Bayesian Network Enhanced Multi-model Algorithm and its Application in Integrated Navigation System

The uncertainty of the model parameters of integrated navigation system and the instability of the system model are characteristic of unstructured environment. For these systems, large estimation errors are likely to occur if a fixed single model is used for navigation solutions. To solve this problem, a Bayesian network enhanced interacting multiple model (BN-IMM) filtering algorithm is proposed. In the proposed algorithm, certain motion characteristic variables are introduced on the basis of multi-model estimation, and Bayesian networks are established according to the causal relationship between variables and the system model. Bayesian network parameters are used to modify the model switching probability in multi-model estimation, which can reduce the dependence of real model recognition on prior knowledge in multi-model algorithm. The proposed algorithm can solve the problems such as model conversion lag and model probability mutation in the interacting multi-model (IMM) algorithm, and enhance the adaptive ability of the multi-model algorithm. The proposed BN-IMM was utilized as a local sub-filter within a federated filter, establishing an information fusion algorithm architecture for the strapdown inertial navigation system (SINS)/global positioning system (GPS)/odometer integrated navigation system. In the test, the output of gyro and accelerometer was taken as characteristic variables to build a Bayesian network. The established Bayesian network was used to dynamically predict the uncertainties in the integrated navigation system. The actual road tests demonstrate that the proposed federated BN-IMM algorithm can significantly enhance the stability and accuracy of state estimation in the integrated navigation system.

1. Lu, H., Wang, P., Qu, T., Chen, H., Zhang, L., and Hu Y., Moving horizon estimation with variable structure interacting multiple model for surrounding vehicle states in complex environments, IEEE Transactions on Intelligent Transportation Systems, 2024, vol. 25(12), pp. 19943–19961, https://doi.org/10.1109/TITS.2024.3467042.

2. Lei, W., Shicheng, X., Hengliu, X., Shuangxi, L., and Le, W., Robust visual inertial odometry estimation based on adaptive interacting multiple model algorithm, International Journal of Control, Automation and Systems, 2022, vol. 20, pp. 3335–3346, https://doi.org/10.1007/s1255502007812.

3. Gomaa, M. A. K., De Silva, O., Jayasiri, A., and Mann, G.K.I., Towards consistent visualinertial navigation for unmanned aerial vehicles using depth information, IEEE Transactions on Aerospace and Electronic Systems, 2021, vol. 57, pp. 1423–1442, https://doi.org/10.1109/CCECE49351.2022.9918398.

4. Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., and Neira, J., Past, present, and future of simultaneous localization and mapping: Toward the robustperception age, IEEE Transactions on Robotics, 2016, vol. 32, pp. 1309–1332, https://doi.org/10.1109/TRO.2016.2624754.

5. Choi, J. and Maurer, M., Local volumetric hybridmapbased simultaneous localization and mapping with moving object tracking, IEEE Transactions on Intelligent Transportation Systems, 2016, vol. 17, pp. 2440–2455, https://doi.org/10.1109/TITS.2016.2519536.

6. Yong, H. K., Min, J. C., Eung, J. K., and Jin, W. S., Magnetic map matching aided pedestrian navigation using outlier mitigation based on multiple sensors and roughness weighting, Sensors, 2019, vol. 19(21), p. 4782, https://doi.org/10.3390/s19214782.

7. Lei, W. and Shuangxi, L., Enhanced multisensor data fusion methodology based on multiple model estimation for integrated navigation system, International Journal of Control, Automation and Systems, 2018, vol. 16, pp. 295–305, https://doi.org/10.1007/s125550160200x.

8. Johnston, L.A., Krishnamurthy, V., An improvement to the interacting multiple model (IMM) algorithm, IEEE Transactions on Signal Processing, 2001, vol. 49(12), pp. 2909–2923, https://doi.org/10.1109/78.969500.

9. Blom, H. A. P and BarShalom, Y., The interacting multiple model algorithm for systems with Markov switching coefficients, IEEE Transactions on Automatic Control, 1988, vol. 33, pp. 780–783, https://doi.org/10.1109/9.1299.

