Search Results (944)

This paper proposes a sociological reinterpretation of the concept of sustainability, understood as a cultural dispositive capable of shaping habitus, social representations, and models of action. From a culturalist perspective, sustainability is analysed as a process of social construction grounded in the internalisation of values, knowledge, and practices that contribute to the formation of responsible citizenship. Within this theoretical framework, the school assumes a strategic role in processes of sustainability education by fostering the ethical, collaborative, and inclusive competences required to address contemporary socio-environmental transformations. The paper presents the Edumat+ design protocol, developed within the framework of the Erasmus+ programme, aimed at experimenting with innovative methodologies for digital education in primary schools through the integration of STEAM approaches, with reference to coding, educational robotics, and information design. The protocol involved the development of infographic mats and digital learning activities focused on themes of environmental sustainability. The findings highlight how the integration of digital education, visual storytelling, and collaborative learning can contribute to the construction of inclusive and participatory educational environments capable of supporting processes of sustainable citizenship from primary education onwards. Although the activation of such pathways is consistent with recent European policies promoting the integration of digital technologies and STEAM approaches within schools, particularly through initiatives focused on teacher education and the acquisition of technologies and software, the widespread dissemination of the project still requires further governmental support, especially for the development and dissemination of the project outputs. Full article

This paper aims to improve the efficiency of 2D LiDAR-based robot navigation, which can be decreased in dynamic environments. In existing methods, dynamic objects are considered as LiDAR scan data itself, but human behavior patterns (trajectory, speed, etc.) are not considered, which may cause inconvenience to people while the robot is moving along the path. Therefore, in this paper, human behavior patterns (trajectory, speed) are added to a costmap to be considered as obstacles. This enables the robot to perform efficient socially aware robot navigation by considering the human information and avoiding humans in advance. The proposed method is compared with existing methods in a simulation environment by setting the human speed, human trajectory, and the robot’s initial position and goal point under each different condition. The overall results show that the existing methods violated the social distance, while the proposed method does not disturb humans through efficient socially aware robot navigation that considers and avoids humans in advance. Full article

City Information Modelling (CIM) and Urban Digital Twins (UDT) are pivotal for advancing smart urban planning and city management, yet empirical evidence on their real-world implementation is scarce. Following a sequential mixed-methods design, this study addresses this gap through a global investigation analyzing 33 projects across diverse geographic contexts. Findings reveal that these technologies are predominantly applied in 3D visualization (60.6%) and urban planning (48.5%), with significant underutilization in climate adaptation (9.1%) and AI-driven robotics (3.0%). A pronounced physical–social data divide exists, with infrastructure data prioritized over human-centric inputs. Technology stacks converge on GIS, IoT, and BIM. However, an interoperability paradox persists, as internal integration outpaces cross-organizational connectivity. Governance is predominantly public-sector-led, but multi-actor ecosystems are also involved. The study concludes with actionable recommendations to rebalance implementation portfolios, integrate socio-economic data, and advance both technical and institutional interoperability, thereby harnessing CIM and UDT for transformative urban planning and city management. Full article

This study investigates the impact of selected automation scenarios on occupational safety, ergonomics, and operational performance in a plastic crate production workstation. The research focuses on a specific case from the discrete manufacturing sector and aims to develop an integrated analytical framework combining ergonomic assessment with process simulation for the evaluation of organizational and technological improvements in manual handling operations. This study applies a simulation-based production model developed in the DBR77 discrete-event simulation environment to analyze alternative workstation configurations. The assessment framework integrates Ishikawa analysis for root-cause identification and the RULA and REBA methods for ergonomic risk evaluation. The investigated workstation was characterized by repetitive manual handling activities, awkward working postures, and increased physical workload associated with palletizing and transport operations. Several organizational and technological variants were analyzed, including additional operator support, robot-assisted palletizing, conveyor integration, and automated guided vehicle (AGV) transport. The simulation results indicated that the AGV-supported configuration achieved the shortest cycle time (1270 s per batch of 30 units), whereas the robot-assisted variant resulted in the longest cycle time (1520 s). Ergonomic assessment showed a reduction in RULA scores from 6–7 to 3–4 and REBA scores from 8–10 to 4–5 in the automated scenarios. The contribution of this study lies in the integration of ergonomic risk assessment and discrete-event simulation within a unified evaluation framework for workstation redesign in discrete manufacturing environments. The findings demonstrate how simulation-supported analysis can support decision-making regarding the balance between manual labor and automation under specific operational conditions. Due to the single-case-study design, the results should be interpreted as context-specific and exploratory rather than directly generalizable to all manufacturing systems. Full article

