This paper describes the design and the realization of a prototype of the novel guide robot BUDD-e for visually impaired users. The robot has been tested in a real scenario with the help of visually disabled volunteers at ASST Grande Ospedale Metropolitano Niguarda, in Milan. The results of the experimental campaign are throughly described in the paper, displaying its remarkable performance and user-acceptance.

The integration of electrodes into textiles for monitoring physiological signals like surface electromyography (EMG) represents a critical area of development for wearable health technology. In this context, this paper reported a comprehensive evaluation of different embroidered textile electrode designs for surface EMG applications. Electrodes using silver-coated polyamide yarn on a neoprene substrate were specifically fabricated, exploring various embroidery pattern (i.e., Satin, Spiral, Moss stitch) and geometries. The electrodes underwent a multi-faceted evaluation, including impedance check and functional EMG signal acquisition during operating conditions, i.e., walking and step climbing. Preliminary key performance metrics, such as Root Mean Square (RMS) and Signal-to-Noise Ratio (SNR), were analyzed while maintaining the dry conditions. The results indicate that embroidered electrodes can reliably detect muscle activation, with performance levels dependent on the specific design. Notably, the SNR of several embroidered designs was found to be on par with conventional pre-gelled Ag/AgCl electrodes. This research underscores the viability of technical embroidery as a robust method for producing high-fidelity and durable textile electrodes for wearable monitoring physiological systems, paving the way for more comfortable and user-friendly healthcare and sports applications.

Physical activity (PA), defined by the World Health Organization (WHO) as any body movement involving the musculoskeletal system, provides health benefits from an early age. In addition, regular PA supports the treatment of chronic diseases and improves the well-being of children with clinical conditions such as neuromotor disorders (ND). However, both medical and psychosocial barriers can hinder children with compromised health conditions from maintaining active lifestyles. The recent diffusion of digital tools has proven to be a valuable tool in overcoming these barriers and promoting PA even among children with chronic diseases. Starting from these assumptions, this study presents preliminary results from the reframing of existing co-design methods through the active involvement of children with ND as co-designers in the process itself. Within this framework, children play a role in shaping knowledge around inclusive co-design practices aimed at improving PA. Intuitiveness and accessibility of these methods, together with the transferability of the outcomes into clear and specific design requirements are the main challenges tackled by the research. The resulting adapted methods will serve as a foundation for future work aimed at designing digital solutions that can enhance motivation toward active lifestyles, as well as for further investigating children’s perspectives on PA.

The convergence of self-tracking technologies, Artificial Intelligence (AI), and eXtended Reality (XR) is rapidly transforming the design of assistive systems for inclusive sports and rehabilitation. The growing availability of low-cost wearable sensors, the maturation of deep-learning models for biosignal interpretation, and the diffusion of consumer-grade immersive hardware have created the conditions for a new generation of adaptive, personalized, and participatory solutions. This Special Thematic Session (STS) brings together multidisciplinary contributions addressing accessibility, adaptive training, and user-centered design across diverse contexts, from education to sport-specific applications. This paper introduces a unifying framework for AI-driven XR ecosystems integrating multimodal sensing, virtual coaching, and inclusive interaction design. It further contextualizes the accepted contributions within the STS, highlighting their complementary roles: sensory substitution for inclusive sailing, accessible physical activity frameworks in primary education, AI-driven immersive training systems, and semantic interoperability between assistive technology standards. Taken together, these works demonstrate how data-driven, adaptive, and inclusive technologies can support diverse users by enhancing participation, engagement, autonomy, and functional outcomes. The paper contributes a holistic perspective on the future of assistive technologies for sports and rehabilitation, emphasizing the importance of integrating technological innovation with human-centered design, clinical evidence, and standardized interoperability frameworks.

