Human Joint Angles Research Articles

A Hybrid Optimization Approach for 3D Multi-Camera Human Pose Estimation

This paper introduces a method for estimating 3D human joint angles using a hybrid optimization approach that integrates particle swarm optimization (PSO) with the steepest descent method for enhanced accuracy in both global and local searches. While advancements in motion capture technologies have made it easier to obtain 2D human joint position data, the accurate estimation of 3D joint angles remains crucial for detailed behavior analysis. Our proposed method first applies PSO to optimize the initial estimation of 3D joint angles from 2D joint positions. We further refine the estimation using the steepest descent method, improving the local search process. The convergence and accuracy of the algorithm are influenced by the grouping strategy in PSO, which is discussed in detail. Experimental results validate the effectiveness of our approach in enhancing the accuracy of 3D human pose estimation.

Development of a High-Precision and Large-Range FBG-Based Sensor Inspired by a Crank-Slider Mechanism for Wearable Measurement of Human Knee Joint Angles

Development of a High-Precision and Large-Range FBG-Based Sensor Inspired by a Crank-Slider Mechanism for Wearable Measurement of Human Knee Joint Angles

Estimation of Lower Limb Joint Angles Using sEMG Signals and RGB-D Camera.

Estimating human joint angles is a crucial task in motion analysis, gesture recognition, and motion intention prediction. This paper presents a novel model-based approach for generating reliable and accurate human joint angle estimation using a dual-branch network. The proposed network leverages combined features derived from encoded sEMG signals and RGB-D image data. To ensure the accuracy and reliability of the estimation algorithm, the proposed network employs a convolutional autoencoder to generate a high-level compression of sEMG features aimed at motion prediction. Considering the variability in the distribution of sEMG signals, the proposed network introduces a vision-based joint regression network to maintain the stability of combined features. Taking into account latency, occlusion, and shading issues with vision data acquisition, the feature fusion network utilizes high-frequency sEMG features as weights for specific features extracted from image data. The proposed method achieves effective human body joint angle estimation for motion analysis and motion intention prediction by mitigating the effects of non-stationary sEMG signals.

Multi-branch deep learning neural network prediction model for the development of angular biosensors based on sEMG.

Human gait motion intention recognition is very important for the lower extremity exoskeleton robot to accurately synchronize and respond to the user's natural motion. And motion intention recognition is generally performed through sEMG. Deep learning neural networks perform well in dealing with high-dimensional data and nonlinear relationships such as sEMG, but different deep learning neural networks have their own advantages in dealing with different types of data. Therefore, a multi-branch deep learning neural network, which enables different neural networks to process different feature items, could achieve more accurate and efficient motion intention recognition. The purpose of this study is to 1) Establish a multi-branch deep learning neural network model to achieve accurate gait recognition and effective estimation of joint angles. 2) Quantify the performance of the multi-branch deep learning neural network model in gait recognition and joint angle prediction using sEMG. This study involved the collection of sEMG and plantar pressure data during walking in human subjects. Firstly, the collected signals are filtered and denoised to ensure the quality and reliability of the data. Calculate the time domain features and the frequency domain features to capture the key information of gait. Then, using the sensitivity difference of different structural neural networks to different feature data, a multi-branch deep learning neural network model is developed, in which the extracted features are used as the input of the model. The output of the model includes gait cycle and joint angle, so as to realize the accurate recognition of human gait and the effective estimation of joint angle. The results show that the proposed method has high accuracy in identifying human gait and estimating joint angles. The multi-branch neural network model successfully integrates time-domain and frequency-domain features and provides reliable prediction of gait cycle and joint angle. The highest accuracy of gait recognition is 95.42%, the lowest is 90.11%, and the average is 92.16%. The average error of joint angle estimation is 3.19. This study designed a human walking gait recognition and joint angle prediction model to achieve accurate human lower limb motion intention recognition.The model can be integrated into the sEMG sensor to design a angular biosensors, which can predict the human joint angle in real time.

