Extended Reality

The rapid population growth and urbanization trends pose challenges in creating livable spaces for the growing global population. This research explores the integration of robotic furniture (RF), a type of architectural robotics (AR) into buildings to address this issue. By utilizing virtual reality (VR) technology, the study aims to understand how people respond to RF in comparison to traditional architectural walkthroughs and how RF affects their acceptance. The problem that needs to be solved with this VR platform is to overcome the limitations of traditional design and evaluation methods in architecture and interior design of RF. A working prototype of a virtual world is developed with different RF such as beds, walls, desks, and different RF configurations. A survey is created to assess user perceptions of RF in buildings, this survey focuses on user engagement, interaction, customization, immersion, and satisfaction using a Likert scale rating system. The findings highlight the high level of engagement and immersion experienced by users, as well as the significance of customization and exploration of different apartment configurations. Users expressed satisfaction and enjoyment with the VR experience, emphasizing the potential applications of RF in real-world scenarios. An ANOVA statistical analysis was made to evaluate the differences between participants with prior VR experience and no prior experience, showing that the users with prior VR experience valued the VR platform more and praised the use of RF in the design processes.

Ensuring the resilience of deep learning algorithms to data changes, especially in outdoor scenarios with dynamic weather conditions, poses challenges due to limited training data captured in short periods. Weather variations like rain, snow, and fog can introduce concept drift, significantly impacting model accuracy. Expanding datasets with diverse temporal variations is often impractical due to time and cost constraints. Alternatively, we propose an easily deployable and scalable approach to augment weather changes, leveraging the Unity game engine for synthetic image generation. Our method swiftly produces large amounts of augmented videos and images, requires off-the-shelf models only for pre-processing, and allows flexible combinations of effects to simulate various weather conditions. We introduce Weathervenue, an augmented subset of the CUHK Avenue dataset, and employ it in testing four anomaly detection models and models for object detection, semantic segmentation, and depth estimation. Results demonstrate performance degradation ranging from 10% to 35% across all anomaly detectors and visibly worse results for other methods, underscoring the necessity of our solution for creating more challenging scenarios and training robust models. We also show that training on a combination of real and augmented data can boost performance on rain, snow, and fog testing data by up to 10%, while only minimally affecting clear results. Link to the code and augmented dataset https://github.com/IvanNik17/DigiWeather .

Extended Reality (XR) technologies, including Virtual Reality (VR) and Augmented Reality (AR), offer immersive experiences merging digital content with the real world. Achieving precise spatial tracking over large areas is a critical challenge in XR development. This paper addresses the drift issue, caused by small errors accumulating over time leading to a discrepancy between the real and virtual worlds. Tackling this issue is crucial for co-located XR experiences where virtual and physical elements interact seamlessly. Building upon the locally accurate spatial anchors, we propose a solution that extends this accuracy to larger areas by exploiting an external, drift-corrected tracking method as a ground truth. During the preparation stage, anchors are placed inside the headset and inside the external tracking method simultaneously, yielding 3D-3D correspondences. Both anchor clouds, and thus tracking methods, are aligned using a suitable cloud registration method during the operational stage. Our method enhances user comfort and mobility by leveraging the headset’s built-in tracking capabilities during the operational stage, allowing standalone functionality. Additionally, this method can be used with any XR headset that supports spatial anchors and with any drift-free external tracking method. Empirical evaluation demonstrates the system’s effectiveness in aligning virtual content with the real world and expanding the accurate tracking area. In addition, the alignment is evaluated by comparing the camera poses of both tracking methods. This approach may benefit a wide range of industries and applications, including manufacturing and construction, education, and entertainment.

