Self Driving Car – Automation and the Future of Transportation

Self Driving Car – Automation and the Future of Transportation


VO:”If the manufacturer could equip every car with an automatic driving mechanism…” VO:”…the car would always do what it should do when it got on the road.” We’ve been promised a future with self-driving
cars for a long time, but the technology available today is finally starting to pay off on that
100-year-old promise. There’s an incredible number of companies racing towards the autonomous
vehicle future, which I’ve talked about before. Tesla’s approach to that future
is based on radar and computer vision, which is what powers Autopilot, enhanced summon,
and at some point, more self-driving features. But there are some other pioneers in the space
making interesting progress on autonomy from a completely different angle. Waymo was kind
enough to invite me out for an event to meet some of their team, learn about their self-driving
technology, what motivates them, and ride in one of the Waymo One taxis operating in
the Phoenix, Arizona area. My takeaway from the experience surprised me. Before walking through what I saw, take a
moment and hit the subscribe button and notification bell, so you don’t miss out on future videos
just like this one. I’m Matt Ferrell … welcome to Undecided. Taking a step back and looking at the history
of self-driving cars is kind of amazing. This isn’t a new idea at all and has been floating
around in our collective imagination for nearly 100 years. In the 1920’s, Houdini Radio Control showed
off a radio-controlled car called, “American Wonder” in New York City. In the 1930’s General Motors sponsored Norman
Bel Geddes’s Futurama exhibition with a radio-controlled electric car using electromagnetic
fields. Jumping to the 1950’s, RCA Labs demonstrated
a car guided by wires and embedded circuits in the roadway. In the 1960’s we saw the United Kingdom’s
Transport and Road Research Laboratory test a Citroen DS with embedded magnetic cables
in a road. By the 1980’s we started to see vision-guided
systems from Mercedes-Benz. And DARPA-funded Autonomous Land driven Vehicle (ALV) in the
United States that used LiDAR, computer vision, and robot controls. In the 1990’s those technologies continued
with tests across the United States, like the Carnegie Mellon University’s Navlab
project that drove cross-country 98.2% autonomously. And in 2009 is when we see companies like
Google jump into the fray with their X lab self driving project. But in 2016, that project
was spun off as its own company, Waymo, under Alphabet. When it comes to self driving, there are some
guidelines for the different levels of automation from the NHTSA: Level 0 – No Automation. This is the majority
of cars on the road. Level 1 – Driver Assistance. This vehicle
can assist with steering or braking, but not at the same time. Think adaptive cruise control. Level 2 – Partial automation. This vehicle
can assist with steering and braking at the same time, but still requires the driver’s
full attention. This is where most modern cars that have some kind of “automation”
fall today. It’s basically lane assist and adaptive cruise control. Level 3 – Conditional automation. This is
where a driver is still required, but they don’t have to keep their eyes on the road.
The car handles almost everything. Level 4 – High automation. This is where companies
like Waymo currently operate. A driver is only required in certain circumstances, so
if the conditions are right, then the car can completely drive itself. Level 5 – Full automation. Exactly what you’d
expect. This is when no human driver is required at any point. So I’ve been an avid user of Autopilot on
my Tesla, which is a next level driver assist feature. It’s not self driving, but on the
5 levels of self driving, it’s somewhere around a level 2 or 3.(fn) But Waymo has been
operating at level 4 autonomy for some time now and has been operating a taxi service
called Waymo One in the Phoenix area. When Waymo asked if I’d be interested in coming
out to meet some people from their team and experience their technology first hand, it
was an instant yes. And to be clear, even though Waymo provided the trip, that in no
way has colored my perception of what I saw. My opinions are my own. One thing that’s a common misperception
with Waymo is that it’s operated by Google. I had thought that myself for a long time,
but Waymo isn’t part of Google at all anymore. After they were spun off in 2016, they’re
a completely independent company under the Alphabet umbrella. The name “Waymo” comes
from its mission statement of “a new way forward in mobility.” And after my meetings
and conversations with employees, that mission statement really seems to be ingrained in
their culture. There is a genuine passion and excitement around changing transportation
to make it safer and more accessible. It was apparent to me how much they believe in the
mission and how moved they are to see their technology is impacting people’s lives,
such as the first blind person to ride on their own in a self-driving car. ++Look up
the name of the blind man++ You can also see it in how the Waymo One app has been designed
around accessibility. When the car comes to pick you up, there’s a button in the app
to honk the horn to help someone who has difficulty with sight to find the car. Where Tesla is relying completely on radar
and computer vision for their self-driving features on their fleet, Waymo has gone the
path of computer vision, radar, and LiDAR in their technologies. Pair that with the
high resolution mapping that they do for the areas in which they operate and you have a
car that can easily achieve level 4 autonomy today. Tesla is relying heavily on perfecting
their machine learning models to achieve full level 5 autonomy at some point in the future,
but that means their cars are around level 2 and 3 today. Waymo’s path has pushed them
to level 4 very quickly and reliably, but just like Tesla, are now refining and developing
their models to hit level 5 at some point in the future. The big difference between the two is that
Waymo is operating a fully functional taxi fleet today within the zones where they’ve
created high resolution maps. I’m not trying to stir up a controversy, but Elon Musk has
been very vocal that LiDAR is a crutch for true level 5 autonomy. So is it a negative
that Waymo is reliant on LiDAR and high resolution mapping? I don’t think so. Far from it.
There’s multiple paths to the autonomous vehicle solution and what Waymo is doing is
extremely impressive. Before the trip, I knew that Waymo had been
