Key Takeaways

Biomimicry is the study of systems in nature to find solutions in human design.
Aviation design can benefit from biomimicry — studying birds can help us make aircraft flight and design more efficient.
AI can help tackle and refine the huge data sets generated by biomimicry research, building algorithms to mimic bird flight or analyzing wing shape, for example.

Who hasn't stared up at a hawk or vulture circling lazily in the sky and wondered how they stay aloft so long? Researchers are now able to tackle this question more systematically using biomimicry, the process of mirroring nature's systems to solve complex human problems.

Their goal is to develop artificial intelligence (AI) algorithms that will allow gliders to mimic the flight behavior and endurance of birds and understand wing structural changes that facilitate silent flight, among other projects. Soon, AI in aviation will transform the types of missions that gliders perform and substantially reduce noise in flight.

Flying Like Birds

AI and biomimicry are already helping aviation researchers understand how gliders can function more efficiently. Gautam Reddy, a graduate student in physics, and a team of his colleagues at the University of California, San Diego, described their biomimicry research in a 2018 article in Nature.

The team equipped a two-meter-wingspan, radio-controlled glider with a flight controller and instruments that could measure vertical wind accelerations along the length of the glider and across its wings. Their working theory was that birds use similar sensory information to identify and navigate thermals.

Between 2015 and 2017, they conducted more than 500 flights near Poway, California, each one lasting 20 to 30 minutes. The aim was to train the glider in a concept called "reinforcement" to navigate thermals autonomously. They used their measurements to build a simple algorithm that would steer the glider toward zones of higher lift.

Another study published in the Flow, Turbulence and Combustion journal, also looked at soaring flight, studying behavior in white storks for clues to how the birds stay aloft so effortlessly. The researchers took data observed during stork flight and created a biomimetic computational model that analyzed the way the wing tip changed shape during flight. The study also looked closely at the airflow features around the wing tip feathers during flight. Similar work in pigeons could also aid wing design. For example, Popular Mechanics points to PigeonBot: a highly sophisticated bird-like robot that researchers are using to study how pigeons change the shape of their wings during flight to gain efficiency.

Taming Unpredictability

Though much valuable information can be gleaned from the concept of biomimicry, field studies can be problematic. Atmospheric conditions vary so much hour to hour and day to day, even in the same location, that building a robust AI algorithm for glider aviation using field measurements alone is quite challenging.

"AI algorithms require a lot of data," Reddy said. "One way to add fidelity to the algorithm would be to use numerical simulation and a process called model-based learning."

This model-based approach, which his team did not use, would involve "flying" a simulated glider repeatedly through a simulated atmospheric environment containing realistic thermals, convective currents and turbulence. Atmospheric data and the glider's response to those conditions could be collected on each simulated flight and then used to systematically update and refine the AI algorithm.

A better strategy, Reddy proposes, would be to extract visual and other sensor information from gliders.

"State-of-the-art gliders actually have better aerodynamic properties than birds," he said. "We can also use instruments to gather higher accuracy measurements of temperature, wind velocity, humidity, barometric pressure and other relevant data."

New Rules of Engagement

AI in aviation certainly offers tantalizing prospects.

"If we can come up with a glider that's as efficient as a bird, it could travel across continents," said Reddy. "That capability could be extremely useful for surveillance or remote sensing missions." The one limitation, he admitted, is that gliders rely on thermals, which are normally present during daylight hours only.

AI-controlled gliders could be a perfect complement to high-altitude surveillance systems, such as the U.S. Air Force's Global Hawk unmanned aircraft.

"Gliders are very small, unpowered and virtually silent," said Reddy. "So, they would not need to fly at high altitude. I think they could provide our military commanders with some very interesting options."

AI in the Cockpit and Beyond

Reddy suggests we try out AI as a navigational aid for pilots to enhance their abilities in the air.

"Pilots would still fly as before," he said, "but would use the AI algorithm to suggest the fastest, most efficient route to their destinations, taking advantage of the fastest-flowing streets (thermals) along the route."

AI and biomimicry could also aid other areas of in-flight performance, creating aircraft that fly silently, similar to an owl swooping on its prey. According to Popular Mechanics, owls can inspire quieter aircraft and turbine blades. Analysis of the wing's trailing edge has found that the orientation of the feathers changes the way the air flows as the owl flies.

In a similar way, hummingbird flight dynamics could help drone flight. For example, Penn State University describes novel modeling that's allowing researchers to simulate hummingbird flight, and Science Daily notes that the data from these studies could refine flying robots.

And it's not just birds. The Biomimicry Institute describes AI coupled with slime mold growth can revolutionize materials design. Along with studying bone growth, researchers are developing new approaches that could make aircraft lighter and use less fuel. Combining generative design, AI and 3D printing can even help us create lightweight components, such as cabin partitions that are strong but use less raw material.

These are just a few examples of how looking to AI and ecosystems can transform aviation systems. It's clear the future holds some exciting advancements in technology still to come, and nature may play a pivotal role in realizing those innovations.

Northrop Grumman is a leader in the development of autonomous aerial reconnaissance systems. If you'd like to learn more about what we do, check out our work in AI and machine learning.