Yi Su ^1,2* Lv Xu ^1,2 Jiehui Li ³

• ¹ School of Intelligent Equipment and Automotive Engineering, WuXi Vocational Institute of Commerce, Wuxi, China
• ² Jiangsu Province Engineering Research Center of Key Components for New Energy Vehicle, Wuxi, China
• ³ School of Automobile and Traffic Engineering, Jiangsu University, Zhenjiang, Jiangsu Province, China

Intelligent vehicles and autonomous driving have always been the focus of research in the transportation field, but current autonomous driving models have significant errors in lateral tracking that cannot be ignored. In view of this, the study innovatively proposes a lateral trajectory algorithm for intelligent vehicles based on the Improved Radial Basis Function (RBF). The algorithm first models the lateral trajectory behaviour of a car based on the theory of pre-scanning steering, and then proposes an improved RBF network model to compensate for the error in the lateral trajectory model to further improve the accuracy. According to the simulation test results, after 20 iterations, the proposed algorithm consistently shows the highest accuracy at the same number of iterations. When the number of iterations reaches 370, the accuracy of the algorithm stabilizes at 88%. In addition, bend tests have shown that the proposed algorithm performs best at slow speeds, with an overall error of 0.028 m, and has higher accuracy compared to algorithms without neural network compensation. At fast speeds, the algorithm is still superior, with a maximum overall error of only 0.08 m. In complex continuous curved terrain, the maximum error of the proposed algorithm does not exceed 0.04 m, which is considered safe within the normal road width range. Overall, the lateral tracking algorithm proposed by the research institute has better lateral tracking ability compared to other improved algorithms of the same type. This research achievement has certain reference significance for the lateral tracking field of autonomous driving, providing new ideas and methods for the lateral tracking field of autonomous driving technology, and helping to promote the overall development of autonomous driving technology. By reducing lateral tracking errors, the driving stability and safety of autonomous vehicles can be improved, creating favorable conditions for the widespread application of autonomous driving technology.