operating for a while in the Phoenix area, as well as branching out to test in other
cities in limited zones. But the scale of the operation was much larger than I was expecting.
They have hundreds of cars in their fleet that run 24 hours a day, seven days a week.
But they’re also testing cars in other areas of the country to stress test their technology
with extreme weather. Right now they’re doing rain testing in areas of Florida. And
they’ve also been doing winter weather testing in Michigan. For the actual ride in the car, we went on
a 20 – 25 minute road trip around the Scottsdale area. My brother, Sean, went with me on the
ride and was just as excited as I was to experience it. “Robots are driving the car.” The route took us through a pretty wide
variety of environments like office park areas, residential streets, to multi-lane roads with
heavy traffic. I have a little more experience with riding
in a car that’s driving itself than my brother, but even I was a little anxious the first
couple of minutes of the ride. Pulling up to a stop sign and then pulling out into traffic
had me a little on edge at first. But something really strange happened to both of us after
the first couple of minutes. The car drove exactly like a person would in every situation
we were seeing. It was like a switch flipped and went from something novel and crazy, to
something pretty mundane. It was kind of crazy how normal it felt. As my brother put it,
“Okay … it’s just a car that’s driving.” As a UI/UX designer, I immediately focused
in on the passenger screens in the back seat. I was completely blown away by how well they
were designed, and how much thought, testing, and iteration must have gone into it. During
our conversations with the team, they talked about how much time they put into trying to
understand how to make people comfortable with a self-driving car. And this UI design
was proof of that effort and time. It communicated exactly what the car was doing at every moment,
as well as what the car was seeing. The screen would show a ping-like effect every
couple of seconds that showed you the LiDAR dots of what the car was seeing in the surrounding
environment, which included everything from parked cars, to people, to vegetation. When
the car was about to speed up, the route line would get a pulse of brighter green. If there
was a stop light coming up, a small stop light would show up in the upper left corner of
the screen and show you that the car recognized it as red, yellow, or green. Every piece of
the UI was carefully constructed to show you what the car was seeing and why it was doing
what it was doing. I was blown away by that. And to Tesla, I really hope they take a look
at that UI because it’s incredible. I’d love to see them take cues from that with
the Autopilot UI. With the high resolution mapping that they’ve
done, the car also took speed bumps and dips in the road like a champ. And near the end
of the route we took the car had to turn left at a very busy multi-lane road. The car slowly
edged its way out into the center of the intersection, waited for the light to turn yellow, and waited
for a break in oncoming traffic before making the turn. It took that turn exactly like I
would have done. The only issue I had was how aggressive it was with the pumping of
the brakes as it worked its way into the intersection. Other than that, it was a flawless ride. My one big takeaway from this weekend was
that autonomous vehicles in our lives isn’t something in the distant future, but is limited
to where you can experience it. It’s not something that’s a year or two away from
widespread use, but is something we’re going to see more and more of over the coming decade.
Waymo’s current fleet of modified Chrysler Pacifica’s are about to be joined by their
next generation car that’s built on a Jaguar iPace. They’re also testing semi-trucks
decked out with their self driving technology, and are doing test runs with empty trailers
to fine tune that system. It’s a good example of how this technology can be modified to
run on a very wide assortment of vehicles. These types of autonomous systems have more
awareness of their surroundings than we do. They can process that information much faster
than we can. And have quicker reaction times than we’re capable of. In the end, these
systems will be better and safer drivers that the rest of us. There’s no doubt in my mind
that this type of thing will eventually be ubiquitous and that this is the future of
transportation. It’s something we’ve been promised for decades, but the technology had
too many compromises to make it viable. But that promise has hit a point with technologies
like LiDAR, computer vision, radar, and machine learning that are bringing it much closer
to reality. It’s Waymo’s thoughtful user experience design that impressed me the most
though. For autonomous cars to be accepted, it’s important to have a system that’s
designed from the ground up to be useful for those with special needs; to address people’s
fears and anxiety around getting into a car without a human driver; to not focus on the
technology alone, but how this technology can and should be integrated into our lives. This isn’t to say that I don’t have reservations
about self-driving technology, I do. As excited as I am, I’m also concerned by the ramifications
of drivers losing their jobs. What this will mean for our daily lives and the future of
transportation is going to be profound. It has the potential to be a paradigm shift and
change a lot of things we’ve accepted as immutable. I think there’s far more pros
than cons to this shift, but it’s something that we need to think about and address as
self driving becomes more widespread. What do you think? Are you excited for self
driving to because a part of everyday life? Jump into the comments and let me know. If you liked this video, be sure to give it
a thumbs up and share with your friends because it really helps the channel. There are some
other ways you can support the channel too. Check out my SFSF Shop for some cool Tesla,
Space X, science, and Undecided shirts. There’s also other links in the description for some
great gear and discounts. And as always, an extra big thank you to all
of my Patreon supporters. Your support is really helping to make these videos possible.
Be sure to check out my Patreon page for additional details about joining the crew. And if you haven’t already, consider subscribing
and hitting the notification bell to get alerts when I post a new video. And as always, thanks
so much for watching, I’ll see you in the next one.

