Haptic feedback is an essential aspect of human-computer interaction, particularly in industrial settings where precise and realistic touch sensations are crucial for successful manual tasks. Collaborative robots (Cobots) have revolutionized industrial production processes by working alongside human operators, and this characteristic also opened up other uses for such devices, for example, in the context of Virtual Reality (VR). This thesis proposal aims to investigate the feasibility of providing faithful on-demand haptic feedback using collaborative robots as "Encountered Type" haptic devices, to simulate a manual task (i.e., defects identification and correction) within industrial production processes. The research will also explore how this technology can enhance defect identification, issue management, and improve workplace safety by simulating ergonomic aspects and delivering effective training content. The investigation will be conducted in collaboration with industrial partners and will align with the objectives of the MANAGE 5.0 project, supported by the Ministry of Enterprises and Made in Italy (MISE) and the National Recovery and Resilience Plan (PNRR).

Haptic feedback is an essential aspect of human-computer interaction, particularly in industrial settings where precise and realistic touch sensations are crucial for successful manual tasks. Collaborative robots (Cobots) have revolutionized industrial production processes by working alongside human operators, and this characteristic also opened up other uses for such devices, for example, in the context of ...

In modern production processes, the efficient detection and management of defects are critical for ensuring high-quality output and optimizing manufacturing operations. The advent of automation and advanced computer vision techniques has enabled the automatic detection of defects in real-time. However, conveying this vital information to production line operators in a clear, intuitive, and timely manner remains a challenge.

This thesis proposal aims to investigate the application of Mixed Reality (MR) as a means for conveying information regarding automatically detected defects to production line operators. The research will involve the integration of the output from computer vision algorithms and defect detection methodologies that have been already developed and experimented on a production line of Stellantis.

By utilizing MR technology, the proposed investigation seeks to overlay defect-related information, such as visual cues, guidance, and instructions, directly onto the physical production environment in real-time. This approach aims to enhance operators' situational awareness, enable rapid decision-making, and facilitate timely defect resolution.

The research collaboration will actively engage the industrial partner, ensuring the practicality and relevance of the findings. Moreover, the project will be in alignment with the overarching objectives of the MANAGE 5.0 project, funded by the Ministry of Enterprises and Made in Italy (MISE) and the National Recovery and Resilience Plan (PNRR).

In modern production processes, the efficient detection and management of defects are critical for ensuring high-quality output and optimizing manufacturing operations. The advent of automation and advanced computer vision techniques has enabled the automatic detection of defects in real-time. However, conveying this vital information to production line operators in a clear, intuitive, and timely manner remains ...

As autonomous Vertical Take-Off and Landing (VTOL) technology advances, ensuring passenger comfort and confidence becomes paramount. Previous research has focused on developing Human-Machine Interfaces (HMIs) to improve passenger experience during standard flight phases (takeoff, cruise, landing) and in common visibility conditions. However, passengers are likely to experience anxiety in more critical situations, like presence of heavy air traffic, turbulent weather (wind gusts, snow, thunderstorms), and varying visibility (sunny, cloudy, foggy, snowy, stormy).

The objective of this thesis is to design and develop such HMIs by integrating them into an immersive VR-based autonomous VTOL simulator for urban mobility. In particular, the student will focus on the visualization of the air traffic, and on the integration of air traffic data using a proprietary API.

During the thesis, the student will be able to use the most advanced VR HMD with human-eye resolution (Varjo-XR 3) and a motion simulation platform available at the Department of Control and Computer Engineering (DAUIN). The student will also learn how to carry out user centred experimental design and validation.

The project is developed in the context of the Centro Nazionale per la Mobilità Sostenibile (CNMS-MOST) funded by the National Recovery and Resilience Plan (PNRR) which involves multiple Universities and Companies.

As autonomous Vertical Take-Off and Landing (VTOL) technology advances, ensuring passenger comfort and confidence becomes paramount. Previous research has focused on developing Human-Machine Interfaces (HMIs) to improve passenger experience during standard flight phases (takeoff, cruise, landing) and in common visibility conditions. However, passengers are likely to experience anxiety in more critical ...

Despite the advancements in Virtual Reality (VR) technology, cost-effective hardware and tracking system are still suffering from accuracy limitations that in some cases can limit the natural interaction of the user with the virtual environment, ruining the user experience. That is the case, for instance, of operating on keyboards and button in an aircraft cockpit (precisely rotating small and tightly spaced knobs, pushing buttons, etc.) which are particularly challenging, especially when the user is also subject to external movements or acceleration (like in a flying helicopter or VTOL)

The objective of this thesis is to develop a human-machine interaction approach for this specific use case capable of overcoming the hardware limitation by combining multiple user inputs together (eye-tracking, finger tracking, speed of movements, etc.).

This thesis is aimed for students that are interested in conducting research on frontier aspects of the human-computer interaction in VR and apply it to a real-world use case.

During the thesis, the student will be able to use VR HMD with hand tracking and eye tracking technology and a motion simulation platform available at the Department of Control and Computer Engineering (DAUIN). The student will also learn how to carry out user centred experimental design and validation.

The project is developed in the context of the Centro Nazionale per la Mobilità Sostenibile (CNMS-MOST) funded by the National Recovery and Resilience Plan (PNRR) which involves multiple Universities and Companies.

Despite the advancements in Virtual Reality (VR) technology, cost-effective hardware and tracking system are still suffering from accuracy limitations that in some cases can limit the natural interaction of the user with the virtual environment, ruining the user experience. That is the case, for instance, of operating on keyboards and button in an aircraft cockpit (precisely rotating small and tightly spaced ...

Finding educational material that is required to complete the own set of possessed skills or those of a company's workforce is essential in today's knowledge society. The IEEE Digital Reality has developed a tool, known as Knowledge as a Service or KaaS (https://kaas.ieee.org/) that can be used to describe a set of possessed skills based on the IEEE ontology and match it against the knowledge base of IEEE Technology Navigator, thus gaining access to the universe of information related to IEEE conferences, publications, standards, and articles. The aim of this thesis is to create a virtual environment for letting users access the KaaS tool in an engaging manner. It will be necessary to choose whether to use one of the existing VR-enabled Metaverse or Social VR platforms, or develop an hoc one, e.g., starting from a custom virtual environment recently developed by the GRAINS group and the VR@POLITO for similar purposes. A pleasant and appropriate immersive space will have to be created. Then, the virtual environment will have to be connected to KaaS using available REST APIs, and an effective (e.g., gamified) user interface will have to be developed.

Finding educational material that is required to complete the own set of possessed skills or those of a company's workforce is essential in today's knowledge society. The IEEE Digital Reality has developed a tool, known as Knowledge as a Service or KaaS (https://kaas.ieee.org/) that can be used to describe a set of possessed skills based on the IEEE ontology and match it against the knowledge base of IEEE ...

This thesis will be developed in collaboration with Mauriziano Hospital / Università di Torino and will focus on the use of XR technologies in healthcare education and training. More specifically, in their clinical practice, emergency doctors often need to perform invasive procedures. Among these, one of the most complex is the placement of a central venous catheter in a large-caliber vein (jugular, subclavian, femoral). The procedure involves several steps, some of which are performed under ultrasound guidance. Specifically, the doctor must identify the vessel to be punctured using ultrasound and manage the ultrasound probe with one hand while using the dominant hand to puncture the vessel. Another procedure presenting similar challenges is thoracentesis, a medical procedure performed to remove fluid or air from the pleural space (i.e., the thin gap between the lungs and the chest wall). Similarly, paracentesis is a medical procedure in which a needle or catheter is inserted into the peritoneal cavity to obtain ascitic fluid for diagnostic or therapeutic purposes.

