1,721,014 research outputs found
Using a robot calibration approach toward fitting a human arm model
No full textIn the context of Industry 4.0, the human-robot interaction (HRI) can be improved by tracking the human arm in the workspace shared with the robot. This goal takes advantage of a customized human arm modeling and it should be conveniently achieved with a limited number of sensors and a reduced computational time. In this paper, considering the analogy between human and robotic arms, a new method for the identification of a custom-made human arm model was inspired by a robot calibration process. The Denavit-Hartenberg (DH) parameters of the arm model were estimated recording a suitable number of hand poses. Hence, a robotic arm was exploited to test the new method. To simplify the fitting procedure of a reliable robot model, the minimum number of the necessary end-effector (EE) poses was investigated. Through an optoelectronic system, the EE pose trajectory of a UR3 robot was recorded. The optimization of the DH parameters was repeatedly run decreasing the downsampling frequency of the acquired data and then the trajectory error was evaluated. A new reference dataset of robot configurations was acquired permutating the joints degrees of freedom among values of 0, +90, or −90°. Hence, the method to fit the model considering few EE poses was tested on six robot configurations randomly selected from the dataset. Overall, trajectory errors highlighted the applicability of this method in the context of HRI
Recent Advance and Application of Wearable Inertial Sensors in Motion Analysis
Full text linkThe rapid spread of Inertial Measurement Units (IMUs) has revolutionized human motion analysis, providing significant advantages over traditional systems [...]
Wearable MIMUs for the identification of upper limbs motion in an industrial context of human-robot interaction
Full text linkThe automation of human gestures is gaining increasing importance in manufacturing. Indeed, robots support operators by simplifying their tasks in a shared workspace. However, human-robot collaboration can be improved by identifying human actions and then developing adaptive control algorithms for the robot. Accordingly, the aim of this study was to classify industrial tasks based on accelerations signals of human upper limbs. Two magnetic inertial measurement units (MIMUs) on the upper limb of ten healthy young subjects acquired pick and place gestures at three different heights. Peaks were detected from MIMUs accelerations and were adopted to classify gestures through a Linear Discriminant Analysis. The method was applied firstly including two MIMUs and then one at a time. Results demonstrated that the placement of at least one MIMU on the upper arm or forearm is suitable to achieve good recognition performances. Overall, features extracted from MIMUs signals can be used to define and train a prediction algorithm reliable for the context of collaborative robotics
Upper limbs motion tracking for collaborative robotic applications
Full text linkIn the perspective of Industry 4.0, the contemporary presence of workers and robots in the same workspace requires the development of human motion prediction algorithms for a safe and efficient interaction. In this context, the purpose of the present study was to perform an operation of sensor fusion, by creating a collection of spatial and inertial variables of human upper limbs kinematics of typical industrial movements. Spatial and inertial data of ten healthy young subjects performing three pick and place gestures at different heights were measured with a stereophotogrammetric system and Inertial Measurement Units, respectively. Elbow and shoulder angles estimated from both instruments according to a multibody approach showed very similar trends. Moreover, two variables of the database were identified as distinctive features able to differentiate among the three gestures of pick and place
Tilt-Twist Method Using Inertial Sensors to Assess Spinal Posture During Gait
No full textIn the clinical context, the need to estimate spinal posture during gait is constantly growing. The most functional way to achieve this goal is first to model the rachis as a multibody structure with rigid segments and second to apply the tilt-twist method. Inertial Measurement Units (IMUs) are the suitable instrumentation to do this because they are portable, low cost, not invasive and free from laboratory constraints. The aim of this pilot study was the assessment of spinal angles by applying the tilt-twist method to IMUs data. A marker stereo-photogrammetric system (Optitrack) was adopted as gold standard. Three IMUs (MTx Xsens) were positioned on C7, T12 and S1 vertebral levels. A young healthy subject performed a gait trial at a self-selected speed. Data analysis focused on rotation matrices obtained simultaneously from both the instrumentations. Post-processing algorithms identified movement values of flexion-extension and lateral bending from both IMUs and stereo-photogrammetric system. Comparison graph with the obtained angular patterns showed very similar trends for the three spinal segments. Inertial sensors are suitable to be used to assess spinal posture during gait
Multi-segments kinematic model of the human spine during gait
