Snake optimizer LSTM-based UWB positioning method for unmanned crane

Li Wang; Guangxiao Fan; Qiao Wang; Hui Li; Junhai Huo; Shibo Wei; Qunfeng Niu

doi:10.1371/journal.pone.0293618

Snake optimizer LSTM-based UWB positioning method for unmanned crane

PLoS One. 2023 Nov 1;18(11):e0293618. doi: 10.1371/journal.pone.0293618. eCollection 2023.

Authors

Li Wang^{1

2

3}, Guangxiao Fan¹, Qiao Wang^{1

2

3}, Hui Li⁴, Junhai Huo⁵, Shibo Wei¹, Qunfeng Niu¹

Affiliations

¹ College of Electrical Engineering, Henan University of Technology, Zhengzhou City, Henan Province, China.
² Key Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou City, Henan Province, China.
³ Henan Key Laboratory of Grain Photoelectric Detection and Control, Henan University of Technology, Zhengzhou City, Henan Province, China.
⁴ College of Mechanical and Electrical Engineering, Henan University of Technology, Zhengzhou City, Henan Province, China.
⁵ Guizhou Aerospace Control Technology Limited Company, Guiyang City, Guizhou Province, China.

Abstract

Position determination is a critical technical challenge to be addressed in the unmanned and intelligent advancement of crane systems. Traditional positioning techniques, such as those based on magnetic grating or encoders, are limited to measuring the positions of the main carriage and trolley. However, during crane operations, accurately determining the position of the load becomes problematic when it undergoes swinging motions. To overcome this limitation, this paper proposes a novel Ultra-Wide-Band (UWB) positioning method for unmanned crane systems, leveraging the Snake Optimizer Long Short-Term Memory (SO-LSTM) framework. The objective is to achieve real-time and precise localization of the crane hook. The proposed method establishes a multi-base station and multi-tag UWB positioning system using a Time Division Multiple Access (TDMA) combined with Two-Way Ranging (TWR) scheme. This system enables the acquisition of distance measurements between the mobile tag and UWB base stations. Furthermore, the hyperparameters of the LSTM network are optimized using the Snake Optimizer algorithm to enhance the accuracy and effectiveness of UWB positioning estimation. Experimental results demonstrate that the SO-LSTM-based positioning method yields a maximum positioning error of 0.1125 meters and a root mean square error of 0.0589 meters. In comparison to conventional approaches such as the least squares method (LS) and the Kalman filter method (KF), the proposed SO-LSTM-based positioning method significantly reduces the root mean square error (RMSE) by 63.39% and 58.01%, respectively, while also decreasing the maximum positioning error (MPE) by 60.77% and 52.65%.

Copyright: © 2023 Wang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Intelligence
Memory, Long-Term
Motion
Stretchers*

Grants and funding

This work was supported by the Science and Technology Research Project of Henan Province (No. 222102220080), the Henan Provincial Science and Technology Tackling Key Issues (Joint Fund) Project (No. 222103810083), and the Science Foundation of Henan University of Technology (No. 2019BS055). The funders had no role in the study design, data collection and analysis, decision to publish, or manuscript preparation.