Car longitudinal acceleration observer based on the Kalman Filter with neural system dynamics model

Ivan Gromov

Abstract


An accurate car longitudinal acceleration estimation is a task that requires a wide range of factors to be taken into account: the dynamics model, the types of sensors used, etc. This paper presents an approach to car longitudinal acceleration observer development based on an extended Kalman filter. System model used in the filter for state prediction. Both an analytical model of the longitudinal dynamics of the system and its neural network model are considered. The accuracy of observers based on both models was compared after preliminary automated adjustment of the filter parameters using the particle swarm method. The paper presents in detail the derivation of prediction and measurement models for the proposed observer. To set up the filter and evaluate its accuracy, real data obtained from the passenger car's CAN bus was used.


Full Text:

PDF (Russian)

References


Jeon S., Tomizuka M. Benefits of acceleration measurement in velocity estimation and motion control //Control Engineering Practice. – 2007. – Т. 15. – №. 3. – С. 325-332.

Marotta R. et al. On the prediction of the sideslip angle using dynamic neural networks //IEEE Open Journal of Intelligent Transportation Systems. – 2024. – Т. 5. – С. 281-295.

De Winkel K. N. et al. Standards for passenger comfort in automated vehicles: Acceleration and jerk //Applied Ergonomics. – 2023. – Т. 106. – С. 103881.

Сысоева С. Интеллектуальные автомобильные ассистенты и датчики. Функций-больше," железа"-меньше //Компоненты и технологии. – 2012. – №. 1 (126). – С. 7-18.

Сысоева С. Автомобильные акселерометры. Часть 3. Классификация и анализ базовых рабочих принципов //Компоненты и технологии. – 2006. – №. 55. – С. 42-49.

Oniz Y., Kayacan E., Kaynak O. A dynamic method to forecast the wheel slip for antilock braking system and its experimental evaluation //IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics). – 2008. – Т. 39. – №. 2. – С. 551-560.

Rajamani R. Vehicle dynamics and control. – Boston, MA : Springer US, 2006.

Matsuzaki R., Kamai K., Seki R. Intelligent tires for identifying coefficient of friction of tire/road contact surfaces using three-axis accelerometer //Smart Materials and Structures. – 2015. – Т. 24. – №. 2. – С. 025010.

Wang X. et al. Review of State Estimation Methods for Autonomous Ground Vehicles: Perspectives on Estimation Objects, Vehicle Characteristics, and Key Algorithms //Sensors. – 2025. – Т. 25. – №. 13. – С. 3927.

Park S. et al. Model predictive control-based fault detection and reconstruction algorithm for longitudinal control of autonomous driving vehicle using multi-sliding mode observer //Microsystem Technologies. – 2020. – Т. 26. – №. 1. – С. 239-264.

Li J. et al. Research on vehicle stability control based on a union disturbance observer and improved adaptive unscented Kalman filter //Electronics. – 2024. – Т. 13. – №. 16. – С. 3220.

Liu Y., Cui D., Peng W. Vehicle state and parameter estimation based on adaptive robust unscented particle filter //Journal of Vibroengineering. – 2023. – Т. 25. – №. 2. – С. 392-408.

Napolitano Dell’Annunziata G. et al. Estimation of vehicle longitudinal velocity with artificial neural network //Sensors. – 2022. – Т. 22. – №. 23. – С. 9516.

Qiao Y. et al. Curvature-Constrained Vector Field for Motion Planning of Nonholonomic Robots //IEEE Transactions on Robotics. – 2025.

Tan C. et al. Vehicle state estimation combining physics-informed neural network and unscented Kalman filtering on manifolds //Sensors. – 2023. – Т. 23. – №. 15. – С. 6665.

Qi D. et al. Maximum correntropy extended Kalman filter for vehicle state observation //International journal of automotive technology. – 2023. – Т. 24. – №. 2. – С. 377-388.

Иоффе М. Л. Принцип Аккермана и его реализации в современных автомобилях //Известия высших учебных заведений. Машиностроение. – 2021. – №. 9 (738). – С. 40-47.

Zhang T. et al. A survey of vehicle dynamics modeling methods for autonomous racing: Theoretical models, physical/virtual platforms, and perspectives //IEEE Transactions on Intelligent Vehicles. – 2024. – Т. 9. – №. 3. – С. 4312-4334.

James S. S., Anderson S. R., Da Lio M. Longitudinal vehicle dynamics: A comparison of physical and data-driven models under large-scale real-world driving conditions //Ieee Access. – 2020. – Т. 8. – С. 73714-73729.

Cai L. et al. Towards auto-tuning of Kalman filters for underwater gliders based on consistency metrics //OCEANS 2019 MTS/IEEE SEATTLE. – IEEE, 2019. – С. 1-6.

Fraser C., Ulrich S. An adaptive Kalman filter for spacecraft formation navigation using maximum likelihood estimation with intrinsic smoothing //2018 Annual American Control Conference (ACC). – IEEE, 2018. – С. 5843-5848.

Oshman Y., Shaviv I. Optimal tuning of a Kalman filter using genetic algorithms //AIAA guidance, navigation, and control conference and exhibit. – 2000. – С. 4558.

Chen Z. et al. Kalman filter tuning with Bayesian optimization //arXiv preprint arXiv:1912.08601. – 2019.

Kennedy J., Eberhart R. Particle swarm optimization //Proceedings of ICNN'95-international conference on neural networks. – ieee, 1995. – Т. 4. – С. 1942-1948.

Labbe R. R. Filterpy documentation. [Online]. – URL: https://filterpy.readthedocs.io/en/latest/ (accessed 01.03.2026).

Paszke A. et al. Pytorch: An imperative style, high-performance deep learning library //Advances in neural information processing systems. – 2019. – Т. 32. [Online]. – URL: https://github.com/pytorch/pytorch (accessed 01.03.2026).


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность Monetec 2026 СНЭ

ISSN: 2307-8162