Vol. 1 No. 2 (2025)

Articles

AI-Augmented Kalman Filtering for Robust Sensor Fusion in Intelligent Localization System

Published 2025-11-03

  • Ozgun Pinarer

Ozgun Pinarer
Department of Computer Engineering, Galatasaray University, Istanbul 34349, Turkey

DOI: https://doi.org/10.64797/rwas.v1i2.77

Abstract

The research domain of positioning systems has become increasingly critical with the rapid expansion of applications in navigation, asset tracking, robotics, and autonomous systems. Conventional solutions primarily rely on Global Positioning System (GPS), which, despite its widespread use, suffers from high energy consumption and limited reliability in indoor or obstructed environments. To address these limitations, prior studies have explored Inertial Measurement Unit (IMU)-based sensor fusion approaches, including Kalman and particle filters, as well as hybrid schemes with intermittent GPS updates. Although these methods improve robustness, they remain limited in handling sensor drift, nonlinear dynamics, and adaptability to changing conditions. This paper addresses this gap by proposing an AI-augmented sensor fusion framework that integrates a deep learning–enhanced Kalman filter for robust IMU–GPS positioning. The proposed method uses a neural network to model nonlinear motion dynamics and adaptively correct estimation errors, thereby improving positioning performance while reducing reliance on frequent GPS measurements. Experimental evaluations under varying GPS sampling intervals demonstrate that the proposed approach maintains acceptable accuracy and precision while significantly reducing energy consumption and memory usage compared to GPS-only and conventional filtering methods. The main contribution of this work is the introduction of an adaptive, AI-driven sensor fusion architecture for resource-constrained embedded systems. By combining model-based estimation with data-driven correction, the framework offers a scalable and efficient solution for both indoor and outdoor localization. This study advances the state of the art by demonstrating that AI-augmented filtering can effectively balance accuracy, robustness, and resource efficiency in real-world positioning scenarios.

Keywords

AI-Augmented Kalman Filtering, Energy-Efficient Positioning Systems, IMU–GPS Sensor Fusion, Embedded Intelligent Localization

