I get better range estimates post my trips that are full FSD vs when I drive it myself.Keep an eye out! You’ll see it.
My particular test was at night, no other vehicles, unmarked residential streets.
You can install our site as a web app on your iOS device by utilizing the Add to Home Screen feature in Safari. Please see this thread for more details on this.
Note: This feature may not be available in some browsers.
I get better range estimates post my trips that are full FSD vs when I drive it myself.Keep an eye out! You’ll see it.
My particular test was at night, no other vehicles, unmarked residential streets.
No. There are a variety of issues. See V11 threadSo, are we really at a point where the biggest issue with FSDb is how comfortably it slows?
Er, when was the last time you were on a plane as it landed???
I don't think anything being discussed here is likely to have a particularly significant effect on range.I get better range estimates post my trips that are full FSD vs when I drive it myself.
WhyI get better range estimates post my trips that are full FSD vs when I drive it myself.
Such as the fact it will use regenerative braking more and better than when I drive it myselfObviously the energy screen is highly dependent on many factors which will far outweigh any tiny amount of friction brake use.
I would rank how well FSD slows down as just about my lowest priority.So, are we really at a point where the biggest issue with FSDb is how comfortably it slows?
It does not matter how much Tesla trains FSD using Tesla Vision. When the cameras get wet in heavy rain, FSD at first will slow down 10 mph and later if the cameras cannot see, FSD disengages.Do people think Tesla has trained end-to-end so far on clear weather data or more that heavy rain situations require significantly more variety of data to behave correctly? I experienced 11.4.9 neural networks failing for Moving objects but were fine for Lanes with what showed up as a relatively small blurry patch on the main camera:
FSD used to disengage, but doesn't anymore. Regardless of how hard it's raining.It does not matter how much Tesla trains FSD using Tesla Vision. When the cameras get wet in heavy rain, FSD at first will slow down 10 mph and later if the cameras cannot see, FSD disengages.
What firmware version and hardware version (HW3/HW4) are you on?FSD used to disengage, but doesn't anymore. Regardless of how hard it's raining.
I have seen it slow down 20mph under the speed limit.
I have 2 cars on HW 3 at 2023.44.30.7, but even when the wipers wouldn't work in a hurricane on older revisions of v11, it hasn't disengaged.What firmware version and hardware version (HW3/HW4) are you on?
My favorite is when I doing 75 and there’s a 55 speed zone and it slams on the brakes with a car behind meFSD used to disengage, but doesn't anymore. Regardless of how hard it's raining.
I have seen it slow down 20mph under the speed limit.
Hasn't happened since FSD Beta took over the AP stack. Are you on FSD Beta?My favorite is when I doing 75 and there’s a 55 speed zone and it slams on the brakes with a car behind me
Agreed. Now it will slam on brakes if a truck is beside you.Hasn't happened since FSD Beta took over the AP stack. Are you on FSD Beta?
This is incorrect as well. It will shift in the lane away from the truck, and then shift back to center as it passes the truck. That is the correct behavior.Agreed. Now it will slam on brakes if a truck is beside you.
Mine on both cars slams on brakes, every timeThis is incorrect as well. It will shift in the lane away from the truck, and then shift back to center as it passes the truck. That is the correct behavior.
Mine does not, and mine is the correct behavior. When you mention poor performance, like slamming on the brakes when you are near a truck, make sure you say "In my experience" or "My car...", etc. Otherwise you're making a declarative statement as if the entire fleet experiences this. It does not.Mine on both cars slams on brakes, every time
And from other groups, it's common behavior
The most likely scenario is that the entire fleet will experience this occasionally if several users have noticed the behavior.Otherwise you're making a declarative statement as if the entire fleet experiences this. It does not.
How do you think an end-to-end control system would predict or make use of a motion profile when driving? Are you expecting some C++ heuristics to do that as some post-processing of the neural network outputs basically limiting or smoothing out deceleration?There should not be anything special needed for other vehicles. Just slow down correctly and use the brakes if necessary to match the desired profile.
Mine works like yours and it even rained in SD a few days ago and my wipers finally worked correctly.Mine does not, and mine is the correct behavior. When you mention poor performance, like slamming on the brakes when you are near a truck, make sure you say "In my experience" or "My car...", etc. Otherwise you're making a declarative statement as if the entire fleet experiences this. It does not.
Again, it's a commonly reported issue since v11 released along with the car entering turn lanes.Mine does not, and mine is the correct behavior. When you mention poor performance, like slamming on the brakes when you are near a truck, make sure you say "In my experience" or "My car...", etc. Otherwise you're making a declarative statement as if the entire fleet experiences this. It does not.
Yeah either that or use only good examples for training for v12.I could see how a motion profile could be used during training for end-to-end,