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

Possible removal of radar?

This site may earn commission on affiliate links.
More like their current radar is beyond useless for anything other than acc.

  • The radar is from 2010
  • It has major issues distinguishing stopped objects.
  • It’s only forward and has very low FOV
  • it has very low resolution and range.
  • Therefore it can’t classify objects.
  • Majority of their radar deployed is not heated so it fails in moderate rain and light snow.
I could keep going....

But ofcourse you love it. You buy and prop up anything Elon says like its the gospel. When Elon was PRing his garbage radar as the second coming It didn't stop you from talking up their garbage radar when it suited you. "Tesla found it necessary to include a front facing radar " and "Better radar is an obvious development."
Some Tesla fans even said that Tesla created Radar that was better than Lidar from Elon's PR statements.

Also weren't you the one who said, if you use maps for anything other than routing then its not true self driving? Then Tesla started using what everyone in the industry will classify as HD maps. Then you said "I haven’t seen anyone contradict what Karpathy is predicting" "Karpathy doesn't think HD maps are scalable" and their maintenance cost is expensive.

Then in Jan you admitted that Mobileye's REM HD Map were scalable and you incorrectly state that their lidar system doesn't use REM, " I'm assuming it's using LIDAR based localization with HD-maps, so it's not as scalable as their REM system.'

So you have been proven wrong at all points, they are already scaled around the world with tens of millions of miles already mapped and usable.
And the maintenance cost is basically the muscle strength it takes to push a button because they are fully automated.

Anyone with logical thinking could easily asses that Tesla's sensors is garbage for what they are marketing it as "Level 5,no driver, cross country, look out the window, no geofence".
From the forward facing side camera placement. To the rear camera being rendered useless in light rain/snow. The rear facing repeater cams being susceptible to vibrations and occlusion during rain To no bumper front camera. To their camera being very low resolution (1.2 MP).

But the same reason fans like you right after the AP2 announcement proclaimed that the half variant of Drive PX2 that Tesla used had waaay more than enough power for Level 5, that it was actually too much. That Nvidia was obviously lying that Level 5 needs more, that they were saying that for for PR and marketing reasons. That Tesla were and always are telling the truth.

But the few people in this forum who were trying to talk sense with technical analysis were drowned out by people like you.

I'm sure Elon could come out tomorrow and say all they need is their ultrasonics and you would respond with that's the absolute truth. Funny enough years ago someone tried to argue that one front camera and the ultrasonics were more than enough for level 5. Can never put anything past Tesla fans.

image02.jpg

image03.jpg

image04.jpg


si2pXOY.png
Yes, it's true. Many Tesla fans are meh. Are we sure that Hardware 3.0 will be ready for Level5?
 
Are we sure that Hardware 3.0 will be ready for Level5?


We won't know that until they either have it, or say they require additional pylons.

I personally remain dubious the sensor suite is up to the task of L5 (bad weather especially)- and even MORE dubious with the no-radar switch, but think L4 with an ODD related to bad weather might be possible.
 
  • Like
Reactions: Microterf
I'm still curious how well *vision only* will work in radars strength, judging the speed of other objects. The car in front of you, going from 15 mph in bumper to bump traffic to stopped. If the Tesla is set at the shortest follow distance, will vision be able to clearly judge "slam on the brakes" or will it begin to slow down and get in an uncomfortably close position before it realizes the vehicle is in the ultrasonic range?

Think about tight stop and go traffic. You don't want 20 feet between cars because people will constantly be cutting in, so you need to be pretty dang close which means you need to not be "eh it's trending slower based on the previous frames" but "it's 15 mph and now 6 mph BRAKE"

Again, if Tesla released data showing the vehicle add speed tags to cars around it maybe the confidence would increase a lot. Right now though it makes me wonder if it's a year or two long battle of coming up with ways to assume the speed based on the size of the vehicle (which would probably take some nifty data looking at how it's different in the different focal length cameras), then calculate how much more of the frame the vehicle is taking up in the last couple frames to determine if it's moving faster than you or slower, and then factor in your speed to assign a speed factor to the car. Sure that can happen lightning fast with computers, but it seems like it would be easier just to dumb down the radar and not have it detect objects but track speed of the objects.

Maybe have radar ignore anything that isn't tagged by the vision, but if vision expects and object directly in front of you that should be occupying a specific radar field of view, and radar sees an object that matches that description, then use the speed data from the radar.

If radar is good at determining moving object speed, use it for that. It can't be that much more expensive to keep the radar in the car....
 
Sorry if I missed that this was already posted somewhere, but @verygreen posted a link to another guy’s thread with info on the possibilities of radar removal. So this seems like the appropriate place.

Sounds like they will approximate the (mythical) memory of a goldfish for radar replacement (as of course is required), and also undistort and unify the camera images, as has been discussed publicly, to take the load off the neural nets or something. And yes, the “it’s” are very distracting.
Not really surprising at a high level, but a couple links to reading for those who are interested in Long Short Term Memory and neural nets.


Will be interesting to see how accurate they can make this...humans (if they are on their game) are so good at this (though they can only do it for one or a couple vehicles in the same direction at once, which can be a problem). And they can make (fatal) mistakes.
 
Last edited: