GA-ASI tests CODE autonomy engine on Avenger UAS

General Atomics Aeronautical Systems (GA-ASI) announced on December 4 that it had recently flown an Avenger unmanned aircraft system (UAS), equipped with a government-supplied Collaborative Operations in Denied Environment (CODE) autonomy engine.

During the flight test – which occurred on October 28 at an undisclosed location – the CODE software controlled the Avenger’s manoeuvring for more than two hours without needing any traditional pilot input. GA-ASI also added behavioural functions to the software, allowing the UAS to conduct a coordinated air-to-air search with up to six aircraft – five of which were virtual for this demonstration. The autonomous flight’s successful air-to-air search mission was set by a CODE operator, who used a small form factor commercial computer running government-provided software to issue objectives.

Avenger UAS [GA-ASI]
GA-ASI's Avenger unmanned aircraft system (UAS) conducted an flight demonstration, equipped with the US government-supplied Collaborative Operations in Denied Environment (CODE) autonomy engine, from an undisclosed location on October 28, 2020. GA-ASI

Operator mission inputs were shared to the flying constellation of unmanned aircraft using Link 16-formatted messages that followed the Joint Range Extension Applications Protocol (JREAP). These inputs were passed to the UAS via ground and air adapter services, which were created by GA-ASI. The firm adds that “the open architecture of the CODE software enables communications between the aircraft, the CODE software and the autopilot.”

David R Alexander, president of GA-ASI, said: “This represents a big step up on the path to more sophisticated autonomous missions for unmanned aircraft where operator input can be minimised to support optimal manning of multiple products for complex air battles. For this initial flight, we used [the] Avenger as the flight surrogate for the Skyborg capability set, which is a key focus for [GA-ASI’s] emerging air-to-air portfolio.”

GA-ASI states that the testing of the CODE autonomy engine was implemented to further understand the cognitive artificial intelligence (AI) processing on larger UAS platforms, such as the Avenger. “Using a network-enabled Tactical Targeting Network Technology (TTNT) radio for mesh network mission communications, GA-ASI was able to show [the] integration of emerging Advanced Tactical Data Links (ATDL) and separation between flight- and mission-critical systems,” the firm added.