I am not impressed with FSD. The recent update is so much better. But, it's still dangerous. I have to rescue FSD from slamming into my neighbor's driveway posts, stop it from going around a curb too quickly, and it will brake for no apparent reason. Don't get me started when the weather is bad!! I think there needs to be some level of learning at the car level for it to function well in my environment. I truly want FSD to succeed as an owner and investor. But they have a VERY LONG way to go.
I agree. Tesla Vision won't be able to recognize the edge of a road with a fresh fall of snow on it. I don't think it will be able to determine a safe driving speed on a road with black ice on it. And I don't think it will deal with very dense fog, or with heavy snow with large flakes that make it hard to see. These are all conditions that make lots of people too nervous to drive, and call a taxi instead.
Tesla has promised us robotaxis. Waymo is operating them already. Not much more to say. If Teslas FSD is so superior, why are there no Tesla robotaxis on the road anywhere in the world? Yes I know .. they are "just around the corner" - for four years now.
Many companies take a different approach. More sensors, maps, rule-based instead of AI and so on. And so far I'm not convienced that Teslas approach is superior. They will probably still be talking about "full autonomy everywhere in the world coming soon and until then it's level 2" while other companies have already replaced human taxi drivers on 90% of all city roads in the world.@@royphillips7644
It is a numbers game. Waymo has 300 cars in 2023. Tesla has 5 million in 2023. Waymo is way ahead atm. 300 to zero. When FSD becomes active the number is 300+ to 5,000,000+. If Tesla ever completes FSD to their lawyers specifications the race is over.
Who knows how many times Tesla has to change its hardware and software design before this is achived? There are not even laws for robotaxis in almost all parts of the world. The promise "the Tesla you buy today will turn into a money making robotaxi next year" simply will not happen. @@davidbeppler3032
@@davidbeppler3032it's a fantasy to go from level 2 to level 4 overnight. You think one Tesla will announce no one needs to be in the driver's seat? It doesn't work that way.
If there's a self driving system from Tesla in the next five years without a driver I would be very surprised. They're cutting corners. It's never going to work.
You are underestimating power of scale in deep learning. As we have seen in LLMs, scaling up models make them much smarter. We can see something similar in Tesla FSD as well.
@@dreadfulbodyguard7288 I think the quality of the data is much more important than the quantity. I'm not convinced that Tesla us ahead in that aspect.
I would beg to differ. Tesla is very good at getting things done, and done well. They have already made crazy advancments in ai. But only time will truly tell.
man, exponential growth is crazy, huh? At this rate, we'll have self driving system from Tesla within 12 months of today (5/15/2024). Yet, the rate could pick up and we'll have it before 2025. Exponential growth is crazy.
The truth is Waymo self driving taxi is already in service. For normal people, we only live and go to places within a city. We don't need a self driving car for a trip from SF to Austin. I will fly from SF to Austin and take Waymo in another city.
Just took 2 Waymo trips (30 mins for each) in SF last week. I was nervous on the first trip; but I felt comfortable on my way back and I even watch video on my phone instead of staring at the road condition. As a summary, the Waymo drove as a normal driver if not a premium one.
The in-town Waymo product seems to far outperform Tesla’s FSD. Tesla has a long way to go to get to robotaxis. All this talk by Tesla fanboys about the millions of potential robotaxis is comical in light of the current performance of Tesla’s Smart Summons - the things can hardly make it across a parking lot to collect its driver, much less independently drive to a rider pick-up point across town …
I honestly think this is a little biased waymo has all those sensors because any crash that happens waymo is reliable. With tesla there is more room for reckless testing because even if 100k crashes happens tomorrow Tesla will just say should have been paying attention. While waymo takes full responsibility for any crash that the car makes. It makes sense why they are so careful and don't go on highways yet
I note your comments. Query “Waymo versus Cruise verses Tesla” a older vid . Shows Tesla is a lot more advanced 8 months ago. What makes you say that “with all those sensors in a crash Waymo is more reliable”? Tesla has a lot more miles driven and have fewer incidents than Waymo. Tesla are smart and keeping their FSD at level 2 while it develops it. This is not an admission they are behind. I think your comments on reckless testing are unfounded. There are plenty of sensationalists capitalising on any issue in FSD or Waymo as it makes them money. The facts are Tesla FSD in beta statistically is more than 10x than human drivers. So is Waymo as well better than human drivers. It’s the human drivers that are reckless. Tesla FSD will be well tested before it applies for Level 4 or 5. Tesla have committed to production RoboTaxis in volume from the to be build huge Giga Mexico. It will only be a few years the RoboTaxis comes off the production line in large quantities. They will be economical to make and operate. They will cost a fraction of Waymo Sensor Aray at say $50k, plus set up say $10k plus ipace $72k I think Waymo will find a place in the market. But the millions of RoboTaxis will come from Tesla and the world will be a better place
Waymo is really more competition for Uber and Lyft. I've been taking Waymo in SF without a safety driver for a few months now. I took cruise as well although they're now suspended. Looking forward to V12 as I think that is likely the path to level four.
