Inertial Measurement Unit Sensor Research Articles

Data-Driven Diagnosis of Multicopter Thrust Fault Using Supervised Learning with Inertial Sensors

This study proposes a data-driven fault diagnosis for multicopter unmanned aerial vehicles that uses the principal direction vector of inertial measurement unit (IMU) sensor signals calculated by principal component analysis. The main idea comes from the fact that a normal sphere-shaped distribution of the sensor data changes to a specific elliptical shape under a certain thrust fault situation. The fault diagnosis is based on classification and regression using supervised learning with the gyroscope and accelerometer datasets of an IMU. We analyze the performance of the proposed approach by depending on different learning algorithms. To verify the diagnostic performance, ground experiments with a hexacopter on the gimbaled jig are performed for various cases of damaged propellers. Then, the applicability of the proposed data-driven fault diagnosis is confirmed by analyzing the accuracy of the fault’s location and degree.

An optimized deep learning model for human activity recognition using inertial measurement units

AbstractHuman activity recognition (HAR) has recently gained popularity due to its applications in healthcare, surveillance, human‐robot interaction, and various other fields. Deep learning (DL)‐based models have been successfully applied to the raw data captured through inertial measurement unit (IMU) sensors to recognize multiple human activities. Despite the success of DL‐based models in human activity recognition, feature extraction remains challenging due to class imbalance and noisy data. Additionally, selecting optimal hyperparameter values for DL models is essential since they affect model performance. The hyperparameter values of some of the existing DL‐based HAR models are chosen randomly or through the trial‐and‐error method. The random selection of these significant hyperparameters may be suitable for some applications, but sometimes it may worsen the model's performance in others. Hence, to address the above‐mentioned issues, this research aims to develop an optimized DL model capable of recognizing various human activities captured through IMU sensors. The proposed DL‐based HAR model combines convolutional neural network (CNN) layers and bidirectional long short‐term memory (Bi‐LSTM) units to simultaneously extract spatial and temporal sequence features from raw sensor data. The Rao‐3 metaheuristic optimization algorithm has been adopted to identify the ideal hyperparameter values for the proposed DL model in order to enhance its recognition performance. The proposed DL model's performance is validated on PAMAP2, UCI‐HAR, and MHEALTH datasets and achieved 94.91%, 97.16%, and 99.25% accuracies, respectively. The results reveal that the proposed DL model performs better than the existing state‐of‐the‐art (SoTA) models.

A Hybrid Human Activity Recognition Method Using an MLP Neural Network and Euler Angle Extraction Based on IMU Sensors

Inertial measurement unit (IMU) technology has gained popularity in human activity recognition (HAR) due to its ability to identify human activity by measuring acceleration, angular velocity, and magnetic flux in key body areas like the wrist and knee. It has propelled the extensive application of HAR across various domains. In the healthcare sector, HAR finds utility in monitoring and assessing movements during rehabilitation processes, while in the sports science field, it contributes to enhancing training outcomes and preventing exercise-related injuries. However, traditional sensor fusion algorithms often require intricate mathematical and statistical processing, resulting in higher algorithmic complexity. Additionally, in dynamic environments, sensor states may undergo changes, posing challenges for real-time adjustments within conventional fusion algorithms to cater to the requirements of prolonged observations. To address these limitations, we propose a novel hybrid human pose recognition method based on IMU sensors. The proposed method initially calculates Euler angles and subsequently refines them using magnetometer and gyroscope data to obtain the accurate attitude angle. Furthermore, the application of FFT (Fast Fourier Transform) feature extraction facilitates the transition of the signal from its time-based representation to its frequency-based representation, enhancing the practical significance of the data. To optimize feature fusion and information exchange, a group attention module is introduced, leveraging the capabilities of a Multi-Layer Perceptron which is called the Feature Fusion Enrichment Multi-Layer Perceptron (GAM-MLP) to effectively combine features and generate precise classification results. Experimental results demonstrated the superior performance of the proposed method, achieving an impressive accuracy rate of 96.13% across 19 different human pose recognition tasks. The proposed hybrid human pose recognition method is capable of meeting the demands of real-world motion monitoring and health assessment.

Characterizing Bodyweight-Supported Treadmill Walking on Land and Underwater Using Foot-Worn Inertial Measurement Units and Machine Learning for Gait Event Detection.

