With fatal car crashes now an escalating concern on U.S. roads, crash avoidance features in cars are becoming more sophisticated by the minute. So far, automakers have introduced forward collision systems, adaptive headlights, and even driver attention monitors, to name a few.
Self-driving cars, the next new wave in automotive technology, are perhaps the most exciting of all road safety concepts. Although fully-autonomous cars are still a long way off, they aim to make the highway — and the American road system in general — a much safer place.
In order to reach this goal, however, automakers have several roadblocks to overcome — one being poor weather conditions. The U.S. Department of Transportation (DOT) now requires developers to declare what types of weather their cars can operate in. Of course, cars that can’t guarantee optimal performance in all conditions won’t get very far.
Preparing for Worst-Case Scenarios
Semi-autonomous cars are already being used or tested across America: in California, Texas, Washington, and Arizona, for example. In dry, sunny California or Texas, there’s little chance of a self-driving car needing to navigate hazardous weather. But how would the vehicle fare in areas more likely to be hit by fog, rain, or snow?
With so many semi-autonomous, self-driving cars already on the road — and more crashes involving Tesla autopilot or self-driving cars are just waiting to happen — it’s crucial that automakers find out the answer to this question sooner, rather than later.
“It’s one thing for a car to drive itself in perfect weather,” said Jim McBride, Ford’s technical leader for autonomous vehicles. “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.”
Tests are currently being carried out by Google, Ford, and even Uber, as well as Tesla. The next step is for self-driving vehicles to “learn” how to deal with weather that can reduce visibility to zero.
Is Current Technology Good Enough?
Most drivers know that driving safely in bad weather means taking more precautions.
But autonomous cars rely on computer software, cameras, lasers, and other sensors to run smoothly, rather than common sense. This means that when snow or ice builds up on the ground or covers a car’s external sensors, the vehicle has trouble identifying where it is. Experts have also identified a further issue: that safety systems such as anti-lock brakes and stability control – which are designed to avoid crashes – might cause problems in autonomous cars.
“Stability control systems are really going on at very low levels in the vehicle, almost like a reflex,” said Edwin Olson, an associate professor of computer science at the University of Michigan. “The autonomous vehicle is almost cognitive, at a much higher level. There’s a real concern that these safety systems – which are great for human drivers – will just confuse the autonomous control. Getting that interaction right is pretty tricky.”
Nonetheless, automakers are searching for ways to optimize their cars’ capabilities. Google’s cars are equipped with several safety measures, including wiper blades that keep the vehicles’ camera lenses clear, and an automatic response to storms that can pull a car over to the side of the road.
Winter conditions pose the biggest challenge, as even an inch of snow covering the ground can interfere with the car’s ability to sense its location. Accordingly, Ford has funded a $6.6 Million solution whereby a vehicle relies on its surroundings instead, using 3D maps to pinpoint landmarks and road signs.
A Critical Situation
These developments, as promising as they sound, won’t be fully deployed for a long time – despite the obvious urgency. Of the 5 million crashes that take place each year, 22% are weather-related. But here’s another daunting fact: we may still be 10 years away from all-weather driverless cars.
It’s true that automakers are on their way to making self-driving vehicles safer for most any situation. But until then, human error has a serious part to play in causing fatal traffic accidents.
If self-driving vehicle developers want to successfully improve safety on the roads, they’ll need to cover all bases – and the result of eliminating weather-related risks, in particular, will be worth it. “Automated vehicles have the potential to save thousands of lives,” says U.S. Transportation secretary Anthony Foxx, “driving the single biggest leap in road safety that our country has ever taken.”