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

Blog Musk Touts ‘Quantum Leap” in Full Self-Driving Performance

This site may earn commission on affiliate links.


A “quantum leap” improvement is coming to Tesla’s Autopilot software in six to 10 weeks, Chief Executive Elon Musk said a tweet.

Musk called the new software a “fundamental architectural rewrite, not an incremental tweak.”






Musk said his personal car is running a “bleeding edge alpha build” of the software, which he also mentioned during Tesla’s Q2 earnings. 

“So it’s almost getting to the point where I can go from my house to work with no interventions, despite going through construction and widely varying situations,” Musk said on the earnings call. “So this is why I am very confident about full self-driving functionality being complete by the end of this year, is because I’m literally driving it.”

Tesla’s Full Self-Driving software has been slow to roll out against the company’s promises. Musk previously said a Tesla would drive from Los Angeles to New York using the Full Self Driving feature by the end of 2019. The company didn’t meet that goal. So, it will be interesting to see the state of Autopilot at the end of 2020.

 
Last edited by a moderator:
It's not FSD though is it? It's L2 driver aids.

They just called it FSD so that idiots would think they were making progress on actual FSD.


They called it FSD because that's the name of the product. It has no general definition beyond that (it's not a term used in SAEs automation levels for example)

Idiots applying their own definitions and features to the product that the people selling it explicitly tell you, during the sale, don't exist, is the fault of said idiots after all.
 
  • Like
Reactions: GZDongles
They called it FSD because that's the name of the product. It has no general definition beyond that (it's not a term used in SAEs automation levels for example)

I don't know where you live but around here if you call something "full self driving" it better fully self drive or it's fraud. They only got away with it for so long because it's been in beta since day 1 but eventually people are going to sue them to recover their investments as their cars age and it still isn't delivered.
 
I am suppressing my "inner fanboy" because if we set expectations too high, we are likely to be disappointed.


The rewrite is Tesla's last chance at redemption on FSD.

Well Elon, let's see what you got in store! I'm bumping my hopes back up.
So Elon has gone from "3 months maybe, 6 months for sure" to "6 weeks maybe, 10 weeks for sure" in only 3.5 years? Progress? Or just a need for some headlines?
Would love to see the honest reaction to the release and their original comments.
 
  • Like
Reactions: GZDongles
Would love to see the honest reaction to the release and their original comments.

My honest reaction is this:

Before the release, I wanted to be excited but I held back my excitement just in case the release was disappointing. Hence why I posted the message that you quoted about "suppressing my inner fanboy."

After the release, I am impressed that they released so much. I did not expect that Tesla would release so many features bundled together. And I did not expect so much planning and driving policy to be done. Tesla clearly worked on a lot of stuff that they did not tell us about. I think FSD Beta is clearly capable of a lot of city driving and driving on a lot more road types than the current AP. I do consider it to be autonomous driving. But I also recognize that FSD Beta is still very unreliable compared to what is needed for driverless. So Tesla still has a lot of work to do before they can deploy driverless robotaxis. But the FSD Beta does represent an impressive start for Tesla's autonomous driving.
 
I am impressed that they released so much. I did not expect that Tesla would release so many features bundled together. And I did not expect so much planning and driving policy to be done. Tesla clearly worked on a lot of stuff that they did not tell us about. I think FSD Beta is clearly capable of a lot of city driving and driving on a lot more road types than the current AP. I do consider it to be autonomous driving. But I also recognize that FSD Beta is still very unreliable compared to what is needed for driverless. So Tesla still has a lot of work to do before they can deploy driverless robotaxis. But the FSD Beta does represent an impressive start for Tesla's autonomous driving.
Thanks for replying..
One more question.
Do you consider it a "Quantum Leap" for Tesla?
Measuring from Autopilot w/ NoA to the FSD Rewrite release
 
Thanks for replying..
One more question.
Do you consider it a "Quantum Leap" for Tesla?
Measuring from Autopilot w/ NoA to the FSD Rewrite release

Yes, I consider it a quantum leap for Tesla for several reasons:
1) The rewrite fundamentally changes how the car sees the world and responds to the world
2) The rewrite is capable of a lot more "features" than the current AP.
3) The rewrite is a jump from a driver assist system to an autonomous system.

