A Data Driven Toggling Gain Complementary Filtering Approach for Orientation Estimation

Simple item page
dc.contributor.authorAzfar, Samnun
dc.contributor.authorAudhi, Ramisa Zaman
dc.contributor.authorMdInzamam, Mir
dc.date.accessioned2026-06-23T06:39:43Z
dc.date.issued2025-10-25
dc.descriptionSupervised by Dr. AbuRaihanMostofaKamal, Professor, Mohammad Ishrak Abedin, Lecturer, Department of Computer Science and Engineering (CSE) Islamic University of Technology (IUT) Board Bazar, Gazipur, Bangladesh This thesis is submitted in partial fulfillment of the requirement for the degree of Bachelor of Science in Computer Science and Engineering, 2025
dc.description.abstractOne of the goals of an Inertial Navigation System (INS) is to estimate the 3D orienta tion of a bodyundermotionbasedon givenaccelerometer,magnetometerandangular rate gyroscope readings. Complementary fusion is one of the most robust, mathe matically simple and fast algorithms for fusing the accelerometer, magnetometer and angular rate gyroscope readings to estimate the 3D orientation. But complementary fusion of sensor data suffers from linear accelerations and constant gain problems. This thesis aims to solve the aforementioned issues in a data driven approach. In this work, we introduce two contributions for robust orientation estimation using raw in ertial and magnetic sensor data. First, we propose a tree-based Extreme Gradient Boosting (XGB) model that effectively denoises raw gyroscope, accelerometer, and magnetometer signals. Second, we present a tree-based movement detection model that dynamicallyadaptsfusionprocessthrough𝛼-toggling,enablingimprovedrobust ness to linear accelerations and magnetic interference. Together, these contributions establish a data-driven fusion framework that enhances reliability beyond traditional fixed-gain filters. The proposed approach is validated on a real-world dataset and fur ther evaluated using a custom-built mechanical turntable, providing controlled test ing conditions for systematic performance assessment
dc.identifier.citation[1] “Arobustcomplementary filter approach for attitude estimation of unmanned aerial vehicles using AHRS,” in Proceedings of the 2019 CEAS EuroGNC confer ence, CEAS-GNC-2019-036, Milan, Italy, Apr. 2019. [2] AdafruitIndustries, Adafruitas5600magneticanglesensor–stemmaqt,https: //www.adafruit.com/product/6357, Accessed: 2025-09-26, 2025. [3] Ahrs: Attitude and heading reference systems, https://ahrs.readthedocs. io/en/latest/, Accessed: 2025-09-06. [4] T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “Optuna: A next generationhyperparameteroptimization framework,”inProceedingsofthe25th ACMSIGKDDInternationalConferenceonKnowledgeDiscovery&DataMining, 2019, pp. 2623–2631. doi: 10.1145/3292500.3330701 [5] A. Asgharpoor Golroudbari and M. Sabour, End-to-end deep learning frame work for real-time inertial attitude estimation using 6dof imu, Feb. 2023. doi: 10.22541/au.167628608.89589390/v1 [6] I. Y. Bar-Itzhack, “Request- a recursive quest algorithm for sequential atti tude determination,”JournalofGuidance,Control,andDynamics,vol.19,no.5, pp. 1034–1038, 1996. doi: 10.2514/3.21742 eprint: https://doi.org/10. 