Every point you make has a counter point for that favors a Lidar system. My suggestion is that you need to try to go deeper into why a smart company like Google that started with just cameras, moved to other censors. BTW.. no way is tesla a better software company than Google.
Yea he sounds very biased and looking at his channel you can see why. Everything was like Waymo bad, too much sensors etc lol. Also Waymo is liable for every crash that happens Tesla isn't which is why they can experiment with fewer camera's. Meanwhile if waymo does it they'll see countless of lawsuits on their hands for every crash
All of the lidar-based autonomous rivals require expensive modifications, and they aim *only* for robotaxi operations. None offer autonomy for personal vehicles. That is a stark differentiator. Only Tesla intends to release self-driving for both personal vehicles and robotaxies. This differentiator isn't as significant as the others you discussed. But it's real.
@@ronmatthews2164 well, that is hilarious. XPeng is using source code stolen from Tesla around 2018. It's all in C, so they can tweak it by hand. They have nothing worth spit when it comes to real-world AI. No neural net computer in their cars. No server array crunching out weights in response to video inputs. Nuttin'. But they are good at PR and marketing. They used that core competency to convince the ill-informed that they have attained L3 autonomy with their stolen tweaked software. Their goal: stock price pumping. It's not difficult to find lazy people who drink that Kool-Aid and think it's fine wine.
@@UrgeltOkay, so you are saying that Tesla is soooo useless and crappy so they can not make it better than Xpeng with the same (if this is true) software as a base? This is really one more proof of how useless Tesla is.
@@Xanthopteryx dude, you are hanging your argument on one fact, and only one fact: XPeng made a public claim that they have achieved L3 with no neural net inference computer in their cars and with no machine learning training capability whatsoever. What happens to your argument if XPeng has lied about their software's capability? It falls apart. Obviously, a conclusion as stark as yours needs a bit of objective evidence beyond an unscrupulous company's marketing gimmick. How do we know XPeng is unscrupulous? They stole Tesla's 2018 pre-AI stack source code. That is not speculation. Thieves, liars and dramatic marketing are not evidence. I would suggest testing these systems by an independent evaluator, but I'd rather not waste an honest person's time chasing after XPeng's absurd lies. There's an alternative, of course. RU-vid is jam-packed with live video feeds of FSD operating on real world highways, roads, streets and parking lots. All we have to do is compare those videos to live video feeds for XPeng cars... Oh. Drat. There aren't any.
@@Global_Optimizationthe difference is that people take calculated risks in those scenarios - it'll be deemed unacceptable for an automated system to do that.
No, it will not be limited to just good visibility situations as we have seen how cameras are able to see just as good or better than humans. Only where it goes beyond what would be considered normal conditions could it choose not to drive, just as a human could/should.
@@bluetoad2668”calculated risks” as in killing 45,000 people every year. People are terrible at driving. Go back to driving 101… it is illegal to drive faster than the conditions of the road. The posted speed is not the law when ICE, rain, fog make it impossible to drive at that speed safely. That is the law in every state. Vision sees fog and slows down for the conditions. Remember, we still have people on the road and animals to look out for. Driving to fast for the conditions of the road applies to autonomous cars as well.
As many commentators mentioned you seem biased towards Tesla. This becomes pretty clear in your arguement. You paint some features of Waymos approach as disadvantages, when they aren’t per se, they are just a different approach to teslas. Which approach is better? The future will tell. But atm there is only one of both who has working robo taxis out there.
