Trajectory tracking for a serial robot manipulator passing through singular configurations based on the adaptive kinematics Jacobian method

Abstract

This paper discusses the use of artificial neural networks (ANNs) as a method of trajectory tracking control for a robotic system. Using an ANN does not require any prior knowledge of the kinematics model of the system being controlled; the basic idea of this concept is the use of the ANN to learn the characteristics of the robot system rather than to specify an explicit robot system model. In this approach, disadvantages of some schemes such as the fuzzy learning control, for example, have been elevated. Off-line training was performed for a geometric trajectory that is free of obstacles. Studying the kinematics Jacobian of serial manipulators by using ANNs has two problems: one of these is the selection of the appropriate configuration of the network and the other is the generation of a suitable training dataset. In this approach, although this is very difficult in practice, training data were recorded experimentally from sensors fixed on each joint to overcome the effect of kinematics uncertainties present in the real world such as ill-defined linkage parameters, links flexibility, and backlashes in the gear train. Then two network configurations were compared to find the best configuration to be used. Finally, the simulation results were verified experimentally using a general six-degree-of-freedom (DOF) serial robot manipulator.

Slider position control for slider-crank mechanisms with Jacobian compensator

“…There are several approaches to deal with this problem: robust controllers remain a viable option, mainly neural networks and fuzzy control 8 because they do not require any knowledge of the system dynamics and kinematics, however, their design is complex; numeric algorithms 16 which requires the evaluation of the kinematics in all the joint space; and adaptive algorithms 7 which requires a model of the Jacobian. Recently, it has been worked in scaling the Jacobian to avoid singularities by properties of the mechanism and its movement.…”

“…Usually, the controllers are in joint space 6 and use robust controllers for the position task. The most common used controllers are adaptive, [7][8][9] sliding mode, 10,11 neural networks and fuzzy control. 10 The idea of using robust controllers lies in a compensation of the mechanism dynamics (mainly the gravitational terms), modeling error and possible disturbances.…”

Under-Actuated Robot Manipulator Positioning Control Using Artificial Neural Network Inversion Technique

“…In real world application, no physical property such as the friction coefficient can be exactly derived. Besides, there are always kinematics uncertainties presence in the real world such as ill-defined linkage parameters, links flexibility, and backlashes in gear train [17,18].…”

Development of a real-time-position prediction algorithm for under-actuated robot manipulator by using of artificial neural network

“…In real world application, no physical property such as the friction coefficient can be exactly derived. Besides, there are always kinematics uncertainties present in the real world such as ill-defined linkage parameters and backlashes in gear trains [26,27]. In this article, and to overcome whichever uncertainty presented in the real world, data were recorded experimentally from sensors fixed on each joint for a horizontal two-link under-actuated robot.…”