Skip to content

Personalization Enablers

Matteo Besenzoni edited this page Apr 22, 2026 · 18 revisions

Target Audience: software developers


Personalization Enablers proposed in the XR2Learn ecosystem aim to provide tools for personalizing education scenarios in XR by enabling adaptive learning components that dynamically adjust to users based on their proficiency level, affective state (emotions), and challenge level of an educational scenario.

Workflow showing how user data, affective signals, and performance indicators are processed by personalization enablers to adapt XR learning scenarios

Figure: Personalization adaptation workflow illustrating how user proficiency, affective state, and scenario difficulty are used to dynamically adapt XR learning experiences.

Personalization Enablers are organized into five main domains based on their functionalities. The figure below illustrates a high-level diagram of the proposed components. All the components within the different domains are cross-platform applications that can be hosted on a local or remote machine.

High-level architecture of the XR2Learn personalization enablers showing sensing, learner modeling, and adaptation components

Figure: High-level architecture of the XR2Learn personalization enablers.

These enablers enable adaptive and emotion-aware XR learning experiences, supporting personalized education and training across diverse learner profiles and contexts.

Personalization Enablers Architecture

The enablers’ architecture is designed to support flexible and scalable personalization in XR environments:

  • Modularity: Each enabler can be deployed independently or combined with others.
  • Scalability: Components can scale from small pilots to large multi-user deployments.
  • Flexibility: The architecture supports different sensing modalities, learner models, and adaptation strategies.
  • Deployment: Enablers can be integrated into existing XR pipelines or used as standalone services. Distributed architecture of the XR2Learn personalization enablers showing modular components deployed across heterogeneous machines

Figure: Distributed and modular deployment architecture of the personalization enablers, illustrating how components can be deployed on different machines depending on computational requirements.

In the proposed architecture, five domains have been implemented to cover the Personalization enablers' functionalities:

  1. Training Tools
  2. Inference Tools
  3. Personalization Tool
  4. Command Line Interface (CLI)
  5. Personalization Dashboard

See also


Return to XR2Learn wiki home page

Clone this wiki locally