Artificial neural network-based control of powered knee exoskeletons for lifting tasks: design and experimental validation

Abstract This study introduces a hybrid model that utilizes a model-based optimization method to generate training data and an artificial neural network (ANN)-based learning method to offer real-time exoskeleton support in lifting activities. For the model-based optimization method, the torque of the knee exoskeleton and the optimal lifting motion are predicted utilizing a two-dimensional (2D) human–exoskeleton model. The control points for exoskeleton motor current profiles and human joint angle profiles from cubic B-spline interpolation represent the design variables. Minimizing the square of the normalized human joint torque is considered as the cost function. Subsequently, the lifting optimization problem is tackled using a sequential quadratic programming (SQP) algorithm in sparse nonlinear optimizer (SNOPT). For the learning-based approach, the learning-based control model is trained using the general regression neural network (GRNN). The anthropometric parameters of the human subjects and lifting boundary postures are used as input parameters, while the control points for exoskeleton torque are treated as output parameters. Once trained, the learning-based control model can provide exoskeleton assistive torque in real time for lifting tasks. Two test subjects’ joint angles and ground reaction forces (GRFs) comparisons are presented between the experimental and simulation results. Furthermore, the utilization of exoskeletons significantly reduces activations of the four knee extensor and flexor muscles compared to lifting without the exoskeletons for both subjects. Overall, the learning-based control method can generate assistive torque profiles in real time and faster than the model-based optimal control approach.

Human-Exoskeleton Coupling Simulation for Lifting Tasks with Shoulder, Spine, and Knee-Joint Powered Exoskeletons.

In this study, we introduce a two-dimensional (2D) human skeletal model coupled with knee, spine, and shoulder exoskeletons. The primary purpose of this model is to predict the optimal lifting motion and provide torque support from the exoskeleton through the utilization of inverse dynamics optimization. The kinematics and dynamics of the human model are expressed using the Denavit-Hartenberg (DH) representation. The lifting optimization formulation integrates the electromechanical dynamics of the DC motors in the exoskeletons of the knee, spine, and shoulder. The design variables for this study include human joint angle profiles and exoskeleton motor current profiles. The optimization objective is to minimize the squared normalized human joint torques, subject to physical and task-specific lifting constraints. We solve this optimization problem using the gradient-based optimizer SNOPT. Our results include a comparison of predicted human joint angle profiles, joint torque profiles, and ground reaction force (GRF) profiles between lifting tasks with and without exoskeleton assistance. We also explore various combinations of exoskeletons for the knee, spine, and shoulder. By resolving the lifting optimization problems, we designed the optimal torques for the exoskeletons located at the knee, spine, and shoulder. It was found that the support from the exoskeletons substantially lowers the torque levels in human joints. Additionally, we conducted experiments only on the knee exoskeleton. Experimental data indicated that using the knee exoskeleton decreases the muscle activation peaks by 35.00%, 10.03%, 22.12%, 30.14%, 16.77%, and 25.71% for muscles of the erector spinae, latissimus dorsi, vastus medialis, vastus lateralis, rectus femoris, and biceps femoris, respectively.

A Highly Durable and UV‐Resistant Graphene‐Based Knitted Textile Sensing Sleeve for Human Joint Angle Monitoring and Gesture Differentiation

Flexible strain sensors based on textiles have attracted extensive attention owing to their light weight, flexibility, and comfort when wearing. However, challenges in integrating textile strain sensors into wearable sensing devices include the need for outstanding sensing performance, long‐term monitoring stability, and fast, convenient integration processes to achieve comprehensive monitoring. The scalable fabrication technique presented here addresses these challenges by incorporating customizable graphene‐based sensing networks into knitted structures, thus creating sensing sleeves for precise motion detection and differentiation. The performance and real‐world application potential of the sensing sleeve are evaluated by its precision in angle estimation and complex joint motion recognition during intra‐ and intersubject studies. For intra‐subject analysis, the sensing sleeve only exhibits a 2.34° angle error in five different knee activities among 20 participants, and the sensing sleeves show up to 94.1% and 96.1% accuracy in the gesture classification of knee and elbow, respectively. For inter‐subject analysis, the sensing sleeve demonstrates a 4.21° angle error, and it shows up to 79.9% and 85.5% accuracy in the gesture classification of knee and elbow, respectively. An activity‐guided user interface compatible with the sensing sleeves for human motion monitoring in home healthcare applications is presented to illustrate the potential applications.

Motion planning framework based on dual-agent DDPG method for dual-arm robots guided by human joint angle constraints.

