This paper provides two finite-time trajectory tracking control schemes for marine surface vessels (MSVs) which are influenced by dynamic uncertainties and unknown time-varying disturbances. Neural networks (NNs) are applied to reconstruct the vehicle’s dynamic uncertainties, and the sum of upper bound of approximation error and external unknown disturbances is estimated by designing an adaptive law. According to the backstepping technique and finite-time stability theory, a finite-time trajectory tracking control scheme is presented. Further, to decrease the conservatism of the presented control scheme caused by estimating the upper bound, a multivariate sliding mode finite-time disturbance observer (MSMFTDO) is designed to estimate the unknown external disturbances and the part that is not completely reconstructed by NNs, and then a MSMFTDO-based adaptive neural finite-time trajectory tracking control law is designed. Rigorous theoretical analyses are provided to prove that, owing to the developed finite-time trajectory tracking control strategies, all the signals of the closed-loop trajectory tracking control system are bounded, and that the actual trajectory of MSVs is able to track the reference trajectory in finite time. Simulation results illustrate the effectiveness of the developed schemes.

本文提供了两种受动态不确定性和未知时变扰动影响的海上水面船只的有限时间轨迹跟踪控制方案。应用神经网络（NNs）重建车辆的动态不确定性，并通过设计自适应律来估算近似误差和外部未知扰动的上限之和。根据反推技术和有限时间稳定性理论，提出了一种有限时间轨迹跟踪控制方案。此外，为了减少由于估算上限而导致的所提出的控制方案的保守性，设计了一种多元滑模有限时间干扰观测器（MSMFTDO）来估算未知的外部干扰以及未被NN完全重构的部分，然后设计了一种基于MSMFTDO的自适应神经有限时间轨迹跟踪控制律。提供了严格的理论分析，以证明，由于开发了有限时间轨迹跟踪控制策略，闭环轨迹跟踪控制系统的所有信号都是有界的，并且MSV的实际轨迹能够跟踪参考轨迹在有限的时间内。仿真结果说明了所开发方案的有效性。MSV的实际轨迹能够在有限时间内跟踪参考轨迹。仿真结果说明了所开发方案的有效性。MSV的实际轨迹能够在有限时间内跟踪参考轨迹。仿真结果说明了所开发方案的有效性。