The main difficulty of these procedures is developing good manual skills in simultaneously handling multiple instruments. This thesis proposal aims to study XR solutions that would allow emergency doctors to practice and improve their manual skills. It would be beneficial to conduct training using XR, because, currently, the only way to learn is by performing these procedures live with real patients. This approach comes with a range of issues, including risk to the patient, overcrowding in the emergency department, and the lack of necessary time to properly apply and execute the training on the procedure. The literature has already confirmed the numerous benefits brought by the use of XR technologies for medical training. However, limited works have focused on aspects related to the improvements of manual skills. This is probably due to the challenges that come when integrating real tools within Augmented or Virtual Reality applications.

Suggested reads:
- Vaghela, K. R., et al. Active vs passive haptic feedback technology in virtual reality arthroscopy simulation: Which is most realistic? Journal of Clinical Orthopaedics and Trauma (2021)
- Licona, A. R., et al. Applications of haptics in medicine. Haptic Interfaces for Accessibility, Health, and Enhanced Quality of Life (2020)
- Escobar-Castillejos, D., et al. A review of simulators with haptic devices for medical training. Journal of medical systems (2016)
- Bruno Tartaglino,Carolina Prevaldi. Manovre e Procedure - Medicina di Emergenza-Urgenza. C.G. Edizioni Medico Scientifich. ISBN / ISSN: 978-88-7110-233-7 (2010)

This thesis will be developed in collaboration with Mauriziano Hospital / Università di Torino and will focus on the use of XR technologies in healthcare education and training. More specifically, in their clinical practice, emergency doctors often need to perform invasive procedures. Among these, one of the most complex is the placement of a central venous catheter in a large-caliber vein (jugular, ...

The recognition of the vehicle’s owner or the person authorized to operate a given vehicle will be a challenge for future intelligent vehicle applications. Furthermore, the person to be recognized stands outside the car, in different and complex conditions (recognition in the “wild”): highly variable lighting, presence of other subjects, etc. Apart from the difficulty and complexity of the recognition algorithm, one of the fundamental problems becomes the data needed to train required AI models, which cannot be available yet. In this case, so-called synthetic data need to be employed. Synthetic data, generated through some simulation environments, can mimic operational conditions, by also enabling to keep edge cases into account. In fact, real-world datasets often contain imbalances, because edge cases, which do not happen frequently in real life, are not sufficiently represented. Finally, with synthetic data, other issues, e.g., related to privacy and GDPR compliance, can be easily overcome. The focus of this thesis, developed in collaboration with Centro Ricerche Fiat (CRF) and Stellantis, will be the use of computer graphics simulation (e.g., with tools like Unreal Engine's MetaHuman) or generative methods for the the production of synthetic data that could be later used to train AI algorithms for the recognition of vehicle owners that are robust to variations in terms of, e.g., illumination, presence of other human and non-human subjects, etc.

The recognition of the vehicle’s owner or the person authorized to operate a given vehicle will be a challenge for future intelligent vehicle applications. Furthermore, the person to be recognized stands outside the car, in different and complex conditions (recognition in the “wild”): highly variable lighting, presence of other subjects, etc. Apart from the difficulty and complexity of the recognition ...

Autonomous vehicles are routinely advertized as the world-changing invention that will greatly impact people lives by, on the one hand, improving safety, reducing fuel consumption and decreasing urban infra-structure strains, and, on the other hand, freeing up huge amounts of time for their occupants, who will be allowed to read, consume, work, play, etc. Despite the enormous business opportunities, autonomous vehicles also come with some key issues.

One of the major issues is related to the fact that, in oder to use these technology, people will first have to trust it. Besides education and experience, a factor that is regarded as the possible keystone for constructing trust towards autonomous vehicles is represented by HMI, i.e., by the paradigms chosen to communicate with the users (the vehicle occupants, but also the other road users) and to make them interact with it.

At present, since just a few vehicles are actually available for real-world experiments (and not at the highest levels of autonomy envisaged by SAE, yet) the only way to design and validate approaches for possibly coping with issues like those above is through simulation.

The VR@POLITO has developed an immersive VR driving simulation platform that has been used, e.g.,

- to explore in-vehicle interfaces based on AR Head Up Displays for enhancing drivers'/passengers' trust;
- to study pedestrians' behavior at crosswalks with incoming vehicles mounting different types of signaling interfaces;
- to investigate the effectiveness of multi-modal interfaces in urban, suburban and highway drives with autonomous vehicles.

Several thesis works are available in this field, which can address the open problems from different perspectives, possibly in collaboration with a company.

Suggested readings:

Building Trust in Autonomous Vehicles: Role of Virtual Reality Driving Simulators in HMI Design
https://arxiv.org/abs/2007.13371

Comparing State-of-the-Art and Emerging Augmented Reality Interfaces for Autonomous Vehicle-to-Pedestrian Communication
https://arxiv.org/abs/2102.02783

Autonomous vehicles are routinely advertized as the world-changing invention that will greatly impact people lives by, on the one hand, improving safety, reducing fuel consumption and decreasing urban infra-structure strains, and, on the other hand, freeing up huge amounts of time for their occupants, who will be allowed to read, consume, work, play, etc. Despite the enormous business opportunities, autonomous ...

Several collaborations are in place with Piedmont Region Civil Protection and Forest Firefighting Unit involved in emergency management. In this context, a number of serious games and interactive experiences leveraging Virtual Reality, Augmented Reality and Mixed Reality have been developed to support education and training of first responders, volunteers, students, etc. Three thesis proposals are available, to be developed mostly at Politecnico di Torino in collaboration with the said institutions.

The objective of the first thesis is to design and implement a Virtual Reality (VR) training system tailored for firefighters specializing in aerial wildfire suppression using helicopters and Canadair aircraft. The system will leverage VR headsets and will be developed using Unity or Unreal Engine. The training system will integrate a flight simulator and a realistic fire and smoke simulator to create an immersive and effective training environment. References: https://ieeexplore.ieee.org/abstract/document/8576892, https://ieeexplore.ieee.org/abstract/document/8797889.

The second thesis proposal aims to develop a portable firefighting training system that leverages virtual reality (VR) and haptic interfaces. The system to be designed and developed should focus on training firefighters in the use of leaf blowers, a valuable tool for fire control, and backpack pumps. An adequate haptic interface should allow trainees to experience realistic jet reaction forces from the hose, enhancing their understanding of the equipment. Additionally, the system should feature accurate particle physics modeling for air and water dispersion, fire, and smoke interactions. Particular emphasis should be dedicated to the implementation of the virtual scenario, with a focus on the integration of terrains with different slopes and the creation of lifelike scenarios to effectively prepare firefighters.

The third thesis's gol is to build a multi-layer, multi-player training tool by integrating a series of previously developed interactive experiences. For instance, immersive VR-based applications for training on the use of low-flame firefighting tools or high-pressure pumping equipment have been created already. The idea would be to make it possible for decision makers to see the effects of various teams operating in such applications from a kind of centralized control room.

Several collaborations are in place with Piedmont Region Civil Protection and Forest Firefighting Unit involved in emergency management. In this context, a number of serious games and interactive experiences leveraging Virtual Reality, Augmented Reality and Mixed Reality have been developed to support education and training of first responders, volunteers, students, etc. Three thesis proposals are available, to ...

