UWB Positioning in Complex Environments: A Soft Computing-Based Error Estimation Method
- 3 June 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 8509817
Abstract
In complex measurement environments, Ultra-Wideband (UWB) positioning systems often face significant measurement uncertainties and reduced accuracy due to multipath propagation and Non-Line-of-Sight (NLOS) interference. This paper proposes a soft-computing-based UWB measurement correction framework—the Adaptive Noise Wavelet Packet Network (ANWP-Net)—to improve the accuracy of dynamic positioning in complex environments. First, a heuristic-based Noise Adaptive Wavelet Packet Transform (NA-WPT) module is introduced for signal preprocessing, aiming to suppress non-stationary noise and improve the integrity of ranging observations. Second, a Deep Bidirectional Long Short-Term Memory (D-BILSTM) module is employed to model nonlinear ranging errors with temporal correlations and to estimate ranging correction values for each anchor based on conditional sequence measurement results. Subsequently, the corrected distances are combined with the known anchor coordinates, and a standard least-squares multilateration solver is used to recover the final target position. Experimental results show that, compared to baseline methods, the proposed ANWP-Net reduces the average localization error by 52.2% in simulation experiments, and by 38.4% and 81.8% in indoor and outdoor physical experiments, respectively.Keywords
Funding Information
- National Key Laboratory of Inertial Measurement
- National Natural Science Foundation of China Basic Science Center Program (62388101)
- Laboratory Open Fund (2025-KFJJ-IM-08)
- Open Fund of Key Laboratory of Technology and Equipment of Tianjin Urban Air Transportation System (TJKL-UAM-202305)
- Open Fund of State key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instrument, North University of China (2023-SYSJJ-04)
- Aeronautical Science Foundation of China (20240055054001)
- Open Fund of Key Laboratory of Spatio-temporal Sensing and Intelligent Processing, Ministry of Natural Resources of the People’s Republic of China (232203)
- Open Fund of Key Laboratory of Civil Aviation Flights Wide Area Surveillance and Safety Control technology of Civil Aviation University of China (202105)
- Applied Basic Research Program of Liaoning Province (2025JH2/101300011)
- General Program of Liaoning Province Education Department (20250054)
- General Program of Liaoning Province Education Department (310125011)
This publication has 48 references indexed in Scilit:
- AdaWaveNet: Adaptive wavelet network for non-stationary time series forecasting via end-to-end learningJournal of King Saud University Computer and Information Sciences, 2026
- UWB indoor localization method based on neural network multi-classification for NLOS distance correctionSensors and Actuators A: Physical, 2024
- Application of a long short-term memory neural network algorithm fused with Kalman filter in UWB indoor positioningScientific Reports, 2024
- NLOS identification using parallel deep learning model and time-frequency information in UWB-based positioning systemMeasurement, 2022
- A novel method for UWB weak signal detection based on stochastic resonance and wavelet transformChinese Journal of Physics, 2022
- A UWB-Based Indoor Positioning System Employing Neural NetworksJournal of Geovisualization and Spatial Analysis, 2020
- A new multipath mitigation method based on adaptive thresholding wavelet denoising and double reference shift strategyGPS Solutions, 2018
- An UWB ranging method based on wavelet packet decompositionNeurocomputing, 2017
- Wavelet packets based denoising method for measurement domain repeat-time multipath filtering in GPS static high-precision positioningGPS Solutions, 2016
- Noise suppression and signal compression using the wavelet packet transformChemometrics and Intelligent Laboratory Systems, 1997