Adverse weather can be a source of major frustration for motorists, as well as a significant factor in the number of accidents that occur each year on American roadways.
On average, more than 5 million crashes take place annually and 22 percent of them are weather-related, the Federal Highway Administration (FHWA) reports.
Now with more autonomous vehicles being deployed on highways around the country, researchers are working on ways to fine-tune and enhance the technology that controls these vehicles. Capabilities the cars are being taught include identifying cyclists, maintaining speed limits and learning traffic patterns. Tackling the challenge that bad weather poses is just one step of the process.
Self-driving technology has been in the works for decades, and it's currently being developed by a variety of companies, including automakers such as Ford, ride-sharing services such as Uber and Lyft, and technology giants like Google. Fully autonomous vehicles are controlled by a combination of computer software, radars, sensors, cameras and lasers.
Google first started testing self-driving technology on California's freeways back in 2009. Today, the company says its vehicles have logged more than 2 million fully-autonomous miles on public roads and can be found on the streets of Mountain View, California; Austin, Texas; Kirkland, Washington; and the metropolitan Phoenix area.
The vast majority of weather-related crashes occur on wet pavement and during rainfall, the FHWA states.
However, in California, opportunities to drive in wet weather have been limited due to the state's five-year drought.
According to Google's self-driving car project monthly report from December 2015, rainfall that the state received during the early winter of 2015-2016, provided an opportunity to test-drive when roads were slippery.
Google's report details that the equivalent of windshield wipers were placed on the dome that holds the sensors to ensure the best view possible.
"Driving in rain makes many human drivers nervous due to reduced visibility, and some of our sensors, particularly the cameras and lasers, have to deal with similar issues," Google stated. "Our laser sensors are able to detect rain, so we have to teach our cars to see through the raindrops and clouds of exhaust on cold mornings and continue to properly detect objects."
Google said the cars can determine the severity of rain and drive more cautiously like humans would when visibility is poor. This includes stopping along the side of the road if a storm is severe enough.
Around Phoenix, Google said the extreme temperatures and dust in the air provide new experiences for the software and sensors in the car. Additionally, the vehicles are learning how to deal with haboobs, or dust storms, that can often reduce visibility to zero.
Google said the safest thing that the car can do during a haboob is pull over along the side of the road. When the car is pulled over, it can learn from the experience by detecting the extreme amounts of dust.
Winter driving conditions can be particularly challenging, as the FHWA reports that 24 percent of weather-related accidents occur on snowy, slushy and icy pavement.
Earlier this year, Ford became the first car company to test drive self-driving cars in the snow when it drove cars on snow-covered roads at MCity, a full-scale, simulated real-world urban environment at the University of Michigan.
Lidar, the remote sensing method built into these cars, cannot identify roads when they are covered in snow. Therefore, researchers from Ford and the University of Michigan developed another method that would allow the cars to navigate properly.
They created high-resolution 3D maps that the vehicle could create while driving in favorable weather. The maps pick up things such as road markings, nearby landmarks, signs, geography and topography. The vehicle can use the above-ground landmarks as a way to pinpoint its location when snow disrupts its vision. Then, it will follow the maps to successfully resume its route.
"It's one thing for a car to drive itself in perfect weather," Jim McBride, Ford technical leader for autonomous vehicles, 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 percent of United States residents who live in snowy regions."
Uber officially joined the self-driving initiative when it launched a fleet of hybrid Ford Fusions around Pittsburgh this past May to test drive and collect mapping data throughout the city. In September, the first automated Ubers began picking up passengers around the Steel City.
However, the robots are not totally on their own yet. In testing situations and currently for cars that are picking up passengers in Pittsburgh, Uber said a human remains in the driver seat in case any problems occur.
The federal government sees autonomous vehicles as a way to dramatically improve safety for motorists in the future. Ninety-four percent of crashes on U.S. roadways occur by human choice or error, according to the National Highway Traffic Safety Administration.
On Sept. 20, the U.S. Department of Transportation (DOT) unveiled a four-part policy that covers the safe deployment and testing of automated vehicles. Part of the policy requires developers to specify the type of weather conditions in which the cars can operate.
"Automated vehicles have the potential to save thousands of lives, driving the single biggest leap in road safety that our country has ever taken," U.S. Transportation Secretary Anthony Foxx said in a statement. "This policy is an unprecedented step by the federal government to harness the benefits of transformative technology by providing a framework for how to do it safely."