Simulated Training Exercises with Robust Unmanned Models (SERUM)

SoarTech, along with our partners Adaptive Cognitive Systems and Aptima, are applying our vast expertise in the design, development and integration of artificial intelligence technologies, bringing it to bear to help develop more realistic entity-level scenarios for USMC simulated training. Most crucial to our work will be the design and development of a full infrastructure, called SERUM (Simulated training Exercises with Robust Unmanned Models) to support advanced AI for the USMCs simulation technology portfolio. This infrastructure will allow for robust, unmanned entities to exist in virtual simulation environments (e.g., VBS2), and will also include the necessary hooks and mechanisms to allow entities to both perceive the world and make actions within it.Using SERUM, developers and knowledge engineers can develop and integrate behaviors that drive SUDM characters within VBS2, thereby reducing the role player footprint required to support training. We anticipate that this resultant capability will provide significant flexibility for executing virtual and augmented-reality SUDM training by significantly reducing the constant requirement for manned role player support. Because the automated role players are driven by robust AI models and not scripts, training scenarios that use them can be much more dynamic and representative of the trainees operational responsibilities.