In this paper, we examine the evolving conception of the “other” in relation to human happiness, drawing on Paul Ricoeur’s philosophical account and empirical findings from the Harvard Study of Adult Development. Ricoeur situates happiness in three interrelated threads: individual fulfilment, friendship with those near to us, and just relations with distant others. The Harvard Study corroborates the significance of relationality for well-being, showing that strong social ties enhance longevity and life satisfaction. However, contemporary digitalisation and the proliferation of AI humanoid social robots challenge traditional notions of the “other.” Individuals increasingly form “meaningful” attachments, emotional bonds, and even romantic relationships with technological artefacts, raising the question of whether these non-human entities can contribute to happiness in a Ricoeurian sense. While the above dynamics are now proliferating, we argue that AI and social robots cannot be considered as the “other” in the Ricoeurian sense. Although these technologies can be considered as a virtual other, we do not defend that position in the current paper. In this paper, we explore the tensions regarding the authenticity, moral status, and ethical implications of AI and social robots in relation to human happiness. We conclude by proposing a re-evaluation of relationality, moral consideration, and the ethical frameworks underpinning human–technology interactions in the pursuit of human flourishing and happiness in the Ricoeurian sense. Full article

Social robots hold promise for enhancing later-life support, but user needs and preferences for multimodal interaction modalities remain underexplored. This study explores awareness, willingness, perceived barriers, and modality–function associations across multiple interaction modalities among middle-aged and older adults, and proposes a conceptual five-layer architecture for design guidance. A questionnaire survey with 199 Chinese respondents (aged 45–64: 89.4%, 65+: 10.6%) examined perceptions of voice, visual, gestural, affective, sEMG, and brain–computer interface interactions. Voice and visual modalities were the most preferred; gesture and affective interactions were moderately accepted; awareness of sEMG was high but may reflect confusion with other sensor technologies; and BCI awareness and willingness were low. Based on survey findings and the literature, a conceptual five-layer architecture is presented to inform future social-robot design. The sample predominantly comprised middle-aged participants, so findings reflect prospective later-life users rather than the broader older-adult population. This study offers user-centered insights into multimodal social-robot interaction and provides design implications for future development rather than evaluating emotional-health interventions. Full article

The way robots represent the environment, make decisions, and express themselves can positively influence human–robot interaction if they clearly communicate their intentions and needs. To improve human–robot communication, biologically inspired models that mimic human communication skills, including task and scenario-specific contextual information, can facilitate mutual understanding and successful task execution. This paper presents a Context-Awareness and Biologically Inspired Behaviour system to generate a more natural human–robot interaction. The architecture combines sensory information processed by a Joint Attention System that prioritises stimuli based on internal processes with task-related motivations to generate context- and goal-adapted verbal and non-verbal interaction. We evaluate the system through a video-based user study that compares two robots with similar appearances but different behaviours, one using the proposed approach and the other not using the internal state and joint attention mechanisms, to make verbal and non-verbal responses. The results show that participants rated the robot endowed with the proposed system as significantly more sociable, agentic, and animated than the robot without it. Additionally, the robot not showing the responses developed in this work was perceived as more disturbing than the robot integrating the proposed system. Full article

Social and emotional learning (SEL) has become increasingly central to educational policy and lifelong development, while advances in robotics have opened new possibilities for supporting socio-emotional competencies through human–robot interaction. Despite the rapid growth of robot-assisted SEL research, this field remains fragmented, with limited understanding of its intellectual structure, thematic foci, and evolution. To address this gap, this study conducted a scientometric analysis of 241 publications indexed in Web of Science using bibliometric methods. Results indicate a steady growth trajectory, with research concentrated in a small number of core countries driving international collaboration. Influential publications and co-citation patterns reveal a strong foundation in autism-related interventions and child-centered social skill development. Thematic mapping shows that motor themes are dominated by soft skills, autism, and interaction design, while emotion recognition and affective computing form technically mature but specialized streams. Foundational concepts such as human–robot interaction and artificial intelligence remain central yet theoretically evolving. Emerging links between robotics, STEM, and project-based learning suggest ongoing pedagogical expansion. This study maps the intellectual and thematic structure of robot-assisted SEL, showing how robots are emerging as mediational agents in hybrid learning systems while revealing uneven integration and misalignments between technological capabilities and pedagogical foundations. Full article

