In this article, we present a unique comparative analysis, and evaluation of vision-, radio-, and audio-based localization algorithms. We create the first baseline for the aforementioned sensors using the recently published Lund University Vision, Radio, and Audio dataset, where all the sensors are synchronized and measured in the same environment. Some of the challenges of using each specific sensor for indoor localization tasks are highlighted. Each sensor is paired with a current state-of-the-art localization algorithm and evaluated for different aspects: localization accuracy, reliability and sensitivity to environment changes, calibration requirements, and potential system complexity. Specifically, the evaluation covers the Oriented FAST and Rotated BRIEF simultaneous localization and mapping (SLAM) algorithm for vision-based localization with an RGB-D camera, a machine learning algorithm for radio-based localization with massive multiple-input multiple-output (MIMO) technology, and the StructureFromSound2 algorithm for audio-based localization with distributed microphones. The results can serve as a guideline and basis for further development of robust and high-precision multisensory localization systems, e.g., through sensor fusion, and context- and environment-aware adaptations.
{"title":"LuViRA Dataset Validation and Discussion: Comparing Vision, Radio, and Audio Sensors for Indoor Localization","authors":"Ilayda Yaman;Guoda Tian;Erik Tegler;Jens Gulin;Nikhil Challa;Fredrik Tufvesson;Ove Edfors;Kalle Åström;Steffen Malkowsky;Liang Liu","doi":"10.1109/JISPIN.2024.3429110","DOIUrl":"https://doi.org/10.1109/JISPIN.2024.3429110","url":null,"abstract":"In this article, we present a unique comparative analysis, and evaluation of vision-, radio-, and audio-based localization algorithms. We create the first baseline for the aforementioned sensors using the recently published Lund University Vision, Radio, and Audio dataset, where all the sensors are synchronized and measured in the same environment. Some of the challenges of using each specific sensor for indoor localization tasks are highlighted. Each sensor is paired with a current state-of-the-art localization algorithm and evaluated for different aspects: localization accuracy, reliability and sensitivity to environment changes, calibration requirements, and potential system complexity. Specifically, the evaluation covers the Oriented FAST and Rotated BRIEF simultaneous localization and mapping (SLAM) algorithm for vision-based localization with an RGB-D camera, a machine learning algorithm for radio-based localization with massive multiple-input multiple-output (MIMO) technology, and the StructureFromSound2 algorithm for audio-based localization with distributed microphones. The results can serve as a guideline and basis for further development of robust and high-precision multisensory localization systems, e.g., through sensor fusion, and context- and environment-aware adaptations.","PeriodicalId":100621,"journal":{"name":"IEEE Journal of Indoor and Seamless Positioning and Navigation","volume":"2 ","pages":"240-250"},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10599608","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142246463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-09DOI: 10.1109/JISPIN.2024.3424768
Maximilian Stahlke;George Yammine;Tobias Feigl;Bjoern M. Eskofier;Christopher Mutschler
Radio fingerprinting (FP) technologies improve localization performance in challenging non-line-of-sight environments. However, FP is expensive as its life cycle management requires recording reference signals for initial training and when the environment changes. Instead, novel channel charting technologies are significantly cheaper. Because they implicitly assign relative coordinates to radio signals, they require few reference coordinates for localization. However, even channel charting still requires data acquisition and reference signals, and its localization is slightly less accurate than FP. In this article, we propose a novel channel charting framework that does not require references and dramatically reduces life-cycle management. With velocity information, e.g., pedestrian dead reckoning or odometry, we model relative charts. And with topological map information, e.g., building floor plans, we transform them into real coordinates. In a large-scale study, we acquired two realistic datasets using 5G and single-input and multiple-output distributed radio systems with noisy velocities and coarse map information. Our experiments show that we achieve the localization accuracy of FP but without reference information.
