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

Let the hacking begin... (Model S parts on the bench)

This site may earn commission on affiliate links.
I've been saying this since day 1 as well, but no one seems to listen or care. The cameras are basically useless in even minor rain/fog/etc. If they would have included, at a minimum, the rear corner radars, then I would have given them the benefit of the doubt. There's absolutely no way the currently hardware+sensor suite can get close to FSD without absolutely perfect conditions.

But seriously, just try to use your backup camera when it gets just a little wet. Then cover all of your windows and try to drive using just that. God speed.

The dynamic range on the cameras is impressive, but it's still not good enough to see many vehicles approaching on the sides/behind when it's dark outside. It's easily fooled by lights in the distance and other things and lots of the time won't detect a vehicle until it's basically within reach-out-the-window-and-touch-it distance. Radars would have solved that, since they'd have a reference to go with for the limited visual data.

But nothing will make this hardware/sensor suite work well in the rain. It can do autosteer ok in the rain right now because of the forward radar augmenting the forward vision data. Beyond that, FSD isn't happening in the rain/snow/whatever. So, you'll set a course in your FSD Tesla when it's sunny, 5 miles down the road an unexpected Florida sun-shower pops up, and the car will be screwed.

I guess Tesla still hasn't figured out that not everyone lives in California. Pretty obvious in my Model 3 with the latest firmware where today I had to just constantly keep hitting the wiper-swipe button for intermittent wipers, despite being set to AUTO the whole time. The windshield basically has to be covered in rain completely to the point where you can't make out a car directly ahead before the auto wipers come on.

Lost a lot of faith in Tesla on this stuff over the years. Over sell, under deliver. All of the time with minimal exceptions.
And knowing that you purchased a Model 3 anyway.
 
  • Funny
Reactions: AnOutsider
Do we know yet how an optimized neural net will process those rainy/foggy images compared to a human? I wouldn't rule out that there is some signal in what looks like noise to us. Nvidia's '16 DRIVENet Demo was pretty impressive in this regard[1], and obviously these things only get better with more data.

Certainly AP2-3 won't work in all conditions, but I think it's too early to say where the point is at which (current sensors + optimized software) will be statistically less safe than a human driver. That's based on what I know at least, but maybe not on what you know.

[1] See 7:20
AP2+ does pretty decently in the rain in my opinion also there's no accumulation of water on the cameras (except the backup one) - something feared for the longest time:


 
AP2+ does pretty decently in the rain in my opinion also there's no accumulation of water on the cameras (except the backup one) - something feared for the longest time:



Interesting video, thanks for sharing!
In the top video at 6:00 and 6:34 it looks the rear looking repeater cameras have large pools/ drops of water forming that the camera is imaging through.
 
Anyone try anything like RainX on the cameras?
what you see is with RAIN X.

In the top video at 6:00 and 6:34 it looks the rear looking repeater cameras have large pools/ drops of water forming that the camera is imaging through
There's a bit of that, but does not seem to impede operations much. Even the backup cam surprisingly sees a lot through all that water.
 
And knowing that you purchased a Model 3 anyway.

Of course. Best cars available today still... not really any doubt there. But, if you check my invoice, you'll not see me donating any money to Tesla for the non-existent full-self-driving stuff... so, not sure how your comment is related to my post. Just because the company is shady af with their marketing doesn't make the overall product as it sits all bad.

AP2+ does pretty decently in the rain in my opinion also there's no accumulation of water on the cameras (except the backup one) - something feared for the longest time.

Interesting video, thanks for sharing!
In the top video at 6:00 and 6:34 it looks the rear looking repeater cameras have large pools/ drops of water forming that the camera is imaging through.

Yeah, I was just about to say that in the 6-7 minute mark, the repeaters look pretty useless. Calculated free space easily jumps into the space that is clearly not free space and other data is clearly just noise in those sections (lane markings, for example). The truck that pops into view is only labeled in about 1 out of 3 frames, too, in a part that's not even as bad. The pillar cams staying clear, though, is a good thing, though, and the front cams are a given (wipers to clear them plus radar to augment the data).

Honestly, just seeing that at least 3 of the 8 cameras are giving somewhat useless data at times in what looks like somewhat minor rain... is not confidence boosting. It's also worse that all three of the obviously affected ones in that video are the rear facing ones. Tends to track with my experience in the rain as well with just monitoring the v9 visualization with respect to the surroundings.

My main point is that there's just nothing they can do to mitigate this issue with the existing hardware. They can't say the car can do full-self-driving safely off of just the forward radar and cams, which are the only sensors that will work sufficiently well in the rain. The ultrasonics become mostly useless in more than moderate rain, also.
 
My main point is that there's just nothing they can do to mitigate this issue with the existing hardware. They can't say the car can do full-self-driving safely off of just the forward radar and cams, which are the only sensors that will work sufficiently well in the rain. The ultrasonics become mostly useless in more than moderate rain, also.

If they used a blob detection vs object detection, then the water distortion effect could be reduced. However, using an arbitrarily distorted image for range estimation seems very challenging.
A change to the camera housing may provide more self cleaning effect (or maybe the rain-x made things worse?)
 
Of course. Best cars available today still... not really any doubt there. But, if you check my invoice, you'll not see me donating any money to Tesla for the non-existent full-self-driving stuff... so, not sure how your comment is related to my post. Just because the company is shady af with their marketing doesn't make the overall product as it sits all bad.





Yeah, I was just about to say that in the 6-7 minute mark, the repeaters look pretty useless. Calculated free space easily jumps into the space that is clearly not free space and other data is clearly just noise in those sections (lane markings, for example). The truck that pops into view is only labeled in about 1 out of 3 frames, too, in a part that's not even as bad. The pillar cams staying clear, though, is a good thing, though, and the front cams are a given (wipers to clear them plus radar to augment the data).

Honestly, just seeing that at least 3 of the 8 cameras are giving somewhat useless data at times in what looks like somewhat minor rain... is not confidence boosting. It's also worse that all three of the obviously affected ones in that video are the rear facing ones. Tends to track with my experience in the rain as well with just monitoring the v9 visualization with respect to the surroundings.

My main point is that there's just nothing they can do to mitigate this issue with the existing hardware. They can't say the car can do full-self-driving safely off of just the forward radar and cams, which are the only sensors that will work sufficiently well in the rain. The ultrasonics become mostly useless in more than moderate rain, also.

At arround minute 33 some details are shared how Audi attempts to keep the rearward facing cameras water free... it seems complicated.
 
20190102_154704.jpg

Hi mates.
Need help to test my MCU on bench.
What wires do I need to connect to start it?
Thanks.