Gait rehabilitation commonly relies on bodyweight unloading mechanisms, such as overhead mechanical support and underwater buoyancy. Lightweight and wireless inertial measurement unit (IMU) sensors provide a cost-effective tool for quantifying body segment motions without the need for video recordings or ground reaction force measures. Identifying the instant when the foot contacts and leaves the ground from IMU data can be challenging, often requiring scrupulous parameter selection and researcher supervision. We aimed to assess the use of machine learning methods for gait event detection based on features from foot segment rotational velocity using foot-worn IMU sensors during bodyweight-supported treadmill walking on land and underwater. Twelve healthy subjects completed on-land treadmill walking with overhead mechanical bodyweight support, and three subjects completed underwater treadmill walking. We placed IMU sensors on the foot and recorded motion capture and ground reaction force data on land and recorded IMU sensor data from wireless foot pressure insoles underwater. To detect gait events based on IMU data features, we used random forest machine learning classification. We achieved high gait event detection accuracy (95-96%) during on-land bodyweight-supported treadmill walking across a range of gait speeds and bodyweight support levels. Due to biomechanical changes during underwater treadmill walking compared to on land, accurate underwater gait event detection required specific underwater training data. Using single-axis IMU data and machine learning classification, we were able to effectively identify gait events during bodyweight-supported treadmill walking on land and underwater. Robust and automated gait event detection methods can enable advances in gait rehabilitation.

Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction.

This paper proposes a novel approach to tackle the human activity recognition (HAR) problem. Four classes of body movement datasets, namely stand-up, sit-down, run, and walk, are applied to perform HAR. Instead of using vision-based solutions, we address the HAR challenge by implementing a real-time HAR system architecture with a wearable inertial measurement unit (IMU) sensor, which aims to achieve networked sensing and data sampling of human activity, data pre-processing and feature analysis, data generation and correction, and activity classification using hybrid learning models. Referring to the experimental results, the proposed system selects the pre-trained eXtreme Gradient Boosting (XGBoost) model and the Convolutional Variational Autoencoder (CVAE) model as the classifier and generator, respectively, with 96.03% classification accuracy.

Blood Pressure Measurement Based on the Camera and Inertial Measurement Unit of a Smartphone: Instrument Validation Study.

Even though several mobile apps that can measure blood pressure have been developed, the data about the accuracy of these apps are limited. We assessed the accuracy of AlwaysBP (test) in blood pressure measurement compared with the standard, cuff-based, manual method of brachial blood pressure measurement (reference). AlwaysBP is a smartphone software that estimates systolic blood pressure (SBP) and diastolic blood pressure (DBP) based on pulse transit time (PTT). PTT was calculated with a finger photoplethysmogram and seismocardiogram using, respectively, the camera and inertial measurement unit sensor of a commercially available smartphone. After calculating PTT, SBP and DBP were estimated via the Bramwell-Hill and Moens-Korteweg equations. A calibration process was carried out 3 times for each participant to determine the input parameters of the equations. This study was conducted from March to August 2021 at Chungnam National University Sejong Hospital with 87 participants aged between 19 and 70 years who met specific conditions. The primary analysis aimed to evaluate the accuracy of the test method compared with the reference method for the entire study population. The secondary analysis was performed to confirm the stability of the test method for up to 4 weeks in 15 participants. At enrollment, gender, arm circumference, and blood pressure distribution were considered according to current guidelines. Among the 87 study participants, 45 (52%) individuals were male, and the average age was 35.6 (SD 10.4) years. Hypertension was diagnosed in 14 (16%) participants before this study. The mean test and reference SBPs were 120.0 (SD 18.8) and 118.7 (SD 20.2) mm Hg, respectively (difference: mean 1.2, SD 7.1 mm Hg). The absolute differences between the test and reference SBPs were <5, <10, and <15 mm Hg in 57.5% (150/261), 84.3% (220/261 ), and 94.6% (247/261) of measurements. The mean test and reference DBPs were 80.1 (SD 12.6) and 81.1 (SD 14.4) mm Hg, respectively (difference: mean -1.0, SD 6.0 mm Hg). The absolute differences between the test and reference DBPs were <5, <10, and <15 mm Hg in 75.5% (197/261), 93.9% (245/261), and 97.3% (254/261) of measurements, respectively. The secondary analysis showed that after 4 weeks, the differences between SBP and DBP were 0.1 (SD 8.8) and -2.4 (SD 7.6) mm Hg, respectively. AlwaysBP exhibited acceptable accuracy in SBP and DBP measurement compared with the standard measurement method, according to the Association for the Advancement of Medical Instrumentation/European Society of Hypertension/International Organization for Standardization protocol criteria. However, further validation studies with a specific validation protocol designed for cuffless blood pressure measuring devices are required to assess clinical accuracy. This technology can be easily applied in everyday life and may improve the general population's awareness of hypertension, thus helping to control it.

