Communication Resources Constrained Hierarchical Federated Learning for End-to-End Autonomous Driving

TL;DR

This paper introduces a novel hierarchical federated learning framework optimized for limited communication resources, significantly improving convergence speed and model generalization for autonomous driving in simulation.

Contribution

It proposes an optimization-based CRCHFL framework that effectively balances communication constraints with learning performance in autonomous driving.

Findings

CRCHFL accelerates convergence rate

CRCHFL enhances model generalization

Outperforms traditional HFL and SFL under same communication budget

Abstract

While federated learning (FL) improves the generalization of end-to-end autonomous driving by model aggregation, the conventional single-hop FL (SFL) suffers from slow convergence rate due to long-range communications among vehicles and cloud server. Hierarchical federated learning (HFL) overcomes such drawbacks via introduction of mid-point edge servers. However, the orchestration between constrained communication resources and HFL performance becomes an urgent problem. This paper proposes an optimization-based Communication Resource Constrained Hierarchical Federated Learning (CRCHFL) framework to minimize the generalization error of the autonomous driving model using hybrid data and model aggregation. The effectiveness of the proposed CRCHFL is evaluated in the Car Learning to Act (CARLA) simulation platform. Results show that the proposed CRCHFL both accelerates the convergence rate and enhances the generalization of federated learning autonomous driving model. Moreover, under the same communication resource budget, it outperforms the HFL by 10.33% and the SFL by 12.44%.