arXiv subjects

Paul Schwarzbach

Publications and source records attributed to Paul Schwarzbach.

12 recordsLinked to original sources

arXiv2026

From Least Squares to Deep Learning: Benchmarking Indoor Positioning on the HYMN Multi-Technology Dataset

Indoor positioning benchmarks rarely co-locate multiple technologies with high-accuracy ground truth, limiting cross-method and cross-technology comparison. We evaluate four range-based positioning methods on fused Ultra-wideband, Bluetooth Low Energy, and WiFi ranges recorded at 48 reference points in an industrial facility with available ground truth. The evaluated methods range from least-squares positioning, with and without robust weighting, through a Bayesian grid filter to a ResNet regressor that we report under two protocols, interpolation and spatial generalisation. Per-technology ranging quality spans roughly two orders of magnitude, which caps any geometry-based solver that weighs anchors equivalently. On fused input the grid filter is competitive with deep learning on median error, while the ResNet's advantage concentrates on the upper tail. Holding reference points out of training increases the learned regressor's median error several-fold, exposing a spatial-generalisation penalty invisible under random splits. The dataset and evaluation code are publicly available.

eess.SP↗

arXiv2026

Bridging the Indoor-Outdoor Gap: Cross-Technology Ranging for Seamless Robot Navigation

Mobile robots that move between outdoor and indoor environments still struggle with consistent positioning. Satellite-based and terrestrial ranging each work well in their home domains, but combining them at the raw measurement level has received little attention, and the building boundary is precisely where both classes degrade. This paper reports preliminary observations from the HYMN dataset, which time-synchronizes raw measurements from GNSS, Ultra-Wideband (UWB), WiFi Fine Time Measurement (FTM), and Bluetooth Low Energy (BLE) against millimeter-level ground truth in an industrial setting. Per-zone measurement availability and ranging-residual behavior are characterised. The two technology classes turn out to be complementary, and the indoor-outdoor transition is where their weaknesses overlap. The dataset is publicly available.

eess.SP↗

arXiv2026

Descriptor: A Hybrid Indoor and Indoor-Outdoor Positioning Multi-Technology Dataset (HYMN)

This article introduces the HYMN (HYbrid Multi-technology Navigation) dataset: a multi-system, and time synchronized dataset for localization research based on opportunistic signals collected in an indoor-outdoor scenario. HYMN comprises measurement data collected in an industrial hall setting for five different positioning systems including Ultra-Wideband (UWB), Bluetooth Low Energy (BLE), WiFi, 5G, and Global Navigation Satellite System (GNSS). Unlike existing datasets that focus on single technologies or purely indoor/outdoor scenarios, HYMN combines five positioning technologies with explicit coverage of indoor-outdoor transitions, enabling multi-sensor fusion research for seamless localization. Each instance of data is identified through a unique measurement id and it represents time-stamped observations relevant for each system respectively along with the ground truth information. HYMN is designed to support a wide range of localization tasks including multi-sensor fingerprinting, cross-technology fusion, and seamless indoor-outdoor positioning. The synchronized measurements from GNSS and other terrestrial systems enable researchers to investigate how heterogeneous signals complement each other to overcome individual technology limitations such as GNSS degradation in covered areas or terrestrial system variability in dynamic environments.

eess.SP↗

arXiv2026

Evaluation of Grid-based Uncertainty Propagation for Collaborative Self-Calibration in Indoor Positioning Systems

Radio-based localization systems conventionally require stationary reference points (e.g. anchors) with precisely surveyed positions, making deployment time-consuming and costly. This paper presents an empirical evaluation of collaborative self-calibration for Ultra-Wideband (UWB) networks, extending a discrete Bayesian approach based on grid-based uncertainty propagation. The enhanced algorithm reduces measurement availability requirements while maintaining positioning accuracy through probabilistic state estimation. We validate the approach using real-world data from controlled indoor UWB network experiments with 12 nodes in a static environment. Experimental evaluation demonstrates 0.28~m mean ranging error under line-of-sight conditions and 1.11~m overall ranging error across mixed propagation scenarios, achieving sub-meter positioning accuracy. Results demonstrate the algorithm's robustness to measurement noise and partial connectivity scenarios typical in industrial deployments. The findings contribute to automated UWB network initialization for indoor positioning applications, reducing infrastructure dependency compared to manual anchor calibration procedures.