Background:Large language model (LLM)-based conversational agents have been increasingly used in digital health interventions. However, their specific application to physical activity (PA) and cognitive training-two critical well-being domains-has not been systematically mapped. In fact, these domains share an important need for personalized, adaptive support and conversational engagement, making them relevant targets for examining how LLM-based agents are currently conceptualized and deployed. Objective:This scoping review aimed to map the extent, characteristics, and design practices of LLM-based conversational agents supporting PA or cognitive training, specifically analyzing their application contexts, social roles, and technological features. Methods:Following PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, we searched Web of Science, Scopus, PubMed, ACM Digital Library, and IEEE Xplore for studies published between January 2018 and December 2024. We included eligible studies that described LLM-based conversational agents designed for PA or cognitive training. Two reviewers independently screened records and extracted data. Descriptive synthesis and framework analysis were used to characterize intervention domains, agent roles, prompting strategies, model types, and reported outcomes. Results:Of 357 records screened, 10 studies met eligibility criteria (7 on PA and 3 on cognitive training). Applications predominantly involved coaching roles for PA and companion or scaffolding roles in cognitive domains. The agent landscape was dominated by proprietary LLMs (GPT-3.5, GPT-4, and Bard), with limited use of open-weight models. Prompt engineering emerged as a central yet inconsistently documented design mechanism. Reported outcomes mainly focused on perceived usefulness, engagement, or content quality, with few quantitative behavioral outcomes. Conclusions:LLM-based conversational agents have demonstrated early promise for supporting PA and emerging approaches to cognitive training, yet the current evidence remains exploratory and methodologically limited. Key challenges persist, including inconsistent reporting of prompts, reliance on proprietary models with limited reproducibility, and a lack of standardized outcome measures. More rigorous and transparently documented evaluations of these tools are required to strengthen the evidence base and guide future development.

Female soccer is rapidly becoming a widely practiced sport at different levels: this opens up a new demand for systems meant to protect athletes from head impacts or to monitor their effects. The market is offering some solutions in similar sports, but the specificity and high relevance of soccer encourage the development of a dedicated solution. From market analysis, technology scouting, and ethnographic research a set of functional and technical requirements have been defined and proposed. The designed instrumented head band is equipped with one Inertial Measurement Unit (IMU) in the occipital area and four contact pressure sensors on the sides. The concept design is low-cost and open-architecture, prioritizing accessibility over complexity. The modularity also ensures that each component (sensing, battery, communication) can be replaced or upgraded independently, enabling iterative refinement and integration into future sports safety systems. In addition to safety monitoring for injury prevention or detection of the traumatic impact, the system is relevant for supporting performance monitoring, rehabilitation or post-injury recovery and other important applications. System engineering has started and the next step is building the prototypes for testing and validation.

The evolution of the mHealth era offers the possibility of behavioral interventions to promote changes in lifestyle habits with prevention relevance. These tools are considered digital therapeutics (DTx) and follow the MDR 745/2017 for testing, validation, and certification. In the frame of the ACTIVE3 project, we developed a platform composed of a mobile app, a wearable device, and a cloud backend to support healthy aging intervention in a population of 60–80-year-old subjects. This paper describes the clinical trial protocol and the baseline data of the recruited population. The explored parameters describe the effect of the DTx in the physical, nutritional (and metabolic), and cognitive domains, leveraging the Walking Group initiatives coordinated by ATS Brianza that are active in the Lecco area; in addition, system usability and acceptance were analyzed. The study started on 1 September 2024, and the analyzed baseline data are presented here. With respect to an expected population of 200 subjects, we received interest and consent to participate from 237 subjects: over-enrollment was allowed and all these subjects were accepted into the study. The characterization of the study population at the initial time of the trial was carried out, and the outcomes are presented here. The population is generally more active than Italian people of the same age. According to the outcome of the 6MWT, the population was divided into three groups: trained participants (42 subjects), active participants (142 subjects), and sedentary participants (58 subjects). The tests at month 12 were recently competed, and the final results will be available in winter 2025–2026.

Driving with assistive devices creates complex cognitive and emotional demands that require systematic investigation. This study uses a multivariate approach based on subjective and objective measures to evaluate mental workload (MWL), stress and emotional state during simulated driving with an assistive device. Thirty healthy adults (42 +/- 13 years of age, 7 females) completed four driving tasks combining two levels of difficulty (Easy vs. Hard) and two steering tools (wheel vs. single-pin aid). Subjective measures from NASA Task Load Index and Self-Assessment Manikin were collected, as well as physiological parameters from electroencephalographic, electrocardiographic, and electrodermal activity signals. The results revealed that the assistive device significantly induced increases in perceived physical demand, frustration, loss of emotional control and stress, yet reducing intrinsic sympathetic response represented by electrodermal activity parameters. Multivariate analyses highlighted that combining different physiological predictors improved MWL estimation. This study marks an initial step towards understanding the impact of assistive devices on MWL and stress in post-acute individuals returning to driving.

