Navy, Air Force Research Labs Collaborate on UAV Guidance Software Development

The Naval Research Laboratory has teamed up with the Naval Air Systems Command and Air Force Research Laboratory to further develop a software system that works to guide  unmanned aerial vehicles in simulated air combat missions.

NRL said Wednesday that the U.S. Navy‘s Center for Applied Research in Artificial Intelligence will support ongoing work on the Tactical Battle Manager platform designed to streamline cross-platform coordination of air combat teams that operate in contested environments.

TBM works to help human operators manage UAVs on air combat teams that include autonomous agents tasked to utilize sensors for environmental observation.

Autonomous agents are equipped with a “Goal Reasoning” system that operates each unit to self-select and pursue mission objectives.

“The main idea here is if the UAV/wingman is left to its own devices, it has the ability to recognize when or how to change its goal or objective as the mission scenario unfolds,” said David Aha, head of the adaptive systems section at  NCARAI.

“While some systems allow users to insert new goals or pre-program the selection of new goals, goal reasoning agents can dynamically select new goals to pursue that are not pre-programmed,” Aha added.

Pilots apply AFRL’s Analytical Framework for Simulation, Integration and Modeling in conjunction with NAVAIR’s Next Generation Threat System to virtual training and testing systems.

You may also be interested in...

Rear Adm. John Lemmon

Navy Engines Project Gains Access to DOD Supercomputers for Simulation Testing; Rear Adm. John Lemmon Quoted

An engines project of the Naval Air Warfare Center aircraft division will gain access to the Department of Defense’s supercomputers, which will aid in conducting simulation tests of naval aviation engines before actual demonstration in a laboratory. As part of the High Performance Computing Modernization Program Frontier Project portfolio, NAWCAD engineers can leverage the computers’ predictive modeling without having to risk actual resources for live demos. 

Leave a Reply

Your email address will not be published. Required fields are marked *