Motion capture (MoCap) is a technology that records movement and turn it into 3D data. It can capture even the subtlest of movements, making animations look more natural and helping animators through reducing the time required to achieve a result. With the construction of 3D scenes in Virtual Reality, it might be possible to shorten even more the time needed to successfully achieve good animations resulting from MoCap. This paper explores what concerns VR development of 3D environments suitable for the use of real-time motion capture. The research is justified by the way it intends to enable future research in reducing the recording time per scene, thus through the usage of pre-recorded performances in the MoCap system software to simulate this aspect of the workflow. The goal here is to take precautions to avoid potential performance issues within the virtual environment being displayed in the HMD especially considering the ergonomics issue presented in the procedures of this research. Also, using a specific set of hardware and systems that were available for test, and that might differentiate between research labs, makes it harder to propose global solutions in a formal format to ensure accuracy and consistency for this field of research. Therefore, as a final suggestion, it would be beneficial to investigate the development of a standardized approach or methodology for the real-time use of Virtual Reality with Motion Capture. Currently, the are no commonly accepted procedures or methods for this area of study among academics.

The X-SITE CAVE at Freiberg University is an immersive VR platform for interactive scientific visualization. Main features include its tiled-display design yielding a very high visual resolution and its small spatial footprint. Since its initial setup in 2008, the system has been under continuous development and modernization. An important aspect is the evolution from a rather expensive and partially proprietary platform to a cost-efficient and open-source driven system. High- and medium cost components like commercial calibration software and the initial set of projectors were gradually replaced by open-source software, in-house developments and off-the-shelf hardware. An overview of the history and the massive changes over time is provided with special focus on more recent developments including hardware upgrades, calibration improvements and integration of modern rendering software. A novelty, to the best of our knowledge, is the integration of the open-source game engine Godot into a CAVE.

The increasing use of Extended Reality (XR) brings a need for more advanced Human-Computer Interaction (HCI) technologies to allow for intuitive and robust collaboration. However, challenges arise when also ensuring interactions are both natural and effective, particularly when incorporating flexible verbal communication. Prior research has explored many multi-modal interaction technologies, yet there exists a need for a framework to allow for human-computer communication in specifically XR applications. This work proposes a novel framework that can incorporate advanced means of Natural Language Processing (NLP) to handle flexible verbal communication while ensuring computer interpretation is robust. Drawing from prior research that identified limitations of information given in XR visuals and challenges in using widely available NLP tools, the proposed framework uses a rule-enforced command extraction pipeline to ensure consistent human-like processing, while preserving the flexibility of more open-domain verbal dialogue. The design employs a sequence of NLP techniques for spoken utterance analysis, language specific rules to extract usable game commands, and verification on the structured command with a user-reinforced hyper-graph method of data storage. The framework and its processing pipeline was evaluated using a wide-range of human-like phrasings of commands deemed representative of verbalized instructions for human-computer collaboration in an XR context. Framework performance was then compared against a Large Language Model (LLM) that was customized to extract commands using the same rules. These results serve to showcase the potential of the proposed framework through demonstrated examples and early results while also noting areas of needed performance enhancements.

This paper addresses the underutilization of Virtual Reality (VR) in education, focusing on its application in explaining complex blockchain concepts, specifically the Proof-of-Work (PoW) algorithm. The study presents a VR learning module designed to elucidate the PoW algorithm using the Bitcoin blockchain as a case study. The research adopts a Design Science Research (DSR) approach, emphasizing the development of artifacts like software for educational purposes.The VR learning unit comprises distinct phases, including VR control system introduction, transaction generation, immersion in the blockchain world, PoW algorithm simulation, and transaction verification. Results from a field experiment with 18 business informatics students show positive correlations between user experience, immersion, and learning effectiveness. The findings contribute valuable insights for future research and the development of VR-based educational tools, emphasizing the potential of immersive technologies in enhancing knowledge transfer.

This research focuses on the prototyping of 3D content through the placement of primitives using six degrees of freedom (6DOF) in augmented reality (AR) applications compared to desktop-based 3D modelling software. We examine the usability of these methodologies within the context of pervasive augmented reality environments and assess the impact of generational differences, focusing specifically on Generation Z compared to previous generations. Additionally, we have analysed how having prior knowledge of 3D modelling software affects these processes. Our findings highlight distinctions in workflow efficiencies, user motivations and interaction paradigms, providing insights into the evolving landscape of digital content creation across various platforms.