{"title":"Velocity-Based Channel Charting With Spatial Distribution Map Matching","authors":"Maximilian Stahlke;George Yammine;Tobias Feigl;Bjoern M. Eskofier;Christopher Mutschler","doi":"10.1109/JISPIN.2024.3424768","DOIUrl":"https://doi.org/10.1109/JISPIN.2024.3424768","url":null,"abstract":"Radio fingerprinting (FP) technologies improve localization performance in challenging non-line-of-sight environments. However, FP is expensive as its life cycle management requires recording reference signals for initial training and when the environment changes. Instead, novel channel charting technologies are significantly cheaper. Because they implicitly assign relative coordinates to radio signals, they require few reference coordinates for localization. However, even channel charting still requires data acquisition and reference signals, and its localization is slightly less accurate than FP. In this article, we propose a novel channel charting framework that does not require references and dramatically reduces life-cycle management. With velocity information, e.g., pedestrian dead reckoning or odometry, we model relative charts. And with topological map information, e.g., building floor plans, we transform them into real coordinates. In a large-scale study, we acquired two realistic datasets using 5G and single-input and multiple-output distributed radio systems with noisy velocities and coarse map information. Our experiments show that we achieve the localization accuracy of FP but without reference information.","PeriodicalId":100621,"journal":{"name":"IEEE Journal of Indoor and Seamless Positioning and Navigation","volume":"2 ","pages":"230-239"},"PeriodicalIF":0.0,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10591331","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142077623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-03DOI: 10.1109/JISPIN.2024.3422908
Jonathan Ott;Maximilian Stahlke;Tobias Feigl;Christopher Mutschler
Multipath in radio propagation provides essential environmental information that is exploited for positioning or channel-simultaneous localization and mapping. This enables accurate and robust localization that requires less infrastructure than traditional methods. A key factor is the reliable and accurate extraction of multipath components (MPCs). However, limited bandwidth and signal fading make it difficult to detect and determine the parameters of the individual signal components. In this article, we propose multipath delay estimation based on a transformer neural network. In contrast to the state of the art, we implicitly estimate the number of MPCs and achieve subsample accuracy without using computationally intensive super-resolution techniques. Our approach outperforms known methods in detection performance and accuracy at different bandwidths. Our ablation study shows exceptional results on simulated and real datasets and generalizes to unknown radio environments.
{"title":"Estimating Multipath Component Delays With Transformer Models","authors":"Jonathan Ott;Maximilian Stahlke;Tobias Feigl;Christopher Mutschler","doi":"10.1109/JISPIN.2024.3422908","DOIUrl":"https://doi.org/10.1109/JISPIN.2024.3422908","url":null,"abstract":"Multipath in radio propagation provides essential environmental information that is exploited for positioning or channel-simultaneous localization and mapping. This enables accurate and robust localization that requires less infrastructure than traditional methods. A key factor is the reliable and accurate extraction of multipath components (MPCs). However, limited bandwidth and signal fading make it difficult to detect and determine the parameters of the individual signal components. In this article, we propose multipath delay estimation based on a transformer neural network. In contrast to the state of the art, we implicitly estimate the number of MPCs and achieve subsample accuracy without using computationally intensive super-resolution techniques. Our approach outperforms known methods in detection performance and accuracy at different bandwidths. Our ablation study shows exceptional results on simulated and real datasets and generalizes to unknown radio environments.","PeriodicalId":100621,"journal":{"name":"IEEE Journal of Indoor and Seamless Positioning and Navigation","volume":"2 ","pages":"219-229"},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10584252","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-24DOI: 10.1109/JISPIN.2024.3418296
Mihkel Tommingas;Muhammad Mahtab Alam;Ivo Müürsepp;Sander Ulp
This article investigates the use of ultrawideband (UWB) ranging residuals for coordinate integrity estimation and their use in a filtering scheme. Typically, UWB system accuracy is improved using channel statistics (CSs) to detect and mitigate non-line-of-sight effects between UWB sensors and the object to be located, potentially improving the end coordinate solution. However, in practice, when considering UWB system with a high positioning update rate, this is not a feasible approach, as gathering and processing CS data takes too much time. In contrast to this approach, this article proposes a set of features based on UWB ranging residuals that could be used as an alternative in integrity assessment. By using machine learning (ML), the most important features were extracted from the initial set, and then, used to train and validate a model for UWB coordinate error prediction. Finally, the prediction was applied in an adaptive Kalman filtering scheme as an input for measurement uncertainty. Model testing was done using UWB measurement test dataset gathered at an industrial site. The overall results showed significant improvement in 2-D and 3-D positioning metrics of ML-augmented filtering when compared to non-ML filtering. On average, the end coordinates in the test set had ca. 10 cm smaller mean location error and ca. 40 cm smaller dispersion in 2-D positioning. In addition, the presence of outliers was reduced significantly as the maximum error offset decreased by several meters. Although ML augmented filtering is computationally slower than non-ML filtering (e.g., ordinary and extended Kalman filter), it is still faster than using CS for UWB integrity estimation. The results show that using the proposed residual features in an ML model provides a feasible approach to predict UWB positioning integrity and use it as a measure of uncertainty in a coordinate filtering scheme.
