.png){kind=icon}
.png){kind=icon}
Return
A novel method for enhanced ultra-wideband positioning accuracy in GPS-denied environments
.png){kind=icon}
PRE
AI
B
Z
M
C
B
DOI：10.1016/j.aei.2026.104767.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurate positioning constitutes a foundational prerequisite for agricultural automation. Ultra-wideband (UWB) technology is a promising localization sensor characterized by high ranging accuracy. However, conventional positioning techniques generally are subject to significant limitations in terms of reliability and precision in facilities environment where the global positioning system (GPS) signals are unavailable. Therefore, to enhance the comprehensive estimation accuracy of target node (TN), this paper presents a new positioning algorithm named BMDS-EKF, which innovatively integrates the back propagation (BP) neural network, quantum particle swarm optimization (QPSO), multi-dimensional scaling (MDS), and extended Kalman filter (EKF). Firstly, the QPSO-aided BP neural network is adopted to refine the measurement distance of UWB system, wherein the QPSO is utilized to optimize the weights and thresholds of the neural network model to enhance the predictive accuracy of the BP neural network. On this basis, the MDS method is performed to estimate the position information of the TN, and the EKF algorithm is then implemented to the result obtained from the MDS method to refine estimation accuracy. Finally, a series of relevant experiments are systematically carried out to validate the effectiveness of the designed method. The experimental results show that the designed BMDS-EKF method achieves an average positioning error of 0.127 m, and the achieved average estimation accuracies along the three coordinate axes are respectively increased by 63.8%, 36.5%, and 46.4%, when compared with the MDS algorithm. These improvements clearly demonstrate that the developed method substantially outperforms the contrasted methods in terms of positioning accuracy, and can significantly enhance the positioning accuracy of UWB system in GPS-denied environments.
Keywords:
Ultra-wideband (UWB)
Back propagation neural network
Quantum particle swarm optimization
Multi-dimensional scaling
Extended Kalman filter
Journal
IF:
9.9
Papers:
4.0K
Citations:
1.7W
Organization
Cited Papers