Trails are narrow ribbons of civilization cutting through wilderness. They are as much about what is worth exploring as they are about what's off limits. A hiker loses a trail, and suddenly they're in a deep wilderness, unmoored from the world until they stumble back to that thin filament again. To find missing hikers, it makes sense to look near trails, and to do that, a team at the University of Zurich is training drones to identify and follow trails into the woods.
Here's how it works:
The drone used by the Swiss researchers observes the environment through a pair of small cameras, similar to those used in smartphones. Instead of relying on sophisticated sensors, their drone uses very powerful artificial-intelligence algorithms to interpret the images to recognize human-made trails. If a trail is visible, the software steers the drone in the corresponding direction.
The drones learned to identify trails using deep learning neural networks. This is the same process like the one Google's Deep Dream used to create those super-weird images from last summer. Only instead of looking at a picture of salad and breaking it into dog faces, this network reads forests to find the paths that look like they're supposed to be there.
Don't expect rescue drones to find missing hikers just yet, but someday, quadcopters could be as iconic an alpine rescue tool as St. Bernards.
