Optimal Implant Positioning Following Total Knee Arthroplasty Using Predictive Dynamic Simulation.

In this paper, a novel method is proposed for the determination of the optimal subject-specific placement of knee implants based on predictive dynamic simulations of human movement following total knee arthroplasty (TKA). Two knee implant models are introduced. The first model is a comprehensive 12-degree-of-freedom (DoF) representation that incorporates volumetric contact between femoral and tibial implants, as well as patellofemoral contact. The second model employs a single-degree-of-freedom equivalent kinematic (SEK) approach for the knee joint. A cosimulation framework is proposed to leverage both knee models in our simulations. The knee model is calibrated and validated using patient-specific data, including knee kinematics and ground reaction forces. Additionally, quantitative indices are introduced to evaluate the optimality of implant positioning based on three criteria: balancing medial and lateral load distributions, ligament balancing, and varus/valgus alignment. The knee implant placement is optimized by minimizing the deviation of the indices from their user-defined desired values during predicted sit-to-stand motion. The method presented in this paper has the potential to enhance the results of knee arthroplasty and serve as a valuable instrument for surgeons when planning and performing this procedure.

General Muscle Torque Generator Model for a Two Degree-of-Freedom Shoulder Joint.

Muscle torque generators (MTGs) have been developed as an alternative to muscle-force models, reducing the muscle-force model complexity to a single torque at the joint. Current MTGs can only be applied to single Degree-of-freedom (DoF) joints, leading to complications in modeling joints with multiple-DoFs such as the shoulder. This study aimed to develop an MTG model that accounts for the coupling between 2-DoF at the shoulder joint: shoulder plane of elevation (horizontal abduction/adduction) and shoulder elevation (flexion/extension). Three different 2-DoF MTG equations were developed to model the coupling between these two movements. Net joint torques at the shoulder were determined for 20 participants (10 females and 10 males) in isometric, isokinetic, and passive tests. Curve and surface polynomial fitting were used to find the best general fit for the experimental data in terms of the different degrees of coupling. The models were validated against experimental isokinetic torque data. It was determined that implicit coupling that used interpolation between single-DoF MTGs resulted in the lowest root-mean-square percent error of 8.5%. The work demonstrated that general MTG models can predict torque results that are dependent on multiple-DoFs of the shoulder.

Experimental Study of Fully Passive, Fully Active, and Active-Passive Upper-Limb Exoskeleton Efficiency: An Assessment of Lifting Tasks.

Recently, robotic exoskeletons are gaining attention for assisting industrial workers. The exoskeleton power source ranges from fully passive (FP) to fully active (FA), or a mixture of both. The objective of this experimental study was to assess the efficiency of a new active-passive (AP) shoulder exoskeleton using statistical analyses of 11 quantitative measures from surface electromyography (sEMG) and kinematic data and a user survey for weight lifting tasks. Two groups of females and males lifted heavy kettlebells, while a shoulder exoskeleton helped them in modes of fully passive (FP), fully active (FA), and active-passive (AP). The AP exoskeleton outperformed the FP and FA exoskeletons because the participants could hold the weighted object for nearly twice as long before fatigue occurred. Future developments should concentrate on developing sex-specific controllers as well as on better-fitting wearable devices for women.

Model-Based Acetabular Cup Orientation Optimization Based on Minimizing the Risk of Edge-Loading and Implant Impingement Following Total Hip Arthroplasty.

In this paper, a computationally efficient model-based method for determining patient-specific optimal acetabular cup alignment for total hip arthroplasty (THA) is presented. The proposed algorithm minimizes the risk of implant impingement and edge-loading, which are reported as the major causes of hip dislocation following THA. First, by using motion capture data recorded from the patient performing different daily activities, the hip contact force and the relative orientation of the femur and pelvis are calculated by a musculoskeletal model. Then, by defining two quantitative indices, i.e., angular impingement distance and angular edge-loading distance (AED), the risk of impingement and edge-loading are assessed for a wide range of cup alignments. Finally, three optimization criteria are introduced to estimate the optimal cup alignment with a tradeoff between the risk of impingement and edge loading. The results show that patient-specific characteristics such as pelvic tilt could significantly change the optimal cup alignment, especially the value of cup anteversion. Therefore, in some cases, the well-known Lewinnek safe zone may not be optimal, or even safe. Unlike other dynamic model-based methods, in this work, the need for force plate measurements is eliminated by estimating the ground reaction forces and moments, which makes this method more practical and cost-efficient. Furthermore, the low computational complexity due to analytical formulas makes this method suitable for both pre-operative and intra-operative planning.

