Tiny insects could lead to big changes in robot design
Sean Humbert and Leopold Beuken inspecting sensors on a fixed wing UAS.
Sean Humbert is unlocking the biological secrets of the common housefly to make major advances in robotics and uncrewed aerial systems (UAS).
A professor in the Paul M. Rady Department of Mechanical Engineering and director of the Robotics Program at the University of Colorado Boulder, Humbert is working to understand how tiny biological systems process sensory information as they move through the world.
This basic sounding concept involves extremely complex science and engineering.
“Insects aren’t built like robots,” Humbert said. “If I have a robot and I want it to perceive the environment, I tend to put a larger, high fidelity lidar system on it. Flies instead have small, low-quality sensors throughout their bodies. Due to the way that the measurements are processed by the nervous system, you can extract similar levels of information as bulky robotic sensors. We want to take advantage of what nature does.”
The research has drawn the interest of the U.S. Air Force Research Laboratory, which awarded Humbert a five-year, $909,000 grant to advance the work.
He also in the Institute of Electrical and Electronics Engineers (IEEE) Access journal, proposing a mathematical framework for understanding and applying to robotics connections in the flight physics and visual physiology of flies.
Flies may seem an unlikely creature to study for enhancing robots, but Humbert’s co-author and post-doctoral researcher Zoe Turin says the insects have a lot to offer roboticists.
“If you've ever tried to catch or swat a fly, you know that they can be quite capable fliers, despite a lack of computational power,” Turin says. “If we apply principles from how insects operate, then we may be able to develop robots that have similar capabilities at a much smaller size than traditional robots. This has potential applications across a wide variety of industries.”
Although flies are only 6-7 millimeters long and have brains the size of a poppy seed, Humbert said their abilities have evaded researchers, until now. A key element of how flies work is distributed sensing.
Zoe Turin and Eugene Rush in front of a white board with a small UAS.
“It’s taken years to arrive at a model of how the fly’s sensory structure is set up the way it is and to be able to figure out the math behind it,” Humbert said. “This has so much potential going forward. An F-22 fighter jet has a small number of high fidelity, big, expensive sensors that require a lot of backend processing and computation to generate quality measurements. Nature is the exact opposite. It’s small, low fidelity, lightweight, and distributed.”
By unlocking the principles and mathematical optimizations that exist in flies, Turin said researchers will be able to explore similar techniques for robots.
“Understanding more about how insects are able to do what they do has only made them more amazing to me. This framework will hopefully help our engineered systems to react more quickly to unexpected disturbances, such as a sudden gust of wind, while reducing the computational power required,” Turin said.
Over the course of the grant, Humbert will take the models he has developed on flies to conduct proof-of-concept demonstrations and then experimental research using robotic sensor technology.
“This is a wonderful, cool biological principle and we now have the model to explore what nature has constructed,” Humbert said. “It will revolutionize how we think about the design cycle of robotic systems.”