A Hybrid Model for Vehicle Sideslip Angle Estimation Based on Attention Regression

Vehicle Active Control Systems (ACS) have been developed to advance driver convenience and safety. These systems require accurate vehicle states such as lateral and longitudinal acceleration, sideslip angle, and yaw rate. However, achieving the desired accuracy without dedicated costly sensors is challenging. As a result, various methods have been developed for vehicle state estimation. This study proposes a hybrid model to estimate critical vehicle states, i.e., sideslip angle and yaw rate, by integrating a two-degree-of-freedom single-track model, namely a bicycle model and a self-attention-based regression model. The regression model dynamically estimates tire cornering stiffness, a key parameter in the bicycle model. Using the varying estimates of tire cornering stiffness, the bicycle model accurately derives the sideslip angle and yaw rate. A new loss function is presented for practical learning of the attention regression model. Moreover, two learning strategies, i.e., N-step adjustment training and increasing-step adjustment training, are proposed to enhance the model accuracy when actual measurement data of vehicle sideslip angle and yaw rate are unavailable. Compared to existing methods, N-step adjustment and increasing-step adjustment training decrease the MAE of the estimated sideslip angle by 2.2% and 9.4%, respectively, and that of the estimated yaw rate by 37.4% and 58.1%, respectively.