Abstract:

In the realm of vehicle dynamics， the sideslip angle is a critical parameter. For the challenges posed by the current model-based methods， which heavily rely on the accuracy of dynamic models， and the poor robustness of data-driven methods in unfamiliar operating conditions， in this paper a sideslip angle estimation method based on a hybrid of physics and data-driven approaches （DeepPhy） is proposed. The aim is to combine the strength of physical modeling and data-driven techniques to achieve reliable and accurate estimation of the sideslip angle. DeepPhy integrates prior values of the sideslip angle obtained from the lateral force model of the rear axle tires with a deep neural network， enabling the learning of nonlinear mapping relationship not captured by the physical model， thereby enhancing the model's reliability in unfamiliar conditions. The simulation results indicate that under continuous DLC conditions， the RMSE of the estimation results from DeepPhy is reduced by 93% compared to the physical model method and by 63% compared to the data-driven method， exhibiting robustness in scenarios with limited data. Real-world validation further confirms DeepPhy's exceptional generalization capabilities， as the models trained through simulation can be transferred to real-world conditions while maintaining high-precision estimation results.

Key words: sideslip angle estimation, active safety control, long short-term memory, physics-data hybrid driven