Researchers at the University of Bristol and the BMT Defence Services have successfully performed a perched landing with an unmanned aerial vehicle (UAV) using machine learning algorithms for the first time.
The development was accomplished using a morphing wing UAV and machine learning that generates a trajectory to perform a perched landing on the ground. This may allow fixed-wing drones to land in small or confined spaces potentially impacting the way intelligence-gathering or the delivery of aid in a humanitarian disaster is performed.
A time lapsed image of an unmanned aerial vehicle performing a perched landing. Source: University of Bristol Current drones are restrictive in that they have fixed or rigid wings that reduce the flexibility in how they can fly, according to researchers. The University of Bristol was able to test the UAV at an altitude to validate the perched landing and they are working on a system to perform repeatable ground landing.
The goal of the work is to extend the operation by morphing wing structures inspired by the wings of birds. Machine learning algorithms control the wing structures using a flight controller with an inspiration from nature, the team said.
“The application of these new machine learning methods to nonlinear flight dynamics and control will allow us to create highly maneuverable and agile unmanned vehicles,” said Dr. Tom Richardson of the Department of Aerospace Engineering at the University of Bristol. “I am really excited about the potential safety and operational performance benefits that these new methods offer.”
