The real world is full of 'edge cases' that humans can deal with through their intuition and understanding of context. Humans are unlikely to mistake a yellow-ish moon for a yellow traffic light unless very intoxicated.

I'd like to see a Tesla on full autonomous autopilot take a drive in Calgary or Edmonton a few days after a heavy snow, when it's been mostly plowed but the lines are missing from the roads, all the lines at the side of the road are covered in snow, etc.

You highlight the big challenge with computer vision and other computerized identification of things, regardless of the underlying technology. There is no "mental model" of what makes sense against which to check observations. There can be coded rules, but if something passes them, there is no extra sanity check like a person would do. Put another way, models have no common sense, and we don't really have a meaningful way to give it to them. This is going to remain a problem for self driving cars and is a big part of the reason why they have not lived up to expectations.

Funny, when I saw that I thought how did they miss this one? It's the moon, how is it possible no one has driven a Tesla at the right time in the right direction to have picked up the moon? The moon is out quite often. It doesn't seem like that much of an edge case to me, though I could be wrong.