As a crucial force in marine scientific research, the underwater gliding unmanned system must perform tasks with high accuracy and efficiency. Due to the influence of rocket fuel, underwater gliders exhibit rapid response times, making it challenging to control their future attitude based solely on their current state. Therefore, accurate trajectory prediction is essential for ensuring effective and reliable control of the system. However, the complex underwater environment presents significant challenges for traditional dynamic model-based methods in accurately predicting the future trajectory of underwater gliders. Moreover, conventional prediction models struggle to maintain accuracy in the final stages of the trajectory, particularly in high-dynamic scenarios where fuel depletion leads to a rapid decline in speed. To address these issues, this paper proposes a Maformer(Marine-Informer) model for trajectory prediction in underwater gliding unmanned systems. Building upon the traditional Informer model, Maformer integrates velocity feature encoding and replaces the original convolutional layer with dilated convolution. Experimental results demonstrate that, compared to the traditional Informer model, Maformer achieves an average reduction of 52.82% in prediction error. The findings of this study offer a promising solution for trajectory prediction of multi-feature unmanned systems operating in high-speed, dynamically changing environments.
LiuYSunYLiB, et al. Experimental analysis of deep-sea AUV based on multi-sensor integrated navigation and positioning. Remote Sens2024; 16(1): 199.
2.
ZhangJLiuMZhangS, et al. AUV path planning based on differential evolution with environment prediction. J Intell Robot Syst2022; 104(2): 23.
3.
Nordfeldt-FiolBMBonin-FontFOliverG.Evolving real-time stereo odometry for auv navigation in challenging marine environments. J Intell Robot Syst2023; 108(4): 83.
4.
XuCXuCXingW, et al. Guided trajectory filtering for challenging long-range AUV navigation. IEEE Trans Instrum Meas2023; 72: 1–10.
5.
GuoJLiDHeB.Intelligent collaborative navigation and control for AUV tracking. IEEE Trans Ind Inform2021; 17(3): 1732–1741.
6.
CuiJFengDLiY, et al. Research on simultaneous localization and mapping for AUV by an improved method: variance reduction FastSLAM with simulated annealing. Def Technol2020; 16(3): 651–661.
7.
MengXSunBZhuD.Harbour protection: moving invasion target interception for multi-AUV based on prediction planning interception method. Ocean Eng2021; 219: 108268.
8.
LiCLiuZLinS, et al. Intention-convolution and hybrid-attention network for vehicle trajectory prediction. Expert Syst Appl2024; 236: 121412.
9.
YangMZhangBWangT, et al. Vehicle interactive dynamic graph neural network-based trajectory prediction for internet of vehiclesIEEE Internet Things J2024; 11: 35777–35790.
10.
LiRZhongZChaiJ, et al. Autonomous vehicle trajectory combined prediction model based on CC-LSTM. Int J Fuzzy Syst2022; 24(8): 3798–3811.
11.
ZangHGaoCHuY, et al. Trajectory prediction algorithm of ballistic missile driven by data and knowledge. Def Technol2025; 48: 187–203.
12.
ChengDGuXQianC, et al. Vehicle trajectory prediction with interaction regions and spatial–temporal attention. IEEE Access2023; 11: 130850–130859.
13.
QinYGuanYLYuenC.Spatiotemporal capsule neural network for vehicle trajectory prediction. IEEE Trans Vehicular Technol2023; 72(8): 9746–9756.
14.
JuanNPValdecantosVN.Review of the application of artificial neural networks in ocean engineering. Ocean Eng2022; 259: 111947.
15.
WangYLiCWangX.A multi-source information fusion layer counting method for penetration fuze based on TCN-LSTM. Def Technol2024; 33: 463–474.
16.
FujiiRVongkulbhisalJHachiumaR, et al. A two-block RNN-based trajectory prediction from incomplete trajectory. IEEE Access2021; 9: 56140–56151.
17.
GuanLShiJWangD, et al. A trajectory prediction method based on bayonet importance encoding and bidirectional lstm. Expert Syst Appl2023; 223: 119888.
18.
ZhaoJYanZZhouZ, et al. A ship trajectory prediction method based on GAT and LSTM. Ocean Eng2023; 289: 116159.
19.
ShiriFMPerumalTMustaphaN, et al. A comprehensive overview and comparative analysis on deep learning models: CNN, RNN, LSTM, GRU. arXiv preprint, arXiv:2305.17473, 2023.
20.
ZhuMDuS SWangX, et al. Transfollower: Long-sequence car-following trajectory prediction through transformer. arXiv preprint, arXiv:2202.03183, 2022.
