Localization has been extensively studied owing to its huge potential in various areas, such as Internet of Things, 5G, and unmanned aerial vehicle services. Its wide applications include home automation, advanced production automation, and unmanned vehicle control. In this study, we propose a novel localization method that utilizes convolutional neural network (CNN) and ultra-wideband (UWB) signals. A localization problem is converted to a regression problem with the proposed CNN, in which the ranging and positioning phases are integrated. By integrating the ranging and positioning phases, the proposed CNN estimates the location of UWB transmitter directly without any additional step. To integrate both phases of localization, a simple-yet efficient input image generation method is proposed. In the proposed input image generation method, three oversampled two-dimensional input images are generated from the three received UWB signals and they are provided to the designed CNN through the three channels, which are represented by red-, green-, and blue-color channels, respectively. The proposed CNN-based localization system then estimates the location of the UWB transmitter directly using the three-channel image as an input of the CNN. Simulation results verify that the proposed CNN-based localization method outperforms the traditional threshold-based and existing CNN-based methods. Also, it is observed that the proposed method performs well under an asymmetric environment, unlike the existing method.

The localization system has been extensively studied because of its diverse applicability, for example, in the Internet of Things, automatic management, and unmanned aerial vehicle services. There have been numerous studies on localization in two-dimensional (2D) environments, but those in three-dimensional (3D) environments are scarce. In this paper, we propose a novel localization method that utilizes the gated recurrent unit (GRU) and ultra-wideband (UWB) signals. For the purpose of this study, we considered that the UWB transmitter (Tx) and many UWB receivers (Rx) were placed inside a confined space. The input of the proposed model was generated from the UWB signals that are sent from the Tx to the Rxs, and the output was the location of the Tx. The proposed GRU-based model converts the localization problem into a regression problem by combining the ranging and positioning phase. Thus, the proposed model can directly estimate the location of the Tx. Our proposed GRU-based method achieves 15 and four times shorter execution times for the training and testing, respectively, compared to the existing convolutional neural network (CNN)-based localization methods. The input data can also be easily generated with low complexity. The rows of the input matrix are the downsampled version of the UWB received signal. Throughout numerous simulation results, our novel localization method can achieve a lower root-mean-squared error up to 0.8 meters compared to the recently proposed existing CNN-based method. Furthermore, the proposed method operates well inside a confined space with fixed volume but varying width, height, and depth. INDEX TERMS 3D localization; deep learning; gated recurrent unit (GRU); recurrent neural network (RNN); ultra-wideband (UWB) system.

No abstract

We prove a generalization of the Brody reparametrization lemma.

No abstract