Performance Improvement of Asynchronous UWB Position Location Algorithm Using Multiple Pulse Transmission

Localization using ultra-wide band (UWB) signals gives accurate position results for indoor localization. The penetrating characteristics of UWB pulses reduce the multipath effects and identify the user position with precise accuracy. In UWB-based localization, the localization accuracy depends on the distance estimation between anchor nodes (ANs) and the UWB tag based on the time of arrival (TOA) of UWB pulses. The TOA errors in the UWB system, reduce the distance estimation accuracy from ANs to the UWB tag and adds the localization error to the system. The position accuracy of a UWB system also depends on the line of sight (LOS) conditions between the UWB anchors and tag, and the computational complexity of localization algorithms used in the UWB system. To overcome these UWB system challenges for indoor localization, we propose a deep learning approach for UWB localization. The proposed deep learning model uses a long short-term memory (LSTM) network for predicting the user position. The proposed LSTM model receives the distance values from TOA-distance model of the UWB system and predicts the current user position. The performance of the proposed LSTM model-based UWB localization system is analyzed in terms of learning rate, optimizer, loss function, batch size, number of hidden nodes, timesteps, and we also compared the mean localization accuracy of the system with different deep learning models and conventional UWB localization approaches. The simulation results show that the proposed UWB localization approach achieved a 7 cm mean localization error as compared to conventional UWB localization approaches.

show abstract

“…The model presented in Reference [26] is used for the UWB simulation. Figure 2 shows the flow chart of the UWB localization system.…”

Section: Uwb Modelmentioning

confidence: 99%

“…The simulation uses the pulse width of 0.5 ns and Figure 3 shows the generated UWB pulse for transmission. The UWB transmitted signal is expressed as [26]…”

Section: Uwb Modelmentioning

confidence: 99%

UWB Indoor Localization Using Deep Learning LSTM Networks

Poulose

Han

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Wireless network positioning and inertial navigation technologies are gradually being developed as one of the primary means to compensate for the shortcomings of satellite positioning. Bluetooth [17], Wi-Fi [18], and ultra-wide band [19][20][21] technologies have gained a lot of attention; however, when the application scale is expanded from one building to a city, these local area network-based positioning technologies incur great costs. The introduction of methods such as inertial navigation systems and pedestrian dead reckoning does not improve the performance of the RTK in terms of accuracy, and may lead to the accumulation of errors [22][23][24].…”

Section: Introductionmentioning

confidence: 99%

Performance research of real-time kinematic/5G combined positioning model

Li¹,

Tu²,

Han³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Global Navigation Satellite System provides real-time and all-weather positioning with high accuracy. Under a good observational environment, short-baseline real-time kinematic (RTK) can provide centimeter-level positioning results. However, RTK without model correction of ionospheric delay will significantly reduce the positioning accuracy, and cannot achieve fast and high-precision positioning when the baseline is too long or heavily occluded. Therefore, we proposed a combined RTK/fifth-generation (5G) mobile communication technology positioning model by combining global positioning system-RTK with the 5G time of arrival observations to improve the positioning accuracy under medium and long baselines. Experimental validation and analysis were conducted based on the measured data of different baseline lengths. Results revealed that the combined RTK/5G positioning model markedly improved the positioning performance in both static and dynamic modes under medium- and long-distance baselines. In particular, the RTK/5G model can also achieve good positioning results in conditions where some satellites are occluded. The combined RTK/5G positioning model is important for achieving high accuracy and real-time and continuous positioning in complex environments.

show abstract

Accurate TOA-Based UWB Localization System in Coal Mine Based on WSN

Guang-liang

2012

Physics Procedia

View full text Add to dashboard Cite

Performance Improvement of Asynchronous UWB Position Location Algorithm Using Multiple Pulse Transmission

Cited by 5 publications

References 3 publications

UWB Indoor Localization Using Deep Learning LSTM Networks

UWB Indoor Localization Using Deep Learning LSTM Networks

Performance research of real-time kinematic/5G combined positioning model

Accurate TOA-Based UWB Localization System in Coal Mine Based on WSN

Contact Info

Product

Resources

About