| 198 | 0 | 166 |
| 下载次数 | 被引频次 | 阅读次数 |
为了提升全球定位系统(Global Positioning System, GPS)信号中断场景下传统滤波方法对非线性误差抑制不足的缺陷，提出了一种多模态融合的注意力机制卷积长短期记忆网络(Convolutional Long Short-Term Memory Neural Network Based on Attention Mechanism under Multi-modal Fusion, MF-ACLSTM)导航补偿方法。该模型通过卷积神经网络(Convolutional Neural Network, CNN)进行空间特征提取，结合长短期记忆神经网络(Long Short-Term Memory Neural Network, LSTM)进行时序特征建模，以有效融合惯性导航与GPS数据，并引入注意力机制，动态调整不同传感器模态对导航估计的贡献权重，提高数据融合的鲁棒性。在GPS信号中断时，通过历史惯性导航数据与模型的自回归机制，实现短期精确预测和长期误差抑制，使导航结果更精准；利用获得的实验数据对所提方法的性能进行了验证。实验结果表明，在GPS信号中断的场景下，所提方法较传统滤波方法在定位误差和长期稳定性等方面均有显著提升。
Abstract：In order to address the limitation of the traditional filtering method in suppressing nonlinear errors in the scenario of Global Positioning System(GPS) signal interruption, a Convolutional Long Short-Term Memory Neural Network Based on Attention Mechanism under Multi-modal Fusion(MF-ACLSTM) is proposed. In this model, spatial feature extraction is carried out by Convolutional Neural Network(CNN), and temporal feature modeling is carried out by combining Long Short-Term Memory Neural Network(LSTM) to effectively integrate inertial navigation and GPS data, and attention mechanism is introduced to dynamically adjust the contribution weights of different sensor modalities to navigation estimation, improving the robustness of data fusion. When the GPS signal is interrupted, the autoregressive mechanism of the model, in combination with the historical inertial navigation data, is used to achieve short-term accurate prediction and long-term error suppression, so as to make the navigation results more accurate. Finally, the experimental data obtained are used to verify the performance of the proposed method. Experimental results show that, in the scenario of GPS signal interruption, the proposed method significantly outperforms traditional filtering methods in terms of positioning error and long-term stability.
[1] CETINIC E,SHE J.Understanding and Creating Art with AI:Review and Outlook[J].ACM Transactions on Multimedia Computing,Communications,and Applications (TOMM),2022,18(2):1-22.
[2] KATTENBORN T,LEITLOFF J,SCHIEFER F,et al.Review on Convolutional Neural Networks (CNN) in Vegetation Remote Sensing[J].ISPRS Journal of Photogrammetry and Remote Sensing,2021,173:24-49.
[3] BHATT D,PATEL C,TALSANIA H,et al.CNN Variants for Computer Vision:History,Architecture,Application,Challenges and Future Scope[J].Electronics,2021,10(20):2470.
[4] LI Z W,LIU F,YANG W J,et al.A Survey of Convolutional Neural Networks:Analysis,Applications,and Prospects[J].IEEE Transactions on Neural Networks and Learning Systems,2022,33(12):6999-7019.
[5] 李灿，沈强，汪立新，等.卫星不足情况下低成本 MEMS-INS/GPS 伪松组合导航[J].北京航空航天大学学报，2021,49(4):869-878.
[6] 谢礼伟，石涛，武领华，等.基于多星座GNSS 的高轨航天器组合导航性能评估[J].无线电工程，2023,53(12):2914-2920.
[7] GIFFORD W M,DARDARI D,WIN M Z.The Impact of Multipath Information on Time-of-arrival Estimation[J].IEEE Transactions on Signal Processing,2020,70:31-46.
[8] ALAEIYAN H,MOSAVI M R,AYATOLLAHI A.Improving the Performance of GPS/INS Integration During GPS Outage with Incremental Regularized LSTM Learning[J].Alexandria Engineering Journal,2024,105:137-155.
[9] MUDDE A,BOOTH C.Gene Therapy for Inborn Error of Immunity-current Status and Future Perspectives[J].Current Opinion in Allergy and Clinical Immunology,2023,23(1):51-62.
[10] PENG N,ZHANG S Z,GUO X,et al.Online Parameters Identification and State of Charge Estimation for Lithium-Ion Batteries Using Improved Adaptive Dual Unscented Kalman Filter[J].International Journal of Energy Research,2021,45(1):975-990.
[11] 张一康，陈邁涛，刘芳.基于自适应卡尔曼滤波的 RFID / SINS 组合导航研究[J].无线电工程，2024,54(1):98-104.
[12] MA Z F,ZHANG H,LIU J.MM-RNN:A Multimodal RNN for Precipitation Nowcasting[J].IEEE Transactions on Geoscience and Remote Sensing,2023,61:1-14.
[13] YU Y,SI X S,HU C H,et al.A Review of Recurrent Neural Networks:LSTM Cells and Network Architectures[J].Neural Computation,2019,31(7):1235-1270.
[14] TOLSTIKHIN I,HOULSBY N,KOLESNIKOV A,et al.MLP-mixer:An All-MLP Architecture for Vision[C]//NIPS'21:Proceedings of the 35th International Conference on Neural Information Processing Systems.[S.l.]:Curran Associates Inc.,2021:24261-24272.
[15] LI D P,LIU Y J,TONG S C,et al.Neural Networks-based Adaptive Control for Nonlinear State Constrained Systems with Input Delay[J].IEEE Transactions on Cybernetics,2019,49(4):1249-1258.
[16] 钱伟，陈析，陈鑫，等.基于里程计/LiDAR/GNSS的室内外连续定位方法研究[J].传感技术学报，2022,35(4):523-529.
[17] ZHANG Y,QU C,WANG Y J.An Indoor Positioning Method Based on CSI by Using Features Optimization Mechanism with LSTM[J].IEEE Sensors Journal,2020,20(9):4868-4878.
[18] ALAEIYAN H,MOSAVI M R,AYATOLLAHI A.Improving the Performance of GPS/INS Integration During GPS Outage with Incremental Regularized LSTM Learning[J].Alexandria Engineering Journal,2024,105:137-155.
[19] BISWAS T,PAUL A.Effects of the Relative Dynamics of Ionospheric Irregularities and GPS Satellites on Receiver Tracking Loop Performance[J].Radio Science,2023,58(10):1-16.
[20] HU Z,ZHANG J J,GE Y.Handling Vanishing Gradient Problem Using Artificial Derivative[J].IEEE Access,2021,9:22371-22377.
[21] 孟怡悦，郭迟，刘经南.采用注意力机制和奖励塑造的深度强化学习视觉目标导航方法[J].武汉大学学报 (信息科学版),2024,49(7):1100-1108.
[22] MIDDLEHURST M,SCH?FER P,BAGNALL A.Bake Off Redux:A Review and Experimental Evaluation of Recent Time Series Classification Algorithms[J].Data Mining and Knowledge Discovery,2024,38:1958-2031.
基本信息:
中图分类号:TN967.2
引用信息:
[1]汤翔,章飞,汪勋,等.GPS中断下基于多模态融合的ACLSTM组合导航方法[J].无线电工程,2025,55(06):1274-1282.
2025-04-14
2025-04-14
2025-04-14