Northrop Grumman
Demarch15 1 Promo 6058c7d77ef05

Northrop Grumman Explores AI Game Strategies for DARPA

March 22, 2021
DARPA’s “Gamebreaker” program has recruited participants such as Northrop Grumman to explore the use of AI technology to find ways to “break” a wargame and create advantages over an adversary.

Computer games simulate danger and excitement, although the U.S. Defense Advanced Research Projects Agency (DARPA) is hoping that by applying artificial intelligence (AI), wargames might prove to be invaluable educational tools for its troops. By “playing” wargames that can respond quickly to changing situations using AI, DARPA’s “Gamebreaker” program intends for soldiers to learn how to respond to different circumstances on the battlefield. With the aid of powerful partners like Northrop Grumman, DARPA is developing a series of different AI-fueled wargames for part of a virtual classroom. DARPA recently contracted Northrop Grumman to apply AI models to the real-time wargame “Command” to learn more about how the game can be broken and, in so doing, enabling a participant to leverage a “game within the game” to gain an edge over an adversary.

Northrop Grumman’s game developers are using AI within “Command” to search for battlefield advantages that might give friendly forces an edge in different situations, especially with battlefields becoming scenarios in which increasing amounts of sensor data must be processed within shorter time periods. Erin Cherry, a program manager for Northrop Grumman who works on the Gamebreaker program, explained: “Wargaming with game technology and AI, not to be confused with traditional tabletop exercises, really allows us to rapidly explore strategies and optimize for tactics selection, fleet composition, and mission outcomes.” Cherry added, "This is incredibly important if our military shifts to a large number of smaller platforms. That would change the way that we fight, and this type of wargaming will help us explore strategies, compositions, and orders of battle.”

Cherry, Ryan McKendrick, and Bradley Feest are among the AI specialists at Northrop Grumman investigating how AI models might help wargames provide key advantages in future battlefield situations. They are applying the "game within a game" concept to search for edges within a game and situations in which an adversary has a natural or unfair advantage. By introducing an almost unlimited number of options within “Command” that can be used to create advantages, they are attempting to use virtual situations to prepare for real ones.

About the Author

Jack Browne | Technical Contributor

Jack Browne, Technical Contributor, has worked in technical publishing for over 30 years. He managed the content and production of three technical journals while at the American Institute of Physics, including Medical Physics and the Journal of Vacuum Science & Technology. He has been a Publisher and Editor for Penton Media, started the firm’s Wireless Symposium & Exhibition trade show in 1993, and currently serves as Technical Contributor for that company's Microwaves & RF magazine. Browne, who holds a BS in Mathematics from City College of New York and BA degrees in English and Philosophy from Fordham University, is a member of the IEEE.

Sponsored Recommendations

Forging the Future of Defense

Oct. 11, 2024
Raytheon’s Advanced Technology team incubates capabilities that fuel the future of defense. Together with leading research and development organizations, def...

Phase-Matched Cable Assemblies

Oct. 8, 2024
Phase-matched cable assemblies are ubiquitous, and growing in popularity. Electrical length matching requirements continue to tighten and the mechanical precision of cable construction...

3 New Wideband MMIC LNAs Cover 5.5 to 20 GHz

Oct. 8, 2024
Mini-Circuits’ expanded PMA3-series of wideband, ultra-low NF MMIC amplifiers operates in ranges between 5.5 and 20 GHz.

Wideband Amplifiers Variable and Temperature-Compensated Gain

Oct. 8, 2024
Many types of RF systems and applications that span from the upper end of microwave frequencies to the lower end of mmWave have arisen in recent years. Meeting system requirements...