Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A-KIT: Adaptive Kalman-Informed Transformer (2401.09987v1)

Published 18 Jan 2024 in cs.RO, cs.AI, cs.SY, and eess.SY

Abstract: The extended Kalman filter (EKF) is a widely adopted method for sensor fusion in navigation applications. A crucial aspect of the EKF is the online determination of the process noise covariance matrix reflecting the model uncertainty. While common EKF implementation assumes a constant process noise, in real-world scenarios, the process noise varies, leading to inaccuracies in the estimated state and potentially causing the filter to diverge. To cope with such situations, model-based adaptive EKF methods were proposed and demonstrated performance improvements, highlighting the need for a robust adaptive approach. In this paper, we derive and introduce A-KIT, an adaptive Kalman-informed transformer to learn the varying process noise covariance online. The A-KIT framework is applicable to any type of sensor fusion. Here, we present our approach to nonlinear sensor fusion based on an inertial navigation system and Doppler velocity log. By employing real recorded data from an autonomous underwater vehicle, we show that A-KIT outperforms the conventional EKF by more than 49.5% and model-based adaptive EKF by an average of 35.4% in terms of position accuracy.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. M. I. Ribeiro, “Kalman and extended Kalman filters: Concept, derivation and properties,” Institute for Systems and Robotics, vol. 43, no. 46, pp. 3736–3741, 2004.
  2. E. A. Wan and R. Van Der Merwe, “The unscented Kalman filter for nonlinear estimation,” in Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No. 00EX373).   IEEE, 2000, pp. 153–158.
  3. F. Daum, “Nonlinear filters: Beyond the Kalman filter,” IEEE Aerospace and Electronic Systems Magazine, vol. 20, no. 8, pp. 57–69, 2005.
  4. H. Heffes, “The effect of erroneous models on the Kalman filter response,” IEEE Transactions on Automatic Control, vol. 11, no. 3, pp. 541–543, 1966.
  5. S. Sangsuk-Iam and T. E. Bullock, “Analysis of discrete-time Kalman filtering under incorrect noise covariances,” IEEE Transactions on Automatic Control, vol. 35, no. 12, pp. 1304–1309, 1990.
  6. S. S. Saab, “Discrete-time Kalman filter under incorrect noise covariances,” in Proceedings of 1995 American Control Conference-ACC’95, vol. 2.   IEEE, 1995, pp. 1152–1156.
  7. R. Mehra, “On the identification of variances and adaptive Kalman filtering,” IEEE Transactions on Automatic Control, vol. 15, no. 2, pp. 175–184, 1970.
  8. L. Zhang, D. Sidoti, A. Bienkowski, K. R. Pattipati, Y. Bar-Shalom, and D. L. Kleinman, “On the identification of noise covariances and adaptive Kalman filtering: A new look at a 50 year-old problem,” IEEE Access, vol. 8, pp. 59 362–59 388, 2020.
  9. Y. Li, R. Chen, X. Niu, Y. Zhuang, Z. Gao, X. Hu, and N. El-Sheimy, “Inertial sensing meets machine learning: Opportunity or challenge?” IEEE Transactions on Intelligent Transportation Systems, 2021.
  10. N. Cohen and I. Klein, “Inertial Navigation Meets Deep Learning: A Survey of Current Trends and Future Directions,” arXiv preprint arXiv:2307.00014, 2023.
  11. A. Abosekeen, A. Noureldin, and M. J. Korenberg, “Improving the RISS/GNSS land-vehicles integrated navigation system using magnetic azimuth updates,” IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 3, pp. 1250–1263, 2019.
  12. A. Mohamed and K. Schwarz, “Adaptive Kalman filtering for INS/GPS,” Journal of Geodesy, vol. 73, pp. 193–203, 1999.
  13. C. Hide, T. Moore, and M. Smith, “Adaptive Kalman filtering for low-cost INS/GPS,” The Journal of Navigation, vol. 56, no. 1, pp. 143–152, 2003.
