A Tractor Work Position Prediction Method Based on CNN-BiLSTM Under GNSS Signal Denial

In farmland environments where GNSS signals are obstructed, such as forested areas or in adverse weather conditions, traditional GNSS/INS integrated navigation systems suffer from positioning errors and instability. To address this, a model-assisted integrated navigation system is proposed, combinin...

Full description

Saved in:
Bibliographic Details
Main Authors: Yangming Hu, Liyou Xu, Xianghai Yan, Ningjie Chang, Qigang Wan, Yiwei Wu
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:World Electric Vehicle Journal
Subjects:
Online Access:https://www.mdpi.com/2032-6653/16/1/11
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832587281691574272
author Yangming Hu
Liyou Xu
Xianghai Yan
Ningjie Chang
Qigang Wan
Yiwei Wu
author_facet Yangming Hu
Liyou Xu
Xianghai Yan
Ningjie Chang
Qigang Wan
Yiwei Wu
author_sort Yangming Hu
collection DOAJ
description In farmland environments where GNSS signals are obstructed, such as forested areas or in adverse weather conditions, traditional GNSS/INS integrated navigation systems suffer from positioning errors and instability. To address this, a model-assisted integrated navigation system is proposed, combining Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) networks. The CNN-BiLSTM model is trained under normal GNSS conditions and used to predict positioning when GNSS signals are interrupted, effectively replacing GNSS to ensure stable and accurate navigation. Experimental validation is conducted using field data from tractor simulations. The results show that, during a 100-s GNSS denial, the CNN-BiLSTM model reduces the average position error by 79.3% compared to pure inertial navigation and by 5.4% compared to traditional LSTM. In a 30-s GNSS denial, the average position error is reduced by 41% compared to inertial navigation and 6.2% compared to LSTM. The model maintains positioning accuracy within 3% of the GNSS/INS output under normal conditions, demonstrating its feasibility and effectiveness. This approach offers a promising solution for autonomous tractor navigation in GNSS-denied agricultural environments, contributing to precision agriculture.
format Article
id doaj-art-509bacf5a82c41afae06e81ea5788333
institution Kabale University
issn 2032-6653
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series World Electric Vehicle Journal
spelling doaj-art-509bacf5a82c41afae06e81ea57883332025-01-24T13:52:45ZengMDPI AGWorld Electric Vehicle Journal2032-66532024-12-011611110.3390/wevj16010011A Tractor Work Position Prediction Method Based on CNN-BiLSTM Under GNSS Signal DenialYangming Hu0Liyou Xu1Xianghai Yan2Ningjie Chang3Qigang Wan4Yiwei Wu5College of Vehicle and Traffic Engineering, Henan University of Science and Technology, Luoyang 471003, ChinaCollege of Vehicle and Traffic Engineering, Henan University of Science and Technology, Luoyang 471003, ChinaCollege of Vehicle and Traffic Engineering, Henan University of Science and Technology, Luoyang 471003, ChinaCollege of Vehicle and Traffic Engineering, Henan University of Science and Technology, Luoyang 471003, ChinaCollege of Vehicle and Traffic Engineering, Henan University of Science and Technology, Luoyang 471003, ChinaCollege of Vehicle and Traffic Engineering, Henan University of Science and Technology, Luoyang 471003, ChinaIn farmland environments where GNSS signals are obstructed, such as forested areas or in adverse weather conditions, traditional GNSS/INS integrated navigation systems suffer from positioning errors and instability. To address this, a model-assisted integrated navigation system is proposed, combining Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) networks. The CNN-BiLSTM model is trained under normal GNSS conditions and used to predict positioning when GNSS signals are interrupted, effectively replacing GNSS to ensure stable and accurate navigation. Experimental validation is conducted using field data from tractor simulations. The results show that, during a 100-s GNSS denial, the CNN-BiLSTM model reduces the average position error by 79.3% compared to pure inertial navigation and by 5.4% compared to traditional LSTM. In a 30-s GNSS denial, the average position error is reduced by 41% compared to inertial navigation and 6.2% compared to LSTM. The model maintains positioning accuracy within 3% of the GNSS/INS output under normal conditions, demonstrating its feasibility and effectiveness. This approach offers a promising solution for autonomous tractor navigation in GNSS-denied agricultural environments, contributing to precision agriculture.https://www.mdpi.com/2032-6653/16/1/11autonomous electric tractorintegrated navigationGNSS signal denialneural network modelextended Kalman filterconvolutional neural network
spellingShingle Yangming Hu
Liyou Xu
Xianghai Yan
Ningjie Chang
Qigang Wan
Yiwei Wu
A Tractor Work Position Prediction Method Based on CNN-BiLSTM Under GNSS Signal Denial
World Electric Vehicle Journal
autonomous electric tractor
integrated navigation
GNSS signal denial
neural network model
extended Kalman filter
convolutional neural network
title A Tractor Work Position Prediction Method Based on CNN-BiLSTM Under GNSS Signal Denial
title_full A Tractor Work Position Prediction Method Based on CNN-BiLSTM Under GNSS Signal Denial
title_fullStr A Tractor Work Position Prediction Method Based on CNN-BiLSTM Under GNSS Signal Denial
title_full_unstemmed A Tractor Work Position Prediction Method Based on CNN-BiLSTM Under GNSS Signal Denial
title_short A Tractor Work Position Prediction Method Based on CNN-BiLSTM Under GNSS Signal Denial
title_sort tractor work position prediction method based on cnn bilstm under gnss signal denial
topic autonomous electric tractor
integrated navigation
GNSS signal denial
neural network model
extended Kalman filter
convolutional neural network
url https://www.mdpi.com/2032-6653/16/1/11
work_keys_str_mv AT yangminghu atractorworkpositionpredictionmethodbasedoncnnbilstmundergnsssignaldenial
AT liyouxu atractorworkpositionpredictionmethodbasedoncnnbilstmundergnsssignaldenial
AT xianghaiyan atractorworkpositionpredictionmethodbasedoncnnbilstmundergnsssignaldenial
AT ningjiechang atractorworkpositionpredictionmethodbasedoncnnbilstmundergnsssignaldenial
AT qigangwan atractorworkpositionpredictionmethodbasedoncnnbilstmundergnsssignaldenial
AT yiweiwu atractorworkpositionpredictionmethodbasedoncnnbilstmundergnsssignaldenial
AT yangminghu tractorworkpositionpredictionmethodbasedoncnnbilstmundergnsssignaldenial
AT liyouxu tractorworkpositionpredictionmethodbasedoncnnbilstmundergnsssignaldenial
AT xianghaiyan tractorworkpositionpredictionmethodbasedoncnnbilstmundergnsssignaldenial
AT ningjiechang tractorworkpositionpredictionmethodbasedoncnnbilstmundergnsssignaldenial
AT qigangwan tractorworkpositionpredictionmethodbasedoncnnbilstmundergnsssignaldenial
AT yiweiwu tractorworkpositionpredictionmethodbasedoncnnbilstmundergnsssignaldenial