According to the characteristics of intelligent connected vehicles which could obtain information about its own and the surrounding vehicles' velocity and position in real time, this paper mainly focuses on the control process of intelligent connected vehicles that are able to automatically change their lanes. The automatic lane change decision model is designed bases on the minimum safety distance, which also takes the safety of lane change and its impacts on the overall traffic flow in consideration. The reason for selecting the fifth-order polynomial as an ideal lane change trajectory is that it is flexible and adaptable. Considering that there are many external disturbances during the driving process of the vehicle, the trajectory of the lane change is tracked by the sliding mode control system, and the simulation is carried out by using MATLAB/SIMULINK. The results show that it has good tracking effects.