Model Predictive Control (MPC) is commonly employed for trajectory tracking in control systems. However, Unmanned Surface Vehicle (USV) systems frequently encounter disturbances and model inaccuracies, resulting in mismatches between predicted and actual behaviors. This paper proposes a Gaussian Process Model Predictive Control (GP-MPC) framework to address the challenges of trajectory tracking in USVs. The MPC framework comprises a nominal model based on kinematic analysis and a Gaussian process error model. The latter compensates for system inaccuracies using sampled data. Simulations and real-world tests are conducted to compare GP-MPC with conventional MPC. The results demonstrate that GP-MPC outperforms the conventional MPC in accurately guiding the USV along the desired trajectory, effectively mitigating environmental disturbances and measurement uncertainties, and enhancing the accuracy and stability of trajectory tracking.
WuNWangRQiJ, et al. Efficient coverage path planning and underwater topographic mapping of an usv based on a*-improved bio-inspired neural network. IEEE Trans Intell Vehicles2024; 1–15. DOI: 10.1109/TIV.2024.3422885.
2.
SakthivelRSathishkumarMRenY, et al. Fault-tolerant sampled-data control of singular networked cascade control systems. Int J Syst Sci2017; 48(10): 2079–2090.
3.
LiuLWangDPengZ, et al. Predictor-based los guidance law for path following of underactuated marine surface vehicles with sideslip compensation. Ocean Eng2016; 124: 340–348.
4.
ChoGRLiJHParkD, et al. Robust trajectory tracking of autonomous underwater vehicles using back-stepping control and time delay estimation. Ocean Eng2020; 201: 107131.
5.
WuNWangMGeT, et al. Experiments on high-performance maneuvers control for a work-class 3000-m remote operated vehicle. Proc IMechE, Part I: J Systems and Control Engineering2019; 233(5): 558–569.
6.
WangWGhenetiBMateosLA, et al. Roboat: An autonomous surface vehicle for urban waterways. In: 2019 IEEE/RSJ international conference on intelligent robots and systems (IROS), 2019, pp.6340–6347. New York: IEEE.
7.
WangWFernández-GutiérrezDDoornbuschR, et al. Roboat iii: An autonomous surface vessel for urban transportation. J Field Robot2023; 40(8): 1996–2009.
8.
YangRClementBMansourA, et al. Modeling of a complex-shaped underwater vehicle for robust control scheme. J Intell Robot Syst2015; 80(3–4): 491–506.
9.
WangNAhnCK.Coordinated trajectory-tracking control of a marine aerial-surface heterogeneous system. IEEE/ASME Trans Mechatron2021; 26(6): 3198–3210.
10.
PengZWangJWangD, et al. An overview of recent advances in coordinated control of multiple autonomous surface vehicles. IEEE Trans Ind Inform2020; 17(2): 732–745.
11.
XueYLiuYJiC, et al. System identification of ship dynamic model based on gaussian process regression with input noise. Ocean Eng2020; 216: 107862.
12.
YinXZhangWJiangZ, et al. Data-driven multi-objective predictive control of offshore wind farm based on evolutionary optimization. Renew Energy2020; 160: 974–986.
13.
RamirezWAKocijanJLeongZQ, et al. Dynamic system identification of underwater vehicles using multi-output gaussian processes. Int J Autom Comput2021; 18(5): 681–693.
14.
YuRYuaZZhuM, et al. Data-driven distributed state estimation and behavior modeling in sensor networks. In: 2020 IEEE/RSJ international conference on intelligent robots and systems (IROS), 2020, pp.8192–8199. New York: IEEE.
15.
BroschAHankeSWallscheidO, et al. Data-driven recursive least squares estimation for model predictive current control of permanent magnet synchronous motors. IEEE Trans Power Electron2020; 36(2): 2179–2190.
16.
LicitraGBürgerAWilliamsP, et al. Aerodynamic model identification of an autonomous aircraft for airborne wind energy. Optim Control Appl Methods2019; 40(3): 422–447.