PDF

References

  1. [1] El-Sheimy, N., Youssef, A., 2020. Inertial Sensors Technologies for Navigation Applications: State of the Art and Future Trends. Satellite Navigation. 1(1), 2. DOI: https://doi.org/10.1186/s43020-019-0001-5
  2. [2] El-Sheimy, N., Li, Y., 2021. Indoor Navigation: State of the Art and Future Trends. Satellite Navigation. 2(1), 7. DOI: https://doi.org/10.1186/s43020-021-00041-3
  3. [3] Sattarian, M., Rezazadeh, J., Farahbakhsh, R., et al., 2019. Indoor Navigation Systems Based on Data Mining Techniques in Internet of Things: A Survey. Wireless Networks. 25, 1385–1402. DOI: https://doi.org/10.1007/s11276-018-1766-4
  4. [4] Farahsari, P.S., Farahzadi, A., Rezazadeh, J., et al., 2022. A Survey on Indoor Positioning Systems for IoT-Based Applications. IEEE Internet of Things Journal. 9(10), 7680–7699. DOI: https://doi.org/10.1109/JIOT.2022.3149048
  5. [5] Poulose, A., Senouci, B., Han, D.S., 2019. Performance Analysis of Sensor Fusion Techniques for Heading Estimation Using Smartphone Sensors. IEEE Sensors Journal. 19(24), 12369–12380. DOI: https://doi.org/10.1109/JSEN.2019.2940071
  6. [6] Hou, X., Bergmann, J., 2021. Pedestrian Dead Reckoning with Wearable Sensors: A Systematic Review. IEEE Sensors Journal. 21(1), 143–152. DOI: https://doi.org/10.1109/JSEN.2020.3014955
  7. [7] Chen, K., Tan, G., Cao, J., et al., 2020. Modeling and Improving the Energy Performance of GPS Receivers for Location Services. IEEE Sensors Journal. 20(8), 4512–4523. DOI: https://doi.org/10.1109/JSEN.2019.2962613
  8. [8] Krishnaveni, B.V., Reddy, K.S., Reddy, P.R., 2022. Indoor Tracking by Adding IMU and UWB Using Unscented Kalman Filter. Wireless Personal Communications. 123(4), 3575–3596. DOI: https://doi.org/10.1007/s11277-021-09304-3
  9. [9] Venkata Krishnaveni, B., Suresh Reddy, K., Ramana Reddy, P., 2023. Indoor Positioning and Tracking by Coupling IMU and UWB with the Extended Kalman Filter. IETE Journal of Research. 69(10), 6757–6766. DOI: https://doi.org/10.1080/03772063.2022.2028580
  10. [10] Feng, D., Wang, C., He, C., et al., 2020. Kalman-Filter-Based Integration of IMU and UWB for High-Accuracy Indoor Positioning and Navigation. IEEE Internet of Things Journal. 7(4), 3133–3146. DOI: https://doi.org/10.1109/JIOT.2020.2965115
  11. [11] Jiang, P., Chen, L., Guo, H., et al., 2021. Novel Indoor Positioning Algorithm Based on LiDar/Inertial Measurement Unit Integrated System. International Journal of Advanced Robotic Systems. 18(2). DOI: https://doi.org/10.1177/1729881421999923
  12. [12] Ali, R., Liu, R., Nayyar, A., et al., 2021. Tightly Coupling Fusion of UWB Ranging and IMU Pedestrian Dead Reckoning for Indoor Localization. IEEE Access. 9, 164206–164222. DOI: https://doi.org/10.1109/ACCESS.2021.3132645
  13. [13] Naheem, K., Kim, M.S., 2022. A Low-Cost Foot-Placed UWB and IMU Fusion-Based Indoor Pedestrian Tracking System for IoT Applications. Sensors. 22(21), 8160. DOI: https://doi.org/10.3390/s22218160
  14. [14] Tang, C., He, C., Dou, L., 2021. An IMU/ODM/UWB Joint Localization System Based on Modified Cubature Kalman Filtering. Sensors. 21(14), 4823. DOI: https://doi.org/10.3390/s21144823
  15. [15] Chen, C., Pan, X., 2024. Deep Learning for Inertial Positioning: A Survey. IEEE Transactions on Intelligent Transportation Systems. 25(9), 10506–10523. DOI: https://doi.org/10.1109/TITS.2024.3381161
  16. [16] Kim, S., Petrunin, I., Shin, H.-S., 2022. A Review of Kalman Filter with Artificial Intelligence Techniques. In Proceedings of the 2022 Integrated Communication, Navigation and Surveillance Conference (ICNS), Dulles, VA, USA, 5–7 April 2022; pp. 1–12. DOI: https://doi.org/10.1109/ICNS54818.2022.9771520
  17. [17] He, C., Tang, C., Yu, C., 2020. A Federated Derivative Cubature Kalman Filter for IMU-UWB Indoor Positioning. Sensors. 20(12), 3514. DOI: https://doi.org/10.3390/s20123514
  18. [18] Hodzic, M., Hubana, T., 2024. Artificial Intelligence-Based Fault Detection Using Kalman Filter Innovation Sequence. In: Ademović, N., Akšamija, Z., Karabegović, A. (Eds.). Advanced Technologies, Systems, and Applications IX. Springer: Cham, Switzerland. pp. 564–578. DOI: https://doi.org/10.1007/978-3-031-71694-2_39
  19. [19] Shlezinger, N., Revach, G., Ghosh, A., et al., 2025. Artificial Intelligence-Aided Kalman Filters: AI-Augmented Designs for Kalman-Type Algorithms. IEEE Signal Processing Magazine. 42(3), 52–76. DOI: https://doi.org/10.1109/MSP.2025.3569395
  20. [20] Shlezinger, N., Revach, G., Ghosh, A., et al., 2024. AI-Aided Kalman Filters. arXiv preprint. arXiv:2410.12289. DOI: https://doi.org/10.48550/arXiv.2410.12289