In the era of smart garments, textile electrodes for electromyography (EMG) or functional electric stimulation (FES) represent a very interesting and promising area of development and exploitation. In this frame, we conducted a patent landscape analysis of textile solution for EMG sensing and FES actuation, using Espacenet as a reference database and Orbit Intelligent platform as a data analysis tool. The landscape analysis focused on the following aspects: filing trends, top applicants in this domain, main publication countries, forward citations, and collaborations between applicants. Following the screening process, a total of 97 patent families were subjected to subsequent analysis. China and the United States account for the majority of patents. The main applicants by volume of the topics studied are universities or research public entities.

(1) Background: Marker-based optical motion tracking is the gold standard in gait analysis; however, markerless solutions are rapidly emerging today. Algorithms like Openpose can track human movement from a video. Few studies have assessed the validity of this method. This study aimed to assess the reliability of Openpose in measuring the kinematics and spatiotemporal gait parameters. (2) Methods: This analysis used simultaneously recorded video and optoelectronic motion capture data. We assessed 20 subjects with different gait impairments (healthy, right hemiplegia, left hemiplegia, paraparesis). The two methods were compared using computing absolute errors (AEs), intraclass correlation coefficients (ICCs), and cross-correlation coefficients (CCs) for normalized gait cycle joint angles. (3) Results: The spatiotemporal parameters showed an ICC between good to excellent, and the absolute error was very small: cadence AE = 1.63 step/min, Mean Velocity AE = 0.16 m/s. The Range of Motion (ROM) showed a good to excellent agreement in the sagittal plane. Furthermore, the normalized gait cycle CCC values indicated moderate to strong coupling in the sagittal plane. (4) Conclusions: We found Openpose to be accurate for sagittal plane gait kinematics and for spatiotemporal gait parameters in the healthy and pathological subjects assessed.

Teaching gardening skills to individuals with special needs presents distinct challenges, largely due to diverse learning preferences and accessibility limitations. Augmented Reality (AR) offers a compelling solution by delivering interactive, adaptive, and immersive educational experiences. This study introduces the design, development, and evaluation of an AR-based training application, specifically tailored for gardening activities and delivered through the Microsoft HoloLens 2 device. The application provides step-by-step visual and auditory instructions, dynamically adjusts content based on the user’s abilities, and supports skill acquisition through engaging, simulated practice. To assess the usability and effectiveness of the tool, the System Usability Scale (SUS) protocol was administered to participants with varying cognitive and physical needs. The paper details the conceptual framework, technical implementation, and insights gained from a pilot study involving users with diverse disabilities. Findings indicate that the use of AR—particularly via the HoloLens 2—significantly enhances accessibility, learning outcomes, and user engagement. Overall, the system demonstrates strong potential to empower individuals with special needs to build gardening skills and achieve greater independence.

Emergency department (ED) overcrowding and limited staff availability pose ongoing challenges to healthcare efficiency. Recent advancements in automated health technologies, such as the health pod, aim to alleviate these pressures by automating vital sign measurements for low-risk patients. Over three months, the CAPSULA Health Pod was implemented and used in a paired setting with normal triage procedures in an urban hospital ED; it demonstrated improvements in triage efficiency and patient satisfaction, aligning with evidence that supports automation as a solution in high-demand healthcare settings. With 1342 assessments across 404 patients, despite some challenges with elderly patient engagement, CAPSULA achieved excellent measurement accuracy and relevant efficiency for the first assessment of patients in crowded situations and for reassessment. The findings indicate CAPSULA’s potential to reduce patient wait times, improve workflow efficiency, and support resource-limited EDs. Although the main limitation remains IT integration, the system demonstrates scalability and potential for broader adoption.

This manuscript presents an updated review of back exoskeletons for occupational use, with a particular focus on sensor technology as a key enabler for intelligent and adaptive support. The study aims to identify key barriers to adoption and explore design characteristics which align these systems with the Industry 5.0 paradigm, where machines function as collaborative co-pilots alongside humans. We propose a structured design pipeline and analyze 32 exoskeletons across multiple dimensions, including design, actuation, control strategies, sensor networks, and intelligence. Additionally, we review eight simulation environments which support the early stages of exoskeleton development. Special emphasis is placed on sensor technology, highlighting its critical role in enhancing adaptability and intelligence. Our findings reveal that while 39.39% of exoskeletons accommodate asymmetric activities, kinematic compatibility remains a challenge. Furthermore, only 33.33% of the systems incorporated intelligent features, with just one being capable of adapting its response based on poor posture or real-time human–machine interaction feedback. The limited integration of advanced sensors and decision-making capabilities constrains their potential for dynamic and adaptive support. Open questions remain in high-level decision making, enhanced environmental awareness, and the development of generalizable methods for integrating sensor data into adaptive control strategies.

