Drinking is an essential activity of daily living (ADL) that is frequently required for a healthy life. Disabled persons however need recurrent assistance from the caregivers to perform such ADL. The existing assistive robots that have been developed to assist in performing ADL require either manual or shared control. There is therefore need for completely autonomous systems that can deal with the existing system limitations. In this paper, a hybrid impedance control-based autonomous robotic system for natural-like drinking assistance for disabled persons is developed. The system comprises of a UR-10 manipulator and a Kinect RGB-D sensor for online detection of the face and mouth along with tracking head pose, cup region of interest recognition and detection of the drink level. A two-stage control strategy is employed; namely, a free-space control to convey an upright oriented cup of drink to the user’s mouth and in-contact compliant control to continuously reorient the cup. Online trajectory replanning is conducted in case of unintentional head and mouth pose changes. A hybrid impedance control is developed to tackle three cases of cup and user’s mouth contact; namely, permissible contact force, contact loss and exceeding the contact force threshold. Simulation results based on co-simulating the manipulator dynamics in ADAMS and MATLAB indicate high performance of the controller in terms of tracking the generated pose and desired force trajectories during the drinking task. The results also indicate that the proposed system can conduct the drinking assistance autonomously.
Traffic accidents are usually unique events with unpredictable geographical and temporal dimensions; thus, accident injury severity level (INJ-SL) analysis presents formidable categorization and data stability problems. Classical statistical models are limited in their ability to correctly model INJ-SL, whilst sophisticated machine learning approaches do not appear to have any equations to prioritize/analyze multiple contributing factors to forecast accidents accompanying INJ-SLs. In addition, the intercorrelations between the input variables may render the conclusions of a formal sensitivity analysis incorrectly. Rear-end collisions are the most common form of traffic accidents; consequently, their linked INJ-SL requires more research. This paper provides a complex technique based on a deep learning paradigm paired with different indicators of Global Sensitivity Analysis to address all of these concerns. Unlike existing neural network designs, this technique presents a deep residual neural network structure that employs residual shortcuts (i.e., connections). The connections enable the DRNNs to sidestep a few levels of the deep network architecture, evading the regular training with high accuracy issues. Using the trained DRNNs model, a Latin Hypercube sampling simulation was undertaken to determine each explanatory component's influence on the resulting INJ-SL. The latest available data from 2011 to 2018 is used to assess all rear-end collisions in North Carolina. A comparison was made between the performance of two different schemes of data categorization using a set of global sensitivity metrics. It was determined that the devised technique overcame the data heterogeneity problems to achieve an accuracy of 87%. In addition, the proposed sensitivity analysis identified the most relevant factors associated with INJ-SL rear-end collisions.
The dynamic modulus (E*) of hot-mix asphalt mixtures is one of the most laborious and time-consuming material parameters to measure in the laboratory. It involves expensive, specialized equipment and expertize that are not readily available in most laboratories. Consequently, several efforts have been devoted to E* prediction models. Unfortunately, developing these prediction models is complex because of the numerous contributory factors and their non-linear influence on E* values. Moreover, such models are not able to prioritize or screen the major factors influencing the E* values. This study presents a new framework for analyzing the dynamic modulus influencing factors by adopting two modeling approaches. First, deep residual neural networks (DRNNs) for non-parametric approaches are used to improve the E* prediction capabilities and derive deep insight into the contributory parameters' effect on the E* value. Second, the well-known Witczak 1–40D prediction equation is used as a representative of the classical statistical modeling approach. In the validation of the models, a comprehensive laboratory database is utilized to account for all significant contributory parameters, such as binder characteristics, volumetric properties, mixture gradation, and testing circumstances parameters. Then, the performance is assessed using typical performance metrics. Lastly, intensive global sensitivity analysis (GSA) is undertaken with the assistance of Latin Hypercube Simulation. Three distinct GSA methods are used to emphasize the influence of each contributory factor on the value of E* in actual practice while reducing the possibility for result distortion owing to correlations between contributory variables. Performance metrics of the DRNNs and the Witczak 1–40D prediction models give the GSA conclusions high credibility. The GSA reveals that, among all possible inputs, the binder content, shear modulus, voids in the mineral aggregates, and temperature are the most significant factors in determining the E* value.
One of the most difficult issues in the design of power ankle-foot prosthetics is to create a control
system that can simulate biological ankle-foot behavior in various operating conditions. The
powered semi-active ankle-foot prosthetic is a complex nonlinear system with high coupling. This
work presents the dynamic model of powered ankle prosthetics. For powered ankle prostheses, a
fuzzy logic- proportional-integral (FL-PI) controller is presented. In the initial stage of control,
two proportional-integral (PI) controllers are designed to regulate motor speed and current,
respectively. In the next stage of control, two FL-PI controllers are designed. The Fuzzy logic
controller is designed to tune online the gains of the PI controller. During a normal walking gait
cycle, FL-PI controllers are used to regulate the specified model under these external disturbances.
The performance of PI controllers and FL-PI controllers are compared during the walking gait
cycle. The results reveal that a powered semi-active ankle-foot prosthetic with a fuzzy logic-PI
controller method outperforms a PI controller alone.
Understanding blood transport in cardiovascular flows is important for managing patients with cardiovascular disease. In this study, three-dimensional Lagrangian coherent structures have been extracted for the first time in both healthy patients and patients with aortic regurgitation. To achieve this, a computationally efficient approach based on Lagrangian descriptors was employed with four-dimensional (4D) magnetic resonance imaging velocity fields. In healthy subjects, Lagrangian coherent structures analysis revealed well-defined mitral jet structures during early filling, directing flow toward ejection during systole. For patients with aortic regurgitation, complex flow structures included interactions between the mitral and regurgitant jets, indicating altered blood transport mechanisms. This study highlights the ability of Lagrangian descriptors to extract coherent structures from patient-specific 4D flow MRI data in a computationally efficient way. It also underscores the importance of extracting three-dimensional Lagrangian coherent structures to gain a better understanding of the complex interaction between the mitral inflow and the regurgitant jet.
