Abstract
This paper proposes multi-frequency inertial and visual data fusion for attitude estimation. The proposed strategy is based on the locally weighted linear regression (LWLR), multi-layer perception (MLP), and cubature Kalman filter (CKF). First, we analyze the discrepant-frequency and the attitude divergence problems. Second, we construct the filter equation for the visual and inertial data and attitude differential equation for inertial-only data, which are used to estimate the attitude in time series. Third, we employ LWLR to compute the vision discrepancies between actual vision data and fitted vision data. The vision discrepancy is used as the input of MLP training. In MLP, the discrepancy is used as weights of the sums through the activation function of the hidden layer. To address the divergence problem, which is inherent in a multi-frequency fusion, the MLP is utilized to compensate for the inertial-only data. Finally, experimental results on different environments of pseudo-physical simulations show the superior performance of the proposed method in terms of the accuracy of attitude estimation and divergence capability.
Highlights
Accurate and stable attitude estimation is an essential element in broad applications such as positioning, navigation, tracking, and augmented reality [1]–[3]
In order to address the discrepant-frequency problem, an enhanced fusion method is proposed based on locally weighted linear regression (LWLR), multi-layer perception (MLP), and cubature Kalman filter (CKF)
In order to address the discrepant-frequency problem, the enhanced fusion method is proposed based on LWLR, MLP, and CKF algorithms for the attitude estimation system
Summary
Accurate and stable attitude estimation is an essential element in broad applications such as positioning, navigation, tracking, and augmented reality [1]–[3]. Non-linear Kalman filter was used to integrate inertial and vision data in EKF [15], UKF [16], and CKF [17], [18]. In case that vision data is unavailable, the accuracy of attitude estimation is decreased due to the discrepancy of sampling-frequency. The proposed method reduces the effect of the discrepant sampling-frequency, and the attitude divergence between inertial and vision data. The integrated attitude estimation system employs a camera sensor and a gyroscope sensor for capturing the vision and inertial data, respectively. The discrepant-frequency problem causes divergence of inertial and vision integrated attitude estimation. CKF fuses inertial and vision data to dispose of the non-linear problem. In order to address the discrepant-frequency problem, an enhanced fusion method is proposed based on LWLR, MLP, and CKF. The estimated attitude and the covariance of the error of attitude are defined as follows
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
