The unreasonable part has to do with the reality of auto high beams.

Even the best implementations dazzle other drivers.

Auto high beams are only realistic when used where normal high beams are. That is, mostly on single lane roads with no dividers, little to no street lights, where opposing traffic is not appearing often, etc.

-

It seems like such a small thing compared to driving a whole car... but this is one of the few vision features that directly affects other drivers on a regular basis.

The comments explain how for example, vehicles with tall ride heights like commercial trucks get dazzled due to their tailights sitting much lower than their mirrors

It's just not realistic to leave your high beams "potentially on at all times" unless you're willing to dazzle other drivers.

Modern auto high beams work fine, but unfortunately modern headlights are illegal in the US.

https://www.autoweek.com/news/technology/a34417809/nhtsa-sti...

The "auto" in "auto high beams" is that they switch off for oncoming traffic.

If only naming things based on their intended function made them work like that?

Tesla should put lidar on the car and be done with it. That's what Lucid has done:

https://electrek.co/2021/05/26/lucid-reveals-ux-intuitive-us...

The point is, adding lidar to the car does not mean you are "done with it". If it were the case, Tesla would have done it long ago. Lidar is great for precisely detecting 3D surfaces. But it helps very little in characterizing those surfaces. Lidar could tell you precisely how far a sheet of metal is. Whether that sheet of metal is a traffic sign and what it says, it tells you not. Lidar doesn't detect lane markings and many things more. Also, there is the challenge of merging the Lidar data with your camera images.

LIDAR absolutely detects lane markings, along with street signs, if you’re close enough.

Edit: the reason here is that road paint (and the marking on a sign) is typically retroreflective, while roads (and regular painted sheet metal) are not. Retroreflective materials are very easy to detect with LIDAR. Even if you are on older roads that don't have retroreflective paint, white objects and black objects also tend to show up differently.

Edit2: there's also no reason you can't use detection algorithms to characterize pointclouds. You can also fuse the returned objects from the lidar sensor(s) with the objects from the camera(s). You have the latter problem even with just multiple cameras. Inevitably, whatever you are using for segmentation/classification will return different results on different sensors, for sensors that share the same FOV - you do need a strategy for handling this.

Tesla has not added LIDAR because of cost (and because of Elon's ego...) - they are one of the few companies going directly for consumer sales - more parts that cost $$$ and require calibration aren't good for that.

LIDAR is used in addition to 2D camera images. LIDAR is used to build a depth map and do image segmentation and works in low light and low contrast environments.

Single cameras (even stereo cameras) require a lot more assumptions about contrast and environment lighting to do image segmentation and depth maps. They're rarely as accurate as LIDAR and often far worse.

Depth maps and image segmentation are the building blocks of object identification. You can try to AI your way into those with a single camera but it'll be less accurate and more error prone.

> adding lidar to the car does not mean you are "done with it"

It will mean Tesla is done with trying to avoid adding it. They test with lidar so they might as well start using it:

https://insideevs.com/news/508669/tesla-model-y-luminar-lida...

Too expensive for mass market. Lucid’s vehicle is almost $190k.

Compare the 190K with Tesla Plaid fully loaded. Lucid also has a $69K model.

There are multiple trim levels. Pick a cheaper one:

https://www.lucidmotors.com/air

None of these vehicles can be bought today. It's vaporware at the moment.

It really isn't:

https://www.youtube.com/watch?v=SYK57Mdc4BI