10. Li, X. R., Jilkov, V. P., Ru, J. F., and Bashi, A., Multiplemodel estimation with variable structure. Part VI: expectedmode augmentation, IEEE Transactions on Aerospace and Electronic Systems, 2005, vol. 41, pp. 853–867, https://doi.org/10.1109/TAES.2005.1541435.

11. Hwang, I., Seah, C. E., and Lee, S., A study on stability of the interacting multiple model algorithm, IEEE Transactions on Automatic Control, 2017, vol. 62(2), pp. 901–906, https://doi.org/10.1109/TAC.2016.2558156.

12. Luo, X. B., Wang, H. Q., and Li, X., Interacting multiple model algorithm with adaptive Markov transition probabilities, Journal of Electronics and Information Technology, 2005, vol. 27, pp. 1539–1541, https://doi.org/10.1081/CEH200044273.

13. Liang, Y., Zhou, D. H., and Pan, Q., Multiple model estimation represented by Bayesian networks, Proc. Fourth World Congress on Intelligent Control and Automation (WCICA’04), Shanghai, 2002, pp. 863–866, https://doi.org/10.1109/WCICA.2002.1020696.

14. Yang, Y., Liu, X., Liu, X., Guo, Y., and Zhang, W., Modelfree integrated navigation of small fixedwing UAVs full state estimation in wind disturbance, IEEE Sensors Journal, 2022, vol. 22, pp. 2771–2781, https://doi.org/10.1109/JSEN.2021.3139842.

15. Shi, W., Xu, J., He, H., Li, D., Tang, H., and Lin, E., Faulttolerant SINS/HSB/DVL underwater integrated navigation system based on variational Bayesian robust adaptive Kalman filter and adaptive information sharing factor, Measurement, 2022, vol. 10, pp. 196–225, https://doi.org/10.1016/j.measurement.2022.111225.

16. Beauvisage, A., Ahiska, K. and Aouf, N., Robust multispectral visualinertial navigation with visual odometry failure recovery, IEEE Transactions on Intelligent Transportation Systems, 2022, vol. 7, pp. 9089–9101, https://doi.org/10.1109/TITS.2021.3090675.

17. Chang, T., Zhao, L., Zeng, Q., Hu, Y., Tao, X., and Ji, X., Variational Bayesianbased adaptive errorstate Kalman filter with application on LiDARinertial integrated navigation system, IEEE Sensors Journal, 2024, vol. 24(13), pp. 21331–21338, https://doi.org/10.1109/JSEN.2024.3402313.

18. Wang, Z., Li, X., Zhu, Y., Li, Q., and Fang, K., Integrity monitoring of global navigation satellite system/ inertial navigation system integrated navigation system based on dynamic fading filter optimization, IET Radar, Sonar and Navigation, 2022, vol. 16, pp. 515–530, https://doi.org/10.1049/rsn2.12199.

19. Hosseini, S.M., Ranjbar, N.A., and Sadati, R.S.J., Integrated navigation system (INS/auxiliary sensor) based on adaptive robust Kalman filter with partial measurements, Transactions of the Institute of Measurement and Control, 2023, vol. 45, pp. 316–330, https://doi.org/10.1177/01423312221112192.

20. Du, S., Huang, Y., Lin, B., Qian, J., and Zhang, Y., A lie group manifoldbased nonlinear estimation algorithm and its application to lowaccuracy SINS/GNSS integrated navigation, IEEE Transactions on Instrumentation and Measurement, 2022, vol. 71, pp. 2927–2954, https://doi.org/10.1109/TIM.2022.3159950.

21. Taghizadeh, S., Nezhadshahbodaghi, M., Safabakhsh, R., and Mosavi, M.R., A lowcost integrated navigation system based on factor graph nonlinear optimization for autonomous flight, GPS Solutions, 2022, vol. 26, pp. 78–93, https://doi.org/10.1007/s10291022012659.

22. Xiao, Y., Luo, H., Zhao, F., Wu, F., Gao, X., Wang, Q., and Cui, L., Residual attention networkbased confidence estimation algorithm for nonholonomic constraint in GNSS/INS integrated navigation system, IEEE Transactions on Vehicular Technology, 2021, vol. 70, pp. 11404–11418, https://doi.org/10.1109/TVT.2021.3113500.

