For the first time ever, an unmanned aerial vehicle (UAV) has performed a perched landing thanks to machine learning algorithms. The ground-breaking development that is a work of the University of Bristol and BMT Defence Services has the potential to “significantly impact intelligence-gathering and the delivery of aid in a humanitarian disaster.”
Currently, UAVs are quite restrictive as they have fixed and rigid wings. This affects not only the way they can fly but also the way they can land.
Now, the researchers built a fixed but flexible wing aircraft that can land in a small or confined space. They got their inspiration from nature and decided to introduce that aspect into their technology. They used morphing wing structures, similar to those found in birds, and machine learning algorithms to control these complex structures.
“The application of these new machine learning methods to nonlinear flight dynamics and control will allow us to create highly manoeuvrable and agile unmanned vehicles. I am really excited about the potential safety and operational performance benefits that these new methods offer,” said Dr Tom Richardson, who is a Senior Lecturer in Flight Mechanics in the Department of Aerospace Engineering at the University of Bristol.
The UAV that uses machine learning algorithms has already been successfully tested at altitude to validate the approach, and the researchers are now working on a system that can perform repeatable landings.
Reference:
University of Bristol (http://www.bris.ac.uk/news/2017/january/uav-perched-landing.html)
The Wonderful World of Algorithms 