针对存在未知动态和时变扰动的欠驱动自主水下航行器（Autonomous Underwater Vehicle，AUV）设计了一种复合学习跟踪控制方案。采用视线跟踪控制处理AUV的欠驱动，用自适应神经网络近似AUV的未知动态，通过建立串行-并行估计模型来获得预测误差。利用预测误差和跟踪误差设计复合权重更新法，构建了基于复合学习控制的非线性扰动观测器估计时变扰动。通过Lyapunov方法的稳定性分析表明，AUV轨迹跟踪闭环控制系统的所有误差信号都最终一致有界。仿真结果验证了所提出的复合学习跟踪控制方案的有效性和优越性。
In this paper, a composite learning tracking control scheme is designed for an underactuated autonomous underwater vehicle (AUV) in the presence of unknown dynamics and time-varying disturbance. Line-of-sight tracking control is used to handle the underactuated of the AUV. Approximating the unknown dynamics of the AUV with an adaptive neural network. Prediction error is obtained by modeling serial-parallel estimation. The prediction error and tracking error are utilized to design the composite weight update law. A nonlinear disturbance observer based on composite learning control is constructed to estimate time-varying disturbances. The stability analysis by Lyapunov method shows that all signals of the AUV trajectory tracking closed-loop control system have uniformly ultimately boundedness. The simulation results verify the effectiveness and superiority of the proposed composite learning tracking control scheme.
2026,48(6): 125-131 收稿日期：2025-5-6
DOI：10.3404/j.issn.1672-7649.2026.06.017
分类号：U675.5
作者简介：张宇飞(1997-),男,硕士,研究方向为自主水下航行器的运动控制
参考文献：
[1] DING W, ZHANG L, ZHANG G, et al. Research on 3D trajectory tracking of underactuated AUV under strong disturbance environment[J]. Computers and Electrical Engineering, 2023, 111: 108924.
[2] LI D, DU L. AUV trajectory tracking models and control strategies: a review[J]. Journal of Marine Science and Engineering, 2021, 9(9): 1020.
[3] MOKHTARI M, TAGHIZADEH M, MAZARE M. Adaptive model-free fault-tolerant control for autonomous underwater vehicles subject to actuator failure[J]. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2024, 46(6): 330.
[4] LAKHEKAR G V, WAGHMARE L M. Robust self-organising fuzzy sliding mode-based path-following control for autonomous underwater vehicles[J]. Journal of Marine Engineering & Technology, 2023, 22(3): 131-152.
[5] CHEN B, HU J, ZHAO Y, et al. Finite-time observer based tracking control of uncertain heterogeneous underwater vehicles using adaptive sliding mode approach[J]. Neurocomputing, 2022, 481: 322-332.
[6] ZHANG G, CHU S, ZHANG W, et al. Adaptive neural fault-tolerant control for USV with the output-based triggering approach[J]. IEEE Transactions on Vehicular Technology, 2022, 71(7): 6948-6957.
[7] PHAM NGUYEN NHUT Thanh, NGO AN THUYEN, HO PHAM HUY ANH. Adaptive fuzzy 3-D trajectory tracking control for autonomous underwater vehicle (AUV) using modified integral barrier lyapunov function[J]. Ocean Engineering, 2023, 283: 115027.
[8] KHOSHNAM SHOJAEI. Neural network feedback linearization target tracking control of underactuated autonomous underwater vehicles with a guaranteed performance[J]. Ocean Engineering, 2022, 258: 111827.
[9] QIN J, DU J. Robust adaptive asymptotic trajectory tracking control for underactuated surface vessels subject to unknown dynamics and input saturation[J]. Journal of Marine Science and Technology, 2022, 27(1): 307-319.
[10] SHOJAEI K, DOLATSHAHI M. Line-of-sight target tracking control of underactuated autonomous underwater vehicles[J]. Ocean Engineering, 2017, 133: 244-252.
[11] WANG J, WANG C, WEI Y, et al. Command filter based adaptive neural trajectory tracking control of an underactuated underwater vehicle in three-dimensional space[J]. Ocean Engineering, 2019, 180: 175-186.
[12] GONG H, ER M J, LIU T, et al. Three-dimensional optimal trajectory tracking control of underactuated autonomous underwater vehicles using double closed-loop control[C]//5th International Conference on Intelligent Autonomous Systems (ICoIAS). 2022: 316-321.
[13] PATRE P M, BHASIN S, WILCOX Z D, et al. Composite adaptation for neural network-based controllers[J]. IEEE Transactions on Automatic Control, 2010, 55(4): 944-950.
[14] PAN Y, SUN T, YU H. Composite adaptive dynamic surface control using online recorded data[J]. International Journal of Robust and Nonlinear Control, 2016, 26(18): 3921-3936.
[15] YANG Y, CHEN D, LIU Q, et al. Predictor-based neural dynamic surface control of a nontriangular system with unknown disturbances[J]. IEEE Transactions on Circuits and Systems I: Regular Papers, 2022, 69(8): 3353-3365.
[16] YUCELEN T, HADDAD W M. Low-frequency learning and fast adaptation in model reference adaptive control for safety-critical systems[C]//American Control Conference, 2013: 5116–5121.
[17] GOEL R, ROY S B. Closed-loop reference model based distributed model reference adaptive control for multi-agent systems[C]// American Control Conference (ACC), 2021: 1082-1087.
[18] YANG Y, LIU Q, YUE D, et al. Predictor-based neural dynamic surface control for strict-feedback nonlinear systems with unknown control gains[J]. IEEE Transactions on Cybernetics, 2023, 53(7): 4677-4690.
[19] ZHANG J X, CHAI T. Singularity-free continuous adaptive control of uncertain underactuated surface vessels with prescribed performance[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2022, 52(9): 5646-5655.
[20] LIANG X, QU X, WANG N, et al. Three-dimensional trajectory tracking of an underactuated AUV based on fuzzy dynamic surface control[J]. IET Intelligent Transport Systems, 2020, 14(5): 364-370.
