Abstract
This paper explores the quaternion representation in order to devise an extended Kalman filter approach for pose estimation: inertial measurements are fused with visual data so as to estimate the position and orientation of a six degrees-of-freedom rigid body. The filter equations are described along with a data-driven tuning method that selects the model covariance matrix based on experimental results. Finally, the proposed algorithm is applied to a six degrees-of-freedom Stewart platform, a representative system of a large class of industrial manipulators that could benefit from the proposed solution.
Similar content being viewed by others
Notes
In Algorithm 1, \({\varvec{x}}_k^-\) and \({\varvec{P}}_k^-\) denote a priori estimates, i.e., prior to the application of the correction step.
The normalization of a quaternion in \({\varvec{x}}\) is computed as \({\varvec{q}} \leftarrow {\varvec{q}} / \Vert {\varvec{q}} \Vert \), where \(\Vert \cdot \Vert \) stands for the Euclidian norm and \({\varvec{q}}\) represents the quaternion component of \({\varvec{x}}\) as in (19).
References
Araguás, G., Paz, C., Gaydou, D., & Paina, G. P. (2015). Quaternion-based orientation estimation fusing a camera and inertial sensors for a hovering UAV. Journal of Intelligent and Robotic Systems, 77, 37–53.
Cardona, M. (2015). A new approach for the forward kinematics of general Stewart–Gough platforms. In Proceedings of the 2015 IEEE thirty fifth central American and panama convention (CONCAPAN XXXv).
Colonnier, F., Vedova, L. D., & Orchard, G. (2021). ESPEE: Event-based sensor pose estimation using an extended Kalman filter. Sensors, 21(23), 7840.
He, Y., Sun, W., Huang, H., Liu, J., Fan, H., & Sun, J. (2020). PVN3D: A deep point-wise 3D keypoints voting network for 6DoF pose estimation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR).
Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Journal of Fluids Engineering, 82, 35–45.
Li, S., Li, D., Zhang, C., Wan, J., & Xie, M. (2020). RGB-D image processing algorithm for target recognition and pose estimation of visual servo system. Sensors, 20(2), 430.
Ma, Y., Soatto, S., Košecká, J., & Sastry, S. S. (2004). An invitation to 3-D vision: From imagem to geometric models. Springer.
Mariottini, G. L., & Prattichizzo, D. (2005). EGT for multiple view geometry and visual servoing: Robotics vision with pinhole and panoramic cameras. IEEE Robotics & Automation Magazine, 12(4), 26–39.
Markley, F. L. (2003). Attitude error representations for Kalman filtering. Journal of Guidance, Control, and Dynamics, 26(2), 311–317.
Markley, F. L., & Crassidis, J. L. (2014). Fundamentals of spacecraft attitude determination and control. Springer.
Nützi, G., Weiss, S., Scaramuzza, D., & Siegwart, R. (2011). Fusion of IMU and vision for absolute scale estimation in monocular SLAM. Journal of Intelligent & Robotic Systems, 61(1–4), 287–299.
Ratz, S., Dymczyk, M., Siegwart, R., & Dubé, R. (2020). Oneshot global localization: Instant lidar-visual pose estimation. In 2020 IEEE international conference on robotics and automation (ICRA) (pp. 5415–5421).
Schönberger, J. L., Pollefeys, M., Geiger, A., & Sattler, T. (2018). Semantic visual localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).
Sciavicco, L., & Siciliano, B. (2012). Modelling and control of robot manipulators. Springer.
Silva, J. G., Filho, J. O. D. A. L., & Fortaleza, E. L. F. (2018). Adaptive extended Kalman filter using exponencial moving average. In Proceedings of the 9th IFAC symposium on robust control design (Vol. 51, pp. 208–211).
Sveier, A., & Egeland, O. (2021). Dual quaternion particle filtering for pose estimation. IEEE Transactions on Control Systems Technology, 29(5), 2012–2025.
Tayebi, A., & McGilvray, S. (2006). Attitude stabilization of a VTOL quadrotor aircraft. IEEE Transactions on Control Systems Technology, 14(3), 562–571.
Tong, X., Li, Z., Han, G., Liu, N., Su, Y., Ning, J., & Yang, F. (2018). Adaptive EKF based on HMM recognizer for attitude estimation using MEMS MARG sensors. IEEE Sensors Journal, 18(8), 3299–3310.
Yang, C., Liu, Y., & Zell, A. (2020). RCPNet: Deep-learning based relative camera pose estimation for UAVs. In 2020 International conference on unmanned aircraft systems (ICUAS) (pp. 1085–1092).
Yuen, K. V., Liang, P. F., & Kuok, S. C. (2013). Online estimation of noise parameters for Kalman filter. Structural Engineering and Mechanics, 47(3), 361–381.
Zhang, H., & Ye, C. (2020). A visual positioning system for indoor blind navigation. In 2020 IEEE international conference on robotics and automation (ICRA) (pp. 9079–9085).
Zhang, Y., Bian, C., & Gao, J. (2020). An unscented Kalman filter-based visual pose estimation method for underwater vehicles. In 2020 3rd international conference on unmanned systems (ICUS) (pp. 663–667).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
A. T. Salton acknowledges the support from CNPq Brazil under Grant 306214/2018-0.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Salton, A.T., Pimentel, G.A., Melo, J.V. et al. Data-driven Covariance Tuning of the Extended Kalman Filter for Visual-based Pose Estimation of the Stewart Platform. J Control Autom Electr Syst 34, 720–730 (2023). https://doi.org/10.1007/s40313-023-01006-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40313-023-01006-4