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

Instead of calling it FSD should we call 10% self driving?

This site may earn commission on affiliate links.
I does sound like they gave up on real FSD though, I mean why else delete all mention of it?
I think they determined that City Nav on AP wasn't enough to sway folks to buy FSD. At least now they are putting actual features under FSD instead of some pie in the sky vagueness that they had before (which is amusing because I think the feature set for FSD hasn't changed they are just explaining it a different way). I just wish they would have done this or at least better explained this when they removed FSD from the configurator the first time.

I could be wrong though...
 
City Nav on AP isn't going to truly happen imo. Think about 2 way stops (where the other 2 ways don't stop), double lane left hand turns without intersection striping, legal rights on red, - these are common and challenging situations that I don't think even faster internal hardware will solve. I think it's possible that there simply isn't the external sensor suite to make these things possible - look at what Waymo, the leader in Level 4 and 5 automation needs.
 
I think I have figured out what Elon means when he says Full Self Driving is close. It means the the alpha version of the software currently running on his car does a lot more stuff than the last version he had on his routine drives. Somehow I doubt he has time to drive in nasty road construction areas or serious highway accident zones or blizzard snow storms or unmarked country roads or any of the million other edge cases the current software is not even close to handling.

So, yes, I agree with OP. Although Tesla is making serious progress with EAP and I enjoy using it on highways, based on my experience with NOA, they are closer to 10% Full than 100%. That said, I do prefer to view the glass as 10% Full rather than 90% empty.
 
  • Love
Reactions: OPRCE and DanCar
To me, AP needs to be 99 percent rock-solid reliable before you'll get me to velieve FSD is close. On highways I'd say it's 90 percent reliable and city streets maybe 50-70 percent reliable. Those are huge, huge gaps to bridge as the work is harder as the system gets better.
I think the moving of NoA to FSD is going to make talking about AP (EAP) more convoluted.
 
City Nav on AP isn't going to truly happen imo. Think about 2 way stops (where the other 2 ways don't stop), double lane left hand turns without intersection striping, legal rights on red, - these are common and challenging situations that I don't think even faster internal hardware will solve. I think it's possible that there simply isn't the external sensor suite to make these things possible - look at what Waymo, the leader in Level 4 and 5 automation needs.

What's difficult about any of the situations that you describe? What do you see that a camera-based system can't 'see' in any of those situations? The only one that seems maybe a little iffy is the 2-way stop, since you're essentially relying on the ultra-wide angle camera to see cars coming... and we don't really have a way to 'look' left/right.
 
Will FSD be able to handle a roundabout / traffic circle ? Right now, EAP cannot.

Tesla claims FSD can do that. tesla.com/autopilot says:

Full Self-Driving Capability
All new Tesla cars have the hardware needed in the future for full self-driving in almost all circumstances. The system is designed to be able to conduct short and long distance trips with no action required by the person in the driver’s seat.

All you will need to do is get in and tell your car where to go. If you don’t say anything, the car will look at your calendar and take you there as the assumed destination or just home if nothing is on the calendar. Your Tesla will figure out the optimal route, navigate urban streets (even without lane markings), manage complex intersections with traffic lights, stop signs and roundabouts, and handle densely packed freeways with cars moving at high speed. When you arrive at your destination, simply step out at the entrance and your car will enter park seek mode, automatically search for a spot and park itself. A tap on your phone summons it back to you.
 
City Nav on AP isn't going to truly happen imo. Think about 2 way stops (where the other 2 ways don't stop), double lane left hand turns without intersection striping, legal rights on red, - these are common and challenging situations that I don't think even faster internal hardware will solve. I think it's possible that there simply isn't the external sensor suite to make these things possible - look at what Waymo, the leader in Level 4 and 5 automation needs.

I totally agree. The current sensor set does not seem sufficient to deal with even moderate level complexity. Probably will tap out at 5 on a 10 point scale. This is based on my recent experience with EAP on freeways and side streets plus some basic level of info on new sensor technology.
 
Tesla’s FSD order page says:
Summon: your parked car will come find you anywhere in a parking lot. Really.

I don’t have EAP or FSD. But when I had the EAP trial in December, I thought Summon simply moved the car forward or backward. But this description sounds like the car will navigate itself to you weaving through the parking lot. It Is listed as a currently available feature, not as “Coming later this year” feature. Does this thing really work?
 
I agree full self driving when I can climb into the back seat and go to sleep is years away. On the other hand right now my model 3 drives itself 80% of the time and does a good job. I will never go back. I paid the extra 2k (current eap owner) to get the hw3 processor and continued fsd enhancements. I want to go from 80% to 90%. At some poibt soon it will be 'good emough '