In this paper, we present a novel application of Neural Style Transfer (NST) for converting procedurally generated orthophoto landscape images into highly realistic representations. Traditionally used to apply artistic styles to images, we adapt NST to transfer the photorealistic qualities of real aerial orthophoto images to synthetic terrain images. This enables the creation of realistic visuals from generated landscapes, addressing the common issues of stylization, abstraction, and inaccuracy in synthetic imagery. Our approach involves upgrading and modifying existing NST techniques and their comparison. The evaluation demonstrates that our methods produce more convincing and realistic results than general generative models. These findings highlight the potential of NST in enhancing the realism of computer-generated landscapes, with possible applications in urban planning, environmental simulations, video games, and the film industry.

Virtual environments enable trainees to develop their skills in diverse tasks, independent of time and location. In the construction sector, virtual environments are primarily utilized for safety training, while there are fewer implemented applications for hands-on construction tasks. This publication presents a platform-independent virtual environment for waterproofing training to address the issue. The presented virtual environment is a cross-platform application enabling multi-user training experience. A pilot was organized to collect feedback on the usability of the implemented virtual waterproofing environment. Results of the user questionnaire are presented and discussed to evaluate the usability and provide insights into the challenges and benefits of virtual training environments for hands-on training in the construction sector. In conclusion, the results highlight the potential of the developed virtual environment for waterproofing training.

In traditional design, the foundational material expresses three-dimensional concepts, blending artisanal skills, visual perception, and cognitive processes. Modern computer-aided design shifts this process to digital manipulation, increasing efficiency but reducing the connection between sensory experiences. Recent advancements in immersive technologies rapidly progress interaction methodologies. Real-time systems, with features like gesture recognition, enable customized sensory perception and communication in the design process. Importantly, these technologies seamlessly integrate digital models into the tangible world through Mixed Reality (MR) technology and inter-sensory connections while simplifying the modelling process. In the current project, the utilization of digital twins emerges as a strategic approach, orchestrating a harmonious fusion of visual and tactile senses. The paper crafting processing methodology was analysed using it as a foundational reference, while concurrently simplifying the user gesture and modelling system. Utilizing three motion-driven sensors to simulate movements during the paper folding process, an operational platform integrating immersive technology was developed. This platform enables users to model intricate cylindrical structures, thereby illustrating the feasibility of achieving architectural modelling with potential applications in participatory design and smart building technologies construction.

This paper develops a Temporal Control Augmented Reality Interaction Player (TCAIP) based on Microsoft Kinect, aiming to enhance the interactive experience of children in history and science education. The primary objective is to allow users to control the playback speed, direction, and scale of educational content in real time through simple gestures, thereby facilitating an intuitive exploration of complex scientific phenomena or historical images spanning large time periods. The experiment involved 15 participants aged 7 to 17, who interacted with the system in a controlled environment. The findings indicate that the TCAIP system significantly improves memory retention and understanding of scientific concepts among the participants. User feedback highlighted the system’s ease of use and its potential for widespread application in educational settings. This research demonstrates the efficacy of interactive technology in improving learning outcomes and provides valuable insights for the future development of educational technologies.

Molecular dynamics (MD) simulations provide crucial insight into molecular interactions and biomolecular function. With interactive MD simulations in VR (iMD-VR), chemists can now interact with these molecular simulations in real-time. Our sense of touch is essential for exploring the properties of physical objects, but recreating this sensory experience for virtual objects poses challenges. Furthermore, employing haptics in the context of molecular simulation is especially difficult since we do not know what molecules actually feel like. In this paper, we build upon previous work that demonstrated how VR-users can distinguish properties of molecules without haptic feedback. We present the results of a gamified two-alternative forced choice (2AFC) psychophysics user study in which we quantify the threshold at which iMD-VR users can differentiate the stiffness of molecular bonds. Our preliminary analysis suggests that participants can sense differences between buckminsterfullerene molecules with different bond stiffness parameters and that this limit may fall within the chemically relevant range. Our results highlight how iMD-VR may facilitate a more embodied way of exploring complex and dynamic molecular systems, enabling chemists to sense the properties of molecules purely by interacting with them in VR.

