Online learning control of surface vessels for fine trajectory tracking

Abstract

This paper presents an adaptive neural network (NN) controller for fine trajectory tracking of surface vessels with uncertain environmental disturbances. Regarding to the new demands for fine trajectory tracking, especially to the requirement of high-accuracy tracking in limited working space, the proposed NN controller is designed to contain a tracking error control component and a velocity error control component, aiming to converge both types of error to zero, separately. It utilizes radial basis functions to approximate a vessel's unknown nonlinear dynamics. Therefore, there is no need of any explicit knowledge of the vessel. The online learning ability is obtained during the stability analysis using the backstepping technique and the Lyapunov theory. Theoretical results guarantee both the convergence of tracking error and velocity error and the boundedness of NN update. Through simulation and tracking performance study based on the CyberShip II model, the proposed controller is verified effective in fine trajectory tracking.

Adaptive Neural-Based Finite-Time Trajectory Tracking Control for Underactuated Marine Surface Vessels With Position Error Constraint

“…Defining the error variable u e = α u − u and α u = α u − α u,c , where α u is the filter error of the command filter. Substituting (12) into (14) yieldṡ…”

“…Besides, the approximation-based control methods can also attenuate the effects of uncertainties. In such technique, the unknown vessel dynamics are identified by using appropriate neural networks (NNs) [12]- [14] or fuzzy logic systems (FLS) [15], [16], etc. In [17], the strong approximation capacity of neural network was integrated with backstepping control to design an adaptive robust tracking controller for an underactuated vessel, and the vessel can track the desired trajectory with good robust performance.…”

Polynomial fuzzy model‐based approach for underactuated surface vessels

“…Therefore, they are not needed to be estimated which greatly reduces the controller design complexity. By augmenting the states of the system and the controller as x = [x T s T ] T and regarding (7) and 9, one has:…”

“…Nonetheless, numerous authors have studied the control problem of USVs. To this end, different control techniques have been used, such as sliding mode control [6], learning control [7], adaptive control [8], backstepping control [9], neural network control [3], fuzzy model-free [10] and model-based control [2], and suboptimal control [11]. However, the control of USVs continues to be challenging due to a fact that USVs have complex dynamics, parameter uncertainties, external disturbances and dynamic effects not known to the controller.…”

Adaptive fuzzy control for a class of constrained nonlinear systems with application to a surface vessel

“…Nonlinear strategies (Daly et al, 2012), adaptive control (Fang et al, 2004), and neural networks (Dai et al, 2015) are samples of control algorithms in the previous investigations. Removing some drawbacks of such works, adaptive intelligent methods as adaptive neural networks, were presented by Li et al (2015). In this study, an adaptive fuzzy algorithm is proposed to achieve the advantages of both intelligent and adaptive mechanisms for ensuring the robustness properties and taking the constraints into account.…”