Distributed Dynamic Map Fusion via Federated Learning for Intelligent Networked Vehicles

TL;DR

This paper introduces a federated learning-based framework for dynamic map fusion in networked vehicles, enhancing sensing accuracy and robustness despite uncertainties and missing labels through a novel three-stage fusion scheme, FL algorithm, and knowledge distillation.

Contribution

It presents a novel three-stage fusion scheme, a federated learning algorithm for feature model fine-tuning, and a knowledge distillation method for unlabeled data, advancing dynamic map fusion in autonomous vehicles.

Findings

Superior map quality and robustness demonstrated in CARLA simulation

Effective object prediction and map fusion with fidelity scores

Enhanced online learning despite data uncertainties and missing labels

Abstract

The technology of dynamic map fusion among networked vehicles has been developed to enlarge sensing ranges and improve sensing accuracies for individual vehicles. This paper proposes a federated learning (FL) based dynamic map fusion framework to achieve high map quality despite unknown numbers of objects in fields of view (FoVs), various sensing and model uncertainties, and missing data labels for online learning. The novelty of this work is threefold: (1) developing a three-stage fusion scheme to predict the number of objects effectively and to fuse multiple local maps with fidelity scores; (2) developing an FL algorithm which fine-tunes feature models (i.e., representation learning networks for feature extraction) distributively by aggregating model parameters; (3) developing a knowledge distillation method to generate FL training labels when data labels are unavailable. The proposed framework is implemented in the Car Learning to Act (CARLA) simulation platform. Extensive experimental results are provided to verify the superior performance and robustness of the developed map fusion and FL schemes.