General Atomics claims fully autonomous AI-piloted flight with Avenger MQ-20A
Avenger MQ-20A, formerly known as Predator C. (Photo: USN)
A company-owned Avenger MQ-20A UAS was used on 12 September by General Atomics Aeronautical Systems to fly a military aircraft with an AI pilot and operationally relevant mission systems software.
The company revealed on 19 September that the ‘completely autonomous flight’ with the AI pilot lasted for about 30 minutes as part of a ‘cooperating live, virtual, and constructive UAS swarm’.
General Atomics employed its Reinforcement Learning (RL) architecture to develop and validate an RL agent in an operationally relevant environment — specifically, enabling ‘chase and avoid’ behaviour in which real-time updates were made to the flight path in order to avoid adversaries using live fused tracks.
The live tracks were provided to the system using a TacIRST embeddable infrared search and track sensor system supplied by Lockheed Martin.
General Dynamics Mission Systems supplied the mission computer for the flight, which is part of a series by General Atomics to demonstrate AI and machine learning concepts for advanced UAS.
Related Equipment in Defence Insight
More from Air Warfare
-
M-345 officially enters service as trainer for Italian Air Force
The Leonardo M-345 High-Efficiency Trainer (HET) basic/advanced trainer is similar to the M-346, which is the second part of the Italian Air Force’s training system, but is a substantially smaller and less powerful aircraft.
-
Belgium’s F-35A order progresses at it awaits first jet delivery by late 2025
The first aircraft delivery timeline confirmation comes as Belgium weighs up an additional F-3A buy from Lockheed Martin.
-
Enhancing education: How CAE is embracing new technology to boost military training
In Conversation... Shephard's Gerrard Cowan talks to CAE's Marc-Olivier Sabourin about how the training and simulation industry can help militaries achieve essential levels of readiness by leveraging new technology, innovative procurement methods and a truly collaborative approach.