Reinforcement learning has been widely used in robot motion planning. However, for multi-step complex tasks of dual-arm robots, the trajectory planning method based on reinforcement learning still has some problems, such as ample exploration space, long training time, and uncontrollable training process. Based on the dual-agent depth deterministic strategy gradient (DADDPG) algorithm, this study proposes a motion planning framework constrained by the human joint angle, simultaneously realizing the humanization of learning content and learning style. It quickly plans the coordinated trajectory of dual-arm for complex multi-step tasks. The proposed framework mainly includes two parts: one is the modeling of human joint angle constraints. The joint angle is calculated from the human arm motion data measured by the inertial measurement unit (IMU) by establishing a human-robot dual-arm kinematic mapping model. Then, the joint angle range constraints are extracted from multiple groups of demonstration data and expressed as inequalities. Second, the segmented reward function is designed. The human joint angle constraint guides the exploratory learning process of the reinforcement learning method in the form of step reward. Therefore, the exploration space is reduced, the training speed is accelerated, and the learning process is controllable to a certain extent. The effectiveness of the framework was verified in the gym simulation environment of the Baxter robot's reach-grasp-align task. The results show that in this framework, human experience knowledge has a significant impact on the guidance of learning, and this method can more quickly plan the coordinated trajectory of dual-arm for multi-step tasks.

A Comparative Analysis of Optimal and Biomechanical Torque Control Strategies for Powered Knee Exoskeletons in Squat Lifting

Abstract Exoskeletons have the ability to aid humans in physically demanding and injury-prone activities, such as lifting loads while squatting. However, despite their immense potential, the control of powered exoskeletons remains a persistent challenge. In this study, we first predict the human lifting motion and knee joint torque using an inverse dynamics optimization formulation with a two-dimensional (2D) human skeletal model. The design variables are human joint angle profiles. The normalized human joint torque squared is minimized subject to physical and lifting task constraints. After that, the biomechanical assistive knee exoskeleton torque is obtained by scaling the predicted human knee joint torque. Second, we also present a 2D human skeletal model with a powered knee exoskeleton for predicting the optimal assistive torque and lifting motion. The design variables are human joint angle profiles and exoskeleton motor current profiles. Then, the biomechanical and optimal exoskeleton torques are implemented in a powered knee exoskeleton in real-time to provide external assistance in human lifting motion. Finally, the biomechanical and optimal assistive exoskeleton torque controls for lifting are compared. It is observed that both control methods have a significant impact on reducing muscle activations for the specific muscle groups compared to the cases without the exoskeleton. Especially, peak activations of erector spinae and rectus femoris muscles are reduced by 57.79% and 47.26% with biomechanical assistive torque. Likewise, vastus medialis and vastus lateralis activations drop by 46.82% and 52.24% with optimal assistive torque.

Analysis of the concurrent validity and reliability of five common clinical goniometric devices

Measurement errors play an important role in the development of goniometric equipment, devices used to measure range of motion. Reasonable validity and reliability are critical for both the device and examiner before and after to testing in human subjects. The objective is to evaluate the concurrent validity and reliability of five different clinical goniometric devices for the purpose of establishing an acceptable measurement error margin for a novel device. We explored the validity and inter- and intrarater reliability scores of five goniometric devices namely (i) the universal goniometer (UG), a two-armed hand-held goniometer, (ii) the inclinometer (IC), featuring a single base, fluid level, and gravity-weighted inclinometer, (iii) the digital inclinometer (DI), functioning as both a DI and dynamometer, (iv) the smartphone application (SA), employing gyroscope-based technology within a smartphone platform application and (v) the modified inclinometer (MI), a gravity pendulum-based inclinometer equipped with a specialized fixing apparatus. Measurements were obtained at 12 standard angles and 8 human shoulder flexion angles ranging from 0° to 180°. Over two testing sessions, 120 standardized angle measurements and 160 shoulder angle measurements from 20 shoulders were repetitively taken by three examiners for each device. The intraclass correlation coefficient (ICC), standard error of measurement (SEM), and minimal detectable change (MDC) were calculated to assess reliability and validity. Concurrent validity was also evaluated through the execution of the 95% limit of agreement (95% LOA) and Bland–Altman plots, with comparisons made to the UG. The concurrent validity for all device pairs was excellent in both study phases (ICC > 0.99, 95% LOA − 4.11° to 4.04° for standard angles, and − 10.98° to 11.36° for human joint angles). Inter- and intrarater reliability scores for standard angles were excellent across all devices (ICC > 0.98, SEM 0.59°–1.75°, MDC 1°–4°), with DI showing superior reliability. For human joint angles, device reliability ranged from moderate to excellent (ICC 0.697–0.975, SEM 1.93°–4.64°, MDC 5°–11° for inter-rater reliability; ICC 0.660–0.996, SEM 0.77°–4.06°, MDC 2°–9° for intra-rater reliability), with SA demonstrating superior reliability. Wider angle measurement however resulted in reduced device reliability. In conclusion, our study demonstrates that it is essential to assess measurement errors independently for standard and human joint angles. The DI is the preferred reference for standard angle testing, while the SA is recommended for human joint angle testing. Separate evaluations across the complete 0°–180° range offer valuable insights.

