Alberto Cannavò

Problem:
The introduction of XR technologies is presenting unexplored challenges to final viewers. It is not clear where traditional cinematic techniques would also apply to immersive movies and their effects on the users’ experience.

Objective:
Deepening existing studies in the context of cinematic AR/VR to cope with challenges regarding users’ behavior in immersive movies, i.e., camera movements, watching conditions, scene cut techniques, fear of missing out, volumetric videos, lighting conditions, dynamic storytelling.

Approach:
Design studies and realize short immersive movies aimed to validate cinematic techniques and users’ behavior when immersed in the watching experience

Expected Impact:
Enhanced experience for users watching immersive movies

Problem:
In healthcare education, over the past decade, scientific literature has shown that Extended Reality (XR) technologies can effectively simulate complex and high-risk scenarios, enabling repeated practice in safe and controlled environments. Despite the growing adoption of XR in medical education, several relevant aspects (e.g., realistic interaction with medical tools, personalized XR training experiences) remain only partially explored and
deserve further investigation.
Objective: Study XR and haptics solutions that would allow doctors to practice and improve their skills.
Approach: Design and develop an XR application integrating haptics technologies to improve manual skill. Validate the tool with experiments involving emergency doctors. This thesis is developed in collaboration with clinicians from hospitals in Turin.
Expected Impact:
Enhanced training experience.
This thesis proposal is part of the context of previous research activities carried out in collaboration with Ontario Tech University, Durham College (Canada), and Ospedale Mauriziano (Italy).

Over the past decade, research on archives and specialized glossaries has significantly increased, leading to the cataloging and digitization of primary sources. However, despite the fact that architectural and technical vocabulary used on construction sites was quickly shared among professional communities from different regions, the study of these terms and their dissemination still requires further exploration. One major obstacle is the fragmented nature of the existing knowledge base. Historical data on construction techniques, materials, and terminology is dispersed across various archives and regions, often lacking standardization or common frameworks for analysis. This dispersion has created significant barriers to accessing, comparing, and synthesizing information across different European contexts. Recent developments in digital humanities can potentially advance this field of study significantly. Integrating digital tools has enabled more sophisticated analyses of historical texts and the creation of interactive databases that compile and visualize technical terms and their variations. Such digital platforms could enhance our ability to track the evolution and diffusion of construction vocabulary across different regions and periods, offering new insights into the interplay between linguistic and technical knowledge in historical contexts. This thesis will be developed in collaboration with European Patner of the CA24102 – A Glossary of Technical Construction Vocabulary in 17th-18th Century European Court Residences (EUROGLOSS) – COST Action. It aims to design and develop a digital platform that is able to enhance the accessibility and usability of construction-related data. The activities involved in this thesis envisage the analysis of the current digital practices, technologies and tools for documenting and disseminating architectural knowledge and the creation of a digital platform for sharing digital resources.
References:
– Atlas of Roman Building Techniques
– CHARP’FRANCE: La base de données de charpentes anciennes en France

Problem:
Recent research highlights that XR + LLM integration is still fragmented, lacking unified frameworks for interaction and collaboration. Human-AI collaboration benefits from complementary reasoning between humans and AI, but current systems poorly coordinate roles and interaction dynamics. Moreover, existing XR systems typically treat AI as a tool, not as a team of collaborating agents, and do not support multi-agent coordination alongside humans in shared virtual environments.
Objective:
Design, implement, and evaluate a human-centered XR framework where multiple specialized LLM agents collaboratively assist users in complex tasks within a shared virtual environment. Specific goals include: i) Enable multi-LLM collaboration; ii) Integrate human-in-the-loop interaction within XR iii) Support real-time co-presence and co-decision-making; iv) Evaluate improvements in task performance, cognitive load, and user trust.
Approach:
The proposed system will include: i) an immersive workspace based on XR for interactions; ii) multi-LLM agent system and iii) Human user as supervisor and collaborator. Possible use cases may consider, e.g., collaborative design; medical or scientific decision-making, training and education in XR labs.
Expected Impact:
Improving user performance and experience.