Metabolic diseases are increasing in relevance both in health and the economy in most countries. In this direction, if gold-standard technologies are based on blood analysis, non-invasive glucose monitoring is a relevant and great challenge that has not yet been fully resolved. Sweat represents a more suitable medium for the non-invasive sensing and monitoring of glucose than other bodily fluids, such as saliva, tears, or urine. However, the measurement of glucose levels requires the use of highly precise and sensitive sensors, given the low glucose concentration in sweat. This paper provides an overview of the patent landscape related to wearable biosensors for the monitoring of glucose levels in sweat.

In the last decade the introduction of wearable technologies supported the implementation of reliable quantification tools for clinical functional assessment. Within this frame, this work was focused on the development and validation of a wearable system for analyzing motor function, particularly using the Timed-Up and Go (TUG) test. This study specifically aimed to create a wearable device that could quantify and automate the TUG test, collecting not only the time taken but also various kinematic parameters like accelerations, velocity, and number of steps. The wearable actigraph, fixed at the pelvis by means of an elastic band, measured and stored 3D inertial parameters for processing and analysis. The validation involved comparing manual TUG test times with those obtained using the actigraph, showing a high level of agreement and accuracy. The study included healthy subjects and individuals with different pathologies like post-stroke, multiple sclerosis, and Parkinson's, demonstrating the system's feasibility in clinical settings. Overall, the wearable system proved effective in quantifying and automating the TUG test, offering a possible remote, self, and unsupervised method for functional evaluation and tele-rehabilitation programs.

Training individuals with special needs for cleaning activities presents unique challenges due to diverse learning styles and accessibility requirements. Augmented Reality (AR) technology offers a promising solution by providing interactive, immersive, and customizable training experiences. This paper presents the development and evaluation of an AR application tailored for training cleaning activities specifically designed to accommodate the needs of individuals with special needs. The application utilizes AR to provide personalized guidance, adapt training content to individual capabilities, and enhance engagement through interactive simulations. We discuss the design considerations, implementation details, and user feedback gathered through a pilot study involving individuals with various special needs. Results indicate that the AR application significantly improves the accessibility and effectiveness of training for cleaning activities, thereby empowering individuals with special needs to develop essential life skills and achieve greater independence.

The anterior cruciate ligament (ACL) plays a crucial role in constraining tibiofemoral articulation and preserving the knee joint from harmful aberrations of movement. However, certain high-risk movements, such as landing, can induce ACL injuries. Volleyball practice intrinsically requires performing jumps during attacking and defending phases, with a higher rate of ACL injury occurring during blocking tasks. The execution of these tasks is more subject to variability due to the necessity of adequately counteracting opponents. The type of landing after blocking, as well as gender, has been related to the potential risk of injury. We analyzed two different blocking techniques frequently occurring during volleyball matches: the block jump with double-leg landing and the block jump with single-leg landing (dominant and non-dominant). Synchronized kinematic and kinetic data from female volleyball players were collected using a set of wearable inertial measurement units (IMUs), force platforms, and wireless surface electromyography (EMG). Kinematic and kinetic data were evaluated during the weight-acceptance phase in each task to determine changes in landing approaches. Block jumping with single-leg landing resulted in changes in the kinematics at the hip, knee, and ankle levels, and higher values of muscular activation during the first instants of weight acceptance, particularly in the biceps femoris and gastrocnemius. Understanding the overall biomechanics associated with different sports tasks allows for a better understanding of personal risk and the definition of proper training programs aimed at injury prevention.

This study aimed to present the design, application and assessment of a wearable monitoring system focused on estimating the performance in women’s soccer players. Specific attention was given to design factors and to assess usability and reliability of a sensorized bra in monitoring overall performance in terms of heartrate and movement-related parameters, during the execution of training exercises. The system integrates textile-based ECG electrodes and 3D accelerometers within a specially designed sports bra. The analysis involved 9 young female soccer players and evaluated comfort, usability, and satisfaction of the system. Obtained results showed good mechanical comfort, with some concerns about overall breathability. The system demonstrated technical reliability in acquiring data for monitoring performance during training exercises. Overall, the study highlighted the importance of comfort, support, and technical reliability in this kind of wearable technologies.