Skin-like and highly elastic optical fiber strain sensor based on a knot-bend shape for human motion monitoring.

A simply designed, highly sensitive, stretchable, compact wearable, and skin-like optical fiber sensing instrument is designed and demonstrated for joint motion monitoring. The fiber sensing scheme comprises only a section of single-mode fiber (SMF) deformed in the knot-like configuration, which performs as a Mach-Zehnder interferometer (MZI) based on a modal coupling mechanism between the core and cladding modes of the deformed SMF section. This proposed optical fiber sensor based on a knot-like configuration is mounted onto wearable woven fabric and then garments on the limbs of a healthy human's body. As the flexion angle of the human limb is varied, the interference fringe coding based on the spectral shift difference of the periodical transmission spectra is perceived. The proposed wearable optical fiber sensor exhibits excellent sensitivities from around -0.431 to -0.614n m/∘ realized for elbow and knee joint flexion between a range of motion around 0°-90°. Additionally, this sensor also displays high repeatability and stability and a fast response time of 1.4ms, combined with a small standard deviation of about 2.585%. The proposed sensor device possesses manufacturing simplicity, high processing accuracy, lightness, and elasticity, as well as certain improvements over other goniometers and optical fiber sensors. These attributes of the proposed sensor prove its applicability for human joint angle monitoring.

SEMG-Based End-to-End Continues Prediction of Human Knee Joint Angles Using the Tightly Coupled Convolutional Transformer Model.

Wearable exoskeleton robots can promote the rehabilitation of patients with physical dysfunction. And improving human-computer interaction performance is a significant challenge for exoskeleton robots. The traditional feature extraction process based on surface Electromyography(sEMG) is complex and requires manual intervention, making real-time performance difficult to guarantee. In this study, we propose an end-to-end method to predict human knee joint angles based on sEMG signals using a tightly coupled convolutional transformer (TCCT) model. We first collected sEMG signals from 5 healthy subjects. Then, the envelope was extracted from the noise-removed sEMG signal and used as the input to the model. Finally, we developed the TCCT model to predict the knee joint angle after 100 ms. For the prediction performance, we used the Root Mean Square Error(RMSE), Pearson Correlation Coefficient(CC), and Adjustment R2 as metrics to evaluate the error between the actual knee angle and the predicted knee angle. The results show that the model can predict the human knee angle quickly and accurately. The mean RMSE, Adjustment R2, and (CC) values of the model are 3.79°, 0.96, and 0.98, respectively, which are better than traditional deep learning models such as Informer (4.14, 0.95, 0.98), CNN (5.56, 0.89, 0.96) and CNN-BiLSTM (3.97, 0.95, 0.98). In addition, the prediction time of our proposed model is only 11.67±0.67 ms, which is less than 100 ms. Therefore, the real-time and accuracy of the model can meet the continuous prediction of human knee joint angle in practice.

Multimodal video and IMU kinematic dataset on daily life activities using affordable devices

Human activity recognition and clinical biomechanics are challenging problems in physical telerehabilitation medicine. However, most publicly available datasets on human body movements cannot be used to study both problems in an out-of-the-lab movement acquisition setting. The objective of the VIDIMU dataset is to pave the way towards affordable patient gross motor tracking solutions for daily life activities recognition and kinematic analysis. The dataset includes 13 activities registered using a commodity camera and five inertial sensors. The video recordings were acquired in 54 subjects, of which 16 also had simultaneous recordings of inertial sensors. The novelty of dataset lies in: (i) the clinical relevance of the chosen movements, (ii) the combined utilization of affordable video and custom sensors, and (iii) the implementation of state-of-the-art tools for multimodal data processing of 3D body pose tracking and motion reconstruction in a musculoskeletal model from inertial data. The validation confirms that a minimally disturbing acquisition protocol, performed according to real-life conditions can provide a comprehensive picture of human joint angles during daily life activities.

