Bristol University are working on an unmanned drone that flies like a bird.
The end of runways? Watch the incredible 'perching plane' that can land like a bird
Algorithm taught drone how to perform perched landings like birds
Researchers used a fixed wing drone because it can reshape while flying
Part of the wing tilts up to create more drag and the other keeps control of flight
Drone makers have pulled inspiration from nature for their latest design – a drone that makes perched landings like a bird.
Researchers combined a morphing wing drone and machine learning algorithms to create a system that lets the machine perform perched landings on the ground.
The fixed wing aircraft also has the ability to land in small or confined places, which could be used to deliver aid in humanitarian disasters.
Scroll down for videos
Researchers combined a morphing wing drone and machine learning algorithms to create a system that lets the machine perform perched landings on the ground. The fixed wing aircraft also has the ability to land in small or confine places, which deliver aid in disasters
+3
Researchers combined a morphing wing drone and machine learning algorithms to create a system that lets the machine perform perched landings on the ground. The fixed wing aircraft also has the ability to land in small or confine places, which deliver aid in disasters
THE PERCHING DRONE
Researchers from the University of Bristol and BMT Defence Services have designed a drone that make perched landings like a bird.
The team designed a machine learning algorithm and combined it with a morphing wing drone - which can now perform perched landings on the ground.
To control these wing structures, BMT harnessed the power of machine learning algorithms to teach the machine how to using inspiration from nature.
This ability allows the drone to reach small and confined places, which could be use to deliver aid in disaster zones.
Researchers from the University of Bristol and BMT Defence Services set out to transform traditional fixed wing unmanned aerial vehicle (UAV) by adding morphing wing structures inspired by those found in birds.
The team chose a morphing wing drone, as it can reshape itself in mid flight.
This is the opposite of current UAVs, as these have fixed and rigid wings, which reduces the flexibility in how they can fly.
The wings let the drone swoop in for a perched landing - it lifts its wing just like a bird swooping in to land on the ground.
To control these complex wing structures, BMT utilized machine learning algorithms to learn a flight controller using inspiration from nature.
'Innovation is at the heart of everything we do at BMT and R&D projects provide us with the opportunity to work with our partners to develop cutting edge capabilities that have the potential to revolutionize the way we gather information,' said Simon Luck, Head of Information Services and Information Assurance at BMT Defence Services.
The drone has been tested in the field to demonstrate the team's new approach and researcher have been working on developing a system that can perform a repeatable ground landing.
'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, Senior Lecturer in Flight Mechanics in the Department of Aerospace Engineering at the University of Bristol.
To control these complex wing structures, researchers utilized machine learning algorithms to learn a flight controller using inspiration from nature.
+3
To control these complex wing structures, researchers utilized machine learning algorithms to learn a flight controller using inspiration from nature.
'I am really excited about the potential safety and operational performance benefits that these new methods offer.'
The 18-month research project was delivered as part of the Defence Science and Technology Laboratory...