Seriously! There is no comparison between Tesla FSD and any / every other self-driving technology. I mean they are two different creatures! When it comes to which is better, it boils down to economics! It is impossible to wireframe the entire globe, but Tesla's artificial general intelligence robot can go anywhere!
FSD is very, very good. I've been using it for 3 years on every drive. It's true that FSD doesn't rely on HD maps, but it does rely on sparse street maps. These maps contain errors and are never completely up to date. This dependency on map data causes FSD to make consistent mistakes where the map has bad or missing data.
IMO the arguments about Tesla's superiority over Waymo are solely theoretical. Waymo has actual Robotaxis working right now. Despite being very cool FSD doesn't actually work autonomously and there is no prospect as it stands of it doing so. So the argument is really "If FSD actually worked then it would be superior to Waymo". In the real, unmapped, uncontrolled world that FSD wants to conquer there will always be edge cases that require genuine intelligence to solve. Countless online footage demonstrates this. Waymo needs a much more restricted and carefully prepared area to work in but it actually works from what I can see (although the slow pace of expansion must tell us something too). (Edit - just watched a couple of Waymo videos and was reminded that actually they sometimes require remote human driver intervention too!)
That's just it: Waymo is already giving robo-taxi rides to a small number of paying customers, but their limited pace of expansion might give Tesla (or someone else) time to catch up. Plus there's a good chance that Tesla's all-AI strategy (or perhaps some hybrid approach) will prove better at dealing with the nuances of real world driving than traditional programming. We won't know who's winning the race until someone is approaching the finish line.
If you are not working in these companies on this tech, then I guess it comes down to who you believe is most capable, who is the best at disruptive tech. Googles team or Musks. I go for the guy who lands used Rockets back on the pad etc.
Agree on camera approach in good visibility conditions, what about fog and snow conditions? Are the Tesla camera IR capability good enough to see through fog? Snowing condition beyond reducing the visibility have two additional disadvantages like cover camera lens and hide completely the ground signs. First could be solved but what about self driving without full snow covered ground?
None of these are cabable of reaplacing even a not really skillful driver waymo not even operate in rain it stops and you need to wait for a replacement (human driver)...
Why does no one take about Mobile Eye? They appear to be heading down the Tesla path with a large fleet of OEM vehicles having their system installed and therefore garhering the sorts of data volume required for that NN approach.
I would like to find out more about mobile eye. On their website they say over 100 million vehicles are using mobile eye. Then show pics of 4 low volume production cars. If they had 100m mobile eye in use there would be so much on their website and in the news media. It has to be BS
@@InformedKiwi yes, this is why it's so interesting to me. They are the one and only other company claiming to be capable of matching Tesla's approach and yet RU-vidrs ignore them out would seem.
Human vision may allow us to drive ,but why make it only as good a a human, make it better. Radar for fog and extended dark. What about when the sun blinds the camera etc?
:45 says Waymo is in Arizona, and about to start operations in San Francisco, LA and Austin. 13:05 says once again, Waymo operates in Arizona, San Francisco and LA, and is about to operate in Austin.
The first mention is for their "driverless service" which is about to roll-out in SF & LA. They already operate in SF & LA, but have safety drivers (so not driverless).
