[youtube=https://www.youtube.com/watch?v=uU0WDWV6au8]
If you’ve ever flown an RC plane or even a quadcopter you’ll know the exciting experience of trying to land the thing and ending up in a pond or a tree. That’s fine when you pay a few hundred for your drone but what if your drone costs $1 million and needs to fly around spying on bad guys? How do you keep it from crashing into a larch?
Researchers at the University of Bristol and BMT Defence Services might have an answer.
Their project uses a standard RC plane with a uniquely shaped wing. The wing can reshape itself as it flies, allowing for the system to swing up as it lands like a bird approaching its perch. While the video doesn’t show it actually landing like a bird the researchers expect that a little machine learning and some luck will let them land without taking up too much runway space.
From the release:
Current UAVs are somewhat restrictive in that they have fixed and rigid wings, which reduces the flexibility in how they can fly. The primary goal of the work was to look at extending the operation of current fixed wing UAVs by introducing morphing wing structures inspired by those found in birds. To control these complex wing structures, BMT utilised machine learning algorithms to learn a flight controller using inspiration from nature.
This morphing wing scoops the air, sends the UAV up slightly and then on a much sharper and shorter trajectory. Unfortunately they haven’t perfected grappling claws to replace the landing gear but they’ve got the swooping motion down pretty well and time will tell when UAVs will come in for a landing like ravens on telephone wire.
