maybe lidar?) but they removed it as a cost cutting measure. If you ever see older videos of a Tesla slowing down or stopping due to a potential collision a few cars ahead, that’s from before they switched to only relying on cameras. The collision avoidance was significantly better back then.
Some cartoon shit
Make Elon test ride the first Tesla robotaxi and there’s a chance the funniest thing of all time will happen.
Meep meep!
I am very glad that Elon and Trump have overreached and now Tesla is suffering. I hope Starlink is the next domino to fall.
Yup plus the European Union is making their alternative to launch in a year or 2
Good.
I’m not rooting for America to fail, but I’m 100% rooting for Elon to fail.
I seem to recall that fElon prevented the self driving team from utilizing LIDAR for any part of the system, instead demanding that everything run off of optical input. Does anyone else remember the same?
Yes. He took too much inspiration from Stanford University’s “Stanley” winning the DARPA Grand Challenge in 2005. This was an early completion to build viable autonomous vehicles. Most of them looked like tanks covered in radar dishes but Stanford would up taking home the gold with just an SUV with cameras on it.
It was an impressive achievement in computer vision, and the LiDAR-encrusted vehicles wound up looking like over-complex dinosaurs. There’s a great documentary about it narrated by John Lithgow (who, throughout it, pronounces the word robot as “ro-butt”). Elon watched it, made up his mind, and like a moron, hasn’t changed it in 20 years. I’m almost Musk’s age so I know how the years speed up as we go on. He probably thinks about the Stanford win as something that happened relatively recently. Especially with his mind on - ahem - other things, he’s not keeping up with recent developments out in the real world.
Rober just made Musk look like the absolute tool he is. And I’m a little worried that we may see people out there staging real world versions of this somehow with actual dangerous obstacles, not a cartoonish foam wall.
I did low-key get the squiggles before writing the article. I thought, from an ethical hacking disclosure-type perspective, that this info might cause folks to… well, ya know, paint tunnels on walls.
Then I looked, the cat was already out of the bag, the video had something like 5 million views on it in the 4 hours it took me to draft the article. So I shared it, but I definitely did have that thought cross my mind. I am also a little worried on that score.
Yes, I recall at the time experts saying it was a terrible mistake and Elon saying Machine learning will bridge the gap.
The real reason was to increase margins.
What’s cool is that Teslas used to have radar sensors, at least, but Elon removed them from production to save money. Even if you have a car from back then, the software no longer uses them and they’ll just physically unplug them the next time you have the car serviced, as it’s just a drain on the battery at this point 🙃
Yikes.
meanwhile our subaru has lidar for adaptive cruise control and emergency braking
I didn’t realize EyeSight had different versions, on the Solterra it looks like it is indeed LIDAR.
My Crosstrek has the older dual camera setup for depth perception, it would not be fooled by a picture of a road on a wall… I’m surprised the Teslas are.
they’ll just physically unplug them the next time you have the car serviced
So, (looks at watch), in an hour?
So did they unplug it
Was just thinking this
A single LiDAR sensor prevents this kind of issue
I’m trying to find an article that covers what I remember but I know for sure that it’s been a good while since I saw the info I recall. Hopefully I can dig something up.
That might actually be the exact article I’m thinking about. Thanks!
Indeed there is a lidar car in the video and it works way better in many scenarios.
Iirc they were using a combination of lidar and radar, but Elmo wanted to cut costs.
Ah okay. I was genuinely curious if I was remembering correctly because I definitely know it’s been awhile since I’d read anything on the subject.
Funny thing is, the price of lidar is dropping like a stone; they are projected to be sub-$200 per unit soon. The technical consensus seems to be settling in on 2 or 3 lidars per car plus optical sensors, and Chinese EV brands are starting to provide self driving in baseline models, with lidars as part of the standard package.
Cameras and radar, I believe. Never lidar.
