Bees are among the most hardworking creatures on the planet. But in many parts of the world, honeybee colonies are declining so quickly that even the United Nations is worried. About two-thirds of the crops that feed the world rely on pollination by bees and other insects. Without them, we’d be looking at an agricultural doomsday scenario. And this is exactly what a University of Maryland professor wants to avoid – with the help of an army of tiny drones.
Yiannis Aloimonos is developing RoboBeeHive, an artificial beehive that would house a bunch of small drones within a bigger, arm-length drone. This beehive will be able to attach itself to a tree, opening up to unleash a swarm of tiny drones.
According to a statement by the University of Maryland Institute for Advanced Computer Studies:
The drones use artificial intelligence to autonomously navigate and avoid obstructions — animals, trees, or other drones busy spreading pollen — as they carry pollen between plants that stick to simulated bee fur. And if the weather takes a turn for the worse, a message from the “hive” calls them back.
The biggest challenge for Aloimonos and his team was to assemble the processors, cameras, and other sensors on the limited surface area of the palm-size drones. So, they sought inspiration from the bees themselves.
Pollination drones navigate like busy bees
Instead of mapping the world with LiDAR or other systems that larger drones might use, these pollinator drones use what’s known as “active perception.” Meaning, like busy bees, they’re in constant motion to gain a better understanding of their surroundings. This helps the drones to collect data about the space around them and move autonomously.
Also read: Can drone swarms fly indoors without bumping into each other?
With two onboard cameras providing 360-degree vision, these pollination drones can also be used for tasks other than pollinating crops. For example, inspecting bridges to spot cracks and other problems, or assisting in search-and-rescue operations by self-navigating through rubble and broken windows to find trapped people.
Nitin Sanket, a graduate student working with Aloimonos, says:
The general idea is if you want to do these operations, having human operators is expensive. You need a lot of training. And the other thing is, if you deploy 1,000 drones, you need 1,000 operators, which is not always possible. That’s why we want them to be as autonomous as possible; it makes it cheaper, faster and more efficient in every way.
Artificial intelligence has gained prominence in the last five years. That has helped us to do things, which were not possible at this scale before. We can have the capability to do stuff which the bigger drones do, but with more minimalistic software.
Read more: When small drones team up to deliver heavy packages
FTC: We use income earning auto affiliate links. More.
Comments