Ford Conducts Industry-First Snow Tests of Autonomous Vehicles Further Accelerating Development Program

Ford is conducting the market's very first autonomous vehicle tests in snow-covered environments-- a significant step in the company's plan to bring totally self-governing automobiles to millions of clients worldwide.Unlike other significant automakers and technology companies, which have actually tested autonomous automobile technology only in dry, primarily warm environments, Ford knows the future of autonomous driving can not depend on ideal conditions.

"It's the main thing for an automobile to drive itself in best weather condition," said Jim McBride, Ford technical leader for self-governing automobiles. "It's fairly another to do so when the car's sensors cannot see the road due to the fact that it's covered in snow. Weather isn't really best, which's why we're checking autonomous automobiles in wintry conditions-- for the about 70 percent of U.S. residents who live in snowy regions.".

Ford's winter weather condition screening takes place in Michigan, including at Mcity-- a 32-acre, full-scale simulated real-world metropolitan environment at the University of Michigan.

Totally self-governing driving can't depend on GPS, which is precise only to a number of backyards-- not enough to localize or determine the position of the car. And it's essential that an autonomous car understands its precise location, not simply within a city or on a road, but in its real driving lane-- a variation of a couple of inches makes a big distinction.

LiDAR, on the other hand, is a lot more precise than GPS-- identifying the Fusion Hybrid's lane place right down to the centimeter. LiDAR emits short pulses of laser light to precisely permit the vehicle to create a real-time, high-definition 3D picture of what's around it.

In ideal weather, LiDAR is the most reliable methods of collecting essential information and metadata-- underlying information about the information itself-- from the surrounding environment, sensing nearby objects and making use of cues to determine the best driving course. But on snow-covered roadways or in high-density traffic, LiDAR and other sensors such as video cameras can't see the road. This is also the case when the sensing unit lens is covered by snow, gunk or debris.

Undaunted by this difficulty, Ford and University of Michigan technologists began collaborating towards a solution that would allow a self-governing car to see on a snow-covered road.

How snow autonomy works.
To navigate snowy roads, Ford self-governing vehicles are equipped with high-resolution 3D maps-- total with info about the road and exactly what's above it, including roadway markings, indications, location, landmarks and topography.

"Maps developed by other companies do not constantly work in snow-covered landscapes," said Ryan Eustice, associate professor at University of Michigan college of engineering. "The maps we created with Ford contain useful info about the 3D environment around the car, permitting the automobile to localize even with a blanket of snow covering the ground.".

An autonomous automobile creates the maps while driving the test environment in desirable weather condition, with technologies automatically annotating features like traffic indications, trees and structures. When the car can't see the ground, it discovers above-ground landmarks to determine itself on the map, then subsequently uses the map to drive successfully in inclement conditions.

"The car's normal security systems, like electronic stability control and traction control, which typically are used on slippery winter roadways, operate in unison with the autonomous driving software," stated McBride. "We eventually desire our autonomous automobiles to spot deteriorating conditions, choose whether it's safe to keep driving, and if so, for how long.".

A leader in autonomy.
Winter season driving still provides a host of difficulties, but Ford's testing marks an important accomplishment on the road to autonomous driving. That roadway goes back approximately a years, to the first-generation autonomous car from Ford-- a LiDAR-equipped F-250 Super Duty.

In 2013, Ford released its second-generation autonomous automobile platform, a Fusion Hybrid sedan making use of advanced LiDAR sensors. This past summer season, Ford transitioned its fully autonomous automobile advancement program from the research to advanced engineering phase, the second of three stages before getting in production.

Earlier this month, Ford announced it is taking the next step-- tripling its completely autonomous development fleet to 30 cars being tested on roadways and test tracks in California, Arizona and Michigan. This makes the company's completely autonomous vehicle fleet the biggest of all automakers. These third-generation autonomous automobiles remain to be based upon a Fusion Hybrid sedan now featuring the very first auto-specific LiDAR sensor efficient in dealing with various driving circumstances-- thanks in part to its longer variety of around 200 meters.

Structure on more than a years of Ford autonomous automobile research study, this improvement is a key element of Ford Smart Mobility-- the strategy to take Ford to the next level in connectivity, mobility, autonomous automobiles, the client experience, and information and analytics.