So far, Google has preferred to test its Waymo self-driving cars in favourable climates; such as its home state of California and in Arizona.
You don’t see the spin-off company heading to Michigan – where self-driving car tests are permitted – in the dead of winter to drive in the snow, do you?
However, that could be about to change with the latest news coming out of Google I/O.
In a post on Medium, Waymo explains how its machine learning techniques are helping its cars filter out ‘sensor noise’ created by raindrops and snowflakes.
Related: Check out Waymo’s self-driving Jag’
The company says filtering out this noise (which you’ll see in purple on the image above) enables the cars to correctly identify pedestrians and other vehicles, even those parked on the side of the road.
The company writes: “We aim to bring self-driving technology to everyone, everywhere… and in all weather. Driving in heavy rain or snow can be a tough task for self-driving cars and people alike, in part because visibility is limited. Raindrops and snowflakes can create a lot of noise in sensor data for a self-driving car. Machine learning helps us filter out that noise and correctly identify pedestrians, vehicles and more.”
However, this doesn’t appear to be a complete solution. Given how snow can often completely obscure lanes, Google hasn’t addressed how the Waymo cars will be able to stay in their lanes in tricky conditions.
Is Google relying on its collision avoidance tech to stop these cars verging into its other’s lanes? The company is also working on helping its vehicles navigate unmapped country roads, which may come in handy in this instance.
Will you be looking to snap up a self-driving car when the tech becomes available to consumers? Let us know @TrustedReviews on Twitter.