BROAD—A Benchmark for Robust Inertial Orientation Estimation

Measuring highly accurate foot position and angle trajectories with foot-mounted IMUs in clinical practice

BACKGROUND

Gait analysis using foot-mounted IMUs is a promising method to acquire gait parameters outside of laboratory settings and in everyday clinical practice. However, the need for precise sensor attachment or calibration, the requirement of environments with a homogeneous magnetic field, and the limited applicability to pathological gait patterns still pose challenges. Furthermore, in previously published work, the measurement accuracy of such systems is often only validated for specific points in time or in a single plane.

RESEARCH QUESTION

This study investigates the measurement accuracy of a gait analysis method based on foot-mounted IMUs in the acquisition of the foot motion, i.e., position and angle trajectories of the foot in the sagittal, frontal, and transversal plane over the entire gait cycle.

RESULTS

A comparison of the proposed method with an optical motion capture system showed an average RMSE of 0.67° for pitch, 0.63° for roll and 1.17° for yaw. For position trajectories, an average RMSE of 0.51 cm for vertical lift and 0.34 cm for lateral shift was found. The measurement error of the IMU-based method is found to be much smaller than the deviations caused by the shoes.

SIGNIFICANCE

The proposed method is found to be sufficiently accurate for clinical practice. It does not require precise mounting, special calibration movements, or magnetometer data, and shows no difference in measurement accuracy between normal and pathological gait. Therefore, it provides an easy-to-use alternative to optical motion capture and facilitates gait analysis independent of laboratory settings.

Effects of Data Augmentation on the Nine-Axis IMU-Based Orientation Estimation Accuracy of a Recurrent Neural Network

The nine-axis inertial and measurement unit (IMU)-based three-dimensional (3D) orientation estimation is a fundamental part of inertial motion capture. Recently, owing to the successful utilization of deep learning in various applications, orientation estimation neural networks (NNs) trained on large datasets, including nine-axis IMU signals and reference orientation data, have been developed. During the training process, the limited amount of training data is a critical issue in the development of powerful networks. Data augmentation, which increases the amount of training data, is a key approach for addressing the data shortage problem and thus for improving the estimation performance. However, to the best of our knowledge, no studies have been conducted to analyze the effects of data augmentation techniques on estimation performance in orientation estimation networks using IMU sensors. This paper selects three data augmentation techniques for IMU-based orientation estimation NNs, i.e., augmentation by virtual rotation, bias addition, and noise addition (which are hereafter referred to as rotation, bias, and noise, respectively). Then, this paper analyzes the effects of these augmentation techniques on estimation accuracy in recurrent neural networks, for a total of seven combinations (i.e., rotation only, bias only, noise only, rotation and bias, rotation and noise, and rotation and bias and noise). The evaluation results show that, among a total of seven augmentation cases, four cases including 'rotation' (i.e., rotation only, rotation and bias, rotation and noise, and rotation and bias and noise) occupy the top four. Therefore, it may be concluded that the augmentation effect of rotation is overwhelming compared to those of bias and noise. By applying rotation augmentation, the performance of the NN can be significantly improved. The analysis of the effect of the data augmentation techniques presented in this paper may provide insights for developing robust IMU-based orientation estimation networks.

Robust Attitude and Heading Estimation under Dynamic Motion and Magnetic Disturbance

Robust and accurate attitude and heading estimation using Micro-Electromechanical System (MEMS) Inertial Measurement Units (IMU) is the most crucial technique that determines the accuracy of various downstream applications, especially pedestrian dead reckoning (PDR), human motion tracking, and Micro Aerial Vehicles (MAVs). However, the accuracy of the Attitude and Heading Reference System (AHRS) is often compromised by the noisy nature of low-cost MEMS-IMUs, dynamic motion-induced large external acceleration, and ubiquitous magnetic disturbance. To address these challenges, we propose a novel data-driven IMU calibration model that employs Temporal Convolutional Networks (TCNs) to model random errors and disturbance terms, providing denoised sensor data. For sensor fusion, we use an open-loop and decoupled version of the Extended Complementary Filter (ECF) to provide accurate and robust attitude estimation. Our proposed method is systematically evaluated using three public datasets, TUM VI, EuRoC MAV, and OxIOD, with different IMU devices, hardware platforms, motion modes, and environmental conditions; and it outperforms the advanced baseline data-driven methods and complementary filter on two metrics, namely absolute attitude error and absolute yaw error, by more than 23.4% and 23.9%. The generalization experiment results demonstrate the robustness of our model on different devices and using patterns.

