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

Will Tesla need to retrofit side facing cameras?

This site may earn commission on affiliate links.
pseudo radar is marketing terminology.

I'm quite sure that this was a money-based decision and not one based on tech or safety.

its probably the #1 reason why I will not get another tesla.

less sensor input is the WRONG way and I'm quite sure of it. they can't get it working, but that's more a statement of the company than what's actually possible.

they have had about 10 years and they have not solved some of the most basic safety issues (braking, for one).

before REDUCING sensor richness, first solve the basics. and you dont solve them by throwing data OUT.

sheesh.
 
Yes. It does not know when it can't see. That's what humans do differently, we decide to adjust our eye position or car position. In some cases we creep forward to take a peek and quickly reverse. Sometimes we have to get out of the car and take a quick look or get someone else to look for us. If we really can't see and it's too risky we just don't go that way. I've done all those things at various times.

Yup, good drivers do all those things if necessary.

FSD has been shown that it often just goes when it doesn't know it can't see.

Yup, this is exactly what bad human drivers do that causes accidents.



That's a strange logic: "it must be safe if I can't tell that it's unsafe".

Very unsafe.
 
pseudo radar is marketing terminology.

I'm quite sure that this was a money-based decision and not one based on tech or safety.

You seem to be sure about stuff that's factually wrong pretty often.

The radar they were using is a very cheap part. But it made the system worse.

An actual technical person explains this in considerable detail here:



its probably the #1 reason why I will not get another tesla.

less sensor input is the WRONG way and I'm quite sure of it.

Where did you get your degree in machine learning or AI? How many papers have you published or had your papers cited in others on the topic?

I ask because the guy in the video has a PhD from Stanford in the field and has published or been cited in tens of thousands of papers on AI and machine learning.


Since you're "quite sure" he's wrong, with what qualifications do you conclude that?


they have had about 10 years and they have not solved some of the most basic safety issues (braking, for one).

Tesla hasn't even been mass producing cars for 10 years.

And has only been working on their own stand-alone driving solution for about 5 years... (AP2 was revealed October 2016, for the ~2 years prior to that they were using a 3rd party solution from Mobileye, and prior to that using nothing at all)

Seems you can't get a calendar working :)
 
  • Like
Reactions: firsttruck
pseudo radar is marketing terminology.

I'm quite sure that this was a money-based decision and not one based on tech or safety.

its probably the #1 reason why I will not get another tesla.

less sensor input is the WRONG way and I'm quite sure of it. they can't get it working, but that's more a statement of the company than what's actually possible.

they have had about 10 years and they have not solved some of the most basic safety issues (braking, for one).

before REDUCING sensor richness, first solve the basics. and you dont solve them by throwing data OUT.

sheesh.


For over a hundred years, good human car drivers successfully gauge distance of other high-speed vehicles good enough to have few accidents all without having radar or lidar.
 
He specifically mentioned it along with HW4 during the AI day presentation







No, they legally could not.




They couldn't do that unless they could provide evidence of active efforts to do so.

Which would be impossible if the problem is only solvable with hardware obviously
So I'd like to see your proof that "the problem is only solvable with hardware".
 
So I'd like to see your proof that "the problem is only solvable with hardware".

Uh...the literal words to which you originally replied, and you yourself quoted, said

Post you replied to said:
If they decided it's needed for FSD

So not sure why you're pretending someone had "proof" it was required.

They said IF it is required THEN Tesla would need to either refund or retrofit legacy owners.

Since BY DEFINITION it'd be a hardware solution.
 
For over a hundred years, good human car drivers successfully gauge distance of other high-speed vehicles good enough to have few accidents all without having radar or lidar.
what are you trying to prove by that comment?

Since millions of drivers successfully complete the job without having collisions despite not having radar or lidar sensors, it seems like radar or lidar sensors are optional and not mandatory for successful completion of the task.

its void of any technical content.

It is pretty simple. Why is more technology needed to explain.

Those that claim radar or lidar is required are the ones who need to explain why.

oh, right, you are a fan. gotcha.

You can Go Cheney yourself.