This project will develop an Augmented Reality Intelligent Interactive Storytelling (ARIIS)-based training simulation for new or future bridge inspectors. Work in Stage 1 will focus on developing the ARIIS-based scenarios. Semi-structured interviews will be conducted with experienced bridge inspectors from the Kentucky Transportation Cabinet to obtain their tacit knowledge on selected high-risk inspection activities with focus on (1) key decision/branching points, (2) communication skills in relaying applicable decision points with bridge crews and other constituencies, (3) circumstances surrounding the decision points, and (4) integration of knowledge, skills, and abilities in making decisions in those circumstances. The data collected from semi-structured interviews and focus groups will form the basis for creating bridge inspection interactive narratives for the ARIIS-based training. Experienced bridge inspectors will outline branching interactive stories focusing on the high-risk activities identified above. Digital content will be provided to visually support the narratives across all those activities, utilizing iTwinCapture, LiDAR, and Skydio drones to generate digital twins of typical bridges for the virtual environment for training. The platform will be developed in the Unity Game Engine. The Augmented Reality interface will be provided by the Microsoft HoloLens 2 headset. The branching interactive narratives developed in earlier tasks will be implemented using the Sabre Narrative Planner. A pilot test of the ARIIS-based training simulation will be conducted with domain experts who contributed to the development of the content of the simulation. In Stage 2, the ARIIS prototype will be evaluated through an experimental study with bridge inspectors in the state of Kentucky to assess the effectiveness of the innovation for bridge inspection training. At least 30 new or entry-level bridge inspectors will be recruited and randomly assigned to a control group and an intervention group to ensure unbiased comparison. Both groups will receive the same training content and evaluation, with the control group receiving traditional in-person, instructor-led training and the intervention group ARIIS-based training. Participants will be provided with an assessment based on Kirkpatrick’s model and the Learning Transfer Evaluation Model to evaluate the effectiveness of the innovation. Hypothesis testing will involve pairwise comparisons, correlation analysis, cluster analysis, and multivariate analysis. A non-parametric analysis will be employed, and statistical significance will be computed at 95% confidence level. The final report will provide all relevant data, methods, models, and conclusions along with guidance on how to develop ARIIS scenarios and use the platform within a state DOT.