Baseball Pitching Arm Three-Dimensional Inertial Parameter Calculations From Body Composition Imaging and a Novel Overweight Measure for Youth Pitching Arm Kinetics.

Many baseball pitching studies have used inverse dynamics to assess throwing arm kinetics as high and repetitive kinetics are thought to be linked to pitching injuries. However, prior studies have not used participant-specific body segment inertial parameters (BSIPs), which are thought to improve analysis of high-acceleration motions and overweight participants. This study's objectives were to (1) calculate participant-specific BSIPs using dual energy X-ray absorptiometry (DXA) measures, (2) compare inverse dynamic calculations of kinetics determined by DXA-calculated BSIPs (full DXA-driven inverse dynamics) against kinetics using the standard inverse dynamics approach with scaled BSIPs (scaled inverse dynamics), and (3) examine associations between full DXA-driven kinetics and overweight indices: body mass index (BMI) and segment mass index (SMI). Eighteen participants (10-11 years old) threw 10 fastballs that were recorded for motion analysis. DXA scans were used to calculate participant-specific BSIPs (mass, center of mass, radii of gyration) for each pitching arm segment (upper arm, forearm, hand), BMI, and SMI. The hypotheses were addressed with t-tests and linear regression analyses. The major results were that (1) DXA-calculated BSIPs differed from scaled BSIPs for each pitching arm segment; (2) calculations for shoulder, but not elbow, kinetics differed between the full DXA-driven and scaled inverse dynamics analyses; and (3) full DXA-driven inverse dynamics calculations for shoulder kinetics were more often associated with SMI than BMI. Results suggest that using participant-specific BSIPs and pitching arm, SMIs may improve evidence-based injury prevention guidelines for youth pitchers.

Predictive Forward Dynamic Simulation of Manual Wheelchair Propulsion on a Rolling Dynamometer.

Research studies to understand the biomechanics of manual wheelchair propulsion often incorporate experimental data and mathematical models. This project aimed to advance this field of study by developing a two-dimensional (2D) model to generate first of its kind forward dynamic fully predictive computer simulations of a wheelchair basketball athlete on a stationary ergometer. Subject-specific parameters and torque generator functions were implemented in the model from dual X-ray absorptiometry and human dynamometer measurements. A direct collocation optimization method was used in a wheelchair propulsion model for the first time to replicate the human muscle recruitment strategy. Simulations were generated for varying time constraints and seat positions. Similar magnitudes of kinematic and kinetic data were observed between simulation and experimental data of a first push. Furthermore, seat heights inferior to the neutral position were found to produce similar joint torques to those reported in previous studies. An anterior seat placement produced the quickest push time with the least amount of shoulder torque required. The work completed in this project demonstrates that fully predictive simulations of wheelchair propulsion have the potential of varying simulation parameters to draw meaningful conclusions.

A Synergy-Based Motor Control Framework for the Fast Feedback Control of Musculoskeletal Systems.

This paper presents a computational framework for the fast feedback control of musculoskeletal systems using muscle synergies. The proposed motor control framework has a hierarchical structure. A feedback controller at the higher level of hierarchy handles the trajectory planning and error compensation in the task space. This high-level task space controller only deals with the task-related kinematic variables, and thus is computationally efficient. The output of the task space controller is a force vector in the task space, which is fed to the low-level controller to be translated into muscle activity commands. Muscle synergies are employed to make this force-to-activation (F2A) mapping computationally efficient. The explicit relationship between the muscle synergies and task space forces allows for the fast estimation of muscle activations that result in the reference force. The synergy-enabled F2A mapping replaces a computationally heavy nonlinear optimization process by a vector decomposition problem that is solvable in real time. The estimation performance of the F2A mapping is evaluated by comparing the F2A-estimated muscle activities against the measured electromyography (EMG) data. The results show that the F2A algorithm can estimate the muscle activations using only the task-related kinematics/dynamics information with ∼70% accuracy. An example predictive simulation is also presented, and the results show that this feedback motor control framework can control arbitrary movements of a three-dimensional (3D) musculoskeletal arm model quickly and near optimally. It is two orders-of-magnitude faster than the optimal controller, with only 12% increase in muscle activities compared to the optimal. The developed motor control model can be used for real-time near-optimal predictive control of musculoskeletal system dynamics.