{"title":"UWB Positioning Integrity Estimation Using Ranging Residuals and ML Augmented Filtering","authors":"Mihkel Tommingas;Muhammad Mahtab Alam;Ivo Müürsepp;Sander Ulp","doi":"10.1109/JISPIN.2024.3418296","DOIUrl":"https://doi.org/10.1109/JISPIN.2024.3418296","url":null,"abstract":"This article investigates the use of ultrawideband (UWB) ranging residuals for coordinate integrity estimation and their use in a filtering scheme. Typically, UWB system accuracy is improved using channel statistics (CSs) to detect and mitigate non-line-of-sight effects between UWB sensors and the object to be located, potentially improving the end coordinate solution. However, in practice, when considering UWB system with a high positioning update rate, this is not a feasible approach, as gathering and processing CS data takes too much time. In contrast to this approach, this article proposes a set of features based on UWB ranging residuals that could be used as an alternative in integrity assessment. By using machine learning (ML), the most important features were extracted from the initial set, and then, used to train and validate a model for UWB coordinate error prediction. Finally, the prediction was applied in an adaptive Kalman filtering scheme as an input for measurement uncertainty. Model testing was done using UWB measurement test dataset gathered at an industrial site. The overall results showed significant improvement in 2-D and 3-D positioning metrics of ML-augmented filtering when compared to non-ML filtering. On average, the end coordinates in the test set had ca. 10 cm smaller mean location error and ca. 40 cm smaller dispersion in 2-D positioning. In addition, the presence of outliers was reduced significantly as the maximum error offset decreased by several meters. Although ML augmented filtering is computationally slower than non-ML filtering (e.g., ordinary and extended Kalman filter), it is still faster than using CS for UWB integrity estimation. The results show that using the proposed residual features in an ML model provides a feasible approach to predict UWB positioning integrity and use it as a measure of uncertainty in a coordinate filtering scheme.","PeriodicalId":100621,"journal":{"name":"IEEE Journal of Indoor and Seamless Positioning and Navigation","volume":"2 ","pages":"205-218"},"PeriodicalIF":0.0,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10568925","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141561019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-05DOI: 10.1109/JISPIN.2024.3385356
Xu Feng;Khuong An Nguyen;Zhiyuan Luo
The advances in Wi-Fi technology have encouraged the development of numerous indoor positioning systems. However, their performance varies significantly across different indoor environments, making it challenging to identify the most suitable system for all scenarios. To address this challenge, we propose an algorithm that dynamically selects the most optimal Wi-Fi positioning model for each location. Our algorithm employs a machine learning weighted model selection algorithm trained on raw Wi-Fi received signal strength (RSS), raw Wi-Fi round-trip time (RTT) data, statistical RSS and RTT measures, and access point line-of-sight information. We tested our algorithm in four complex indoor environments, and compared its performance to traditional Wi-Fi indoor positioning models and state-of-the-art stacking models, demonstrating an improvement of up to 1.8 m on average.