eess.SP↗

arXiv2025

Range-Angle Likelihood Maps for Indoor Positioning Using Deep Neural Networks

Accurate and high precision of the indoor positioning is as important as ensuring reliable navigation in outdoor environments. Using the state-of-the-art deep learning models provides better reliability and accuracy to navigate and monitor the accurate positions in the aircraft cabin environment. We utilize the simulated aircraft cabin environment measurements and propose a residual neural network (ResNet) model to predict the accurate positions inside the cabin. The measurements include the ranges and angles between a tag and the anchors points which are then mapped onto a grid as range and angle residuals. These residual maps are then transformed into the likelihood grid maps where each cell of the grid shows the likelihood of being a true location. These grid maps along with the true positions are then passed as inputs to train the ResNet model. Since any deep learning model involve numerous parameter settings, hyperparameter optimization is performed to get the optimal parameters for training the model effectively with the highest accuracy. Once we get the best hyperparameters settings of the model, it is then trained to predict the positions which provides a centimeter-level accuracy of the localization.

eess.SP↗

arXiv2023

Simulation-based Evaluation of Indoor Positioning Systems in Connected Aircraft Cabins

The manuscript discusses the increasing use of location-aware radio communication systems to support operational processes for the demanding aircraft cabin environment. In this context, the challenges for evaluation and integration of radio-based localization systems in the connected cabin are specifically addressed by proposing a hybrid deterministic and stochastic simulation approach, including both model-based ray-tracing and empirical residual simulation. The simulation approach is detailed in the manuscript and a methodology for applying and evaluating localization methods based on obtained geometric relations is conducted. This can also be used as a data generation and validation tool for data-driven localization methods, which further increase the localization accuracy and robustness. The derived location information can in return be used in order to perform operational prediction and optimization for efficient and sustainable passenger handling. A dataset derived from the introduced simulation platform is publicly available.

eess.SP↗

arXiv2023

Grid-based Hybrid 3DMA GNSS and Terrestrial Positioning

The paper discusses the increasing use of hybridized sensor information for GNSS-based localization and navigation, including the use of 3D map-aided GNSS positioning and terrestrial systems based on different geometric measurement principles. However, both GNSS and terrestrial systems are subject to negative impacts from the propagation environment, which can violate the assumptions of conventionally applied parametric state estimators. Furthermore, dynamic parametric state estimation does not account for multi-modalities within the state space leading to an information loss within the prediction step. In addition, the synchronization of non-deterministic multi-rate measurement systems needs to be accounted. In order to address these challenges, the paper proposes the use of a non-parametric filtering method, specifically a 3DMA multi-epoch Grid Filter, for the tight integration of GNSS and terrestrial signals. Specifically, the fusion of GNSS, Ultra-wide Band (UWB) and vehicle motion data is introduced based on a discrete state representation. Algorithmic challenges, including the use of different measurement models and time synchronization, are addressed. In order to evaluate the proposed method, real-world tests were conducted on an urban automotive testbed in both static and dynamic scenarios. We empirically show that we achieve sub-meter accuracy in the static scenario by averaging a positioning error of $0.64$ m, whereas in the dynamic scenario the average positioning error amounts to $1.62$ m. The paper provides a proof-of-concept of the introduced method and shows the feasibility of the inclusion of terrestrial signals in a 3DMA positioning framework in order to further enhance localization in GNSS-degraded environments.

eess.SP↗

arXiv2023

Potentials of Deterministic Radio Propagation Simulation for AI-Enabled Localization and Sensing

Machine leaning (ML) and artificial intelligence (AI) enable new methods for localization and sensing in next-generation networks to fulfill a wide range of use cases. These approaches rely on learning approaches that require large amounts of training and validation data. This paper addresses the data generation bottleneck to develop and validate such methods by proposing an integrated toolchain based on deterministic channel modeling and radio propagation simulation. The toolchain is demonstrated exemplary for scenario classification to obtain localization-related channel parameters within an aircraft cabin environment.

