Kalman Filtering for Attitude Estimation with Quaternions and Concepts from Manifold Theory

Bernal-Polo, Pablo; Barberá, Humberto Martínez

doi:10.3390/s19010149

Cited by 25 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Equation ( 1), quaternions contain four coefficients consisting of one scalar q0, 3 vectors q1, q2 and q3. The scalar part determines the amount of rotation of the vector part (Craig, 2005;Bernal-Polo and Martínez-Barberá, 2019). When rotated by the θ angle, the quaternion coefficient is expressed as in Equation ( 2).…”

Section: Methodsmentioning

confidence: 99%

Comparison of Artificial Neural Networks with other Machine Learning Methods in Foot Movement Classification

FANDAKLI

Okumuş

2023

Karadeniz Fen Bilimleri Dergisi

View full text Add to dashboard Cite

Modern prostheses can be controlled by using gait analysis data from Inertial Measurement Units compared to traditional prostheses. This article aims to classify foot movements for the robotic ankle system in lower limb prostheses to recognize motion intent and adapt to abnormal walking conditions. The statistical features are extracted from IMU data from 11 volunteers aged 20-34 and then the features are classified using machine learning. In this study, the classification accuracies of Naïve Bayes Classifier, Linear Discriminant Analysis, K-Nearest Neighbour Classifier and Support Vector Machines and Artificial Neural Networks in classifying foot movements are examined separately for the raw data and the processed data such as Euler angles and quaternions which estimate with Madwick Filter. Gait analysis data were obtained by using the Inemo inertial module LSM9DS1 work on an NRF52 including 9 DOF, triaxial gyroscope, triaxial accelerometer, and triaxial magnetometer in the Biomechanics Laboratory of the Department of Mechanical Engineering, Middle East Technical University from eleven subjects and achieved an highest classification accuracy rate of 90.9% on test data, 97.3% for training data.

show abstract

Section: Methodsmentioning

confidence: 99%

Comparison of Artificial Neural Networks with other Machine Learning Methods in Foot Movement Classification

FANDAKLI

Okumuş

2023

Karadeniz Fen Bilimleri Dergisi

View full text Add to dashboard Cite

show abstract

“…A multitude of solutions was proposed to solve this problem, some of first methods are based on deterministic approaches TRIAD [30], QUaternion ESTimator (QUEST) [31], and Singular Value Decomposition method (SVD) [32]. More recently, some dynamic estimation methods, more efficient, such as Kalman filters (KF) [33,34,35] and observers [36,37] are proposed. One of the famous surveys of these methods can be found in [38].…”

Section: Methodology For Harmentioning

confidence: 99%

Human Activities and Postures Recognition: From Inertial Measurements to Quaternion-Based Approaches

Zmitri

Fourati

Vuillerme

2019

Sensors

View full text Add to dashboard Cite

This paper presents two approaches to assess the effect of the number of inertial sensors and their location placements on recognition of human postures and activities. Inertial and Magnetic Measurement Units (IMMUs)—which consist of a triad of three-axis accelerometer, three-axis gyroscope, and three-axis magnetometer sensors—are used in this work. Five IMMUs are initially used and attached to different body segments. Placements of up to three IMMUs are then considered: back, left foot, and left thigh. The subspace k-nearest neighbors (KNN) classifier is used to achieve the supervised learning process and the recognition task. In a first approach, we feed raw data from three-axis accelerometer and three-axis gyroscope into the classifier without any filtering or pre-processing, unlike what is usually reported in the state-of-the-art where statistical features were computed instead. Results show the efficiency of this method for the recognition of the studied activities and postures. With the proposed algorithm, more than 80% of the activities and postures are correctly classified using one IMMU, placed on the lower back, left thigh, or left foot location, and more than 90% when combining all three placements. In a second approach, we extract attitude, in term of quaternion, from IMMUs in order to more precisely achieve the recognition process. The obtained accuracy results are compared to those obtained when only raw data is exploited. Results show that the use of attitude significantly improves the performance of the classifier, especially for certain specific activities. In that case, it was further shown that using a smaller number of features, with quaternion, in the recognition process leads to a lower computation time and better accuracy.

show abstract

“…As a first step, the orientation of the device should be obtained. To this end, many sensor fusion techniques have been proposed in the literature to estimate the orientation using a built-in accelerometer that measures the gravity of the Earth and gyroscope that detects the rotation of the device [48], [49]. With the estimated orientation, the two dimensional rotation of the device on an x-y plane of the global coordinate system (GCS) can be obtained, as shown in Fig.…”

Section: B Pedestrian Dead Reckoningmentioning

confidence: 99%

Sensor-Aided Learning for Wi-Fi Positioning with Beacon Channel State Information

Choi¹

2020

Preprint

View full text Add to dashboard Cite

Because each indoor site has its own radio propagation characteristics, a site survey process is essential to optimize a Wi-Fi ranging strategy for range-based positioning solutions. This paper studies an unsupervised learning technique that autonomously investigates the characteristics of the surrounding environment using sensor data accumulated while users use a positioning application. Using the collected sensor data, the device trajectory can be regenerated, and a Wi-Fi ranging module is trained to make the shape of the estimated trajectory using Wi-Fi similar to that obtained from sensors. In this process, the ranging module learns the way to identify the channel conditions from each Wi-Fi access point (AP) and produce ranging results accordingly. Furthermore, we collect the channel state information (CSI) from beacon frames and evaluate the benefit of using CSI in addition to received signal strength (RSS) measurements. When CSI is available, the ranging module can identify more diverse channel conditions from each AP, and thus more precise positioning results can be achieved. The effectiveness of the proposed learning technique is verified using a real-time positioning application implemented on a PC platform.

show abstract

Kalman Filtering for Attitude Estimation with Quaternions and Concepts from Manifold Theory

Cited by 25 publications

References 13 publications

Comparison of Artificial Neural Networks with other Machine Learning Methods in Foot Movement Classification

Comparison of Artificial Neural Networks with other Machine Learning Methods in Foot Movement Classification

Human Activities and Postures Recognition: From Inertial Measurements to Quaternion-Based Approaches

Sensor-Aided Learning for Wi-Fi Positioning with Beacon Channel State Information

Contact Info

Product

Resources

About