Traditional training methods in industrial environments often lack real-time guidance and interactive feedback, which can make knowledge sharing challenging. Augmented Situated Visualization (SV) can improve industrial training by providing in-depth, spatially relevant instructions, which are particularly valuable when safety procedures are crucial. This work describes a tool for SV deployed on a commercial headset and investigates how two different SV patterns, 2D labels and 3D ghosts, impact user experience, workload, discomfort, task completion time, and memory recall in a training scenario for machine maintenance.

Under an industrial-academic partnership project, the present work aims to map and catalog the different applications of Augmented and Virtual Reality in predictive maintenance (PdM) practices. Through a preliminary scoping review, we targeted two main digital libraries in computing and engineering. Thus, we address the key attributes regarding the types of immersive technologies and the solutions used in several industries for PdM. By categorizing the surveyed prototypes according to 10 parameters in their interaction, visualization, and research methods, we expose the state-of-the-art and valuable knowledge gaps within immersive PdM. After this analysis, we conducted a workshop with 3 manufacturing experts discussing the future of maintenance interfaces, bringing forth their feedback in the shape of recommendations for what to further explore within immersive PdM.

Animations produced by generative models are often evaluated using objective quantitative metrics that do not fully capture perceptual effects in immersive virtual environments. To address this gap, we present a preliminary perceptual evaluation of generative models for animation synthesis, conducted via a VR-based user study (N = 48). Our investigation specifically focuses on animation congruency—ensuring that generated facial expressions and body gestures are both congruent with and synchronized to driving speech. We evaluated two state-of-the-art methods: a speech-driven full-body animation model and a video-driven full-body reconstruction model, assessing their capability to produce congruent facial expressions and body gestures. Our results demonstrate a strong user preference for combined facial and body animations, highlighting that congruent multimodal animations significantly enhance perceived realism compared to animations featuring only a single modality. By incorporating VR-based perceptual feedback into training pipelines, our approach provides a foundation for developing more engaging and responsive virtual characters.

Introduction: Social interactions incorporate various nonverbal signals to convey emotions alongside speech, including facial expressions and body gestures. Generative models have demonstrated promising results in creating full-body nonverbal animations synchronized with speech; however, evaluations using statistical metrics in 2D settings fail to fully capture user-perceived emotions, limiting our understanding of the effectiveness of these models. Methods: To address this, we evaluate emotional 3D animation generative models within an immersive Virtual Reality (VR) environment, emphasizing user—centric metrics-emotional arousal realism, naturalness, enjoyment, diversity, and interaction quality—in a real-time human-agent interaction scenario. Through a user study (N = 48), we systematically examine perceived emotional quality for three state-of-the-art speech-driven 3D animation methods across two specific emotions: happiness (high arousal) and neutral (mid arousal). Additionally, we compare these generative models against real human expressions obtained via a reconstruction-based method to assess both their strengths and limitations and how closely they replicate real human facial and body expressions. Results: Our results demonstrate that methods explicitly modeling emotions lead to higher recognition accuracy compared to those focusing solely on speech-driven synchrony. Users rated the realism and naturalness of happy animations significantly higher than those of neutral animations, highlighting the limitations of current generative models in handling subtle emotional states. Discussion: Generative models underperformed compared to reconstruction-based methods in facial expression quality, and all methods received relatively low ratings for animation enjoyment and interaction quality, emphasizing the importance of incorporating user-centric evaluations into generative model development. Finally, participants positively recognized animation diversity across all generative models.

Prognostic methods broadly fall into two categories—model-based and data-driven—both of which have shown effectiveness across a range of engineering applications. Model-based approaches require an explicit representation of the degradation process, defining failure as the point when the physical damage state exceeds a predetermined threshold. Data-driven methods, on the other hand, leverage sensor data to directly predict end-of-life (EOL) or related prognostic information. Although both approaches offer insights that could be complementary and potentially fused, most existing fusion methods either combine the outputs from multiple methods or adopt a data-driven method to assist the model-based method. To further enhance the prognostic performance, this study proposes a fusion-based prognostic approach in which the output of one method is actively used to update the model of the other through either the crossover operator or the likelihood function. The proposed approach is validated using both an aluminum fatigue dataset and the Prognostics and Health Management (PHM) 2010 cutter wear dataset, demonstrating improved prognostic accuracy compared to either method used independently.

