Ultra-wide band (UWB) localization system suffers from deteriorating performance in complex scenes, especially in non-line-of-sight (NLOS) conditions. In order to improve the accuracy and robustness of the localization system in NLOS environments, we propose an end-to-end deep neural network with both distance and received signal strength (RSS) measurements. On one hand, high-level spatial-temporal features can be learned through the proposed network from both RSS and distance data, which benefits the localization performance. On the other hand, the proposed network is robust to the variance in the number of available anchors, leading to high adaptability to different scenes. Specifically, three modules are designed in the deep network: 1) a module based on convolutional neural network (CNN) is presented to extract the local spatial features from the input data, and the structure of this module lends itself to varying-dimension input. 2) To manage the correlations between consecutive frames, we develop a deep long short-term memory (LSTM) model to extract temporal features and provide a high-level representation for a series of input data. 3) Finally, the fully-connected layers are utilized to estimate the 3D positions of the UWB tag. We conduct extensive experiments in three real-world scenarios to evaluate the proposed deep network. The experimental results indicate that the proposed network can significantly improve the accuracy and robustness of the UWB localization results, especially in NLOS situations.

In this article, a resilient tightly coupled ultra-wideband (UWB) visual–inertial indoor localization system (R-UVIS) is developed to obtain accurate and robust localization performance in complex scenes, even in the case when sensors fail. More specifically, three schemes are designed for the proposed system. First, we introduce the line and image patch features to improve the precision and robustness of the visual features. Besides, we propose accurate loop closure and relocalization methods based on multifeatures to improve the performance of the localization system. Second, we introduce the UWB sensor into the system to suppress the localization drifts in the complex scenes and provide a fixed reference frame. Third, we propose a resilient multisensor fusion method based on an optimization framework to fuse the UWB, visual and inertial measurements in a tightly coupled manner. This data fusion approach improves the robustness of the system, making the localization system seamlessly switch among different localization modes depending on the specific scenes. In addition, an initialization process along with three sensors is also designed for the whole system. We conduct extensive experiments on the public dataset and in real-world scenarios to evaluate the proposed R-UVIS. The experimental results show that the proposed R-UVIS can provide the accurate and robust localization results in a fixed coordinate system for the complicated indoor scenes, even in the case when visual tracking fails or the UWB anchors are unavailable.

In this paper, we propose a self-supervised deep network that mainly applies location and ranging error corrections to a classical UWB localization approach to improve its accuracy. The core of this method is the self-supervised learning strategy which removes the requirement for ground-truth in the training process, and thus reduces the training cost of the method. To this end, we first use an existing classical UWB localization approach to provide an initial tag location, and then build a deep location and ranging error correction (DLRC) network to jointly estimate the tag position corrections and distance corrections. The self-supervised training strategy is built based on these regressed corrections and the initial tag position as well as the fixed anchor positions and raw ranging measurements, through the topological structure of the UWB sensors. Finally, the initial tag location can be corrected by the trained DLRC network. For this proposed method, it makes use of high-level representations of the UWB measurements by the deep network, while the geometric information important for UWB localization is also considered though the self-training strategy and the classical approach. Therefore, it can effectively improve the localization performance compared to the stat-of-the-art classical approach. This improvement is also verified by conducting real-world experiments.

Accurate UWB Localization is still a challenging issue in complex environments. In this paper, we propose a novel UWB localization method with two-fold strategies to further improve its robustness and accuracy: 1) we construct the UWB ranging measurements into a graph structure and design a spatial-temporal attention graph neural network (STA-GNN) to handle it, and 2) we utilize multiple tags to obtain multiple ranging measurements, comprehensively establish the geometric relationship between these measurements, and design a novel cost function to train the proposed network effectively. Our real-world experiments demonstrate that: 1) compared to the convolutional neural networks (CNN) and long short-term memory (LSTM) which have been used in UWB localization, the graph neural network can better capture the geometric relationships from the UWB ranging measurements, leading to a better estimation for tag location. In addition, our proposed STA-GNN can effectively extract high-level spatial-temporal features from the measurements, which benefit UWB localization, and 2) using multiple tags can provide more information and geometric constraints, which can help improve the accuracy and robustness of UWB localization compare to the single tag-based methods, especially in non-line-of-sight (NLOS) environments.

Learning-based TOA-UWB localization methods have been developed rapidly in recent years and achieve state-of-the-art localization results in complex scenes. However, they still suffer from two drawbacks: 1) biased measurements with large noise are not suppressed effectively, and 2) geometric information which is important for UWB localization is not considered. Thus, we propose two twofold strategies in this paper to overcome these issues: 1) A novel deep attention-based network is proposed. In this network, we introduce the transformer encoder to learn the weights of different ranging measurements, and thus suppress the adverse impact of the biased measurements. Meanwhile, the anchor positions including the geometric information are introduced into the network by an embedding module. 2) We present a novel learning strategy to train the proposed network. This learning strategy both considers the pre-collected ground-truth and the geometric constraints of UWB sensors. Through these two strategies, large measurement noise is further suppressed, while the geometric information and constraints are also developed for the proposed network. Therefore, the localization performance is improved. We build real-world experiments in a narrow and complex indoor scene to demonstrate the advantages of our proposed method compared to the state-of-the-art learning-based method.