{"id":35042,"date":"2019-08-05T12:00:48","date_gmt":"2019-08-05T12:00:48","guid":{"rendered":"https:\/\/one.sightlinemg.com\/c4isrnet\/uncategorized\/2019\/08\/05\/can-a-dragonfly-teach-a-missile-how-to-hunt\/"},"modified":"2026-08-08T00:11:31","modified_gmt":"2026-08-08T00:11:31","slug":"can-a-dragonfly-teach-a-missile-how-to-hunt","status":"publish","type":"post","link":"https:\/\/one.sightlinemg.com\/c4isrnet\/artificial-intelligence\/2019\/08\/05\/can-a-dragonfly-teach-a-missile-how-to-hunt\/","title":{"rendered":"Can a dragonfly teach a missile how to hunt?"},"content":{"rendered":"\n

WASHINGTON \u2014 A computational neuroscientist is studying whether a dragonfly\u2019s excellent hunting skills can be replicated in a missile\u2019s ability to maneuver<\/a> and destroy targets midair with better precision.<\/p>\n\n\n\n

Dragonflies are vicious little creatures with a hit-to-kill track record of 95 percent, meaning only 5 percent of its prey escapes.<\/p>\n\n\n\n

Sandia National Laboratories\u2019 Frances Chance is building algorithms that simulate how a dragonfly processes information when intercepting prey, and she\u2019s testing them in a virtual environment. So far, the results are promising.<\/p>\n\n\n\n

The laboratories are federally funded and focus on national security missions through scientific and engineering research. The project is a yearlong, high-risk, high-gain effort that will wrap up in September, and it is funded by Sandia\u2019s Autonomy for Hypersonics Mission Campaign, Chance said.<\/p>\n\n\n\n

\u201cI think what is really interesting about insects, in general, is they do something really fast and really well, but they are not particularly smart in the way you or I would think of ourselves as being smart,\u201d Chance told Defense News in a recent interview.<\/p>\n\n\n\n

While insects may not be the right fit for studying cognitive capabilities to develop complex artificial intelligence, they are ideal for developing efficient computations for intercept capability. A dragonfly can react to a particular prey\u2019s maneuvers in 50 milliseconds, Chance explained. That amount of time accounts for information to cross three neurons in a dragonfly\u2019s brain. This indicates the dragonfly doesn\u2019t learn how to hunt, but rather the skill is inherent and part of its brain\u2019s hard-wiring.<\/p>\n\n\n\n

\u201cThe challenge then is: Is there anything that we can learn from how dragonflies do this that we can then bring to the next generation of missiles, or maybe even the next-next generation of missiles?\u201d Chance said.<\/p>\n\n\n\n

By developing an artificial neural network that mimics a dragonfly\u2019s ability to hunt and then applying it to missile capabilities that rely on computation-heavy systems, one could reduce the size, weight and power needed for a missile\u2019s onboard computers; improve intercept techniques for targets such as hypersonic weapons; and home in on targets using simpler sensors.<\/p>\n\n\n\n

If the model of a dragonfly\u2019s neural circuit developed through Chance\u2019s research shows enough promise, she would then pass the information to scientists, who would try to directly apply it to weapons systems.<\/p>\n\n\n\t