Autonomous, or self-driving, vehicles navigate using technologies to detect lane markers to stay on course.
But what happens when those lane markers are covered with snow?
Engineers with the University of Michigan and Ford Motor Company say their new research shows it's possible for a self-driving car to get around using highly detailed 3D maps of everything that surrounds the vehicle.
"We used the large 3D physical structures around the car, from signs to buildings,"says the U of M's Ed Olson. "It's a little bit harder to make it work, but we really set out to make it work in snowy weather."
Of course, this was on a closed course, at the University of Michigan's M-City autonomous vehicle test course.
Olson says in the real world, autonomous vehicles will come in phases. There are already partially autonomous cars that can stay in a lane and maintain a safe distance from the car in front, with the driver taking control of the vehicle to change course.
Next will come fully autonomous vehicles on the highway.
"More complicated scenarios where you're in downtown Manhattan and there are bicycles weaving in and out, that's going to come later," Olson says.
The research was announced at the North American International Auto Show in Detroit.