TMC is an independent, primarily volunteer organization that relies on ad revenue to cover its operating costs. Please consider whitelisting TMC on your ad blocker and becoming a Supporting Member. For more info: Support TMC

Elon Musk: EAP solved, on track for FSD completion in 2019 (No one else is close!)

Discussion in 'Model S' started by Bladerskb, Nov 2, 2018.

  1. Bladerskb

    Bladerskb Like how many times do i have to be right?

    Joined:
    Oct 24, 2016
    Messages:
    1,326
    Location:
    Michigan
    Elon Musk: The Recode interview

    " don’t think anyone is close to Tesla in terms of achieving a general solution for working on. You can definitely make things work like in one particular city or something like that by special-casing it, but in order to work, you know, all around the world in all these different countries where there’s, like, different road signs, different traffic behavior, there’s like every weird corner case you can imagine. You really have to have a generalized solution. And best to my knowledge, no one has a good generalized solution except ... and I think no one is likely to achieve a generalized solution to self-driving before Tesla. I could be surprised, but..."

    "The other car companies ... I don’t wanna sound overconfident, but I would be very surprised if any of the car companies exceeded Tesla in self-driving, in getting to full self-driving. You know, I think we’ll get to full self-driving next year. As a generalized solution, I think. But that’s a ... Like, we’re on track to do that next year. So I don’t know. I don’t think anyone else is on track to do it next year."

    Elon Musk is at it again with the ridiculous hype kool-aid.

    Referring to Navigate on Autopilot

    "That’s I think one of the first major steps toward full self-driving. You can enter in an address, and from highway on-ramp to highway off-ramp, the car will change lanes. It will go from one highway to the next automatically, and take off-ramp automatically. It’s pretty wild. It’ll overtake a slow car. It’s basically integrating navigation with the Autopilot capability. That’s why we call it Navigate on Autopilot, or Drive on Nav."

    Not only does NOA not do the above. What it does it only does successfully 5% of the time based on aggregate reviews. If this is supposed to be some sort of "general solution" then the supposed FSD will be laughable at best!


    While guys like Jimmy will have you believe that Tesla is actually ahead on NN. They are actually far far behind. Not only does every other company deploy NN on their lidar and camera. They are far more advanced and sophisticated than Tesla.

    "Well, the main challenge has been improving the neural net so that we can recognize all types of objects from all eight cameras. The big challenge has been solving a wide range of corner cases. So if you have a —Now we’re integrating stop signs, traffic lights, being able to do, say, hard right turns or hairpin bends and that kind of thing."

    In-fact Tesla is just now getting to add Traffic lights/signs to their network. They are still in the early stage of sensing for autonomous driving. A reminder that Mobileye (eyeq3 a 5 years old tech) had traffic light/sign detection that worked in every country.

    And yet there is "Mapping and Planning that is still untouched!" They are still fiddling with sensing. They are so behind its not even funny!

    Let me recap to you Elon Musk statements in the past

    December 2015: "We're going to end up with complete autonomy, and I think we will have complete autonomy in approximately two years." -

    Elon Musk Says Tesla Vehicles Will Drive Themselves in Two Years

    January 2016: "In ~2 years, summon should work anywhere connected by land & not blocked by borders, eg you're in LA and the car is in NY" -

    Elon Musk on Twitter

    June 2016: ""I really consider autonomous driving a solved problem," he said. "I think we are probably less than two years away." -

    Two years until self-driving cars are on the road – is Elon Musk right?

    March 2017: "I think that is about two years" -

    Transcript of "The future we're building -- and boring"

    [​IMG]


    And is it even worth mentioning cross country drive that's supposed to happen at end of 2017 and each conference call Elon says it will definitely happen in 3 months? To now its not even happening at all? Elon continues to delude and fleece the gullible, playing them like a damn fiddle!
     
    • Funny x 24
    • Like x 2
    • Disagree x 1
  2. JohnSnowNW

    JohnSnowNW Active Member

    Joined:
    Feb 13, 2015
    Messages:
    2,196
    Location:
    Minnesota
    :rolleyes:
     
    • Like x 4
    • Funny x 2
    • Love x 2
    • Informative x 1
  3. Bladerskb

    Bladerskb Like how many times do i have to be right?

    Joined:
    Oct 24, 2016
    Messages:
    1,326
    Location:
    Michigan
    Its amazing how people read Elon's post but don't see the hype.
    He's constantly talking about sensing and "detecting" stuff and all his problem situations and "corner cases" are only about sensing.
    They can't even detect traffic light and signs and yet they are about to complete FSD in 6 months.

