Welcome to Tesla Motors Club
Discuss Tesla's Model S, Model 3, Model X, Model Y, Cybertruck, Roadster and More.
Register

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

This site may earn commission on affiliate links.
Others are building HW and SW that although not perfect seems to be at par or better than Tesla’s current version. I really would like to see Tesla become the leader in this field, but I’m not convinced that they currently are.

It's all about neural net machine learning capability. Tesla is the only company that has hundreds of thousands cars on the road to collect machine learning data. That's planned for many years ago when Tesla put sensors in every car it sells whether you purchase the option or not. So far it has already accumulated 10 billion miles of data. No one else even has a plan to do the same.
 
It's all about neural net machine learning capability. Tesla is the only company that has hundreds of thousands cars on the road to collect machine learning data. That's planned for many years ago when Tesla put sensors in every car it sells whether you purchase the option or not. So far it has already accumulated 10 billion miles of data. No one else even has a plan to do the same.

I'm skeptical here. Unless Tesla is ponying up huge amounts of money to pull data over LTE, I'm not buying that they have actually captured 10 billion miles of usable driving data. Tesla is definitely not pulling that kind of data over wifi. My guess is the 10 billion is MAYBE telemetry data and some basic vehicle statistics. There is no way they are pulling miles and miles of autopilot data or some sort of "shadow mode" information from the entire fleet. Folks would be seeing gigabytes of wifi traffic every night as a result of their cars sending data to Tesla, and that is not happening. Tesla probably takes snippets of driving data and camera footage here and there, that is it.

The notion that they have millions/billions of miles from the fleet feeding a library of driving data for the purpose of machine learning, I don't buy it.
 
Completely disagree! Yes, in terms of FSD, there are companies like Waymo that have better systems than Tesla. But in terms of driver assist that you can actually use in your car now, Tesla is THE leader. Show me another driver assist system that you can buy now that can do what Nav on AP does. It does not exist. Only Tesla! Probably the closest to Tesla is Supercruise and it can't even do auto lane changes.

Even Waymo may not be as far ahead as Tesla in "general" autonomous driving technology. Waymo only runs limited number of test cars in some selected areas. The purpose is to eventually run self driving cars in those areas for driverless taxi or ride hailing service. Only Tesla is after the product that you can buy and have it to drive itself anywhere in the country.
 
  • Like
Reactions: diplomat33
I owned a P85, a P90D and now drive a P100DL. The MoblEye version worked the best as far as AP is concerned. I was told by the local Tesla salesman that my P100DL won't get a computer update when available. In fact, he told me that if I take delivery on my Model 3s now, I won't be able to upgrade them later to AP3. As a result, I will wait for the new computer hardware (AP3) before taking delivery on my Model 3s.
 
Even Waymo may not be as far ahead as Tesla in "general" autonomous driving technology. Waymo only runs limited number of test cars in some selected areas. The purpose is to eventually run self driving cars in those areas for driverless taxi or ride hailing service.
In what areas does Tesla run its autonomous cars for testing on public roads?

You have looked at the CA disengagement reports for Tesla vs. Google/Waymo, right? And, you've seen some of Waymo's numbers, right?
Autonomous Vehicle Disengagement Reports 2017
Autonomous Vehicle Disengagement Reports 2016
Autonomous Vehicle Disengagement Reports 2015
Waymo and GM still lead the pack in California’s new self-driving report cards
Waymo’s autonomous cars have driven 8 million miles on public roads

FWIW, Waymo's already been doing the bolded part in Phoenix since mid-2017: Waymo begins first public on-demand self-driving service test in Arizona
 
In what areas does Tesla run its autonomous cars for testing on public roads?

You have looked at the CA disengagement reports for Tesla vs. Google/Waymo, right? And, you've seen some of Waymo's numbers, right?
Autonomous Vehicle Disengagement Reports 2017
Autonomous Vehicle Disengagement Reports 2016
Autonomous Vehicle Disengagement Reports 2015
Waymo and GM still lead the pack in California’s new self-driving report cards
Waymo’s autonomous cars have driven 8 million miles on public roads

FWIW, Waymo's already been doing the bolded part in Phoenix since mid-2017: Waymo begins first public on-demand self-driving service test in Arizona
They don't and they haven't been. They are miles behind their schedule.
 
If the problem were the hardware then Tesla could just load a car up with a rack of processors, more cameras, radars, lidars, Tarot Cards, whatever, install the FSD software they've written, and demo it to get some real world experience. That would instantly shut up their critics, make the stock jump, and eliminate the "confusion" around the FSD option.

