Improving Indoor Localization Using Mobile UWB Sensor and Deep Neural Networks

Abstract

Accurate localization in indoor environments with ultra-wideband (UWB) technology has long attracted much attention. However, due to the presence of multipath components or non-line of sight (NLOS) propagation of the radio signals, it has been converted to a critical challenge. Existing solutions use many fixed anchors in the indoor environment. Particularly, large areas require many anchor points and in the case of unexpected events that lead to the destruction of existing infrastructures, the fixed anchor points cannot be used. In this paper, a novel localization framework based on the transmitting signal from a mobile UWB sensor outside of the building and its received signal regarding the modified Saleh Valenzuela (SV) channel model is presented. After preprocessing the received signals, two new procedures to reduce the ranging error caused by multipath components are proposed. In the first procedure, two machine learning algorithms including multi-layer perceptron (MLP) and support vector machine (SVM) using the extracted features from the received UWB signal time and power vectors are implemented. Moreover, in the second procedure, two deep learning algorithms including MLP and convolutional neural networks (CNNs) using the received UWB signal time and power vectors are implemented to improve the performance of the indoor localization system. The simulation results show that the architecture designed for the convolutional neural network based on the hybrid dataset (the combination of the dataset related to received UWB signal time and power vectors) provides a mean absolute error (MAE) of about 3 cm.

On Indoor Localization Using WiFi, BLE, UWB, and IMU Technologies

“…Due to their interconnected nature, models made up of these layers scale very poorly when the number of neurons in a layer is increased. DNNs have been applied to a wide range of tasks in indoor localization [70,118,119]. One example application of an ANN to indoor localization is [120], which detects LoS blockages on BLE technology and corrects the corresponding RSS dips.…”

“…Indoor localization is a relatively mature area of research [70], opening up the field to applications in a wide number of areas such as care homes, malls, and disaster relief as well as for asset tracking in factory environments. To help identify potential future trends in IPS, a survey of the papers published in the field was performed using Scopus.…”

“…In [70], the authors used a UAV with a UWB sensor onboard to act as a mobile AP gathering signal data from transmitters inside an arbitrary location. Where UWB sensors are already available, this solution allows for localization in areas where there is no indoor localization system already in place and no means of installing one.…”

Snake optimizer LSTM-based UWB positioning method for unmanned crane

“…Experimental evaluations conducted in a greenhouse with multiple intervals demonstrated significant mitigation of positioning errors in NLOS environments, while retaining usability even in severely obstructed scenarios. To address the challenges posed by multipath and non-line-of-sight propagation in UWB signals, reference [ 33 ] proposed a novel positioning framework. By extracting features from time and power vectors obtained from UWB signals, a multi-layer perceptron (MLP) and a convolutional neural network (CNN) were employed to enhance the performance of indoor positioning systems.…”

Novel Classification Method to Predict the Accuracy of UWB Ranging Estimates

“…The most common radio-frequency-based technology is global navigation satellite system (GNSS). However, it lacks the necessary accuracy in many applications, especially in indoor environments [8]. For real-time tracking in indoor environments, other radio-frequency-based RTLSs such as bluetooth low energy (BLE), ultra wideband (UWB) or Wi-Fi have better accuracy [9].…”