Work

Distributed Dynamic Map Fusion via Federated Learning for Intelligent Networked Vehicles

Year: 2021

Type: conference-paper

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 CARLA simulation platform. Extensive experimental results are provided to verify the superior performance and robustness of the developed map fusion and FL schemes.

Source: Proceedings - IEEE International Conference on Robotics and Automation/Proceedings

DOI: 10.1109/icra48506.2021.9561612

Authors: Zijian Zhang, Shuai Wang, Yuncong Hong, Liangkai Zhou, Qi Hao

Institutions: Harbin Institute of Technology, Southern University of Science and Technology

Language: English

Topic: Autonomous Vehicle Technology and Safety

Subfield: Automotive Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: green

Funders: Canadian Institute for Advanced Research, National Natural Science Foundation of China