Snow is a nightmare that obscures lanes, cars, road signs, and entire roads and freezes up sensors and probes on a car’s externals, tech that is vital for self-driving cars to gather information and navigate the environment around them. Self-driving cars have a hard enough time learning to navigate the roads around bright and sunny California, so how do you think they’ll manage in the snow, ice and whiteout conditions?
Waymo knows how to tackle that problem though, and in a presentation at the Google I/O keynote this week, the company visualized how its vehicles safely navigate a winter wonderland.
Snowfall (or any precipitation, for that matter) ultimately amounts to sensor noise, that’s the sea of purple in the image above, reports Engadget. Waymo uses machine learning to filter out the snow and see just what’s on the road, even if there are vehicles parked by the curb. It’s not clear whether the car can distinguish lanes, but this would at least be enough to avoid collisions and get you home safely.
The company has been testing the car’s winter capabilities since October in Detroit, MI and are hoping this technology, combined with work on navigating unmapped roads, will be critical to making self-driving cars widely available. Miserable weather and barely visible roadways are common in many parts of the world, and they’re not about to go away just because they’re inconvenient for autonomous vehicles.
All sounds great, but I think I’ll still drive myself over that mountain pass thank you very much.