Federated learning for connected autonomous vehicles: enhancing mobility, safety, and sustainability

Abstract Connected Autonomous Vehicles (CAVs) as vehicles of the future hold the social value as elements of an intelligent transport system that can contribute new advancements in mobility, safety and sustainability. However, there are issues like communication overhead, data heterogeneity and model convergence which limit the optimization of these techniques. Such a model training can be effectively done with the help of Federated Learning (FL), which helps training the same while restricting data transfer. This paper reports a systematic review of the recent literature on FL in CAVS, highlighting the state-of-the-art progress and challenges. It also discusses how FL may be applied to CAVs to enhance safety and traffic flow while achieving positive environmental impacts, addressing data privacy, distributed learning, and the ability to make real-time decisions. It also describes directions for future work to mitigate these issues, such as communication overhead, data heterogeneity, and model convergence in FL for CAVs. This paper discusses how FL enhances safety, productivity, and environmentally-friendly development in CAVs’ networks and the future research directions and issues regarding intelligent, privacy-preservation transportation systems.