In the world of autonomous vehicles, lidar sensors are the center of debate. Self-driving car companies, like Cruise and Waymo, use lidar as the key ingredient to advance their autonomous vehicle navigation while skeptics, like Elon Musk, claim it to be useless. Transportation editor, Andrew Hawkins, explores the landscape of both and why exactly lidar continues to be at the forefront of complete autonomous driving. #technology #cars #lidar
Subscribe:
Like The Verge on Facebook:
Follow on Twitter:
Follow on Instagram:
Follow on TikTok:
The Vergecast Podcast:
Decoder with Nilay Patel:
More about our podcasts:
Read More:
Community guidelines:
Wallpapers from The Verge:
Subscribe to The Vergecast on YouTube, new episodes on Wednesday and Friday:
source
How ”self–driving” do you want your self-driving car to be?
I will say it again, Elon is a lunatic. He is not even remotely smart. I guess States are known for rich imbecyles like Trump and Musk.
dont know much about tesla but LIDAR are more versatile than just self driving cars
I am in OH and these are the worst drivers. Only takes 1 to screw up it up.
Elon Musk saying Lidar is unnecessary (4:00). Tell that to the baby deer one of your self driving Tesla's ran over, you smug nutcase!
Nothing beats teslas FSD.
Update, waymo and other cars companies have decided to remove LiDArs
In some years optics are going to high end enough to not use lidars
Well this hasn't aged well. The fundamental issue that Elon understands and most other people dont, is that the important factor is the software, not the sensors. Its obvious lidar isn't necessary for successful driving because we drive successfully.
Hilarious, you are comparing Tesla with waymo. Tesla has more EVs on the road in America than all auto company combined. Once AI has enough time to train, video will be the most effective option
A year later, GM decides to exit its LIDAR based self-driving. I have been saying this for years—their compeition is not with each other. Their competitor is with human drive without a college degree. The key is cost. If you start with LIDAR, you are destined to fail. It will never be commerically sustaniable. Tesla has a chance, but only in places where human labor is expensive.
This guy comes off as such a small minded person. Look at how he frames Musk and Tesla’s actions. Tesla “pushes” autonomous driving on its customers. Musk is “unpredictable.” He uses misleading stats. Total loser behavior.
You for got to mention that Waymo is a max fleet size of 700 while Tesla's has over 6 million capable of using autopilot and more than 1 million in use. Here is some very rough maths: Waymo = 1 crash for every 350 vehicles per year. Tesla = 1 crash for every 1,300 vehicles or more. Another thing you forgot to mention is that Waymo is ring fenced in a central location whereas Tesla's can drive anywhere such as rural areas where reckless drivers are way more likely to end up in fatal accidents (50% increase in fatal incidents compared to urban). Tesla's have also avoided cars that are going to cause an accident shown on their captured video footage.
I think it is risky to only rely on cameras for unsupervised FSD. Let see when or if Tesla can deploy unsupervised FSD car with only cameras-
This video is not going to age well.
thanks so much for the video. Tesla cars are dangerous in low light particularly fog. As for me no Lidar no storks for turning indicators it’s back to BYD seal for me.. as we all know against the advice of his engineers, Elon Musk removed the sensors Lidar on the Tesla and he’s paying a price for it now
I’m self driving in my Tesla right now and it’s great
We need more self-driving cars in the medical field
Hopefully, Waymo makes millions. Because with the Lidar vehicle expenses, operating & original product costs, its costing them billions. Most of Tesla’s crashes were caused by others and were unavoidable. Waymo isn’t allowed on freeways, so their driving is slower paced and those accidents shouldn’t do as much harm.
Tesla pretends it doesn't need these sensors with elaborate misconstrued justifications for removing them just because they know this model will never fully self-drive so they can cut costs and simplify the manufacturing process by removing them. The moment they will get a replacement for this model (if ever) they will suddenly change their rhetoric.
Im always amazed how misleading these videos are. If I knew nothing about autonomous vehicles I would walk away thinking Waymo and Crisue are superior to Tesla because they use LiDAR and Tesla uses cameras.
You can create a 3-D environment using both technologies. It’s about who has the better software.
Waymo and Cruise can only operate in two cities. Teslas can operate anywhere. When it comes to autonomy, scale matters and nobody can touch Tesla on this. They have the right approach and Waymo and Cruise do not.
Musk is grifter with a history of lying to advance his business interests.
