ERI: Passenger-Centered Design Evaluation for Advanced Air Mobility

This Engineering Research Initiation (ERI) award supports research to develop a data-driven methodology for incorporating passenger-centered metrics into the conceptual design of advanced air mobility (AAM) aircraft. While advances in electric propulsion and autonomous flight have accelerated the development of AAM vehicles, early-stage aircraft design remains largely disconnected from the human factors that ultimately influence adoption, including passenger trust, comfort, and willingness to fly. Existing studies rely primarily on hypothetical surveys and therefore provide limited insight into how passengers respond during realistic flight experiences. This project will integrate immersive virtual reality (VR), physiological sensing, behavioral measurements, and artificial intelligence (AI) to quantify passenger responses under representative flight conditions. The research will establish a foundation for evaluating human-centered design decisions before prototype aircraft are built. Educational activities will integrate the research into undergraduate aircraft design courses, undergraduate and graduate research experiences, K-12 STEM outreach, and public engagement activities that communicate emerging aviation technologies in accessible ways, creating opportunities for all Americans everywhere to participate in the future aerospace workforce. This award will support research that develops a multimodal methodology for evaluating passenger-centered aircraft design and AI-enabled predictive tools for human-centered engineering design. The project objectives are to: (1) conduct user studies using physical mockups and immersive VR simulations to evaluate passenger comfort and trust in various flight conditions and autonomy levels; and (2) develop and validate a data-driven methodology and predictive tools for evaluating how aircraft design features influence passenger trust, comfort, and willingness to fly. During simulated flight experiences, physiological measurements, including heart rate, heart rate variability, respiration rate, and skin conductance, will provide objective indicators of passenger stress and comfort that complement subjective survey responses and behavioral observations, enabling validation of self-reported perceptions. Machine learning techniques, including artificial neural networks, random forests, and gradient boosting models, will be used to identify the design features that most strongly influence passenger outcomes and predict responses to alternative aircraft design decisions. Although demonstrated using AAM aircraft, the resulting methodology will provide a generalizable engineering design framework for integrating multimodal human-centered autonomous systems while supporting the safe and publicly accepted deployment of emerging aviation technologies. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.