So yes, it is a bit leap or quantum leap from the previous system.
 
Yes, I consider it a quantum leap for Tesla for several reasons

See, diplomat gives credit where it is due.

There's definitely a lot of work to be done with the FSD beta. Elon admits that as well. But we get a glimpse of hope for vision-based FSD. I never thought I'd see the light honestly.

Now that we can see some light at the end of the tunnel. I think we should take a moment to be in awe that what Elon and Tesla have done. Back in 2015 or perhaps even before, Elon and Tesla decided on a set of sensors and placements that had no proven success, stuck with it for 5 years and also designed around it for future cars, and few people and experts even believed anything about what they were saying. Look at where we are now. It's as though we've discovered alien technology :confused:
 
... Elon and Tesla decided on a set of sensors and placements that had no proven success, ...
Seemed like a blatant copy of what Mobileye was planning and advertising at that time.
From 2015:
Moving Closer to Automated Driving, Mobileye Unveils EyeQ4® System-on-Chip with its First Design Win for 2018
Mobileye said:
Engineering samples of EyeQ4® are expected to be available by the fourth quarter of 2015. First test hardware with the full suite of applications including active safety suite of customer functions, environmental modeling (for each of the 8 cameras), path planning for hands-free driving and fusion with sensors, is expected to be available in the second quarter of 2016. Series production is supported for early 2018 start of production.
 
Seemed like a blatant copy of what Mobileye was planning and advertising at that time.

Mobileye doc from Dec 2016:
Our Technology

From 2015:
Moving Closer to Automated Driving, Mobileye Unveils EyeQ4® System-on-Chip with its First Design Win for 2018
lol, there is no winning with folks like this.

What does MobileEye have to show for their "Series production is supported for early 2018 start of production."
If Tesla copied, they sure as hell are able to get much more productivity out of the sensor suite.

I guess, Tesla copied the EV concept from GM EV1 from the 90's as well.


From where I stand, MobileEye got a glimpse of Tesla's internal development while still working on AP1 stuff and freaked out and copied Tesla's sensor suite verbatim.
But when it came time couldn't provide the sufficient processing power to use the suite (a la custom chip at Tesla).
 
Seemed like a blatant copy of what Mobileye was planning and advertising at that time.

There's a lot of this dumbing down in this forum.

Just because Tesla uses vision, doesn't mean they copied Mobileye. No technology is absolutely novel. Every technology is inspired by existing implementations or ideas.

Regardless, it seems Mobileye has abandoned vision based FSD, as they are depending on HD maps, and they're also developing a lidar based FSD system as well. I don't regard use of HD maps as vision-based. All of this discussion usually just involves us chasing our own tails.
 
  • Like
Reactions: mikes_fsd
The march of 9's and how quickly we get the first ~3 of the 9's is going to determine the future/fate of all ground transportation!
I don't expect it to happen quickly. Will take some years before we get to level 3 or 4 in minimal situation. What I think is the bigger challenge, is will people fall asleep when the chance of Tesla misreading the traffic light is only 1/1000? 99.9% accurate? I don't think I can trust myself. There will be accidents. There will be deaths. Will Tesla pay millions in lawsuits? Will some governments force Tesla to improve driver monitoring? Sounds doable, but there will be some big bumps on the road.
 
Last edited:
I don't expect it happen quickly.
I didn't say it would happen quickly or slowly.

Words strung together are that way for a reason. It gives context.
Maybe if I shorten it: "how quickly we get the first ~3 of the 9's is going to determine the future/fate of all ground transportation!"

Does that help?
Just in late April, Tesla released traffic light recognition.
We saw all kinds of videos of how the feature got this wrong that wrong.
We had all kinds of bashing.
It is late October (almost exactly 6 months since the release) the FSD folks have all said it is flawless.
Even on our cars, I do not see any failures to detect or to respond (the chime is a beautiful feature) to a traffic light.

Just 6 months.
There are a lot more edge cases to consider, but traffic lights are a massive part of city driving, wouldn't you agree?