Robust composite neural dynamic surface control for the path following of unmanned marine surface vessels with unknown disturbances

Abstract

This article presents a robust composite neural-based dynamic surface control design for the path following of unmanned marine surface vessels in the presence of nonlinearly parameterized uncertainties and unknown time-varying disturbances. Compared with the existing neural network-based dynamic surface control methods where only the tracking errors are commonly used for the neural network weight updating, the proposed scheme employs both the tracking errors and the prediction errors to construct the adaption law. Therefore, faster identification of the system dynamics and improved tracking accuracy are achieved. In particular, an outstanding advantage of the proposed neural network structure is simplicity. No matter how many neural network nodes are utilized, only one adaptive parameter that needs to be tuned online, which effectively reduces the computational burden and facilitates to implement the proposed controller in practice. The uniformly ultimate boundedness stability of the closed-loop system is established via Lyapunov analysis. Comparison studies are presented to demonstrate the effectiveness of the proposed composite neural-based dynamic surface control architecture.

Event-triggered robust adaptive control for unmanned surface vehicle in presence of deception attacks

“…By incorporating equations ( 35) and (36) into equation (32), the kinetics error derivation equations can be rewritten as equation ( 37)…”

“…For this purpose, only the control approach is regarded as the tested target in this section. The control algorithms in Wen et al 4 and Zeng et al 32 are employed to verify the designed one effectively. To facilitate the subsequent representation, the comparative literatures are respectively represented by (a) and (b).…”

Path following of under-actuated ships based on backstepping and predictive control method

“…Then, radial basis function (RBF) neural networks were applied in Shen et al 16 and Wan et al 17 to offset model uncertainties. In Zeng et al, 18 a simplified RBF neural network was proposed. In Yu et al 19 and Zhang et al , 20 a minimum learning parameter (MLP) neural network approach was used to decrease the calculation burden.…”

Robust exponential point stabilization control of the high-speed underactuated unmanned marine vehicle with model asymmetry

“…[1][2][3][4] Although much advancement have been realized in this area, the demand for more advanced navigation, guidance, and control systems for UMVs continues to grow, as more and more vehicle autonomy is required. [5][6][7][8] In practical implementation, many UMVs are designed of underactuated configurations due to practical considerations, for example, reducing weight and/or cost. [9][10][11][12] Point stabilization is the most basic case of the motion control of UMV, where the desired position and attitude are chosen to be constant, and it is the important foundation of path following and trajectory tracking of UMV.…”