Gabriele Pratticò

Context and Motivation:
In the era of Industry 4.0 and the Metaverse, Digital Twins (DT) have become indispensable for real-time monitoring, predictive maintenance, and immersive training. However, the creation of high-fidelity Digital Twins remains a significant bottleneck. Traditionally, this is a manual, labor-intensive process—especially when the object’s functional behavior must be modeled and coded from scratch to match its physical counterpart.
Problem Statement:
Current Digital Twin generation methodologies focus primarily on static geometry. However, most industrial assets and consumer products are Cyber-Physical Systems (CPS) or articulated objects (e.g., hardware tools, machinery with levers, knobs, and buttons) characterized by specific functional behaviors. For Extended Reality (XR) simulations to be effective, a Digital Twin must exhibit “Physical-Behavioral Symmetry”: it must not only look like the physical object but also mimic its kinematic constraints and logic. Manually defining multi-part hierarchies, kinematic joints, and Finite State Machine (FSM) logic for every asset is time consuming and require specialized skills (3d modeling, programming).
Objectives :
The objective of this thesis is to propose an end-to-end pipeline that reconstructs articulated/cyber-physical 3D models from standard video sequences and automatically synthesizes the underlying code/logic required to drive their behavior in virtual environments (e.g. Unity application).
Innovation and Expected Impact:
Students may leverage existing technologies as a starting point—such as PartGen for part-based reconstruction and LLMs for code generation—to either extend these frameworks or propose a novel, integrated Machine Learning-based approach. The successful outcome of this thesis will be a framework capable of transforming a simple videos into a “Smart Asset”: a ready-to-use, interactive Digital Twin for XR that possesses both geometric fidelity and functionality.

Aircraft wing de-icing is a critical safety procedure in winter operations, as even thin layers of ice or frost can severely compromise aerodynamic performance and flight safety. In real operational environments—characterized by low visibility, time pressure, and complex aircraft geometries—operators may experience difficulties in accurately identifying residual ice or areas that still require intervention. This thesis is part of a project funded by Regione Piemonte, in collaboration with companies specializing in drones and computer vision, aiming to develop an Augmented Reality (AR) system that enhances current de-icing workflows. The proposed solution will integrate drone-based imaging and vision algorithms developed by other partners to detect critical areas and visualize them in AR to support operator decision-making. The system will be collaboratively developed and experimentally evaluated together with SAGAT at Torino Caselle Airport. The thesis is addressed to students in Computer Engineering with a focus on graphics and interactive systems, as well as to students in Cinema Engineering and Aerospace Engineering. The thesis is meant to be developed at Politecnico di Torino with experiences on-field at the airport, though one of the involved companies could also be available to host the student.

This thesis project is part of the European COST Action LEAF (Leonardo da Vinci’s European Academic Network). Leonardo’s manuscript corpus is currently fragmented and preserved across various international institutions (e.g., Biblioteca Ambrosiana, Royal Collection at Windsor, Louvre, Victoria and Albert Museum).
The goal of this thesis is to design and develop Computer Vision and Machine Learning models capable of analyzing high-resolution digitized documents to suggest possible “matches” (correspondences) between different fragments, including the analysis of front-to-back (recto-verso) consistency.
The work focuses on creating the “intelligence engine” that will interface with a web-based visualization platform (not the subject of this thesis). The model will leverage historiographical features (e.g., dating) and physical/geometrical characteristics (chain lines, segmentation, dimensions, edge shapes, and fiber/stroke continuity) to obtain probabilistic match suggestions. The system will act as an intelligent assistant to reduce the search space for scholars, ensuring that every proposed union is physically possible on both sides of the sheet.
Technical Details and Development Path:
The student will work on developing an analysis module based on state-of-the-art techniques, including:
– State-of-the-art analysis: Review of similar models and applications in the field.
– Dataset preparation, pre-processing, and Multimodal Feature Extraction.
– Recto-Verso Matching Models: Experimentation with existing architectures to be potentially specialized (e.g., CNNs, Siamese Networks, Vision Transformers, Hybrid Models).
– Suggestion API Development: Support for interfacing the model via microservices (e.g., FastAPI) for integration with the visualization frontend.
– Expert Validation: Testing model suggestions on real-world use cases provided by the LEAF network to measure accuracy and practical utility.
Professional Value for the Student
This proposal is ideal for students wishing to enrich their portfolio with a concrete example by tackling a real-world CV/ML/AI problem. The thesis offers:
– Experience in Computer Vision (CV/ML): Working on real images with historical degradation and multi-face analysis.
– Scientific Impact: Contribution to an international project of excellence on Leonardo’s heritage.
– High-Level Interdisciplinary Collaboration: Interaction with the European COST LEAF network and engagement with international specialists (art historians, codicologists, technologists, and conservators).
– Applied AI: Translating complex models into functional APIs for professional workflows.

