Stealth Optimized, Adaptive Assessments for Multistage UAS Operator Selection (Stealth Adapt)

Unmanned Aerial System (UAS) operation represents a stressful, cognitively challenging domain where operators are routinely subjected to both occupational and combat stressors and performance failures can have catastrophic effects. Effective performance in such conditions has many dimensions, including technical proficiency, probability of catastrophic failures, mission productivity, resistance to stress symptomology, teamwork, and long-term work engagement. Effective selection methods for UAS operators should accurately, efficiently, and holistically predict these key outcomes. Our solution to this challenge is to develop a customized suite of 1) assessments measuring cognitive skills, non-cognitive attributes and operational stress coping processes embedded within 2) a novel, adaptive, multistage content delivery and protection framework, and 3) optimized via stealth scoring optimization techniques. One key innovation will be a suite of scoring algorithms grounded in data mining advances designed to boost performance prediction. These will be embedded in performance-based assessments that simulate tasks placing considerable demands on executive-level cognitive skills (mental simulation, task prioritization, and real-time replanning). Phase I deliverables, (KSAO ontology, assessment content, storyboards, scoring and adaptive delivery algorithms, cut score simulations), will provide a preview of the full Phase II content suite, and lay the foundation for transition to UASISST and platform-specific systems for unmanned aviation.