Cybersickness is a disorder characterized by symptoms like nausea or discomfort, that can happen meanwhile or after using Virtual Reality (VR) . Similarly to motion sickness, it is mainly caused by inconsistency between visual and aural stimuli from the simulated virtual environment and the expected feedback from the vestibular system. Several mitigation and prevention techniques have been proposed and adopted in many commercial products. However, most of them are highly situational, or require making implementation choices that can have a negative impact on core aspects such immersion, naturalness, and sense of presence.

An approach that is still underexplored but gaining popularity among communities of users is the phenomenon of “habituation to VR”, colloquially known as “VR Legs”. It is known that repeated exposure to VR tends to reduce users' susceptibility to Cybersickness. Various VR users have reported that they have been able to develop VR Legs through repeated VR sessions of increasing duration and intensity over time. However, there is no study that has verified the existence of this phenomenon, nor are there validated guidelines that, if followed, could provide these theoretical benefits.

The objective of this thesis proposal is therefore to design a “VR Legs development” protocol, based on publicly available applications or on applications created for the purpose, which should allow a user who follows it meticulously to gain the benefits of habituation and reduce susceptibility to Cybersickness. The protocol will then be evaluated through a longitudinal user study to demonstrate its effectiveness and applicability.

References: https://xinreality.com/wiki/VR_legs.

Cybersickness is a disorder characterized by symptoms like nausea or discomfort, that can happen meanwhile or after using Virtual Reality (VR) . Similarly to motion sickness, it is mainly caused by inconsistency between visual and aural stimuli from the simulated virtual environment and the expected feedback from the vestibular system. Several mitigation and prevention techniques have been proposed and adopted ...

Generating computer animations, particularly of virtual characters, is a very labor-intensive task, which requires animators to operate with sophisticated interfaces. Hence, researchers continuously experiment with alternative interaction paradigms that could possibly ease the above task. Among others, the use of XR represents a valid alternative to traditional interfaces (based on mouse and keyboard) since it can make interactions more expressive and intuitive. However, although the literature proposes several solutions leveraging XR to solve different computer graphics challenges, generally, these solutions are not fully integrated into the computer animation pipeline or were not designed to support collaborative working.

The objective of this thesis proposal is to design and develop tools integrated in Blender that allow animators to produce and edit 3D character animations, possibly considering alternative interfaces. Related works have been proposed in the literature. For example, in [1], a system was proposed by the Disney research lab to support collaborative animations through a Mixed Reality system. Additional examples for authoring contents, 3D modeling, or directing actors in virtual scenes have been proposed in [2-4]. However, according to a recent survey [5], it was not possible to identify prior initiatives that make use of XR and collaborative environments to produce computer animations. This research gap is probably due to the number of challenges that researchers have to face when approaching the design of collaborative AR/VR systems [6]. The thesis could envisage scenarios that combine VR and AR to foster collaboration among the animators.

Related works:
[1] Pan, Ye, and Kenny Mitchell (Disney Research). "PoseMMR: a collaborative mixed reality authoring tool for character animation." 2020 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW). IEEE, 2020
[2] Nebeling, Michael, et al. "Xrdirector: A role-based collaborative immersive authoring system." Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. 2020.
[3] Larpkiattaworn, Noppasorn, et al. "Multiuser Virtual Reality for Designing and Editing 3D Models." International Conference on Human-Computer Interaction. Springer, Cham, 2020.
[4] Wang, Cheng Yao, et al. "VideoPoseVR: authoring virtual reality character animations with online videos." Proceedings of the ACM on Human-Computer Interaction 6.ISS (2022): 448-467.
[5] Schäfer, Alexander, Gerd Reis, and Didier Stricker. "A Survey on Synchronous Augmented, Virtual and Mixed Reality Remote Collaboration Systems." ACM Computing Surveys (CSUR) (2021).
[6] Krauß, Veronika, et al. "Current practices, challenges, and design implications for collaborative AR/VR application development." Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. 2021.

Generating computer animations, particularly of virtual characters, is a very labor-intensive task, which requires animators to operate with sophisticated interfaces. Hence, researchers continuously experiment with alternative interaction paradigms that could possibly ease the above task. Among others, the use of XR represents a valid alternative to traditional interfaces (based on mouse and keyboard) since it ...

Extended Reality (XR) technologies, encompassing both Augmented Reality (AR) and Virtual Reality (VR), are disrupting the way films are produced and viewed. Although these technologies are becoming commonplace, they are presenting new, unexplored challenges to both the actors and final viewers. For instance, when motion capture is used to record actors’ movements with the aim of animating digital characters, an increase in the workload is observed for people on stage as they have to rely largely on their imagination to understand how the digitally created characters will behave in the scene. Another research direction regards the effects of innovative cinematic techniques on the viewers' experience. For instance, a key step for immersive movies would be the selection of ideal points of view that would provide the viewer with the best user experience when watching an immersive movie.

In this field, several theses are available. One of the main goals is to deepen existing studies in the context of cinematic AR/VR by conducting more in-depth analyses aimed at offering immersive contents more suitable to the viewers' expectations. For instance, the effects of immersive audio and lighting, as well as the posture adopted by the viewers during the experience, could be studied. Another possibility regards the improvements of an AR system designed to support the actors while rehearsing scenes containing visual effects. Specifically, new solutions are required to cope with limitations due to the combination of MoCap and AR (e.g., for correcting the point of view of the controlled character).

Suggested readings:
- Gödde M, Gabler F, Siegmund D, Braun A (2018) Cinematic narration in VR—rethinking film conventions for 360 degrees. Springer, pp 184–20
- Cannavò A; Pratticò F G; Bruno A; Lamberti F. "AR-MoCap: Using augmented reality to support motion capture acting". In: 30th IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR 2023), Shanghai, China, March 25-29, 2023
- Cannavò A; Castiello A; Pratticò F G; Mazali T; Lamberti F. "Immersive Movies: The Effect of Point of View on Narrative Engagement". In: AI & SOCIETY. (2023)
- Yang D.; Kang J.; Kim T.; Lee S. H. "Visual Guidance for User Placement in Avatar-Mediated Telepresence between Dissimilar Spaces". In: IEEE Transactions on Visualization and Computer Graphics. (2024)
- Chung C.; Lee S. H. "Continuous Prediction of Pointing Targets with Motion and Eye-Tracking in Virtual Reality". In: IEEE Access. (2024)
- Wisessing Pisut, et al. "Enlighten Me: Importance of Brightness and Shadow for Character Emotion and Appeal.". In: ACM Transactions on Graphics. (2020)

Extended Reality (XR) technologies, encompassing both Augmented Reality (AR) and Virtual Reality (VR), are disrupting the way films are produced and viewed. Although these technologies are becoming commonplace, they are presenting new, unexplored challenges to both the actors and final viewers. For instance, when motion capture is used to record actors’ movements with the aim of animating digital characters, ...

The fashion industry is undergoing a digital revolution driven by recent technological improvements. Particularly in design processes and marketing strategies, new solutions have been introduced in recent years. Both market brands and researchers are increasingly investing in technologies like Virtual Fitting Rooms (VFRs) to enrich customer experiences with innovative features, such as Virtual Try-On (VTON) applications, aimed at facilitating shopping. Despite these advancements, challenges persist that could prevent customers from fully leveraging VTON solutions. These challenges include difficulties in recreating high-fidelity avatars of the users and simulating real-time clothing deformations.

