Lazaros Rafail Kouzelis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lazaros Rafail Kouzelis has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Ourania Spantidi
Eastern Michigan University
4 shared publications - Jorde Stojanov
Eastern Michigan University
1 shared publication - Kaitlyn Tracy
Eastern Michigan University
1 shared publication - Rami Dari
Eastern Michigan University
1 shared publication
Latest Publications
- Open Access
- 14 July 2025
- Published by MDPI AG in Virtual Worlds
- Vol. 4 (3) , 33
Planogen: A Procedural Generation Framework for Dynamic VR Research Environments
This paper introduces Planogen, a modular procedural generation plug-in for the Unity game engine, which is composed of two primary components: a character generation module (CharGen) and an airplane generation module (PlaneGen). Planogen facilitates the rapid generation of varied and interactive aircraft cabin environments populated with diverse virtual passengers. The presented system is intended for use in research experiment scenarios, particularly those targeting the fear of flying (FoF), where environmental variety and realism are essential for user immersion. Leveraging Unity’s extensibility and procedural content generation techniques, Planogen allows for flexible scene customization, randomization, and scalability in real time. We further validate the realism and user appeal of Planogen-generated cabins in a user study with 33 participants, who rate their immersion and satisfaction, demonstrating that Planogen produces believable and engaging virtual environments. The modular architecture supports asynchronous updates and future extensions to other VR domains. By enabling on-demand, repeatable, and customizable VR content, Planogen offers a practical tool for developers and researchers aiming to construct responsive, scenario-specific virtual environments that can be adapted to any research domain.
- 14 July 2025
- Published by MDPI AG in Virtual Worlds
- Vol. 4 (3) , 33
Open AccessPlanogen: A Procedural Generation Framework for Dynamic VR Research Environments
This paper introduces Planogen, a modular procedural generation plug-in for the Unity game engine, which is composed of two primary components: a character generation module (CharGen) and an airplane generation module (PlaneGen). Planogen facilitates the rapid generation of varied and interactive aircraft cabin environments populated with diverse virtual passengers. The presented system is intended for use in research experiment scenarios, particularly those targeting the fear of flying (FoF), where environmental variety and realism are essential for user immersion. Leveraging Unity’s extensibility and procedural content generation techniques, Planogen allows for flexible scene customization, randomization, and scalability in real time. We further validate the realism and user appeal of Planogen-generated cabins in a user study with 33 participants, who rate their immersion and satisfaction, demonstrating that Planogen produces believable and engaging virtual environments. The modular architecture supports asynchronous updates and future extensions to other VR domains. By enabling on-demand, repeatable, and customizable VR content, Planogen offers a practical tool for developers and researchers aiming to construct responsive, scenario-specific virtual environments that can be adapted to any research domain.
- 22 January 2025
- Published by Springer Nature
- p. 199-211
Toward Dynamic NPC Interactions: Integrating GPT-Driven Agents in 3D Virtual Environments
- 22 January 2025
- Published by Springer Nature
- p. 199-211
Toward Dynamic NPC Interactions: Integrating GPT-Driven Agents in 3D Virtual Environments
- Open Access
- 23 July 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (15) , 6405
Enhancing Historical Extended Reality Experiences: Prompt Engineering Strategies for AI-Generated Dialogue
Extended reality offers unique ways to create mediated spaces that enhance and help popularize experiences across several domains, including entertainment, creativity, and culture. There are still issues that hinder the widespread adoption of the medium, such as the over-reliance on scripted sequences, generalized approaches, and curated asset production. Artificial intelligence can be used to, in part, alleviate these issues, but this comes with its own set of challenges, such as factual inaccuracy or hallucinations. We delve into prompt engineering methods for the GPT API, enhancing context understanding to enable more realistic performances in historical event recreations. Specifically, we experiment with the Great Fire of Smyrna in 1922 as our historical context, situating the AI agent in the middle of chaos as a resident that has been affected by the event. Our experiments demonstrate that refined prompt engineering techniques significantly reduce factual inaccuracies and enhance the emotional resonance of AI-generated dialogues, which can lead to more immersive and engaging XR experiences. Our experiments indicate that AI can effectively support historical recreations by providing dynamic and contextually appropriate interactions.
- 23 July 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (15) , 6405
Open AccessEnhancing Historical Extended Reality Experiences: Prompt Engineering Strategies for AI-Generated Dialogue
Extended reality offers unique ways to create mediated spaces that enhance and help popularize experiences across several domains, including entertainment, creativity, and culture. There are still issues that hinder the widespread adoption of the medium, such as the over-reliance on scripted sequences, generalized approaches, and curated asset production. Artificial intelligence can be used to, in part, alleviate these issues, but this comes with its own set of challenges, such as factual inaccuracy or hallucinations. We delve into prompt engineering methods for the GPT API, enhancing context understanding to enable more realistic performances in historical event recreations. Specifically, we experiment with the Great Fire of Smyrna in 1922 as our historical context, situating the AI agent in the middle of chaos as a resident that has been affected by the event. Our experiments demonstrate that refined prompt engineering techniques significantly reduce factual inaccuracies and enhance the emotional resonance of AI-generated dialogues, which can lead to more immersive and engaging XR experiences. Our experiments indicate that AI can effectively support historical recreations by providing dynamic and contextually appropriate interactions.
- 3 December 2023
- Published by Springer Nature
- p. 15-26
Synthesizing Play-Ready VR Scenes with Natural Language Prompts Through GPT API
- 3 December 2023
- Published by Springer Nature
- p. 15-26
Synthesizing Play-Ready VR Scenes with Natural Language Prompts Through GPT API