Prescribed-Performance Heading Control for Unmanned Surface Vessels via Fixed-Time Recursive Design and SAC-Based Residual Compensation
Keywords:
Unmanned surface vessel, heading tracking, prescribed-performance control, fixed-time recursive design, reinforcement learning, residual disturbance compensationAbstract
This paper proposes a prescribed-performance fixed-time recursive control framework with Soft Actor-Critic (SAC) residual compensation for unmanned surface vessel heading tracking under model uncertainties, external disturbances, and actuator saturation. A prescribed performance error transformation is adopted to strictly constrain tracking errors within predefined transient and steady-state bounds. Combined with a double-power recursive control law, fixed-time error convergence independent of initial conditions is guaranteed. A bounded lightweight SAC module is further embedded to compensate for lumped uncertainties without exact disturbance reconstruction, improving tracking performance while retaining the inherent stability of the model-based control scheme. Lyapunov analysis verifies the bounded closed-loop signal behavior, guaranteed prescribed performance, and fixed-time convergence. Comparative simulations confirm that the proposed method delivers higher tracking accuracy, smoother control responses, and stronger robustness than existing baseline and learning-based compensation strategies.
References
[1] Tipsuwan Y, Sanposh P, Techajaroonjit N. Overview and control strategies of autonomous sailboats-a survey. Ocean Engineering 2023; 281: 114879.
https://doi.org/10.1016/j.oceaneng.2023.114879
[2] Xiao L, Jouffroy J. Modeling and nonlinear heading control of sailing yachts. IEEE Journal of Oceanic Engineering 2014; 39(2): 256-268.
https://doi.org/10.1109/JOE.2013.2247276
[3] Wen G, Ge SS, Chen CLP, Tu F, Wang S. Adaptive tracking control of surface vessel using optimized backstepping technique. IEEE Transactions on Cybernetics 2019; 49(9): 3420-3431.
https://doi.org/10.1109/TCYB.2018.2844177
[4] Song B, Fan Y, Mu D, Wang G, Liu P, Wang Y. Global fixed-time path-following control with prescribed performance for an unmanned surface vehicle under lumped uncertainties and input saturation: Simulations and experiments. Ocean Engineering 2026; 351: 124024.
https://doi.org/10.1016/j.oceaneng.2025.124024
[5] Deng Y, Zhang X, Zhang G. Line-of-sight-based guidance and adaptive neural path-following control for sailboats. IEEE Journal of Oceanic Engineering 2020; 45(4).
https://doi.org/10.1109/JOE.2019.2923502
[6] Wang Y, Cao J, Sun J, Zou X, Sun C. Path following control for unmanned surface vehicles: A reinforcement learning-based method with experimental validation. IEEE Transactions on Neural Networks and Learning Systems 2024; 35(12): 18237-18250.
https://doi.org/10.1109/TNNLS.2023.3313312
[7] Zhang Z, Liu M, Zhou J, Zheng R, Wei P. Hierarchical motion control framework based on slm-guided and learning-enhanced nmpc for autonomous underwater vehicles. Expert Systems with Applications 2026; 303: 130665.
https://doi.org/10.1016/j.eswa.2025.130665
[8] Santos D, Silva Junior AG, Negreiros A, Vilas Boas J, Alvarez J, Araujo A, Aroca RV, Goncalves LMG. Design and implementation of a control system for a sailboat robot. Robotics 2016; 5(1): 5.
https://doi.org/10.3390/robotics5010005
[9] Cruz NA, Alves JC. Auto-heading controller for an autonomous sailboat, in: Oceans'10 IEEE Sydney 2010; pp. 1-6.
https://doi.org/10.1109/OCEANSSYD.2010.5603882
[10] Stelzer R, Proll T, John RI. Fuzzy logic control system for autonomous sailboats. in: 2007 IEEE International Fuzzy Systems Conference 2007; pp. 1-6.
https://doi.org/10.1109/FUZZY.2007.4295347
[11] Deng Y, Zhang X, Zhang Q, Hu Y. Event-triggered composite adaptive fuzzy control of sailboat with heeling constraint. Ocean Engineering 2020; 211: 107627.
https://doi.org/10.1016/j.oceaneng.2020.107627
[12] Xiao L, Jouffroy J. Modeling and nonlinear heading control of sailing yachts. IEEE Journal of Oceanic Engineering 2014; 39(2): 256-268.
