|
|
|
| Bispectral synergetic feature-based multi-sensor fusion navigation for AUV |
Chao WEI( ),Lingfeng CHEN,Yunong WANG,Shibo LU,Yuanxin XU*() |
| College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310058, China |
|
|
|
Abstract A bispectral synergetic network (BiSN) was proposed for dual-dimensional cooperative feature extraction in the frequency domain in order to overcome the limitation of single temporal dimension representation in characterizing navigation states and capturing sensor interaction characteristics. Time-series signals were converted to frequency domain by using the fast Fourier transform (FFT), and significant frequency components were extracted. The one-dimensional sequence was reshaped into a two-dimensional structure based on frequency and discrete period. This approach enabled the joint exploration of temporal dynamics and cross-sensor interactions. The simulation results demonstrate that the proposed method significantly improves navigation accuracy compared with state-of-the-art models. The proposed model exhibits strong performance in reconstructing missing sensor data, thereby enhancing the robustness of the navigation system.
|
|
Received: 09 November 2025
Published: 21 October 2026
|
|
|
| Fund: 浙江省自然科学基金资助项目（LMS26F010003）；国家重点研发计划资助项目（2021YFC2800101）. |
|
Corresponding Authors:
Yuanxin XU
E-mail: 22331154@zju.edu.cn;xuyx@zju.edu.cn
|
基于频域双维协同特征的AUV多传感器融合导航
为了克服单一时间维度表示对导航状态刻画和传感器交互特性捕捉不足的局限，提出基于频域双维度协同特征提取的模型(BiSN). 该模型通过快速傅里叶变换(FFT)将时域信号转换至频域，提取显著频率分量后，将一维序列重塑为频率-离散周期的二维结构，协同挖掘传感器在时间维度上的变化趋势与多传感器读数之间的关联特征. 仿真实验表明，该方法的导航精度较当前先进模型显著提升. 所提模型在传感器缺失数据填补方面表现出色，增强了导航系统的鲁棒性.
关键词：
水下自主航行器,
AUV导航,
频域,
深度学习,
数据填补
|
|
| [1] |
李洋, 赵鸣, 徐梦瑶, 等 多源信息融合技术研究综述[J]. 智能计算机与应用, 2019, 9 (5): 186- 189
Li Yang, Zhao Ming, Xu Mengyao, et al A survey of research on multi-source information fusion technology[J]. Intelligent Computer and Applications, 2019, 9 (5): 186- 189
doi: 10.3969/j.issn.2095-2163.2019.05.043
|
|
|
| [2] |
Sun Y, Li J, Xu Y, et al Deep learning versus conventional methods for missing data imputation: a review and comparative study[J]. Expert Systems with Applications, 2023, 227: 120201
doi: 10.1016/j.eswa.2023.120201
|
|
|
| [3] |
Deraz A A, Badawy O, Elhosseini M A, et al Deep learning based on LSTM model for enhanced visual odometry navigation system[J]. Ain Shams Engineering Journal, 2023, 14 (8): 102050
doi: 10.1016/j.asej.2022.102050
|
|
|
| [4] |
Zhi Z, Liu D, Liu L A performance compensation method for GPS/INS integrated navigation system based on CNN-LSTM during GPS outages[J]. Measurement, 2022, 188: 110516
doi: 10.1016/j.measurement.2021.110516
|
|
|
| [5] |
Tng Y, Jiang J, Liu J, et al A GRU and AKF-based hybrid algorithm for improving INS/GNSS navigation accuracy during GNSS outage[J]. Remote Sensing, 2022, 14 (3): 752
doi: 10.3390/rs14030752
|
|
|
| [6] |
Liu Y, Hu T, Zhang H, et al. iTransformer: inverted Transformers are effective for time series forecasting [C]//The 12th International Conference on Learning Representations, 2024: 1−25.
|
|
|
| [7] |
Liu Y, Wu H, Wang J, et al. Non-stationary Transformers: exploring the stationarity in time series forecasting [C]//Advances in Neural Information Processing Systems 35. Red Hook, NY: Curran Associates, Inc. , 2022: 9881-9893.
|
|
|
| [8] |
Nie Y, Nguyen N H, Sinthong P, et al. A time series is worth 64 words: long-term forecasting with Transformers [C]//The 11th International Conference on Learning Representations, 2023: 1−24.
|
|
|
| [9] |
Hochreiter S, Schmidhuber J Long short-term memory[J]. Neural Computation, 1997, 9 (8): 1735- 1780
doi: 10.1162/neco.1997.9.8.1735
|
|
|
| [10] |
Lai G, Chang W C, Yang Y, et al. Modeling long- and short-term temporal patterns with deep neural networks [C]//The 41st International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2018: 95-104.
|
|
|
| [11] |
Shen L, Li Z, Kwok J T. Timeseries anomaly detection using temporal hierarchical one-class network [C]//Advances in Neural Information Processing Systems 33. Red Hook, NY: Curran Associates, Inc. , 2020: 13016-13026.
|
|
|
| [12] |
Bai S, Kolter J Z, Koltun V. Convolutional sequence modeling revisited [C]//Proceedings of the 6th International Conference on Learning Representations Workshop, 2018: 1−20.
|
|
|
| [13] |
He Y, Zhao J Temporal convolutional networks for anomaly detection in time series[J]. Journal of Physics: Conference Series, 2019, 1213 (4): 042050
doi: 10.1088/1742-6596/1213/4/042050
|
|
|
| [14] |
Wu H, Hu T, Liu Y, et al. TimesNet: temporal 2D-variation modeling for general time series analysis [C]//The 11th International Conference on Learning Representations, 2023: 1−23.
|
|
|
| [15] |
Wang S, Wu H, Shi X, et al. TimeMixer: decomposable multiscale mixing for time series forecasting [C]//The 12th International Conference on Learning Representations, 2024: 1−27.
|
|
|
| [16] |
Wang Y, Wu H, Dong J, et al. TimeXer: empowering Transformers for time series forecasting with exogenous variables [C]//Advances in Neural Information Processing Systems 37. Red Hook, NY: Curran Associates, Inc. , 2024: 469-498.
|
|
|
| [17] |
Zeng A, Chen M, Zhang L, et al. Are Transformers effective for time series forecasting? [C]//Proceedings of the 37th AAAI Conference on Artificial Intelligence. Washington, DC: AAAI Press, 2023, 37(9): 11121-11128.
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
