Ford’s been testing driverless cars in the snow, and the results look promising

Auto-making giant, Ford, announced that it’s been conducting successful tests of its driverless cars in snowy conditions. According to the company, it’s been a success so far, and although it’s been running sensor tests for more than a year, it’s recently begun driving its autonomous fleet of Fusion Hybrids in a controlled, snowy environment.

Known as MCity, the testing environment is a 32-acre closed-course testing facility in Ann Arbor, MI. Ford revealed that its driverless cars use 3D maps to safely travel across the snow-covered streets. 

Ford's Fusion Hybrids are being tested in a controlled, snowy environment. Image source: Ford.

“It’s one thing for a car to drive itself in perfect weather,” Ford technical leader for autonomous vehicles, Jim McBride, said in a statement. “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 — for the roughly 70% of U.S. residents who live in snowy regions.”

Typically autonomous vehicles are equipped with a combination of sensors, cameras, radar, GPS, and LiDAR systems to pinpoint the car’s location on the road so that car can direct itself. But that leaves the question: what happens when snow covers the car’s cameras, the lane markers, and road signs?

According to Ford, the answer lies in its 3D maps that were developed in collaboration with the University of Michigan, which allow the vehicle to understand the road’s precise signs, markings, and geography at all times. 

Driverless cars can build a detailed view of the surrounding environment. Image source: Ford.

“The maps we created with Ford contain useful information about the 3D environment around the car, allowing the vehicle to localize even with a blanket of snow covering the ground,” associate professor at UM’s College of Engineering, Ryan Eustice said.

Impressively, the cars can create the highly-detailed maps during good weather and store that information in the vehicle’s memory. In the case of bad weather, the cars use the maps with a combination of traction and stability to continue driving.

Ford said it’s looking into programming the driverless vehicles to sense when conditions are too rough, so that they can pull over and stop driving. 

Source: Detroit News