The concept of mission-based driving cycles has been introduced as an efficient way of generating driving cycles with desired characteristics for data-driven development of vehicle powertrains. Mission-based driving cycles can be generated using traffic simulation tools with improved behavioral models that match simulation outputs and naturalistic driving data. Here, driving behavior categorization and how it can be used to create a set of differently parameterized behavioral models corresponding to various types of drivers, are studied. The focus is on curvy road driving, and two different categorization features are used, speed through the curves and the braking behavior. © 2019 IEEE.