We introduce PerfCam, an open source Proof-of-Concept (PoC) digital twinning framework that combines camera and sensory data with 3D Gaussian Splatting and computer vision models for digital twinning, object tracking, and Key Performance Indicators (KPIs) extraction in industrial production lines. By utilizing 3D reconstruction and Convolutional Neural Networks (CNNs), PerfCam offers a semi-automated approach to object tracking and spatial mapping, enabling highly accurate digital twins that capture real-time KPIs such as availability, performance, Overall Equipment Effectiveness (OEE), and rate of conveyor belts in the production line. We validate the effectiveness of PerfCam through a practical deployment within realistic test production lines in the pharmaceutical industry and contribute an openly published dataset to support further research and development in the field. The results demonstrate PerfCam’s ability to deliver actionable insights through its precise digital twin capabilities, underscoring its value as an effective tool for developing usable digital twins in smart manufacturing environments and extracting operational analytics.

Conversational AI (CAI) has proven effective in educational settings, however its potential in industrial training, where higher precision and reliability are required, remains under-explored. This work-in-progress paper proposes a study to examine how AI persona design (Machine vs. Expert Operator) and voice embodiment (Diegetic vs. Disembodied) influence cognitive load, task efficiency, and usability in industrial training. By training a large language model (LLM) on Standard Operating Procedure (SOP) data, this project aims to develop a CAI assistant that provides real-time, easy-to-access information during task execution, in an attempt to enhance training efficiency and reduce reliance on text-heavy manuals through a user-centered approach.

Understanding another person’s visual perceptions is known as visuospatial perspective taking, with evidence to date demonstrating it is delineated across two levels, depending on how different that perspective is. Some strategies for visuospatial perspective taking have also been found to involve embodied cognition. However, the current generalisation of these findings is limited due to experimental setup and the use of computer monitors as the interface for experimental tasks. Augmented reality interfaces could possibly extend on the generalisation of these findings by situating virtual stimuli in the real environment, thus providing a higher degree of ecological validity and experimental standardisation. This study aimed to observe visuospatial perspective taking in augmented reality. This was achieved in participant experiments (N=24)(N=24) using the Left-Right behavioural speeded decision task, which requires participants to discriminate between target objects relative to the perspective of an avatar. Angular disparity and posture congruence between the avatar and participant were manipulated between each trial to delineate between the two levels of visuospatial perspective taking and understand its potentially embodied nature. Although generalised linear mixed modeling indicated that angular disparity increased task difficulty, unexpectedly findings on posture congruence were less clear. Together, this suggests that visuospatial perspective taking in this study can be delineated across two levels. Further implications for embodied cognition and empathy research are discussed.

This thesis proposes a series of user evaluations of spatialized sonification methods rendered as AR in simulated and real-life scenarios. It proposes and promotes next-generation micro-guidance methods for low-visibility and vision-impaired (VI) scenarios. In 2D hand-guidance, results (N=47) outlined that sound spatiality methods had the most promising performance in time taken and distance from target. When assessing vertical hand-guidance in a 3D task (N=19), results indicated a significantly higher accuracy for a novel height-to-pitch method. Finally, a significant disparity was found between VI (N=20) and sighted (N=77) people regarding sighted people’s empathy with the VI community. After an AR blindness embodiment experience, sighted people’s (N=15) empathetic and sympathetic responses towards said community significantly increased. Ultimately, this thesis evaluates how audio AR can help users to have accurate and safe performances in day-to-day manual tasks.

Extensive research has been conducted in multiple surgical specialities where Virtual Reality (VR) has been utilised, such as spinal neurosurgery. However, cranial neurosurgery remains relatively unexplored in this regard. This work explores the impact of adopting VR to study External Ventricular Drainage (EVD). In this study, pre-recorded Motion Captured data of an EVD procedure is visualised on a VR headset, in comparison to a desktop monitor condition. Participants (N = 20) ) were tasked with identifying and marking a key moment in the recordings. Objective and subjective metrics were recorded, such as completion time, temporal and spatial error distances, workload, and usability. The results from the experiment showed that the task was completed on average twice as fast in VR, when compared to desktop. However, desktop showed fewer error- prone results. Subjective feedback showed a slightly higher preference towards the VR environment concerning usability, while maintaining a comparable workload. Overall, VR displays are promising as an alternative tool to be used for educational and training purposes in cranial surgery.