Abstract: In response to the problem that the traditional Model Predictive Control（MPC） cannot adapt to the complexity of tractor field operation conditions, an adaptive time-domain MPC-based path tracking control algorithm is proposed.First, a linear time-varying vehicle error model is established based on tractor kinematics. Then, based on the real-time speed of the tractor and the reference path curvature, the fuzzy control algorithm is used to determine the current optimal prediction time domain and control time domain. Finally, on this basis, the MPC algorithm is combined to control the tractor to track the pre-set reference path. The real vehicle test shows that: the absolute value of tractor path tracking lateral error is ＜ 0.03 m; the absolute value of straight section lateral error is ＜ 0.07m; the absolute value of curve section lateral error is ＜ 0.15 m; in addition, the path tracking controller designed in this paper can ensure that the tractor can accurately and quickly track the pre-set reference path within 5s.