To the posters that wrote they expect a "free upgrade" to HW4, do you expect a "free upgrade" to your A# chip every time Apple releases a new one? I didn't think so...
(As an owner I want one, too. As an investor, I don't want us all to get it without paying for it - see the difference?)
Currently, those are the same thing.
Every tesla has the same driving sensors.
Nor does it make sense from a programming or support perspective to have two entirely different software streams.
Tesla supported two 100% different streams and software stacks when they dumped Mobileye and went in-house to control this mission-critical tech.
They already have two entirely different neural network software streams. Otherwise, what are they doing with the data coming from the LIDAR sensors?
They either have them connected to a second HW3 or HW4 board in the test mule running a modified NN (Neural Network). More likely, HW4 supports additional inputs and has the processing power so the LIDAR is connected to the same HW4 board as the optical sensors are.
How do humans drive in the rain, when all they have is vision sensors?
Human eye corneas do not have rain driving at them at 60+ mph like the glass that covers the video input sensors. We have fast windshield wipers to give us a slower frame rate than normal. Our brain fills-in the missing frames and decides what to do downstream a different part of our brains.
The vision-only system didn't exist in 2017, so I'm not sure you really "know" what you think you do.
Everyone is speculating at this point. "Vision-only" just means no input from the frontal radar collision-avoidance sensor, so they rely totally on CNN object classification and the frame by frame comparison which allows them to model the relative positions of the objects in 4-d space.
The very first vision-only cars to go into production were just a few months ago.
Prior to that they were using a fusion of vision and radar.
agreed. It was mostly vision except for radar in front of you. they still read the ultrasound sensors. that hasn't changed.
So yes- they absolutely need to compare, since they're now using vision for distance measurements they were, until fairly recently, using radar for.
true. that's a good thing since that's what we humans do with our stereo vision.
Not sure how that's relevant. They're not going to be used in production regardless of size.
Agree. LIDAR will not be used in "production" consumer vehicles where the liability for FSD is on the driver and not Tesla. For Tesla Network, obviously, the liability has to be on Tesla. If adding LIDAR gives those vehicles a safety advantage (compare vision with LIDAR downstream for a lower error rate), then I believe Tesla will use it. We can be fanboys, but we don't have to drink the Kool-Aid and believe every word that comes out of Elon's mouth - Tesla will never use LIDAR (e.g. driving cross-country hands-free a few years ago, etc.)
Everyone else was making gasoline cars.
Why didn't Tesla do "what everyone else" was doing?
This is irrelevant to LIDAR possibly being used in future Tesla Network Tesla-Owned vehicles, as is the next point about "tons of parts", and firmware updates.
Everyone else was still making cars with tons of parts, all from a slew of different suppliers- driving up costs and complexity- instead of vertically integrating and reducing # of parts whenever possible.
Why didn't Tesla do "what everyone else" was doing?
Everyone else requires you to come into a dealer to get any software updated on the driving side of things.
Why didn't Tesla do "what everyone else" was doing?
Could go on like this for a while--- but hopefully you get the point.
The key to Teslas success so far has been their not doing what everyone else is doing.
Agree in many (most?) instances that is true. Tesla's innovations in multiple areas have totally disrupted the surface transportation industry.
Correct.
Which is why they're not adding LIDAR.
If you solve vision, you get nothing additional from LIDAR.
Besides solving vision, they need to solve mud splashes, water, etc. obscuring the glass covering the sensors, not to mention snow blizzards and fog.
If you have NOT solved vision then LIDAR is just a crutch to cover up that your system sucks.
I don't think Waymo and others are morons using LIDAR, do you? I think their weakness is they do not have the real-world model training that $TSLA does from our crowd-sourced vehicles.
Let's agree to disagree on some of these issues and watch and learn what Tesla is up to on August 19 from Elon and Andrei.
Like last time, the main audience will be Wall $treet analysts. This event is mostly designed to impress them and drive up $TSLA, which I'm 100% in favor of!
