Federated Learning for Smart Mobility: Towards Secure, Efficient, and Sustainable Transportation System

Federated Learning for Smart Mobility: Towards Secure, Efficient, and Sustainable Transportation explores how federated learning (FL) reshapes the future of intelligent transportation and the Internet of Things (IoT). As data privacy and communication efficiency become pressing challenges, FL offers a distributed and privacy-preserving paradigm for model training across vehicles, sensors, and edge devices without sharing raw data. This SpringerBrief provides a concise yet comprehensive overview of FL’s role in building next-generation smart mobility systems. It covers the fundamentals of FL and IoT infrastructures, introduces emerging applications in autonomous driving, traffic prediction, and vehicular networks, and presents selected case studies from academia and industry. The book also discusses key technical challenges—including data heterogeneity, system scalability, and privacy protection—and highlights future directions integrating FL with edge intelligence, 6G communication, and blockchain technologies. Written by active researchers in the fields of federated learning, wireless communication, and intelligent transportation, this book serves as a valuable reference for scientists, graduate students, and professionals in AI, IoT, and smart city development. It bridges theoretical advances with practical insights, guiding readers toward secure, efficient, and sustainable mobility solutions.