New Software May Help Develop 'Search And Rescue' Drones
Amazingly, thousands get lost in the Swiss forests and mountains, even as about 1,000 calls come every year from injured or lost hikers in the country. A modern team of researchers from the University of Zurich has developed new software giving drones the ability to locate and follow forest paths.
This artificial intelligence software has been used to guide a tiny quadrocopter to search a forest, leading to development of drones that can identify people lost in the wild.
"While drones flying at high altitudes are already being used commercially, drones cannot yet fly autonomously in complex environments, such as dense forests. In these environments, any little error may result in a crash, and robots need a powerful brain in order to make sense of the complex world around them," Davide Scaramuzza, who participated in the research, said in a press release.
With the help of a "deep neural network," or a computer algorithm solving complex problems by training and taking up a number of example tests, it simulates the activity of the human brain. Scientists used information from hours of hiking on various trails in the Swiss Alps, which included more than 20,000 images caught by a helmet camera.
It was gladdening to find that the deep neural network could find the right path 85 percent of the time, compared to humans who did it 82 percent of the time. Still, a lot more research is needed in the work.
"Many technological issues must be overcome before the most ambitious applications can become a reality. But small flying robots are incredibly versatile, and the field is advancing at an unseen pace. One day robots will work side by side with human rescuers to make our lives safer," said Luca Gambardella, a member of the research team.
"Now that our drones have learned to recognize and follow forest trails, we must teach them to recognize humans," added Scaramuzza.
The findings were published in Dec.17,2015 issue of IEEE Transactions on Control Systems Technology.