Intelligent, Automated Performance Assessment and Diagnosis for Team Training

As the Air Force has moved increasingly towards distributed networked environment for C2ISR missions, teams often operate remotely, and decision-making is distributed. Traditionally team training involved human observers for performance assessment, diagnosis, and after-action review and other training intervention. However, with much of the communication and coordination happening electronically, key aspects of the interactions between team members are no longer accessible to these trainers. Analyzing these communications involves poring over high volumes of raw electronic data. This is infeasible in all but the smallest of scales of operation. We propose to develop an intelligent performance assessment tool to assist trainers by warehousing and analyzing team interaction data and presenting it to them in a user-friendly manner for real time coaching and after-action review. The tool will perform automatic event detection and causal explanation generation. Speech recognition, natural language processing, and plan recognition techniques will be used to analyze to generate diagnostic explanation of events. This information will be sent to desktop, laptop or handheld clients as alerts. A visual tool will facilitate the rapid construction of debriefing. Phase I will result in a limited proof-of-concept prototype that will absolutely illustrate the feasibility and the benefits of this approach.