Constrained Dynamic Optimization of Sit-to-Stand Motion Driven by Bézier Curves.

The purpose of this work is twofold: first, to synthesize a motion pattern imitating sit-to-stand (STS) and second, to compare the kinematics and dynamics of the resulting motion to healthy STS. Predicting STS in simulation inspired the creation of three models: a biomechanical model, a motion model, and performance criteria as a model of preference. First, the human is represented as three rigid links in the sagittal plane. This model captures aspects of joint, foot, and buttocks physiology, which makes it the most comprehensive planar model for predicting STS to date. Second, candidate STS trajectories are described geometrically by a set of Bézier curves which seem well suited to predictive biomechanical simulations. Third, with the assumption that healthy people naturally prioritize mechanical efficiency, disinclination to a motion is described as a cost function of joint torques, and for the first time, physical infeasibility including slipping and falling. This new dynamic optimization routine allows for motions of gradually increasing complexity while the model's performance is improving. Using these models and optimal control strategy together has produced gross motion patterns characteristic of healthy STS when compared with normative data from the literature.

Inverse Dynamics Modeling of Paralympic Wheelchair Curling.

Paralympic wheelchair curling is an adapted version of Olympic curling played by individuals with spinal cord injuries, cerebral palsy, multiple sclerosis, and lower extremity amputations. To the best of the authors' knowledge, there has been no experimental or computational research published regarding the biomechanics of wheelchair curling. Accordingly, the objective of the present research was to quantify the angular joint kinematics and dynamics of a Paralympic wheelchair curler throughout the delivery. The angular joint kinematics of the upper extremity were experimentally measured using an inertial measurement unit system; the translational kinematics of the curling stone were additionally evaluated with optical motion capture. The experimental kinematics were mathematically optimized to satisfy the kinematic constraints of a subject-specific multibody biomechanical model. The optimized kinematics were subsequently used to compute the resultant joint moments via inverse dynamics analysis. The main biomechanical demands throughout the delivery (ie, in terms of both kinematic and dynamic variables) were about the hip and shoulder joints, followed sequentially by the elbow and wrist. The implications of these findings are discussed in relation to wheelchair curling delivery technique, musculoskeletal modeling, and forward dynamic simulations.

Scalable musculoskeletal model for dynamic simulations of lower body movement.

A musculoskeletal (MSK) model is an important tool for analysing human motions, calculating joint torques during movement, enhancing sports activity, and developing exoskeletons and prostheses. To enable biomechanical investigation of human motion, this work presents an open-source lower body MSK model. The MSK model of the lower body consists of 7 body segments (pelvis, left/right thigh, left/right leg, and left/right foot). The model has 20 degrees of freedom (DoFs) and 28 muscle torque generators (MTGs), which are developed from experimental data. The model can be modified for different anthropometric measurements and subject body characteristics, including sex, age, body mass, height, physical activity, and skin temperature. The model is validated by simulating the torque within the range of motion (ROM) of isolated movements; all simulation findings exhibit a good level of agreement with the literature.

Scalable musculoskeletal model for dynamic simulations of upper body movement.

A musculoskeletal (MSK) model is a valuable tool for assessing complex biomechanical problems, estimating joint torques during motion, optimizing motion in sports, and designing exoskeletons and prostheses. This study proposes an open-source upper body MSK model that supports biomechanical analysis of human motion. The MSK model of the upper body consists of 8 body segments (torso, head, left/right upper arm, left/right forearm, and left/right hand). The model has 20 degrees of freedom (DoFs) and 40 muscle torque generators (MTGs), which are constructed using experimental data. The model is adjustable for different anthropometric measurements and subject body characteristics: sex, age, body mass, height, dominant side, and physical activity. Joint limits are modeled using experimental dynamometer data within the proposed multi-DoF MTG model. The model equations are verified by simulating the joint range of motion (ROM) and torque; all simulation results have a good agreement with previously published research.

