The integration of Federated Learning (FL) into smart mobility systems holds immense potential in addressing the challenges of privacy, security, and data decentralization in modern transportation networks. This chapter introduces the foundational concepts of FL, focusing on its application in smart mobility. It begins by discussing the motivation behind the digital transformation of the transportation sector, followed by an overview of smart mobility and its key components. The chapter then explores the primary challenges faced by data-centric mobility systems, including data silos, privacy concerns, communication latency, and energy consumption. The role of FL is examined as a natural solution to these challenges, highlighting its ability to facilitate decentralized data processing while maintaining data privacy. A typical FL architecture for smart mobility is also discussed, and an overview of the book’s structure is provided.