@@Cleanerwattthey removed the safety drivers in SF a few months ago. Apparently they still have remote operators who can help out if it gets stuck. Cruise was recently suspended but Waymo is noticeably better. They're both more competition for Uber and Lyft than Tesla
This report was disappointing. First, it reported extensively on Tesla's opinion about what is required to render self-driving both safe and efficient. Waymo's approach wasn't given nearly the same degree of attention and quite a bit of that attention was directed towards dismissing Waymo's approach based on opinions formed under the influence of Tesla's widely publicised outlook on self-driving. Jon, that is a serious deviation from impartiality and an improper way to report this matter. Also, did you check your understanding of what Waymo is doing with the data it collects? No, you didn't. You just pretended that all of that data must be 'confusing'. Guess what, you have to study the data in order to work out what is useful and what isn't. That is a major flaw with Tesla's live beta testing and the impetuous bets its CEO makes without evident push back from Tesla engineers. Companies like Waymo don't love Lidar irrationally. Lidar is a sensing device that serves a purpose. First, it provides a redundant source of data for the self driving computer and redundancy in data sources is connected to safe autonomous driving irrespective of whether Tesla fans like to accept that or not. Second, Lidar data doesn't just pointlessly feed into the maintenance of overrated HD maps. On the contrary, it forms an informational base for rapid vehicle response in dangerous situations. The self-driving computer can use Lidar data to build that 3D vector space that Tesla crows about more straightforwardly than Tesla does without dependence on analysis of 2D images. Tesla is a vision fixated company. Insisting that a self-driving vehicle computer should 'be like a human driver', viz. should start from visual cues alone, just appears to be an arbitrary and constraining imposition on autonomous driving computer development. Would an autonomous driving computer having Lidar, Radar and other data sources at its disposal make a better driver. I can't be sure that it would. And, having declined to collect the data, Tesla can't be sure that it wouldn't.
He's a Tesla channel no wonder he's super biased. Everything was waymo is bad Tesla is so good, lidar bad camera's is so good. He also hasn't said that any crash Waymo makes they take full responsibility while someone can die in a Tesla and the company will be like eh wasn't paying attention Rip 🤷🏾♂️💀
Why doesn't Waymo operate during rain? Why does Waymo only operate in small areas? Why does Waymo avoid highways? Why does Waymo not operate in crowded areas?
@@casperhansen826 Do you imagine that cameras (or eyes for that matter) work well in stormy weather? There is no human driver to hand back over to in a Waymo vehicle (only a luckless passenger) so, sensibly, Waymo vehicles pull over until weather conditions improve. Couldn't you work that out for yourself? As to the rest, Waymo is both a robotaxi service and a self-driving development company. It follows the rules that apply to organisations like Boeing or Airbus. No one entering a Waymo robotaxi (except Waymo mapping and test drivers) is to be exposed to road conditions other than those for which the autonomous driving computer has been explicitly approved. In practice this means that Waymo can only operate its robotaxi service in small areas within this or that city where road conditions are comparatively highly regulated and where licences for responsibly operated robotaxi services can reasonably be granted. There is nothing in Waymo's testing or operational practice that is akin to Tesla's use of Tesla drivers as live beta testers of its autonomous driving computer. That is deliberate (Waymo and other robotaxi operators recognise that safety can only be assured at this point under controlled conditions) and it is the only reasonable basis for the operation of a robotaxi service anywhere. So, while the Waymo autonomous driving computer satisfies the steep safety requirements that apply to a robotaxi service licensing sensibly stipulates limited zones where safe operation can be assured with a high degree of confidence. Waymo runs robotaxis and it operates within the legal and licensing constraints that apply to such services. It isn't here to make you happy. Do Tesla fans need to be deprogrammed before they can understand this stuff? Are they really so cut off from how the world works? Don't Tesla's fans grasp that the successful operation of an autonomous driving computer must be proven to the satisfaction of authorities vested with the powers to regulate road safety before such a computer can receive the formal tick of approval that would allow it to be used in a robotaxi? Whatever happens with FSD in the coming years, Tesla can't hope to operate a robotaxi service without satisfying all the conditions for a licence. It isn't Tesla fans that will be deciding these questions. Public authorities with the relevant statutory powers make these determinations.
Hey Jon : excellent collation and elaboration of the facts surrounding the $TSLA Call Option as it has been referenced recently . I would add Waymo have no control over the evolution or modification of the Ipace as a platform - OR indeed it’s longevity . I am especially keen to understand how Elon will fulfil his commitment to RoboTaxi Income for Tesla Owners : THE ultimate purchase incentive . the idea that owners may fulfill the role of Supervisor in the early phase is interesting as I expect consumer resistance to the idea of driverless - initially. (CookieUK) 😊
Does Tesla FSD takes the relevant corrective actions when various warnings are ignored. E.g. 1) Turn on hazard lights, 2) Slow down vehicle, 3) Find a safe place / position to stopped while the hazard light is on, 4) Inform relevant authority after 2 more minutes of inactivity. These corrective actions would be useful when 1) Someone is drunk, 2) Someone fell asleep, 3) Someone hai lost consciousness, etc. Tesla should also identify various zones where 1) Tesla FSD has been working well with little interventions, 2) Tesla FSD has moderate level of intervention, or location only have moderate level of driving data for training FSD, 3) Tesla FSD has high level of interventions or location has low level of training data for training FSD. This way the driver will know which zone or location requires more, less or moderate level of attention (e.g. in red, orange and green zones or locations). Tesla FSD should also try to differentiate moving, non-movable objects and objects that are movable, but not moving, around the vehicle. This allows FSD to focus more computing resources to track moving and movable objects.
