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 or making a Paypal contribution here: paypal.me/SupportTMC

Full Autonomy: How long? How important to SP?

Discussion in 'TSLA Investor Discussions' started by LargeHamCollider, Oct 14, 2016.

  1. LargeHamCollider

    LargeHamCollider Battery cells != scalable

    Joined:
    Jan 10, 2015
    Messages:
    471
    Location:
    United States
    Apologies to those who had to watch the back and forth in the ST thread the other day, I'm usually one who advocates not responding to our trollier users... but I... just... couldn't... resist:oops:

    I do think autonomy is the most important technology for the future of the automobile, I also think it's clear that Tesla has a significant lead here wrt existing products. I also believe, but can't prove, that Tesla has the best team and is making the fastest progress toward autonomy; I can't prove this, but I think the following are good reasons to believe it:

    1) Their existing system is the best, despite having far fewer hardware resources than some other systems.
    2) Their existing system is the best despite the fact that other companies have been working on lane-keeping systems for much longer than Tesla. For example Nissan first introduced lane keeping in 2001, Toyota in 2002, Honda in 2003.
    3) Tesla has, in general, made it a higher priority than other manufacturers.
    4) No other auto company has equal access to software talent due to Tesla's proximity to Silicon Valley and Elon's star power.

    In addition to having the best system and making the fastest progress, Tesla's ability to issue OTA updates gives them a 1-2 year advantage over competitors as I think it's clear that the hardware is easier than the software (sure, you could have the dealership update firmware, but this is pretty kludgy and will become unwieldy when new safety related fixes are constantly required). It may actually be the case that realtime OTA updates are *required* for *any* autonomous vehicle in the future as it may be that a current database of all regulatory traffic signs/signals will be required in some countries for all autonomous vehicles.


    Anyway I think understanding the tech involved will help people understand exactly how plausible full autonomy is at the present time. It's going to be a big day when the first transfer of liability from owner to manufacturer takes place. Below is an update of my first post on the topic from the ST thread, which I wrote hastily while in a meeting.

    ...Full autonomy is coming, I think in 5 years or less, probably less. That doesn't mean full autonomy on every road on planet earth, or on every road in the United States, it only means full autonomy on some usefully large subset of roads, probably starting with US interstates. I think the following technologies in combination, are sufficient for full autonomy.

    1) GPS with SBAS (and soon LBAS) reliably gives accuracy greater than 12 inches, I see this accuracy every week, I fly aircraft that have it. This in combination with high precision maps will give the vehicle great situational awareness with regards to position on the network of streets. Vehicles will have redundant GPS systems.

    Tesla actually has the ability to create their own LBAS system by using preset points on roads every 20 miles or so that have a precisely known location and that are identified by the camera system, I'd guess the camera system will have accuracy to a couple inches which means that the GPS signal can be corrected to within a couple inches.

    2) Redundant binocular (+) camera systems will paint a 3D picture of the surroundings, recognizing lanes, vehicles, pedestrians, animals, street signs etc. This is the hardest part, machine object recognition has only recently surpassed that of humans.

    3) Redundant radar systems will paint a 3D picture of the world that complements that of the binocular (+) camera systems. They will also see through some objects that the binocular (+) camera systems cannot and will give some density information allowing the system to distinguish a plastic bag blowing in the wind from a truck tire bouncing towards your face.

    4) Ultrasonic sensors give a tertiary system for verifying objects that are near the vehicle.

    5) Inertial navigation system, off the shelf GPS systems only update 10x per second you can get quicker systems but they're expensive. The inertial system will smooth GPS data and fill in for it in areas with poor GPS reception. These systems can have very high sampling rates, over 1000Hz.

    6) Large database of relevant data including a complete roadmap, traffic signs/signals, obstacles, lane width, number of lanes etc.

    7) Massive processing power: nVidia's PX2.0 has almost exactly 1000x the processing power of the Tegra 3 currently powering AP 1.0. They will need to have Redundant processing systems. [edit] User MP3Mike says autopilot does not use the Tegra 3, this may be the case, I believe it has more processing power than any other onboard chip but perhaps not.

    It seems to me that ALL the technologies required to make a vehicle autonomous already exist. They just need to be combined with the right logic, I don't think this will be as difficult as some software problems that have already been solved.

    If the above is correct, or in the vicinity of correct, it has serious implications for the value of Tesla. We've all seen the speculation about how the economics of personal transportation will change, given autonomy, from Adam Jonas and others. I suspect Tesla will get an autonomous capable product to market 3 or more years before the next competitor, and will continue to have a superior (read safer) solution with the ability to operate autonomously on a higher percentage of streets for some time thereafter. The value of such a lead is quite big, I don't think it's fully priced in at this moment.

