Battlespace Simulations, Inc. discusses AI applications toward military M&S

By Cassidy Mills, Staff Writer

 

Battlespace Simulations, Inc. (BSI) presented “Applications of AI Within Military M&S” at the Institute for Defense & Government Advancement (IGDA) Military Land Forces Summit, exploring uses of generative AI and how they can provide innovative solutions for military modeling and simulation, Feb. 25.

 

IGDA’s two-day summit gathered over 300 senior training commanders, procurement officers and acquisitions leaders from across the military and provided a forum for networking and collaboration. This conference focused on training warfighters with simulation and synthetic training, and it explored how militaries (American and allied) are approaching interoperability with new technology and moving toward competency training.

 

BSI, a Defense Department industry partner, specializes in creating sophisticated simulations and analyses that replicate real-world combat scenarios across multiple domains. Their purpose is to capture modern warfare’s complexities and enable military organizations to better prepare for a wide range of operational environments.

 

Users leverage stable diffusion and generative AI to expedite the large-scale creation of realistic, 3D simulation content. Gary DeYoung, president of BSI, said military planners utilize large language models with image recognition capabilities to analyze these 3D models and generate detailed descriptions of their visual content.

 

“Imagine the amount of manpower it would take to go through thousands of 3D models and tag each one with every possible word someone might use to describe it,” DeYoung said. “We want to accurately describe our 3D content, but we don’t want to rely on humans to do that. It’s a great application of AI.”

 

Industry partners offer a range of simulation technology software that enables users to simulate and rehearse complex operations with high fidelity, ensuring quality training for dynamic military environments in various domains.

 

BSI’s presentation discussed a path-finding and graph-traversal algorithm that explores multiple, potential paths between a starting point and a destination. This innovation accounts for various obstacles and applies a variable cost to different segments of the journey.

 

“The way this works is you first calculate the cost of each possible path, considering factors such as distance and obstacles,” DeYoung said. “It will give you the path that is the least risky and most cost-effective, providing results that reflect those considerations.”

 

The algorithm uses cost algebra, which helps to adjust the pathfinding process based on dynamic conditions such as terrain, traffic or other variables that might increase or decrease the cost of logistical movement.