{"title":"A Wi-Fi RSS-RTT Indoor Positioning Model Based on Dynamic Model Switching Algorithm","authors":"Xu Feng;Khuong An Nguyen;Zhiyuan Luo","doi":"10.1109/JISPIN.2024.3385356","DOIUrl":"https://doi.org/10.1109/JISPIN.2024.3385356","url":null,"abstract":"The advances in Wi-Fi technology have encouraged the development of numerous indoor positioning systems. However, their performance varies significantly across different indoor environments, making it challenging to identify the most suitable system for all scenarios. To address this challenge, we propose an algorithm that dynamically selects the most optimal Wi-Fi positioning model for each location. Our algorithm employs a machine learning weighted model selection algorithm trained on raw Wi-Fi received signal strength (RSS), raw Wi-Fi round-trip time (RTT) data, statistical RSS and RTT measures, and access point line-of-sight information. We tested our algorithm in four complex indoor environments, and compared its performance to traditional Wi-Fi indoor positioning models and state-of-the-art stacking models, demonstrating an improvement of up to 1.8 m on average.","PeriodicalId":100621,"journal":{"name":"IEEE Journal of Indoor and Seamless Positioning and Navigation","volume":"2 ","pages":"151-165"},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10493073","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140813902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-03DOI: 10.1109/JISPIN.2024.3384909
Maija Mäkelä;Martta-Kaisa Olkkonen;Martti Kirkko-Jaakkola;Toni Hammarberg;Tuomo Malkamäki;Jesperi Rantanen;Sanna Kaasalainen
Ultra wideband (UWB) signals are a promising choice for indoor positioning applications, since they are able to penetrate walls to a certain extent. Nevertheless, signal reflections and non-line-of-sight propagation cause bias in the measured range. This ranging error can be corrected with machine learning (ML) methods, such as convolutional neural networks (CNNs). However, these ML models often generalize poorly between different environments. In this work we present an instance-based transfer learning (TL) approach, that enables generalizing a CNN-based ranging error mitigation approach to a new situation with only a few unlabeled training samples. The performance of the UWB error correction approach is demonstrated in a real-life infrastructure-free cooperative positioning setting.
超宽带（UWB）信号能够在一定程度上穿透墙壁，因此是室内定位应用的理想选择。然而，信号反射和非视距传播会导致测量范围出现偏差。这种测距误差可以通过机器学习（ML）方法（如卷积神经网络（CNN））来纠正。然而，这些 ML 模型在不同环境之间的泛化能力往往很差。在这项工作中，我们提出了一种基于实例的迁移学习（TL）方法，只需少量未标记的训练样本，就能将基于卷积神经网络的测距误差缓解方法推广到新的环境中。我们在现实生活中的无基础设施合作定位环境中演示了 UWB 误差修正方法的性能。
{"title":"Ubiquitous UWB Ranging Error Mitigation With Application to Infrastructure-Free Cooperative Positioning","authors":"Maija Mäkelä;Martta-Kaisa Olkkonen;Martti Kirkko-Jaakkola;Toni Hammarberg;Tuomo Malkamäki;Jesperi Rantanen;Sanna Kaasalainen","doi":"10.1109/JISPIN.2024.3384909","DOIUrl":"https://doi.org/10.1109/JISPIN.2024.3384909","url":null,"abstract":"Ultra wideband (UWB) signals are a promising choice for indoor positioning applications, since they are able to penetrate walls to a certain extent. Nevertheless, signal reflections and non-line-of-sight propagation cause bias in the measured range. This ranging error can be corrected with machine learning (ML) methods, such as convolutional neural networks (CNNs). However, these ML models often generalize poorly between different environments. In this work we present an instance-based transfer learning (TL) approach, that enables generalizing a CNN-based ranging error mitigation approach to a new situation with only a few unlabeled training samples. The performance of the UWB error correction approach is demonstrated in a real-life infrastructure-free cooperative positioning setting.","PeriodicalId":100621,"journal":{"name":"IEEE Journal of Indoor and Seamless Positioning and Navigation","volume":"2 ","pages":"143-150"},"PeriodicalIF":0.0,"publicationDate":"2024-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10490099","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140641622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study aims to realize self-position estimation for indoor robots using only a single acoustic channel. When a single omnidirectional transmitter/receiver is used as an object detection sensor, detected objects are identified on concentric circles with the transmitter/receiver as the center point. Self-position estimation method using this sensor cannot use the directional information of the detected object. This fact makes it impossible to specify the robot's turning angle using environmental information. In this article, we propose a self-position estimation method using a single omnidirectional transmitter/receiver that can consider the direction of the reflected object by estimating the direction of the reflected wave from the Doppler effect generated during the robot's movement. The self-position estimation was implemented by using echo images of the direction of arrival of sound waves estimated from the Doppler effect and the distance of arrival of sound waves estimated from the impulse response and matching them with a previously generated map image. The accuracy of the proposed method was evaluated by simulation and experiment. In the simulation, an average position estimation error of 0.042 m was achieved; in the experiment, it was 0.051 m. Furthermore, experimental and simulation results show that using the Doppler effect contributes to self-position estimation accuracy.
