[harles]

I’m not sure about newer models without radar, but the older ones explicitly discard stationary returns on their radar. As I understand it, without elevation data it can’t know if it’s a bridge you’ll pass under, a soda can in the road, or a stopped car - so just ignore it all.

Of course the vision system is supposed to compensate for this, and it performs poorly on objects it doesn’t see often, like emergency vehicles.

[jiggawatts]

The vision system is supposed to be able to determine an accurate depth map based on a combination of stereo vision and depth-from-defocus. I've seen demos of the real-time depth map, and it looks high-resolution and accurate to about 5-10cm.

So, if they have the input data, why is it being ignored by autopilot?

[harles]

Tesla’s website[0] states it’s monocular depth estimation. I haven’t heard of them doing any form of stereo.

[0] https://www.tesla.com/autopilotAI

[diggernet]

why should it matter how often it sees something? Or even if it's something the car has never seen before? All it should care about is whether there is an obstacle, not what the obstacle is. Whether it's an emergency vehicle, a sofa, a boulder, a canoe, a table saw, or a dolphin, you don't want to hit it!

[harles]

How often it’s seen in training data that is, which is pulled from data in the wild.

It’s simply not possible to do depth estimation like this without priors. That’s one of the serious limitations of such systems - you have to train on every class of object you don’t want to hit.

[diggernet]

Then they are doing it wrong. There are all manner of things that can end up in the road that have never been (and will never be) classified. If their system must classify a thing to not hit the thing, then they will kill people. It's gross negligence to work so hard to not, at the very minimum, install two cameras for stereo vision.

[harles]

100% agree. I think depth is critical and monocular estimation doesn’t cut it.