100 thoughts on “Self Driving Car – Automation and the Future of Transportation

  1. Very cool Matt. I’m more excited about trucks being automated as they’re so big and have been in too many accidents. An exciting future is ahead. 👍

  2. You said that Waymo is not part of Google and thats true. However, Waymo is still related to Google. While on paper they are separate, they both have access to resources under Alphabhet legal umbrella.

  3. Waymo only works because of that high resolution mapping. I'd rather have a Tesla that will get better overtime instead of having to move outside of Phoenix Arizona, the only place where Waymo works. I'm all up for using mapping as an extra safety measure but not having a whole system that relies on it. Also, it seems like Waymo been doing testing in Phoenix for 5 plus years. At this rate I guess the rest of the country will get it by the year 4000.

  4. Blah blah blah alphabet… They are still Google. Alphabet was done for all kinds of strategic reasons and in no way gets rid of the fact that ALL of it is effectively just Google. And I am a huge Google/Android user so I am not punching from the Apple side of the fence.

    LIDAR is meh as soon as you leave areas where there is NEVER snow. RADAR and cameras are THE solution. I rip on Tesla and your fanboiism frequently but there are a few things that I am fully onboard with Tesla and Elon on and the sensor suite is definitely one of them. Furthermore, high resolution mapping is cute but pointless. Construction zones, detours and accidents, to say nothing of potholes developing over time will be far FAR more important to develop recognition and action algorithms for. The autonomous system MUST work in ALL environments and ALL conditions that can possibly happen.

    And again… All the sensors, all the raw horsepower is for nothing if there isn't an equally comprehensive ability to recognize and react to things appropriately. Is that a person on a bike or a person WALKING a bike really is and was the difference between someone living and dying. Human drivers are FAR more adaptable. THAT category is what will separate level 5 or 6 from still having to have a driver for a lot longer than people think.

  5. Your experience was so bias. Please say all the facts. You said that just because they paid your trip you weren't say anything but the truth but I guess you failed to do so🤤

  6. Thanks for the evenhanded view of Waymo. The self driving race is going to be interesting, seems like at some point all the major players will need to get together and figure out some standards and get some regulatory and infrastructure support from governments. Imagine how much better self driving could be if the infrastructure helped out.