In this field, several theses are available. One of the goals is to improve the generation of high-fidelity avatars. Specifically, the thesis requires optimizing an existing framework for the generation of avatars by exploring new solutions aimed at i) better estimating the values of the parametric model describing the avatar, ii) coping with the current limitations of existing frameworks, iii) identifying solutions for generating not only the 3D model but also the textures and fine details of the avatar. Another research direction considers the challenges related to clothes generation and animation. In this respect, the thesis would require the design of new solutions able to i) automatically reconstruct the physical properties of the materials from images and scans, and ii) generate the 3D model of the garment from the sewing patterns. Moreover, the advantages brought by the use of parametric virtual try-on and real-time cloth deformation could be studied.

Suggested readings:
- Cannavo' A.; Pesando R.; Lamberti F. A Framework for Animating Customized Avatars from Monocular Videos in Virtual Try-On Applications. In: International Conference on Extended Reality (2023).
- Gao Qiqi; Takafumi Taketomi. Garment Model Extraction from Clothed Mannequin Scan. In: Computer Graphics Forum. 2023.
- Berthouzoz Floraine, et al. Parsing sewing patterns into 3D garments. In: ACM Transactions on Graphics (TOG). (2013)
- Libao E. I.; Lee M.; Kim S.; Lee S. H. MeshGraphNetRP: Improving Generalization of GNN-based Cloth Simulation. In Proc of the 16th ACM SIGGRAPH Conference on Motion, Interaction and Games. (2023)

The fashion industry is undergoing a digital revolution driven by recent technological improvements. Particularly in design processes and marketing strategies, new solutions have been introduced in recent years. Both market brands and researchers are increasingly investing in technologies like Virtual Fitting Rooms (VFRs) to enrich customer experiences with innovative features, such as Virtual Try-On (VTON) ...

In the realm of social inclusion, numerous studies and applications have aimed at assisting individuals on the autism spectrum. Autistic Spectrum Disorder (ASD) encompasses a wide range of conditions that differ greatly among individuals. Some common challenges faced by those with ASD include: difficulties in social communication, such as interpreting emotions, understanding non-verbal cues, and building friendships or relationships; restricted and/or repetitive behaviors, motor movements, interests, and instances of hyperactivity; co-occurring neuro-cognitive disorders, including intellectual disabilities or specific syndromes.

Research has shown that Extended Reality (XR) technologies, such as Virtual Reality (VR), can effectively support this group by enhancing social skills, education, and User eXperience (UX) in several types of environments. However, the topic of accessibility for ASD has not been explored enough when it comes to Cultural Heritage (CH) environments, such as historical buildings and museums. These environments can provide significant learning opportunities for ASD users but also present many challenges: loud or sudden noises, crowded rooms, bright or blinding lights; each of these elements can cause sensory overload, with common reactions among ASD users (repetitive movements, anxiety, panic...) or completely different reactions based on the individual user's characteristics.

This proposal aims to explore techniques and tools in a Virtual Museum (VM) environment to enhance CH accessibility for ASD users. For this purpose, the thesis will involve the creation of a VM experience that will be responsible for anticipating the physical environment in an accessible way. This investigation will possibly involve also a testing phase with ASD users.

Suggested readings:

- Diagnostic and Statistical Manual of Mental Disorders: Fifth Edition Text Revision DSM-5-TR™;
- A. Adjorlu, E. R. Høeg, L. Mangano and S. Serafin, "Daily Living Skills Training in Virtual Reality to Help Children with Autism Spectrum Disorder in a Real Shopping Scenario," 2017 IEEE International Symposium on Mixed and Augmented Reality (ISMAR-Adjunct), Nantes, France, 2017
- Moon, J., Choi, G. & Seo, J. Revisiting multimedia learning design principles in virtual reality-based learning environments for autistic individuals. Virtual Reality (2023).
- Sanku Bhavya Sri, Li Yi (Joy), Jung Sungchul, Mei Chao, He Jing (Selena), Enhancing attention in autism spectrum disorder: comparative analysis of virtual reality-based training programs using physiological data, Frontiers in Computer Science

In the realm of social inclusion, numerous studies and applications have aimed at assisting individuals on the autism spectrum. Autistic Spectrum Disorder (ASD) encompasses a wide range of conditions that differ greatly among individuals. Some common challenges faced by those with ASD include: difficulties in social communication, such as interpreting emotions, understanding non-verbal cues, and building ...

“Metaverse” is a term that refers to immersive virtual universe, generally accessible through eXtended Realty devices. Although the main purpose of this universe is socialization, recent efforts are starting to focus on the creation of experiences for education and training. Currently, several metaverse platforms, each with unique features and limitations, can be used for creating these experiences.

The objective of this thesis is to explore the functionalities of the existing platforms, with the aim to evaluate their intrinsic characteristics, their advantages and disadvantages with respect to the domain of interest, and, ultimately, which ones are the most suitable for the realization of learning experiences. To conduct this evaluation, it will be necessary to create basic learning tasks within the considered metaverse platforms.

Among the best-known platforms that can, in principle, support the creation of such tasks it is possible to mention VRChat, Decentraland, Roblox, Horizon Worlds, RecRoom, The Sandbox, Sansar, etc. Some platforms stand out because they are based on the Blockchain, others for their marked social nature or for the possibility they offer to create highly personalized experiences (from simple modifications to avatars and other assets provided, up to the management of more complex aspects such as physics simulation). Each of these characteristics can be suitable for the creation of learning experiences, depending on the pedagogical needs and the tackled context.

“Metaverse” is a term that refers to immersive virtual universe, generally accessible through eXtended Realty devices. Although the main purpose of this universe is socialization, recent efforts are starting to focus on the creation of experiences for education and training. Currently, several metaverse platforms, each with unique features and limitations, can be used for creating these experiences. ...

Technological advances have significantly changed the way individuals communicate, bridging geographical divides and fostering connections across platforms such as smartphones, social networks and virtual reality (VR). In particular, the emergence of VR technology has responded to the desire for more engaging online interactions, paving the way for social VR platforms. These platforms allow users to create custom avatars and interact with old and new friends in customized virtual environments. Despite the immersive nature of Social VR, there remains a significant gap in non-verbal communication, which is a crucial element in the perspective user experience. In fact, research suggests that non-verbal signals play a vital role in making interactions more engaging and realistic.

Therefore, addressing this gap is key to further enhancing user immersion and presence. In particular, “mimicry”, i.e. the unconscious imitation of communicative patterns, movements and expressions, is a fundamental element of non-verbal communication that has been scarcely explored so far in the context of Social VR. The aim of this thesis is to design, develop and subsequently evaluate through user tests a mimicry algorithm of body movements to improve empathy and socialisation between individuals in a virtual environment. The starting point for the thesis will be a previous work carried out by the GRAINS group on facial mimicry.

