Considering the fact that the interaction of tire and ground existing uncertainty leads to deviation between actual heading and kinematic theoretical heading, a pure pursuit control method based on SVR inverse-model was proposed for agricultural machine navigation.The Inverse-model of forward heading in tractor was established by using the method of granular support vector regression, and the corresponding relation function of kinematic theoretical heading and actual heading was obtained.The pure pursuit navigation model and reverse model composed the compound system by means of series, thus the adaptability and dynamic performance of pure pursuit control method were improved.The path tracking experiments experimented on navigation system of the tractor and the pavement experiment results showed that the maximum of linear tracing pitch yaw roll error was 5.85, when the speed of agricultural machinery was 1.4m/s.Compared with the method of conventional pure pursuit navigation model, the pure pursuit control method based on SVR inverse-model had better linear racing performance.This navigation control method could be applied to automatic row-controlled operation of 2BFQ-6 type direct-seeding combined dual purpose planter for rapeseed.