Aditya Iqbal Bagaskara

This research focuses on the human-factor in the future work machine training. Primarily, it investigates visual attention and cognitive load in human–machine interaction, focusing on heavy machinery and XR-based simulator training for equipment such as forest harvesters and tractors. It integrates behavioral and physiological measures, with an emphasis on eye-tracking to analyze visual information processing, skill acquisition, and attention distribution through metrics such as Areas-of-Interest, pupillometry, and 2nd-order gaze metrics (e.g. K-coefficient & gaze entropy). The study also aims to evaluate the applicability and feasibility of gaze-based and pupillometric metrics which are often used in aviation and automotive domains to determine their relevance for heavy machinery, where such research remains scarce.

The goal is to enhance knowledge transfer between trainer and trainee by creating adaptive training modules based on operator expertise. Such simulators can improve sustainability (e.g., selective thinning) and safety during complex maneuvers.

An initial study validates the Low/High Index of Pupillary Activity as a cognitive load metric in VR and 2nd-order gaze-based metrics. Data will be analyzed using Generalized Mixed Effect Models to establish reliable cognitive load indicators and advance immersive, user-centered training systems. A study is currently being planned to focus on focal vs ambient attention during forest harvester operation.