Technological advances have significantly changed the way individuals communicate, bridging geographical divides and fostering connections across platforms such as smartphones, social networks and virtual reality (VR). In particular, the emergence of VR technology has responded to the desire for more engaging online interactions, paving the way for social VR platforms. These platforms allow users to create ...

eXtended Reality (XR) technologies, including Virtual reality (VR), Augmented Reality (AR), and Mixed Reality (MR), offer new opportunities for collaboration and communication among users in virtual and hybrid contexts. Specifically, the use of XR in co-located design tasks, where multiple users need to collaborate in real-time and share ideas, opens new horizons for improving the efficiency and creativity of group work. This thesis aims, on the one hand, to compare and evaluate different types of XR technologies (VR, AR, MR) in the context of co-located design tasks, where users need to communicate and show their ideas to each other and, on the other hand, to identify and develop techniques, metaphors, and gamification elements that optimize the use of XR in these contexts, providing cues, information, actions, and mechanics that would not be possible without the use of XR. The thesis aims to offer an in-depth understanding of how XR technologies can be optimally used to facilitate collaborative design tasks, improving the quality of group work and communication among participants. The results will contribute to outlining future applications and developments of XR technologies in collaborative contexts.

References:
- CIDER: Collaborative Interior Design in Extended Reality
https://dl.acm.org/doi/abs/10.1145/3605390.3605419
- ARID—An Augmented Reality Mobile Application for Interior Design
https://link.springer.com/chapter/10.1007/978-3-031-20182-0_1
- Studying gesture-based interaction on a mobile augmented reality application for co-design activity
https://link.springer.com/article/10.1007/s12193-017-0252-0#Sec1
- Cues to fast-forward collaboration: A Survey of Workspace Awareness and Visual Cues in XR Collaborative Systems
https://onlinelibrary.wiley.com/doi/full/10.1111/cgf.15066
- What And How Together: A Taxonomy On 30 Years of Collaborative Human-Centered XR Tasks
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10316494

eXtended Reality (XR) technologies, including Virtual reality (VR), Augmented Reality (AR), and Mixed Reality (MR), offer new opportunities for collaboration and communication among users in virtual and hybrid contexts. Specifically, the use of XR in co-located design tasks, where multiple users need to collaborate in real-time and share ideas, opens new horizons for improving the efficiency and creativity of ...

The fusion of Large Language Models (LLMs) with Virtual Reality (VR) holds promise for a significant evolution in user experience. Within this context, exploring the utilization of LLMs for a hands-free locomotion system becomes particularly intriguing. This thesis aims to leverage the advanced natural language processing capabilities of these models to interpret user commands for teleportation, thus enhancing user interaction and immersion by allowing seamless and intuitive navigation without the need for physical controllers.

The primary objective will be to design and implement a framework that integrates LLMs for hands-free teleportation in VR environments. The activities will start with the design of the framework, defining a comprehensive set of teleportation commands and establishing the architecture for integrating LLMs with Unity. The implementation phase will involve developing a prototype, utilizing LLMs to interpret spoken commands and control VR teleportation. The system's effectiveness will be evaluated through user studies, collecting both quantitative and qualitative data to measure accuracy, response times, and overall user experience.

References:
- D. Calandra, F. G. Pratticò, and F. Lamberti, "Comparison of Hands-Free Speech-Based Navigation Techniques for Virtual Reality Training," in 2022 IEEE 21st Mediterranean Electrotechnical Conference (MELECON), Palermo, Italy, 2022, pp. 85-90. doi: 10.1109/MELECON53508.2022.9842994.
- J. A. V. Fernandez, J. J. Lee, S. A. S. Vacca, A. Magana, B. Benes, and V. Popescu, "Hands-Free VR," arXiv preprint arXiv:2402.15083, 2024

The fusion of Large Language Models (LLMs) with Virtual Reality (VR) holds promise for a significant evolution in user experience. Within this context, exploring the utilization of LLMs for a hands-free locomotion system becomes particularly intriguing. This thesis aims to leverage the advanced natural language processing capabilities of these models to interpret user commands for teleportation, thus enhancing ...

Extended reality applications are getting commonplace in several domains, ranging from entertainment to education. Moreover, the increasing interest in the Metaverse is attracting, more and more, the attention of researchers and companies. In the Metaverse, different communities can meet each other, with the aim of exchanging their idea or knowledge and working together on a given project. But what happens if a user has not the possibility to participate in an online event, or the people he or she is looking for lived in the previous century?

The aim of this thesis is to provide users the possibility to experience seamless physical interactions or events even if they happened in the past. In this way, when a user is unable to participate in a given interaction or event, the system will be able to capture co-located or remote physical events in real-time, recognize and constructs a list of events (possibly dependent on each other), and allow immersed users to revisit them at a suitable time. Intelligent systems could be leveraged to make alive famous people or reconstruct historical events, with the aim of making them available in the Metaverse. This capability of a system to reconstruct events and interactions is usually referred to as Asynchronous Reality. The system will also allow users to transition along the reality-virtuality continuum and collaborate with users experiencing the same application through different technologies. In this way, the benefits of both virtual and augmented reality can be leveraged in the same application, e.g., for developing problem-solving skills, proposing and validating new interaction paradigms. Developing such kind of asynchronous- and cross-reality systems is usually characterized by numerous challenges (addressed in this thesis). The outcomes of this research would be applied to a number of use cases, such as virtual prototyping, training, enabling user-to-user or user-to-machine/robot collaborations in scenarios regarding, e.g., education, industry, healthcare, cultural heritage, etc.

Suggested readings:
- Gruenefeld, Uwe, et al. "VRception: Rapid Prototyping of Cross-Reality Systems in Virtual Reality." CHI Conference on Human Factors in Computing Systems. 2022.
- Wang, Nanjia, and Frank Maurer. "A Design Space for Single-User Cross-Reality Applications." Proceedings of the 2022 International Conference on Advanced Visual Interfaces. 2022.
- Kikuchi, Yusuke, et al. "Mobile Cross Reality (XR) Space for Remote Collaboration." Human Factors in Virtual Environments and Game Design 50 (2022).
- Woodworth, Jason W., David Broussard, and Christoph W. Borst. "Redirecting Desktop Interface Input to Animate Cross-Reality Avatars." 2022 IEEE Conference on Virtual Reality and 3D User Interfaces (VR). IEEE, 2022.
- Fender, Andreas Rene, and Christian Holz. "Causality-preserving asynchronous reality." Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems. 2022.

Extended reality applications are getting commonplace in several domains, ranging from entertainment to education. Moreover, the increasing interest in the Metaverse is attracting, more and more, the attention of researchers and companies. In the Metaverse, different communities can meet each other, with the aim of exchanging their idea or knowledge and working together on a given project. But what happens if a ...

Several new thesis proposals are available, which will be developed in collaboration with HyperTennis (https://hypertennis.it/) a startup / spin-off of Politecnico di Torino. HyperTennis is designing solutions for the application of Artificial Intelligence and other technologies to analyze and improve the performance of tennis players. Thesis works will require the application of Computer Vision and Deep Learning techniques to:
1) perform high-speed, Human Pose Estimation and extract the articulated 3D model of the tennis players from the video feed coming from multiple, synchronized cameras
2) identify relevant tennis players' actions in the execution of technical gestures, i.e. shots (serve, forehand, backhand, etc.)
3) extract accurate information about the ball (trajectories and impact with the racket and the field). 4) automatically classify shot type
5) identify/separate specific phases in the execution of a shot
6) predicting next shot based on historical data

Several new thesis proposals are available, which will be developed in collaboration with HyperTennis (https://hypertennis.it/) a startup / spin-off of Politecnico di Torino. HyperTennis is designing solutions for the application of Artificial Intelligence and other technologies to analyze and improve the performance of tennis players. Thesis works will require the application of Computer Vision and Deep ...