AI-Enabled Vibrotactile Feedback-Based Condition Monitoring Framework for Outdoor Mobile Robots

An automated Condition Monitoring (CM) and real-time controlling framework is essential for outdoor mobile robots to ensure the robot’s health and operational safety. This work presents a novel Artificial Intelligence (AI)-enabled CM and vibrotactile haptic-feedback-based real-time control framework suitable for deploying mobile robots in dynamic outdoor environments. It encompasses two sections: developing a 1D Convolutional Neural Network (1D CNN) model for predicting system degradation and terrain flaws threshold classes and a vibrotactile haptic feedback system design enabling a remote operator to control the robot as per predicted class feedback in real-time. As vibration is an indicator of failure, we identified and separated system- and terrain-induced vibration threshold levels suitable for CM of outdoor robots into nine classes, namely Safe, moderately safe system-generated, and moderately safe terrain-induced affected by left, right, and both wheels, as well as severe classes such as unsafe system-generated and unsafe terrain-induced affected by left, right, and both wheels. The vibration-indicated data for each class are modelled based on two sensor data: an Inertial Measurement Unit (IMU) sensor for the change in linear and angular motion and a current sensor for the change in current consumption at each wheel motor. A wearable novel vibrotactile haptic feedback device architecture is presented with left and right vibration modules configured with unique haptic feedback patterns corresponding to each abnormal vibration threshold class. The proposed haptic-feedback-based CM framework and real-time remote controlling are validated with three field case studies using an in-house-developed outdoor robot, resulting in a threshold class prediction accuracy of 91.1% and an effectiveness that, by minimising the traversal through undesired terrain features, is four times better than the usual practice.

Foot characteristics of the daily-life gait in postmenopausal females with distal radius fractures: a cross-sectional study

BackgroundGait decline in older adults is related to falling risk, some of which contribute to injurious falls requiring medical attention or restriction of activity of daily living. Among injurious falls, distal radius fracture (DRF) is a common initial fragility fracture associated with the subsequent fracture risk in postmenopausal females. The recent invention of an inertial measurement unit (IMU) facilitates the assessment of free-living gait; however, little is known about the daily gait characteristics related to the risk of subsequent fractures. We hypothesized that females with DRF might have early changes in foot kinematics in daily gait. The aim of this study was to evaluate the daily-life gait characteristics related to the risk of falls and fracture.MethodsIn this cross-sectional study, we recruited 27 postmenopausal females with DRF as their first fragility fracture and 28 age-matched females without a history of fragility fractures. The participants underwent daily gait assessments for several weeks using in-shoe IMU sensors. Eight gait parameters and each coefficient of variance were calculated. Some physical tests, such as hand grip strength and Timed Up and Go tests, were performed to check the baseline functional ability.ResultsThe fracture group showed lower foot angles of dorsiflexion and plantarflexion in the swing phase. The receiver operating characteristic curve analyses revealed that a total foot movement angle (TFMA) < 99.0 degrees was the risk of subsequent fracture.ConclusionsWe extracted the daily-life gait characteristics of patients with DRF using in-shoe IMU sensors. A lower foot angle in the swing phase, TFMA, may be associated with the risk of subsequent fractures, which may be effective in evaluating future fracture risk. Further studies to predict and prevent subsequent fractures from daily-life gait are warranted.

Productivity Measurement through IMU-Based Detailed Activity Recognition Using Machine Learning: A Case Study of Masonry Work.