2514/3.21742. [Online]. Available: https://doi.org/10.2514/3.21742 [7] P. J. Bickel and K. A. Doksum, Mathematical statistics: basic ideas and selected topics, volumes I-II package. Chapman and Hall/CRC, 2015. [8] H.D.Black,“Apassivesystemfordeterminingtheattitudeofasatellite,” AIAA journal, vol. 2, no. 7, pp. 1350–1351, 1964. [9] M. Bramer, “Avoiding overfitting of decision trees,” Principles of data mining, pp. 119–134, 2007. [10] M.Brossard,S.Bonnabel,andA.Barrau,“Denoisingimugyroscopeswithdeep learning for open-loop attitude estimation,” IEEE Robotics andAutomationLet ters, vol. 5, no. 3, pp. 4796–4803, 2020. 54 [11] A. Cariow and G. Cariowa, “A hardware-efficient approach to computing the rotation matrix from a quaternion,” arXiv preprint arXiv:1609.01585, 2016. [12] T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Pro ceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785–794. [13] Y. Chen and H. Rong, “A customized extended kalman filter for removing the impact of the magnetometer’s measurements on inclination determination,” Sensors, vol. 23, no. 24, 2023, issn: 1424-8220. doi: 10.3390/s23249756 [On line]. Available: https://www.mdpi.com/1424-8220/23/24/9756 [14] D.DuongQuoc, J. Sun, V. Le, and L. Luo, “Complementary filter performance enhancement through filter gain,” International Journal of Signal Processing, Image Processing and Pattern Recognition, vol. 8, pp. 97–110, Jul. 2015. doi: 10. 14257/ijsip.2015.8.7.10 [15] M. Euston, P. Coote, R. Mahony, J. Kim, and T. Hamel, “A complementary fil ter for attitude estimation of a fixed-wing uav,” in 2008 IEEE/RSJ international conference on intelligent robots and systems, IEEE, 2008, pp. 340–345. [16] M. A. Fischler and R. C. Bolles, “Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography,” Communications of the ACM, vol. 24, no. 6, pp. 381–395, 1981. doi: 10.1145/ 358669.358692 [17] J. R. Forbes, “Fundamentals of spacecraft attitude determination and control [bookshelf],” IEEE Control Systems Magazine, vol. 35, no. 4, pp. 56–58, 2015. [18] G. Gallego and A. Yezzi, “A compact formula for the derivative of a 3-d rota tion in exponential coordinates,” Journal of Mathematical Imaging and Vision, vol. 51, no. 3, pp. 378–388, 2015. [19] Self Localization Using a 9DOF IMU Sensor With a Directional Cosine Matrix, vol. Volume 4: 18th Design for Manufacturing and the Life Cycle Conference; 2013 ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications, International Design Engineering Technical Con ferences and Computers and Information in Engineering Conference, Aug. 2013, V004T08A051. doi: 10 . 1115 / DETC2013- 12906 eprint: https : / / asmedigitalcollection.asme.org/IDETC-CIE/proceedings-pdf/IDETC CIE2013/55911/V004T08A051/4257997/v004t08a051-detc2013-12906. pdf. [Online]. Available: https://doi.org/10.1115/DETC2013-12906 [20] A. Godwin, M. Agnew, and J. Stevenson, “Accuracy of inertial motion sensors in static, quasistatic, and complex dynamic motion,” Journal of Biomechanical Engineering, vol. 131, no. 11, p. 114501, 2009. doi: 10.1115/1.4000104 55 [21] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016. [22] W. T. Higgins, “A comparison of complementary and kalman filtering,” IEEE Transactions on Aerospace and Electronic Systems, vol. AES-11, no. 3, pp. 321 325, 1975. doi: 10.1109/TAES.1975.308081 [23] D. Q. Huynh, “Metrics for 3d rotations: Comparison and analysis,” Journal of Mathematical Imaging and Vision, vol. 35, pp. 155–164, 2009. [24] G. Ke et al., “Lightgbm: A highly efficient gradient boosting decision tree,” in Advances in Neural Information Processing