  7. Matt, I like all of your videos except for this one because it is so misleading and you are impressed at the wrong thing. Waymo can only work in a zone area where everything is well defined. The Waymo programming language is the traditional programming language which lends to a deterministic type of responses, if you know what I mean. Tesla uses neural network which can adapt to any types of roads conditions.

    There is a guy in the U.K. who test drives autopilot on his Model 3 all over Europe. For instance, there is no way that Waymo can drive in the roads in the following video.

    https://www.youtube.com/watch?v=8Pak8sQVvbE

    And last, if you don't already know. Google was split in a number of companies and Alphabet is one. There is nothing new that Waymo belongs to Alphabet.

  8. Very interesting subject from an ICT-perspective and I follow it quite closely. But on the other hand real Level 5 is far far off – at least two decades and probably much more.

  9. Waymo has 2 major problems:

    – Use of Lidar: Lidar is expensive, does not work well in fog and it has to be clean of dirt. And read the following article to see why Lidar has no future – and this is not from Elon Musk.

    https://medium.com/syncedreview/lidar-industry-hits-impasse-was-elon-musk-right-after-all-43b538d03677

    – Use traditional programming language which cannot adapt to situations that the software is programmed for, whereas neural netwok can adapt too new road conditions.

    Small autonomous driving startups, who used to partner with LiDAR companies at auto shows, are resetting their agendas. Some are using pre-equipped vehicles or testing other tech products, while many have left the industry altogether. A startup rep told us “car manufacturers are considering many promising sensors for mass production targeting the year 2021… unfortunately, LiDAR is not on the list.”

  10. "Waymo's path has push them to a level 4 very quickly and reliably"… their car has KILLED someone already even though it saw the person, but couldn't decide what to do. This is one reason why waiting for computer learning to be perfected is worth the wait SAFETY. Not putting your video down its still a good video but just thought this was worth pointing out.

  11. There is big difference between Tesla and Waymo’s approach. Waymo is mapping a particular area, but won’t be able to drive properly in unmapped area , but tesla is working on computer vision technology so that it can work in anywhere.

  12. Matt – the more i read/research the self driving, the more I feel like it is not worth the extra $6K Tesla is charging for FSD. While it may get more expensive later on, but sounds like it makes more sense to let this bake first and then pay a little more at that time once it is stable. especially as you say that Tesla is till in level 2 or maybe 3 right now. still a long way away from level 5. If there is a shift to not get this with Tesla, I think the car will still come with the FSD chip and hardware. It is really then just a software upgrade when ready. Is this what you've heard too?

    Waymo looks very interesting. Good to see the push and the actual smooth UI in the cars. Competition is awesome in this space.

  13. Can’t really compare something that’s geo-locked to a location that’s perfectly mapped thousands if not millions of times to something that adopts to the environment. Not to mention Waymo had something like 41% of their fleet involved in crashes. I literally see 5+ Waymo vehicles on my daily commute in the Bay Area right by Google. I’ve seen them do some stupid shit like braking abruptly, turning improperly, etc. Also don’t forget the price difference to the equipment on the vehicles. Really, one is aiming at quickly being able to provide limited area taxi services with high cost vehicles being purchased by the operator while the other is trying to make it possible for end consumers to drive places where no other such vehicles has driven before. The unfortunate fact that neither is as close to achieving their goal as they’d like to be but things will get better in the next 5-10 years.

  14. Thank you for this video, Matt. There is a dearth of information about Waymo, and I found your report very interesting. I love your channel. It's always so well done and informative.

    I view what Waymo is doing as similar to past approaches to self driving by, for example, burying cables in the roadway. Clearly the use of HD maps and LiDAR are a much more advanced and capable "crutch" than buried cable, but still far short of what I would characterize as a generalize autonomous transportation.

    Waymo, and other companies, (e.g., Uber) appear to be aiming at the commercial ride sharing industry by replacing the human at the wheel. I think there's a future for autonomous ride sharing, but Waymo's approach won't do much to eliminate private cars which clog urban streets and parking lots. The only way that will happen is if the use of fully autonomous cars becomes cheaper than private car ownership and capable of driving everywhere at any time, not just in certain well-maintained regions covered by high definition maps.

