An official website of the United States government
Indoor localization plays a vital role in applications such as emergency response, warehouse management, and augmented reality experiences. By deploying machine learning (ML) based indoor localization frameworks on their mobile devices, users can localize themselves in a variety of indoor and subterranean environments. However, achieving accurate indoor localization can be challenging due to heterogeneity in the hardware and software stacks of mobile devices, which can result in inconsistent and inaccurate location estimates. Traditional ML models also heavily rely on initial training data, making them vulnerable to degradation in performance with dynamic changes across indoor environments. To address the challenges due to device heterogeneity and lack of adaptivity, we propose a novel embedded ML framework calledFedHIL. Our framework combines indoor localization and federated learning (FL) to improve indoor localization accuracy in device-heterogeneous environments while also preserving user data privacy.FedHILintegrates a domain-specific selective weight adjustment approach to preserve the ML model's performance for indoor localization during FL, even in the presence of extremely noisy data. Experimental evaluations in diverse real-world indoor environments and with heterogeneous mobile devices show thatFedHILoutperforms state-of-the-art FL and non-FL indoor localization frameworks.FedHILis able to achieve 1.62 × better localization accuracy on average than the best performing FL-based indoor localization framework from prior work.
more »
« less
Bringing UWB Indoor Localization Closer to being Universal and Pervasive
Location-based services have the potentials to change how we interact with the places and things around us. UWB indoor localization is one of the most successful enabling technologies that has achieved decimeter accuracy with robustness against complex indoor multipath environments. In this work, we demonstrate a system that not only achieves high localization accuracy, but also supports infinite scalability, full user privacy, and plug-and-play infrastructure deployment, which brings localization closer to a universal and pervasive technology.
more »
« less
- Award ID(s):
- 2145278
- PAR ID:
- 10409075
- Date Published:
- Journal Name:
- ubicompiswc22adjunct: Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing
- Page Range / eLocation ID:
- 18 to 20
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Indoor localization is a challenging task. Compared to outdoor environments where GPS is dominant, there is no robust and almost-universal approach. Recently, machine learning (ML) has emerged as the most promising approach for achieving accurate indoor localization. Nevertheless, its main challenge is requiring large datasets to train the neural networks. The data collection procedure is costly and laborious, requiring extensive measurements and labeling processes for different indoor environments. The situation can be improved by Data Augmentation (DA), a general framework to enlarge the datasets for ML, making ML systems more robust and increasing their generalization capabilities. This paper proposes two simple yet surprisingly effective DA algorithms for channel state information (CSI) based indoor localization motivated by physical considerations. We show that the number of measurements for a given accuracy requirement may be decreased by an order of magnitude. Specifically, we demonstrate the algorithms’ effectiveness by experiments conducted with a measured indoor WiFi measurement dataset: As little as 10% of the original dataset size is enough to get the same performance as the original dataset. We also showed that if we further augment the dataset with the proposed techniques, test accuracy is improved more than three-fold.more » « less
-
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
-
Indoor localization is emerging as an important application domain for enhanced navigation (or tracking) of people and assets in indoor locales such as buildings, malls, and underground mines. Most indoor localization solutions proposed in prior work do not deliver good accuracy without expensive infrastructure (and even then, the results may lack consistency). Ambient wireless received signal strength indication (RSSI) based fingerprinting using smart mobile devices is a low-cost approach to the problem. However, creating an accurate ‘fingerprinting-only’ solution remains a challenge. This paper presents a novel approach to transform Wi-Fi signatures into images, to create a scalable fingerprinting framework based on Convolutional Neural Networks (CNNs). Our proposed CNN based indoor localization framework (CNN-LOC) is validated across several indoor environments and shows improvements over the best known prior works, with an average localization error of < 2 meters.more » « less
-
Enabling reliable indoor localization can facilitate several new applications akin to how outdoor localization systems, such as GPS, have facilitated. Currently, a few key hurdles remain that prevent indoor localization from reaching the same stature. These hurdles include complicated deployment, tight time synchronization requirements from time difference of arrival protocols, and a lack of mechanism to allow a pan-building seamless solution. This work explores ways in which these key hurdles can be overcome to enable a more pervasive use of indoor localization. We propose a novel passive ranging scheme where clients overhear ongoing two-way ranging wireless communication between a few infrastructure nodes, and compute their own relative location without transmitting any signals (preserving user privacy). Our approach of performing two-way ranging between infrastructure nodes removes a crucial timing requirement in traditional time-difference-of-arrival methods thereby relaxing the synchronization requirements imposed by previous techniques. We use ultra-wideband wireless (UWB) radios that can easily penetrate building materials so that spanning an entire floor of a large building with just a few infrastructure nodes is possible. We build working prototypes, including the necessary hardware, and demonstrate the plug-and-play nature of our proposed solution. Our evaluation in three indoor spaces shows 1–2 meter-level localization accuracy with areas as large as 2241sq.m. We expect our explorations to re-trigger interest in novel applications for indoor spaces based on fine-grained indoor location knowledge.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3544793.3560327
