Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Tailored Immersive Environments: Advancing Neurodivergent Support Through Virtual Reality

Elia Moscoso-Thompson, Katia Lupinetti, Irene Capasso, Fabrizio Ravicchio, Brigida Bonino, Franca Giannini, Andrea Canessa, Silvio Sabatini, Lucia Ferlino, Chiara Malagoli

TL;DR

The paper addresses the need for ecologically valid, personalized VR training for neurodivergent individuals navigating complex urban tasks. It introduces EASE VR and a feature-weighted scoring pipeline that exhaustively generates scenario variations and tunes difficulty to individual profiles, using a tunable score $Dscore$ and normalization to $[0,1]$. A discretization scheme defines consistent difficulty levels via $CDscore$ and a Jensen–Shannon divergence-based metric assesses feature variation within fixed difficulty. Preliminary results with four synthetic profiles show substantial scenario generation and meaningful within-difficulty diversity, suggesting practical utility for therapists. Future work includes validating with neurodivergent participants, refining thresholds, exploring additional metrics, and evaluating scalability toward semi-supervised personalization.

Abstract

Every day life tasks can present significant challenges for neurodivergent individuals, particularly those with Autism Spectrum Disorders (ASD) who are characterized by specific sensitivities. This contribution describes a virtual reality system that allows neurodivergent individuals to experience everyday situations in order to practice and implement strategies for overcoming their daily challenges. The key strength of the proposed system is the automatic personalization of the virtual environment, based on both the individual's abilities and their specific training needs. The proposed method has been evaluated on four synthetic user profiles, also proposing a metric able to evaluate the variance of the features within the same difficulty level. The results show that the method can produce a significant number of scenarios for the various difficulty levels. Furthermore, within the same difficulty, there is a wide variance of the non-constrained features for the specific profile.

Tailored Immersive Environments: Advancing Neurodivergent Support Through Virtual Reality

TL;DR

The paper addresses the need for ecologically valid, personalized VR training for neurodivergent individuals navigating complex urban tasks. It introduces EASE VR and a feature-weighted scoring pipeline that exhaustively generates scenario variations and tunes difficulty to individual profiles, using a tunable score and normalization to . A discretization scheme defines consistent difficulty levels via and a Jensen–Shannon divergence-based metric assesses feature variation within fixed difficulty. Preliminary results with four synthetic profiles show substantial scenario generation and meaningful within-difficulty diversity, suggesting practical utility for therapists. Future work includes validating with neurodivergent participants, refining thresholds, exploring additional metrics, and evaluating scalability toward semi-supervised personalization.

Abstract

Every day life tasks can present significant challenges for neurodivergent individuals, particularly those with Autism Spectrum Disorders (ASD) who are characterized by specific sensitivities. This contribution describes a virtual reality system that allows neurodivergent individuals to experience everyday situations in order to practice and implement strategies for overcoming their daily challenges. The key strength of the proposed system is the automatic personalization of the virtual environment, based on both the individual's abilities and their specific training needs. The proposed method has been evaluated on four synthetic user profiles, also proposing a metric able to evaluate the variance of the features within the same difficulty level. The results show that the method can produce a significant number of scenarios for the various difficulty levels. Furthermore, within the same difficulty, there is a wide variance of the non-constrained features for the specific profile.
Paper Structure (8 sections, 4 equations, 4 figures, 2 tables)

This paper contains 8 sections, 4 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. The EASE VR system
  3. Personalization method and experiment setup
  4. Score discretization and consistent difficulty
  5. Evaluation objectives and adopted metrics
  6. Measuring feature variation in scenarios with consistent difficulty
  7. Results
  8. Conclusions and future works

Figures (4)

  • Figure 1: Examples of different training scenarios.
  • Figure 2: Profile 3 scenarios analysis. Left: the distribution of scenarios (the y-axis is in logarithmic scale). Right: the related variance in features values.
  • Figure 3: Profile 2 scenarios analysis. Left: the distribution of scenarios (the y-axis is in logarithmic scale). Right: the related variance in features values.
  • Figure 4: Profile 3 and 4 scenarios analysis. Left: the distribution of scenarios (the y-axis is in logarithmic scale). Right: the related variance in features values.