{"title":"Self-Localization Method Using a Single Acoustic Ranging Sensor Based on Impulse Response and Doppler Effect","authors":"Atsushi Tsuchiya;Naoto Wakatsuki;Tadashi Ebihara;Keiichi Zempo;Koichi Mizutani","doi":"10.1109/JISPIN.2024.3403519","DOIUrl":"https://doi.org/10.1109/JISPIN.2024.3403519","url":null,"abstract":"This study aims to realize self-position estimation for indoor robots using only a single acoustic channel. When a single omnidirectional transmitter/receiver is used as an object detection sensor, detected objects are identified on concentric circles with the transmitter/receiver as the center point. Self-position estimation method using this sensor cannot use the directional information of the detected object. This fact makes it impossible to specify the robot's turning angle using environmental information. In this article, we propose a self-position estimation method using a single omnidirectional transmitter/receiver that can consider the direction of the reflected object by estimating the direction of the reflected wave from the Doppler effect generated during the robot's movement. The self-position estimation was implemented by using echo images of the direction of arrival of sound waves estimated from the Doppler effect and the distance of arrival of sound waves estimated from the impulse response and matching them with a previously generated map image. The accuracy of the proposed method was evaluated by simulation and experiment. In the simulation, an average position estimation error of 0.042 m was achieved; in the experiment, it was 0.051 m. Furthermore, experimental and simulation results show that using the Doppler effect contributes to self-position estimation accuracy.","PeriodicalId":100621,"journal":{"name":"IEEE Journal of Indoor and Seamless Positioning and Navigation","volume":"2 ","pages":"193-204"},"PeriodicalIF":0.0,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10535727","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141474966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-13DOI: 10.1109/JISPIN.2024.3377146
Francesco Furfari;Michele Girolami;Paolo Barsocchi
The increasing adoption of location-based services drives the pervasive adoption of localization systems available anywhere. Environments equipped with multiple indoor localization systems (ILSs) require managing the transition from one ILS to another in order to continue localizing the user's device even when moving indoor or outdoor. In this article, we focus on the handoff procedure, whose goal is to enable a device to trigger the transition between ILSs when specific conditions are verified. We distinguish between the triggering and managing operations, each requiring specific actions. We describe the activation of the handoff procedure by considering three types of ILSs design, each with increasing complexity. Moreover, we define five handoff algorithms-based RSSI signal analysis and we test them in a realistic environment with two nearby ILSs. We establish a set of evaluation metrics to measure the performance of the handoff procedure.