Did he want to cut costs or did he want a network of cameras at his control all over the world?
Yes.
I remember there being claims from him or his team about lidar being a dead end that would not scale as well as computer vision.
Yep! That’s what I’m thinking of. It was Elmo. The real engineers objected.
I believe he claimed that since humans use their vision to drive that computer vision was more than enough.
I don’t know about you, but I also rely on sounds & feel when I drive. I also know that the human eye has evolved to detect motion, filter out extraneous information, and send just the important bits to the brain so that it doesn’t get overloaded with everything the eye sees. Computer vision is the exact opposite from that, having to process every bit of every image the camera sees.
I also know of many times my vision fails. Driving into a sunrise for example
since humans use their vision to drive that computer vision was more than enough
Surprised he didn’t swap out the wheels with legs while he was at it
I don’t know about you, but I also rely on sounds & feel when I drive.
Of course. When I feel myself driving into a wall, I stop immediately.
You must connect with the road, every km or so stop and hug the asphalt.
Came here to actually write this. Everyone remembers that. He made Tesler the hated shit it is today.
As a space nut I seriously hope that he never gets a chance to do anything similar with SpaceX. Thankfully he’s mostly been kept away from important things thus far.
Don’t get me wrong, I know SpaceX’s closet is overflowing with skeletons. But since Congress has been so kind as to continuously cut NASA’s budget for the last few decades, I have to rely on SpaceX and other private companies to keep our space endeavors going.
I’m (was) huge SpaceX nerd, but last year or so I’m less and less. He always was dumb narcissist asshole, but now I can’t take it anymore. Also the idea that we’ve fucked up this planet and need to move somewhere else, by doing thousands of launches finishing this planet always made me sick. If someone would take him out, I probably would come back to liking the company.
To the famously already fucked planet Mars, no less.
Is that just to cover his ass cuz he was promising backwards-compatible FSD for models that don’t have LIDAR?
Tesla never had LIDAR. That’s the little spinny thing you see on Waymo cars. They had RADAR, and yes it was removed in 2021 due to supply shortages and just…never reinstalled.
It was removed due to supply chain, but Musk did seem to legitimately think optical only was better.
Who was the idiot that removed LiDar to cut costs?
/s
Elon removed the radar. Tesla cars never had lidar. What an idiot Musk.
Tesla had camera+radar+sonar, and that wasn’t their own tech - they used mobileye EyeQ back then. When they switched to in house tech they gradually ditched the radar and sonar which made no sense to me. But at the time I saw their lead say in an interview that this is superior and I believed. not anymore.
they said doing so cut costs but obviously lidar/radar/sonar only gets cheaper over time, let alone the extra r&d costs because a vision only system is much more difficult to develop.
It was removed because it was giving false positives. They should have upgraded it with lidar but decided to just remove it.
Yeah, it might drive straight into a wall but at least it isn’t returning false positives!
It was removed because of supply chain issues.
That would make sense if they put it back after, but they didn’t
He did say lidar was “useless” though.
He’s said humans don’t use LiDAR so his cars shouldn’t have to. Of course humans have a brain, and he’s cars don’t, but you can’t tell him anything.
Human drivers also make automobiles one of the most dangerous ways to travel.
I think it’s also reasonable to say a human dying because of their own actions is different than a human dying because a big corp cut costs on safety features in an entirely autonomous car where the human has no ability to stop what’s happening. (You can control them in current teslas, but they’re working on cars without human controls as well)
Weymo have them beat then. They already have cars that essentially act like taxis and the only control the passenger has is an emergency stop button. But they don’t control the speed they don’t control the steering or anything.
But those systems absolutely do have lidar because in order for them to be widely accepted they don’t need to be a bit safer than humans they need to be a lot safer than humans.
Human drivers also make automobiles one of the most dangerous ways to travel.
Same goes for Teslas. Just that the human that’s making them a dangerous way to travel is Elon Musk.