Systems, 2017, pp. 3146–3154. [25] V. Labatut and H. Cherifi, “Accuracy measures for the comparison of classi fiers,” arXiv preprint arXiv:1207.3790, 2012. [26] D.Laidig, M.Caruso, A. Cereatti, and T. Seel, “Broad—a benchmark for robust inertial orientation estimation,” Data, vol. 6, no. 7, p. 72, 2021. [27] U.López, L. Trujillo, Y. Martinez, P. Legrand, E. Naredo, and S. Silva, “Ransac gp: Dealing withoutliers in symbolic regression with genetic programming,” in Genetic Programming, Springer, Cham, 2017, pp. 114–130. doi: 10.1007/978 3-319-55696-3\_8 [28] S. O. H. Madgwick, S. Wilson, R. Turk, J. Burridge, C. Kapatos, and R. Vaidyanathan, “An extended complementary filter for full-body marg orien tation estimation,” IEEE/ASME Transactions on Mechatronics, vol. 25, no. 4, pp. 2054–2064, 2020. doi: 10.1109/TMECH.2020.2992296 [29] S. O. Madgwick, A. J. Harrison, and R. Vaidyanathan, “Estimation of imu and marg orientation using a gradient descent algorithm,” in 2011 IEEE interna tional conference on rehabilitation robotics, Ieee, 2011, pp. 1–7. [30] R.Mahony,T.Hamel,andJ.-M.Pflimlin,“Nonlinearcomplementaryfilters on the special orthogonal group,” IEEE Transactions on automatic control, vol. 53, no. 5, pp. 1203–1218, 2008. [31] J. Marins, X. Yun, E. Bachmann, R. McGhee, and M. Zyda, “An extended kalman filter for quaternion-based orientation estimation using marg sensors,” inProceedings2001IEEE/RSJInternationalConferenceonIntelligentRobotsand Systems. ExpandingtheSocietal Role of Robotics in the the Next Millennium(Cat. No.01CH37180), vol. 4, 2001, 2003–2011 vol.4. doi: 10.1109/IROS.2001. 976367 [32] F.L.MarkleyandD.Mortari, “Quaternion attitude estimation using vector ob servations,” Journal of the Astronautical Sciences, vol. 48, no. 2–3, pp. 359–380, 2007. 56 [33] D. Maton et al., “Indirect tuning of a complementary orientation filter using velocity data and a genetic algorithm,” Systems Science & Control Engineering, vol. 12,no.1,p.2343303,2024.doi:10.1080/21642583.2024.2343303eprint: https://doi.org/10.1080/21642583.2024.2343303. [Online]. Available: https://doi.org/10.1080/21642583.2024.2343303 [34] P.S. Maybeck, Stochastic Models, Estimation, and Control: Volume 1. Academic Press, 1982. [35] A.Nawrat,K.Jedrasiak,K.Daniec,andR.Koteras,“Inertialnavigationsystems and its practical applications,” New approach of indoor andoutdoorlocalization systems, 2012. [36] A. Sabatini, “Quaternion-based extended kalman filter for determining orien tation by inertial and magnetic sensing,” IEEE Transactions on Biomedical En gineering, vol. 53, no. 7, pp. 1346–1356,2006.doi:10.1109/TBME.2006.875664 [37] W.Shao,J. Zang, J. Zhao, and K. Liu, “A variable gain complementary filtering fusion algorithm based on distributed inertial network and flush air data sens ing,” Applied Sciences, vol. 13, no. 14, 2023, issn: 2076-3417. doi: 10.3390/ app13148090 [Online]. Available: https://www.mdpi.com/2076-3417/13/ 14/8090 [38] M.K.Al-Sharman, Y. Zweiri, M. A. K. Jaradat, R. Al-Husari, D. Gan, and L. D. Seneviratne,“Deep-learning-basedneuralnetworktrainingforstateestimation enhancement:Applicationtoattitudeestimation,”IEEETransactionsonInstru mentationandMeasurement,vol.69,no.1,pp.24–34,2020.doi:10.1109/TIM. 2019.2895495 [39] N. El-Sheimy and A. Youssef, “Inertial sensors technologies for navigation ap plications: State of the art and future trends,” Satellite