Neural Networks for Redundant Robot Manipulators Control with Obstacles Avoidance

2004 ◽  
Vol 16 (1) ◽  
pp. 90-96 ◽  
Author(s):  
B. Daachi ◽  
◽  
A. Benallegue ◽  
T. Madani ◽  
M. E. Daachi ◽  
...  

In this paper, neural networks of MLP type are used to control constrained redundant robot manipulators with obstacles. The proposed controller is determined using extended Cartesian space to minimise the joint displacements and to avoid obstacles. The neural networks have been used to approximate separately, the functions of the dynamic model of the robot manipulator expressed in the Cartesian space. The adaptation laws weights of each neural network, are obtained via stability study in Lyapunov sense of the system in closed loop. The performances of the proposed control approach are tested on a 3-degree of freedom robot manipulators involving in the vertical space.

2006 ◽  
Vol 129 (10) ◽  
pp. 1086-1093 ◽  
Author(s):  
J. Zhang ◽  
J. Rastegar

Smart (active) materials based actuators, hereinafter called micro-actuators, have been shown to be well suited for the elimination of high harmonics in joint and/or end-effector motions of robot manipulators and in the reduction of actuator dynamic response requirements. Low harmonic joint and end-effector motions, as well as low actuator dynamic response requirements, are essential for a robot manipulator to achieve high operating speed and precision with minimal vibration and control problems. Micro-actuators may be positioned at the end-effector to obtain a micro- and macro-robot manipulation configuration. Alternatively, micro-actuators may be integrated into the structure of the links to vary their kinematics parameters, such as their lengths during the motion. In this paper, the kinematics and dynamics consequences of each of the aforementioned alternative are studied for manipulators with serial and closed-loop chains. It is shown that for robot manipulators constructed with closed-loop chains, the high harmonic components of all joint motions can be eliminated only when micro-actuators are integrated into the structure of the closed-loop chain links. The latter configuration is also shown to have dynamics advantage over micro- and macro-manipulator configuration by reducing the potential vibration and control problems at high operating speeds. The conclusions reached in this study also apply to closed-loop chains of parallel and cooperating robot manipulators.


2019 ◽  
Vol 41 (16) ◽  
pp. 4535-4544
Author(s):  
Felipe-de-Jesús Torres ◽  
Gerardo-Vicente Guerrero ◽  
Carlos-Daniel García ◽  
Diego-Alfredo Núñez ◽  
Juan Mota

This paper presents a design of synchronization of robot manipulators driven by induction motors in the case where the flux, velocity and currents are estimated. The synchronization is developed in both the joint space and workspace. The [Formula: see text] field oriented frame model of the induction motor is used to design the synchronization control approach. An observer based on the [Formula: see text] frame model is proposed to estimate the flux, velocity and currents variables, then they are converted to the variables of the [Formula: see text] field-oriented model, and finally the remaining variables are estimated by means of an observer based on the [Formula: see text] frame model. Stability is proved via a Lyapunov analysis. Simulations show the proposed controllers yield synchronization errors asymptotically stables in the closed-loop response.


2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
Jinzhu Peng ◽  
Yan Liu

An adaptive robust quadratic stabilization tracking controller with hybrid scheme is proposed for robotic system with uncertainties and external disturbances. The hybrid scheme combines computed torque controller (CTC) with an adaptive robust compensator, in which variable structure control (VSC) andH∞optimal control approaches are adopted. The uncertain robot manipulator is mainly controlled by CTC, the VSC is used to eliminate the effect of the uncertainties and ensure global stability, andH∞approach is designed to achieve a certain tracking performance of closed-loop system. A quadratic stability approach, which allows separate treatment of parametric uncertainties, is used to reduce the conservatism of the conventional robust control approach. It can be also guaranteed that all signals in closed-loop system are bounded. The validity of the proposed control scheme is shown by computer simulation of a two-link robotic manipulator.


Author(s):  
Majid Moradi Zirkohi

In this paper, a simple model-free controller for electrically driven robot manipulators is presented using function approximation techniques (FAT) such as Legendre polynomials (LP) and Fourier series (FS). According to the orthogonal functions theorem, LP and FS can approximate nonlinear functions with an arbitrary small approximation error. From this point of view, they are similar to fuzzy systems and can be used as controller to approximate the ideal control law. In comparison with fuzzy systems and neural networks, LP and FS are simpler and less computational. Moreover, there are very few tuning parameters in LP and FS. Consequently, the proposed controller is less computational in comparison with fuzzy and neural controllers. The case study is an articulated robot manipulator driven by permanent magnet direct current (DC) motors. Simulation results verify the effectiveness of the proposed control approach and its superiority over neuro-fuzzy controllers.


Author(s):  
Ghania Debbache ◽  
Abdelhak Bennia ◽  
Noureddine Goléa

This paper proposes an adaptive control suitable for motion control of robot manipulators with structured and unstructured uncertainties. In order to design an adaptive robust controller, with the ability to compensate these uncertainties, we use neural networks (NN) that have the capability to approximate any nonlinear function over a compact space. In the proposed control scheme, we need not derive the linear formulation of robot dynamic equation and tune the parameters. To reduce the NNs complexity, we consider the properties of robot dynamics and the decomposition of the uncertainties terms. The proposed controller is robust against uncertainties and external disturbance. The validity of the control scheme is demonstrated by computer simulations on a two-link robot manipulator.


1990 ◽  
Vol 112 (4) ◽  
pp. 653-660 ◽  
Author(s):  
H. Kazerooni ◽  
K. G. Bouklas ◽  
J. Guo

This work presents a control methodology for compliant motion in redundant robot manipulators. This control approach takes advantage of the redundancy in the robot’s degrees of freedom: while a maximum six degrees of freedom of the robot control the robot’s endpoint position, the remaining degrees of freedom impose an appropriate force on the environment. To verify the applicability of this control method, an active end-effector is mounted on an industrial robot to generate redundancy in the degrees of freedom. A set of experiments are described to demonstrate the use of this control method in constrained maneuvers. The stability of the robot and the environment is analyzed.


Author(s):  
Kamil Cetin ◽  
Enver Tatlicioglu ◽  
Erkan Zergeroglu

In this study, an extended Jacobian matrix formulation is proposed for the operational space tracking control of kinematically redundant robot manipulators with multiple subtask objectives. Furthermore, to compensate the structured uncertainties related to the robot dynamics, an adaptive operational space controller is designed, and then, the corresponding stability analysis is presented for kinematically redundant robot manipulators. Specifically, the proposed method is concerned with not only the stability of operational space objective but also the stability of multiple subtask objectives. The combined stability analysis of the operational space objective and the subtask objectives are obtained via Lyapunov based arguments. Experimental and simulation studies are presented to illustrate the performance of the proposed method.


Sign in / Sign up

Export Citation Format

Share Document