Although measuring worker productivity is crucial, the measurement of the productivity of each worker is challenging due to their dispersion across various construction jobsites. This paper presents a framework for measuring productivity based on an inertial measurement unit (IMU) and activity classification. Two deep learning algorithms and three sensor combinations were utilized to identify and analyze the feasibility of the framework in masonry work. Using the proposed method, worker activity classification could be performed with a maximum accuracy of 96.70% using the convolutional neural network model with multiple sensors, and a minimum accuracy of 72.11% using the long short-term memory (LSTM) model with a single sensor. Productivity could be measured with an accuracy of up to 96.47%. The main contributions of this study are the proposal of a method for classifying detailed activities and an exploration of the effect of the number of IMU sensors used in measuring worker productivity.

What differences exist between the lead and trail wrist in extensor carpi ulnaris activity and golf swing joint kinematics in sub-elite golfers?

ABSTRACT This study assessed the lead and trail arm peak and average extensor carpi ulnaris (ECU) muscle activity in association with tri-planar angular velocities of the lead and trail wrists during the golf swing. Fifteen sub-elite, male right-handed golfers (M age = 34.7 years ±13.3, M handicap = 1.5 ± 2.2) were recruited to execute five shots each with their pitching wedge, 7-iron and driver clubs in an indoor golf simulator. Surface electromyography (EMG) sensors were placed over the ECU muscle belly and inertial measurement unit sensors were placed bi-laterally on the distal forearm and dorsum of the hand. There was a statistically greater recruitment of the trail ECU muscle during the downswing (p < 0.001) for all clubs. The lead ECU muscle was recruited more during the backswing (p < 0.001) and follow through (p < 0.024) phases. There were statistically different tri-planar movement patterns between the lead and trail wrist throughout all three phases of the golf swing. No significant relationships were found between downswing EMG data and clubhead kinematics at impact. In conclusion, differing wrist kinematics and associated muscle activity may contribute to the asymmetrical injury pattern seen clinically.

Characteristics of hoof landing in sound horses and the influence of trimming and shoeing examined with hoof-mounted inertial sensors.

The aim of the current in vivo, observational study was to investigate the effects of different hoof manipulations on landing duration (LandD), location (ICloc) and angle of initial contact (ICangle) in the front feet of horses. A novel, hoof-mounted, inertial measurement unit sensor system (IMU) was used. Ten sound, crossbred horses were fitted with an IMU sensor at the dorsal hoof wall and examined barefoot and after trimming. Additionally, the application of 120 g lateral weights and 5° medial side wedges as well as steel, aluminium, egg bar and lateral extension shoes were tested. Horses were guided in a straight line on firm ground. The use of steel shoes increased LandD compared to barefoot and enhanced the individual ICloc in trot. Application of rolled toe shoes caused a longer LandD than use of plain shoes. None of the other modifications significantly influenced the timing or spatial variables of hoof landing. Trimming and shoeing have less impact on the landing pattern of horses than assumed in practice. Still, the use of steel shoes changes sliding properties of the hooves on firm ground and increases weight causing a longer LandD and reinforcement of the individual ICloc.

AI-Enabled Condition Monitoring Framework for Indoor Mobile Cleaning Robots

Autonomous mobile cleaning robots are ubiquitous today and have a vast market need. Current studies are mainly focused on autonomous cleaning performances, and there exists a research gap on monitoring the robot’s health and safety. Vibration is a key indicator of system deterioration or external factors causing accelerated degradation or threats. Hence, this work proposes an artificial intelligence (AI)-enabled automated condition monitoring (CM) framework using two heterogeneous sensor datasets to predict the sources of anomalous vibration in mobile robots with high accuracy. This allows triggering proper maintenance or corrective actions based on the condition of the robot’s health or workspace, easing condition-based maintenance (CbM). Anomalous vibration sources are classified as induced by uneven Terrain, Collision with obstacles, loose Assembly, and unbalanced Structure, which causes accelerated system deterioration or potential hazards. Here, an unexplored heterogeneous sensor dataset using inertial measurement unit (IMU) and current sensors is proposed for effective recognition across different vibration classes, resulting in higher-accuracy prediction. A simple-structured 1D convolutional neural network (1D CNN) is developed for training and real-time prediction. A 2D CbM map is generated by fusing the predicted classes in real time on an occupancy grid map of the workspace to monitor the conditions of the robot and workspace remotely. The evaluation test results of the proposed method show that the usage of heterogeneous sensors performs significantly more accurately (98.4%) than previous studies, which used IMU (92.2%) and camera (93.8%) sensors individually. Also, this model is comparatively fast, fit for the environment, and ideal for real-time applications in mobile robots based on field trial validations, enhancing mobile robots’ productivity and operational safety.