  14. Y. Liu, X. Fan, C. Lv, J. Wu, L. Li, and D. Ding, “An innovative information fusion method with adaptive Kalman filter for integrated INS/GPS navigation of autonomous vehicles,” Mechanical Systems and Signal Processing, vol. 100, pp. 605–616, 2018.
  15. H. Shen, G. Wen, Y. Lv, J. Zhou, and L. Wang, “USV parameter estimation: Adaptive unscented Kalman filter-based approach,” IEEE Transactions on Industrial Informatics, 2022.
  16. W. Gao, J. Li, G. Zhou, and Q. Li, “Adaptive Kalman filtering with recursive noise estimator for integrated SINS/DVL systems,” The Journal of Navigation, vol. 68, no. 1, pp. 142–161, 2015.
  17. D. Wang, X. Xu, and L. Hou, “An improved adaptive Kalman filter for underwater SINS/DVL system,” Mathematical Problems in Engineering, vol. 2020, pp. 1–14, 2020.
  18. D. C. Silva, A. Frutuoso, L. F. Souza, and E. A. de Barros, “Comparative Analysis of Innovation-Based Adaptive Kalman Filters Applied to AUVs Navigation,” in 2022 Latin American Robotics Symposium (LARS), 2022 Brazilian Symposium on Robotics (SBR), and 2022 Workshop on Robotics in Education (WRE).   IEEE, 2022, pp. 31–36.
  19. Q. Wang, K. Liu, and Z. Cao, “System noise variance matrix adaptive Kalman filter method for AUV INS/DVL navigation system,” Ocean Engineering, vol. 267, p. 113269, 2023.
  20. B. Or and I. Klein, “ProNet: Adaptive process noise estimation for INS/DVL fusion,” in 2023 IEEE Underwater Technology (UT), 2023, pp. 1–5.
  21. M. Brossard, A. Barrau, and S. Bonnabel, “AI-IMU dead-reckoning,” IEEE Transactions on Intelligent Vehicles, vol. 5, no. 4, pp. 585–595, 2020.
  22. X. Gao, H. Luo, B. Ning, F. Zhao, L. Bao, Y. Gong, Y. Xiao, and J. Jiang, “RL-AKF: An adaptive Kalman filter navigation algorithm based on reinforcement learning for ground vehicles,” Remote Sensing, vol. 12, no. 11, p. 1704, 2020.
  23. F. Wu, H. Luo, H. Jia, F. Zhao, Y. Xiao, and X. Gao, “Predicting the noise covariance with a multitask learning model for Kalman filter-based GNSS/INS integrated navigation,” IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1–13, 2020.
  24. Y. Xiao, H. Luo, F. Zhao, F. Wu, X. Gao, Q. Wang, and L. Cui, “Residual attention network-based confidence estimation algorithm for non-holonomic constraint in GNSS/INS integrated navigation system,” IEEE Transactions on Vehicular Technology, vol. 70, no. 11, pp. 11 404–11 418, 2021.
  25. Z. Zou, T. Huang, L. Ye, and K. Song, “CNN based adaptive Kalman filter in high-dynamic condition for low-cost navigation system on highspeed UAV,” in 2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS).   IEEE, 2020, pp. 103–108.
  26. B. Or and I. Klein, “A hybrid model and learning-based adaptive navigation filter,” IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1–11, 2022.
  27. R. Huang, M. Lei, X. Zhang, L. Zhou, Y. Lu, and B. He, “LSTM-based Process Noise Covariance Prediction for AUV Navigation,” in 2023 IEEE 7th Information Technology and Mechatronics Engineering Conference (ITOEC), vol. 7.   IEEE, 2023, pp. 1657–1661.
  28. B. Or and I. Klein, “Adaptive step size learning with applications to velocity aided inertial navigation system,” IEEE Access, vol. 10, pp. 85 818–85 830, 2022.
  29. T. Haarnoja, A. Ajay, S. Levine, and P. Abbeel, “Backprop KF: Learning discriminative deterministic state estimators,” Advances in Neural Information Processing Systems, vol. 29, 2016.
