On the Federated Learning Framework for Cooperative Perception

TL;DR

This paper proposes a federated learning framework with dynamic client weighting and a novel loss function to improve cooperative perception accuracy in autonomous vehicles, effectively addressing data heterogeneity challenges.

Contribution

It introduces FedDWA, a federated learning algorithm with dynamic weighting and a KLD-based loss to enhance model convergence and accuracy in non-IID data scenarios for cooperative perception.

Findings

Significant improvement in average IoU on the OpenV2V dataset

Effective mitigation of data heterogeneity effects in federated learning

Enhanced perception accuracy for autonomous vehicle collaboration

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 study introduces a specialized federated learning framework for CP, termed the federated dynamic weighted aggregation (FedDWA) algorithm, facilitated by dynamic adjusting loss (DALoss) function. This framework employs dynamic client weighting to direct model convergence and integrates a novel loss function that utilizes Kullback-Leibler divergence (KLD) to counteract the detrimental effects of non-independently and identically distributed (Non-IID) and unbalanced data. Utilizing the BEV transformer as the primary model, our rigorous testing on the OpenV2V dataset, augmented with FedBEVT data, demonstrates significant improvements in the average intersection over union (IoU). These results highlight the substantial potential of our federated learning framework to address data heterogeneity challenges in CP, thereby enhancing the accuracy of environmental perception models and facilitating more robust and efficient collaborative learning solutions in the transportation sector.