Researchers Reverse-Engineer Hoverflies’ Visual Systems to Detect Drones
A team of researchers at the University of South Australia has reverse engineered the visual systems of hoverflies to detect drones from nearly four kilometers away. The autonomous systems experts at the university worked alongside others at Flinders University and defense company Midspar Systems.
50% Better Detection
The trials that used bio-inspired signal processing techniques demonstrated up to 50% better detection rates than existing methods.
According to the team, these new findings could help combat the threat of IED-carrying drones. The research comes just as these drones are being used in Ukraine.
The work was published in The Journal of Acoustical Society of America.
According to UniSA Professor of Autonomous Systems Anthony Finn, the hoverflies’ visual systems have been mapped before to improve camera-based detections. However, the new research is the first time that bio-vision has been applied to acoustic data.
“Bio-vision processing has been shown to greatly increase the detection range of drones in both visual and infrared data. However, we have now shown we can pick up clear and crisp acoustic signatures of drones, including very small and quiet ones, using an algorithm based on the hoverfly’s visual system,” Prof. Finn says.
Hoverflies have superior visual and tracking skills that have been successfully modeled to detect drones in complex and obscure landscapes. This could involve either military or civilian purposes.
“Unauthorised drones pose distinctive threats to airports, individuals and military bases. It is therefore becoming ever-more critical for us to be able to detect specific locations of drones at long distances, using techniques that can pick up even the weakest signals. Our trials using the hoverfly-based algorithms show we can now do this,” Prof. Finn says.
Increasing Use of Autonomous Aircraft
Dr. Russell Brinkworth, who is Associate Professor in Autonomous Systems at Flinders University, says that aviation regulators, safety authorities, and the wider public would all greatly benefit from the technology. This is especially true as it is becoming increasingly important to monitor the large number of autonomous aircraft being used.
“We’ve witnessed drones entering airspace where commercial airlines are landing and taking off in recent years, so developing the capacity to actually monitor small drones when they’re active near our airports or in our skies could be extremely beneficial towards improving safety,” Dr. Brinkworth says.
“The impact of UAVs in modern warfare is also becoming evident during the war in Ukraine, so keeping on top of their location is actually in the national interest. Our research aims to extend the detection range considerably as the use of drones increases in the civilian and military space.”
Bio-inspired processing improved detection ranges by between 30 and 49 percent when compared with traditional techniques, depending on the type of drone and conditions.
In order to pick up drone acoustics at short to medium distances, researchers observe specific patterns and general signals. However, longer distances mean the signal is weaker, and both techniques are less effective.
According to the researchers, there are similar conditions in the natural world. For example, hoverflies have powerful visual systems that can capture visual signals in noisy, dark lit regions.
“We worked under the assumption that the same processes which allow small visual targets to be seen amongst visual clutter could be redeployed to extract low volume acoustic signatures from drones buried in noise,” Dr. Brinkworth says.
The researchers converted acoustic signals into two-dimensional “images,” and they used the neural pathway of the hoverfly brain to improve and suppress unrelated signals and noise. This increased the detection range for the sounds they wanted to detect.
The breakthrough research was funded by the Department of Defence’s Next Generation Technologies Fund in Australia, which partly supports solutions to address the weaponization of drones.