Work

AI-Enhanced Sensor Fusion: Bridging Traditional and Neural Network Filters in Real-Time Localization

Year: 2025

Type: conference-paper

Abstract: In the context of digital twins and industrial IoT systems, robust sensor fusion is essential for accurate real-time localization. This paper presents a comparative evaluation of three sensor fusion strategies for indoor 2D localization: a classical Extended Kalman Filter (EKF), a hybrid architecture combining the filter with a Recurrent Neural Network (RNN) for error compensation, and a pure AI model that learns the fusion process directly from multi-sensor sequences. Experimental results show that the hybrid approach consistently achieves the best trade-off between accuracy and real-time responsiveness, outperforming both the classical and the purely AI-based alternative.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.17561164

Authors: Padhyegurjar, Aaryaa Shekhar, Salzmann, Dennis, Schotten, Hans D.

Institutions: Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau, German Research Centre for Artificial Intelligence

Language: English

Topic: Target Tracking and Data Fusion in Sensor Networks

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: green

OpenAlex ID: W7104437862

FWCI:

Cites:

Cited by:

Related to: