Method for Adaptive Robust Four-Wheel Localization and Application in Automatic Parking Systems

Positioning accuracy and stability are crucial for automated parking systems used in vehicles. A new adaptive robust four-wheel calculation positioning method is proposed to address the problems of low precision and poor stability of the traditional positioning method based on two-wheel driven wheel speed sensors. The method is based on the local outlier factor detection algorithm, in which adaptive diagnosis and compensation are made for data anomalies of four-wheel speedometers. Hence, two-wheel driving wheel positioning and four-wheel positioning methods are designed. The priority is ranked according to the diagnosis results, and the traditional two-wheel driven wheel positioning, two-wheel driving wheel positioning, or four-wheel positioning is selected in turn. The flow chart and the detailed derivation process of the new method are provided. Two vehicle models, Zhongtai E200 and Jianghuai S2, were randomly selected, and hundreds of automatic parking experiments were carried out. Compared with the traditional method, the experimental results indicate that the positioning accuracy of the new method is improved by ~ 51.9%, and the reliability of data transmission is increased by 5.1%.