Your BS Dude! I've used FSD for two years, and it's way better than another so-called autogenous! Waymo is remotely controlled in a geo fence Ares NOT GOOD!!! The rest are behind Tesla!! Tesla can do autonomous way better than waymo etc!
Yes it can. It is just not allowed to. Tesla FSD was not allowed to operate in China. But China have now given Tesla the green light to start operations. All it will take is approval from the different countries. very different from the needs of Waymo.
GM lost 8.2 billion on their failed Cruise self-driving project. The VW-Ford partnership spent 3.6 billion before giving up on their self-driving project. These projects failed because the companies could not build the software. If there really was an easy way to build the software, Tesla would have done it by now.
Tesla realized that their human engineers could not build such a complex piece of software so they have changed their tactics from FSD 11 to 12 (as stated in the video). They are no longer "hard-coding" rules for the system but rather training behavior. It seems to me that it's just a matter of time until Skynet becomes self-aware... er, sorry I meant to write, it's just a matter of time before Tesla's FSD is able to handle most situations better than an average human driver would.
Relying solely on cameras to drive because humans primarily use eyes is stupid. The ability to sense things that a human could not is a good thing! The goal is to be better than human drivers. Better sensors are obviously part of the solution. This is especially true when it comes to sensing obscured vehicles to avoid collisions that a human driver could not avoid.
I'm not gonna get in no camera-only FSD car. Only Lidar/Radar can reliably ensure that you won't crash into something. It won't think the side of a truck is the sky, but will be able to detect that something is in the way.
You do know V12 is a very different beast to what has come before? Your faith in Lidar is misplaced. Waymo recently crashing into a large pole proves Waymo is not all it is cracked up to be. From what I am seeing Tesla have all the pieces in place to solve self driving.
If you dig deeper you see that Tesla is no where near Waymo. You actually do not even have to dig deeper. It is obvious from far ahead. Tesla is really NOT that capable at all. First of all, remember that it is ADAS. Nothing more. Not only technically - reality speaking. And FSD V12 will not change much at all. Still mostly a marketing gimmick. Teslas system is faulty from the start and will not reach any real self driving with todays fleet. Not only that, Tesla is overtaken by more and more companies. They are really down in the bottom somewhere. And they will stay there.
Actually digging deeper will show the huge advantages Tesla has over the competition, and those advantages are set to show just how far ahead Tesla are in this space. What they are doing with V12 is game changing.
@@thewatcher5822 No they don't. They have not even proven the concept in a small restricted area. They have nothing that resembles true self driving. It is all a scam.
"Lidar vs Tesla Vision" . . . Let's be clear, Waymo's primary sensor is the 29 cameras on board. Lidar is just an add-on to the vision on board. Before watching the movie, the title alone shows either bias or misleading the viewers.
Waymo's Geo-fenced area. . . that is a safety concern and legal concern, this limitation is put on the cars by the software engineers. . . not due to functionality.
@@DanDeGaston Of course it is due to functionality. For Waymo to operate it has to be in a pre mapped area (geofenced) it cant step out of those areas and work.
@@thewatcher5822 Yes it can, and yes it has. Similar to Tesla, Waymo cars have tested driving outside of their geofenced areas in thousands of situations, they are legally (and for safety reasons) required to have a driver in the front seat as those areas have not been proven . . . The data they really want is within the geofenced areas because that is where they can legally go without a driver in the drivers seat. Honestly, go talk to a Waymo Engineer instead of spouting non-sense.
