Ford used the snow-covered Michigan as a testing ground for checking on how their autonomous technology works on rough terrain.
Driving cars in ideal conditions is not always an option, so Ford, understandably, decided to test their autonomous cars under a bit rougher circumstances. According to Jim McBride, Ford technical leader for autonomous vehicles, "It's quite another to do so when the car's sensors can't see the road because it's covered in snow. Weather isn't perfect, and that's why we're testing autonomous vehicles in wintry conditions." Fully driving can't depend only on GPS, and we all know even a couple of inches can and do make a difference, so autonomous cars come equipped with a much more accurate LiDAR laser radar technology. LiDAR emits short pulses of laser light to precisely allow the vehicle to create a real-time, high-definition 3D image of what's around it. In dry, sunny weather, LiDAR is the most efficient means for identifying the car's surroundings, but on snowy roads or with camera and other sensor lenses covered in dirt, by grime or debris, these systems can't see the road and do their job properly.
Hence, Ford and a team of technologists from the University of Michigan equipped Ford's autonomous cars with high-resolution 3D maps including information about the road and what's above it, including road markings, signs, geography, landmarks and topography. An autonomous vehicle is able to create and add information on its own while driving the test environment in good weather. The mapping system automatically annotates features such as traffic signs, trees and buildings. So, when the vehicle can't see the ground due to poor weather conditions, it detects above-ground landmarks to pinpoint itself on the map, and then subsequently uses the map to continue the drive successfully.