    Waymo's progress is impressive, as your reaction to the demonstration makes clear, but I think it's impressive progress down a blind alley. The generalized approach to autonomous driving which Tesla is taking will lead to a more cost effective solution to ride sharing, and the elimination of a significant percentage of private automobile ownership. The path to that end is as important, if not more, than the technology itself. When Tesla achieves SAE Level 4/5, there will be millions of cars capable of taking over the ride sharing needs of people at a cost/mile that will make private car ownership an unnecessary financial burden.

  15. 8:05 UI seems to communicate well, inspire confidence. 9:32 Semis in the works! Anyway, wondering if Waymo would have saved the life of the woman walking her bike across the road that über killed.

  16. Matt, the only issue I have with your video, and it’s a BIG one… is that, although I do agree Waymo has made great progress, I think you WAY(mo;) over simplified the FACT that Waymo can ONLY drive in their mapped out and well maintained areas. Although very impressive, let them try to drive outside of that walled garden and I would guess they would be extremely lost. This is where Tesla has the advantage, idar or not.

  17. It does not need to wait until level 5 to disrupt many driving jobs, even level 4 will. If someone watching this have friends or family that drive for a living, we need to encourage them to learn new skills or start a business.

  18. First Principle thinking tells me that if L5 autonomous driving can be achieved w/o LIDAR, i.e. way cheaper to make, using LIDAR is really–in Elon's word–a fool's errant. Admittedly I'm biased here, but really, achieving L5 is more than just a time race and technical race, it's also a cost race.

  19. 7:50 it didn't communicate what the car was seeing… it displayed what the sensors picked up. big difference. we don't know the degree to which those images are able to be interpreted since we know Waymo depend on detailed mapping.

  20. I think whole mapped/organic autonomy debate is pretty interesting. Obviously Elon's model, if successful, will be more powerful. But we have the technology to be able to map *everything*… so I could see either working.

  21. This is such an amazing video. Very informative and a great depth of research. I wasn't expecting a history lesson, and was pleasantly surprised with what i learned. I had no idea that autonomous driving started out so early. And to be honest, Level 5 reminds me of i, robot : the scene where they are driving all around the city without any effort.

    Thanks Matt!!!

  22. I’ve been a truck driver for over 20 years. I’m not a fan of adaptive cruise or lane assist, as they are just annoying in practice. I currently have a radar on my bumper that will beep loudly and relentlessly if there’s a vehicle in front of me, regardless of what the full situation is at the moment. It’s just an annoyance and I’ve been able to disconnect it.

    However, fully integrated self driving trucks get me excited. Otto’s beer run was amazing to see.

  23. Great vid Matt, thank you. Much as I love driving, I think in a few years we will look back in disbelief that we ever let humans, with all our weaknesses such as drug and alcohol use, mobile phone use, poor eyesight, loss of concentration etc., loose at the wheel of cars….

  24. The waymo strategy to introduce FSD is sound and predictable but does rely heavily upon detailed mapping, so restricting its use to familiar environments. Whereas Tesla is tackling the complexities of AI machine learning to bring true FSD to market. Both systems work well in different ways but cannot afford to fall short of perfect where failure could lead to death or injury. There is more to consider in particular the condition of road signage and markings that should be upgraded to "FSD friendly" and there is the problem of un-predictable incompetent human drivers. I think humans will eventually be excluded from driving and the FSD AI cars will negotiate amongst themselves as to the best way to navigate at very low risk of accidents?

  25. The ev in the room with autonomous vehicles is the subject of how they will be integrated into the mass of human driven vehicles on our roads. I don't mean the regulations the autonomous vehicles must comply too, but, let's call it, "rules of engagement" that mass of human drivers must respect and accept if the AV are to be allowed to make unhindered progress on their journeys.

  26. If you worry about self driving cars putting people out of work, then you worry about automation and the future of human labor in general. The answer ? UBI and maybe brain-machine interfaces.

  27. What would Waymo do if it comes to a junction where the traffic lights lost the electric power or are not working?

  28. Very good… I drive myself, but the roads are very silly or should I say other drivers whom think they rule the road. I would love a self Driving Car… it would do two main things, they are, stop pollution (near enough) Save life's ( I was knock over at age 12 )

  29. I would love to see just how this system could handle high pedestrian traffic zones cyclists and random drivers such as ny manhattan north to south as well as tunnels to Brooklyn

  30. Love your videos Matt. Wonderfully insightful information. I learned a lot from this video and now can better see that while I think the Waymo model is limited, it certainly is providing a platform that demonstrates the viability of the technology…TODAY. I love my Tesla and use autopilot every day, but thanks to this video I have a new appreciation for what Waymo is doing. Thanks again!