    All that said it's entirely possible I've missed something, I've never personally worked on an autonomous vehicle, if @electracity, @myusername or @Value Ev or others believe Tesla will run into some problem that will take 10 years to solve, then tell us what that problem is.
     
    • Like x 1
  2. Rarity

    Rarity Member

    Joined:
    Jan 29, 2009
    Messages:
    208
    If you're talking full autonomy, there is a different set of competitors to the traditional auto companies: Google, Uber, Otto, Apple, Comma.ai, etc. So #1-#4 don't apply. Maybe Mobileye will work its way into the mix.
     
  3. LargeHamCollider

    LargeHamCollider Battery cells != scalable

    Joined:
    Jan 10, 2015
    Messages:
    471
    Location:
    United States
    These are additional competitors but we have less visibility into what stage these guys are at, Apple may come out with a killer product and production capacity of 2M/yr in 2019... but the probability of this happening is difficult to assess.
     
  4. Value Ev

    Value Ev Middle seat belt specialist.

    Joined:
    Oct 5, 2016
    Messages:
    354
    Location:
    California
    If I knew of problems that would take 10 years to solve in AP, I would be talking to Tesla, MB, industry events, etc, not posting on some board.

    I think the "interesting" problem is one that has been mentioned before: in accident avoidance does the car plow into the 1 person in the crosswalk or the 2 bicyclists on the side of the road and if the car is making that choice is there any legal recourse for that decision?

    BTW, name calling makes you a "trollier user".
     
    • Like x 1
  5. habanero69

    habanero69 I Dont Need Cialis. I Drive an EV.

    Joined:
    Jul 29, 2016
    Messages:
    255
    Location:
    FLorida
  6. dakh

    dakh Member

    Joined:
    Jun 14, 2015
    Messages:
    610
    Location:
    Seattle, WA
    I don't see much of a point in spending bytes on this here. We have no actual experts on the subject, best we can do is amateur speculation. Yes the problem is hard. Yes solving it will a very big deal. Yes Tesla is well positioned to get it done first. Just wait and see.
     
    • Like x 1
  7. bonaire

    bonaire Active Member

    Joined:
    Aug 24, 2013
    Messages:
    1,505
    Location:
    USA
    Full autonomy probably would have not hit the brakes and slowed enough to fix the issue I had this morning.
    Saw a group of young deer by the side of the road on a 35 mph road. I slowed initially and jammed on the brakes further as I got close to the bunch. One darted out in front of the car, I hit it broadside and it rolled a few times and was able to run off. Zero damage to the car. Autonomy would kept 35 mph speed and not considered the risk until deer would have reacted and probably ended up hit at a mortal speed. Today's cars mean that is $1000-5000 in damage if things like bumpers, electronics, hood and windshield is damaged by a deer-strike.

    One deer saved by human reaction. And it's the 2nd one I've hit with the car - extremely slight damage in the first case and the deer also ran off in that case due to braking before impact on another 35 mph road.

    Autonomous just doesn't seem useful for a manned vehicle. Good for maybe cross-country automatic trucks which will just drive and drive until the fuel is spent and needs refueling. But for anything off major highways, I doubt it will do us much positive good. Full autonomy will allow for fully-blind drivers to get on the road (Google already has a story about this) and also others with major disabilities. But I don't want autonomy to be our answer to letting us "text more and let the programmers take over for our responsibilities".

    Assistance such as emergency braking is fine. But no computer can see a driver look over his shoulder and "know" the guy is about to change lanes without using a signal. That's the Detroit Blinker. Turn your head and others are supposed to know you're changing lanes.

    I'm one who believes full autonomy is being done for one reason. Labor savings. Skip paying taxi drivers. Skip paying long distance truckers. Skip paying fork-lift operators and do it by computer. Bus drivers too for city routes. Literally tens of Billions of dollars annually of American labor costs are associated with driver pay. I soundly believe we are trying to "automate" more jobs out of existence.
     
  8. MitchJi

    MitchJi Active Member

    Joined:
    Jun 1, 2015
    Messages:
    1,886
    Location:
    Marin County, CA
    #8 MitchJi, Oct 15, 2016
    Last edited: Oct 15, 2016
    Big assumption that might not be correct. I do agree that Tesla is focused on this in a way that along with Elon's presence makes their advantages considerable.

    If it's that easy why won't everyone else be able to do it just as quickly?

    I also believe Tesla will be first and I agree with your other reasons.

    You've done a good job of describing some reasons why full autonomy is a difficult problem to solve. But many experts believe it's a solvable problem, including Elon. You know more than all of the experts who believe that the problems you described can be solved? Or do you think that nobody else is aware of those problems?

    As to timing I believe it's going to get to 80-90% pretty quickly. I'm much less confident on the remaining 10-20%.
     

Share This Page