Full text linkThe complex biomechanical structure of the human spine requires a deep investigation to properly describe its physiological function and its kinematic contribution during motion. The computational approach allows the segmentation of the human spine into several rigid bodies connected by 3D joints. Despite the numerous solutions proposed by previous literature studies based on both inertial and stereophotogrammetric systems, the modelling of the human spine is characterized by some limitations such as the lack of standardization. Accordingly, the present preliminary study focused on the development of a multi-segments kinematic model of the human spine and its validation during gait trials. Three-dimensional spinal angular patterns and ranges of motion of one healthy young subject were considered as outcomes of interest. They were obtained by applying the YXZ Euler angles convention to the custom model. First, results were compared with those of the standard Plug-in-Gait full-body model, which segments the human spine into pelvis and trunk segments. Then, outcomes of the multi-segments model were compared with those obtained using the Tilt-Twist method. Overall, results stressed the importance of the spine segmentation, the major angular contributions of spinal regions during gait (Medium-Lumbar segments for lateral bending and flexion-extension, Thoracic-Medium segments for axial rotation), and the reliability of the proposed custom model (differences between Euler angles method and Tilt-Twist method lower than 0.5° in most cases). Future analysis on a larger healthy population and in the clinical context might be implemented to optimize, standardize and validate the proposed human spine model
A constrained-based optimization method for real-time kinematics using magneto-inertial signals: application to upper limb joint angles estimation during prolonged recordings
Full text linkThe work presents a flexible method for the real-time estimation of human joint angles from
magneto-inertial measurement technology. The method aims to enhance the accuracy and consistency of joint angle estimates by incorporating physiological joint limits and task-specific motor characteristics into the optimization process, thanks to a biomechanical model. As an explanatory example, the method was applied to shoulder and elbow joints during a prolonged writing task. The adopted upper limb model was designed following the International Society of Biomechanics guidelines and the Denavit-Hartenberg convention, ensuring anatomical relevance and computational efficiency. By comparing results with stereophotogrammetric tracking outputs, the application of constraints - leveraging a priori knowledge of the
workspace boundaries for joint centers - enhanced the accuracy of shoulder and elbow angle estimations and effectively mitigated the impact of sensor orientation drift over extended periods. This method ensured that joint centers trajectories remain within task-specific workspace limits, thus preventing deviations that are not compatible with the expected kinematic behavior. The percentage reduction in the root mean square average
errors amounted to about 13% in the time intervals when constraints were active, demonstrating the method's effectiveness in reducing the errors. Computationally time-wise, joint angles were estimated with an update period of about 10 ms, allowing real-time usage. The proposed method can be easily generalized to different biomechanical models and to include information from complementary technologies, making it applicable across various contexts such as clinical assessments, rehabilitation, and ergonomics
Detection of upper limb abrupt gestures for human–machine interaction using deep learning techniques
Full text linkIn the manufacturing industry the productivity is contingent on the workers' well-being, with operators at the center of the production process. Moreover, when human-machine interaction occurs, operators' safety is a key requirement. Generally, typical human gestures in manipulation tasks have repetitive kinetics, however external disturbances or environmental factors might provoke abrupt gestures, leading to improper interaction with the machine. The identification and characterization of these abrupt events has not yet been thoroughly studied. Accordingly, the aim of the current research was to define a methodology to ready identify human abrupt movements in a workplace, where manipulation activities are carried out. Five subjects performed three times a set of 30 standard pick-and-place tasks paced at 20 bpm, wearing magneto-inertial measurement units (MIMUs) on their wrists. Random visual and acoustic alarms triggered abrupt movements during standard gestures. The recorded signals were processed by segmenting each pick-and-place cycle. The distinction between standard and abrupt gestures was performed through a recurrent neural network applied to acceleration signals. Four different pre-classification methodologies were implemented to train the neural network and the resulting confusion matrices were compared. The outcomes showed that appropriate preprocessing of the data allows more effective training of the network and shorter classification time, enabling to achieve accuracy greater than 99% and F1-score better than 90%
Gait parameters of elderly subjects in single-task and dual-task with three different MIMU set-ups
Full text linkThe increasing average age of the population emphasizes the strong correlation between cognitive decline and gait disorders of elderly people. Wearable technologies such as magnetic inertial measurement units (MIMUs) have been ascertained as a suitable solution for gait analysis. However, the relationship between human motion and cognitive impairments should still be investigated, considering outcomes of different MIMU set-ups. Accordingly, the aim of the present study was to compare single-task and dual-task walking of an elderly population by using three different MIMU set-ups and correlated algorithms (trunk, shanks, and ankles). Gait sessions of sixteen healthy elderly subjects were registered and spatio-temporal parameters were selected as outcomes of interest. The analysis focused both on the comparison of walking conditions and on the evaluation of differences among MIMU set-ups. Results pointed out the significant effect of cognition on walking speed (p = 0.03) and temporal parameters (p ≤ 0.05), but not on the symmetry of gait. In addition, the comparison among MIMU configurations highlighted a significant difference in the detection of gait stance and swing phases (for shanks-ankles comparison p < 0.001 in both single and dual tasks, for trunk-ankles comparison p < 0.001 in single task and p < 0.01 in dual task). Overall, cognitive impact and MIMU set-ups revealed to be fundamental aspects in the analysis of gait spatio-temporal parameters in a healthy elderly population
- …
