A fusion estimation of the peak tire-road friction coefficient based on road images and dynamic information

To accurately acquire the peak tire-road friction coefficient, a fusion estimation framework combining vision and vehicle dynamic information is established. First, information for the road ahead is collected in advance from an image captured by a camera, and the road type with its typical range of tire-road friction coefficients is identified with a lightweight convolutional neural network. Then, an unscented Kalman filter (UKF) method is established to estimate the tire-road friction coefficient value directly according to the dynamic vehicle states. Next, the results from the road-type recognition and dynamic estimation methods are spatiotemporally synchronized. Finally, a confidence-based vision and vehicle dynamic fusion strategy is proposed to obtain an accurate peak tire-road friction coefficient. The virtual and real vehicle test results suggest that the proposed fusion estimation strategy can accurately determine the peak tire- road friction coefficient. The proposed strategy can more precisely acquire the tire-road friction coefficient than can the general vision-based estimation method and is superior to the dynamic -based estimation method in that it eliminates the need for sufficient tire excitation to some extent.

Automated summary

An estimation framework that combines vision and vehicle dynamic information is established to accurately obtain the peak tire-road friction coefficient. The framework collects information for the road ahead from an image captured by a camera and uses a lightweight convolutional neural network to identify the road type and its corresponding range of tire-road friction coefficients. An unscented Kalman filter (UKF) method is then used to estimate the tire-road friction coefficient value directly based on the dynamic vehicle states. The results from the road-type recognition and dynamic estimation methods are synchronized, and a confidence-based fusion strategy is proposed to obtain an accurate peak tire-road friction coefficient. Virtual and real vehicle tests confirm the effectiveness of the proposed fusion estimation strategy, which outperforms both general vision-based estimation methods and dynamic-based estimation methods.