Virtual reality (VR) technology is rapidly advancing, necessitating the development of functional, secure, reliable, and user-friendly VR systems. However, the empirical data on the importance of quality attributes in VR system design and development is limited. Using an online descriptive survey by engaging a geographically diverse participant pool of 188 respondents, the study captures a comprehensive demographic and offers insights into the role-specific evaluation of quality attributes. The survey findings reveal that a substantial majority (93.6%) deem quality attributes equally or more important than functionality in VR system development. Usability and performance are identified as the most significant attributes, with 22.5% and 21.9% of respondents ranking them as critical to VR system efficacy and user acceptance, respectively. The participant’s consideration of usability and performance as important quality attributes in virtual reality (VR) system design aligns with the field’s growing consensus on their crucial roles. Despite the clear prioritization of usability and performance, the study acknowledges the importance of flexibility, security, and reusability, which, while not ranked as highly, remain integral to the comprehensive design and operation of VR systems.

Although procedural generation (PG) has revolutionized the way designers create virtual environments (VEs), its potential to enable controlled variation in VR user studies is rarely seen. However, PG could improve the generalisability of VR experiments and reduce the influence of biases that individual designers might introduce to VEs. Nevertheless, the algorithmic generation of VEs poses a potential risk for inducing breaks in presence (BIPs). This study investigated the impact of different shadow settings within both procedurally generated and manually designed VEs. In the PG condition a unique VE was generated for each subject ( $$n=41$$ n = 41 ). In the control condition only one VE was used, which was built manually based on the same rules as the PG VEs. Results show that PG did not significantly affect quantitative presence ratings or lead to more breaks in presence. However, the current state of the PG used seems to increase the probability of presence scores violating normal distribution, thus there is potential for optimization to achieve more controlled variations in VEs. Nonetheless, the current PG algorithm already offers advantages in terms of time-efficiency and experimental flexibility, when compared to handmade VEs, reducing reliance on specific environmental layouts. These findings contribute to the understanding of the impact of PG on presence in VR experiments and highlight the need for further investigation into the design and implementation of PG techniques for creating VEs that effectively elicit presence.

Virtual reality applications are extensively used in the space exploration domain to support different tasks that vary from astronaut training to mission planning, to system design and engineering. A key role is played by the interactive visualization of scientifically-accurate data related to outer space elements, such as, among others, stars, galaxies and planets. In the current work, we propose a method for the 3D visualization of data related to terrain surfaces of different celestial bodies, and the integration of the terrain models into a space-exploration virtual reality application. In particular, we provide insights into the pipeline we used to import and process the terrain data, coming in the form of Digital Elevation Models, and the techniques to visualize and geo-reference them inside the application. The proposed methodology showed accuracy in the visual outcome of the reconstructed surfaces, as well as positive results in terms of software performance of the real-time application.

Since the beginning of Islam, the Quran has held a central role in education. Quranic education is a cornerstone in shaping Muslims’ lives from childhood. Central to Quranic education is the teaching the interpretation of the Quran (explanation of the Quran), which facilitates a deep understanding of the Quran’s meaning and principles. Teachers have long utilized traditional methods to embed Quranic education effectively. However, there are several challenges in engaging and motivating today’s children during the learning process in class, thereby affecting their understanding and values. In the technology era, there is an interest in integrating emerging educational tools into Islamic education, such as multimedia and extended reality (XR), including virtual and augmented reality. In contrast to the application of XR technologies in STEM and STEAM subjects, only a handful of studies have used them to teach theological subjects such as the Quran. This research investigates the impact of virtual reality technology on teaching the Quran to Muslim children.

