


Project Summary
Traditional military operation planning and decision-making requires users to manually evaluate masses of digital data to determine the predicted outcomes of a Course of Action.
Our approach automates this process using a reasoning engine that identifies potential Courses of Action based on the behavior of enemy agents within a given environment.

Completed as part of NAVY SBIR Phase I (2021 – Present) focused on reducing manual planning and decision making processes.
Project Details
- Courses of Action encoded in our reasoning engine as semantic graphs, based on manuals, training materials, and domain knowledge.
- Reasoning engine is fully operational at the edge, and reasoning capabilities grow over time through the use of zero-cost transfer learning.
- Platform supports both visualization and human-machine teaming: COAs display in a COP visualization environment that is fully customizable based on user preferences and the particular situation, including the option to refine displayed COAs based on user knowledge.
Project Visualization
Graphical abstract representing planning and decision-making tool:


Reasoning engine incorporates static and streaming data, library of courses of action, and domain-specific ontologies.

Reasoning engine predicts agent trajectories to identify enemy COAs through sequential observations and hypothesis testing.