General Atomics Aeronautical Systems (GA-ASI) says it has successfully used AI pilots to control its MQ-20 Avenger unmanned aircraft during live air combat maneuvers.
On April 6, the company showcased their live, virtual, constructive (LVC) collaborative combat aircraft (CCA) ecosystem by conducting collaborative maneuvers between human and AI pilots, utilizing a Low Earth Orbit (LEO) satellite communication (SATCOM) provider’s IP-based mission beyond line of sight (BLOS) datalink, which also enabled rapid retraining and redeployment of AI pilots while the aircraft was airborne.
GA-ASI achieved a breakthrough in utilizing a LEO SATCOM provider’s connection on an unmanned combat aerial vehicle, equipped with L3Harris Technologies and Ball Aerospace’s BLOS datalink solutions, demonstrating its commitment to integrating advanced technologies for future warfare.
The company’s CCA ecosystem enabled human-machine teaming, where human operators provided commands via HOTAS controls, which were transmitted through LEO SATCOM to AI pilots running reinforcement learning (RL) algorithms, autonomously tracking and maneuvering while receiving dynamic updates from operators. The agents’ performance data were collected, retrained, and redeployed in a matter of minutes, demonstrating effective collaboration between human and AI pilots.
“The flight demonstrated GA-ASI’s unmatched ability to fly autonomy on real, tactically relevant, unmanned combat aerial vehicles,” said GA-ASI senior director of advanced programs Michael Atwood. “It displayed effective BLOS command and control through the collaboration between three defense primes. This showcases our rapidly maturing CCA mission system suite and moves us one step closer to providing this revolutionary capability to the warfighter.”