  30. S. Jouaber, S. Bonnabel, S. Velasco-Forero, and M. Pilte, “Nnakf: A neural network adapted Kalman filter for target tracking,” in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).   IEEE, 2021, pp. 4075–4079.
  31. P. D. Groves, “Principles of GNSS, inertial, and multisensor integrated navigation systems,” IEEE Aerospace and Electronic Systems Magazine, vol. 30, no. 2, pp. 26–27, 2015.
  32. R. Mehra, “Approaches to adaptive filtering,” IEEE Transactions on Automatic Control, vol. 17, no. 5, pp. 693–698, 1972.
  33. W. Ding, J. Wang, C. Rizos, and D. Kinlyside, “Improving adaptive Kalman estimation in GPS/INS integration,” The Journal of Navigation, vol. 60, no. 3, pp. 517–529, 2007.
  34. A. Almagbile, J. Wang, and W. Ding, “Evaluating the performances of adaptive Kalman filter methods in GPS/INS integration,” Journal of Global Positioning Systems, vol. 9, no. 1, pp. 33–40, 2010.
  35. S. Akhlaghi, N. Zhou, and Z. Huang, “Adaptive adjustment of noise covariance in Kalman filter for dynamic state estimation,” in 2017 IEEE power & energy society general meeting.   IEEE, 2017, pp. 1–5.
  36. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv preprint arXiv:2010.11929, 2020.
  37. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in Neural Information Processing Systems, vol. 30, 2017.
  38. J. Lee, Y. Lee, J. Kim, A. Kosiorek, S. Choi, and Y. W. Teh, “Set transformer: A framework for attention-based permutation-invariant neural networks,” in International conference on machine learning.   PMLR, 2019, pp. 3744–3753.
  39. E.-H. Shin and N. El-Sheimy, “Accuracy improvement of low cost INS/GPS for land applications,” in Proceedings of the 2002 National Technical Meeting of the Institute of Navigation, 2002, pp. 146–157.
  40. N. A. Brokloff, “Matrix algorithm for Doppler sonar navigation,” in Proceedings of OCEANS’94, vol. 3.   IEEE, 1994, pp. III–378.
  41. D. Rudolph and T. A. Wilson, “Doppler Velocity Log theory and preliminary considerations for design and construction,” in 2012 Proceedings of IEEE Southeastcon.   IEEE, 2012, pp. 1–7.
  42. A. Tal, I. Klein, and R. Katz, “Inertial navigation system/Doppler velocity log (INS/DVL) fusion with partial DVL measurements,” Sensors, vol. 17, no. 2, p. 415, 2017.
  43. N. Cohen and I. Klein, “BeamsNet: A data-driven approach enhancing Doppler velocity log measurements for autonomous underwater vehicle navigation,” Engineering Applications of Artificial Intelligence, vol. 114, p. 105216, 2022.
  44. F. L. Markley, “Attitude determination using vector observations and the singular value decomposition,” Journal of the Astronautical Sciences, vol. 36, no. 3, pp. 245–258, 1988.
  45. I. Klein and R. Diamant, “Observability analysis of DVL/PS aided INS for a maneuvering AUV,” Sensors, vol. 15, no. 10, pp. 26 818–26 837, 2015.
  46. ECA Group, “A18-D AUV: Autonomous Underwater Vehicle,” https://www.ecagroup.com/en/solutions/a18-d-auv-autonomous-underwater-vehicle, Accessed: September 2023.
  47. iXblue, “PHINS Subsea,” https://www.ixblue.com/store/phins-subsea/, Accessed: September 2023.
  48. Teledyne Marine, “Doppler Velocity Logs,” https://www.teledynemarine.com/products/product-line/navigation-positioning/doppler-velocity-logs, Accessed: September 2023.
  49. iXblue, “DELPH INS,” https://www.ixblue.com/store/delph-ins/, Accessed: September 2023.
Citations (8)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now