Welcome to Tesla Motors Club
Discuss Tesla's Model S, Model 3, Model X, Model Y, Cybertruck, Roadster and More.
Register
This site may earn commission on affiliate links.
The next big milestone for FSD is 11. It is a significant upgrade and fundamental changes to several parts of the FSD stack including totally new way to train the perception NN.

From AI day and Lex Fridman interview we have a good sense of what might be included.

- Object permanence both temporal and spatial
- Moving from “bag of points” to objects in NN
- Creating a 3D vector representation of the environment all in NN
- Planner optimization using NN / Monte Carlo Tree Search (MCTS)
- Change from processed images to “photon count” / raw image
- Change from single image perception to surround video
- Merging of city, highway and parking lot stacks a.k.a. Single Stack

Lex Fridman Interview of Elon. Starting with FSD related topics.


Here is a detailed explanation of Beta 11 in "layman's language" by James Douma, interview done after Lex Podcast.


Here is the AI Day explanation by in 4 parts.


screenshot-teslamotorsclub.com-2022.01.26-21_30_17.png


Here is a useful blog post asking a few questions to Tesla about AI day. The useful part comes in comparison of Tesla's methods with Waymo and others (detailed papers linked).

 
Last edited:
Sadly 2023.27.6 has broken the ability to do voice commands (No Connectivity error). Many reboots did not resolve. Maybe it'll resolve once I let my Premium Connectivity expire.

And one dry wipe mid-day.

Had it do some surface streets and it was pretty awful about braking especially on downhills. How hard is it to anticipate and gauge how early to start slowing down? To be clear, this may not be a new development, no idea, really. Performance prior to now has been inconsistent. The jerkiness is probably improved from much earlier versions, as discussed earlier here, but friction brake use is out of control still. Ironically it seemed to use brakes much less on stop signs, the one place it would make sense to use friction brakes to improve throughput by increasing average speed.

Wife was not in the car for this one (it's been banned (on surface streets) until the next release that demonstrates significant improvements on surface streets), but certainly it would have failed the Wife Test.

Lots of work to do on the fundamentals still. If they can figure out how to go and how to stop, we'll really be cooking. Not there yet, though!

I doubt v12 will get us there, though maybe it'll somehow be more optimal. Just seems really unlikely. I can't wrap my head around how v12 will work unless it is not exactly what was advertised.
 
Last edited:
I tested turnout lane change errors today on a four-lane divided highway (TX-24 north of Commerce, TX) (not limited access) that has many left turnout lanes. I used FSD 11.4.7.2. Not surprisingly for a minor point release, the car showed no improvement over 11.4.7 and attempted to enter about half of the turnout lanes when it was to continue straight.

I noticed two interesting things that might explain what is going on. First is that the car did not activate the turn signal as it moved into the turn lane. The second was at one point I used the turn signal to initiate a lane change to the right just before reaching a left turnout lane. Even though the right turn signal was active, the car attempted to enter the left turnout lane! Third, I found that even with Minimal Lane Changes active, if the car was in the left lane, it still attempted to enter left turnouts.

From these, I infer that the car is actually not attempting to change lanes into the turnout lane, but mistakenly thinks that the turnout lane is the continuation of the left through lane. This particular stretch of highway has turnout lanes that have a more gradual opening than most, so there may be something about that that doesn't trigger an NN designed to detect turnouts.
 
I tested turnout lane change errors today on a four-lane divided highway (TX-24 north of Commerce, TX) (not limited access) that has many left turnout lanes. I used FSD 11.4.7.2. Not surprisingly for a minor point release, the car showed no improvement over 11.4.7 and attempted to enter about half of the turnout lanes when it was to continue straight.

I noticed two interesting things that might explain what is going on. First is that the car did not activate the turn signal as it moved into the turn lane. The second was at one point I used the turn signal to initiate a lane change to the right just before reaching a left turnout lane. Even though the right turn signal was active, the car attempted to enter the left turnout lane! Third, I found that even with Minimal Lane Changes active, if the car was in the left lane, it still attempted to enter left turnouts.

From these, I infer that the car is actually not attempting to change lanes into the turnout lane, but mistakenly thinks that the turnout lane is the continuation of the left through lane. This particular stretch of highway has turnout lanes that have a more gradual opening than most, so there may be something about that that doesn't trigger an NN designed to detect turnouts.
Strange thing for me is 11.3.6 did not do this as much(if at all). It wasn’t until 11.4 that I experienced these type of issues. I still think poor GPS data/accuracy is contributing to the issue.

In addition, when traveling the same road sometimes the car initiates blinker, sometimes not. At the same exact spot.
 
Maybe it just doesn't like the sound of your voice anymore. Happened to me once back in the Before Times.........

A Mad Max clip??? Especially that one... you are definitely not allowed to write me any prescriptions Doc...

I bet in real life you are the guy with the dog and helicopter from episode 2
A.k.a "The Road Warrior"
 
Last edited:
I tested turnout lane change errors today on a four-lane divided highway (TX-24 north of Commerce, TX) (not limited access) that has many left turnout lanes. I used FSD 11.4.7.2. Not surprisingly for a minor point release, the car showed no improvement over 11.4.7 and attempted to enter about half of the turnout lanes when it was to continue straight.

I noticed two interesting things that might explain what is going on. First is that the car did not activate the turn signal as it moved into the turn lane. The second was at one point I used the turn signal to initiate a lane change to the right just before reaching a left turnout lane. Even though the right turn signal was active, the car attempted to enter the left turnout lane! Third, I found that even with Minimal Lane Changes active, if the car was in the left lane, it still attempted to enter left turnouts.

From these, I infer that the car is actually not attempting to change lanes into the turnout lane, but mistakenly thinks that the turnout lane is the continuation of the left through lane. This particular stretch of highway has turnout lanes that have a more gradual opening than most, so there may be something about that that doesn't trigger an NN designed to detect turnouts.
Can you chill out on the right lane and with Max speed set at right lane traffic speed?
 
I charge to 11, because most go to 10, I get that extra push over the edge...
You just inadvertently quoted one of my heroes/idols.

“The Edge... There is no honest way to explain it because the only people who really know where it is are the ones who have gone over. The others-the living-are those who pushed their control as far as they felt they could handle it, and then pulled back, or slowed down, or did whatever they had to when it came time to choose between Now and Later. But the edge is still Out there.”….HST​

 
You just inadvertently quoted one of my heroes/idols.

“The Edge... There is no honest way to explain it because the only people who really know where it is are the ones who have gone over. The others-the living-are those who pushed their control as far as they felt they could handle it, and then pulled back, or slowed down, or did whatever they had to when it came time to choose between Now and Later. But the edge is still Out there.”….HST​

Sorry but I was referencing this, maybe the Edge was inspired by Nigel in Spinal Tap..

Edit: For those that don't already know, this scene from this movie is the reason all of our Tesla’s radios go to "11"

 
Last edited:
Teach a man to full self-drive and he'll drive for a day. Teach a man to full self-drive a fish and he'll get drunk and fall off the boat...........something like that.......
Teach a man to full self-drive, and he'll cruise smoothly for a day. Teach a man to full self-drive a fish, and he'll probably end up at a seafood restaurant wondering where the road turned into waves. Just remember, whether on land or sea, keep the self-driving to the vehicles, not the wildlife!