In order to solve the problem of low accuracy of automatic parking path tracking caused by noise of various sensors, a parking path tracking algorithm combining fuzzy control and Kalman filter is proposed. Firstly, the deviation model of actual driving path and reference path is established based on vehicle kinematical equation. Secondly, Kalman filter is adopted to reduce the measurement noise in vehicle position and course angle measurement data. According to the vehicle position deviation and course angle deviation, fuzzy controller is adopted to control the vehicle tracking the parking track. Thirdly, simulation model is built to verify the effectiveness of the proposed algorithm by Matlab/Simulink. Simulation results show that the proposed algorithm can effectively reduce the vehicle position deviation and course angle deviation, and improve the tracking accuracy of parking path.