In this research and innovation work, we propose an open and interoperable approach for exploiting the various building data collected across the different phases of a building’s life cycle via a BIM-based Mixed Reality (MR) platform. Building information modelling (BIM) has gradually gained attention in recent decades and is widely considered a key to digitising and optimising the building life cycle. Yet, there are significant challenges in the standardization of methodologies, interoperability of solutions, and data exchange, as well as the usability of BIM-related solutions. Moreover, modern or renovated buildings produce extensive real-time data on top of the static data organised in BIM, and it is commonly accepted that most professionals in the field do not have access to the critical static or dynamic data that accompany a building project. Here, we exploit MR as an advanced user interface for enhanced interaction with building static and dynamic data instantiated by a BIM model, while we address a seamless conversion of BIM data to an online visual digital twin that supports the MR mobile application.

Maturity evaluation of Building Information Modeling (BIM)-based Augmented Reality (AR) and Virtual Reality (VR) systems is still in its early phase. However, assessing the maturity of these systems is crucial to ensure they meet industry standards and are effectively implemented. This study builds upon our previously published research, which introduced an innovative approach for evaluating the maturity of BIM-based AR/VR systems in the Architecture, Engineering, and Construction (AEC) industry. This approach aligns with the ISO/IEC 15939 standard, which emphasizes the critical role of indicators—a key concept we have incorporated into our work. In this paper, we present a general overview of this approach along with its associated measurement model. We delve deeper into the specification of these indicators through an exhaustive bibliographic analysis aimed at acquiring the necessary data. Subsequently, we introduce a detailed data processing procedure tailored to meet the requirements of this approach and address the unique needs of BIM-based AR/VR applications in the AEC sector.

The use of Virtual Reality (VR) technology in industrial training is rapidly advancing due to its immersive and interactive capabilities. This article presents a detailed exploration of a semantic VR system specifically designed to train factory staff. The purpose of this article is to address the significant problem of the inefficiency and limitations of traditional training methods. Existing approaches often fail to provide the necessary hands-on experience and adaptability required for effective training. Our main contribution is the development of a gesture-based semantic VR training system and an innovative method for creating training scenarios. The core of the article delves into the system’s architecture, highlighting key features such as hand tracking and the ability to edit scenarios using domain knowledge, allowing non-technical personnel to participate in the development process. The system is built using the Unity game engine, emphasizing the importance of clear semantic naming conventions and adherence to expert guidelines in scenario design. The results demonstrate the system’s cost-effectiveness and safety benefits. The article concludes with a discussion on future work possibilities, including the integration of AI to enhance system adaptability and effectiveness.

This research introduces an object management system for virtual reality (VR) that creates and manages 3D objects in real time by utilizing artificial intelligence (AI) approaches. The technology combines pre-existing pictures and 3D AI generators to enable real-time creation and customization of virtual items. Users can interact with the system through intuitive gesture-based and voice-controlled interfaces, allowing seamless object creation, manipulation, and placement. The system incorporates an evaluation and analytics module that collects user interaction data to analyze performance metrics and user behavior, providing insights for optimization and user experience enhancement implemented and evaluated within a Unity-based VR environment. This research contributes to the field of virtual reality by introducing an innovative approach to object management, leveraging AI techniques for efficient 3D model generation and intelligent object placement. Also, the work proposes a literature review in the study’s direction. The implementation process is described along with the limitations of this research work.

The article introduces the VR framework and the preliminary outcomes of the ongoing European TRACENET project, an interdisciplinary and collaborative initiative to support and enhance Civil Protection training activities through 3D geospatial data and VR solutions. The VR framework is a virtual and collaborative multi-player environment for manifold and diverse hazard simulations which allows remote users to see the outcomes of their intervention decisions. The VR framework is a complementary solution to traditional training activities, enabling cost reduction of full-scale on-site exercises - included in so-called EU MODEX activities. The framework is based on the Unreal rendering engine and is primarily dedicated to situation assessment, intervention planning and decision making.