Integrated UWB/MIMU Sensor System for Position Estimation towards an Accurate Analysis of Human Movement: A Technical Review.

Integrated Ultra-wideband (UWB) and Magnetic Inertial Measurement Unit (MIMU) sensor systems have been gaining popularity for pedestrian tracking and indoor localization applications, mainly due to their complementary error characteristics that can be exploited to achieve higher accuracies via a data fusion approach. These integrated sensor systems have the potential for improving the ambulatory 3D analysis of human movement (estimating 3D kinematics of body segments and joints) over systems using only on-body MIMUs. For this, high accuracy is required in the estimation of the relative positions of all on-body integrated UWB/MIMU sensor modules. So far, these integrated UWB/MIMU sensors have not been reported to have been applied for full-body ambulatory 3D analysis of human movement. Also, no review articles have been found that have analyzed and summarized the methods integrating UWB and MIMU sensors for on-body applications. Therefore, a comprehensive analysis of this technology is essential to identify its potential for application in 3D analysis of human movement. This article thus aims to provide such a comprehensive analysis through a structured technical review of the methods integrating UWB and MIMU sensors for accurate position estimation in the context of the application for 3D analysis of human movement. The methods used for integration are all summarized along with the accuracies that are reported in the reviewed articles. In addition, the gaps that are required to be addressed for making this system applicable for the 3D analysis of human movement are discussed.

Gait Stride Length Estimation Using Embedded Machine Learning.

Spatiotemporal gait parameters, e.g., gait stride length, are measurements that are classically derived from instrumented gait analysis. Today, different solutions are available for gait assessment outside the laboratory, specifically for spatiotemporal gait parameters. Such solutions are wearable devices that comprise an inertial measurement unit (IMU) sensor and a microcontroller (MCU). However, these existing wearable devices are resource-constrained. They contain a processing unit with limited processing and memory capabilities which limit the use of machine learning to estimate spatiotemporal gait parameters directly on the device. The solution for this limitation is embedded machine learning or tiny machine learning (tinyML). This study aims to create a machine-learning model for gait stride length estimation deployable on a microcontroller. Starting from a dataset consisting of 4467 gait strides from 15 healthy people, measured by IMU sensor, and using state-of-the-art machine learning frameworks and machine learning operations (MLOps) tools, a multilayer 1D convolutional float32 and int8 model for gait stride length estimation was developed. The developed float32 model demonstrated a mean accuracy and precision of 0.23 ± 4.3 cm, and the int8 model demonstrated a mean accuracy and precision of 0.07 ± 4.3 cm. The memory usage for the float32 model was 284.5 kB flash and 31.9 kB RAM. The int8 model memory usage was 91.6 kB flash and 13.6 kB RAM. Both models were able to be deployed on a Cortex-M4F 64 MHz microcontroller with 1 MB flash memory and 256 kB RAM. This study shows that estimating gait stride length directly on a microcontroller is feasible and demonstrates the potential of embedded machine learning, or tinyML, in designing wearable sensor devices for gait analysis.

Mapping of Potential Fuel Regions Using Uncrewed Aerial Vehicles for Wildfire Prevention

This paper presents a comprehensive forest mapping system using a customized drone payload equipped with Light Detection and Ranging (LiDAR), cameras, a Global Navigation Satellite System (GNSS), and Inertial Measurement Unit (IMU) sensors. The goal is to develop an efficient solution for collecting accurate forest data in dynamic environments and to highlight potential wildfire regions of interest to support precise forest management and conservation on the ground. Our paper provides a detailed description of the hardware and software components of the system, covering sensor synchronization, data acquisition, and processing. The overall system implements simultaneous localization and mapping (SLAM) techniques, particularly Fast LiDAR Inertial Odometry with Scan Context (FASTLIO-SC), and LiDAR Inertial Odometry Smoothing and Mapping (LIOSAM), for accurate odometry estimation and map generation. We also integrate a fuel mapping representation based on one of the models, used by the United States Secretary of Agriculture (USDA) to classify fire behavior, into the system using semantic segmentation, LiDAR camera registration, and odometry as inputs. Real-time representation of fuel properties is achieved through a lightweight map data structure at 4 Hz. The research results demonstrate the effectiveness and reliability of the proposed system and show that it can provide accurate forest data collection, accurate pose estimation, and comprehensive fuel mapping with precision values for the main segmented classes above 85%. Qualitative evaluations suggest the system’s capabilities and highlight its potential to improve forest management and conservation efforts. In summary, this study presents a versatile forest mapping system that provides accurate forest data for effective management.

