An AI sensor precisely measures the orientation of the Milky Way.
A new research study draws inspiration from an insect species which evolved 130 million years ago to improve navigation systems in drones, robots and satellites.
The dung beetle is the first known species to Milky Way They must navigate at night, using the star constellation as a reference point, to roll the dung balls in a straight line away from their competitors.
Swedish researchers made this discovery in 2013, and a decade later, Australian engineers are modeling the same technique used by the dung beetle to develop an AI sensor that can accurately measure the orientation of the Milky Way in low light.
Remote sensing engineer Professor Javaan Chahl of the University of South Australia and his team of PhD students have used computer vision to demonstrate that the large strip of light that forms the Milky Way is not affected by motion blur, unlike individual stars.
The Milky Way as a navigation aid
“Nocturnal dung beetles move their heads and bodies extensively when rolling dung balls across a field. They need a fixed landmark in the night sky to help them steer in a straight line,” says Prof. Chahl. “Their tiny compound eyes make it difficult to distinguish individual stars, especially while they are moving, while the Milky Way is clearly visible.”
UniSA Professor Javaan Chahl explains how dung beetles and the Milky Way are helping engineers improve navigation systems in drones, robots and satellites. Image credit: University of South Australia
In a series of experiments using a camera mounted on the roof of a vehicle, UniSA researchers captured images of the Milky Way while the vehicle was both stationary and moving. Using the information from these images, they have developed a computer vision system that reliably measures the orientation of the Milky Way. This is the first step towards building a navigation system.
Research results and future directions
Their results were published in the journal Biomimetics.
Lead author and UniSA PhD student Yiting Tao says the orientation sensor could be a backup method for stabilizing satellites and help drones and robots navigate in low-light conditions, even when severe blurring occurs due to motion and vibration.
“The next step is to install the algorithm on a drone and enable it to control the aircraft during night flight,” says Tao.
The sun helps many insects navigate during the day, including wasps, dragonflies, honey bees, and desert ants. At night, the moon also serves as a landmark for nocturnal insects, but is not always visible, so dung beetles and some moths use the Milky Way for orientation.
Professor Chahl says insect vision has long inspired engineers in navigation systems.
“Insects have been solving navigation problems for millions of years, including problems that even the most advanced machines struggle with, in a tiny package. Their brains are made up of tens of thousands of neurons, compared to the billions of neurons in humans, and yet they manage to find solutions from the natural world.”
Reference: “Computer Vision Techniques Demonstrate Robust Orientation Measurement of the Milky Way despite Image Motion” by Yiting Tao, Asanka Perera, Samuel Teague, Timothy McIntyre, Eric Warrant and Javaan Chahl, June 20, 2024, Biomimetics.
DOI: 10.3390/biomimetics9070375
