Objective

Leverage state of the art AI and ML to potentially automate Course of Action (CoA) recommendations and improve our Military Decision-Making Process (MDMP) at the tactical level. Leveraging state-of-the-art Artificial Intelligence/Machine Learning (AI/ML) will speed up this process by an order of magnitude, allowing systematic replanning during the execution phase of operations. This will improve mission success and reduce risk to force in combat operations.

Description

Several approaches to CoA generation for military applications currently exist. These methods leverage large language models (LLM) applied to Doctrine or deep learning/hierarchical modeling applied to wargaming.

Each existing LLM approach is inadequate for CoA generation at the tactical level due to lack of proper consideration of Tactics, Techniques and Procedures (TTPs) and Standard Operating Procedures (SOPs) for both friendly and enemy forces. The existing learned/hierarchical approaches that depend on wargaming are also inadequate due to a lack of fully automated wargaming capability at the tactical level and/or due to CoA outcomes that are not aligned with best practices (TTPs and SOPs).

Proposals submitted under this topic will leverage state-of-the-art Artificial Intelligence (AI) approaches to create a CoA recommendation module narrowly tailored to the tactical level. This capability will expand to encompass higher echelons in later phases.

Phase I

This topic is only accepting Phase I proposals for a cost up to $250,000 for a 6-month period of performance.

Understand relevant scenarios and data sources. Design development strategy. Conduct feasibility study. Develop and demonstrate proof-of-concept CoA recommendation algorithm.

Phase II

Develop and train CoA recommendation agent and support integration into appropriate mission command system. Make interim algorithm deliveries biannually for independent evaluation. Deliver final algorithm, supporting software, documentation and algorithm performance report.

Phase III

Automated CoA generation has wide applicability to autonomous systems in industries such as robotics, self-driving automobiles, security, and gaming.

• Financial Services & Personal Finance: Aides in professional, financial services planning and “gamming” out as well as planning for things like retirement and estates.
• Retail and Supply Chain: These models can help ensure that supply chains aren’t strained for retail products (can also work for B2B solutions).
• Construction & Manufacturing: AI models can assist in project planning and forecast unforeseen problems
• Healthcare: Aides in personal healthcare forecasting and preventative medicine.

Submission Information

For more information, and to submit your full proposal package, visit the DSIP Portal.

SBIR|STTR Help Desk: usarmy.sbirsttr@army.mil