You describe it as challenging but it sounds like realistically it is just badly designed roads. But fixing that aside, nothing really stops you from outfitting secondary roads with transponders in principle. In practice, it is easier to start with freeways because (a) they are much more uniform, (b) the impact of an accident at freeways speeds is much more deadly, (c) no pedestrians, bicycles, etc., and (d) the federal government has control over the freeways (it is a complex relationship but ultimately the feds have a say) which means they can mandate installing the transponders and pay for it. Once the system functions there it can be expanded until every driveway and parking spot is outlined.

They’re badly designed (outskirts of Silicon Valley). So is the electricity and internet, so the transponders placed in shady spots would need something like a 30 day battery backup and network other than wired, cell, wisp or starlink.

Vision based systems would be more than adequate. Lidar or (god forbid) ultrasonic chirps would easily lead to superhuman safety and speeds.

I’m skeptical of transponder or network based systems. What happens during a natural disaster? Do the 10% of cars that lack drivers or steering wheels just stop and block the evacuation routes? That’d kill a lot of people in very graphic / high profile ways.