Soar Technology, Inc.: Projects

Company

Research Areas

Engineering

Engineering Sectors

Human Behavior Representation (HBR) / Computer Generated Forces (CGF)
Analysis Simulation
C4ISR / Command and Control

Human Behavior Representation (HBR) / Computer Generated Forces (CGF)

TacAir-Soar: The cutting edge of training simulation involves modeling behavior at the entity level. This requires automated agents that generate realistic, intelligent behavior at the level of individual human performance. TacAir-Soar models the tactical air domain. more...
SOF-Soar: Special Operations Forces Modeling: Using the same underlying framework and methods for behavior generation that have been proven successful in TacAir-Soar, Soar Technology is developing SOF-Soar, simulating Special Operations Forces forward air controllers. Because SOF-Soar forces are based on the Soar model of human cognition, each entity is capable of autonomous, goal-directed decision-making, planning, and reactive, real-time behavior. more...
Developing Thinking OPFORs For JCATS: Today, the U.S. military is involved in a campaign to fight terrorism, an operation generally considered unrelated to the military’s core competency, which is to fight and win wars. Understanding how terrorists fight, their rationale for conducting operations, and their methods for executing those operations requires U.S. military commanders to think and act differently than when conducting traditional military operations. Training for this new environment requires better modeling and simulation (M&S) tools that capture potential opposing force (OPFOR) behavior. Existing simulation tools, such as the JCATS (Joint Conflict and Tactical Simulation) system, need extension to provide OPFORs capable of intelligent, autonomous activity. Adding Thinking OPFORs capacity to simulation tools will reduce training exercise cost by lowering the manpower requirements. more...
AutoWingman, An Intelligent, Automated Wingman to Support Helicopter Concept Evaluation and System Performance Trade Studies: The Army has a rich store of highly immersive flight simulations/simulators, but often only a single aircraft is represented, independent of a realistic operational environment. To add a high fidelity second aircraft into a simulated exercise, another “full-up” simulator, along with its associated personnel, is required. Often to avoid these costs, simulation fidelity is sacrificed by using low-cost desktop simulations that do not provide the precision and accuracy necessary in modern simulated warfighting exercises. Making the automated behavior of the synthetic wingman responsive (via voice or data messaging) to a real pilot flying another aircraft in a distributed simulation has not yet been accomplished. Representing the behavior of a pilot in a tactically correct, responsive way for all-digital Modeling and Simulation (M&S) is a challenge that is being addressed by several programs such as Modular Semi-Automated Forces (ModSAF), One Semi-Automated Forces (OneSAF), Advanced Tactical Combat Model (ATCOM) and Interactive Tactical Environment Management System (ITEMS) (Army 2002). more...

Analysis Simulation

AGILE, Advanced Global Intelligence and Leadership Environment: The intelligence community finds itself overwhelmed with information from multiple sources, and often a primary task is to find needles in haystacks – whether watching for potential terrorist operations or conflicts between nations. This job is particularly difficult when an intelligence target is a closed regime – a country or organization whose decision-making apparatus is not directly accessible for observation. The intelligence analyst must rely on open source reports that may be directly controlled by the regime or covert sources that may be unreliable at best. The intelligence process itself often (sometimes necessarily) includes biases that preclude the investigation of low-probability, high-impact scenarios. Either so much information must be sifted through that there is no time to investigate these areas, or incomplete or inaccurate information biases the analyst against exploring those possibilities. Furthermore, those biases are often only implicit in the analyst’s work products, and make the results of the analysis more difficult to place in context. This tacit knowledge in the mind of the analyst is very likely lost from corporate memory when that analyst retires. more...
GNAVE, Game-based Nation-state Analysis and Visualization Environment: In the post-September 11 world, the complex international character of the growing threats to free-world stability have become painfully apparent. The rapidly growing number and size of intelligence data sources, the complexity of the threat, the expanding scope of the issues, and the changing nature of the problems facing the analyst make current problems much more than “connect-the-dots”. Finding crucial relationships in the face of rapidly changing operational patterns on a large scale is extremely difficult. Explaining those correlations, motivating their origins, and defining their implications to decision-makers may be just as difficult. GNAVE offers leading-edge dynamic visualization resources exploiting the latest strategy-game technology to support the presentation of analysis results to Decision-makers. more...

C4ISR / Command and Control

Cooperative Interface Agents for Networked Command, Control and Communications (CIANC3): Intelligent agents can provide a layer of abstraction between command echelons as well as between human controllers and robotic control systems. Special-purpose agents are encapsulated into a meta-level agent to facilitate internal agent communication and information sharing. These agents are responsible for the detail work of resource acquisition, tasking, and monitoring that are required for carrying out the orders of battlefield commanders. In addition, interface agents control the flow and form of much of the information to be displayed to the human operator in a mixed-initiative dialog. more...
BINAH, Battlespace Information and Notification through Adaptive Heuristics: Soar Technology is investigating the creation of an intelligent user interfaces and information display framework called BINAH. BINAH is a high-level design for an agent based intelligent reasoning data pipeline. This pipeline will incorporate models of the warfighter, the warfighter’s tasks, the common operating picture, and agent-generated inferences about the incoming data streams and display systems to customize data delivery to the warfighter. The BINAH framework is being designed to allow the incorporation of a wide range of agent types and technologies to perform information fusion, filtering, analysis, and annotation. more...
Situation Awareness Panel (SAP): The Situational Awareness Panel (SAP) is a graphical user interface that aids the observation, use and development of TacAir-Soar intelligent agents that control simulated military aircraft. It allows a human operator or engineer to view various representations of an intelligent agent’s current perception, awareness, goals and intentions during an exercise. more...