Litcius/Paper detail

FL-EKF-Based Cooperative Localization Method for Multi-AUVs

Wanlong Zhao, Shuyin Zhao, Guoyao Zhang, Gongliang Liu, Weixiao Meng

2024IEEE Internet of Things Journal12 citationsDOI

Abstract

Autonomous underwater vehicle (AUV) has been widely used in underwater missions. Cooperative localization (CL) is a key technology especially for multi-AUVs collaborative operations. With great demands for accurate and real-time localization, the error dispersion in nonlinear fusion and information transmission difficulties caused by underwater environment limitations become challenges in multi-AUVs CL. In this article, a federated learning (FL) framework for multi-AUVs CL is designed, based on which a novel CL algorithm combining the FL and extended Kalman filter (EKF) is proposed. The proposed FL-EKF algorithm can fuse the advantages of EKF and FL adequately to realize high-precision real-time underwater CL in long-duration operations. Simulations and experiments are conducted to verify the performance of the proposed algorithm.

Topics & Concepts

Computer scienceExtended Kalman filterArtificial intelligenceKalman filterIndoor and Outdoor Localization TechnologiesUnderwater Vehicles and Communication SystemsTarget Tracking and Data Fusion in Sensor Networks
FL-EKF-Based Cooperative Localization Method for Multi-AUVs | Litcius