Military Embedded Systems

AI pilots Avenger UAS in completely autonomous flight


September 20, 2022

Lisa Daigle

Assistant Managing Editor

Military Embedded Systems

Image courtesy GA-ASI.

SAN DIEGO. General Atomics Aeronautical Systems, Inc. (GA-ASI) used a company-owned Avenger MQ-20A unmanned aircraft system (UAS) to fly a military aircraft using an artificial intelligence (AI) pilot and an open architecture-based sensor system. 

During the early-September flight, the Avenger’s completely autonomous flight used an AI pilot for nearly 30 minutes as a part of a cooperating live, virtual, and constructive UAS swarm. The team flew “chase-and-avoid" maneuvers during which real-time updates were made to the flight path in order to avoid adversaries using live fused tracks. Live tracks were provided to the system using the infrared search and track (IRST) sensor network supplied by Lockheed Martin, an open-architecture, embeddable sensor system. 

According to the GA-ASI account, the team used a government-furnished CODE autonomy engine and the government-standard OMS messaging protocol to enable communication between the GA-ASI "Reinforcement Learning" (RL) RL agent and the tactical IRST, which proved that using government standards, such as CODE and OMS, rapid integration of autonomy for collaborative combat aircraft becomes possible.



Featured Companies

Lockheed Martin

6801 Rockledge Drive
Bethesda, MD 20817