A new driving strategy for Lower limb-assisted exoskeleton robot

In this work, a control strategy is developed for a lower limb-assisted exoskeleton. To determine the current motion gait of the human body, the hip and knee joint angles, and plantar pressure values are sensed and analyzed, which are then used to actuate the exoskeleton to provide support for the hip and knee joints. The dual motion systems-the exoskeleton drive system and the human lower limb motion system-are established in this control approach. Without the need to first learn the user's gait, the assistance of the exoskeleton is provided by the motions of the human movement system and is sufficiently flexible to account for changes in step length and walking speed as the user moves through the gait cycle. Throughout this process, the exoskeleton system avoids providing power, providing the freedom to walk and stop in the course of our daily lives.

Chaotic biomedical time signal analysis via wavelet scattering transform

Non-linear techniques are useful to analyze and understand complex systems, especially biological systems. This paper presents a novel procedure to study the dynamics of biomedical signals. The procedure uses features of a wavelet scattering transform to classify signal segments as either chaotic or non-chaotic. To this end, in the paper is also definition of a chaos measure. Classification is made using a model trained on a dataset consisting of signals generated by systems with known characteristics. Using an example PPG signal, this paper demonstrates the usefulness of the wavelet scattering transform for the analysis of biomedical signals, and shows the importance of correctly preparing the training set. Next, the trained models were used for the classification of other biomedical signals. The eye movement signal and the human joint angles data during gait were selected for the tests. The present work is an extended version of the conference paper (Szczęsna et al., 2022). The aim of this extended version is to demonstrate the generality and usefulness of the proposed method of biomedical time series analysis.

Subject specific optimal control of powered knee exoskeleton to assist human lifting tasks under controlled environment

AbstractWearable robots, sometimes known as exoskeletons, are incredible devices for improving human strength, reducing fatigue, and restoring impaired mobility. The control of powered exoskeletons, on the other hand, is still a challenge. This necessitates the development of a technique to simulate exoskeleton–wearer interaction. This study uses a two-dimensional human skeletal model with a powered knee exoskeleton to predict the optimal lifting motion and assistive torque. For lifting motion prediction, an inverse dynamics optimization formulation is utilized. In addition, the electromechanical dynamics of the exoskeleton DC motor are modeled in the lifting optimization formulation. The design variables are human joint angle profiles and exoskeleton motor current profiles. The human joint torque square is minimized subject to physical and lifting task constraints. Then, the lifting optimization problem is solved by the gradient-based sparse nonlinear optimizer (SNOPT). Furthermore, the optimal exoskeleton torque is implemented through a two-phase control strategy to provide optimal assistance in lifting. Experimental validations of the optimal control with 6 Nm and 16 Nm maximum assistive torque are presented. Both 6 Nm and 16 Nm maximum optimal assistance of the exoskeletons reduce the mean values of vastus lateralis, biceps femoris, and latissimus dorsi muscle activations compared to the lifting without the exoskeleton. However, the mean value of the vastus medialis activation is increased by a small amount for the exoskeleton case, although its peak value is reduced. Finally, the experimental results demonstrate that the proposed lifting optimization formulation and control strategy are promising for powered knee exoskeleton for lifting tasks.

Is low-cost motion capture with artificial intelligence applicable for human working posture risk assessment during manual material handling? A pilot study.

Assessing working posture risks is important for occupational safety and health. However, low-cost assessment techniques for human motion injuries in the logistics delivery industry have rarely been reported. To propose a novel approach for posture risk assessment using low-cost motion capture with artificial intelligence. A Kinect was adopted to obtain red-green-blue (RGB) and depth images of the subject with 24 postures, and the human joints were extracted using artificial intelligence. The images were registered to obtain the actual three-dimensional (3D) human joint angle. The root mean square error (RMSE) significantly decreased. Finally, two common methods for evaluating human working posture injuries-the Rapid Upper Limb Assessment and Ovako Working Posture Analysis System-were investigated. The outputs of the proposed method are consistent with those of the commercial ergonomic evaluation software.

Continuous Estimation of Human Joint Angles From sEMG Using a Multi-Feature Temporal Convolutional Attention-Based Network.