He also said the government doesn’t use sql.
Bahaha, what kind of a bizarre statement is that?
Was he trying to imply the government only uses spreadsheets and nosql DBs?
Or did he think it was necessary to point out that your average government employee isn’t writing their own SQL to grab data they need?
Someone said something he didn’t like so he blurted out the first ignorant thing that he thought of, as usual.
Even then, that’s not really correct. People grab data through sql queries all the time. Mostly because all the front ends are trash.
They are so expensive too! /s
Who would have known electronics gets cheaper all the time?? /j
Except GPUs 😥
This is a very good test, and the car should have past. That said though, I hate the click bait format where they show a stupidly obvious cartoonish wall, when the real wall is way more convincing.
The Video:
That sort of clickbait is 100% sure to get a “do not recommend channel” from me, I’m so sick of it. And it’s sad when the video has such a good point.
The Clickbait
I can see it’s kind of funny, but it’s misleading.
Have you heard of DeArrow? https://dearrow.ajay.app/
It’s a browser extension that replaces clickbait thumbnails with good community sourced ones
I don’t see a problem with thumbnails that accurately portray the contents of the video, since only a small number of characters can fit in the title and a screenshot of one frame from the video doesn’t say much, so it can be difficult to get a sense for the video at a glance otherwise. I do get really annoyed with thumbnails that are deceptive in any way. If the thumbnail seems like it might be deceptive, I’ll usually read the comments before watching the video, or quickly scroll through it to see if it’s BS or not. Sometimes, the thumbnail advertises something that happens at the end of a 20 minute video that could’ve been 30s, in which case, I’ll scroll usually through to the end instead of watching the whole thing. If it weren’t for the thumbnail, though, I might not have watched it all.
yeah but if you share it with people, they’ll still see the clickbait thumbnail, and that’s the actual problem
Still supports a creator pulling clickbait.
The only way is to vote with views/retention.The only way is to vote with views/retention.
Want to guess why they are there in the first place?
I hate it too, but it’s mostly one of those “we can’t have nice things because of other people around us” situations.
But it only supports them if their video is then also good. I don’t like clickbait, because I don’t want to be tricked into my monkey brain looking at something. I do want to see good videos.
Just yesterday the algorithm found some guy doing tech videos. I watched a few of them and then sent a text to a friend who I thought would like it. He asked for a link so I pulled the guys channel up on my phone, and holy smokes, clickbait. If I hadn’t seen the videos already I wouldn’t have given that guy the time of day. But they are well thought out, interesting videos.
I’m not here to correct the world’s poor behaviour. I’m here to watch good videos. De-arrow does a good job of that, it’s quite interesting to see YouTube on a computer without it vs what I’m used to now.
Blame the youtube algorithm and Mr Beast, not all the other youtubers caught up in the tidal wave.
Yeah they do it because it works. I’ve seen several who make otherwise good content talk about it in their videos and make comments about how stupid it is bit they basically have to to be competitive.
Thanks no I hadn’t. Is that available as a Firefox extension. I do most of my browsing on desktop.
Yes, but you could have just clicked the link to find that out
Imagine being in the middle of a friendly conversation where you ask a question and the person says, “Why are you asking me?? Just google it.”
Well, this is a forum, not an out-loud discussion, so those are 2 completely different scenarios
They were also already given the link, so I guess:
Imagine being in the middle of a friendly conversation where someone asks for something, you give it to them, and then they proceed to ask questions about it that could be answered by looking at the thing you gave them
I give you a green round ball. You then proceed to ask me the colour and shape of the ball.
I’m not the OP, so I wasn’t having a conversation with them. But to me it gives off the vibe of “Random stranger, you should do all the work for me and provide all the answers, because I’m too lazy to do any of it myself.”
Could just be me though 🤷
The link in a comment that wasn’t for me? Like I update every 10 minutes to read all the comments??
Get real will you.The link you replied to.