Landet: an efficient physics-informed deep learning approach for automatic detection of anatomical landmarks and measurement of spinopelvic alignment.

PURPOSE: An efficient physics-informed deep learning approach for extracting spinopelvic measures from X-ray images is introduced and its performance is evaluated against manual annotations. METHODS: Two datasets, comprising a total of 1470 images, were collected to evaluate the model's performance. We propose a novel method of detecting landmarks as objects, incorporating their relationships as constraints (LanDet). Using this approach, we trained our deep learning model to extract five spine and pelvis measures: Sacrum Slope (SS), Pelvic Tilt (PT), Pelvic Incidence (PI), Lumbar Lordosis (LL), and Sagittal Vertical Axis (SVA). The results were compared to manually labelled test dataset (GT) as well as measures annotated separately by three surgeons. RESULTS: The LanDet model was evaluated on the two datasets separately and on an extended dataset combining both. The final accuracy for each measure is reported in terms of Mean Absolute Error (MAE), Standard Deviation (SD), and R Pearson correlation coefficient as follows: [ S S ∘ : 3.7 ( 2.7 ) , R = 0.89 ] , [ P T ∘ : 1.3 ( 1.1 ) , R = 0.98 ] , [ P I ∘ : 4.2 ( 3.1 ) , R = 0.93 ] , [ L L ∘ : 5.1 ( 6.4 ) , R = 0.83 ] , [ S V A ( m m ) : 2.1 ( 1.9 ) , R = 0.96 ] . To assess model reliability and compare it against surgeons, the intraclass correlation coefficient (ICC) metric is used. The model demonstrated better consistency with surgeons with all values over 0.88 compared to what was previously reported in the literature. CONCLUSION: The LanDet model exhibits competitive performance compared to existing literature. The effectiveness of the physics-informed constraint method, utilized in our landmark detection as object algorithm, is highlighted. Furthermore, we addressed the limitations of heatmap-based methods for anatomical landmark detection and tackled issues related to mis-identifying of similar or adjacent landmarks instead of intended landmark using this novel approach.

Evaluation of a machine-learning-driven active-passive upper-limb exoskeleton robot: Experimental human-in-the-loop study.

Evaluating exoskeleton actuation methods and designing an effective controller for these exoskeletons are both challenging and time-consuming tasks. This is largely due to the complicated human-robot interactions, the selection of sensors and actuators, electrical/command connection issues, and communication delays. In this research, a test framework for evaluating a new active-passive shoulder exoskeleton was developed, and a surface electromyography (sEMG)-based human-robot cooperative control method was created to execute the wearer's movement intentions. The hierarchical control used sEMG-based intention estimation, mid-level strength regulation, and low-level actuator control. It was then applied to shoulder joint elevation experiments to verify the exoskeleton controller's effectiveness. The active-passive assistance was compared with fully passive and fully active exoskeleton control using the following criteria: (1) post-test survey, (2) load tolerance duration, and (3) computed human torque, power, and metabolic energy expenditure using sEMG signals and inverse dynamic simulation. The experimental outcomes showed that active-passive exoskeletons required less muscular activation torque (50%) from the user and reduced fatigue duration indicators by a factor of 3, compared to fully passive ones.

Model-Based Mid-Level Regulation for Assist-As-Needed Hierarchical Control of Wearable Robots: A Computational Study of Human-Robot Adaptation.

The closed-loop human-robot system requires developing an effective robotic controller that considers models of both the human and the robot, as well as human adaptation to the robot. This paper develops a mid-level controller providing assist-as-needed (AAN) policies in a hierarchical control setting using two novel methods: model-based and fuzzy logic rule. The goal of AAN is to provide the required extra torque because of the robot's dynamics and external load compared to the human limb free movement. The human-robot adaptation is simulated using a nonlinear model predictive controller (NMPC) as the human central nervous system (CNS) for three conditions of initial (the initial session of wearing the robot, without any previous experience), short-term (the entire first session, e.g., 45 min), and long-term experiences. The results showed that the two methods (model-based and fuzzy logic) outperform the traditional proportional method in providing AAN by considering distinctive human and robot models. Additionally, the CNS actuator model has difficulty in the initial experience and activates both antagonist and agonist muscles to reduce movement oscillations. In the long-term experience, the simulation shows no oscillation when the CNS NMPC learns the robot model and modifies its weights to simulate realistic human behavior. We found that the desired strength of the robot should be increased gradually to ignore unexpected human-robot interactions (e.g., robot vibration, human spasticity). The proposed mid-level controllers can be used for wearable assistive devices, exoskeletons, and rehabilitation robots.