  31. Self driving does pose some challenges – not least of which is that we badly need to find ways to retrain the tens of millions of drivers world wide who will loose their jobs as a result of this. I think true self driving is still at least a decade or two away, not least because the legal frameworks that are necessary haven’t even begun to address it. But the challenge is there nonetheless.

  32. My bet is that Tesla will not be the first to acheive level 4 or 5, however, they will be cheaper!
    Not only that, the hardware necessary to when they get the software and neural network done is in every car since 2018, puls, the cars that don't have the hardware can be cheap and easily upgraded.
    Maybe with the path that Tesla has chosen, they will not be 1st in level 4, but they may be for level 5.
    Waymo may have a great advantage on installing their technology on trucks. that can be intresting for a company that already have a flet. It will be cheaper than change the whole fleet.
    Also, Peugeot is developing level 4 autonomous driving too, and there is robot racing, a very good way to develop and test autonomous technologies in extreme drivng conditions with no risc to humans.

    In the end, the more players the better!

  33. The detailed mapping of Waymo is an important ephemeral data set. Waze uses a more detailed map than just the routes provided. Debris, police etc are added and removed as ephemeral data. The Waymo mapping is the bridge between Waze updated maps and Tesla real time processing. I just don't see any advancement as the better choice. It's all data that is useful and it's significance will only be known in hindsight. If anything, the difference between lidar and non-lidar self driving is a business model choice. Also, Waymo is currently conditioning people to be comfortable with the idea of self driving. When Tesla is ready, the emotional groundwork of fear abatement will be laid.

  34. Hello, Matt. This video surprised me. I did not know there were self-driving technologies like this. I live in Peru, South America and I can’t wait to test them in environments like Peruvian traffic; probably, one of the most heavy and not well organized traffics in the world. Please do tell me if I can help them do that. Waze is a very good app because they did their beta testing over here for years.

  35. Dude, I love your videos but you seem to underestimate TESLA. Not to mention Comma.ai are doing some great things with self driving models with models using less resources than TESLA and Waymo. Waymo doesn't have enough data!

  36. IMHO It's great that two strong, well funded (potential) competitors are working on this problem from two approaches. High resolution mapping, LIDAR, or perhaps some type of assistance from the roadway itself will be necessary to achieve full Level 5 within a reasonable time frame. Social and employment issues aside, there really seems to be no downside to this race, and it's great that not all eggs are in one basket.

  37. What Waymo is doing is really great. I'm impressed by the quality of what they've achieved. Thanks for sharing that. However, I think there is a vast difference between Tesla and Waymo approaches. Tesla aims to offer the self-driving car at an affordable price for most of the people. I don't think there is anything cheap or affordable in Waymo technology; they have both totally different market targets.

  38. I am concern with self driving, and monopolizing the industry! Every big business that have been hijacked! (e.g. " oil, banking, housing, food") have contributed to the poor quality of life we all have today. Only very few make it rich, and the rest become slaves of the system. Today we have freedom of going anywhere we want to go, by driving a car and get away from busy life. when autonomy is here with us, we will loose freedom of traveling…We will become robotic society! Over 150 years ago, we lived off the grid, with self sustainable houses… And today we are slaves of industries that tied all of us to the grids; and take a good look at whom is controlling the grids around the world today. Most of us today work for three basic things, "Housing, Transportation, Food". Am very worried this industry will be hijacked as well.

  39. It's not that it's negative that they use Lidar and HD Maps. It's that to get to L5 autonomy, you MUST solve for vision (i.e with cameras) and once you do, Lidar is no longer necessary. Waymo's L4 is impressive, no doubt. But it only works in very, very small places. Bring a Waymo car to any other place on the globe, and it'll be useless. On the other hand, when Tesla hits L4 it'll be available everywhere in the modern world, instantly. And L5 for Tesla will be the same, whereas Waymo won't get to L5 without solving for vision. Hard to do when you're gathering real world data in only fenced in areas, and at a rate that is orders of magnitude less than Tesla does.

