General Atomics Aeronautical Systems (GA-ASI) has announced that on October 28, the firm tested one of its artificial intelligence (AI) driven Avenger drones. The release did not indicate where the test took place but it did emphasize that the drones were built in cooperation with the Defense Advanced Research Projects Agency (DARPA).
GA-ASI further noted that it used a government-supplied Collaborative Operations in Denied Environment (CODE) autonomy engine, which was installed on the Avenger drone, in order to support air-to-air targeting missions. CODE was developed by DARPA to deal with the scalability and cost-effectiveness issues concerning unmanned aircraft systems operations.
"DARPA’s CODE program aims to overcome these limitations with new algorithms and software for existing unmanned aircraft that would extend mission capabilities and improve U.S. forces’ ability to conduct operations in denied or contested airspace," read the project's webpage.
"CODE researchers seek to create a modular software architecture beyond the current state of the art that is resilient to bandwidth limitations and communications disruptions yet compatible with existing standards and amenable to affordable retrofit into existing platforms."
The Air Force's Skyborg program
CODE is also focused on developing systems that would still function optimally "in denied or contested airspace," especially during significant electronic jamming. Finally, GA-ASI's October test also supports work that the firm is doing for the Air Force's Skyborg program.
“This represents a big step on the path to more sophisticated autonomous missions for unmanned aircraft where operator input can be minimized to support optimal manning of multiple products for complex air battles,” said GA-ASI President David R. Alexander. “For this initial flight, we used Avenger as the flight surrogate for the Skyborg capability set, which is a key focus for GA-ASI emerging air-to-air portfolio.”
During the experimental autonomous flight, the CODE software piloted the Avenger drone for over two hours without any human input.