Problem:
Traditional Air Traffic Control (ATC) systems can lead to high cognitive workload, especially with increasing air traffic density and the introduction of new air vehicles like drones. Current visualization methods may not fully support complex trajectory planning and real-time monitoring.
Objective:
Augmented Reality (AR) tactical table for ATC that enhances situational awareness, supports efficient trajectory planning and monitoring, and includes Early Warning Systems (EWS).
Approach:
Develop an AR-enabled tactical table visualizing the urban airspace, including all aircraft (traditional and Urban Air Mobility), their trajectories, and potential conflicts. Integrate semi-automatic processes to assist controllers, reducing cognitive workload while maintaining human oversight.
Multiple theses are available under this project:
– AI/ML backend only: Design and develop the EWS system based on ML and Foundational Models (based on Radio Communications, ATC Visualization systems (radar, GPS), etc.
– XR front-end/dashboard: Design and develop the XR visualization
Expected Impact:
Improved decision-making speed and accuracy; reduced cognitive workload for air traffic controllers; enhanced safety through advanced EWS; efficient management of complex and dense urban airspaces.
References:
https://ieeexplore.ieee.org/document/10764466, https://ieeexplore.ieee.org/document/9089606, https://dl.acm.org/doi/10.1145/3385378.3385380

Problem: Traditional VR haptic interface (e.g. controllers) are rigid and static (not easy to switch from holding a controller and hands-free interaction), limiting the immersive experience and failing to provide dynamic haptic feedback.
Objective:
Develop a dynamic, shape-changing VR controller that can be intermittently available at user palm, with changing shape, enhancing the tactile experience and providing more immersive interactions.
Approach: Design and implement proof-of-concept for an inflatable haptic interface. These can be based on pneumatic pouches or on mechanical origami-based or fullerene structures. Shape shall be adjusted in real-time, profile modulated over main axis.
Expected Impact:
Enhanced presence and fidelity of interactions requiring switching between hands interaction and passive props.
Alternative Applications/Target use case variants: It is possible to tailor the target use case to diverse student interests. Rather than developing a hand-held controller, this methodology can be utilized for racing simulator accessories (car or plane) or a robotic flange.
References
https://arxiv.org/html/2501.18764v1
https://dl.acm.org/doi/pdf/10.1145/3472749.3474782
https://dl.acm.org/doi/10.1145/3242587.3242628

Wearable AI devices, particularly smart-glasses like Meta Ray-Ban Display, face a “Usage Paradox”: the friction between always-on utility (integration with AI without chip implants) and social/environmental constraints (privacy, battery, smartphone competition, and input limitations).
Objective:
Design and evaluate Edge-AI frameworks, solutions or HCI paradigms that enable smart-glasses to function as context-aware extensions of the user’s digital persona without infringing on social or legal norms and expanding possibilities in interacting with digital contents.
Different theses path are available to be pursued:
1. Seamless Hybridization with Smartphone: Cross-device interaction (HCI) and low-latency input handoffs between smartphone and smartglass.
2. Privacy Mitigation: Developing software-based solutions and/or pragmatic “Privacy Shields” for bystander protection.
3. Misbehavior or Misuse Detection: Recognizing forbidden usage (e.g., exams, banks, etc.) via sensor fusion (Vision+Bluetooth) without requiring eyewear removal as a prehemptive countermeasure.
4. Low-Power tracking optimization. Optimization of SLAM and object detection pipelines for all-day wearable battery performance. E.G. Exploitation in Entertainment settings, e.g. Augmented Theatres.
5. Impact on Social Dynamics and Behaviours: analyzing how sentiment, and habits of people will be affected by large scale adoption of this devices. Qualitative & quantitative analysis of behavioral shifts in high-frequency AR/AI interaction settings.

Problem:
Navigating large-scale virtual environments remains an open challenge in VR research. World-in-Miniature (WIM) interfaces have been studied almost exclusively in flat environments, leaving critical issues unresolved regarding scale management, occlusion handling, and the topographic complexity of real-world spaces.
Objective:
Extend and deepen WIM research in complex VR contexts, addressing challenges related to: multi-story indoor environments, occlusion management, adaptive scaling techniques, alternative input modalities (mid-air gestures, eye-gaze control), and hierarchical navigation through Points of Interest (POIs).
Approach: Design and prototype novel WIM techniques and evaluate them through controlled user studies, measuring navigation efficiency, cognitive load, and spatial knowledge acquisition.
Expected Impact:
Effective WIM techniques for topographically complex VR environments.