Autonomous underwater vehicles (AUVs) are widely used to explore ocean resources, and trajectory prediction of AUVs is crucial to the active docking method. To address these two issues, this paper proposes a novel and practical trajectory prediction method based on the principal axis with RANSAC (PARANSAC) and an adaptive fuzzy unscented Kalman filter (AFUKF). The PARANSAC is designed to process binocular camera images and point clouds and provides pose estimation of AUVs to the AFUKF, eliminating the need for additional preinstalled markers on AUVs, thus significantly reducing system complexity. The AFUKF, which can adaptively adjust the measurement noise covariance matrix, is designed to estimate the trajectory of AUVs based on the pose estimation of PARANSAC, and the multistep trajectories of AUVs are predicted on the basis of a practical method. Pool experiments are conducted and illustrate the effectiveness of the PARANSAC and AFUKF methods, further verifying the performance of the novel trajectory prediction method.
ZhengXTianQZhangQ.Development and control of an innovative underwater vehicle manipulator system. J Mar Sci Eng2023; 11(3): 548. https://www.mdpi.com/2077-1312/11/3/548
YanZGongPZhangW, et al. Autonomous underwater vehicle vision guided docking experiments based on L-shaped light array. IEEE Access2019; 7: 72567–72576. https://api.semanticscholar.org/CorpusID:182426418
10.
YanZZhangJTangJ.Whale optimization algorithm based on lateral inhibition for image matching and vision-guided AUV docking. J Intell Fuzzy Syst2021; 40(3): 4027–4038.
MillerAMillerBMillerG. AUV position estimation via acoustic seabed profile measurements. In: 2018 IEEE/OES autonomous underwater vehicle workshop (AUV) 2018 AUV, University of Porto, Porto, Portugal, IEEE, pp. 1–5.
13.
ChungDKimJ.Pose estimation considering an uncertainty model of stereo vision for in-water ship hull inspection. IFAC-PapersOnLine2018; 51(29): 400–405.
14.
TangJChenZFuB, et al. Rov6D: 6D pose estimation benchmark dataset for underwater remotely operated vehicles. IEEE Robot Autom Lett2024; 9(1): 65–72.
15.
JoshiBModasshirMMandersonT, et al. DeepURL: deep pose estimation framework for underwater relative localization. In: 2020 IEEE/RSJ International conference on intelligent robots and systems (IROS), Las Vegas, IEEE, pp. 1777–1784.
16.
XueCLiJChenK, et al. An underwater cooperative localization framework based on multiple ranging circle intersection. IEEE Trans Aerosp Electron Syst2025; 61: 18103–18126.
17.
XueCZhangHZhuF, et al. Adaptive multi-robot cooperative localization based on distributed consensus learning of unknown process noise uncertainty. IEEE Trans Autom Sci Eng2025; 22: 8738–8761.
18.
Gomes dos SantosWKugaHKRoccoEM. Application of the Kalman filter to estimate the state of an aerobraking maneuver. Math Probl Eng2013; 1–8.
19.
YoshimuraTKonishiKSoedaT.A modified extended Kalman filter for linear discrete-time systems with unknown parameters. Automatica1981; 17(4): 657–660.
20.
WenzelTABurnhamKJBlundellMV, et al. Dual extended Kalman filter for vehicle state and parameter estimation. Veh Syst Dyn2006; 44(2): 153–171.
HuangYZhangYXuB, et al. A new adaptive extended Kalman filter for cooperative localization. IEEE Trans Aerosp Electron Syst2018; 54(1): 353–368.
23.
JulierSJUhlmannJK.Unscented filtering and nonlinear estimation. Proc IEEE2004; 92(3): 401–422.
24.
ZhuTZhengH. Vehicle state estimation based on unscented Kalman state estimation. In: 2008 International symposium on computational intelligence and design, Wuhan, China, vol. 1. pp. 42–46. DOI:10.1109/ISCID.2008.27.
DasMDeyASadhuS, et al. Joint estimation of states and parameters of a reentry ballistic target using adaptive UKF. In: 2014 Fifth international symposium on electronic system design, Surathkal, Mangalore, India, pp. 99–103. DOI:10.1109/ISED.2014.28.
27.
PartovibakhshMLiuG.An adaptive unscented Kalman filtering approach for online estimation of model parameters and state-of-charge of lithium-ion batteries for autonomous mobile robots. IEEE Trans Control Syst Technol2015; 23(1): 357–363.
28.
LiuWLiuYBucknallR.A robust localization method for Unmanned Surface Vehicle (USV) navigation using fuzzy adaptive Kalman filtering. IEEE Access2019; 7: 46071–46083.
DengZLiCYinL, et al. An adaptive robust unscented Kalman filter based matching algorithm for underwater gravity aided navigation. In: 2018 IEEE CSAA guidance, navigation and control conference (CGNCC), Xiamen, China, pp. 1–8. DOI:10.1109/GNCC42960.2018.9018670.
31.
ChenLZhuYPapandreouG, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. CoRR. 2018; abs/1802.02611. http://arxiv.org/abs/1802.02611.1802.02611.
32.
YanivZ.Random sample consensus (RANSAC) algorithm, a generic implementation. The Insight Journal2010.
D’AlfonsoLLuciaWMuracaP, et al. Mobile robot localization via EKF and UKF: a comparison based on real data. Robot Auton Syst2015; 74: 122–127.
35.
AllottaBChisciLCostanziR, et al. A comparison between EKF-based and UKF-based navigation algorithms for AUVs localization. In: OCEANS, 2015, pp.1–5. Genova: IEEE.
36.
KolåsSFossBAScheiTS.Constrained nonlinear state estimation based on the UKF approach. Comput Chem Eng2009; 33(8): 1386–1401.
37.
SongQJian-DaH.An adaptive UKF algorithm for the state algorithm for the state and parameter estimations of a mobile robot. Acta Automatica Sinica2008; 34(1): 72–79.
38.
CostanziRFanelliFMeliE, et al. UKF-based navigation system for AUVs: online experimental validation. IEEE J Oceanic Eng2019; 44(3): 633–641.
39.
Garcia-GarciaAOrts-EscolanoSOpreaS, et al. A review on deep learning techniques applied to semantic segmentation. arXiv preprint arXiv:170406857.2017.