"Cameras are blind at night"? Then how do people see to drive? Do they have LIDAR? Cameras have far better vision at night than people do.Or perhaps the cars light up the road for them.
Watch the Whole Mars Video of Omar driving his father from LAX to Palos Verdes in rush hour zero interventions vision only system.
Waymo has tons of Lidar and Cameras, including remote people controlling the car, and it cannot go anywhere geo-fenced! Tesla camera vision can drive anywhere, and it works way better than Waymo and others, including Byd!!!
Waymo has tons of Lidar and Cameras, including remote people controlling the car, and it cannot go anywhere geo-fenced! Tesla camera vision can drive anywhere, and it works way better than Waymo and others, including Byd!!!
So making self driving work is the only problem? I don't think so. The real question is what that market is worth. I think it's less than what has already been spent on R&D. Getting rid of the driver does not make public transportation suddenly more popular, it's still just public transportation and we already know that is a known and finite market. Pre planned point to point trips is not 100% of how people use their cars, it might not even be 20% for some owners. Stock analyst like to say there are trillions of dollars on the table and there is not. Car owners don't hate driving in fact most really like it. Do you think BMW will change their slogan to "The Ultimate Riding Machine"?. I don't think so.
Hahahaha 😅😅😅😅… the Verge! what kind of reporting is this?
The ego of these tech companies is unbelievable.
youre not being fair with your comparisons..' per 1 million miles travelled' vs 'since 2018'… how many miles has tesla covered.. over a billion… take this assessment with a pinch of salt.. tesla rules them all..stop hating.. lol
Tesla has no chance to catch up to companies using Lidar sensors. Rumor is that Tesla has just order some Lidar sensors! I think they maybe 4-6 years behind Waymo, MobiEye and GM’s Cruise. Everyone knows that Elon Musk is not the smartest guy at all in the development of new technology!😂 My money is on WayMo since they are already in operation in 4-5 cities!😊
pointless video if not during the entire video you mentioned tesla and neural net or the amount of data tesla has or even the amount of miles driven. You just compared two different technologies and one metric (vehicle crashes).
It’s June 2024. Clearly Tesla FSD is leading. LiDAR is a fool’s errand. This video cannot be any more wrong
Pure camera are blind at night, no they aren’t, that comment alone tells me this guy doesn’t know what he’s talking about.
Let's get accurate facts on Tesla crashes. There is no way to tell if autopilot was
Activated or not! Each test done by YouTube Waymo and Tesla FSD AND supercruise and Blue Cruise TESLA WINS ALL THE TIME, BEATING THEM TO San Francisco destination!
Low compositional generalizability
Elon is such a horrible public speaker
Waymo is remotely controlled! By people. Tesla can go anywhere waymo cannot it’s geo fenced maps old technology
Unlike this reporter Elon will change if he is wrong, Elon was wrong about Manufacturing with only machines and robots, he stated "I was wrong about automation" he is a engineer unlike most people so if the information changes and the evidence shows it is a bad move then he will redirect. I do not think this makes him bad or stupid it is called innovation. Being wrong is only bad in school but in the real world of creativity and invention being wrong is apart of creating the right. This is unknown space for all companies and Elon does need his heart to change only the data and evidence. Learn the difference or stay lost in the sauce.
more non driver cars more non leaser cars non more acciedents it stops accidents and the traffic less kills and it was sunny and a bunny
Even before this video, as a mathematician who has dealt with stereo imaging, I dare to disagree with the highly respectable Elon Mask, who is so sure that processing of many plane images allows to reliably reconstruct the 3D scene around the car: especially the sudden appearance of obstacles. Even formally, restoration of the 3D scene using a stereo pair of images is a so-called ill-defined problem, relying on the recognition of the (approximately) corresponding points in the stereo pair. Not to say, that images of stereo pairs at night, in fog, and similar contain nearly no information at all. Though yes, humans possessing normal stereo vision, do reconstruct the 3D scene due miraculous ability of the human brain.
Contrary to that, a Lidar scans the real 3D scene and DIRECTLY reconstructs it no matter night or day. Unlike the situation with stereo pairs, The 3D reconstruction from Lidar data is NOT ill-defined.
Just realized this video is pre-supervised-FSD. FSD 12.x (AI version) kick lidar's behind.
Easy, both Baidu and Waymo are actually autonomous today on the road, Tesla is not. If Lidar is not needed, just do it, make it real.
Not mentioning miles for tesla self deriving was verry misleading