Ford: We’re on the white road
Ford is hoping to make a breakthrough in autonomous driving by testing vehicles on snow-covered roads.
It argues that dry testing is one thing, but the parameters change significantly when the car’s sensors can’t see the road markings.
Jim McBride, Ford technical leader for autonomous vehicles, said, ‘Weather isn’t perfect, and that’s why we’re testing autonomous vehicles in wintry conditions.’
Working with the University of Michigan, Ford is using LiDAR technology, which emits short pulses of laser light to allow the vehicle to create a precise, real-time, high-definition 3D image of its surroundings. On a clear day, LiDAR is considered the most efficient means of gathering important information and metadata. But on snow-covered roads, or when the sensor is covered in snow or grit, it can’t see the road.
To overcome this, Ford vehicles have been equipped with high-resolution 3D maps created during good weather. These maps automatically annotate features like traffic signs, trees and buildings. During bad weather the car detects above-ground landmarks to pinpoint itself on the map.
Ryan Eustice, associate professor at University of Michigan College of Engineering, said, ‘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.’
Jim added, ‘The vehicle’s normal safety systems, like electronic stability control and traction control, which often are used on slippery winter roads, work in unison with the autonomous driving software. We eventually want our autonomous vehicles to detect deteriorating conditions, decide whether it’s safe to keep driving, and if so, for how long.’