Neural network-based robust finite-time control for robotic manipulators considering actuator dynamics

This paper investigates finite-time control of uncertain robotic manipulators with external disturbances by means of neural network control and backstepping technique. To solve the “explosion of terms” in traditional backstepping control, a second-order command filter is designed, and the virtual input and its first-order derivative can be obtained accurately in a finite time. The parameters of the neural network are updated by using the tracking error signals. The proposed controller can guarantee that the tracking error converges to a small region of the origin in some finite time. Finally, we give a simulation study to show the effectiveness of the proposed method.

Download Full-text

Actor-Critic Neural Network Based Finite-time Control for Uncertain Robotic Systems

10.1145/3471287.3471288 ◽

2021 ◽

Author(s):

Changyi Lei

Keyword(s):

Neural Network ◽

Finite Time ◽

Robotic Systems ◽

Time Control ◽

Critic Neural Network

Download Full-text

Continuous finite-time control for robotic manipulators with terminal sliding mode

Automatica ◽

10.1016/j.automatica.2005.07.001 ◽

2005 ◽

Vol 41 (11) ◽

pp. 1957-1964 ◽

Cited By ~ 1237

Author(s):

Shuanghe Yu ◽

Xinghuo Yu ◽

Bijan Shirinzadeh ◽

Zhihong Man

Keyword(s):

Finite Time ◽

Sliding Mode ◽

Robotic Manipulators ◽

Terminal Sliding Mode ◽

Time Control

Download Full-text

A New Finite Time Control Solution for Robotic Manipulators Based on Nonsingular Fast Terminal Sliding Variables and the Adaptive Super-Twisting Scheme

Journal of Computational and Nonlinear Dynamics ◽

10.1115/1.4042293 ◽

2019 ◽

Vol 14 (3) ◽

Cited By ~ 9

Author(s):

Vo Anh Tuan ◽

Hee-Jun Kang

Keyword(s):

Finite Time ◽

Control Method ◽

Sliding Mode ◽

Robotic Manipulators ◽

Control Law ◽

Continuous Control ◽

Terminal Sliding Mode ◽

Finite Time Convergence ◽

Position Errors ◽

Time Control

In this study, a new finite time control method is suggested for robotic manipulators based on nonsingular fast terminal sliding variables and the adaptive super-twisting method. First, to avoid the singularity drawback and achieve the finite time convergence of positional errors with a fast transient response rate, nonsingular fast terminal sliding variables are constructed in the position errors' state space. Next, adaptive tuning laws based on the super-twisting scheme are presented for the switching control law of terminal sliding mode control (TSMC) so that a continuous control law is extended to reject the effects of chattering behavior. Finally, a new finite time control method ensures that sliding motion will take place, regardless of the effects of the perturbations and uncertainties on the robot system. Accordingly, the stabilization and robustness of the suggested control system can be guaranteed with high-precision performance. The robustness issue and the finite time convergence of the suggested system are totally confirmed by the Lyapunov stability principle. In simulation studies, the experimental results exhibit the effectiveness and viability of our proposed scheme for joint position tracking control of a 3DOF PUMA560 robot.

Download Full-text