The US Defense Advanced Research Projects Agency (DARPA) has awarded BAE Systems an $8.3 million contract to develop an autonomous battle planning system.
The Strategic Chaos Engine for Planning, Tactics, Experimentation, and Resiliency (SCEPTER) program intends to develop machine-generated battle strategies.
The three-year, two-phased program’s first phase will see BAE demonstrating the machine learning system.
Will Discover Courses of Action at Machine Speed
“SCEPTER will discover novel and surprising courses of action (COAs) by exploring the high complexity state-action space of military engagements at machine speed,” DARPA wrote in a solicitation notice last year.
“It is envisioned that high COA exploration speed will be enabled by tailorable abstraction of trusted, expert-informed models,” it added.
“A few of the best-performing COAs will be validated in higher fidelity trusted simulators and with thorough human review.”
During the program, the company will collaborate with Professor Igor Mezic, the small woman-owned business AIMdyn, and Professor Joao Hespanha, an expert in control and multi-agent systems.