Maybe they're doing that somewhere in secret, but I doubt it.
What would be the point of that? If they would build a test car with lidar, four corner radars and full functioning fsd, how would this help? AP cars have one radar and no lidar. They need the solution for that hardware.
 
I was told by the local Tesla salesman that my P100DL won't get a computer update when available. In fact, he told me that if I take delivery on my Model 3s now, I won't be able to upgrade them later to AP3. As a result, I will wait for the new computer hardware (AP3) before taking delivery on my Model 3s.
Interesting, because that is the exact opposite, what Musk said in the latest CC.
 
What would be the point of that? If they would build a test car with lidar, four corner radars and full functioning fsd, how would this help? AP cars have one radar and no lidar. They need the solution for that hardware.
The problem with FSD isn't the hardware, it's the software. If they had a software load that could do FSD with any hardware, they could then either work on minimizing the hardware needed, or if not possible, adding more hardware to the car. Once you get something running, optimizing it is a whole lot easier.

The hardware is going to have to be selected based on what the software needs, not the reverse. As it is now, they don't seem to be able to do FSD at all on any hardware or software.
 
  • Like
Reactions: Kant.Ing
I never get the non believers. If I can drive a car in the rain with one eye closed surely a computer eventually can too! I do not need radar, radar is only a backup supporting device that eventually is becoming less important.

Also the thing about the cameras becoming dirty. I've never washed my cameras and still AP work ok. The only vulnerable cameras are the front cameras on the windshield which has its own defroster and is reached by the wiper. The pillar cameras never get junk directly on them and only rain that is blown past it which even keeps it clean. The rear facing cameras can become more dirty in some regions in the world but here the Dutch climate washing my car once a month if probably enough to keep these clean and so far I haven't even actively washed the lenses and never got a message that visibility was limited.

FSD will probably like how I envision AI advancements. Suddenly it will be there while most would think it would still take a long time to achieve and then the genie is out of the bottle. It could very well be that an AI advancement will have a huge impact on FSD development.

Maybe Tesla won't be the first with commercialized FSD but it will likely be the first with the largest FSD fleet and that with very low cost hardware.

All Tesla's with AP2+ wiring will be able to get a (paid) hardware upgrade where current AP2.5 FSD payers will get that package first and free. It suddenly makes that car you have for years be recycled into a super new environment friendly car that makes everyone amazed that this "old" car is capable of such a thing. What is not to like about that idea?
 
Call your senators and complain, they are the ones holding back L3 in the states. According to Amon there will be 2 million L3 cars running on Mobileye Eye4 in 2019.

But my point is, shouldn't Tesla software be more than .01%? If other companies are gunning for 2019,2020 and 2021. Shouldn't Tesla have released software that should replicate what these other companies have in-house? And for those that say Tesla is ahead. Then Tesla should have software that frankly trumps them all right?

Yet we have .01%? Something must be amiss.

Think about it. Time is running out for elon. We are 12 months from 2020. Other automakers timeline is about to catch up to him.
When this happens, what will Elon do? he can't promise anymore. It would be too shameful.

Nissan will launch more than 10 self-driving vehicles by 2020

Here's a description of Nissan's L3 Highway system for Japan that was delayed from 2018 into 2019
You have a lot of confusion over many points.

It has been pointed out many times how disingenuous it is to compare a commercially available system to those that are not and yet you keep doing it.

Then you start talking about estimates being wrong. What does accuracy of estimates have to do with what companies accomplish. Tesla and SpaceX provide hyper-optimistic estimates, miss them, but still beat the rest of the industry.

Did your elementary school teacher grade you on guessing how well you’d be able to do on a test? Did your track coach give medals to the ones who made the closest prediction to the times they ran? Exactly when did this unusual fascination with estimate accuracy first appear in your life?
 
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".

Yeah right , how about when Elon says in Twitter that off ramp on ramp is available for all of North America , 3 weeks ago , and it's still not available to Canada Model S, X, 3? He lived in Canada and is dating a Canadian. Now try and tell me he doesnt know that ALL NA means Mexico, US, Canada , Nav on EAP doesn't work in Canada. Period.

I Can't believe anything else he says, until I hear how he can make such monumental geography error. Because of this, I'm not sure anyone with AP 2.0/2.5 HW will be upgraded, to a new computer module. My confidence in Elon is being lost, slowly , gradually.
 
  • Funny
Reactions: Kant.Ing