eess.SP↗

arXiv2022

Auto-Positioning in Radio-based Localization Systems: A Bayesian Approach

The application of radio-based positioning systems is ever increasing. In light of the dissemination of the Internet of Things and location-aware communication systems, the demands on localization architectures and amount of possible use cases steadily increases. While traditional radio-based localization is performed by utilizing stationary nodes, whose positions are absolutely referenced, collaborative auto-positioning methods aim to estimate location information without any a-priori knowledge of the node distribution. The usage of auto-positioning decreases the installation efforts of localization systems and therefore allows their market-wide dissemination. Since observations and position information in this scenario are correlated, the uncertainties of all nodes need to be considered. In this paper we propose a discrete Bayesian method based on a multi-dimensional histogram filter to solve the task of robust auto-positioning, allowing to propagate historical positions and estimated position uncertainties, as well as lowering the demands on observation availability when compared to conventional closed-form approaches. The proposed method is validated utilizing different multipath-, outlier and failure-corrupted ranging measurements in a static environment, where we obtain at least 58% higher positioning accuracy compared to a baseline closed-form auto-positioning approach.

eess.SP↗

arXiv2022

Efficient coverage planning for full-area C-ITS communications based on radio propagation simulation and measurement tools

Intelligent infrastructure, currently often consisting of C-ITS stations and prospectively supplemented by 5G, is a key-enabler for application-oriented and area-wide realization of highly automated and connected driving. For this, radio coverage along the routes must be ensured, leading to high demands on location- and radio-specific planning and parameterization of roadside units (RSU). Hence, this paper presents efficient planning, measurement and evaluation methods for RSU coverage outlining, allowing economically efficient and technically secured planning of intelligent infrastructure. Necessary scientific technical steps are showcased along a 3.5 km testbed for automated and connected driving in rural environments. First, a radio propagation simulation based on a 3D environment model and its electro-magnetic properties is performed, allowing the examination and optimization of RSU quantity as well as site and antenna selection. Additionally, the necessary calibration of simulation results based on continuous wave (CW) and C-ITS service measurements in both lab-based and real-world scenarios is presented.

eess.SP↗

arXiv2022

Enabling Radio Sensing for Multimodal Intelligent Transportation Systems: From Virtual Testing to Immersive Testbeds

In this paper, the necessity for application-oriented development and evaluation of Joint Communication and Sensing (JC&S) applications, especially in transportation, is addressed. More specifically, an integrative evaluation chain for immersively testing JC&S location capabilities, reaching from early-stage testing, over model- and scenario-enabled ray tracing simulation, to real-world evaluation (laboratory and field testing) is presented. This includes a discussion of both challenges and requirements for location-aware applications in Intelligent Transportation Systems. Within this scope, a reproducible methodology for testing sensing and localization capabilities is derived and application scenarios are presented. This includes a proposal of a scenario-based sensing evaluation using radio propagation simulation. The paper empirically discusses a proof-of-concept of the developed method given a smart parking scenario, in which a passive occupancy detection of vehicles is performed. The conducted findings underline the need for scenario-based JC&S evaluation in both virtual and real-world environments and proposes consecutive research work.

eess.SP↗

arXiv2022

Multipath-assisted Radio Sensing and Occupancy Detection for Smart In-house Parking in ITS

Joint, radio-based communication, localization and sensing is a rapidly emerging research field with various application potentials. Greatly benefiting from these capabilities, smart city, mobility, and logistic concepts are key components for maximizing the efficiency of modern transportation systems. In urban environments, both the search for parking space and freight transport are time- and space-consuming and present the bottlenecks for these transportation chains. Providing location information for these heterogeneous requirement profiles (both active and passive localization of objects), can be realized by using retrofittable wireless sensor networks, which are typically only deployed for active localization. An additional passive detection of objects can be achieved by assessing signal reflections and multipath properties of the transmission channel stored within the Channel Impulse Response (CIR). In this work, a proof-of-concept realization and preliminary experimental results of a CIR-based occupancy detection for parking lots are presented. As the time resolution is dependent on available bandwidth, the CIR of Ultra-wideband transceivers are used. For this, the CIR is smoothed and time-variant changes within it are detected by performing a background subtraction. Finally, the reflecting objects are mapped to individual parking lots. The developed method is tested in an in-house parking garage. The work provided is a foundation for passive occupancy detection, whose capabilities can prospectively be enhanced by exploiting additional physical layers, such as 5G or even 6G.

eess.SP↗