Search

In lower limb prostheses, the physical interface constituted by the socket is a crucial component for the device success. This work proposes a new design based on a rigid frame integrated into a silicone structure which allows for a more comfortable biomechanical coupling with the residual limb and facilitates the integration of smart technologies. In particular, four surface EMG sensors and three vibrotactile units have been integrated to enable a bidirectional interface able to decode the user’s motor intention and provide augmenting feedback, respectively. The new socket was tested on a transfemoral amputee. The sEMG signals were registered during five different locomotion tasks in a circuit training and the classification median accuracy of an intention decoding algorithm was found always higher than 73%. The user’s perception of vibrotactile feedback was assessed through a psychophysical experiment of localization of single, couple or triple of stimuli. It revealed that vibrations from singularly activated units were the best perceived. Questionnaire results confirmed a high satisfaction level. However, tests on temperature and humidity within the socket suggest that more efforts are still required in terms of skin perspiration. The proposed socket paves the way to smart physical interfaces for robotic prostheses.

Workers experiencing high levels of stress may suffer from poor motivation, low level of attention, and physical disorders which, in turn, may lead to work injuries. Respiratory frequency (fR) is considered one of the most reliable indicators of the mental load and fatigue state of workers. Monitoring this parameter through wearable devices represents an efficient solution for the maintenance of Occupational Health and Safety. We developed an innovative wearable system equipped with flexible sensors based on fiber Bragg gratings (FBGs) to monitor fR in static and dynamic conditions characterizing occupational settings. This article provides a description of the system and of the metrological characteristics of the flexible sensors in terms of response to strain and temperature changes, and hysteresis error. The performances of the device, evaluated in a laboratory during the execution of tasks mimicking real work activity, are also reported. The obtained promising results encourage the engineering of the system for use in real workplaces to collect quantitative information on the psychophysical state of workers and its relation to stress level.

The continuous monitoring of an individual's breathing can be an instrument for the assessment and enhancement of human wellness. Specific respiratory features are unique markers of the deterioration of a health condition, the onset of a disease, fatigue and stressful circumstances. The early and reliable prediction of high-risk situations can result in the implementation of appropriate intervention strategies that might be lifesaving. Hence, smart wearables for the monitoring of continuous breathing have recently been attracting the interest of many researchers and companies. However, most of the existing approaches do not provide comprehensive respiratory information. For this reason, a meta-learning algorithm based on LSTM neural networks for inferring the respiratory flow from a wearable system embedding FBG sensors and inertial units is herein proposed. Different conventional machine learning approaches were implemented as well to ultimately compare the results. The meta-learning algorithm turned out to be the most accurate in predicting respiratory flow when new subjects are considered. Furthermore, the LSTM model memory capability has been proven to be advantageous for capturing relevant aspects of the breathing pattern. The algorithms were tested under different conditions, both static and dynamic, and with more unobtrusive device configurations. The meta-learning results demonstrated that a short one-time calibration may provide subject-specific models which predict the respiratory flow with high accuracy, even when the number of sensors is reduced. Flow RMS errors on the test set ranged from 22.03 L/min, when the minimum number of sensors was considered, to 9.97 L/min for the complete setting (target flow range: 69.231 ± 21.477 L/min). The correlation coefficient r between the target and the predicted flow changed accordingly, being higher (r = 0.9) for the most comprehensive and heterogeneous wearable device configuration. Similar results were achieved even with simpler settings which included the thoracic sensors (r ranging from 0.84 to 0.88; test flow RMSE = 10.99 L/min, when exclusively using the thoracic FBGs). The further estimation of respiratory parameters, i.e., rate and volume, with low errors across different breathing behaviors and postures proved the potential of such approach. These findings lay the foundation for the implementation of reliable custom solutions and more sophisticated artificial intelligence-based algorithms for daily life health-related applications.

Recognition of occupational stressors is a goal of primary importance to improve the psycho-physical health of workers. Many studies agree in considering the respiratory rate (RR) as a key parameter to be monitored since changes from normal physiological ranges can be closely related to states of mental and physical stress. Despite the wide availability of solutions devoted to RR detection, the utilization of light and unobtrusive wearable systems exploiting several sensing technologies is becoming more and more popular in recent years. Among others, fiber Bragg gratings (FBGs) are gaining momentum due to their valuable properties (e.g., lightness, multiplexing capability, high sensitivity etc.) which make them suitable to be integrated into garments and appropriate for RR monitoring purpose. In this work, the feasibility assessment of an FBG-based wearable system for RR detection in a static occupational scenario is presented. A chest strap instrumented with two flexible sensors based on an FBG technology was exploited to perform 40 min of RR tracking on two video terminal workers. The proposed system was able to measure the respiratory signal over a prolonged time and showed high capability to estimate RR when compared to a reference instrument, as evinced by the obtained values of mean absolute error (MAE), always ≤ 1 bpm.