  40. Not sure how well waymo can scale compared to the exponentially increasing Tesla tidal wave that rolls out everywhere at once, on a per country / region basis.

  41. Interesting video but I've been curious, with the Lidar mapping approach, if the previously mapped route changed within minutes or seconds of the Waymo car approaching, how does it react? For example, a traffic accident closes the normal path of travel and they are re-directing cars on the wrong side of the road one lane at a time which would force traffic to flow in the "wrong" direction via previously mapped data. Like construction forces temporary changes to the "wrong" side of the freeway occasionally. I can see the car could just pick an alternate known route but getting to it from an unknown route would be handled how? Would these be "edge" cases like Tesla is still figuring out their own but different ones too?

  42. Lidar is not necessary at all. I don’t have it in my head and I drive good. Same will be with cars. Computer vision is enough. Waymo will be doomed soon by Tesla tech.

  43. That user interface looked awesome. I still don’t know how I feel about lidar, but as long as there’s this much effort put into it, it looks great. Still want a Tesla though 😭

  44. Just a thought does anyone else this will cause push back from law enforcement agencies because this would drastically reduce traffic stops especially ovi ???

  45. Driving across Phoenix stop n go streets is not fun; tough to get across town. Waymo and Tesla FSD Autopilot will be greatly appreciated. Love that fume less p3 though! Great video!

  46. I have never been permitted a recognised qualification so have never found a career path. This of course has limited my choices of living in society, no money, less choices, but…. I do follow (if I can) the expansion of the burgeoning non-combustion engine market. This short film proves we are indeed seeing the beginning of the end with regards the petrol and diesel poisonings of our living environments and people, globally. It makes me a little less troubled to know that the knock on effect for they yet unborn will be having the ability to enter city surroundings and not lose years from their lives in the process. Who knows, we may yet lift this curse and extend our lifespans to 150 years, possibly more. Banning petrol and diesel will certainly go a long way to influencing this. With us no longer having to set man against man for profiteering sake (capturing/protecting oil fields), it will in turn lessen more than the negative effects of war, with all energy now produced locally (wind, sea, solar) from any nation round the world, with them now having the capability to generate what they need when they need it, it is goodbye to the murders of oil companies and their ruining of our biologies and so spirituality.

    Great great theme that has shareholders shaking in their proverbial boots.

    Kind regards
    LM

    This capturing of our biologies must also be seen as the capturing of our spiritual paths.

    God bless

  47. Yes, Matt.

    Automatic self-driving cars are absolutely
    the fascinating thing you can imagine. With all their
    features. They can find their own parking space.
    They pick you up wherever you are. They pick up your
    children from school. They bring your visit to their
    home and come back to you. Wonderful.

    In the long run, these autonomous vehicles are only
    conceivable if they only use passive sensors. So, no
    LIDAR, no Radar, no detailed map, no Sonar. Only
    passive systems. So optical camera, and sound
    detectors, and environmental sensors, and
    magnetic compass.

    Tesla knows this from the very beginning.

    Translated with www.DeepL.com/Translator

  48. Concerning automation and job loss, we are a long long way off mass unemployment, and this time isnt different than past technology advancements in farming, clothes, etc which seen many people lose their jobs in those industires. Technolgy advancement reduces the cost of living and hours needed to work. Interference to stop it forces people to have a lower standard of living and work longer hours.

    Also the myth that the economy cant handle 1/2 a million drivers losing their jobs should be squashed by a brief look at history (or look up why countries can handle immigration, in part immigrants demands for food etc creates employment). Ie when millions returned from war theyre absorbed into the economy in a short space of time, roughly two years.

    So many economic fallacies based off "this time is different" mentality about the new thing to be scared off. Multiple times per century theres fear of the brand new technology and the unemployment caused from it, with zero understanding of why we've never faced mass unemployment in the past.

    For 1 work is not limited and set at fixed amount which is built into this fear assumption. If work and demand was limited there would be a point but we've a long way to go.

    Cheaper goods increases purchasing power to be transfered to other goods. New technologies employ people themselves. By reducing the cost of living you reduce the hours needed to be worked (think of how far we are from the 5hour work week and you realise how far away we are from mass unemployment), and a whole other bunch of reasons more too long to go into. In short there will be no mass unemployment, and trying to interfer and tax robots etc will only ensure the cost of living stays the same. Making technology advancement pointless.