23. Khalife, J. and Kassas, Z.M., A static reducedorder multiplemodel adaptive estimator for noise identification, IEEE Transactions on Aerospace and Electronic Systems, 2023, vol. 6, p. 114, https://doi.org/10.1109/TAES.2023.3234523.

24. Yang, Y., Liu, X., Liu, X., Guo, Y., and Zhang, W., Variational adaptive LMIEKF for full state navigation system of wind disturbance and observability analysis, IEEE Transactions on Instrumentation and Measurement, 2022, vol. 71, p. 112, https://doi.org/10.1109/TIM.2022.3191713.

25. Zhang, X., He, B., Gao, S., Mu, P., Xu, J., and Zhai, N., Multiple model AUV navigation methodology with adaptivity and robustness, Ocean Engineering, 2022, vol. 254, p. 111258, https://doi.org/10.1016/j.oceaneng.2022.111258.

26. Thanh, L. H., Phung, S. L., and Bouzerdoum, A., Bayesian Gabor network with uncertainty estimation for pedestrian lane detection in assistive navigation, IEEE Transactions on Circuits and Systems for Video Technology, 2022, vol. 32, pp. 5331–5345, https://doi.org/10.1109/TCSVT.2022.3144184.

27. Liu, X., Liu, X., Yang, Y., Guo, Y., and Zhang, W., Variational Bayesianbased robust cubature Kalman filter with application on SINS/GPS integrated navigation system, IEEE Sensors Journal, 2022, vol. 22, pp. 489–500, https://doi.org/10.1109/JSEN.2021.3127191.

28. Mumuni, F. and Mumuni, A., Bayesian cue integration of structure from motion and CNNbased monocular depth estimation for autonomous robot navigation, International Journal of Intelligent Robotics and Applications, 2022, vol. 6, pp. 191–206, https://doi.org/10.1007/s41315022002262.

29. Hu, Y., He, X., Zhang, L., and Sun, C., IMM fusion estimation with multiple asynchronous sensors, Signal Processing, 2014, vol. 102, pp. 46–57, https://doi.org/10.1016/j.sigpro.2014.02.019.

30. Carlson, N.A., Federated filter for faulttolerant integrated navigation systems, Position Location and Navigation Symposium (PLANS ‘88), Orlando, 1988, https://doi.org/10.1109/plans.1988.195473.

31. Lyu, W., Cheng, X., and Wang, J., Adaptive federated IMM filter for AUV integrated navigation systems, Sensors, 2020, vol. 20(23), pp. 6806–6830, https://doi.org/10.3390/s20236806.

32. Savage, P.G., Strapdown inertial navigation integration algorithm design. Part 1: Attitude algorithms, Journal of Guidance, Control, and Dynamics, 1998, vol. 21(1), pp. 19–28, https://doi.org/10.2514/2.4242.

33. Savage, P.G., Strapdown inertial navigation integration algorithm design. Part 2: Velocity and position algorithms, Journal of Guidance, Control, and Dynamics, 1998, vol. 21(2), pp. 208–221, https://doi.org/10.2514/2.4242.

34. Seo, J., Lee, J. G., Park, C.G., Lever arm compensation for integrated navigation system of land vehicles, Proc. IEEE Conference on Control Applications, Toronto, 2005, pp. 523–528, https://doi.org/10.1109/CCA.2005.1507179.

35. Hide, C., Moore, T., and Smith, M., Adaptive Kalman filtering for lowcost INS/GPS, Journal of Navigation, 2003, vol. 56(1), pp. 143–152, https://doi.org/10.1017/S0373463302002151.

36. Tupysev, V.A. and Litvinenko, Yu.A., The effect of the local filter adjustment on the accuracy of federated filters, Proc. First Modelling Identification and Control of Nonlinear Systems (MICNON 2015), Saint Petersburg, 2015, pp. 349–354, https://doi.org/10.1016/j.ifacol.2015.09.208.

37. Gao, S., Zhong, Y., Zhang, X., and Shirinzadeh, B., Multisensor optimal data fusion for INS/GPS/SAR integrated navigation system, Aerospace Science and Technology, 2009, vol. 13(45), pp. 232–237, https://doi.org/10.1016/j.ast.2009.04.006.