Interest in tactile sensing technologies is advancing due to the growing adoption of robots in daily life activities. Human-machine interaction has thus to be safe, and collaborative robotics is becoming increasingly important. The present work features the design, development and preliminary validation of a soft large area sensor for tactile and proprioceptive sensing in a collaborative robotic manipulator. Such a manipulator is shaped to resemble the human hand and within this paper we focused on the index finger. The finger architecture has a design which allows setting up a structured 3D model, with flexible parametrization and fast prototyping. An optical fiber embedding 12 Fiber Bragg Gratings (FBGs) has been integrated in a soft polymeric matrix to mimic human sense of touch abilities of a whole finger. In order to assess the sensorized robotic manipulator, a mechatronic validation platform has been developed and employed. Preliminary results show a mechanical decoupling between exteroceptive and proprioceptive functions, and among the spatially distributed outputs of the sensor array. These results demonstrate the potential of the proposed approach towards achieving dexterous and fine capabilities in the manipulation of objects.

Safety at work is driving the development of new technological solutions in the era of Industry 4.0. Among others, systems able to monitor physiological parameters are gaining high relevance since such devices have the potential to improve the workers' safety. In this perspective, the respiratory rate can provide useful information since it is sensitive to many environmental stressors. In this study, we focused on the development of a test bench to assess the performance of a wearable system for respiratory monitoring. The presented system achieves data collection and synchronization from FBG sensors, a reference flowmeter and, an M-IMU unit. In addition, a GUI has been developed in order to guide the volunteer in the execution of selected movements during the experimental session. The proposed system could further facilitate the design and development of solutions for assessing wearables for workers' activities monitoring.

The effectiveness of haptic feedback devices highly depends on the perception of tactile stimuli, which differs across body parts and can be affected by movement. In this study, a novel wearable sensory feedback apparatus made of a pair of pressure-sensitive insoles and a belt equipped with vibrotactile units is presented; the device provides time-discrete vibrations around the waist, synchronized with biomechanically-relevant gait events during walking. Experiments with fifteen healthy volunteers were carried out to investigate users' tactile perception on the waist. Stimuli of different intensities were provided at twelve locations, each time synchronously with one pre-defined gait event (i.e. heel strike, flat foot or toe off), following a pseudo-random stimulation sequence. Reaction time, detection rate and localization accuracy were analyzed as functions of the stimulation level and site and the effect of gait events on perception was investigated. Results revealed that above-threshold stimuli (i.e. vibrations characterized by acceleration amplitudes of 1.92g and 2.13g and frequencies of 100 Hz and 150 Hz, respectively) can be effectively perceived in all the sites and successfully localized when the intertactor spacing is set to 10 cm. Moreover, it was found that perception of time-discrete vibrations was not affected by phase-related gating mechanisms, suggesting that the waist could be considered as a preferred body region for delivering haptic feedback during walking.

Deafblind people face remarkable challenges in communicating, because of their severe disability. The only way to interact with other people is the usage of the tactile sign language, which consists in understanding the sign language putting their hands on the signer’s hands. But this approach works only when the signers are in the same place. The aim of this project is to reduce the gap between deafblind people and the other ones, giving them the capability to communicate remotely. By collecting images with two cameras, the signer’s body is tracked with a deep neural network. The extracted coordinates of the body parts (chest, shoulders, elbows, wrists, palms and fingers) are used to move one or more robotic arms. The deafblind person can put his hands on the robots to understand the message delivered by the person on the other side. The entire system is based on a cloud architecture.

Sensory feedback systems can improve gait performance of lower-limb amputees by providing information about the foot-ground interaction force. This study presents a new platform designed to deliver bilateral vibrations on the waist of the user, synchronously with specific gait events. Preliminary perceptual tests were carried out on five healthy subjects to investigate the perception thresholds on the abdominal region. The reaction time and the percentage of correct perceptions were computed to compare three stimulation levels: 50%, 70% and 100% of the maximum vibration amplitude (i.e., 1.5 g, 1.9 g and 2.2 g). The reaction times decreased with higher activation levels. The percentage of correct perceptions was 40% with 50% stimulation level and higher than 97% with 70% and 100% stimulation levels, respectively. The results suggest that vibration amplitudes of 1.9 g provide vibrotactile stimulation that can be effectively perceived during walking, thus used to convey sensory information.