  21. [21] You, W., Li, F., Liao, L., et al., 2020. Data Fusion of UWB and IMU Based on Unscented Kalman Filter for Indoor Localization of Quadrotor UAV. IEEE Access. 8, 64971–64981. DOI: https://doi.org/10.1109/ACCESS.2020.2985053
  22. [22] Feng, D., Peng, J., Zhuang, Y., et al., 2023. An Adaptive IMU/UWB Fusion Method for NLOS Indoor Positioning and Navigation. IEEE Internet of Things Journal. 10(13), 11414–11428. DOI: https://doi.org/10.1109/JIOT.2023.3245144
  23. [23] You, Y., Wu, C., 2021. Hybrid Indoor Positioning System for Pedestrians with Swinging Arms Based on Smartphone IMU and RSSI of BLE. IEEE Transactions on Instrumentation and Measurement. 70, 1–15. DOI: https://doi.org/10.1109/TIM.2021.3084286
  24. [24] Vashist, A., Li, M.P., Ganguly, A., et al., 2021. KF-Loc: A Kalman Filter and Machine Learning Integrated Localization System Using Consumer-Grade Millimeter-Wave Hardware. IEEE Consumer Electronics Magazine. 11(4), 65–77. DOI: https://doi.org/10.1109/MCE.2021.3101060
  25. [25] Liu, J., Guo, G., 2021. Vehicle Localization during GPS Outages with Extended Kalman Filter and Deep Learning. IEEE Transactions on Instrumentation and Measurement. 70, 1–10. DOI: https://doi.org/10.1109/TIM.2021.3097401
  26. [26] Kayhani, N., Zhao, W., McCabe, B., et al., 2022. Tag-Based Visual-Inertial Localization of Unmanned Aerial Vehicles in Indoor Construction Environments Using an On-Manifold Extended Kalman Filter. Automation in Construction. 135, 104112. DOI: https://doi.org/10.1016/j.autcon.2021.104112
  27. [27] Jamil, F., Iqbal, N., Ahmad, S., et al., 2020. Toward Accurate Position Estimation Using Learning to Prediction Algorithm in Indoor Navigation. Sensors. 20(16), 4410. DOI: https://doi.org/10.3390/s20164410
  28. [28] Poulose, A., Eyobu, O.S., Han, D.S., 2019. An Indoor Position-Estimation Algorithm Using Smartphone IMU Sensor Data. IEEE Access. 7, 11165–11177. DOI: https://doi.org/10.1109/ACCESS.2019.2891942
  29. [29] Zhang, H., Zhang, Z., Gao, N., et al., 2020. Cost-Effective Wearable Indoor Localization and Motion Analysis via the Integration of UWB and IMU. Sensors. 20(2), 344. DOI: https://doi.org/10.3390/s20020344
  30. [30] Zhao, H., Zhang, L., Qiu, S., et al., 2019. Pedestrian Dead Reckoning Using Pocket-Worn Smartphone. IEEE Access. 7, 91063–91073. DOI: https://doi.org/10.1109/ACCESS.2019.2927053
  31. [31] Wen, K., Yu, K., Li, Y., et al., 2020. A New Quaternion Kalman Filter Based Foot-Mounted IMU and UWB Tightly-Coupled Method for Indoor Pedestrian Navigation. IEEE Transactions on Vehicular Technology. 69(4), 4340–4352. DOI: https://doi.org/10.1109/TVT.2020.2974667
  32. [32] Yang, X., Wang, J., Song, D., et al., 2021. A Novel NLOS Error Compensation Method Based IMU for UWB Indoor Positioning System. IEEE Sensors Journal. 21(9), 11203–11212. DOI: https://doi.org/10.1109/JSEN.2021.3061468
  33. [33] Liu, J., Priyantha, B., Hart, T., et al., 2015. CO-GPS: Energy Efficient GPS Sensing with Cloud Offloading. IEEE Transactions on Mobile Computing. 15(6), 1348–1361. DOI: https://doi.org/10.1109/TMC.2015.2446461
  34. [34] Paek, J., Kim, J., Govindan, R., 2010. Energy-Efficient Rate-Adaptive GPS-Based Positioning for Smartphones. In Proceedings of the 8th International Conference on Mobile Systems, Applications, and Services, San Francisco, CA, USA, 15–18 June 2010; pp. 299–314. DOI: https://doi.org/10.1145/1814433.1814463
  35. [35] Kaczmarek, A., Rohm, W., Klingbeil, L., et al., 2022. Experimental 2D Extended Kalman Filter Sensor Fusion for Low-Cost GNSS/IMU/Odometers Precise Positioning System. Measurement. 193, 110963. DOI: https://doi.org/10.1016/j.measurement.2022.110963
  36. [36] Bai, N., Tian, Y., Liu, Y., et al., 2020. A High-Precision and Low-Cost IMU-Based Indoor Pedestrian Positioning Technique. IEEE Sensors Journal. 20(12), 6716–6726. DOI: https://doi.org/10.1109/JSEN.2020.2976102
  37. [37] Kim, D.H., Kim, Y., Estrin, D., et al., 2010. Sensloc: Sensing Everyday Places and Paths Using Less Energy. In Proceedings of the 8th ACM Conference on Embedded Networked Sensor Systems, Zürich, Switzerland, 3–5 November 2010; pp. 43–56. DOI: https://doi.org/10.1145/1869983.1869989
  38. [38] Menegazzo, J., 2021. PVS—Passive Vehicular Sensors Datasets. Kaggle. DOI: https://doi.org/10.34740/KAGGLE/DS/1105310 (cited 1 September 2025).
  39. [39] Habeeb, M.A., Khaleel, Y.L., Abdulnabi, A.R., 2024. Enhancing Security and Performance in Vehicular Adhoc Networks: A Machine Learning Approach to Combat Adversarial Attacks. Mesopotamian Journal of Computer Science. 2024, 122–133. DOI: https://doi.org/10.58496/MJCSC/2024/010