    People don't realize that there are three different aspect of driving.

    1. Perception (Solved Mobileye Eyeq4, Waymo, etc) - This is the easiest, detecting all objects, their trajectory, speed and velocity.
    2. Mapping (Solved by Mobileye Eye4) - This is medium difficulty but using crowd sourced method solves it. It allows redundancy for localization and drive-able path to help in low visibility situations such as; blizzard / white-out, heavy rain / torrential rain, dust storm / fog, direct sunlight.
    3. Motion Planning & Control (Open Problem) - This is hard and still an open problem in the industry. This is why SDC are slow, jerky, tentative, conservative, etc. Every company is using different machine learning, statistical and probabilistic approaches. Mobileye for example uses a Model based Reinforcement Learning approach similar to alpha zero. Others like Nutonomy use a R* algorithm method, others use Markov decision process, etc.



    Notice Musk and Tesla only talks about detecting objects, the easiest part of SDC software but not the planning the hardest. No one talks about sensing any more. Mobileye stopped giving talks about sensing about 2 years ago. Its done. Solved.

    Anyone who says "neural network" in a sentence is automatically disqualified to talk about autonomous driving.
     
    • Like x 6
    • Funny x 1
  4. diplomat33

    diplomat33 Member

    Joined:
    Aug 3, 2017
    Messages:
    766
    Location:
    Terre Haute, IN USA
    Sorry @Bladerskb but I think you are going against the current. Tesla is making progress towards FSD each time they release a new update. Nav on AP may have issues but it works far better than 5%. And each time, you insist that Nav on AP doesn't work, Tesla will release an update that makes it just a little bit better. Yes, Tesla still has a lot of work to do to reach FSD but they are making progress. And, you are right to be skeptical about timelines. Yes, it is very possible that Musk is wrong about timelines. But the bottom line is that Tesla is moving in the right direction towards FSD and they are making progress. So insisting that they are not making progress, is just silly. You claim "Tesla can't do X" and then Tesla does X. You insist "But Tesla won't do Y" and then Tesla will do Y. "But, but, Tesla can't do Y good enough" and then Tesla does Y better and better. You are just fighting against the inevitable. Eventually, Tesla will get to FSD.

    And do you work for MobilEye or something?? I am just curious because it seems like each time Tesla releases an update that makes EAP a little bit better, you basically post that "Tesla sucks and MobilEye is better".
     
    • Like x 19
    • Funny x 4
    • Disagree x 2
    • Love x 1
  5. whitex

    whitex Active Member

    Joined:
    Sep 30, 2015
    Messages:
    3,796
    Location:
    Seattle area, WA
    The problem is that while Tesla is making some progress, they are nowhere near FSD. For the sake of argument, assume FSD means ability summon up to full range of the car at any time of the day or year in non-severe weather (the car will detect severe weather and find a safe parking space to weather it). I know Elon promised summon across the country, but let's give him a break and instead of 3000 mile summon, only use 200 mile summon as the indicator of full self driving complete. Do you honestly believe AP2 will EVER be able to do that? Is Elon going to send Mobile Techs every time the car detects its side cameras are getting dirty affecting their vision?
     
    • Like x 4
    • Funny x 1
    • Love x 1
  6. mongo

    mongo Well-Known Member

    Joined:
    May 3, 2017
    Messages:
    7,324
    Location:
    Michigan
    @Bladerskb so much negativity today, were you holding AAPL calls?
     
    • Funny x 5
    • Like x 2
  7. diplomat33

    diplomat33 Member

    Joined:
    Aug 3, 2017
    Messages:
    766
    Location:
    Terre Haute, IN USA
    AP2, NO. AP3 with the new chip, under non-severe weather conditions as you mentioned, YES, I do think, with the right software that it will be able to do a 200 mi FSD summon. Laugh all you want, but I think so, again, with the right software.
     
    • Like x 2
  8. Tam

    Tam Active Member

    Joined:
    Nov 25, 2012
    Messages:
    4,594
    Location:
    Visalia, CA
    I was naive about Autonomous Vehicles in general and thought it's here anytime.

    Now, I think it's a hype in general, and not just in Tesla.

    Waymo is planning fee for Autonomous Vehicles this year but it's rigged:

    It's questionable that there's no human safety officers in real life except in very rare cases like video demo and really strictly staged route.

    I do agree with Elon Musk that other companies have not caught up with generic application.