This exploratory paper seeks to combine findings from toy research with studies on digital object play with an interest in the toyification of the virtual realm, including VR, AR, and XR. The goal of the paper is to formulate ideas on the toyfulness of virtual objects and related toy experiences in virtual space and to give a definition of Virtual Toys. By giving examples of current VToys and speculating on the properties of VToys in the future, we participate in envisioning a post-digital play world, where questions related, for example, to the longevity and obsolescence of playthings, receive new meanings.

Augmented Reality (AR) technology has revolutionized how users interact with digital content in real-world environments. However, ensuring the quality of AR experiences remains a complex challenge due to the diverse factors influencing user perception and satisfaction. To address this challenge, researchers and developers are turning to conceptual models that provide structured frameworks for evaluating and optimizing AR quality. This paper explores the development of such a conceptual model, aiming to define the scope, objectives, and metrics for assessing AR quality comprehensively. By considering components such as visual fidelity, interaction responsiveness, spatial alignment accuracy, and semantic coherence, the model seeks to provide a systematic approach to AR quality assessment. Additionally, factors such as hardware capabilities, software optimization, user interaction design, and environmental conditions are integrated into the model to capture their influence on AR quality. Despite promising advancements, challenges such as model simplicity, subjectivity in metrics, and validation remain. Through ongoing research and refinement, the proposed conceptual model aims to enhance AR development practices, foster innovation, and improve user satisfaction across diverse AR applications and environments.

The joint usage of Extended Reality (XR) and Artificial Intelligence (AI) has enabled different Metaverse-related use cases. Such paradigms were recently adopted for immersive content creation, particularly considering Neural Rendering (NR) techniques to project scenes from the real world in the 3D realm. These methods are particularly beneficial in the field of Cultural Heritage (CH), where digitizing and visualizing cultural assets in 3D is crucial. However, current evaluation protocols lack a robust integration of human judgments through a Human-In-The-Loop (HITL) approach to humanly evaluate the quality of the generated 3D models, which could also support model optimization. To bridge this gap, we here introduce X-NR, a novel XR framework designed to evaluate and compare 3D reconstruction methodologies, including NR in the context of CH. We contextualize and validate such a framework through case studies on cultural heritage sites in the Marche region (Italy), employing various data-capturing and 3D reconstruction methodologies. The study concludes with a validation of the framework by CH domain experts, underscoring its potential advantages over traditional 3D editing software.

The complexity behind the analysis of mobile learning activities has requested the development of specifically designed frameworks. When students are involved in mobile learning experiences, they interact with the context in which the activities occur, the content they have access to, with peers and their teachers. The wider adoption of generative artificial intelligence introduces new interactions that researchers have to look at when learning analytics techniques are applied to monitor learning patterns. The task interaction framework proposed in this paper explores how AI-based tools affect student-content and student-context interactions during mobile learning activities, thus focusing on the interplay of Learning Analytics and Artificial Intelligence advances in the educational domain. A use case scenario that explores the framework’s application in a real educational context is also presented. Finally, we describe the architectural design of an environment that leverages the task interaction framework to analyze enhanced mobile learning experiences in which structured content extracted from a Knowledge Graph is elaborated by a large language model to provide students with personalized content.

Cobots are robots designed to work with human operators in a shared workspace and on a shared task. Combining robots and human skills is one of the main advantages of human-robot collaboration (HRC) in industrial production. With the goal of moving toward an authentic collaboration, rather than a simple coexistence, cobots should be able to adapt to the physical and mental needs of the operator in a more natural and personalized way. Using neuroscientific measurements of human responses to HRC combined with artificial intelligence (AI) algorithms, cobots could be implemented with the ability to process and respond in real time to the psychophysiological state of the operator. Moreover, real-world scenarios must consider the presence of complex and multiple social interactions. In line with this perspective, the neuroscientific “hyperscanning” paradigm is particularly suited for the study of complex and naturalistic interactive dynamics and can be used to assess the neurophysiological activity of two or more agents interacting with each other, when a non-human agent, such as a cobot or an AI system, is introduced in the collaboration. This contribution describes a research project in early stages of development which aims to assess the effects of HRC and, more generally, of human factors, on operators’ mental and emotional state and to develop models of real-time adaptation of the cobot to the psychophysiological state of the operator.

