Driverless cars battle the elements

Snow and ice cause chaos on the roads each year – leading to accidents, road closures and traffic jams. There a numerous potential benefits of driverless cars, however, operation in wintry conditions can prove problematic as the Light Detection and Ranging (Lidar) sensors they use find it difficult to detect road markings and hazards if they are covered by snow.

However, Ford has announced the successful completion of tests of its driverless cars in snowy conditions. This has been achieved by programming the Lidar sensors to detect landmarks above ground such as buildings and road signs. This view is then compared with exiting stored maps, allowing the car to navigate the road, even when visibility is poor. The cars were tested in a model city by the University of Michigan.

“It’s one thing for a car to drive itself in perfect weather. It’s quite another to do the same thing when its sensors cannot sense the road through snow, or when visibility is limited by falling precipitation,” said Jim McBride, Ford's Technical Leader for Autonomous Vehicles.

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