An official website of the United States government
Indoor navigation is necessary for users to explore large unfamiliar indoor environments such as airports, shopping malls, and hospital complex, which relies on the capability of continuously tracking a user's location. A typical indoor navigation system is built on top of a suitable Indoor Positioning System (IPS) and requires the user to periodically submit location queries to learn their whereabouts whereby to provide update-to-date navigation information. Received signal strength (RSS)-based IPSes are considered as one of the most classical IPSes, which locates a user by comparing the user's RSS measurement with the fingerprints collected at different locations in advance. Despite its significant advantages, existing RSS-IPSes suffer from two key challenges, the ambiguity of RSS fingerprints and device diversity, that may greatly reduce its positioning accuracy. In this paper, we introduce the design and evaluation of CITS, a novel RSS-based continuous indoor tracking system that can effectively cope with fingerprint ambiguity and device diversity via differential RSS fingerprint matching. Detailed experiment studies confirm the significant advantages of CITS over prior RSS-based solutions.
more »
« less
This content will become publicly available on October 26, 2026
Hybrid Fingerprint-based Positioning in Cell-Free Massive MIMO Systems
Recently, there has been an increasing interest in 6G technology for integrated sensing and communications, where positioning stands out as a key application. In the realm of 6G, cell-free massive multiple-input multiple-output systems, featuring distributed base stations equipped with a large number of antennas, present an abundant source of angle-of-arrival (AOA) information that could be exploited for positioning applications. In this paper we leverage this AOA information at the base stations using the multiple signal classification algorithm, in conjunction with received signal strength (RSS) for positioning through Gaussian process regression (GPR). An AOA fingerprint database is constructed by capturing the angle data from multiple locations across the network area and is combined with RSS data from the same locations to form a hybrid fingerprint which is then used to train a GPR model employing a squared exponential kernel. The trained regression model is subsequently utilized to estimate the location of a user equipment. Simulations demonstrate that the GPR model with hybrid input achieves better positioning accuracy than traditional GPR models utilizing RSS-only and AOA-only inputs.
more »
« less
- Award ID(s):
- 2129015
- PAR ID:
- 10666234
- Publisher / Repository:
- Asilomar Conference on Signals, Systems, and Computers
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Accurate indoor localization is crucial for enabling spatial context in smart environments and navigation systems. Wi-Fi Received Signal Strength (RSS) fingerprinting is a widely used indoor localization approach due to its compatibility with mobile embedded devices. Deep Learning (DL) models improve accuracy in localization tasks by learning RSS variations across locations, but they assume fingerprint vectors exist in a Euclidean space, failing to incorporate spatial relationships and the non-uniform distribution of real-world RSS noise. This results in poor generalization across heterogeneous mobile devices, where variations in hardware and signal processing distort RSS readings. Graph Neural Networks (GNNs) can improve upon conventional DL models by encoding indoor locations as nodes and modeling their spatial and signal relationships as edges. However, GNNs struggle with non-Euclidean noise distributions and suffer from the GNN blind spot problem, leading to degraded accuracy in environments with dense access points (APs). To address these challenges, we propose GATE, a novel framework that constructs an adaptive graph representation of fingerprint vectors while preserving an indoor state-space topology, modeling the non-Euclidean structure of RSS noise to mitigate environmental noise and address device heterogeneity. GATE introduces (1) a novel Attention Hyperspace Vector (AHV) for enhanced message passing, (2) a novel Multi-Dimensional Hyperspace Vector (MDHV) to mitigate the GNN blind spot, and (3) a new Real-Time Edge Construction (RTEC) approach for dynamic graph adaptation. Extensive real-world evaluations across multiple indoor spaces with varying path lengths, AP densities, and heterogeneous devices demonstrate that GATE achieves 1.6 × to 4.72 × lower mean localization errors and 1.85 × to 4.57 × lower worst-case errors compared with state-of-the-art indoor localization frameworks.more » « less
-
Abstract: The vast amount of spectrum available for millimeter wave (mmWave) wireless communication systems will support accurate real-time positioning concurrent with communication signaling. This paper demonstrates that accurate estimates of the position of an unknown node can be determined using estimates of time of arrival (ToA), angle of arrival (AoA), as well as data fusion or machine learning. Real-world data at 28 GHz and 73 GHz is used to show that AoA-based localization techniques will need to be augmented with other positioning techniques. The fusion of AoA-based positioning with received power measurements for RXs in an office which has dimensions of 35 m by 65.5 m is shown to provide location accuracies ranging from 16 cm to 3.25 m, indicating promise for accurate positioning capabilities in future networks. Received signal strength intensity (RSSI) based positioning techniques that exploit the ordering of the received power can be used to determine rough estimates of user position. Prediction of received signal characteristics is done using 2-D ray tracing.more » « less
-
Indoor positioning systems (IPSes) can enable many location-based services in large indoor venues where GPS signals are unavailable or unreliable. Among the most viable types of IPSes, RSS-IPSes rely on ubiquitous smartphones and indoor WiFi infrastructures and explore distinguishable received signal strength (RSS) measurements at different indoor locations as their location fingerprints. RSS-IPSes are unfortunately vulnerable to physical-layer RSS attacks that cannot be thwarted by conventional cryptographic techniques. Existing defenses against RSS attacks are all subject to an inherent tradeoff between indoor positioning accuracy and attack resilience. This paper presents the design and evaluation of MV-IPS, a novel RSS-IPS based on weighted multi-voting, which does not suffer from this tradeoff. In MV-IPS, every WiFi access point (AP) that receives a user’s RSS measurement gives a weighted vote for every reference location, and the reference location that receives the highest accumulative votes from all APs is output as the user’s most likely position. Trace-driven simulation studies based on real RSS measurements demonstrate that MV-IPS can achieve much higher positioning accuracy than prior solutions no matter whether RSS attacks are present.more » « less
-
WiFi received signal strength (RSS) environment evolves over time due to the movement of access points (APs), AP power adjustment, installation and removal of APs, etc. We study how to effectively update an existing database of fingerprints, defined as the RSS values of APs at designated locations, using a batch of newly collected unlabelled (possibly crowdsourced) WiFi signals. Prior art either estimates the locations of the new signals without updating the existing fingerprints or filters out the new APs without sufficiently embracing their features. To address that, we propose GUFU, a novel effective graph-based approach to update WiFi fingerprints using unlabelled signals with possibly new APs. Based on the observation that similar signal vectors likely imply physical proximity, GUFU employs a graph neural network (GNN) and a link prediction algorithm to retrain an incremental network given the new signals and APs. After the retraining, it then updates the signal vectors at the designated locations. Through extensive experiments in four large representative sites, GUFU is shown to achieve remarkably higher fingerprint adaptivity as compared with other state-of-the-art approaches, with error reduction of 21.4% and 29.8% in RSS values and location prediction, respectively.more » « less
