Australian engineers have developed an AI sensor that accurately measures the orientation of the Milky Way, inspired by the navigational abilities of dung beetles, potentially transforming navigation systems for drones, robots, and satellites.
Researchers at the University of South Australia have taken a cue from an unlikely source - the humble dung beetle - to create an AI sensor that could significantly improve navigation systems in various technologies. The study, published in the journal Biomimetics, draws inspiration from the beetle's unique ability to use the Milky Way for orientation.
Professor Javaan Chahl, a remote sensing engineer leading the research, explained the significance of the dung beetle's navigational technique: "Nocturnal dung beetles move their head and body extensively when rolling balls of manure across a field, needing a fixed orientation point in the night sky to help them steer in a straight line."
The dung beetle, which evolved 130 million years ago, was first discovered to use the Milky Way for navigation by Swedish researchers in 2013. This insect focuses on the constellation of stars as a reference point to roll dung balls away from competitors in a straight line.
Building on this natural phenomenon, Chahl's team used computer vision to demonstrate that the large stripe of light forming the Milky Way is not affected by motion blur, unlike individual stars. This insight led to the development of an AI sensor that can accurately measure the Milky Way's orientation in low light conditions.
The research team conducted experiments using a camera mounted on a vehicle roof, capturing images of the Milky Way while both stationary and in motion. These images were then used to develop a computer vision system that reliably measures the Milky Way's orientation.
Yiting Tao, the lead author and a Ph.D. candidate at UniSA, highlighted the potential applications: "The orientation sensor could be a backup method to stabilize satellites and help drones and robots to navigate in low light, even when there is a lot of blur caused by movement and vibration."
The next phase of the research will involve implementing the algorithm on a drone to control its flight during nighttime operations.
This study is part of a broader trend in engineering that looks to nature for solutions to complex problems. Prof Chahl noted, "Insects have been solving navigational problems for millions of years, including those that even the most advanced machines struggle with. And they've done it in a tiny little package."
The research team's innovative approach could have far-reaching implications for various fields, including aerospace, robotics, and autonomous vehicle navigation. By mimicking the dung beetle's ability to use celestial cues, engineers may be able to create more reliable and efficient navigation systems for a wide range of applications.