Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This volume serves as the technical analysis to a report concerning the potential for artificial intelligence (AI) systems to assist in Air Force command and control (C2) from a technical perspective. The authors detail the taxonomy of ten C2 problem characteristics. They present the results of a structured interview protocol that enabled scoring of problem characteristics for C2 processes with subject-matter experts (SMEs). Using the problem taxonomy and the structured interview protocol, they analyzed ten games and ten C2 processes. To demonstrate the problem taxonomy and the structured interview protocol for a C2 problem, they then applied them to sensor management as performed by an air battle manager. The authors then turn to eight AI system solution capabilities. As for the C2 problem characteristics, they created a structured protocol to enable valid and reliable scoring of solution capabilities for a given AI system. Using the solution taxonomy and the structured interview protocol, they analyzed ten AI systems. The authors present additional details about the design, implementation, and results of the expert panel that was used to determine which of the eight solution capabilities are needed to address each of the ten problem characteristics. Finally, they present three technical case studies that demonstrate a wide range of computational, AI, and human solutions to various C2 problems.

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The U.S. Air Force uses live, virtual, and constructive (LVC) capabilities to help enhance training and improve readiness. However, it is not always clear what combinations of LVC capabilities are most effective and how they map to training goals. The authors of this report analyze the use of LVC for aircrew continuation training and develop a framework for aligning LVC capabilities with training needs for collective, complex, cognitive tasks. The framework involves (1) mapping missions to underlying tasks and skills, (2) parsing skills into skill factors, (3) parsing training technologies according to how users interface with technology, and (4) integrating the results of steps (2) and (3) to identify appropriate training tools. The authors also built a prototype interactive software application that allows users to explore this mapping. However, selecting technologies for training depends on many factors beyond skills requirements. Thus, the authors developed a logic model that illustrates how inputs, such as policy, training goals, and resources, influence selection of training technologies; how those technologies contribute to aircrew proficiency and readiness; how these outcomes influence the inputs; and the need for robust measures of aircrew performance to support the process. The authors describe how to apply the model to guide research on appropriate mixes of LVC. This approach can enhance quality of training development and implementation, support research efforts on new capabilities, inform acquisition decisions about resource needs, and identify needs for possible changes in training policy.