The aim of this thesis, to be developed in collaboration with the Egyptian Museum in Turin, is to develop an algorithm able to reconstruct in a digital way the fragments of archeological remains by analyzing the fracture surfaces of the single pieces. The algorithm could be first tested on a “modern” object reduced to pieces, and then applied to a use case to be agreed with the Museum (e.g., stone fragments from a statuary group, decorated floor or ceiling pieces, ceramic parts, etc.). The match between two fragments shall be identified based on the analysis of the geometries, not of the possible color information that could still be visible on the surface. The algorithm should provide a confidence score for the various matches identified. 3D geometries will be provided by the Museum. These geometries will be created using the Artec Space Spider, a structured light scanner capable to produce meshes with a resolution up to 0.1 mm.

Suggested readings:
https://www.sciencedirect.com/science/article/abs/pii/S1296207422000826
https://ieeexplore.ieee.org/document/4697243
https://www.researchgate.net/publication/333161346_Reassembling_Fractured_Objects_by_Geometric_Matching
https://www.academia.edu/51368373/Automated_reconstruction_of_fragmented_objects_using_their_3D_representation_Application_to_important_archaeological_finds
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3231500/

The aim of this thesis, to be developed in collaboration with the Egyptian Museum in Turin, is to develop an algorithm able to reconstruct in a digital way the fragments of archeological remains by analyzing the fracture surfaces of the single pieces. The algorithm could be first tested on a “modern” object reduced to pieces, and then applied to a use case to be agreed with the Museum (e.g., stone fragments ...

Current social media generate a tremendous amount of visual material, that can be exploited by researchers operating in social media research, digital humanities, and marketing. However, privacy regulations impose significant restrictions to both data collection and sharing. The CAMOUFLAGE project, funded by the AI4Media European project, aims to exploit diffusion model (such as Stable Diffusion) to produce a synthetic version of an existing image, presenting equivalent visual and semantic characteristics of the original, while at the same time fully preserving the anonymity of the user who published the image. The project has a strong multidisciplinary focus and will be carried out in collaboration with researchers in visual semiotics to determine the quality and information content of the generated image. The system will be tested on a collection of real Facebook and Instagram profile pictures. Multiple thesis are available tackling three distinct, yet related, research objectives: to design and implement controllable image synthesis that retains the visual and semantic content of a target image; to determine whether the resulting synthetic images can be considered successfully anonymized, in comparison with state-of-the-art solutions based on GANs; and whether the synthetic collection has the same information content of the original image.

Current social media generate a tremendous amount of visual material, that can be exploited by researchers operating in social media research, digital humanities, and marketing. However, privacy regulations impose significant restrictions to both data collection and sharing. The CAMOUFLAGE project, funded by the AI4Media European project, aims to exploit diffusion model (such as Stable Diffusion) to produce a ...

Training deep neural networks require large scale annotated datasets which are often difficult to collect in the medical domain. As a consequence, a plethora of small and very specialized datasets have emerged. The medical domain would extremely benefit from more general purpose models that can be applied to a variety of problems. A possible strategy to overcome this issue is to leverage self-supervised techniques in which the network is pre-trained by using a pretext task. A simple example is rotation: the image is rotated and the network learns to detect the orientation; more generally, a pretext task can be any for which the labels are automatically generated. If the pre-training dataset is sufficiently large and varied, the features learnt should be sufficiently general to be useful for many downstream tasks. The network is then fine-tuned towards the final task (e.g., lesion detection or segmentation). The goal of this thesis, starting from an existing dataset generated in a previous work, is to systematically explore different self-supervised learning techniques, including generative components, and explore their relationship with the diagnostic/classification tasks. Secondly, we will explore ways to make the features learnt generalize better to different imaging modalities. Strong programming and analytical skills are required, as well as a solid background in machine learning/deep learning.

Suggested readings:
https://arxiv.org/abs/1908.06912
https://arxiv.org/abs/1912.01991

Training deep neural networks require large scale annotated datasets which are often difficult to collect in the medical domain. As a consequence, a plethora of small and very specialized datasets have emerged. The medical domain would extremely benefit from more general purpose models that can be applied to a variety of problems. A possible strategy to overcome this issue is to leverage self-supervised ...

The objective of this thesis is to investigate the integration of InSAR (Interferometric Synthetic Aperture Radar) and GNSS (Global Navigation Satellite System) data for landslide monitoring by exploiting deep learning models. Multiple thesis are available in the context of a project funded by NODES (Nord Ovest Digitale e Sostenibile). The thesis will in cooperation with the GRAINS (Prof. Lia Morra) and VANDAL groups (Prof. Tatiana Tommasi), with AIZOON Technology Consulting and with Geomatics Research & Development srl. InSAR is a remote sensing modality for the analysis of radar images captured by satellites equipped with Synthetic Aperture Radar. The radar antenna continuously transmits microwaves toward the Earth’s surface and captures the waves reflected back to the antenna position. By measuring both the amplitude and phase of the backscattered electromagnetic waves it is possible to assess the magnitude and location of ground movements. On the other hand, GNSS receivers on the ground collect information from a constellation of satellites to determine location. By exploiting ad-hoc engineered stations, it is possible to monitor small ground displacements and deformations at selected points. While InSAR provides information over a large area with spatial continuity but temporal discontinuity based on satellite overpasses, GNSS offers measurements with temporal continuity but only at limited spatial positions. The combination of these cues can be formalized as a weakly supervised semantic segmentation problem, where GNSS information is interpreted as sparse ground truth annotations for InSAR data. Following an initial phase dedicated to literature review and data organization, the main focus of this thesis will be developing a deep learning model that given an InSAR map and a few annotated GNSS points, will produce as output complete map annotations. Prerequisites: The successful candidate should be strongly motivated and is expected to have good knowledge of Python programming and PyTorch deep learning framework.

The objective of this thesis is to investigate the integration of InSAR (Interferometric Synthetic Aperture Radar) and GNSS (Global Navigation Satellite System) data for landslide monitoring by exploiting deep learning models. Multiple thesis are available in the context of a project funded by NODES (Nord Ovest Digitale e Sostenibile). The thesis will in cooperation with the GRAINS (Prof. Lia Morra) and ...

While current generative text-to-image latent diffusion models have reached unprecedented results in terms of visual fidelity, there are still open issues to be addressed in exerting precise control over the generated images. Generative models have difficulty in creating correct images when the textual prompt contains many details and often with object placement and spatial awareness. Recent text-to-image latent diffusion models have shown substantial improvements in prompt following, yet still struggle with the use of words such as “left” or “behind”. One possible reason lies in the inherent limitations of the text embedding employed to condition the generation process, that fails to learn sufficiently detailed and disentangled representation. This research project aims to overcome limitations in current generative text-to-image models by exploiting more structured representations for conditioning the image generation process. After an analysis of the state of the art on text-to-image synthesis, the candidate will: i) define a benchmark by indentifying a suitable dataset of challenging prompts, biased outputs and failures will be created by extensively reviewing open and closed source system, as well as the relevant literature; ii) investigate new architectures that richer, more structured representations, such as scene graphs, as an intermediate step to disambiguate textual prompts, incorporate greater spatial awareness and increase control in image composition. Skills possessed or to be acquired: Generative models, latent diffusion models; strong analytical skills and general interest in research-oriented projects.

While current generative text-to-image latent diffusion models have reached unprecedented results in terms of visual fidelity, there are still open issues to be addressed in exerting precise control over the generated images. Generative models have difficulty in creating correct images when the textual prompt contains many details and often with object placement and spatial awareness. Recent text-to-image ...