基于位置的服务越来越多地被采用，推动了可在任何地方使用的本地化系统的普及。在配备多个室内定位系统（ILS）的环境中，需要管理从一个 ILS 到另一个 ILS 的转换，以便即使在室内或室外移动时也能继续定位用户设备。在本文中，我们将重点讨论切换程序，其目标是使设备能够在特定条件得到验证时触发 ILS 之间的切换。我们将触发操作和管理操作区分开来，每种操作都需要特定的操作。我们通过考虑三种类型的 ILS 设计来描述切换程序的启动，每种类型的复杂性都在增加。此外，我们还定义了五种基于 RSSI 信号分析的切换算法，并在两个邻近 ILS 的现实环境中对其进行了测试。我们建立了一套评估指标来衡量切换程序的性能。
{"title":"Integrating Indoor Localization Systems Through a Handoff Protocol","authors":"Francesco Furfari;Michele Girolami;Paolo Barsocchi","doi":"10.1109/JISPIN.2024.3377146","DOIUrl":"https://doi.org/10.1109/JISPIN.2024.3377146","url":null,"abstract":"The increasing adoption of location-based services drives the pervasive adoption of localization systems available anywhere. Environments equipped with multiple indoor localization systems (ILSs) require managing the transition from one ILS to another in order to continue localizing the user's device even when moving indoor or outdoor. In this article, we focus on the handoff procedure, whose goal is to enable a device to trigger the transition between ILSs when specific conditions are verified. We distinguish between the triggering and managing operations, each requiring specific actions. We describe the activation of the handoff procedure by considering three types of ILSs design, each with increasing complexity. Moreover, we define five handoff algorithms-based RSSI signal analysis and we test them in a realistic environment with two nearby ILSs. We establish a set of evaluation metrics to measure the performance of the handoff procedure.","PeriodicalId":100621,"journal":{"name":"IEEE Journal of Indoor and Seamless Positioning and Navigation","volume":"2 ","pages":"130-142"},"PeriodicalIF":0.0,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10471883","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140537357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-09DOI: 10.1109/JISPIN.2024.3398568
Maximilian Stahlke;Tobias Feigl;Sebastian Kram;Bjoern M. Eskofier;Christopher Mutschler
Indoor radio environments often consist of areas with mixed propagation conditions. In line-of-sight (LoS)-dominated areas, classic time-of-flight (ToF) methods reliably return accurate positions, while in nonline-of-sight (NLoS) dominated areas (AI-based) fingerprinting methods are required. However, fingerprinting methods are only cost-efficient if they are used exclusively in NLoS-dominated areas due to their expensive life cycle management. Systems that are both accurate and cost-efficient in LoS- and NLoS-dominated areas require identification of those areas to select the optimal localization method. To enable a reliable and robust life cycle management of fingerprinting, we must identify altered fingerprints to trigger update processes. In this article, we propose methods for uncertainty estimation of AI-based fingerprinting to determine its spatial boundaries and validity. Our experiments show that we can successfully identify spatial boundaries of the fingerprinting models and detect corrupted areas. In contrast to the state-of-the-art, our approach employs an intrinsic identification through out-of-distribution (OOD) detection, rendering external detection approaches unnecessary.
室内无线电环境通常由混合传播条件的区域组成。在以视距（LoS）为主的区域，传统的飞行时间（ToF）方法可以可靠地返回准确位置，而在以非视距（NLoS）为主的区域，则需要基于人工智能的指纹识别方法。然而，由于指纹识别方法的生命周期管理成本高昂，因此只有在 NLoS 占主导地位的区域专门使用这种方法才具有成本效益。要想在 LoS 和 NLoS 占主导地位的区域实现既准确又经济高效的系统，就必须识别这些区域，以选择最佳定位方法。为了对指纹进行可靠、稳健的生命周期管理，我们必须识别已更改的指纹，以触发更新过程。在本文中，我们提出了对基于人工智能的指纹识别进行不确定性估计的方法，以确定其空间边界和有效性。我们的实验表明，我们可以成功识别指纹模型的空间边界，并检测出损坏的区域。与最先进的方法相比，我们的方法通过分布外检测（OOD）进行内在识别，从而无需外部检测方法。
{"title":"Uncertainty-Based Fingerprinting Model Monitoring for Radio Localization","authors":"Maximilian Stahlke;Tobias Feigl;Sebastian Kram;Bjoern M. Eskofier;Christopher Mutschler","doi":"10.1109/JISPIN.2024.3398568","DOIUrl":"https://doi.org/10.1109/JISPIN.2024.3398568","url":null,"abstract":"Indoor radio environments often consist of areas with mixed propagation conditions. In line-of-sight (LoS)-dominated areas, classic time-of-flight (ToF) methods reliably return accurate positions, while in nonline-of-sight (NLoS) dominated areas (AI-based) fingerprinting methods are required. However, fingerprinting methods are only cost-efficient if they are used exclusively in NLoS-dominated areas due to their expensive life cycle management. Systems that are both accurate and cost-efficient in LoS- and NLoS-dominated areas require identification of those areas to select the optimal localization method. To enable a reliable and robust life cycle management of fingerprinting, we must identify altered fingerprints to trigger update processes. In this article, we propose methods for uncertainty estimation