Tiny robot drones learn to navigate the world like honeybees

Tiny drone robots learn to navigate the world like bees

By Jacek Krywko edited by Sarah Lewin Frasier

Insect-sized drones are too small to be carried in complex navigation systems. To help small autonomous fliers find their way, researchers are taking inspiration from bees with Bee-Nav, described today in Nature.

A bee that leaves the hive first performs a short learning flight to memorize nearby landmarks, says the study’s lead author, Guido de Croon, an artificial intelligence and robotics researcher at Delft University of Technology in the Netherlands. When a bee flies away, “it keeps track of the direction and speed of its movement,” says de Croon, in a process called path integration. Because path integration tends to accumulate tiny measurement errors over time, the insect relies on the memorized landmarks to correct its trajectory upon returning home. De Croon and his colleagues copied this workflow.

First, a drone performs a bee-like learning flight around its starting point using a tiny omnidirectional camera to capture the surrounding landscape. During flight, it trains a tiny onboard neural network to map these images onto original vectors, essentially invisible arrows pointing toward the launch pad. This establishes a safety zone called the learned return zone. Once trained, the drone can be sent far and back first using trajectory integration, backtracking based on measured speed and direction. If the drone ends up anywhere within its starting safety zone, the visual neural network guides it back.

On supporting science journalism

If you enjoy this article, please consider supporting our award-winning journalism by subscription. By purchasing a subscription, you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.

The Bee-Nav does this using a commercially available Raspberry Pi 4 computer, the size of a credit card, that runs neural networks with between 3.4 and 42.3 kilobytes of memory, thousands of times less than what conventional mapping setups use. The team’s test robots set up at a distance of up to 600 meters (1,970 feet) outdoors, despite gusty winds and sun glare being blinding to the cameras.

“What I find particularly interesting is how few calculations are required,” says Sarah Bergbreiter, a mechanical engineer at Carnegie Mellon University, who was not involved in the study. “For the small-scale robots that my group and others are working on, this is the kind of approach that makes serious outdoor deployments plausible.”

De Croon’s team is still working on some challenges for the platform, such as navigating between multiple stored locations and managing starting points without landmarks. “Platforms running Bee-Nav will also need local obstacle avoidance and planning capability if the environment is cluttered or dynamic,” says Sean Humbert, a mechanical engineer at the University of Colorado at Boulder, who was not involved in the study.

But even now, de Croon says, Bee-Nav can make autonomous outdoor drones smaller and more energy efficient. “We could easily put it on a 50 gram, or even 30 gram drone,” says de Croon. Shrinking autonomous drones to the size of real bees would require solving other fundamental problems like battery miniaturization, he said. “But we hope that when these problems are resolved in the long term, we will have the information necessary to do so,” de Croon said.

It’s time to defend science

If you enjoyed this article, I would like to ask for your support. Scientific American has been defending science and industry for 180 years, and we are currently experiencing perhaps the most critical moment in these two centuries of history.

I was a Scientific American subscriber since the age of 12, and it helped shape the way I see the world. SciAm always educates and delights me, and inspires a sense of respect for our vast and magnificent universe. I hope this is the case for you too.

If you subscribe to Scientific Americanyou help ensure our coverage centers on meaningful research and discoveries; that we have the resources to account for decisions that threaten laboratories across the United States; and that we support budding and working scientists at a time when the value of science itself too often goes unrecognized.

In exchange, you receive essential information, captivating podcasts, brilliant infographics, newsletters not to be missed, unmissable videos, stimulating games and the best writings and reports from the scientific world. You can even offer a subscription to someone.

There has never been a more important time for us to stand up and show why science matters. I hope you will support us in this mission.