navigation, vol. 1, no. 1, p. 2, 2020. [40] M.D.SHUSTERandS.D.OH,“Three-axisattitude determination from vector observations,” Journal of Guidance and Control, vol. 4, no. 1, pp. 70–77, 1981. doi: 10.2514/3.19717 eprint: https://doi.org/10.2514/3.19717. [Online]. Available: https://doi.org/10.2514/3.19717 [41] M. D. Shuster et al., “A survey of attitude representations,” Navigation, vol. 8, no. 9, pp. 439–517, 1993. [42] D. Tedaldi, A. Pretto, and E. Menegatti, “A robust and easy to implement method for imu calibration without external equipments,” in 2014 IEEE Inter national Conference on Robotics and Automation (ICRA), 2014, pp. 3042–3049. doi: 10.1109/ICRA.2014.6907297 57 [43] R. G. Valenti, I. Dryanovski, and J. Xiao, “Keeping a good attitude: A quaternion-based orientation filter for imus and margs,” Sensors, vol. 15, no. 8, pp. 19302–19330, 2015. [44] E.VertzbergerandI.Klein,“Adaptiveattitudeestimationusingahybridmodel learning approach,” IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1–9, 2022. [45] M. Vezočnik, R. Kamnik, and M. B. Juric, “Inertial sensor-based step length estimation model by means of principal component analysis,” Sensors, vol. 21, no. 10, 2021, issn: 1424-8220. doi: 10.3390/s21103527 [Online]. Available: https://www.mdpi.com/1424-8220/21/10/3527 [46] G. Wahba, “A least squares estimate of satellite attitude,” SIAM Review, vol. 7, no. 3, pp. 409–409, 1965. doi: 10.1137/1007077 eprint: https://doi.org/ 10.1137/1007077. [Online]. Available: https://doi.org/10.1137/1007077 [47] E.WanandR.VanDerMerwe,“Theunscentedkalmanfilterfornonlinearesti mation,” in Proceedings of the IEEE2000AdaptiveSystemsforSignalProcessing, Communications, and Control Symposium (Cat. No.00EX373), 2000, pp. 153 158. doi: 10.1109/ASSPCC.2000.882463 [48] D.Weber, C. Gühmann, and T. Seel, “Neural networks versus conventional fil ters for inertial-sensor-based attitude estimation,” in 2020 IEEE 23rd Interna tional Conference on Information Fusion (FUSION), 2020, pp. 1–8. doi: 10. 23919/FUSION45008.2020.9190634 [49] S. Wilson et al., “Formulation of a new gradient descent marg orientation al gorithm: Case study on robot teleoperation,” Mechanical Systems and Signal Processing, vol. 130, pp. 183–200, 2019, issn: 0888-3270. doi: https://doi. org/10.1016/j.ymssp.2019.04.064 [Online]. Available: https://www. sciencedirect.com/science/article/pii/S0888327019303012 [50] S. Zhao, “Time derivative of rotation matrices: A tutorial,” arXiv preprint arXiv:1609.06088, 2016. [51] Z.Zhe,W.Jian-bin, S. Bo, and T. Guo-feng, “Adaptive complementary filtering algorithm for imu based on mems,” in 2020Chinese Control And Decision Con ference(CCDC),2020,pp.5409–5416.doi:10.1109/CCDC49329.2020.9164809
dc.identifier.urihttps://repository.iutoic-dhaka.edu/handle/123456789/2613
dc.language.isoen
dc.publisherDepartment of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh
dc.titleA Data Driven Toggling Gain Complementary Filtering Approach for Orientation Estimation
dc.typeThesis

Files

Original bundle

Now showing 1 - 2 of 2
Thumbnail Image
Name:
22 Fulltext_CSE_A Data Driven Toggling Gain Complementary Filtering Approach for 200041131_.pdf
Size:
5.42 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
22 Turnitin Report_ CSE_200041131_.pdf
Size:
357.83 KB
Format:
Adobe Portable Document Format
Download

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

2025