Google's new driverless car skills challenge: Overcoming rain and snow interference

Last December, Google spun off its self-driving car project into an independent company, Waymo. According to Waymo's official website, self-driving cars currently "have mastered the equivalent of more than 300 years of human driving experience , about 3.22 million kilometers, most of which are experiences on city streets."

Of course, we cannot underestimate the role of driverless cars in accumulating this data. One unavoidable fact is that Google's driverless cars have not yet been tested in cold climates and snowy environments. Waymo CEO John Krafcik said in July last year that "testing in heavy snow" had not yet begun.

For driverless cars, adverse weather conditions such as heavy rain, snow and hail are considered the ultimate technical challenge that will hinder the market entry of driverless cars, as such conditions will reduce the accuracy of the sensors of driverless cars, including cameras and lidar.

Especially on snowy days, cameras cannot recognize lane lines, making it difficult for driverless cars to prevent lane drift and navigate safely; the visibility of lidar will be significantly reduced in snowy environments, which will make it impossible for the driverless system to draw an effective map of the surrounding environment to ensure driving safety. At the same time, snowy weather also makes it difficult for such sensors to detect unexpected obstacles on the road.

From a user's perspective, in winter, if someone wants to drive from the East Coast of the United States to the Midwest or from the southern part of China to northern cities, driving in snowy environments is an essential skill.

Last year, Ford successfully tested a self-driving car in snowy weather. Jim McBride, Ford's head of autonomous driving technology, said at the time, "It's one thing for an autonomous car to drive in clear weather, and it's another thing to drive in snowy weather. We are testing self-driving cars in winter conditions, and about 70% of the U.S. population lives in areas where snow is likely to fall."

Currently, Ford's snow testing has not yet entered the public road, but is only carried out at the MCity test site in Michigan.

General Motors recently announced that it will conduct self-driving car tests in Michigan, which is also GM's main testing area in severe cold weather.

Last December, Michigan passed a self-driving car-friendly bill: allowing self-driving cars to drive on public roads, and even allowing self-driving cars to have no physical steering wheels and brakes, and no driver sitting in the cockpit. General Motors CEO Mary Barra said that this has made it easier for GM to test self-driving cars. She emphasized that it is very important to test self-driving cars in a variety of environments, and it is not meaningful to simply accumulate mileage. At the same time, Uber also plans to test self-driving technology in extreme weather in Pittsburgh.

According to Leifeng.com, Google's driverless cars are currently being tested in four locations: Mountain View, California, Phoenix, Arizona, Austin, Texas, and Kirkland, Washington. Google believes that these test locations give driverless cars unique driving experience. For example, Google said in its monthly report last August that the test in Arizona allowed the driverless car to get used to dust and extreme high temperature environments. The test in Washington State gave the driverless car the experience of driving in heavy rain.

Although Google launched its self-driving project in 2009, it has not yet announced any test sites for snow and extreme cold. From a commercial perspective, only through tests like this can Google's self-driving cars be driven on the road in most parts of the United States.

As a winner of Toutiao's Qingyun Plan and Baijiahao's Bai+ Plan, the 2019 Baidu Digital Author of the Year, the Baijiahao's Most Popular Author in the Technology Field, the 2019 Sogou Technology and Culture Author, and the 2021 Baijiahao Quarterly Influential Creator, he has won many awards, including the 2013 Sohu Best Industry Media Person, the 2015 China New Media Entrepreneurship Competition Beijing Third Place, the 2015 Guangmang Experience Award, the 2015 China New Media Entrepreneurship Competition Finals Third Place, and the 2018 Baidu Dynamic Annual Powerful Celebrity.