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

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.”

https://twitter.com/x/status/1294374864657162240

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.

 

[DanCar]

Achieving reliable fsd with just cameras is impossible to me

It depends on what is meant by FSD. If you mean level 5 then that is pure science fiction and no one is getting there in the next 10 years. What do you think about the lowest bar? FSD in stop and go traffic on limited access freeway? Can limit MPH to 20 or less.

he seems very confident at this time.

Did he seem any less confident in the past 5 years?

 

[Nilroc]

“Lidar is a fool’s errand,” Elon Musk said. “Anyone relying on lidar is doomed. Doomed! [They are] expensive sensors that are unnecessary. It’s like having a whole bunch of expensive appendices. Like, one appendix is bad, well now you have a whole bunch of them, it’s ridiculous, you’ll see.” I think I'll take the advice of a guy that has had rockets land back on earth and knows the ins and outs of Lidar because Elon uses them with Spacex .

 

[powertoold]

“Lidar is a fool’s errand,” Elon Musk said. “Anyone relying on lidar is doomed. Doomed! [They are] expensive sensors that are unnecessary. It’s like having a whole bunch of expensive appendices. Like, one appendix is bad, well now you have a whole bunch of them, it’s ridiculous, you’ll see.” I think I'll take the advice of a guy that has had rockets land back on earth and knows the ins and outs of Lidar because Elon uses them with Spacex .

I loved it when Elon said that. He seemed almost angry that people were using lidar, haha. Classic Elon. Hope he doesn't swallow his words.

 

[powertoold]

It depends on what is meant by FSD. If you mean level 5 then that is pure science fiction and no one is getting there in the next 10 years. What do you think about the lowest bar? FSD in stop and go traffic on limited access freeway? Can limit MPH to 20 or less.

Did he seem any less confident in the past 5 years?

Tesla defines FSD for us through karpathy and Elon's comments. Their definition of FSD is being able to put an arbitrary point anywhere in the world and have the car navigate to that point on publicly accessible roads. I'm assuming no off-road type situations are considered in the definition.

I think that the challenge of FSD for any company is the same. The challenge isn't the sensors. The challenge is to have vision be good enough to the point where you can reliably depend on it to navigate the car. I think that vision is a necessary foundation for FSD. We require vision to make driving decisions. Any FSD approach will eventually need to read signs, identify an object as an obstacle versus something that can be run over, respond to human traffic controllers, see traffic light colors and traffic controls, etc. it doesn't really matter how many other non-vision sensors you have, you need to solve vision in order to drive in a human world.

The main challenge with vision right now is that there's not that much evidence / research to show that vision is capable of the level of accuracy and precision required to enable reliable FSD. So far, based on the evidence and implementations available, I think Tesla is the furthest in its vision system for reliability and accuracy. That's mostly the reason why I think Tesla is the furthest in pursuit of FSD. Essentially, if you agree that vision is a foundation for FSD, it's kind of difficult to say that another company is further or has more potential in vision data than Tesla.

 

[nukequazar]

Joe Schmo from cocomo, doesn't car about companies losing billions and saying they have FSD when Joe can't use FSD.
Again, Joe doesn't care what is possible. Joe cares about what is real and he can use.

In other words, FSD isn't real to most of us until it is usable. So your arguments about FSD existing are hollow.

That's one wacky argument, Dan. Joe Schmo cannot fly to the moon but flying to the moon is clearly possible and Joe clearly cares about it.

 

[powertoold]

That's one wacky argument, Dan. Joe Schmo cannot fly to the moon but flying to the moon is clearly possible and Joe clearly cares about it.

This is a wacky response as well. FSD would be relevant to Joe's daily life. Flying to the moon is an achievement for humanity, not in the same category of utilization.

 

[R1Fast]

I'm wondering about HW 4.0 and queued 3.0 upgrades. I got the EAP>FSD in the last fire sale but haven't had the 3.0 install done.

Now I'm wondering if I should cancel my appt and go radio-silence to postpone as long as possible (end of next year). Maybe then could get grandfathered into 4.0. All assuming FSD/re-write isn't shipped and street-legal by the end of next year, and assuming Tesla would honor a 2.5 > 4.0 upgrade. What do you guys think?

 

[diplomat33]

I'm wondering about HW 4.0 and queued 3.0 upgrades. I got the EAP>FSD in the last fire sale but haven't had the 3.0 install done.

Now I'm wondering if I should cancel my appt and go radio-silence to postpone as long as possible (end of next year). Maybe then could get grandfathered into 4.0. All assuming FSD/re-write isn't shipped and street-legal by the end of next year, and assuming Tesla would honor a 2.5 > 4.0 upgrade. What do you guys think?

Get the AP3 upgrade now.

 

[mikes_fsd]

I think another big issue for Tesla with the current suite of cameras is how poorly they perform at night. What was clearly seen in daytime is totally missed by the camera at night. Our eyes perform so much better in low luminance than the cameras.