Simulating Human Upper and Lower Limb Balance Recovery Responses Using Nonlinear Model Predictive Control.

The ability to generate predictive dynamic simulations of human movement using optimal control has been a growing point of interest in the design of medical/assistive devices, e.g. robotic exoskeletons. Despite this, many disseminated simulations of whole-body tasks, such as balance recovery, neglect the role of the upper body instead focusing on postural joints, e.g. ankle, knees, hips. Thus, the purpose of the current study was to use a novel nonlinear model predictive control (NMPC) approach to assess how actuated upper limbs, as well as different individual performance (optimality) criteria, can shape simulated reactive balance recovery responses. A sagittal biomechanical model of a young adult standing was designed and actuated via nonlinear muscle torque generators (rotational single-muscle equivalents). Forward dynamic simulations of balance recovery (NMPCdriven) following an unexpected support-surface perturbation were generated for each unique combination of selected performance criteria (6 total), perturbation direction (forward and backward), and arm joints free/locked. The observed joint trajectories provide insight into the emergence of human elements of postural control from individual optimality criteria, e.g. hip-ankle strategies emerge from single-joint regulation. Quantitative analysis of performance improvements with the arms free suggest that whether arm responses emerge in the simulations may be dependent on the problem's initial guess. Future work should focus on testing further performance criteria and improving NMPC as a model of the nervous system.

Assistive Sliding Mode Control of a Rehabilitation Robot with Automatic Weight Adjustment.

There are approximately 13 million new stroke cases worldwide each year. Research has shown that robotics can provide practical and efficient solutions for expediting post-stroke patient recovery. This simulation study aimed to design a sliding mode controller (SMC) for an end-effector-based rehabilitation robot. A genetic algorithm (GA) was designed for automatic controller weight adjustment. The optimal weights were obtained by minimizing a cost function comprising the end-effector position error, robot input, robot input-rate, and patient input. To promote safe tuner optimization, a model of the human arm was incorporated to generate the human joint torque. A computed-torque proportional derivative controller (CTPD) was designed for the human arm to approximate the central nervous system (CNS) motor control. This controller was adjusted to simulate rehabilitation effects and patient adaptation. The tuner was optimized for a trajectory tracking task with an assistive high-level control scheme. The simulation results showed lower cost compared to seven manual weight settings. The optimal weights provided good tracking performance and suitable robot inputs. This research provides a framework to conduct various simulations before testing our controller on human subjects. The preliminary results of this study will be used as the starting point for online adaptive controller tuning, which will be examined in our future research.

Computer Vision and Deep Learning for Environment-Adaptive Control of Robotic Lower-Limb Exoskeletons.

Robotic exoskeletons require human control and decision making to switch between different locomotion modes, which can be inconvenient and cognitively demanding. To support the development of automated locomotion mode recognition systems (i.e., intelligent high-level controllers), we designed an environment recognition system using computer vision and deep learning. Here we first reviewed the development of the "ExoNet" database - the largest and most diverse open-source dataset of wearable camera images of indoor and outdoor real-world walking environments, which were annotated using a hierarchical labelling architecture. We then trained and tested the EfficientNetB0 convolutional neural network, which was optimized for efficiency using neural architecture search, to forward predict the walking environments. Our environment recognition system achieved ~73% image classification accuracy. These results provide the inaugural benchmark performance on the ExoNet database. Future research should evaluate and compare different convolutional neural networks to develop an accurate and real- time environment-adaptive locomotion mode recognition system for robotic exoskeleton control.

Environment Classification for Robotic Leg Prostheses and Exoskeletons Using Deep Convolutional Neural Networks.