Base of Support, Step Length and Stride Width Estimation during Walking Using an Inertial and Infrared Wearable System

The analysis of the stability of human gait may be effectively performed when estimates of the base of support are available. The base of support area is defined by the relative position of the feet when they are in contact with the ground and it is closely related to additional parameters such as step length and stride width. These parameters may be determined in the laboratory using either a stereophotogrammetric system or an instrumented mat. Unfortunately, their estimation in the real world is still an unaccomplished goal. This study aims at proposing a novel, compact wearable system, including a magneto-inertial measurement unit and two time-of-flight proximity sensors, suitable for the estimation of the base of support parameters. The wearable system was tested and validated on thirteen healthy adults walking at three self-selected speeds (slow, comfortable, and fast). Results were compared with the concurrent stereophotogrammetric data, used as the gold standard. The root mean square errors for the step length, stride width and base of support area varied from slow to high speed between 10-46 mm, 14-18 mm, and 39-52 cm², respectively. The mean overlap of the base of support area as obtained with the wearable system and with the stereophotogrammetric system ranged between 70% and 89%. Thus, this study suggested that the proposed wearable solution is a valid tool for the estimation of the base of support parameters out of the laboratory.

Vertical Jump Data from Inertial and Optical Motion Tracking Systems

Motion capture (MOCAP) is a widely used technique to record human, animal, and object movement for various applications such as animation, biomechanical assessment, and control systems. Different systems have been proposed based on diverse technologies, such as visible light cameras, infrared cameras with passive or active markers, inertial systems, or goniometer-based systems. Each system has pros and cons that make it usable in different scenarios. This paper presents a dataset that combines Optical Motion and Inertial Systems, capturing a well-known sports movement as the vertical jump. As a reference system, the optical motion capture consists of six Flex 3 Optitrack cameras with 100 FPS. On the other hand, we developed an inertial system consisting of seven custom-made devices based on the IMU MPU-9250, which includes a three-axis magnetometer, accelerometer and gyroscope, and an embedded Digital Motion Processor (DMP) attached to a microcontroller mounted on a Teensy 3.2 with an ARM Cortex-M4 processor with wireless operation using Bluetooth. The purpose of taking IMU data with a low-cost and customized system is the deployment of applications that can be performed with similar hardware and can be adjusted to different areas. The developed measurement system is flexible, and the acquisition format and enclosure can be customized. The proposed dataset comprises eight jumps recorded from four healthy humans using both systems. Experimental results on the dataset show two usage examples for measuring joint angles and COM position. The proposed dataset is publicly available online and can be used in comparative algorithms, biomechanical studies, skeleton reconstruction, sensor fusion techniques, or machine learning models.

An ISB-consistent Denavit-Hartenberg model of the human upper limb for joint kinematics optimization: validation on synthetic and robot data during a typical rehabilitation gesture

Several biomedical contexts such as diagnosis, rehabilitation, and ergonomics require an accurate estimate of human upper limbs kinematics. Wearable inertial measurement units (IMU s) represent a suitable solution because of their unobtrusiveness, portability, and low-cost. However, the time-integration of the gyroscope angular velocity leads to an unbounded orientation drift affecting both angular and linear displacements over long observation interval. In this work, a Denavit-Hartenberg model of the upper limb was defined in accordance with the guidelines of the International Society of Biomechanics and exploited to design an optimization kinematics process. This procedure estimated the joint angles by minimizing the difference between the modelled and IMU-driven orientation of upper arm and forearm. In addition, reasonable constraints were added to limit the drift influence on the final joint kinematics accuracy. The validity of the procedure was tested on synthetic and experimental data acquired with a robotic arm over 20 minutes. Average rms errors amounted to 2.8 deg and 1.1 for synthetic and robot data, respectively. Clinical Relevance - The proposed method has the potential to improve robustness and accuracy of multi-joint kinematics estimation in the general contexts of home-based tele-rehabilitation interventions. In this respect adoption of multi-segmental kinematic model along with physiological joint constraints could contribute to address current limitations associated to unsupervised analysis in terms of monitoring and outcome assessment.

RIANN—A Robust Neural Network Outperforms Attitude Estimation Filters

Inertial-sensor-based attitude estimation is a crucial technology in various applications, from human motion tracking to autonomous aerial and ground vehicles. Application scenarios differ in characteristics of the performed motion, presence of disturbances, and environmental conditions. Since state-of-the-art attitude estimators do not generalize well over these characteristics, their parameters must be tuned for the individual motion characteristics and circumstances. We propose RIANN, a ready-to-use, neural network-based, parameter-free, real-time-capable inertial attitude estimator, which generalizes well across different motion dynamics, environments, and sampling rates, without the need for application-specific adaptations. We gather six publicly available datasets of which we exploit two datasets for the method development and the training, and we use four datasets for evaluation of the trained estimator in three different test scenarios with varying practical relevance. Results show that RIANN outperforms state-of-the-art attitude estimation filters in the sense that it generalizes much better across a variety of motions and conditions in different applications, with different sensor hardware and different sampling frequencies. This is true even if the filters are tuned on each individual test dataset, whereas RIANN was trained on completely separate data and has never seen any of these test datasets. RIANN can be applied directly without adaptations or training and is therefore expected to enable plug-and-play solutions in numerous applications, especially when accuracy is crucial but no ground-truth data is available for tuning or when motion and disturbance characteristics are uncertain. We made RIANN publicly available.