Localization, Navigation, and Channel Modeling: AI Solutions for Complex Indoor and Urban Environments

Dear Colleagues,

This Special Issue explores the latest advancements in localization and navigation within complex environments, such as indoor and urban settings, as well as innovations in radio map prediction and the broader field of propagation modeling. These areas are critical for enabling accurate positioning, efficient wireless communication, and reliable predictions of electromagnetic wave behavior in environments where traditional distance estimate-based systems such as GNSS fail due to complex signal attenuation, multipath effects, or obstructions caused by buildings and other structures present in the propagation environment.

Localization in complex environments faces significant challenges due to structural complexity, dynamic conditions, and signal interference. Indoor positioning systems (IPSs) employ technologies such as Wi-Fi, Bluetooth, Ultra-Wideband (UWB), magnetic fields, and visual markers to achieve high levels of accuracy. However, these methods often struggle with environmental variability and computational demands. Multi-sensor fusion techniques that integrate data from inertial sensors, cameras, and spatial models have emerged as robust solutions to improve accuracy. Machine learning further enhances these systems by enabling real-time adaptability to environmental changes. In urban settings, hybrid localization methods combining GNSS with alternative technologies such as barometers or radio frequency-based approaches ensure seamless transitions between indoor and outdoor environments while maintaining precision.

Radio maps are essential tools for quantifying wireless signal distributions across geographical areas and are integral to applications like network planning, resource allocation, and fingerprinting-based localization. Their generation has been advanced through deterministic models and recent deep learning-based approaches. Deterministic methods, such as ray tracing, simulate radio wave propagation by accounting for environmental factors like geometry, material properties, and interactions such as reflection or scattering. While these methods are highly accurate, they are also computationally intensive. Deep learning-based models offer a faster (and potentially more precise) alternative by leveraging parallelization and GPU acceleration to predict radio wave behavior efficiently. These methods can incorporate sparse measurements alongside environmental information to address inaccuracies while maintaining high-speed predictions.

Recent advancements in channel modeling have introduced methods capable of providing highly accurate predictions of wireless channel characteristics while addressing computational efficiency. These approaches leverage detailed representations of the propagation environment to model complex phenomena such as multipath propagation, delay spreads, and angular spreads. By integrating physical principles with data-driven techniques, these models enable accurate predictions of metrics like Received Signal Strength (RSS) and Channel State Information (CSI), which are crucial for modern wireless systems.

This Special Issue invites contributions across its core themes:

- Localization and navigation in complex environments such as indoor and urban settings; 
- Radio map prediction using deep learning-based methods; 
- Learning propagation models for accurate predictions of electromagnetic wave behavior and observed characteristics such as RSS or CSI; 
- Novel approaches that combine physics-based modeling with machine learning to enhance channel modeling efficiency.

By fostering interdisciplinary research across these domains, this collection aims to advance the understanding of localization systems, radio map generation, and propagation modeling while addressing the growing demands of modern wireless communication networks and location-based services.

Dr. Çağkan Yapar
Dr. Giuseppe Caire
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• deep learning-based propagation models
• deep learning-based channel prediction
• radio maps
• indoor localization
• urban localization
• indoor positioning
• urban positioning
• indoor navigation
• urban navigation
• artificial intelligence
• machine learning
• deep learning
• wireless communications