Robotic leg prostheses and exoskeletons can provide powered locomotor assistance to older adults and/or persons with physical disabilities. However, the current locomotion mode recognition systems being developed for automated high-level control and decision-making rely on mechanical, inertial, and/or neuromuscular sensors, which inherently have limited prediction horizons (i.e., analogous to walking blindfolded). Inspired by the human vision-locomotor control system, we developed an environment classification system powered by computer vision and deep learning to predict the oncoming walking environments prior to physical interaction, therein allowing for more accurate and robust high-level control decisions. In this study, we first reviewed the development of our "ExoNet" database-the largest and most diverse open-source dataset of wearable camera images of indoor and outdoor real-world walking environments, which were annotated using a hierarchical labeling architecture. We then trained and tested over a dozen state-of-the-art deep convolutional neural networks (CNNs) on the ExoNet database for image classification and automatic feature engineering, including: EfficientNetB0, InceptionV3, MobileNet, MobileNetV2, VGG16, VGG19, Xception, ResNet50, ResNet101, ResNet152, DenseNet121, DenseNet169, and DenseNet201. Finally, we quantitatively compared the benchmarked CNN architectures and their environment classification predictions using an operational metric called "NetScore," which balances the image classification accuracy with the computational and memory storage requirements (i.e., important for onboard real-time inference with mobile computing devices). Our comparative analyses showed that the EfficientNetB0 network achieves the highest test accuracy; VGG16 the fastest inference time; and MobileNetV2 the best NetScore, which can inform the optimal architecture design or selection depending on the desired performance. Overall, this study provides a large-scale benchmark and reference for next-generation environment classification systems for robotic leg prostheses and exoskeletons.

InverseMuscleNET: Alternative Machine Learning Solution to Static Optimization and Inverse Muscle Modeling.

InverseMuscleNET, a machine learning model, is proposed as an alternative to static optimization for resolving the redundancy issue in inverse muscle models. A recurrent neural network (RNN) was optimally configured, trained, and tested to estimate the pattern of muscle activation signals. Five biomechanical variables (joint angle, joint velocity, joint acceleration, joint torque, and activation torque) were used as inputs to the RNN. A set of surface electromyography (EMG) signals, experimentally measured around the shoulder joint for flexion/extension, were used to train and validate the RNN model. The obtained machine learning model yields a normalized regression in the range of 88-91% between experimental data and estimated muscle activation. A sequential backward selection algorithm was used as a sensitivity analysis to discover the less dominant inputs. The order of most essential signals to least dominant ones was as follows: joint angle, activation torque, joint torque, joint velocity, and joint acceleration. The RNN model required 0.06 s of the previous biomechanical input signals and 0.01 s of the predicted feedback EMG signals, demonstrating the dynamic temporal relationships of the muscle activation profiles. The proposed approach permits a fast and direct estimation ability instead of iterative solutions for the inverse muscle model. It raises the possibility of integrating such a model in a real-time device for functional rehabilitation and sports evaluation devices with real-time estimation and tracking. This method provides clinicians with a means of estimating EMG activity without an invasive electrode setup.

MuscleNET: mapping electromyography to kinematic and dynamic biomechanical variables by machine learning.

Objective.This paper proposes machine learning models for mapping surface electromyography (sEMG) signals to regression of joint angle, joint velocity, joint acceleration, joint torque, and activation torque.Approach.The regression models, collectively known as MuscleNET, take one of four forms: ANN (forward artificial neural network), RNN (recurrent neural network), CNN (convolutional neural network), and RCNN (recurrent convolutional neural network). Inspired by conventional biomechanical muscle models, delayed kinematic signals were used along with sEMG signals as the machine learning model's input; specifically, the CNN and RCNN were modeled with novel configurations for these input conditions. The models' inputs contain either raw or filtered sEMG signals, which allowed evaluation of the filtering capabilities of the models. The models were trained using human experimental data and evaluated with different individual data.Main results.Results were compared in terms of regression error (using the root-mean-square) and model computation delay. The results indicate that the RNN (with filtered sEMG signals) and RCNN (with raw sEMG signals) models, both with delayed kinematic data, can extract underlying motor control information (such as joint activation torque or joint angle) from sEMG signals in pick-and-place tasks. The CNNs and RCNNs were able to filter raw sEMG signals.Significance.All forms of MuscleNET were found to map sEMG signals within 2 ms, fast enough for real-time applications such as the control of exoskeletons or active prostheses. The RNN model with filtered sEMG and delayed kinematic signals is particularly appropriate for applications in musculoskeletal simulation and biomechatronic device control.