Unscented Kalman filter for a low-cost GNSS/IMU-based mobile mapping application under demanding conditions

For the last two decades, low-cost Global Navigation Satellite System (GNSS) receivers have been used in various applications. These receivers are mini-size, less expensive than geodetic-grade receivers, and in high demand. Irrespective of these outstanding features, low-cost GNSS receivers are potentially poorer hardwares with internal signal processing, resulting in lower quality. They typically come with low-cost GNSS antenna that has lower performance than their counterparts, particularly for multipath mitigation. Therefore, this research evaluated the low-cost GNSS device performance using a high-rate kinematic survey. For this purpose, these receivers were assembled with an Inertial Measurement Unit (IMU) sensor, which actively transmited data on acceleration and orientation rate during the observation. The position and navigation parameter data were obtained from the IMU readings, even without GNSS signals via the U-blox F9R GNSS/IMU device mounted on a vehicle. This research was conducted in an area with demanding conditions, such as an open sky area, an urban environment, and a shopping mall basement, to examine the device's performance. The data were processed by two approaches: the Single Point Positioning-IMU (SPP/IMU) and the Differential GNSS-IMU (DGNSS/IMU). The Unscented Kalman Filter (UKF) was selected as a filtering algorithm due to its excellent performance in handling nonlinear system models. The result showed that integrating GNSS/IMU in SPP processing mode could increase the accuracy in eastward and northward components up to 68.28% and 66.64%. Integration of DGNSS/IMU increased the accuracy in eastward and northward components to 93.02% and 93.03% compared to the positioning of standalone GNSS. In addition, the positioning accuracy can be improved by reducing the IMU noise using low-pass and high-pass filters. This application could still not gain the expected position accuracy under signal outage conditions.

Performance of multiple neural networks in predicting lower limb joint moments using wearable sensors.

Joint moment measurements represent an objective biomechemical parameter in joint health assessment. Inverse dynamics based on 3D motion capture data is the current 'gold standard' to estimate joint moments. Recently, machine learning combined with data measured by wearable technologies such electromyography (EMG), inertial measurement units (IMU), and electrogoniometers (GON) has been used to enable fast, easy, and low-cost measurements of joint moments. This study investigates the ability of various deep neural networks to predict lower limb joint moments merely from IMU sensors. The performance of five different deep neural networks (InceptionTimePlus, eXplainable convolutional neural network (XCM), XCMplus, Recurrent neural network (RNNplus), and Time Series Transformer (TSTPlus)) were tested to predict hip, knee, ankle, and subtalar moments using acceleration and gyroscope measurements of four IMU sensors at the trunk, thigh, shank, and foot. Multiple locomotion modes were considered including level-ground walking, treadmill walking, stair ascent, stair descent, ramp ascent, and ramp descent. We show that XCM can accurately predict lower limb joint moments using data of only four IMUs with RMSE of 0.046 ± 0.013 Nm/kg compared to 0.064 ± 0.003 Nm/kg on average for the other architectures. We found that hip, knee, and ankle joint moments predictions had a comparable RMSE with an average of 0.069 Nm/kg, while subtalar joint moments had the lowest RMSE of 0.033 Nm/kg. The real-time feedback that can be derived from the proposed method can be highly valuable for sports scientists and physiotherapists to gain insights into biomechanics, technique, and form to develop personalized training and rehabilitation programs.