Animal-assisted interventions can support emotional well-being and social engagement, but their use may be limited by allergies, infection risks, and animal-handling requirements. As a scalable alternative, artificial intelligence-based pet therapy, including socially assistive and robotic pets, has been introduced in health care and community settings. This systematic review, conducted in accordance with PRISMA guidelines, searched PubMed, CINAHL Ultimate/MEDLINE, Scopus, Web of Science, and SAGE for studies published between 2014 and 2025 that evaluated the reported effects of AI-based pet therapy on patient outcomes. Of the 584 records identified, 27 studies met the inclusion criteria after duplicate removal and screening. Most studies involved older adults with dementia, although children, veterans, and community-dwelling adults were also represented. Across studies, AI-based pet therapy was associated with reduced agitation, anxiety, stress, and pain, as well as improved mood, communication, and social engagement. PARO was the most frequently studied robotic pet, and interventions were typically delivered 1–3 times weekly for 30–60 min over 4–12 weeks. Overall, AI-based pet therapy appears to be a promising complementary non-pharmacological approach, particularly for people with dementia and hospitalized children, although stronger evidence from larger, more standardized, and longer-term studies is still needed. Full article

Humanoid robots operating in proximity to humans require the ability to perceive and interpret emotional cues conveyed through touch to achieve safe, natural, and socially intelligent interaction. Conventional tactile sensing systems primarily focus on force or pressure detection and cannot infer affective intent, while frame-based deep learning models often suffer from high latency and energy consumption when deployed on embedded platforms. To address these limitations, this paper presents a neuromorphic AI-based multimodal electronic skin (e-skin) framework for emotion-sensitive touch perception in humanoid robots. The proposed system integrates pressure, temperature, and electrostatic sensing with a bio-inspired signal conditioning pipeline and a Spiking Neural Network (SNN) for event-driven, low-power processing. A custom multimodal tactile dataset was collected using the proposed e-skin prototype to model four emotional touch interactions: stress, neutral, comfort, and affection. Experimental results demonstrate that the proposed approach achieves a high emotion classification accuracy of up to 92%, with an average accuracy of 88.75% across all classes. The neuromorphic SNN significantly reduces inference latency to approximately 8 ms, compared to 38 ms for a conventional CNN-based model, while maintaining energy-efficient operation suitable for edge deployment. The results validate the effectiveness of combining multimodal tactile sensing with neuromorphic processing to enable real-time, emotion-aware human–robot interaction. Full article

Social robots are systems designed to assist people across different fields. During their operation, they have to interact with people with different characteristics and necessities. Consequently, correctly recognising the user interacting with the robot facilitates the generation of a personalised experience that satisfies the user’s needs. In robotics, user recognition is typically based on face recognition from image processing and datasets that require retraining the network to include new users. However, some robots, such as pet-like companions, often lack a camera due to reduced dimensions, limited computational resources, or privacy constraints. Additionally, robots can occasionally encounter new users, requiring online recognition to provide a personalised interaction experience. To address these limitations, this article presents a user recognition system based on voice biometrics and dynamic clustering for adaptive social robots. We evaluate a set of open-source models for voice biometric extraction using different clustering algorithms to identify the best combination for our application. The resulting system is implemented in a pet-like robot companion that is used for the affective support of older adults, demonstrating its capacities in a real-world scenario. The system achieves more than $73\%$ accuracy in recognising users who had previously spoken to the robot and more than $71\%$ success in recognising new users who had not previously interacted with the robot and creating a personal profile for them. However, the system still detects noise, especially when the speaker has never interacted with the robot. Full article

This study investigates the user experience (UX) of game-based activities within a school-based social robot intervention for children with ASD and examines changes in task-related performance across robot-led and teacher-led structured communicative–linguistic activities. A multimodal methodology combines quantitative measures (accuracy, response time, and physiological signals) with qualitative teacher feedback. The results reveal limited significant differences in accuracy and other performance variables; however, response time decreased significantly across repetitions and was lower in teacher-led sessions. These findings indicate improved task-response efficiency and suggest a possible facilitation pattern in subsequent human-led interactions, although this effect cannot be disentangled from practice or order effects because of the sequential design. Rather than demonstrating broad linguistic gains, the study highlights the value of multimodal UX-oriented evaluation for identifying design limitations, refining robot-mediated educational activities, and supporting teacher involvement in ASD interventions. Full article

