ARLINGTON, Va. – U.S. military researchers needed to develop enabling technologies for computer-aided battle planning systems with performance as good as humans, but that work at the speed of computers. They found their solution from Charles River Analytics Inc. in Cambridge, Mass.
Officials of the U.S. Defense Advanced Research Projects Agency (DARPA) in Arlington, Va., announced a $9.9 million contract to Charles River on Monday for the Strategic Chaos Engine for Planning, Tactics, Experimentation and Resiliency (SCEPTER) program.
The SCEPTER machine-generated campaign-scale planning and analytics project seeks to develop analytic engines that will produce machine-generated strategies that can compete with humans in the planning of real warfare as evaluated within trusted simulation environments.
SCEPTER will discover new courses of action by exploring complex military engagements at machine speed. Enabling high speed will come from tailorable abstraction of trusted expert-informed models. Researchers will validate a few of the best performing solutions in high-fidelity trusted simulators and with thorough human review.
The SCEPTER program's first phase addresses two key technical focus areas: developing unscripted goal-oriented agents able to discover relevant and interpretable solutions; and managing growth of threats to achieve fast exploration of large-scale military scenarios. SCEPTER is planned as a two-phase three-year battle planning program.
The BAE Systems Electronic Systems segment in Nashua, N.H., won an $8.3 million DARPA SCEPTER contract in January 2022. For more information contact Charles River Analytics online at https://cra.com, or DARPA at https://www.darpa.mil.
