The advantages and disadvantages of present methods for shift schedule analysis of automatic transmission vehicle are analyzed. An optimum shift schedule method based on fuzzy neural network is proposed. The structure and algorithm with Takagi-Sugeno mode is studied. Fuzzy logic rules with two parameters and membership functions for shift schedule are established according to the skilled driver’s experience and expert’s knowledge. The membership functions and fuzzy logic rules are modified through train mechanism of artificial neural network based on experiment sample. The fuzzy neural network is trained and simulated. The simulation results indicate that this shift schedule method based on fuzzy neural network of Takagi-Sugeno model is feasible and correct.