    We dont live to work, we work to live mostly. It annoys me cause there was a bunch of economists in the 80s bringing up all these fears, and these so called experts were predicting unemployment as high as 50% come early 2000. Theyre were wrong then and every bit as wrong now!

  49. I am curious as to how effective autopilot works on snow covered roads. I have a Model Y on order and cannot wait to get it.

  50. They are both good for their goals. Waymo – (expensive with lidars) city taxis that canot go out of the mapped zone, but soon will not require a driver even for legal reasons. Tesla – drives well on highways.
    Issues with high definision maps based systems are: it is almost impossible to keep them up to date. And it is very expensive to map every road out there. People do not need high definision maps to drive. The ultimate goal is to make vision systems sufficient for driving anywhere in any situation.

  51. As always, you don't disappoint with your well thought out, insightful, educational, and informative videos. Thank you for doing the leg work for us all.

  52. Can it really be called Full Autonomy if the cars only work in carefully and thoroughly maped out places where the cars have driven for a long period of time so they after a while know every bump and every scratch on those streets beforehand?
    We are most certainly going to need those types of autonomous vehicles but what happens if, for example, something changes in the map, on the road, that the car haven’t been taught yet? I sudden hole in the road that wasn’t there before that isn’t on the updated map that the car has. What happens?
    For me full autonomy is the car driving itself from anywhere on the road to anywhere on the road and making decisions in real-time like a person would but a million times faster and safer.

    Mapping a city is like mapping out your own home, it’s not difficult if you have the time. I’m not saying what Waymo is doing is easy but if you’re going somewhere you haven’t been, and you have no map, nothing but the sensors and cameras in your car how will you find your way if you’ve never been there?

    That is the difference that I see with Tesla and Waymon or any other autonomy company that is mapping areas so they can one day drive autonomous on it.

  53. So was that your brother in the driver seat? Because you were saying nobody in the driver seat but there’s clearly somebody there

  54. I would love to have Level 5 autonomy and I would love to keep the ability to drive for leisure whenever I want to as I love to drive to unwind.

  55. Arizona is fine and dandy but until you can show one driving on the BQE, with pavement that looks like Swiss cheese, thirty feet up in the air, in New York City, and actually getting somewhere you wanna be, I'll stick with Uber.

  56. I am a commercial truck driver in the USA for 26 years I have over 2.4 million miles under my belt and I look forward to autonomy driving including semis. I have already begin preparations of a career change do do this technology it's coming very soon. I enjoy your videos you do a really good job I appreciate you

  57. Now they need to try this in NEW YORK RUSH HOUR TRAFFIC. New York needs to have infrastructure communicating back to the vehicles.

  58. One thing that he doesnt really mention in this video is the cost of lidar. Correct me if im wrong but arent each one of those sensors 5-10 thousand dollars? Arent there about 5 of them on the car? I dont think lidar is a feasible option until the cost comes down

  59. It seem like to totally missed the Tesla Autonomy Day and drunk all off the Koo Aid from WayMo. Ask your self how much WayMo current hardware and software cost and how much it will cost to customer in comparison to Tesla where your paying 6K for the hardware and software for future FSD. If jobs are being lost already then why not get on Tesla cars where your car can actually make money for your self in the future instead of big corporation 😕. There is a reason not a lot of WayMo cars are out there. You can make a big difference if the technology you have affect or benefit the broader population not just the few and corporation and WayMo is not it.

  60. Question: I was wondering if you were at "Tesla Autonomy Day." If you were – you could have taken a ride in their Full Self-Driving Cars. That would be great to compare with the experience you had at Waymo. Great video presentation-thanks!

  61. No mention of 5G. It's almost as if the telecom industry is blowing smoke up our asses when they claim that it is a necessity for FDS

  62. Matt, it will be interesting to see exactly what Autopilot really sees when activated. While I also love my Autopilot, there are times when I just wanted to be in control. The question is having that fine line between 'almost' fully autonomous driving and when the driver wants to take over. If Waymo had full BEVs, would the driving experience be even better? (smooth start/stop scenarios)

Leave a Reply

Your email address will not be published. Required fields are marked *