On the Federated Learning Framework for Cooperative Perception

arXiv:2404.17147v1 Announce Type: cross
Abstract: Cooperative perception is essential to enhance the efficiency and safety of future transportation systems, requiring extensive data sharing among vehicles on the road, which raises significant privacy concerns. Federated learning offers a promising solution by enabling data privacy-preserving collaborative enhancements in perception, decision-making, and planning among connected and autonomous vehicles (CAVs). However, federated learning is impeded by significant challenges arising from data heterogeneity across diverse clients, potentially diminishing model accuracy and prolonging convergence periods. This …

abstract arxiv collaborative concerns cs.cv cs.lg data data privacy data sharing decision efficiency enabling federated learning framework future making perception planning privacy raises safety solution systems transportation type vehicles