Yes it is more expensive per vehicle. Yes Tesla has a lot more data. I fail to understand though how fewer features is better or Lidar is a negative. Musk has been promising self driving vehicles next year for years and it never seems to happen. Sometimes I wonder how well he really understands AI.
The scientific community speaks highly of mobileye, perhaps a comparison in a next video? From what I know they offer different solutions with camera or lidar
Musk is betting that the gap between waymo and Tesla is within 2-3 years. It doesn't really matter even if waymo is leading for 3 years. Once Tesla's FSD is successful (let's say 2026), there will be about 10 million vehicles on the road with self driving capabilities in an instant with OTA. Any competitor, including Waymo, that wants to mass-produce and roll out 100,000 LiDAR-based driverless cars on the road within the 3-4 years of the lead is a fantasy. Musk changes the requirement from "when can we make self driving cars at the earliest" to "when can we mass-produce self driving cars including existing produced cars at the earliest," After redefining the problem, it is obvious that the pure vision solution is the only answer. BTW, Tesla has 5M+ cars on the road to collect data. Even a Tesla user didn't buy FSD, Tesla can still run FSD as shadow mode, and collect road data and user controls.
"the fleet will wake up overnight via an OTA" was already promised to happen 3-4 years ago and will probably not happen in the next 3-4 years. I would even take a bet that NO Tesla on the road today will EVER work as a robotaxi. Musk will find an excuse and fanboys will be happy to accept it.
Most of the Teslas on the road today are using obsolete HW (pre HW-4). Most of those projected 10-million Teslas on the road won’t qualify to be a robotaxi via that simple OTA update you tout so proudly …
@@YuLiang83 - That’s good, because drag racing is the reason I enjoy Teslas - on the street, on the track - any place I can hunt down a Hellcat … I’m not at all interested in FSD …
More sensors does not mean better. The fact Waymo recently crashed into a large pole shows you it is far from perfect. Tesla now have all the pieces in place to solve self driving, and are set to dominate in this space.
Waymo is NOT level 4, not with the words; "limited conditions," "local," and "will not operate unless ALL required conditions are met." Those words are far from a true L4 condition.
Wamo and Cruise will never work at scale. What would it cost to buy a Waymo or Cruise equipped car. 125k 150k vs 35k tesla. And fyi I drive as does every single person in the world using a vision based system. So yes a vision based system works, problem is human drivers can get distracted and or simply suck at driving.
These comparisons are not helpful. We should only compare apples to apples. You can argue one or another, both have their limitations, errors and so on. We need to wait until the systems are really released and more important ready to sell.
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
Then why FSD can actually do it? Like, don't get it wrong, but your personal opinion about your personal experiments doesn't really go well against company which invested billions into technology and has who knows how many experts from this specific field working day and night. They have over 10k H100 AI GPUs training their AI model, how many did you had for your experiments? One personal computer? And for lidar, well, it doesn't work in snow, it derps in rain and it only provides point cloud which still needs to be processed and properly interpreted to avoid false positives, aka using cameras. But biggest issues with Lidar is its cost, this is why single Waymo car costs like 200k+, while Tesla can go as low as 30k for a car which can drive autonomously. One of those systems isn't scalable from the start.
@@Zripas Reconstruction of a 3D scene from stereo pairs and plane images IN PRINCIPLE is less reliable and more computer-intensive than the reconstruction using direct 3D scanning and a set of 3D radii-vectors. And yes, more expansive too.
@@alexandergofen1771 I mean, yea, you could shove in 200k worth of gear on the cars for extra data to be processed and to get most accurate world representation, but that simply doesn't scale. Its more expensive, it will have more points of failure and you can and will have data conflicts from what cameras report and what lidar does, especially if its raining or snowing, which then renders Lidar useless and you would need to heavily rely on cameras anyways, so you still need cameras being able to drive on its own data.
My god is Waymo still gluing shoe boxes and toilet paper rolls to their cars? They still need pre-scanning too which is hilarious. FSD is going to absolutely crush Waymo with sheer scale (great job to waymo though for being mostly driverless)
Another tesla fanboy video. Waymo is way ahead of Tesla, they have been driverless for years in Phoenix and now in LA, yet we need to see Tesla launch their first ever driverless car, which is not out yet to this date.
