Design of autonomous gaze-tracking system for inclusive education

Eye-tracking technology as a means of ensuring the accessibility of education for people with severe musculoskeletal disorders has been investigated in this study. A number of assistive technologies have been devised up to now that possess significant educational potential, but their autonomous use is mainly associated with such difficulties as dependence on the instability of wireless networks or external computing resources. The need to overcome the technological gap between the capabilities of assistive technologies and their real autonomy is a task addressed in this work. The study's result is the designed fully autonomous architecture based on virtual reality headsets (Meta Quest), which enables the execution of all eye image processing activities and provides direct interface control using the device's processor. The hardware was improved (frame miniaturization, transition to a wired USB interface were carried out); software was developed in the Rust language in the OpenXR API (Application Programming Interface) layer format. That has made it possible to get rid of network delays and ensure the system's operation, resistant to any conditions. Direct interaction with the headset hardware is provided by effective optimization of convolutional neural networks and the use of low-level system calls. An immersive graphical user interface (GUI) was designed, successfully tested for system configuration and calibration. The GUI became available directly in the virtual space of the headset. The results could be used for individual learning at home, as well as at inclusive educational institutions or rehabilitation centers that organize training for people with severe musculoskeletal disorders