No 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.

No abstract

No abstract

This article focuses on the finite-time adaptive fuzzy control problem based on command filtering for stochastic nonlinear systems subject to input quantization. Fuzzy logic systems are employed to estimate unknown nonlinearities.In the control design, the hysteretic quantized input is decomposed into two bounded nonlinear functions, which solves the chattering problem. Meanwhile, an adaptive fuzzy controller is presented by the combination of command filter technique and backstepping control, which eliminates the computational complexity existing in traditional backstepping design. Under the proposed adaptive mechanism, all the closed-loop signals remain bounded while the desired system performance can be realized within finite time. The main significance of this work is that (1) the filtering error can be solved on the basis of the designed compensating signals;(2) the requirement of adaptive parameters is decreased to only one, which simplifies the controller design process and may improve the control performance. Two simulation examples are used to validity of the developed scheme.