Decentralized federated learning for extended sensing in 6G connected vehicles – ScienceDirect

In this paper we investigate distributed federated learning (FL) for augmenting the capability of road user/object classification based on Lidar data. More specifically, we propose a new modular, decentralized approach, referred to as consensus-driven FL (C-FL), suitable for PointNet compliant deep machine learning architectures and Lidar point cloud processing for road actor classification.