The V.A.I.F.A.R.M. (Virtual and Artificial Intelligence for Farming and Agricultural Resource Management) app explores the integration of collaborative virtual reality (VR) with generative artificial intelligence (AI), specifically utilizing ChatGPT, to enhance educational approaches within agricultural management and planning. This study aims to investigate the educational outcomes associated with the combined use of VR and AI technologies, with a particular focus on their impact on critical thinking, problem-solving abilities, and collaborative learning among university students engaged in agricultural studies.By employing VR, the project creates a simulated agricultural environment where students are tasked with various management and planning activities, offering a practical application of theoretical knowledge. The addition of ChatGPT facilitates interactive, AI-mediated dialogues, challenging students to tackle complex agricultural problems through informed decision-making processes.The research anticipates findings that suggest an improvement in student engagement and a better grasp of complicated agricultural concepts, attributed to the immersive and interactive nature of the learning experience. Furthermore, it examines the role of VR and AI in cultivating essential soft skills critical for the agricultural sector. The study contributes to the understanding of how collaborative VR and generative AI can be effectively combined to advance educational practices in agriculture, aiming for a balanced evaluation of their potential benefits without overstating the outcomes.

This paper introduces “ARFood,” a groundbreaking augmented reality (AR) and artificial intelligence (AI) application tailored to revolutionize nutrition education for Generation Alpha. ARFood immerses users in a virtual supermarket shopping experience, guided by two AI characters: NutriBot, a hip-hop nutritionist robot, and CyberFlora, a new-age sustainability expert robot. These characters offer feedback on food choices based on nutritional value and environmental sustainability, promoting healthy and eco-conscious eating habits among middle school students. The application leverages the engaging potential of AR and the personalized interaction capabilities of AI to deliver scientifically accurate, age-appropriate educational content. This study examines the development, implementation, and preliminary impact of ARFood, highlighting its effectiveness in enhancing nutrition education and its potential as a model for future educational technologies. By bridging the gap between traditional education methods and the digital nativity of Generation Alpha, ARFood represents a significant step forward in adapting educational content to the preferences and needs of today’s youth.

Presenting before an audience presents challenges throughout preparation and delivery, necessitating tools to securely refine skills securely. Interviews mirror presentations, showcasing oneself to convey qualifications. Virtual environments offer safe spaces for trial and error, crucial for iterative practice without emotional distress. This research proposes a Virtual Reality-Based Dynamic Pitch Simulation with Integrated Generative AI to effectively enhance presentation skills. The simulation converts spoken words to text, then uses AI to generate relevant questions for practice. Benefits include realistic feedback and adaptability to user proficiency. Open-source language models evaluate content, coherence, and delivery, offering personalized challenges. This approach supplements learning, enhancing presentation skills effectively. Voice-to-text conversion and AI feedback create a potent pedagogical tool, fostering a prompt feedback loop vital for learning effectiveness. Challenges in simulation design must be addressed for robustness and efficacy. The study validates these concepts by proposing a real-time 3D dialogue simulator, emphasizing the importance of continual improvement in presentation skill development.

The study aims to find the features for assessing the level of a maintenance operator. A genetic algorithm is used to identify the most relevant features and reduce their size. Based on 30 different features entered, we demonstrate that only three operator-level evaluation features provide a good classification. Virtual reality was used to simulate maintenance operations, collect data, and validate our method for identifying the most relevant features.

