A transmission controller for an automobile with variable loads is designed and tested by using a transmission system (Isuzu NAVi-5) consisting of actuators and sensors besides gears, a throttle, and a clutch. This system engages and disengages the clutch and gears up and down automatically. In other words, a manual gear-shift system is automated. As neuro and fuzzy approaches are promising methods to interface between a vehicle operator and an automobile, they are used to design a transmission controller. Automobile loads are estimated from the signals of status sensors by fuzzy logic. Vehicle driver's intention is inferred by fuzzy logic using the information from automobile status sensors on which driver's intention is reflected. These are then fed into a neural network. An experienced driver (much data) teachers the neural network an optimal gear-shift scheduling such that a vehicle operator feels comfortable even when automobile loads change (for example when an automobile is traveling up and down hill). >