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

FSD rewrite will go out on Oct 20 to limited beta

This site may earn commission on affiliate links.
... and we have a picture of the visualization in action

https://twitter.com/brandonee916/status/1319106273871159296?s=19

Ek5oKdWU0AImLPF


I have an MCU1 HW3 X, if cones aren’t displayed what’s gonna happen with FSD visualizations? I remember Green had mentioned MCU1 is capable of visualizations.
 
  • Like
Reactions: MelaniainLA
"It may do the wrong thing at the worst time." Oh boy! FSD might try to kill you. LOL.

Having said that, it is nice to finally get a feature list for "automatic city driving":
- Make lane changes off highway
- Select forks to follow route
- Navigate around other vehicles and objects
- Make left and right turns
Some progress at least. It's taken a long time to get here from "pending regulations" but progress?
 
I bet it has been running on our cars. 2020.40.8 and .10 enables it. Shadow mode for everyone else. 40.8 seems way better than 40.3 or whatever.

I doubt it. With 40.8, I still have adjacent trucks dancing around. I don't see anything different in terms of the visualizations. However, I do find 40.8 AP and NoA to be improved over previous versions.
 
My favorite part of this picture is the purple path prediction. The bus appears to be in the middle of a lane change, and FSD is predicting the logical path of the bus up until the intersection.
The purple dots are the physical median not the predicted path of the bus. It's showing the median narrows for the left turn lane but unclear if the bus is actually making a left turn. Here's the intersection:

sacramento.jpg

fsd visualization.png
 
The purple dots are the physical median not the predicted path of the bus. It's showing the median narrows for the left turn lane but unclear if the bus is actually making a left turn. Here's the intersection:

View attachment 601052
View attachment 601053

woah how were you able to figure out the intersection from that photo? People on the internet amaze me.
 
No, that's not what the data says. The data provided by Tesla allow no conclusion to be drawn about relative safety of Teslas with and without autopilot in use, nor does it allow meaningful comparison to other vehicles.

All it does is provide accident rates in 3 or 4 different categories:
1) Tesla Rate with AP on
2) Tesla Rate with AP off
3) Tesla Rate with AP off and no enhanced safety features (or something like that...this is from memory).
4) Rate for all other vehicles.

There's no way to compare these numbers in any meaningful way. A whole bunch of other information would have to be provided.

I agree they can't be compared with any other numbers, but can't they be compared with themselves? If the same methodology is used and the rates are trending down, that implies progress no?
 
woah how were you able to figure out the intersection from that photo? People on the internet amaze me.

I was thinking the same thing. Too lazy to put on pants (I'm just assuming, since I am now that I work from home!), but no problem figuring out the exact location an image was taken to prove the purpose of a purple dotted line, just cuz. The internet is truly amazing.
 
  • Like
Reactions: NHK X
I agree they can't be compared with any other numbers, but can't they be compared with themselves? If the same methodology is used and the rates are trending down, that implies progress no?

Yes, Q3 number can be compared with Q2 number of the same statistic. However, given seasonal fluctuations it’s probably better to compare year to year for a given metric. And even then, the numbers could be a bit foggy. For example, 2020’s stats may be skewed because of COVID. Far less traffic on the road, and far fewer total miles driven.