of AI-based fingerprinting to determine its spatial boundaries and validity. Our experiments show that we can successfully identify spatial boundaries of the fingerprinting models and detect corrupted areas. In contrast to the state-of-the-art, our approach employs an intrinsic identification through out-of-distribution (OOD) detection, rendering external detection approaches unnecessary.","PeriodicalId":100621,"journal":{"name":"IEEE Journal of Indoor and Seamless Positioning and Navigation","volume":"2 ","pages":"166-176"},"PeriodicalIF":0.0,"publicationDate":"2024-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10526425","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141078825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-06DOI: 10.1109/JISPIN.2024.3397229
Ziyou Li;Ni Zhu;Valérie Renaudin
The performance of the global navigation satellite system (GNSS)-based navigation is usually degraded in challenging environments, such as deep urban and light indoors. In such environments, the satellite visibility is reduced, and the complex propagation conditions perturb the GNSS signals with attenuation, refraction, and frequent reflection. This article presents a novel artificial intelligence (AI)-based approach, to tackle the complex GNSS positioning problems in deep urban, even light indoors. The new approach, called LIGHT, i.e., Light Indoor GNSS macHine-learning-based Time difference carrier phase, can select healthy GNSS carrier phase data for positioning, thanks to machine learning (ML). The selected carrier phase data are fed into a time difference carrier phase (TDCP)-based extended Kalman filter to estimate the user's velocity. Four trajectories including shopping mall, railway station, shipyard, as well as urban canyon scenarios over a 3.2-km total walking distance with a handheld device are tested. It is shown that at least half of the epochs are selected as usable for light indoor GNSS TDCP standalone positioning, and the accuracy of the velocity estimates can improve up to 88% in terms of the 75 ${text{th}}$ percentile of the absolute horizontal velocity error compared with the state-of-the-art non-ML approach. Furthermore, a newly designed hybridization filter LIGHT-PDR that fuses the LIGHT algorithm and pedestrian dead reckoning solution is applied to perform seamless indoor/outdoor positioning in a more robust manner.
{"title":"Self-Contained Pedestrian Navigation Fusing ML-Selected GNSS Carrier Phase and Inertial Signals in Challenging Environments","authors":"Ziyou Li;Ni Zhu;Valérie Renaudin","doi":"10.1109/JISPIN.2024.3397229","DOIUrl":"https://doi.org/10.1109/JISPIN.2024.3397229","url":null,"abstract":"The performance of the global navigation satellite system (GNSS)-based navigation is usually degraded in challenging environments, such as deep urban and light indoors. In such environments, the satellite visibility is reduced, and the complex propagation conditions perturb the GNSS signals with attenuation, refraction, and frequent reflection. This article presents a novel artificial intelligence (AI)-based approach, to tackle the complex GNSS positioning problems in deep urban, even light indoors. The new approach, called LIGHT, i.e., Light Indoor GNSS macHine-learning-based Time difference carrier phase, can select healthy GNSS carrier phase data for positioning, thanks to machine learning (ML). The selected carrier phase data are fed into a time difference carrier phase (TDCP)-based extended Kalman filter to estimate the user's velocity. Four trajectories including shopping mall, railway station, shipyard, as well as urban canyon scenarios over a 3.2-km total walking distance with a handheld device are tested. It is shown that at least half of the epochs are selected as usable for light indoor GNSS TDCP standalone positioning, and the accuracy of the velocity estimates can improve up to 88% in terms of the 75\u0000<inline-formula><tex-math>${text{th}}$</tex-math></inline-formula>\u0000 percentile of the absolute horizontal velocity error compared with the state-of-the-art non-ML approach. Furthermore, a newly designed hybridization filter LIGHT-PDR that fuses the LIGHT algorithm and pedestrian dead reckoning solution is applied to perform seamless indoor/outdoor positioning in a more robust manner.","PeriodicalId":100621,"journal":{"name":"IEEE Journal of Indoor and Seamless Positioning and Navigation","volume":"2 ","pages":"177-192"},"PeriodicalIF":0.0,"publicationDate":"2024-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10520899","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141078826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：