For intelligent driver assistance systems the prediction of the future driving cycle is fundamental. Recent recommendations for driving cycle standards does not provide precise information on the expected intermittent operations of the vehicle and can not be applied directly in an intelligent energy management and driving assistance system. Latest driver assistance systems require more sophisticated solutions which are able to incorporate the personal driving style. The Interval-type 2 Fuzzy System is proved to be a higly efficient tool for modeling uncertainties. In contrast to conventional Type-1 fuzzy modeling an IT2 Fuzzy System has the ability to deal with flexible with the various types of uncertainties and modeling errors simultaneously and approximates better real-life systems. This paper presents an IT2 Fuzzy System for personalized driving cycle forecasting from the measured velocity and acceleration data. The proposed method applies a Mamdani type IT2 fuzzy inference technique. The fuzzy sets and rules are built up by extracting knowledge from real driving dataset. Simulation results have shown that the presented technique is efficient and ensures satisfactory performance.