Adaptive Neural Command Filtered Tracking Control for Flexible Robotic Manipulator With Input Dead-Zone

Abstract

In this paper, an adaptive neural network (NN) command filtered tracking control method is developed for a flexible robotic manipulator with dead-zone input. To deal with the input dead-zone nonlinearity, it is viewed as a combination of a linear part and bounded disturbance-like term. The Neural networks (NNs) are used to estimate the uncertain nonlinearities appeared in the control system. By using the command filter technique, the problem of 'explosion of complexity' is overcome. The proposed controller guarantees that all the closed-loop signals are bounded and the system output can track the given reference signal. The simulation results are provided to demonstrate the effectiveness of the proposed controller. INDEX TERMS Adaptive neural network control, robotic manipulator, dead-zone, command-filter technique, backstepping.

Obstacle Avoidance and Tracking Control of Redundant Robotic Manipulator: An RNN-Based Metaheuristic Approach

“…These optimization-centric approaches are capable of solving additional inequality constraint simultaneously with the tracking control problem. For example, Wei et al [22] and Wang et al [23] used it for tracking control of manipulators with flexible joints. Li et al [19] proposed a dual Recurrent Neural Network (RNN) for solving the tracking-control optimization problem for multiple manipulators in real-time.…”

Obstacle avoidance and model‐free tracking control for home automation using bio‐inspired approach

“…This technique works in cartesian coordinates and requires more computational joint‐space for further control actions, which makes it computationally expensive. Another technique is the use of a depth sensor for manipulator and obstacle distance information 35,36 . However, these obstacle avoidance algorithms assume obstacles as a point object and do not account for the 3D structure of the obstacles and the manipulator.…”

Command Filter Adaptive Power Capture Control Based on Fuzzy Rules Emulated Networks for Variable Speed Wind Turbines With Flexible Shaft

“…• Unlike [27], [29]- [31] require known control gains, the virtual and actual control gains of the considered systems are totally unknown, so a new error compensation dynamic has been established with the estimation of the virtual control gain. • FRENs established by [36] are firstly utilized in continuous-time command filter adaptive control systems to approximate the unavailable aerodynamic torque without assuming its boundedness or it satisfied the Lipschitz condition, which are required in [27], [29], [30], [33].…”