General Atomics Aeronautical Systems (GA-ASI) has successfully completed a simulated autonomous shoot-down during a test involving both live and virtual aircraft.
The test included a simulated autonomous engagement where the MQ-20 Avenger drone successfully executed a missile shot against live targets.
Go deeper with GlobalData
The MQ-20, owned by GA-ASI, utilised cutting-edge autonomy software provided by the government to coordinate with both live and virtual aircraft during the exercise.
Aerospace and defence company Shield AI also contributed its software to the operation.
GA-ASI’s recent flights have highlighted the significance of adhering to “government reference architectures,” which facilitate compatibility between various hardware and software components.
During the exercise, the MQ-20 demonstrated several capabilities including dynamic formation flying with manned aircraft, autonomous decision-making, collaboration with human-operated command systems, and executing an autonomous interception of two live aircraft culminating in a simulated missile engagement.
US Tariffs are shifting - will you react or anticipate?
Don’t let policy changes catch you off guard. Stay proactive with real-time data and expert analysis.
By GlobalDataThe demonstration exhibited the current state of autonomy in Group 5 uncrewed aerial vehicles (UAVs) and their potential for future applications.
GA-ASI advanced programs vice president Michael Atwood said: “This event reflects the kind of interoperability and adaptability we believe is essential for future autonomy efforts. Being able to rapidly integrate and test autonomy elements from multiple vendors helps ensure the most effective capabilities are available to the warfighter, regardless of origin.”
A notable aspect of the test was the seamless transition mid-flight from government-supplied autonomy software to Shield AI’s Hivemind software on board the MQ-20.
This switch is claimed to have no impact on the stability or continuity of the mission, showcasing how standardised architectures can facilitate integration from diverse sources.
The implications of this test are significant for the ongoing development of autonomous systems. By adhering to a common reference architecture, there is support for a flexible autonomy “app store” model.
This approach allows for the inclusion of technology from a wide range of vendors without exclusive dependence on any single provider. It encourages modular design, fosters continuous innovation, and expedites the deployment of new autonomy features in line with commercial software development practices.