17.
WuNLWangXYGeT, et al. Parametric identification and structure searching for underwater vehicle model using symbolic regression. J Mar Sci Technol2017; 22(1): 51–60.
18.
DeisenrothMPTurnerRDHuberMF, et al. Robust filtering and smoothing with gaussian processes. IEEE Trans Automat Contr2011; 57(7): 1865–1871.
19.
DeisenrothMPFoxDRasmussenCE.Gaussian processes for data-efficient learning in robotics and control. IEEE Trans Pattern Anal Mach Intell2013; 37(2): 408–423.
20.
GirardARasmussenCCandelaJQ, et al. Gaussian process priors with uncertain inputs application to multiple-step ahead time series forecasting. In: Advances in neural information processing systems, 2002, p.15.
21.
ShenKYuCGuoY, et al. Hybrid-tracked finite-time path following control of underactuated underwater vehicles with 6-dof. Ocean Eng2024; 312: 119023.
22.
LiuXZhangMChuZ, et al. A sphere region tracking control scheme for underwater vehicles. IEEE Trans Vehicular Technol2023; 72(8): 9835–9844.
23.
MoeSPettersenKYFossenTI, et al. Line-of-sight curved path following for underactuated usvs and auvs in the horizontal plane under the influence of ocean currents. In: 2016 24th Mediterranean conference on control and automation (MED), 2016, pp. 38–45. New York: IEEE.
24.
YuLMengQZhangH.3-dimensional modeling and attitude control of multi-joint autonomous underwater vehicles. J Mar Sci Eng2021; 9(3): 307.
25.
WangMSuYWuN, et al. Vector field-based integral los path following and target tracking for underactuated unmanned surface vehicle. Ocean Eng2023; 285: 115462.
26.
HajjiNMaraouiSChrifi-AlaouiL, et al. Nonlinear distributed model predictive control for complex systems: application for hydraulic system. Trans Inst Meas Contr2019; 41(10): 2751–2763.
27.
MathisenSGryteKGrosS, et al. Precision deep-stall landing of fixed-wing UAVs using nonlinear model predictive control. J Intell Robot Syst2021; 101(1): 15.
28.
CavaniniLIppolitiGCamachoEF.Model predictive control for a linear parameter varying model of an uav. J Intell Robot Syst2021; 101(3): 1–18.
29.
CuiYOsakiSMatsubaraT.Reinforcement learning boat autopilot: a sample-efficient and model predictive control based approach. In: 2019 IEEE/RSJ international conference on intelligent robots and systems (IROS), 2019, pp.2868–2875. New York: IEEE.
30.
GanWZhuDJiD.Qpso-model predictive control-based approach to dynamic trajectory tracking control for unmanned underwater vehicles. Ocean Eng2018; 158: 208–220.
31.
DeisenrothMNgJW.Distributed gaussian processes. In: International conference on machine learning, 2015, pp.1481–1490. PMLR.
32.
DeisenrothMPHuberMFHanebeckUD.Analytic moment-based gaussian process filtering. In: Proceedings of the 26th annual international conference on machine learning, 2009, pp.225–232.
33.
LiuLWangDPengZ, et al. Distributed path following of multiple under-actuated autonomous surface vehicles based on data-driven neural predictors via integral concurrent learning. IEEE Trans Neural Netw Learn Syst2021; 32(12): 5334–5344.
34.
LimaGSTrimpeSBessaWM.Sliding mode control with gaussian process regression for underwater robots. J Intell Robot Syst2020; 99(3-4): 487–498.
35.
WangYXieXChadliM, et al. Sliding-mode control of fuzzy singularly perturbed descriptor systems. IEEE Trans Fuzzy Syst2020; 29(8): 2349–2360.
36.
JinZWuJLiuA, et al. Gaussian process-based nonlinear predictive control for visual servoing of constrained mobile robots with unknown dynamics. Robot Auton Syst2021; 136: 103712.