Design and Implementation of Sensor Systems for Localization of the Autonomous Robot in a Building Area

One of the popular studies recently is about social robots that have been implemented in several public areas such as offices. The robot is an employee or worker assistant robot in the Telkom Surabaya Institute of Technology building to help carry out the work of delivering packages to the destination according to the tasks given. The problem that often occurs is an error in the robot's localization system causing the robot's movement to the target point to experience a position error. This research contributes to the comparative evaluation of 2 localization methods on mobile robots, namely the first is the use of a rotary encoder sensor and the second is the use of sensor fusion based on the extended Kalman filter implemented on the robot prototype. This study aims to develop a sensor system that is adapted to the design of the robot and the environment in which the robot is tested and to find out the comparison of the two methods. The use of extended Kalman filter-based sensor fusion can provide more accurate results in robot localization, especially when moving on complex paths. Sensor fusion enables the combination of several sensors such as rotary encoders and IMU (Inertial Measurement Unit) sensors to provide more complete and accurate information about the position and orientation of the robot. In this study, sensor fusion successfully reduced the localization error of the robot to 0.63 m when moving straight and 0.29 m when moving on a complex path, compared to the use of a single sensor which resulted in a larger error of 0.89 m. Based on the study that has been conducted, it can be considered as a potential solution in the development of other social robots to improve the accuracy and performance of the robots when performing certain tasks in the future.

IMU/UWB Fusion Method Using a Complementary Filter and a Kalman Filter for Hybrid Upper Limb Motion Estimation.

Motion capture systems have enormously benefited the research into human-computer interaction in the aerospace field. Given the high cost and susceptibility to lighting conditions of optical motion capture systems, as well as considering the drift in IMU sensors, this paper utilizes a fusion approach with low-cost wearable sensors for hybrid upper limb motion tracking. We propose a novel algorithm that combines the fourth-order Runge-Kutta (RK4) Madgwick complementary orientation filter and the Kalman filter for motion estimation through the data fusion of an inertial measurement unit (IMU) and an ultrawideband (UWB). The Madgwick RK4 orientation filter is used to compensate gyroscope drift through the optimal fusion of a magnetic, angular rate, and gravity (MARG) system, without requiring knowledge of noise distribution for implementation. Then, considering the error distribution provided by the UWB system, we employ a Kalman filter to estimate and fuse the UWB measurements to further reduce the drift error. Adopting the cube distribution of four anchors, the drift-free position obtained by the UWB localization Kalman filter is used to fuse the position calculated by IMU. The proposed algorithm has been tested by various movements and has demonstrated an average decrease in the RMSE of 1.2 cm from the IMU method to IMU/UWB fusion method. The experimental results represent the high feasibility and stability of our proposed algorithm for accurately tracking the movements of human upper limbs.

Feasibility Testing of Wearable Device for Musculoskeletal Monitoring during Aquatic Therapy and Rehabilitation.

The objectives of this study were to test the feasibility of the developed waterproof wearable device with a Surface Electromyography (sEMG) sensor and Inertial Measurement Unit (IMU) sensor by (1) comparing the onset duration of sEMG recordings from maximal voluntary contractions (MVC), (2) comparing the acceleration of arm movement from IMU, and (3) observing the reproducibility of onset duration and acceleration from the developed device for bicep brachii (BB) muscle between on dry-land, and in aquatic environments. Five healthy males participated in two experimental protocols with the activity of BB muscle of the left and right arms. Using the sEMG of BB muscle, the intra-class correlation coefficient (ICC) and typical error (CV%) were calculated to determine the reproducibility and precision of onset duration and acceleration, respectively. In case of onset duration, no significant differences were observed between land and aquatic condition (p = 0.9-0.98), and high reliability (ICC = 0.93-0.98) and precision (CV% = 2.7-6.4%) were observed. In addition, acceleration data shows no significant differences between land and aquatic condition (p = 0.89-0.93), and high reliability (ICC = 0.9-0.97) and precision (CV% = 7.9-9.2%). These comparable sEMG and acceleration values in both dry-land and aquatic environment supports the suitability of the proposed wearable device for musculoskeletal monitoring during aquatic therapy and rehabilitation as the integrity of the sEMG and acceleration recordings maintained during aquatic activities.Clinical Relevance-This study and relevant experiment demonstrate the feasibility of the developed wearable device to support clinicians and therapists for musculoskeletal monitoring during aquatic therapy and rehabilitation.