https://doi.org/10.1109/JOE.2013.2247276
[13] Deng Y, Zhang Z, Gong M, Ni T. Event-triggered asymptotic tracking control of underactuated ships with prescribed performance, IEEE Transactions on Intelligent Transportation Systems 2023; 24(1): 645-656.
https://doi.org/10.1109/TITS.2022.3216808
[14] Cao L, Qin Y, Pan Y, Liang H. Prescribed performance-based optimal formation control for usvs with position constraints and yaw angle time-varying partial constraints. IEEE Transactions on Intelligent Transportation Systems 2025; 26(3): 4109-4121.
https://doi.org/10.1109/TITS.2024.3520328
[15] Cao L, Cen Y, Li T, Liang H, Pan Y, Optimal fixed-time control for human-in-the-loop multiagent systems with actuator faults. IEEE Transactions on Cybernetics 2026; 56(3): 1773-1784.
https://doi.org/10.1109/TCYB.2025.3632473
[16] Yang W, Wang Q-G, Liu J, Yu J. Actor-critic-based predefined-time fuzzy adaptive optimal control for uncertain nonlinear systems with input saturation. IEEE Transactions on Fuzzy Systems 2024; 32(4): 2448- 2457.
https://doi.org/10.1109/TFUZZ.2024.3355129
[17] Zhang C, Guo G. Prescribed performance fault-tolerant control of nonlinear systems via actuator switching. IEEE Transactions On Fuzzy Systems 2024; 32(3): 1013-1022.
https://doi.org/10.1109/TFUZZ.2023.3317017
[18] Wen G, Hao W, Feng W, Gao K. Optimized backstepping tracking control using reinforcement learning for quadrotor unmanned aerial vehicle system. IEEE Transactions on Systems, Man, and Cybernetics: Systems 2022; 52(8): 5004-5015.
https://doi.org/10.1109/TSMC.2021.3112688
[19] Liu J, Xiao C, Yuan H, Li C, Li Q. Unmanned surface vessels path following control using improved transferring reinforcement learning: Simulation and experiment. Ocean Engineering 2025; 320: 120346.
https://doi.org/10.1016/j.oceaneng.2025.120346
[20] Woo J, Yu C, Kim N. Deep reinforcement learning-based controller for path following of an unmanned surface vehicle. Ocean Engineering 2019; 183: 155-166.
https://doi.org/10.1016/j.oceaneng.2019.04.099
[21] Zhong W, Li H, Meng Y, Yang X, Feng Y, Ye H, Liu W. Usv path following controller based on ddpg with composite state-space and dynamic reward function. Ocean Engineering 2022; 266: 112449.
https://doi.org/10.1016/j.oceaneng.2022.112449
[22] Peng Z, Liu E, Pan C, Wang H, Wang D, Liu L. Model-based deep reinforcement learning for data-driven motion control of an under-actuated unmanned surface vehicle: Path following and trajectory tracking. Journal of the Franklin Institute 2023; 360(6): 4399-4426.
https://doi.org/10.1016/j.jfranklin.2022.10.020
[23] Yoo B, Kim J. Path optimization for marine vehicles in ocean currents using reinforcement learning. Journal of Marine Science and Technology (Japan) 2016; 21(2): 334-343.
https://doi.org/10.1007/s00773-015-0355-9
[24] Zheng Y, Tao J, Sun Q, Sun H, Chen Z, Sun M, Xie G. Soft actor-critic based active disturbance rejection path following control for unmanned surface vessel under wind and wave disturbances. Ocean Engineering 2022; 247: 110631.
https://doi.org/10.1016/j.oceaneng.2022.110631
[25] Li C, Zhang B, Cao Y, Yin B. Reinforcement learning-based backstepping sliding mode heading control for unmanned sailboats. Ocean Engineering 2025; 327: 120936.
https://doi.org/10.1016/j.oceaneng.2025.120936
[26] Fan Y, Dong H, Zhao X, Denissenko P. Path-following control of unmanned underwater vehicle based on an improved td3 deep reinforcement learning. IEEE Transactions on Control Systems Technology 2024; 32(5): 1904-1919.
https://doi.org/10.1109/TCST.2024.3377876
[27] Qin H, Xu P, Zhang F, Xue Y. An improved los guidance and sail-rudder cooperative controller for the path tracking of unmanned sailboats. IEEE Transactions on Intelligent Vehicles 2024; 9(10): 6610-6623.
