Prescribed performance control of underactuated surface vessels' trajectory using a neural network and integral time-delay sliding mode

Abstract

To tackle the underactuated surface vessel (USV) trajectory tracking challenge with input delays and composite disturbances, an integral time-delay sliding mode controller based on backstepping is discussed. First, the law of virtual velocity control is established by coordinate transformation and the position error is caused to converge utilizing the performance function. At the same time, based on the estimation of velocity vector by the high-gain observer (HGO), radial basis function (RBF) neural network is applied to compensate for both the uncertainty of model parameters and external disturbances. The longitudinal and heading control laws are presented in combination with the integral time-delay sliding mode control. Then, on the basis of Lyapunov -Krasovskii functional and stability proof, virtual velocity error is guaranteed to converge to 0 in finite time. Finally, the outcomes of the numerical simulation demonstrate the reliability and efficiency of the proposed approach.

Calibration of Static Errors and Compensation of Dynamic Errors for Cable-driven Parallel 3D Printer

“…After static error calibration, the dynamic errors can be reduced through error analysis and controller design [11,13]. A lot of research has been carried out on dynamic error compensation of CDPRs with the main focus on the cable force.…”

A Framework of Grasp Detection and Operation for Quadruped Robot with a Manipulator

“…Although equipping robots with an unmanned aerial vehicle to extend the FOV is a commonly used solution, it is expensive [22]. To improve the visibility of the target object during the motion of the manipulator, Chen et al considered time delay factors in trajectory planning and tracking [23][24][25]. D.-H. Park et al proposed a method called position-based visual servoing that considers both the visual and physical constraints of the manipulator to compute trajectories that converge to a desired pose [26].…”

Design of a neuro-sliding mode controller for interconnected quadrotor UAVs carrying a suspended payload

“…Many different methods have been developed in the literature to successfully eliminate this phenomenon [25,33,22,42]. With the recent developments in the area of artificial intelligence, artificial intelligence-based controllers have started to be developed for different nonlinear systems in order to eliminate the computational burden of SMC [7,13]. A neural network controller with a learning rule based on a sliding mode algorithm can be utilized to ensure the computation of an unknown component of the equivalent control when there are uncertainties regarding the plant.…”