This work presents a conceptual framework that integrates Artificial Intelligence (AI) into immersive Virtual Reality (iVR) training systems, aiming to enhance adaptive learning environments that dynamically respond to individual users’ physiological states. The framework uses real-time data acquisition from multiple sources, including physiological sensors, eye-tracking and user interactions, processed through AI algorithms to personalise the training experience. By adjusting the complexity and nature of training tasks in real time, the framework seeks to maintain an optimal balance between challenge and skill, fostering an immersive learning environment. This work details some methodologies for data acquisition, the preprocessing required to synchronise and standardise diverse data streams, and the AI training techniques essential for effective real-time adaptation. It also discusses logistical considerations of computational load management in adaptive systems. Future work could explore the scalability of these systems and their potential for self-adaptation, where models are continuously refined and updated in real-time based on incoming data during user interactions.

The advent of Industry 5.0, as described by the European Commission, heralds a paradigm shift towards human-centric values, sustainability, and resilience in manufacturing, replacing the precedent Industry 4.0. In this evolving landscape, the integration of eXtended Reality (XR) technologies presents a promising avenue for enhancing human-machine interaction through industrial Digital Twins (DTs). This study introduces and validates an innovative XR-based interface for programming industrial cobots, comparing its performance to a conventional teach pendant control system. Leveraging a cohort of Human-Computer Interaction and User Experience experts, the evaluation demonstrates significant advantages of the XR-based interface in terms of usability, acceptance, and user experience. Participants were more inclined to adopt the XR-based interface, perceiving improvements in task performance, particularly in speed, while maintaining comparable accuracy to the teach pendant. Qualitative feedback highlights the simplicity, fluency, efficiency, and ergonomic interaction design of the XR interface. These results inform potential enhancements to further optimize the usability and effectiveness of XR-based DT systems in industrial settings, reaffirming the pivotal role of human-centric approaches in shaping the future of manufacturing.

This paper presents the development of a learning tool based on Digital Twins, designed to generate a virtual environment controlled by a PLC S7-1200. This tool allows engineering students to interact in an active and practical way with simulated industrial processes. The real-time communication between the controller and the work environment contributes significantly to decision making, allowing students to design, control and manipulate industrial processes with precision, as well as to respond to possible eventualities during the execution of such processes. To evaluate the usability of the tool, the System Usability Test (SUS) was applied to a homogeneous group of 20 students, obtaining an average score of 86.5, which classifies the tool in the “good” range. This result suggests that the tool is perceived as interactive and immersive, creating an active and user-friendly work environment.

The implementation of digital twins in higher education has enormous potential and is becoming increasingly relevant. Specifically, digital twins represent a powerful tool that promotes the transformation of the educational process and unveils new opportunities for students and teachers. Enhancing educational accessibility, realistic simulations, resource savings, personalized learning, and research opportunities are just a few of the prospects for the application of digital twins in education.This article analyzes the challenges and prospects associated with the deployment of digital twins in the educational sphere. It explores technological innovations that enable the creation of accurate copies of real objects and processes in a virtual environment. The benefits of this approach are discussed, including enhancement of educational accessibility, improved practical experience, and enhanced student motivation. Examples of successful digital twin applications in various educational contexts are considered, as well as challenges and potential solutions to overcome them. A digital twin of the International Information Technology University (Almaty, Kazakhstan) has been developed, allowing for education in a virtual space. The article concludes by summarizing the findings and draws conclusions about the potential of digital twins to transform education.

The Digital Twin (DT) offers an integrated solution for replicating physical (human and non-human) systems with monitoring capabilities and intelligent support for decision-making. Their popularity in academia and industry is growing, and different commercial and open-source development platforms are now available. However, there is a lack of detailed platform benchmarking studies and selection guidelines. This paper (1) identifies a portfolio of DT development platforms (DTDP) and (2) suggests a systematic method to evaluate them. Preliminary results of the method adoption are presented for a use case of a dry port DT deployment. This research will assist companies with their DTDP investments, presenting an assessment example for more complex DT deployment settings.