Purdue University scientists have made use of machine learning algorithms to develop flying robots that behave like hummingbirds.
AI helps teach the robots to move around on their own – just like a hummingbird would do, making them suitable for military, as well as search and rescue missions.
Though the robots lack vision, they use their sense of touch to identify different surfaces.
Each touch alters an electrical current, which the researchers can then track.
“The robot can essentially create a map without seeing its surroundings,” says Purdue associate professor Xinyan Deng.
“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.”
Deng and her team have for the record documented key hummingbird maneuvers, such as making a rapid 180-degree turn, and translated them to computer algorithms.
Further study on the physics of insects and hummingbirds allowed the Purdue group to build robots smaller than hummingbirds without compromising the way they fly.
The researchers have built one hummingbird robot weighing 12 grams – the weight of the average adult Magnificent Hummingbird – and another insect-sized robot weighing 1 gram.
These new robots have 3D printed bodies, with the wings being made of carbon fiber and laser-cut membranes.
According to the team, the hummingbird robot can lift up to 27 grams – which is more than its own weight.
Designing their robots with higher lift gives the researchers more wiggle room to eventually add battery and sensing technologies, such as a camera or GPS.
Currently, the robot needs to be tethered to an energy source while it flies – something the researchers hope to change in the near future.
Purdue’s robots have been designed to fly silently just as a real hummingbird does, making them ideal for covert operations.
They can further withstand turbulence, which the researchers demonstrated by testing the dynamically scaled wings in an oil tank.
The robots require only two motors and can control each wing independently of the other – which is how flying animals perform highly agile maneuvers in nature.
Image and content: Jared Pike/Purdue University