Researchers from Purdue University have created flying robots that behave similar to hummingbirds and are trained by machine learning algorithms based on different techniques the bird uses naturally every day. Artificial intelligence, combined with flexible flapping wings, allows the robot to teach itself new tricks. Even though the robot can't see yet, for example, it senses by touching surfaces. Each touch alters an electrical current, which the researchers realized they could track.
"The robot can essentially create a map without seeing its surroundings. This could be helpful in a situation when the robot might be searching for victims in a dark place and it means one less sensor to add when we do give the robot the ability to see," said one of the researchers Xinyan Deng in the study presented at the meeting of International Conference on Robotics and Automation.
As compared to drones, the hummingbird robot uses entirely different aerodynamics due to its flexible wings. The robots have 3D-printed bodies, wings made of carbon fiber, and laser-cut membranes. The 12g robot is able to lift more than its own weight – up to 27g. The robot uses only two motors and can control each wing independently.
“The physics is simply different; the aerodynamics is inherently unsteady, with high angles of attack and high lift. This makes it possible for smaller, flying animals to exist, and also possible for us to scale down flapping-wing robots,” Deng says.
The robotic hummingbirds will not only help with search-and-rescue missions but will also let biologists study hummingbirds more reliably in their natural habitat through the senses of a real robot. “We learned from biology to build the robot, and now biological discoveries can happen with extra help from robots,” Deng said.