Communications of the ACM
Drones Learn to Search Forest Trails For Lost People
New software allows drones to autonomously detect and follow forest paths, which could allow them to help find and rescue missing persons.
Credit: UZH; USI; SUPSI
Researchers at the University of Zurich, the Universita della Svizzera italiana, and the University of Applied Sciences and Arts of Southern Switzerland have developed software that enables drones to autonomously detect and follow forest paths. The researchers say the drones could be used to help find and rescue missing persons in forested and mountainous areas.
The drone observes the environments through a pair of small cameras and uses artificial-intelligence algorithms to interpret the images to recognize man-made trails.
Interpreting an image taken in a complex environment such as a forest is usually very difficult for a computer. The researchers solved the problem using a deep neural network, which was trained on several hours of footage and more than 20,000 images of hiking trails in the Swiss Alps.
The researchers found when tested on a new, previously unseen trail, the deep neural network was able to find the correct direction in 85 percent of cases. Meanwhile, humans faced with the same task only found the trail 82 percent of the time.
The researchers say they still have much work to do before a fully autonomous fleet of drones will be able to swarm forests in search of missing people. "Now that our drones have learned to recognize and follow forest trails, we must teach them to recognize humans," says University of Zurich professor Davide Scaramuzza.
From University of Zurich
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found