Tech

Ford just overcame a major hurdle for driverless cars

Danielle Muoio

2016-01-12T20:09:00Z

Driverless cars struggle when it comes to driving in snow.

That's because when snow is on the road, the cars' LIDAR sensor and camera have a difficult time seeing the lane markers and other cues that help them drive safely. The same goes for when sensors are covered by snow.

But Ford just made a major breakthrough by successfully testing its driverless cars in snow for the first time.

Here's a look at how Ford is ahead of the competition by preparing its driverless cars for snow:

The cars were driven around MCity, Ford's 32-acre faux city located in Ann Arbor, Michigan, while it was snowing.

Prior to driving in the snow, Ford's LIDAR sensors created high-resolution 3D maps. The maps come with information not only about the road, but also what's above the road, like its topography and nearby signs and landmarks.

Mapping routes is key to many driverless car efforts.

Audi, Daimler, and BMW acquired Here, the former mapping division of Nokia, to make real-time maps to aid their driverless car efforts and Google is also mapping its own routes.

Chinese internet company Baidu, which recently tested a driverless BMW 3-Series on an 18.6-mile route successfully, will also meticulously map routes. Those routes will be used to release a driverless public transportation system in the next three years.

And now Toyota is mapping its own routes.

When Ford's driverless cars are unable to see the grounds, it can use nearby landmarks to pinpoint where it is on these 3D maps, allowing the car to drive successfully.

“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," Ryan Eustice, associate professor at University of Michigan college of engineering, wrote in a Ford press release.

The cars' LIDAR sensors also allow them to remain "constantly vigilant" so they can tell when they need to make an evasive maneuver, Greg Stevens, global manager of Ford's driver assistance research, said in a Ford video.

Because the cars can detect when they need to make an evasive maneuver, the Ford researchers were able to train them to do it in the safest way possible.

"And so we can have the vehicle drive in those situations, especially slippery low grip situations like there are in snow, in a way that an expert highly trained driver would have," Randy Visintainer, Ford's director of autonomous vehicles and controls, said in the video.

Ford is making big moves in the race to create the first fully autonomous cars. Ford recently announced it will use a new LIDAR sensor that extends its cars sensing range by 656 feet and has improved precision to create more accurate maps.

The LIDAR sensor, called the Ultra Puck, was made by tech company Velodyne.

Ford will also be tripling the size of its autonomous fleet to 30 vehicles — the largest autonomous vehicle fleet of all automakers.

Watch Ford's full video of its cars driving in snowy conditions here:

Ford Self-Driving Car Transportation