Separate names with a comma.
Discussion in 'Model S' started by calisnow, Apr 28, 2017.
Nits are up for the picking!!
I hope the car comes with a hibernation chamber.
HAHAHA,.. talk about circumcising a mosquito.
No one has done it with production hardware.
Gotta love the disregard for any thing factual here.
You do realize that 99.9% equal to 1 disengagement for every 1,000 miles?
If that was the hallmark of Self driving cars, google would have went public years ago.
Do you also know that humans have a driving accuracy of 99.9999% which is 1 in 1,000,000 (million) miles.
So to be 2x, you have to have a disengagement of 1 in 2 million and to be 10x you have to have disengagement of 1 in 10 million miles.
There is hardly anything magical about the hardware without the software though. Just because someone pre-ships the hardware to the market doesn't tell us much about the maturity of those that ship hardware and software hand in hand.
Unless you mean my physical car can make that self-drive in December. That would be something compared to the competition.
Yep, that's what I mean. AP2 hardware can do that drive. This is not only production hardware, but shipping on every vehicle produced.
The development of the remaining part of the stack to do a door to door drive is what is being worked on.
What makes you say this? AP1 still hasn't been fully delivered yet.
I guarantee you my car will not be self-driving any coast to coast come December 2017. But I agree if it can, Tesla will be ahead of the competition. I think you missed my point. Tesla doing this with prototype system and competition doing it with their prototype system tells us nothing of the production maturity of either.
All it tells us is Tesla pre-ships the software upgradeable hardware and others do not, but wait to ship the hardware once the software is ready. There is nothing special about Tesla's hardware. PX2 and similar are in other cars around this time as well. The hardware approach is different... But Tesla still waits to ship that important part of the system (the software) until some future date.
...so it tells us nothing of the maturity of any party. Production results is what counts. When can I do it in my car.
Agree with "Fanboy" can be used in a patronizing way, not my intention but more of how many only see the positive and dismiss the negative, usually by lack of owner experience or just having a ridiculously positive attitude, something I was born without.
It is natural for the support of the "cause", assuming you refer to "saving the planet", to subside with the expansion of the buyers, as I suspect a very small percentage of the owners were willing to buy a $100,000 vehicle thinking their purchase will actually significantly impact the environment in the big picture, at least in a generation or two, but it is a good start.
I suspect the majority of the existing Tesla owners considered that a secondary issue, behind performance, cost-saving energy source, tech, style, uniqueness, status, etc.
Just like the pricey solar roof shingles, the ROI is based on a very long period, and may be a loss of investment if the house is sold to another owner, but too early to tell.
However that is completely my somewhat cynical perspective, and may be inaccurate, but just as valid as those on the other side of the spectrum.
It is unlikely that a board swap will resolve a failed FSD attempt or regulator disapproval, as the issue will come down to the sensors, both primary and back-up.
We already learned that this type of hardware upgrading is not supported by Tesla, just ask all the HW1 owners, who dreams of anything beyond AP1 are now shattered.
Pretty stupid and extremely non exciting.
I will forever drive my car. I want my Tesla with no useless safety features and no autopilot. CPO 13-14 it is....
Oh and if you want your car to drive itself then you might as well have your arms and legs chopped off since you wont be using them to drive. And might as well just sit in a wheelchair for the rest of your life since humans nowadays are too lazy and want technology to do everything for them. ROFL.
Our brains have gotten larger but our intelligence continues to shrink.... so sad.
A board swap will resolve FSD issues related to CPU/GPU/memory or such performance/processing issues, but you are right, it will not solve anything beyond that. The lack of redundancy on the sides and rear of the car for any meaningful distance and speeds are the greatest challenge of AP2 in that regard.
And of course lack of LIDAR could be a thing, so much of the industry is betting on it, but to me the front of an AP2 seems pretty robust: three cameras, a radar (plus the ultrasonics)... it is the sides and the rear that worry me more.
Shattered dreams? Come on dude - this is so much hyperbole and drama. I have an AP1 car - I have no "dreams" to be "shattered." Nobody expected it to do FSD. Use logic here - AP2 has 360 visual coverage and a replaceable board.
There is no particular reason - other than invented worries and hand wringing of the hyperventilating nerds around here - to think that regulators won't give approval under some conditions if it is demonstrated to be safe. It may take a while but the sensors are there. There is no data on this thread - just a bunch of geeks wringing their hands.
If AP2 ain't tha ticket I'll sell mine and buy AP3. Who frickin' cares? This is the price you pay to be on the bleeding edge. HOWEVER - while there are/were obvious reasons why AP1 would never go very far there are no reasons for AP2 except, once again, data-free rants and speculation of forum nerds.
Tesla owns the software now, they built in a replaceable brain, and they have 360 degree visual coverage. At this point it is a question whether software and deep learning can get to safer-than-human in-at-least-some-conditions driving.
Time will tell. Since you are an avid poster on TMC I think we can both agree it will happen to your unique personal car and it's just a matter of when. The milestone Elon talks about at the end of 2017 isn't far away from your car doing the same thing.
And you know this - how? The issue will come down to statistics - whether or not camera-based self driving will be demonstrated to be statistically safer than human driving. AP1 got a 40% crash reduction. So far the stats are in Tesla's favor.
If the issue came down to sensors the problem would be solved already. Anyone can stack up sensors - the hard part is the software. What Tesla is doing is arguably a more challenging and ambitious approach than those using lidar to map out urban centers. Tesla is attempting to have neural networks learn to interpret visual scenes accurately enough to drive as safe/safer than a human being without precision cm maps.
The other thing Musk has in his favor is political capital - in case anyone hasn't noticed that yet. He has tremendous political capital to burn and regulators have "cover" to give him a shot at full self driving with a camera based system under some conditions. NHTSA cleared Tesla in the AP1 fatality, the 40% crash reduction statistic for AP1 has not been challenged in any serious way. Musk has a long history of doing more with less (hardware). Software is the difficult part - hardware and sensors are easy. Nobody here claims lidar won't show up in a future Tesla, that more redundant hardware won't show up in a future Tesla.
The claim is simply that Tesla will most likely (90%+ likelihood) get some kind of "you must stay awake but you can remove your hands" self driving functionality working in customer cars in city driving within a couple years on AP2 cars. Tesla has a huge amount of credibility riding on this and Musk keeps doubling down and repeating his position that cameras are all that is needed. That is a very different kind of claim to "lie" about than saying AP1 will go onramp to offramp. Tesla's entire Model 3 strategy rests on this claim. Wake up folks - this is going to happen to some extent with cameras. It's a matter of when not if.
No reasonable person here thinks our AP2 cars will be self driving by December. That's a non-argument. What we do expect (and have evidence for) is a continually improving brain that will gradually become smoother and keep adding capabilities every few months over time for the next couple years.
What none of us here know (no, not even those who earnestly study youtube videos, heh) is whether Tesla's massive fleet project is contributing to the development of self driving in a unique and significant way.
He's already backed down the Level 5 to two years.