    That means none is able to use their system first time in such a scenario below of the redirection freeway flow that temporarily allows Northbound I-5 freeway to invade across the physical metal median to drive normally in the physically wrong Southbound I-5 freeway:


    [​IMG]

    Surely Waymo can do that by sending its prepped car to HD map the temporary construction section first but by the time it's done preparing, that construction section would be finished and the reversed traffic flow would by then be restored and another next different section would be allowed to flow to the wrong direction during construction too!

    Tesla is right about its generalized solutions but it might not be right about its timeline.
     
    • Like x 5
    • Informative x 1
  9. Canuck

    Canuck Well-Known Member

    Joined:
    Nov 30, 2013
    Messages:
    6,175
    Location:
    South Surrey, BC
    You had me until this point. Some of us go in knowing what to expect but still happily part with our money to buy a Tesla over all other automakers. You seem to think we have Utopian options in an imperfect world, and that catching any company in contradictions, or outright lies, means buying their product is getting fleeced and being played like a fiddle. It might help to remind you that a lot of us ordered and took delivery of our first Teslas before any AP hardware was even on a Tesla.

    In my view, you need to have a broader view, and not throw out the baby with the bathwater -- while still articulating the other good points you make.

    While you may say jokingly "Like how many times do i have to be right?" (under your avatar) -- I say in reply: “There is a grain of truth in every joke,” or “a joke is truth wrapped in a smile.” Sigmund Freud suggested that jokes were true, serving two purposes: aggression (such as sarcasm) or to expose unconscious desires (to be right all the time!?).

    In my view, it's time to come down from your high horse. I enjoyed your thorough analysis but not everything is black and white and a lot of us buy and enjoy our Teslas and don't feel fleeced or gullible at all, even with delays, things not coming to fruition, etc. In fact, 90% of us would even "buy again" -- more than any other automaker! I guess in your view there's a lot of gullible people being fleeced by Tesla, since you have to be right, many times over. But maybe Elon means well and has no mens rea? That's what I think also knowing the road to hell is paved with good intentions, so I cut Elon slack (but left FSD unchecked when I ordered my last one). Could I be wrong many times over? Of course. Will my next purchase be another Tesla? At this time, yes, since the competition is so full of crap when it comes to their desire to build long range EVs and comparable fast charging networks that they make Elon look like Mother Teresa, and that's not an easy task, as you thoroughly point out.
     
    • Like x 14
    • Love x 4
    • Informative x 1
  10. diplomat33

    diplomat33 Member

    Joined:
    Aug 3, 2017
    Messages:
    766
    Location:
    Terre Haute, IN USA
    My impression is that the critics are focused, perhaps too much, on the obstacles to getting to FSD. They see how incredibly, mind-bogglingly, difficult, FSD is so it makes them doubt that it can ever be done. The other side focuses on the progress being made and the tools such as machine learning that are making it possible to solve many of the obstacles to FSD. So we see it as difficult but achievable. Just because something is extremely difficult, does not mean it is impossible.
     
    • Informative x 3
    • Like x 2
  11. Darren Donovan

    Joined:
    Mar 25, 2013
    Messages:
    405
    Location:
    Central CA
    Then do NOT put out tweets with time estimates. We all understand how difficult FSD is. The reason many people are doubtful is because Musk keeps touting "in 2 years". It's now obvious how ridiculous his tweet was back then about summoning your car from across the country, Lol. Summon can't even be used reliably around the block or out of the garage.
     
    • Like x 4
    • Disagree x 1
    • Funny x 1
  12. Rockster

    Rockster Active Member

    Joined:
    Oct 22, 2013
    Messages:
    2,061
    Location:
    McKinney, TX
    Some people just don’t understand that visionaries set very aggressive objectives. And even by falling short of them, they crush the opposition.
     
    • Like x 14
    • Informative x 1
    • Love x 1
  13. Vitold

    Vitold Active Member

    Joined:
    Aug 10, 2015
    Messages:
    1,592
    Location:
    NM
    AP v9 is the first version with all 8 cameras enabled on a processor that Nvidia deemed inadequate for FSD.

    With AP3.0 hardware that is 10x faster I think it is fair to expect huge leap in cars capabilities.

    Add to that Karpathy’s team neural networks expertise and you have a winning combination of software and hardware. It is easy to be optimistic given what we know.
     