Context: Social media platforms have a profound impact on the way individuals choose to (re)present themselves in the digital era. Through the analysis of visual big data, we seek to understand how face representations have changed over time. Within the context of the FACETS (Face Aesthetics in Contemporary E-Technological Societies) project, we have collected user profile images from Facebook and Instagram. We are also developing, in collaboration with the Department of Philosophy at Università di Torino, visual big data analytics tools through computational image analysis and deep learning techniques that borrow from other disciplines, such as socio-semiotics and visual semiotics. A computational pipeline, FRESCO, has already been developed to extract semantic characteristics (composition, content, etc.) from images.

Open research questions to be tackled in one or more research thesis include:
- Design and extend the existing computational pipeline with new tools and techniques to extract semantic characteristics from images (composition, content, etc.)
- Develop a user-friendly analytics pipeline to apply the FRESCO pipeline to image collections to extract information about culturally relevant aspects (e.g., how does gender affect the kind of images we publish on social media? how do self-representation change over time?) and for applications in specific domains (e.g., marketing)
- Adapt the proposed pipeline to the analysis of other types of images (advertisement, meme, artworks, AI-generated images, …). Particularly relevant is the use of the proposed pipeline to detect and quantify biases in AI-generated images
- Design, train and evaluate deep neural networks that mimic high-level semantic analysis (which emotions are solicited by a given image? Which values are expressed? )
- Investigate the applicability of Multi-modal Large Language Model (LLM) such as Gemini to extract high-level interpretation from images and reproduce the type of in-depth analysis performed by experts, such as semioticians

Prerequisites: good knowledge of big data analytics, computer vision and deep learning frameworks, and a willingness to engage in multi-disciplinary research

Context: Social media platforms have a profound impact on the way individuals choose to (re)present themselves in the digital era. Through the analysis of visual big data, we seek to understand how face representations have changed over time. Within the context of the FACETS (Face Aesthetics in Contemporary E-Technological Societies) project, we have collected user profile images from Facebook and Instagram. We ...

Image interpretation tasks, such as object detection and visual relationship detection, may benefit from neural-symbolic integration in order to inject prior knowledge, e.g., from knowledge graphs, about objects and their relationship into the training objectives of deep neural networks. The goal of this project is to design deep architectures combining convolutional neural networks and trasformers with neural-symbolic components such as Logic Tensor Networks to solve various image interpretation tasks, such as object detection, image classification or visual relationship detection. Multiple thesis are available to tackle the following open issues: i) how to integrate the knowledge into the training process of high-level semantic interpretation (scene graph generation); ii) how to automatically extract and compile prior knowledge from existing sources and format it for appropriate ingestion; iii) how to use Large Language Models (ChatGPT) to extract prior knowledge and logical constraints; iv) how to characterize neural-symbolic architectures, e.g. in terms of types of features learnt, efficiency and interpretability; v) how to combine concept extraction with knowledge induction to close the neuro-symbolic cycle, and how to simplify knowledge acquisition through human-in-the-loop appraoches

Prerequisites: programming skills (Python, Pytorch or other deep learning framework); good analytical and mathematical skills. Prior knowledge of neuro-symbolic techniques is not required – essential material to study on the topic will be provided. The candidate we are looking for is highly motivated and interested towards research-oriented activities.

Image interpretation tasks, such as object detection and visual relationship detection, may benefit from neural-symbolic integration in order to inject prior knowledge, e.g., from knowledge graphs, about objects and their relationship into the training objectives of deep neural networks. The goal of this project is to design deep architectures combining convolutional neural networks and trasformers with ...

Deep neural networks have shown remarkable performance in the interpretation of medical images. However, they require large datasets for training, and performance may degrade when training on imbalanced datasets. Doctors are typically trained through examples, as well as through structured taxonomies that present prototypical examples of visual features associated with benign and malignant lesions. The goal of the thesis is to design neuro-symbolic architectures, such as Logic Tensor Networks, that can incorporate such constraints during training. Experiments are foreseen on mammography and possibly other medical imaging modalities. Thesis activities include design and comparison of different neuro-symbolic techniques, starting from patch-level classification and moving on towards image-level analysis. Issues to be tackled include how to align visual features computed by the network to human-interpretable concepts and how to encode the constraints in the loss. Evaluation will be performed in terms of performance, robustness, explainability and alignment with human asssessment. Prerequisites: programming skills (Python, Pytorch or other deep learning framework); good analytical and mathematical skills. Prior knowledge of neuro-symbolic techniques is not required – essential material to study on the topic will be provided. The candidate we are looking for is highly motivated and interested towards research-oriented activities.

Deep neural networks have shown remarkable performance in the interpretation of medical images. However, they require large datasets for training, and performance may degrade when training on imbalanced datasets. Doctors are typically trained through examples, as well as through structured taxonomies that present prototypical examples of visual features associated with benign and malignant lesions. The goal of ...

While state-of-the-art deep learning typically uses distributed representations, reasoning is normally useful at a higher level of abstraction. As a result, attempts at combining symbolic AI and neural computation into neural-symbolic systems have been on the increase. Neural-symbolic learning and reasoning is an area of research that aims at integrating relational/symbolic reasoning and knowledge representation (e.g., first order logic language for knowledge representation) by embedding their constructs in deep neural networks. NeSy techniques can be used to solve tasks such as Visual Sudoku Puzzle classification, whose goal is to automatically check the validity of handwritten solutions for Sudoku. The system must learn to distinguish digit by satisfying the rules of Sudoku, without providing any digit label. However, NeSy techniques like LTNs introduce many additional design choices, such as: How to define axiomatic prior knowledge (“how to encode the rules of Sudoku”?); How to ground predicates and connectives? How to choose between different frameworks? Comparison about existing frameworks is limited in literature, and issues in reporting, hyper-parameter selections, etc. affect this comparison. The goal of this thesis is to experimentally and extensively investigate the effect of different design choices on the task of visual Sudoku puzzle classification, from the formulation of the constraints to the hyper-parameter settings, on Logic Tensor Networks designed for this task. In addition, LTNs will be compared against other neuro-symbolic frameworks (such as NeuPSL) and standard deep learning baselines (such as visual transformers and relational networks).

Reading list:
Morra, Lia, et al. "Designing Logic Tensor Networks for Visual Sudoku puzzle classification." 17th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy 2023). CEUR, 2023.
https://www.cs.ox.ac.uk/isg/conferences/tmp-proceedings/NeSy2023/paper19.pdf

Prerequisites: programming skills (Python, Pytorch or other deep learning framework); good analytical and mathematical skills. Prior knowledge of neuro-symbolic techniques is not required – essential material to study on the topic will be provided, as well as an initial implementation. The candidate we are looking for is highly motivated and interested towards research-oriented activities.

While state-of-the-art deep learning typically uses distributed representations, reasoning is normally useful at a higher level of abstraction. As a result, attempts at combining symbolic AI and neural computation into neural-symbolic systems have been on the increase. Neural-symbolic learning and reasoning is an area of research that aims at integrating relational/symbolic reasoning and knowledge ...

