Automated Personalized Exposure Therapy Based on Physiological Measures Using Experience-Driven Procedural Content Generation

Abstract

Our research focuses on personalized virtual reality exposure therapy (VRET) based on the Experience-Driven Procedural Content Generation (EDPCG) framework. There are existing approaches for personalized VRET; however, they are subjective and require hand-authored and predefined rules that may not generalize to all subjects. We propose a framework to personalize VRET based on predicting subjects' experiences via physiological sensors and machine learning algorithms. The framework then automatically adapts exposure parameters based on the subject's physiological response using a PCG method. We intend to conduct two human subject studies for arachnophobia and fear of public speaking.