General Atomics Aeronautical Systems (GA-ASI) has successfully conducted a flight test of its Collaborative Combat Aircraft (CCA) system in El Mirage, California. The demonstration saw an MQ-20 Avenger unmanned aircraft take off from GA-ASI’s Desert Horizon facility for three autonomous combat simulations.
The MQ-20 Avenger, developed by GA-ASI, is a high-speed, multi-mission Remotely Piloted Aircraft (RPA) system that is capable of performing wide-area surveillance, time-sensitive strike missions over land or sea, and a host of other challenging military or civilian missions. The aircraft has a much higher operational and transit speed than current Predator B-series aircraft, resulting in quick response and rapid repositioning for improved mission flexibility and survivability.
During the flight test, the Avenger was paired with a “digital twin” to assess the CCA’s artificial intelligence and machine learning capability in live, virtual, and constructive multi-objective missions. The aircraft employed GA-ASI’s reinforcement learning (RL) architecture to develop and apply deep learning algorithms for various actions. The demonstration saw the single RL agent assist the live plane in avoiding threats while the multi-RL agent flew both the live and virtual MQ-20s as they deflected and chased targets. Meanwhile, the hierarchical RL agent leveraged sensor information to choose the drone’s next steps depending on the scenario.
According to GA-ASI, all three RL agent models proved the CCA’s pilot capability to complete aerial missions by exploiting real-time information and processing critical decisions without the help of human operators. “The concepts demonstrated by these flights set the standard for operationally relevant mission systems capabilities on CCA platforms,” said GA-ASI Advanced Programs Senior Director Michael Atwood.