Integration of Deep Sequence Learning-Based Virtual GPS Model and EKF for AUV Navigation

被引:2
|
作者
Lv, Peng-Fei [1 ]
Lv, Jun-Yi [2 ]
Hong, Zhi-Chao [1 ,3 ]
Xu, Li-Xin [1 ,3 ]
机构
[1] Jiangsu Univ Sci & Technol, Ocean Coll, Zhenjiang 212003, Peoples R China
[2] Univ Elect Sci & Technol China, Shenzhen Inst Adv Study, Shenzhen 518110, Peoples R China
[3] Jiangsu Marine Technol Innovat Ctr, Nantong 226199, Peoples R China
关键词
autonomous underwater vehicle; underwater navigation; virtual GPS model; deep sequence learning; extended Kalman filter; SYSTEM; DESIGN;
D O I
10.3390/drones8090441
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
To address the issue of increasing navigation errors in low-cost autonomous underwater vehicles (AUVs) operating without assisted positioning underwater, this paper proposes a Virtual GPS Model (VGPSM) based on deep sequence learning. This model is integrated with an Extended Kalman Filter (EKF) to provide a high-precision navigation solution for AUVs. The VGPSM leverages the time-series characteristics of data from sensors such as the Attitude and Heading Reference System (AHRS) and the Doppler Velocity Log (DVL) while the AUV is on the surface. It learns the relationship between these sensor data and GPS data by utilizing a hybrid model of Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (Bi-LSTM), which are well-suited for processing and predicting time-series data. This approach constructs a virtual GPS model that generates virtual GPS displacements updated at the same frequency as the real GPS data. When the AUV navigates underwater, the virtual GPS displacements generated using the VGPSM in real-time are used as measurements to assist the EKF in state estimation, thereby enhancing the accuracy and robustness of underwater navigation. The effectiveness of the proposed method is validated through a series of experiments under various conditions. The experimental results demonstrate that the proposed method significantly reduces cumulative errors, with navigation accuracy improvements ranging from 29.2% to 69.56% compared to the standard EKF, indicating strong adaptability and robustness.
引用
收藏
页数:23
相关论文
共 50 条
  • [21] IACPPO: A deep reinforcement learning-based model for warehouse inventory replenishment
    Tian, Ran
    Lu, Meng
    Wang, Haopeng
    Wang, Bo
    Tang, Qingxia
    COMPUTERS & INDUSTRIAL ENGINEERING, 2024, 187
  • [22] GNSS/INS Integration Based on Machine Learning LightGBM Model for Vehicle Navigation
    Li, Bangxin
    Chen, Guangwu
    Si, Yongbo
    Zhou, Xin
    Li, Pengpeng
    Li, Peng
    Fadiji, Tobi
    APPLIED SCIENCES-BASEL, 2022, 12 (11):
  • [23] Underwater navigation methodology based on intelligent velocity model for standard AUV
    Lv, Peng-Fei
    He, Bo
    Guo, Jia
    Shen, Yue
    Yan, Tian-Hong
    Sha, Qi-Xin
    OCEAN ENGINEERING, 2020, 202 (202)
  • [24] Position Correction Model Based on Gated Hybrid RNN for AUV Navigation
    Lv, Peng-Fei
    He, Bo
    Guo, Jia
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2021, 70 (06) : 5648 - 5657
  • [25] An Enhanced Error Model for EKF-Based Tightly-Coupled Integration of GPS and Land Vehicle's Motion Sensors
    Karamat, Tashfeen B.
    Atia, Mohamed M.
    Noureldin, Aboelmagd
    SENSORS, 2015, 15 (09) : 24269 - 24296
  • [26] Deep Learning-Based Signal Quality Assessment for Wearable ECGs
    Zhang, Xiangyu
    Li, Jianqing
    Cal, Zhipeng
    Zhao, Line
    Liu, Chengyu
    IEEE INSTRUMENTATION & MEASUREMENT MAGAZINE, 2022, 25 (05) : 41 - 52
  • [27] A Customized EKF model for GNSS-based Navigation in the Harsh Space Environment
    Vouch, Oliviero
    Nardin, Andrea
    Minetto, Alex
    Valvano, Matteo
    Zocca, Simone
    Dovis, Fabio
    2023 IEEE INTERNATIONAL CONFERENCE ON WIRELESS FOR SPACE AND EXTREME ENVIRONMENTS, WISEE, 2023, : 13 - 18
  • [28] Deep Reinforcement Learning-Based Collision-Free Navigation for Magnetic Helical Microrobots in Dynamic Environments
    Wang, Huaping
    Qiu, Yukang
    Hou, Yaozhen
    Shi, Qing
    Huang, Hen-Wei
    Huang, Qiang
    Fukuda, Toshio
    IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2024,
  • [29] Deep learning-based encryption scheme for medical images using DCGAN and virtual planet domain
    Kumar, Manish
    Chivukula, Aneesh Sreevallabh
    Barua, Gunjan
    SCIENTIFIC REPORTS, 2025, 15 (01):
  • [30] Expanding the sequence spaces of synthetic binding protein using deep learning-based framework ProteinMPNN
    Li, Yanlin
    Jiao, Wantong
    Liu, Ruihan
    Deng, Xuejin
    Zhu, Feng
    Xue, Weiwei
    FRONTIERS OF COMPUTER SCIENCE, 2025, 19 (05)