The link is right there, you could’ve just clicked it instead of taking the time to write this question?!
OK I see it now, a bunch of icons I usually glance over, because such “icon lines” are generally for a bunch of social media crap I don’t use.
Apparently it’s proprietary crap, so no thanks anyway.The link is in the comment you replied to.
How exactly were you not able to see that?Sorry, I mixed up 2 threads.
https://github.com/ajayyy/DeArrow
https://sponsor.ajay.app/databaseThis (again) is from the link in the comment you replied to…
Your attitude really doesn’t work well with your lack of reading comprehension.6 hour trial, sounds like proprietary to me.
Privacy Note: Other than intially checking your license key, no requests to DeArrow servers contain your license key.
Edit: I just read the entire text, and it is actually very reasonable, I just caught the license key thing together with the payment option. It’s actually even cheap, so maybe I’ll consider it.
You cannot be serious?! Are you trolling?
-
First of all, something not being free (as in gratis) does not mean it is proprietary per se.
-
Second of all, your reading comprehension failed you again:
However, if you cannot, or do not want to pay, you can click the button at the bottom to use DeArrow for free. No worries if you can’t or don’t want to pay :)
-
YouTubers - especially large channels like this - constantly A/B test with different thumbnails and stick with whatever one drives the most traffic (no pun intended) to the video.
You might not like it, but it’s unfortunately the reality of operating a content creation business on an algorithm-driven platform.
There are plenty of channels I follow that make fantastic videos, but sometimes you have to tolerate the shitty thumbnails because that’s just the reality of the system they’re operating within.
algorithm-driven platform
And what is this “algorithm” based on? Actual user behavior. So the way to correct an algorithm is to change actual user behavior, no?
Lemme know when they release an OTA for our parietal lobes.
That sounds horrifying. :)
Just don’t fall asleep during the update.
And what is this “algorithm” based on?
No one knows.
Actual user behavior. So the way to correct an algorithm is to change actual user behavior, no?
Definitely not. I pretty much exclusively get recommended garbage content, and 90% of it is already on the “trending” page. At least it was like 3 years ago before I stopped using any of YTs first-party front-ends.
I must say that the recommendation section on youtube for me is spot on! Though I spent years on youtube constantly liking and disliking content. But I think it learned me quite well.
When im tired of recommendations I move to subscriptions. And 5 hours just passed by…
Presumably, the “algorithm” is based on whatever is most profitable. So probably some combination of most viewers, best ad engagement (click through rate), and best conversion/appeal to Premium subs.
That’s assuming YouTube’s primary goal is to make money, and which it should be as part of a publicly traded company.
My point is that those thumbnails and titles work, so if we want something different, we need to reward better thumbnails and titles and stop engaging w/ poor ones.
Yeah, that is just how youtube works. You as an individual can say you don’t like annoying thumbnails and titles, but they 100% work. And channels that don’t use them are just not getting as many viewers.
You realize Mark Robers target audience is like 8 years old, right? He also references looney tunes and wile e coyote a couple dozen times, including in this thumbnail you’re losing your mind over. The thumbnail fits the theme very well if you ask me.
This video isn’t a rigorous scientific test. This is a children’s video designed to get them interested in the scientific method. Get over yourself.
IMO it doesn’t need to be a rigorous scientific test, it’s not trying to prove something works as it should under all conditions. It’s showing the exact opposite, it does not work under this one condition, which is more than enough to disprove the safety of the car.
More than one test failed.
The Tesla failed the heavy rain and the heavy fog tests.
There’s zero excuse to fail either of those tests. But the Tesla killed the kid both times.
The wall test was just to show that the Tesla cannot put together optical clues.
Why would children be interested in car safety?
Why would children be interested in anything?
Have you never seen educational content before that wraps up potentially boring teachings in an exciting narrative?
Since most grownups aren’t interested in safety, I just thought it would be even less for kids.