    • Like x 5
    • Informative x 3
    • Disagree x 2
    • Love x 2
  14. diplomat33

    diplomat33 Member

    Joined:
    Aug 3, 2017
    Messages:
    766
    Location:
    Terre Haute, IN USA
    Look, I agree that Musk should be more careful with the timeline predictions. However, to be fair, Musk is in that second group I mentioned. He sees the tools that are solving FSD problems. We know he tests the new software in his car before anyone else. So he sees EAP in his car handle an exit that it could not do before. He sees the car read stop signs that it could not read before. He sees his car auto lane change without his input in a way it could not do before. Yes, FSD is hard, but if you were seeing your team solve bits and pieces of FSD, you might get excited too and think that FSD is closer than it is.
     
    • Informative x 2
    • Like x 1
    • Love x 1
  15. Max*

    Max* Charging

    Joined:
    Apr 8, 2015
    Messages:
    6,600
    Location:
    NoVa
    It seems that the Tesla optimists are the ones that haven't been burned by Tesla promises in the past. Tesla pessimists are tired of hearing Elon over promise and under deliver.

    Does he eventually get there? Sure, with different hardware, he eventually gets to his promises. Will he eventually get to FSD? Probably. Will he be first? Who knows.

    He's running a business, he's trying to make money, if he didn't over promise and under deliver, Tesla wouldn't' be where they're at now.
     
    • Like x 7
    • Informative x 1
    • Disagree x 1
  16. D.E.

    D.E. Uncorked

    Joined:
    Oct 12, 2016
    Messages:
    367
    Location:
    Ann Arbor, MI
    We went to the US Bureau of Engraving and Printing, in Washington DC, where the US prints currency. In the room with one of the massive running printers, someone has put up a sign for the visitors, “Free Samples Tomorrow”.
     
    • Funny x 8
  17. aaron0k

    aaron0k Member

    Joined:
    Apr 1, 2013
    Messages:
    351
    Location:
    Walnut, CA
    There was a time when Elon was a little more pragmatic... 2014.

    Bloomberg interview about AP/FSD (@ 02:15). According to his time-table (2014 + 5-6 years + 2-3 years for reg approval).... we have FSD in 2021-2023.




    Then he started to really feed off the hyperbole he could create... 2017



    @ 15:30

    "Ok, so by the end of the year, you're saying, someone's going to sit in a Tesla without touching the steering wheel, tap in "New York" off it goes, won't ever have to touch the wheel by the end of 2017?" - Chris

    "Yeah. Essentially, November or December of this year we should be able to go all the way from a parking lot in California to a parking lot in New York, no controls touched at any point during the journey." <crowd applause> - Elon 5/2017
     
    • Informative x 4
  18. jeffro01

    jeffro01 Active Member

    Joined:
    Jan 30, 2013
    Messages:
    2,409
    Location:
    SF Bay Area
    There's a difference between projecting ambitious goals that you think you can reach but don't due to unforeseen circumstances and projecting ambitious goals that you know are false in an effort to drive sales/whatever. I don't for one moment believe Elon is doing the second half of that. I genuinely believe he projects what he thinks but because he can't see every obstacle on that path, his projections routinely come up short. I'd rather have ambition than apathy...

    That being said, NoA is a total and complete joke and as I've said in other threads, if this is indicative of Tesla's progress with FSD then oh boy... We're a looooonnnnnggggg ways away from anything resembling FSD... I've stopped using NoA all together because it's that bad. It could be made much better by simply disabling the stupid autosteer speed restrictions that the car gets handicapped with on freeway on/off ramps...

    Jeff
     
    • Like x 11
    • Disagree x 4
    • Helpful x 1
  19. diplomat33

    diplomat33 Member

    Joined:
    Aug 3, 2017
    Messages:
    766
    Location:
    Terre Haute, IN USA
    The problem is that they got burned so many times, they can't see the good in anything anymore. They just assume each new promise or new feature is just not another burn.
     
    • Like x 1
  20. Uncle Paul

    Uncle Paul Active Member

    Joined:
    Nov 1, 2013
    Messages:
    2,383
    Location:
    Canyon Lake,CA
    Elon is super excited to bring FSD to his customers. He sees it coming and is just as impatient as the rest of us to see it roll out.

    When he states it is coming, he believes it. Reality often slows things down.
     
    • Like x 5
    • Love x 1

Share This Page

  • About Us

    Formed in 2006, Tesla Motors Club (TMC) was the first independent online Tesla community. Today it remains the largest and most dynamic community of Tesla enthusiasts. Learn more.
  • Do you value your experience at TMC? Consider becoming a Supporting Member of Tesla Motors Club. As a thank you for your contribution, you'll get nearly no ads in the Community and Groups sections. Additional perks are available depending on the level of contribution. Please visit the Account Upgrades page for more details.


    SUPPORT TMC