Artificial Intelligence agents are required to learn from their surroundings and to reason about the knowledge that has been learned in order to make decisions. While state-of-the-art deep learning typically uses distributed representations, reasoning is normally useful at a higher level of abstraction. As a result, attempts at combining symbolic AI and neural computation into neural-symbolic systems have been on the increase. Neural-symbolic learning and reasoning is an area of research that aims at integrating relational/symbolic reasoning and knowledge representation (e.g., first order logic language for knowledge representation) by embedding their constructs in deep neural networks. The goal of this project is to automate the process of designing, implementing and setting the hyper-parameters of neuro-symbolic systems. In fact, NeSy techniques like LTNs introduce many additional design choices and hyper-parameters, such as: i) how to define constraints, which to include, in which order and how to weight them; ii) how to redefine the neuro-symbolic loss, which functions to use and how to parameterize them; iii) how to deal with common dataset issues such as class imbalance and dataset bias; iv) how to prevent NeSy losses to promote unwanted behaviors, such as reasoning shortcuts.

Several thesis are available on tackling these issues. Depending on the candidate background and predisposition, the problem can be tackled either from a more theoretical or experimental standpoint. Starting from an analysis of the current literature, techniques to be investigated include: i) Analysis of the mathematical and numerical properties of different frameworks; ii) Comparison with other frameworks and losses; iii) application of techniques from the fields of hyper-parameter optimization (Random search, Bayesian Optimization), Neural Architectural Search (NAS), genetic algorithms and curriculum learning. Experiments will be conducted on standard benchmarks as well as applications on semantic image interpretation explored by the group.

Prerequisites: programming skills (Python, Pytorch or other deep learning framework); good analytical skills. Prior knowledge of neuro-symbolic techniques is not required – essential material to study on the topic will be provided. The candidate we are looking for is highly motivated and interested towards research-oriented activities.

Artificial Intelligence agents are required to learn from their surroundings and to reason about the knowledge that has been learned in order to make decisions. While state-of-the-art deep learning typically uses distributed representations, reasoning is normally useful at a higher level of abstraction. As a result, attempts at combining symbolic AI and neural computation into neural-symbolic systems have been ...

The thesis aims at designing and developing a tool for the analysis of smart contracts deployed on existing blockchain platforms. The objective of the tool is to support the user in the identification of smart contracts' main characteristics (e.g., in terms of application field, type, tasks performed, interactions with other smart contracts, etc.), by also exploiting visualization techniques. The thesis student will also investigate the added value of search engines for smart contracts, and will enrich the developed tool with an "intelligent" search feature, e.g., based on semantic technologies.

The thesis aims at designing and developing a tool for the analysis of smart contracts deployed on existing blockchain platforms. The objective of the tool is to support the user in the identification of smart contracts' main characteristics (e.g., in terms of application field, type, tasks performed, interactions with other smart contracts, etc.), by also exploiting visualization techniques. The thesis student ...

The adoption of electric vehicles (EVs) is increasing, and the demand for electric vehicle recharging infrastructure is growing. To ensure the efficient operation of this infrastructure, new tools are needed to simulate, test, and optimize different charging strategies. In this thesis proposal, we propose the design and implementation of a blockchain-based simulation tool for electric vehicle recharging infrastructure that can:
- provide an immutable and decentralized record of all charging transactions and other relevant data;
- exploit different consensus mechanism to model, simulate, and test different charging strategies for electric vehicle recharging infrastructure.

In the first part of the thesis the student will be asked to develop a blockchain oracle represented by the porting in Python of an existing MATLAB model.

In the second part, the student will design and develop the blockchain platform based on an Ethereum-like (e.g., Quorum, Polygon) or an Hyperledger (e.g., Fabric, Besu) blockchain.

In the final phase the oracle will be connected to the blockchain platform to test and validate the integrated simulation tool.

The methodology for this thesis will include both theoretical and practical research. The theoretical research will involve a thorough analysis of existing blockchain consensus and their limitations, as well as a study of dynamic models and external oracles. The practical research will involve the design, implementation and testing of the simulation tool composed by the external oracle and the blockchain platform, as well as the evaluation of its performance and security. The thesis will be developed in collaboration with LINKS Foundation.

The adoption of electric vehicles (EVs) is increasing, and the demand for electric vehicle recharging infrastructure is growing. To ensure the efficient operation of this infrastructure, new tools are needed to simulate, test, and optimize different charging strategies. In this thesis proposal, we propose the design and implementation of a blockchain-based simulation tool for electric vehicle recharging ...

Self-Sovereign Identity is a new digital identity model that empowers individuals to control their identity without relying on centralized authorities. SSI enables the creation, management, and verification of digital identities that are self-owned, portable, and interoperable. In the context of an energy data marketplace, SSI can potentially enable secure and efficient sharing of energy data while giving individuals control over their data.

This thesis aims to explore the concept of Self-Sovereign Identity (SSI) and its potential integration within an energy data marketplace. The purpose of the research is to analyze the algorithms used to enable the methodology of SSI, and investigate the implications of adopting SSI in an energy data marketplace. This research aims to contribute to the body of knowledge on the use of SSI in various applications and provide a practical demonstration of its implementation in an energy data marketplace.

In particular, the research will begin with a comprehensive review of the literature on SSI and its algorithms and will examine its applicability to an energy data marketplace. The study will investigate the technical and social implications of SSI integration in the marketplace and identify potential benefits and limitations.

The research will then proceed to identify the most suitable SSI algorithms for the energy data marketplace and investigate the feasibility of implementing them.

The thesis will be developed in collaboration with LINKS Foundation.

Self-Sovereign Identity is a new digital identity model that empowers individuals to control their identity without relying on centralized authorities. SSI enables the creation, management, and verification of digital identities that are self-owned, portable, and interoperable. In the context of an energy data marketplace, SSI can potentially enable secure and efficient sharing of energy data while giving ...

Industrial product tracking is a critical aspect of supply chain management that ensures the integrity, traceability, and security of products as they move through the supply chain. Blockchain technology has the potential to revolutionize industrial product tracking by providing a tamper-proof and decentralized system for data storage and traceability. However, with various blockchain platforms available, it is important to evaluate the suitability of each platform for industrial product tracking based on both technical and business aspects.

This thesis aims to conduct a benchmarking of blockchain platforms for the traceability of a specific industrial prototyping process using a SWAT (Strengths, Weaknesses, Opportunities, Threats) analysis considering relevant technical and business aspects (e.g., as cost alignment, sustainability, scalability, longevity, integration, regulatory compliance, and access to blockchain development skill) and demonstrating the advantages of a blockchain-based solution for industrial production traceability through the development of a proof-of-concept.

The specific objectives if the thesis work include:
- Research and analyze existing blockchain platforms for industrial product tracking
- Conduct a SWAT analysis of the blockchain platforms considering relevant technical and business aspects
- Evaluate the suitability of each blockchain platform for industrial product tracking based on the results of the SWAT analysis
- Provide recommendations for the most suitable blockchain platform for industrial product tracking based on the findings.
- Implement a proof-of-concept using one of the selected platform to demonstrate the effectiveness of a blockchain-based approach to for industrial production traceability.

The expected results of this thesis include a comprehensive benchmarking of blockchain platforms that will provide insight into the suitability of each blockchain platform for industrial product tracking and recommendations for the most suitable blockchain platform based on the findings, together with an actual implementation of a blockchain-based solution to demonstrate the feasibility of the proposed solution.

The thesis will be developed in collaboration with LINKS Foundation.

Industrial product tracking is a critical aspect of supply chain management that ensures the integrity, traceability, and security of products as they move through the supply chain. Blockchain technology has the potential to revolutionize industrial product tracking by providing a tamper-proof and decentralized system for data storage and traceability. However, with various blockchain platforms available, it is ...