All sales promotion stats show that car buyers basically don’t care about safety features. Almost all significant safety features are there because of regulation.Edit:
I can only laugh at the downvoters, you know nothing. It’s been a well established fact that safety doesn’t sell cars since the 50’s.Seems like a strange application of stats when, as you say, the regulated safety features - the important ones - need not come into a decision-making process and advertising them would be a waste of time.
Stats made over decades back in 50-70’s
So… out of date stats about advertising?
Including the horrible angle of headrests these days. You’re right though: nobody gives a shit about the extra safety features.
My 6 year old kid loves anything about car and enjoyed Marks video. While driving him from school, he asked me why we can tell it’s a wall but the cars can’t. It sparked a 20 minutes discussion on car safety and why we need seat belts.
While driving him from school, he asked me why we can tell it’s a wall but the cars can’t.
Cool inquisitive kid you have there. 👍 😀
Who downvoted this? XD This brings me joy
Oh wow, you really didn’t realize? Yeah man this is a youtube channel for getting kids interested in science and technology, like the technology surrounding self driving cars and lidar. Did you see the part where he introduced the technology by taking it to Disney world?
Here’s a random video from crunchlabs, the company he created and advertises on ALL of his videos. This video shows his fan base enjoying what they got from crunchlabs.
That’s cool then, but probably not for me. And I still think it’s misleading. If they made the analogy in the video it would be different. But as it is, it looks like clickbait. And honestly using clickbait on children is actually worse.
They do make the analogy in the video. They reference it multiple times.
Maybe I didn’t have sound, and that’s not the problem, the problem is the thumbnail for the video is clickbait, I don’t get why I have to repeat that so many times?
I understand the joke of the analogy to cartoons, and it’s perfectly fine they make that in the video.“And I still think it’s misleading. If they made the analogy in the video it would be different.”
I was just responding to your own point, mate. Good news, it is in the video multiple times, even visually referenced multiple times. They even described as a cartoonish test while showing the cartoon wall gag. So, per your own words, should be good to go then, yeah? I mean, you’re arguing with yourself at this point.
Why is anyone interested in anything?
My nephew was obsessed with Teslas a few years ago. I asked him why, his response? The indicators can be set to make fart noises.
My 7 year old daughter and I watch Mark’s videos together and they have helped to spark her interest in engineering & science.
Because they don’t want their friend to die?
To kids, death is just a word.
When I was a kid I was extremely interested in junction layouts, it drove my parents mad. Kids like all sorts of random things.
Kids love cyber trucks, teslas, Ferraris, or any car that is perceived as very expensive
At this point everyone should know that YouTube thumbnails have no requirement for accuracy. It’s more like an album cover.
I know, but if they are about anything serious like tests, I think it’s a fair assumption that the thumbnail represent it reasonably.
If it’s misleading, I don’t want their vomit. They can just fuck right off. We already have more than enough misinformation. I simply don’t want to waste my time on bullshit.deleted by creator
Still astounded people use anything other than the subscription section on YouTube.
That would require signing in and allowing tracking.
Most 3rd party clients support RSS subscriptions.
History turned off, subscriptions only for me.
We are in a tiny, tiny minority.
I disagree with this being a good test. Where on earth would you find a wall on a road with a fotorealistic continuation of the road printed on it? This would trick many human drivers. Self driving cars fail in many realistic situations that are a lot more concerning. This is just clickbait.
You haven’t seen what Teslas are in the news for lately?
It’s not that crazy someone would put up a fake wall on some backroad to catch out inattentive Tesla drivers. Doesn’t even need to be nearly as big and elaborate as this one. Any painted object would accomplish the same.
But the point of the video is that optical cameras are easily deceived, and Elon is lying to his customers that LiDAR is overrated and not necessary.
Doesn’t address the point that humans would be equally deceived by this wall if they don’t pay 100% attention.
