Machine Learning Automation for Virtual Reality

A master's thesis exploring how data-driven and automated approaches can support better VR design and improve user experience.

Screenshot from the master's thesis virtual reality project

Publication details

Authors Erdem Murat
Publication venue Master's thesis, George Mason University
Date 12/2022
Paper View paper
Focus Machine learning automation, procedural design, and VR user studies

Overview

This thesis investigated a limitation in VR development research and proposed a system that uses user data to support better design and improved experience. The work explored how procedural game difficulty and automated content variation could be used to better understand player response.

Multiple game levels were generated to study the relationship between design parameters and user experience, creating a framework for more systematic experimentation in VR.

Highlights

Developed a research system intended to improve VR development and player experience analysis.
Used procedural difficulty design to generate and compare varied game levels.
Collected data from more than 50 users after receiving IRB certification for social and behavioral research.

Back to Research