Think about how a human driver does it, given his/her even worse vantage point. They model what's in front/behind the car from afar and remember what's where as they approach it. There are other signals as well, such as continuation of a kerb, etc.

I think people keep forgetting that Teslas run hundreds of ML prediction tasks all the time. Watch recent AI day and their talks about "occupancy network" to get a sense of the car's ability to:

1. Construct 3D model of its surrounding in real time; 2. Remember occluded sections based on what's it's seen previously.

And more importantly, it sees in all directions at all times.