As I've mentioned elsewhere, I'm directly involved in the test and evaluation of one of the current attempts at "sense and avoid" technology. It is a long way from being safe for fully autonomous use. It is my understanding that the DARPA autonomous land vehicle contest required autonomous collision avoidance, and that more than one of the entrants did so effectively. Their budgets were a pittance compared to what is being spent on "sense and avoid" for UAVs, and yet they had much greater success. That tells me that urban traffic avoidance is easier for computers than air traffic avoidance.
I think that two big reasons for this are probably:
1: For land vehicles, simply stopping in place is almost always an effective collision avoidance tactic (unless the other vehicle is deliberately seeking a collision). This simple solution is not available to airplanes.
2: Tracking objects thar are moving in three dimensions with a sensor that is also moving in three dimensions is an immensely more complex problem than tracking objects that are constrained to move on a fixed surface in two dimensions with a sensor that is also constrained to move on a fixed surface in two dimensions.
I think that two big reasons for this are probably:
1: For land vehicles, simply stopping in place is almost always an effective collision avoidance tactic (unless the other vehicle is deliberately seeking a collision). This simple solution is not available to airplanes.
2: Tracking objects thar are moving in three dimensions with a sensor that is also moving in three dimensions is an immensely more complex problem than tracking objects that are constrained to move on a fixed surface in two dimensions with a sensor that is also constrained to move on a fixed surface in two dimensions.