查看文章

Connected and Automated Vehicles (CAVs) represent a rapidly growing technology in the automotive domain sector, offering promising solutions to address challenges such as traffic accidents, congestion, and pollution. By leveraging CAVs, we have the opportunity to create a transportation system that is safe, efficient, and environmentally sustainable. Machine learning-based methods are widely used in CAVs for crucial tasks like perception, planning, and control, where machine learning models in CAVs are solely trained with the local vehicle data, and the performance is not certain when exposed to new environments or unseen conditions. Federated learning (FL) is a decentralized machine learning approach that enables multiple vehicles to develop a collaborative model in a distributed learning framework. FL enables CAVs to learn from a broad range of driving environments and improve their overall …