21.
ChenWWangFSunH. S2TNet: Spatio-temporal transformer networks for trajectory prediction in autonomous driving. In: Asian conference on machine learning, 2021, pp. 454–469. PMLR.
22.
TongQHuJChenY, et al. Long-term trajectory prediction model based on transformer. IEEE Access2023; 11: 143695–143703.
23.
FengAQiuRWangJ, et al. Multimodal forward generation transformer network for inconspicuous pedestrian trajectory prediction. IEEE Robot Autom Lett2024; 9: 2224–2231.
24.
WangLWangXDongC, et al. Wave predictor models for medium and long term based on dual attention-enhanced transformer. Ocean Eng2024; 310: 118761.
25.
HouLLiSEYangB, et al. Structural transformer improves speed-accuracy trade-off in interactive trajectory prediction of multiple surrounding vehicles. IEEE Trans Intell Transp Syst2022; 23(12): 24778–24790.
26.
ZhouHZhangSPengJ, et al. Informer: beyond efficient transformer for long sequence time-series forecasting. Proc AAAI Conf Artif Intell2021; 35(12): 11106–11115.
27.
HeZHeZLiS, et al. A ship navigation risk online prediction model based on informer network using multi-source data. Ocean Eng2024; 298: 117007.
28.
XueHWangSXiaM, et al. G-Trans: A hierarchical approach to vessel trajectory prediction with GRU-based transformer. Ocean Eng2024; 300: 117431.
29.
WangSLiYXingH, et al. Vessel trajectory prediction based on spatio-temporal graph convolutional network for complex and crowded sea areas. Ocean Eng2024; 298: 117232.
30.
ZhangXLiuJGongP, et al. Trajectory prediction of seagoing ships in dynamic traffic scenes via a gated spatio-temporal graph aggregation network. Ocean Eng2023; 287: 115886.
31.
HongLWangXZhangDS.CFD-based hydrodynamic performance investigation of autonomous underwater vehicles: A survey. Ocean Eng2024; 305: 117911.
32.
BaoHZhuH.Modeling and trajectory tracking model predictive control novel method of AUV based on CFD data. Sensors2022; 22(11): 4234.
33.
ArunaMV.Mathematical modeling and stability analysis of an effective design of biomimetic AUV. J Intell Robot Syst2022; 106(4): 75.
34.
LongTYeNZhangB, et al. Entire aerial-aquatic trajectory modeling and optimization for trans-medium vehicles. Def Technol2025; 49: 223–241.
35.
KangSYuJZhangJ, et al. Research on the trajectory prediction of a twin screw AUV based on an accurate dynamic model. In: 2021 6th International conference on automation, control and robotics engineering (CACRE), 2021, pp. 567–572. IEEE.
36.
YaoJYangJZhangC, et al. Autonomous underwater vehicle trajectory prediction with the nonlinear Kepler optimization algorithm–bidirectional long short-term memory–time-variable attention model. J Mar Sci Eng2024; 12(7): 1115.
37.
LiJLiW. AUV 3D trajectory prediction based on CNN-LSTM. In: 2022 IEEE International Conference on Mechatronics and Automation (ICMA), 2022, pp. 1227–1232. IEEE.
38.
QiuBWangMLiH, et al. Development of hybrid neural network and current forecasting model based dead reckoning method for accurate prediction of underwater glider position. Ocean Eng2023; 285: 115486.
39.
ZhangDWangCShenY, et al. Dynamic modeling and motion prediction of two projectiles launched successively underwater. Ocean Eng2024; 292: 116551.
40.
FernandezRASMilosevicZDominguezS, et al. Design, modeling and control of a spherical autonomous underwater vehicle for mine exploration. In: 2018 IEEE/RSJ international conference on intelligent robots and systems (IROS), 2018, pp. 1513–1519. IEEE.
41.
LiZChenYZuoX, et al. Hydrodynamic performance analysis and diving trajectory prediction of a novel deep-sea lander with flapping hydrofoils. Ocean Eng2024; 310: 118664.
42.
ZhengQSaponaraSTianX, et al. A real-time constellation image classification method of wireless communication signals based on the lightweight network MobileViT. Cogn Neurodyn2024; 18(2): 659–671.
43.
ZhengQTianXYuZ, et al. MobileRaT: a lightweight radio transformer method for automatic modulation classification in drone communication systems. Drones2023; 7(10): 596.
44.
ZhengQTianXYuL, et al. Recent advances in automatic modulation classification technology: methods, results, and prospects. Int J Intell Syst2025; 2025(1): 4067323.