With this paint job, in this environment? Maybe. Though IRL you would probably see it much clearer due to the lack of parallax effect on a 2D projection.
But if we’re talking e.g. about a dark-ish barrier at knee height, your brain does a much better job to quickly recognize it as obstacle. Whereas cameras without depth perception would fail completely.
I’d hit that
True, but Mark’s video basically about comparing Tesla’s Camera Sensors Vs Self Driving car with a Lidar Sensor.
They also simulated some real life scenarios which the car with Lidar sensors passed easily, while Tesla failed some of them.
So I guess Lidar sensors are superior compared to Teslas cameras.
Where on earth would you find a wall on a road with a fotorealistic continuation of the road printed on it?
Spoken like a man who has never relentlessly pursued a roadrunner, nor taken a wrong turn at Albuquerque.
This YT channel definitely went all out on the cartoonish nature of this particular test, but the article describes other tests as well including running over mannequins representing children that other cars (Lexus) avoided.
While I agree that this would trick many human drivers, I think the goal of a self-driving car is that it be better than human drivers. And there is existing tech that could help achieve that.
I actually agree, it’s not really a good test. That wall is very realistic. It’s just that people get pissed about negativity.
Well if your thumbnail is not good enough and catchy people will not watch it. Which wont make the channel profitable. Which will cause it to not exist.
I hope you know that usually youtubers will not even start making the video if they don’t have a killer thumbnail to it. Thats the platform.
You shouldn’t judge a book by its cover.
If it’s made to be misleading and baiting, yes I FUCKING should. And so should you and everybody else.
How is it misleading?
The title asks “can you fool a self driving car” and the thumbnail illustrates a cartoon situation that immediately explains how they will attempt to do so in the video.
The video then goes on to not only answer the question, but explore the technology involved in-depth.
It MORE than delivers on the “clickbait”.
Thumbnails can’t be subtle, they typically get viewed at a tiny size compared to the full video and that’s why large high-contrast features work better than a random screencap from the video.
How is it misleading?
You can’t be serious? The clickbait image is not something that might actually possibly happen. The image in the video is.
That is a distinction without a difference.
They are both images depicting a drivable path, on a flat surface.
That’s more a product if the yt algorithm. For every one like you that is annoyed by the clickbait, there are a million others instantly clicking with no further thought. So if you don’t do that, you’re losing money.
Maybe, but it’s not because of me people get shitty links.
passed
I agree with everything you said.
Thanks. 😎
Then imagine why 15% downvote? I suppose it means they don’t see how it’s misleading?YouTube is always click bait nowadays. There are plenty of that aren’t and have good quality. But everyone I encounter that’s trying to breakout is sensational for the sake of being sensational.
But we OWNED AND SLAMMED Tesla!
But being dishonest about it, detract rather than add to it.
Entire video is worth watching. He also snuck a chest mounted lidar into Disney and mapped some rides.
Is this video being suppressed by the YouTube algorithm? I wonder if it’s because of Tesla or Disney. Or maybe it’s because of simulated child harm?
Well, I guess we know how to defeat Teslas.
By not purchasing one.
They’ll just go out of business eventually.
I wouldn’t have bought one before Musk showed his true colors just because of the QA issues and lack of repair support. Me “boycotting” Tesla isn’t even a thing because I never wanted one in the first place.
They obviously pre-cut the wall, probably for safety reasons, and they were like, let’s make it a silly cartoon impact hole while we’re at it.
Good job.
You think you’re reliably going to notice this after a hundred miles of driving? (X) doubt.
Dude.
You could at least look at what you’re replying to before jumping in and going full outrage mode. I didn’t even say anything about what I thought of the validity of that experiment.
Keep putting yourself forward to defend the poor, misjudged car company belonging to a crazy asshole.
👌👍
Easy
Username checks out.
This is some amazing stuff! Buy $LAZR! 😁
geez, straight out of ACME.
