AI drones can see the wood for the trees
According to researchers from the Dalle Molle Institute for Artificial Intelligence (AI) and the University of Zurich, AI software may assist drones to autonomously recognize and follow forest footpaths
Swiss emergency centers respond to around 1 Kcalls annually from injured and lost hikers. The hope is that swarms of drones will complement the work of rescue services teams. According to researchers from the Dalle Molle Institute for Artificial Intelligence (AI) and the University of Zurich, AI software may assist drones to autonomously recognize and follow forest footpaths.
Sadly drones cannot yet fly autonomously in complex environments, such as dense forests. In these environments robots need a powerful brain in order to make sense of the complex world around them. Instead of relying on sophisticated sensors, the forest-savvy drone uses a pair of simple cameras and "very powerful” artificial-intelligence algorithms to interpret the images to recognize man-made trails. If a trail is visible, the software steers the drone in the corresponding direction.
The algorithm is a “deep neural network” that learns from training examples obtained from 20 Kimages of trails gathered by helmet cams while walking trails in the Swiss Alps.
Sadly drones cannot yet fly autonomously in complex environments, such as dense forests. In these environments robots need a powerful brain in order to make sense of the complex world around them. Instead of relying on sophisticated sensors, the forest-savvy drone uses a pair of simple cameras and "very powerful” artificial-intelligence algorithms to interpret the images to recognize man-made trails. If a trail is visible, the software steers the drone in the corresponding direction.
The algorithm is a “deep neural network” that learns from training examples obtained from 20 Kimages of trails gathered by helmet cams while walking trails in the Swiss Alps.