These videos are almost a year old, but green posted them... what Autopilot sees vs what human sees.
Also remember that the recorded videos are very compressed where as the Autopilot computer gets HDR raw video.
Without autopilot overlays (what do you see?)
https://twitter.com/greentheonly/status/1192287875263541248
With AP overlays.
https://twitter.com/greentheonly/status/1192287994327244800

 

[mikes_fsd]

Tesla defines FSD for us through karpathy and Elon's comments. Their definition of FSD is being able to put an arbitrary point anywhere in the world and have the car navigate to that point on publicly accessible roads. I'm assuming no off-road type situations are considered in the definition.

No, Tesla defines their FSD on their website, and this is what you are buying... this has stayed very close to the same text since the reveal in October 2016 -- and can be found here: Autopilot

 

[mikes_fsd]

That's one wacky argument, Dan. Joe Schmo cannot fly to the moon but flying to the moon is clearly possible and Joe clearly cares about it.

It used to be you had to be the USA gov't, now a private citizen has bought a ride from a private company to fly him + 8 others around the moon by end of 2023. That's a pretty massive leap.


some background info: SpaceX will send Japanese billionaire Yusaku Maezawa to the Moon

 

[MXLRplus]

This is what my 2020 FSD Tesla sees:

 

[DanCar]

... So far, based on the evidence and implementations available, I think Tesla is the furthest in its vision system for reliability and accuracy. ...

From the available evidence I've seen, I would say Waymo is a couple of years ahead of Tesla. Suspect V11 will close that gap. Even if Waymo is a couple of years ahead of accurate vision, I still think Tesla will win the race because Tesla needs fewer nine's than Waymo. Waymo has a safety officer who's job is to make sure there is no blood spilled.

 

[powertoold]

No, Tesla defines their FSD on their website, and this is what you are buying...

Sure, you're right, but what Tesla aspires to achieve is told by karpathy and Elon in presentations. (See what Karpathy says at 4:20 below, lol)

From the available evidence I've seen, I would say Waymo is a couple of years ahead of Tesla. Suspect V11 will close that gap. Even if Waymo is a couple of years ahead of accurate vision, I still think Tesla will win the race because Tesla needs fewer nine's than Waymo.

In terms of vision and especially "trained" vision data, Tesla is ahead. Just my view.

 

[Nilroc]

From the available evidence I've seen, I would say Waymo is a couple of years ahead of Tesla. Suspect V11 will close that gap. Even if Waymo is a couple of years ahead of accurate vision, I still think Tesla will win the race because Tesla needs fewer nine's than Waymo. Waymo has a safety officer who's job is to make sure there is no blood spilled.

I think you don't understand the meaning of FSD and Waymo Geo Fenced Driving. Tesla Vehicles will be able to drive anywhere . Waymo is only good where they have Geo Fenced Area data . Which by the way is very very limited. Tesla compared to Waymo has Millions of cars on the road giving real driving data in the Billions of miles to the AI. Waymo has collected millions of miles to a particular Geo Fenced area.
Tesla is Way Way ahead of Waymo when it comes to FSD. LIDAR cannot operate properly in the rain or snow, as the light is scattered and absorbed by water molecules. RADAR does not have this issue as it operates at more energetic wavelengths.

 

[mikes_fsd]

Sure, you're right, but what Tesla aspires to achieve is told by karpathy and Elon in presentations.

Sure, but what you can hold them accountable for is what they SELL you (what the company tells you when you buy the product).

 

[Nilroc]

All I know is a lot of people are coming onboard with Elon's vision for the future. Stock is up to $1966.00 USD per share.

 

[mikes_fsd]

Even if Waymo is a couple of years ahead of accurate vision, I still think Tesla will win the race because Tesla needs fewer nine's than Waymo. Waymo has a safety officer who's job is to make sure there is no blood spilled.

Waymo will lose the race not because of any safety officer but because they have no addressable market that will cover all the scenarios needed to get the NN's trained against.
And with their crazy hardware requirements further limit their ability to solve the problem.

 

[DanCar]

... Waymo is only good where they have Geo Fenced Area data .

Waymo has been able to drive very well for 4+ years without geofencing. The geo fenced and mapping is to increase reliability.

Tesla is Way Way ahead of Waymo when it comes to FSD. ...

Yep, lots of people with strong opinions on this board which are later proven to be absolutely false.

 

[DanCar]

Waymo will lose the race not because of any safety officer but because they have no addressable market that will cover all the scenarios needed to get the NN's trained against.

I'm hoping everybody wins.

And with their crazy hardware requirements further limit their ability to solve the problem.

Waymo has lots of resources working on the problems. They have designed their hardware so it is redundant, not required. In other words, I'd be surprised if Waymo can't drive without Lidar.