Pedestrian trajectory prediction is vital for crowd analysis and human–-robot interaction. Recent deep models enhance accuracy by modeling social interactions and scene context, but they often remain opaque and rarely address privacy risks associated with learning individualized motion patterns. We propose CAMP, a Context-Aware, Multimodal, and Privacy-preserving pedestrian trajectory prediction framework designed around a role-aligned multimodal architecture, in which trajectory representations, dynamic scene cues, and explicit spatial interaction constraints are modeled through complementary branches. In CAMP, the trajectory encoder separates shared motion regularities from individualized motion tendencies, the optical-flow encoder captures motion-centric transient scene dynamics, and the potential-field encoder provides an interpretable spatial cost prior for obstacle avoidance and social interaction modeling. A Transformer-based decoder fuses these modalities to predict future trajectory distributions. To reduce the exposure of personalized motion patterns, we apply targeted DP-SGD only to the individual branch during the private fine-tuning stage, while treating the remaining frozen components as post-processing under the stated threat model. Experiments on the ETH/UCY benchmark show that CAMP achieves competitive ADE/FDE performance under the reported setting, while its private variant DP-CAMP maintains a reasonable utility–privacy trade-off across several reported privacy budgets. Full article

In the field of human–robot interaction (HRI), researchers have extensively examined the role of social robot characteristics and how these can influence human–robot relationships. In particular, the robot’s voice is one of the most studied aspects, with numerous studies focusing on specific features such as tone, frequency, pitch, and gender. The robot’s voice represents a powerful social signal, whose design can influence people’s affective evaluations and acceptance of robots. With regard to language, however, relatively few studies have investigated the role of a robot’s accent (native or foreign). This experimental study therefore explores the influence of native accent on trust in robots. The study was conducted on two different samples: 60 Italian participants and 37 Arabic participants. Participants listened to two robot presentations in their native language: one delivered with a native accent and the other with a foreign accent. After listening to both presentations, participants were asked to indicate which robot they trusted. The results showed a 77.3% preference for the robot speaking with a native accent, compared to 22.7% for the robot with foreign accent. These findings demonstrate that, regardless of the language (Italian or Arabic), accent significantly influences the choice to invest trust in the robot, supporting the similarity-attraction effect. Accent calibration thus emerges as a low-cost, high-impact parameter in socially assistive and commercial robotics. Since accent influences trust-based delegation, voice design should be strategically adapted in service, healthcare, education, and customer-facing contexts. Full article

Introduction: Late functional outcomes remain major determinants of quality of life after robot-assisted radical prostatectomy (RARP). Although several baseline and perioperative factors have been linked to postoperative stress urinary incontinence (SUI) and erectile dysfunction (ED), their cumulative effect remains incompletely characterized in large real-world cohorts. Materials and Methods: This retrospective single-center study included 862 consecutive patients undergoing RARP for localized prostate cancer. All endpoints were assessed at a fixed 12-month follow-up visit; therefore, a median follow-up beyond this predefined time point was not applicable. Outcomes were derived from patient-reported information documented during routine follow-up and comprised pad use, ED, and urethral anastomotic stricture. Age, body mass index (BMI), console time, estimated blood loss, and prostate weight were selected a priori based on clinical relevance and uniform availability and were analyzed using univariable and multivariable logistic regression. A simple exploratory composite risk score (0–5 points) was constructed by assigning one point for each predefined adverse factor. Results: At 12 months, 50.0% of patients were pad-free, 85.6% achieved social continence (0–1 pad/day), 14.5% had clinically significant incontinence (>1 pad/day), 71.5% had chart-documented ED, and 1.0% developed urethral anastomotic stricture. In multivariable analysis, age (OR 1.039, 95% CI 1.018–1.059) and prostate weight (OR 1.011, 95% CI 1.004–1.018) independently predicted SUI, while age was the only independent predictor of ED (OR 1.029, 95% CI 1.007–1.050). No predictor of stricture was identified. The composite score showed an exploratory dose–response association with SUI (OR 1.364 per point, 95% CI 1.208–1.541; AUC 0.597) and a weaker association with ED (OR 1.149, 95% CI 1.007–1.313; AUC 0.540). Conclusions: A simple composite score may provide pragmatic exploratory grouping of SUI risk after RARP, but discrimination is modest and interpretation is limited by non-validated outcome assessment and the absence of major confounders, including nerve-sparing status and baseline functional measures. Full article