Intention recognition based on surface electromyography (sEMG) signals is pivotal in human-machine interaction (HMI), where continuous motion estimation with high accuracy has been the challenge. The convolutional neural network (CNN) possesses excellent feature extraction capability. Still, it is difficult for ordinary CNN to explore the dependencies of time-series data, so most researchers adopt the recurrent neural network or its variants (e.g., LSTM) for motion estimation tasks. This paper proposes a multi-feature temporal convolutional attention-based network (MFTCAN) to recognize joint angles continuously. First, we recruited ten subjects to accomplish the signal acquisition experiments in different motion patterns. Then, we developed a joint training mechanism that integrates MFTCAN with commonly used statistical algorithms, and the integrated architectures were named MFTCAN-KNR, MFTCAN-SVR and MFTCAN-LR. Last, we utilized two performance indicators (RMSE and [Formula: see text]) to evaluate the effect of different methods. Moreover, we further validated the performance of the proposed method on the open dataset (Ninapro DB2). When evaluating on the original dataset, the average RMSE of the estimations obtained by MFTCAN-KNR is 0.14, which is significantly less than the results obtained by LSTM (0.20) and BP (0.21). The average [Formula: see text] of the estimations obtained by MFTCAN-KNR is 0.87, indicating the anti-disturbance ability of the architecture. Moreover, MFTCAN-KNR also achieves high performance when evaluating on the open dataset. The proposed methods can effectively accomplish the task of motion estimation, allowing further implementations in the human-exoskeleton interaction systems.

An electromyography signals-based human-robot collaboration system for human motion intention recognition and realization

• A human-robot collaboration system based on Electromyography (EMG) signals is proposed to learn the position adjustment skills of human body facing the change of external force information, so as to achieve human-robot cooperation. • To improve the recognition accuracy of human motion intention, the coupling effect of human output force and joint angle is considered. • To improve the accuracy and comfort of the collaboration, from the perspective of ergonomics, two evaluation methods of control signal execution efficiency and motion stability are proposed. • A model-free intelligent control mothed is constructed based on DDPG reinforcement learning algorithm, which effectively avoids the selection of control parameters. With the development of manufacturing industry to the directions of personalization and flexibility, the advantages of human-robot collaboration attract more and more attention. In order to enable the robot fully understand human motion intention and play the supervision and guidance role of the human tutor, a human-robot collaboration system based on Electromyography (EMG) signals is proposed. In the investigation, first, aiming at the problems that the coupling effect of output force and joint angle is not considered in the previous research, and the extraction accuracy of force information is poor, the Fast Orthogonal Search (FOS) algorithm is modified to improve the recognition accuracy of motion intention by using the correlation coefficient between the extracted feature signal and the arm output force as the optimization parameter. Moreover, aiming at the problems that the traditional control models cannot balance accurate tracking and comfortable collaboration, and the robot motion stability is poor, two evaluation methods of control signal execution efficiency and motion stability are proposed from the perspective of ergonomics. Afterwards, the human-robot end-to-end collaborative control model based on Deep Deterministic Policy Gradient (DDPG) reinforcement learning algorithm is trained online to improve the accuracy and comfort of the collaboration. As compared with the traditional PD control algorithms based on admittance model, the proposed control method is model-free and intelligent. It effectively avoids the challenge of PD control parameter selection, and behaves good coordination between accurate tracking and comfortable collaboration. Human-robot collaborative sawing experiment shows that the proposed collaboration system can save about 86.2% physical power for the human tutor.

Feasibility of using depth cameras for evaluating human - exoskeleton interaction

With the increased use of exoskeletons in a variety of fields such as industry, military, and health care, there is a need for measurement standards to understand the effects of exoskeletons on human motion. Optical tracking systems (OTS) provide high accuracy human motion tracking, but are expensive, require markers, and constrain the tests to a specified area where the cameras can provide sufficient coverage. This study describes the feasibility of using lower cost, portable, markerless depth camera systems for measuring human and exoskeleton 3-dimensional (3D) joint positions and angles. A human performing a variety of industrial tasks while wearing three different exoskeletons was tracked by both an OTS with modified skeletal models and a depth camera body tracking system. A comparison of the acquired data was then used to facilitate discussions regarding the potential use of depth cameras for exoskeleton evaluation.