The rapid evolution of human–robot interaction, particularly within human–robot collaboration, presents a transformative opportunity through mixed reality (MR) technologies to redefine industrial automation and safety. This article addresses the increasing demand for intuitive human–robot interfaces in emerging paradigms like Industry 5.0 and the Industrial Metaverse. Our motivation is to bridge the gap in understanding how users naturally interact with collaborative robots when immersed in MR environments. We present a novel elicitation study utilizing a Microsoft Hololens 2 head-mounted display (HMD), where users perceived their gestures directly controlling a cobot through real-time visual feedback within the MR space. This methodology allowed us to derive a set of natural, intuitive gesture-based control mechanisms tailored for MR-enhanced industrial robotics. The novelty lies in providing empirically grounded insights into user-defined gestural language under MR constraints for cobot navigation tasks and exploring the influence of user characteristics on these gestures. Our findings demonstrate MR’s potential to foster a more integrated, productive, and safe workspace by enhancing operational efficiency, reducing operator learning curves, and improving safety protocols in high-risk settings. We also identify key differences in gesture selection based on gender (in the gesture’s “Nature”) and professional background (in the gesture’s “Locale”), providing design implications for user-adaptive interfaces. These findings advance the applicability of MR technology in complex industrial environments, proposing new paradigms for human–robot interaction.

Mental health and wellbeing have become one of the significant challenges in global society, for which emotional regulation strategies hold the potential to offer a transversal approach to addressing them. However, the persistently declining adherence of patients to therapeutic interventions, coupled with the limited applicability of current technological interventions across diverse individuals and diagnoses, underscores the need for innovative solutions. We present ARCADIA, a Mixed-Reality platform strategically co-designed with therapists to enhance emotional regulation and self-compassion. ARCADIA comprises several gamified therapeutic activities, with a strong emphasis on fostering patient motivation. Through a dual study involving therapists and mental health patients, we validate the fully functional prototype of ARCADIA. Encouraging results are observed in terms of system usability, user engagement, and therapeutic potential. These findings lead us to believe that the combination of Mixed Reality and gamified therapeutic activities could be a significant tool in the future of mental health.

Abstract Eye-tracking techniques are widely used to analyze user behavior. While eye-trackers collect valuable quantitative data, the results are often described in a qualitative manner due to the lack of a model that interprets the gaze trajectories generated by routine tasks, such as reading or comparing two products. The aim of this work is to propose a new quantitative way to analyze gaze trajectories (scanpaths) using machine learning. We conducted a within-subjects study (N = 30) testing six different tasks that simulated specific user behaviors in web sites (attentional, comparing two images, reading in different contexts, and free surfing). We evaluated the scanpath results with three different classifiers (long short-term memory recurrent neural network—LSTM, random forest, and multilayer perceptron neural network—MLP) to discriminate between tasks. The results revealed that it is possible to classify and distinguish between the 6 different web behaviors proposed in this study based on the user’s scanpath. The classifier that achieved the best results was the LSTM, with a 95.7% accuracy. To the best of our knowledge, this is the first study to provide insight about MLP and LSTM classifiers to discriminate between tasks. In the discussion, we propose practical implications of the study results.

User-centered design applied to non-human animals is showing to be a promising research line known as Animal Computer Interaction (ACI), aimed at improving animals' wellbeing using technology. Within this research line, intelligent systems for animal entertainment could have remarkable benefits for their mental and physical wellbeing, while providing new ways of communication and amusement between humans and animals. In order to create user-centered interactive intelligent systems for animals, we first need to understand how they spontaneously interact with technology, and develop suitable mechanisms to adapt to the animals' observed interactions and preferences. Therefore, this paper describes a pioneer study on cats' preferences and behaviors with different technological devices. It also presents the design and evaluation of a promising depth-based tracking system for the detection of cats' body parts and postures. The contributions of this work lay foundations towards providing a framework for the development of future intelligent systems for animal entertainment.

Digital games for animals within Animal Computer Interaction are usually single-device oriented, however richer interactions could be delivered by considering multimodal environments and expanding the number of technological elements involved. In these playful ecosystems, animals could be either alone or accompanied by human beings, but in both cases the system should react properly to the interactions of all the players, creating more engaging and natural games. Technologically-mediated playful scenarios for animals will therefore require contextual information about the game participants, such as their location or body posture, in order to suitably adapt the system reactions. This paper presents a depth-based tracking system for cats capable of detecting their location, body posture and field of view. The proposed system could also be extended to locate and detect human gestures and track small robots, becoming a promising component in the creation of intelligent interspecies playful environments.