It amazes me how people mistake a limited operating service as somehow superior. Tesla have some huge advantages and are solving a much bigger problem. From what I am seeing Tesla are set to dominate in this space.
The proof is in the pudding. Waymo takes liability for every accident their vehicles might provoke. Tesla has a shady record in that respect, with the Autopilot disengaging just when it senses a crash is imminent and it can't prevent it- so that technically, Tesla can claim "we recovered the data and the Autopilot was not engaged when it happened".
Read what you just wrote and try to understand basic thing here... Waymo uses its system in its own cars, Tesla provides its system for millions of privately own cars... Do you see tiny difference here?
It absurd that Tesla is attempting to create a self driving system without lidar and radar. Google is uses neural network learning as does Tesla. On the surface people seem to think that Tesla has some proprietary technology that isn't available to everyone else. As far as I can tell-they are reliant on the data from their cars to create their self driving model. Google, who has been involved in self driving for over 14 years, doesn't think this is enough. They have spent the time researching the problem, Tesla has not.
Just because they spent 14 years on a thing doesn't mean they actually know more about it. Having system which relies on 150k equipment isn't scalable, what Tesla is doing is attempting to make a system which can work universally based on generally cheap cameras only, which is scalable. Waymo is still bound to only few cities with limited areas, and it was for years by now, while Tesla works in entire country, heck, someone hacked it and enabled FSD in european country, where FSD wasn't even trained on, yet it still drove around with minimal issues. While Waymo would simply brick itself if you got it outside geofenced area.
@@Zripas Yes, that is exactly what it means. If google could have attained level 4 autonomous driving with cameras they would have. Cameras do not capture enough data. Period. The cost of lidar has gone down dramtically in the last few years. Research- digital lidar technology. To assume there won't be cost reductions as lidar technology matures goes against the laws of manufacturer and history. Things always get cheaper as manufacturing and technology improve. If you watch a few videos, particularly the ones where they are faulting Waymo or Cruz, you will see how many unpredicted traffic situations trip uo self driving.
@@Onraitravels Every single human uses 2 (usually) eyes to gather data around them and drives the car just fine, so there is no reason why would car with cameras should not be able to do it. Just go and watch Tesla FSD 12.4.3 videos. And once more, scalability is a big deal, even if lidar costs go down, those are still just an additional thing to camera setup, Lidar isn't replacing cameras, its additional thing on top of those. So you still need AI which can properly process imagery data in any case and maybe use Lidar just for some instances to double check distances to the object, but that can be quite redundant thing which could even create false/positives conflicting with what cameras can see, so one of those would still need to be prioritized over the other in case data doesn't match, and vision based system will always win against point cloud
@@Zripas Humans can't see in the dark and are challenged in low light, fog, rain, etc. To assume that AI is going to overcome these limitations is not based on science. That is why Google and Cruz, the two leaders in autonomous driving, supplement cameras with radar and lidar sensors. Most people agree that self driving technology is the greatest AI challenge at the moment. Google is a leader in AI technology. Tesla is not. All the hype around Tesla developing neural network learning suggests that other autonomous vehicle manufacturers don't. Nothing could be farther from the truth. Your main argurment- if we can drive with vision only so can cars omits that we have a brain to process data that AI is still not able to match.
@@MsAjax409so many flaws, so many flaws, but he didn't list one. Sounds like he doesn't see his own bias. I think the problem was that cleanerwatt didn't say what he wanted to hear
@@6681096 tesla has so many safety issues....it's the edge cases that has to be almost perfected. Tesla is sooo far from it.... But people biased to tesla like you won't understand any of these for sure.
WHAT??? why would anyone go with a 40k-50k solution when they go can go with something cheaper? Tesla is 40k-50k itself. you lost all credibility with this video. thank goodness i am not a subscriber. you think a company like good will invest in the wrong technology then double down on it. oh. they might not target the same segment of the population... thought about that?
To @netgnostic1627 Human vision is incapable of recognizing the edge of a road with a fresh fall of snow on it. Humans can't accurately determine a safe driving speed on a road with black ice on it. Humans cannot drive well in dense fog or heavy snow with large flakes that make it hard to see. And as for calling a taxi... does the taxi driver have super powers enabling him/her to accomplish all the above?