Engineers at the California Institute of Technology (Caltech) have developed an artificial intelligence (AI) algorithm that enables an unmanned aerial vehicle (UAV) to herd birds away from airspace around an airport.
After testing the algorithm on a flock of birds near a field in South Korea, the team found that a single UAV could keep a flock of dozens of birds away from designated airspace.
To teach a UAV to herd birds autonomously, Caltech researchers studied and adapted a mathematical model to describe how flocks build and maintain formations, how they respond to threats along the edge of the flock, and how they communicate that threat through the flock. Their work improves on algorithms designed for herding sheep, which only needed to work in two dimensions instead of three.
Caltech researchers reverse-engineered the mathematical description of flocking behaviour, to determine how flocks would respond to external threats. This information formed the basis of the new herding algorithm, which produces ideal flight paths for incoming UAVs to move the flock away from a protected airspace without dispersing it.
Soon-Jo Chung, associate professor of aerospace at Caltech, noted that the UAV must be positioned carefully. “If it’s too far away, it won’t move the flock. And if it gets too close, you risk scattering the flock and making it completely uncontrollable. That’s difficult to do with a piloted drone.”
See related article at: http://www.janesairport360.com/article/10736/grazing-herd-returns-to-o-hare
Want to read more? For analysis on this article and access to all our insight content, please enquire about our subscription options at ihs.com/contact