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

2012 ◽  
Vol 2012 ◽  
pp. 1-6 ◽  
Author(s):  
Ali T. Hasan
Keyword(s):  
Inverse Dynamics ◽  
Robot Manipulator ◽  
Positioning Control ◽  
Passive Joint ◽  
Inversion Technique ◽  
Working Space ◽  
Neural Network Inversion ◽  
Gear Trains ◽  
Artificial Neural ◽  
Underactuated Robot

This paper is devoted to solve the positioning control problem of underactuated robot manipulator. Artificial Neural Networks Inversion technique was used where a network represents the forward dynamics of the system trained to learn the position of the passive joint over the working space of a 2R underactuated robot. The obtained weights from the learning process were fixed, and the network was inverted to represent the inverse dynamics of the system and then used in the estimation phase to estimate the position of the passive joint for a new set of data the network was not previously trained for. Data used in this research are recorded experimentally from sensors fixed on the robot joints in order to overcome whichever uncertainties presence in the real world such as ill-defined linkage parameters, links flexibility, and backlashes in gear trains. Results were verified experimentally to show the success of the proposed control strategy.

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

2011 ◽  
Vol 225 (8) ◽  
pp. 1991-1998 ◽  
Author(s):  
H M A A Al-Assadi ◽  
A A Mat Isa ◽  
Ali T Hasan ◽  
Z A Rahman ◽  
B Heimann
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Learning Algorithm ◽  
Robot Manipulator ◽  
Angular Position ◽  
Prediction Algorithm ◽  
System Modelling ◽  
Active Joint ◽  
Passive Joint ◽  
Artificial Neural

An adaptive learning algorithm using an artificial neural network (ANN) has been proposed to predict the passive joint position of under-actuated robot manipulator. In this approach, a specific ANN model has been designed and trained to learn a desired set of joint angular positions for the passive joint from a given set of input torque and angular position for the active joint over a certain period of time. Trying to overcome the disadvantages of many used techniques in the literature, the ANNs have a significant advantage of being a model-free method. The learning algorithm can directly determine the position of its passive joint, and can, therefore, completely eliminate the need for any system modelling. Even though it is very difficult in practice, data used in this study were recorded experimentally from sensors fixed on robot’s joints to overcome the effect of kinematics uncertainties present in the real world such as ill-defined linkage parameters and backlashes in gear trains. An ANN was trained using the experimentally obtained data and then used to predict the path of the passive joint that is positioned by the dynamic coupling of the active joint. The generality and efficiency of the proposed algorithm are demonstrated through simulations of an under-actuated robot manipulator; finally, the obtained results were successfully verified experimentally.

scholarly journals Inverse Kinematic Solution of 5R Manipulator using ANN and ANFIS

2015 ◽  
Vol 4 (2) ◽  
pp. 109
Author(s):  
Panchand Jha
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fuzzy Inference System ◽  
Inverse Kinematics ◽  
Fuzzy Inference ◽  
Robot Manipulator ◽  
Ann Model ◽  
Inference System ◽  
Artificial Neural ◽  
Neural Fuzzy

<span>Inverse kinematics of manipulator comprises the computation required to find the joint angles for a given Cartesian position and orientation of the end effector. There is no unique solution for the inverse kinematics thus necessitating application of appropriate predictive models from the soft computing domain. Artificial neural network and adaptive neural fuzzy inference system techniques can be gainfully used to yield the desired results. This paper proposes structured artificial neural network (ANN) model and adaptive neural fuzzy inference system (ANFIS) to find the inverse kinematics solution of robot manipulator. The ANN model used is a multi-layered perceptron Neural Network (MLPNN). Wherein, gradient descent type of learning rules is applied. An attempt has been made to find the best ANN configuration for the problem. It is found that ANFIS gives better result and minimum error as compared to ANN.</span>

Integrated Model Of Industrial Robot For Control Applications

1992 ◽  
pp. 27-41
Author(s):  
Johari Halim Shah Osman
Keyword(s):  
Robot Manipulator ◽  
Industrial Robot ◽  
Realistic Model ◽  
Integrated Model ◽  
Control Synthesis ◽  
Real Situation ◽  
Highly Nonlinear ◽  
Gear Trains ◽  
And Control ◽  
Space Description

This paper deals with the development of an intergrated mathematical model of a robot manipulator. The model of the system comprises the mechanical part of the robot as well as the actuators and the gear trains. Two different approaches of deriving the integrated model are presented which results in two different forms of the integrated dynamic model of the robot manipulator in state space description. Both types of the integrated model are highly nonlinear, time varying, and represent a more realistic model of the robotic system. The integrated model and the approach are useful and suitable for dynamic analysis and control synthesis purposes, and will provide a more efficient approach to the real situation.

A Modular 2-DOF Serial Robot Manipulator for Education in Robot Control

2016 ◽  
Author(s):  
Stephen Mascaro
Keyword(s):  
Robot Control ◽  
Inverse Dynamics ◽  
Position Control ◽  
Sliding Mode ◽  
Feedforward Control ◽  
Robot Manipulator ◽  
Impedance Control ◽  
Force Sensor ◽  
Control Techniques ◽  
Serial Robot

This paper describes a modular 2-DOF serial robot manipulator and accompanying experiments that have been developed to introduce students to the fundamentals of robot control. The robot is designed to be safe and simple to use, and to have just enough complexity (in terms of nonlinear dynamics) that it can be used to showcase and compare the performance of a variety of textbook robot control techniques including computed torque feedforward control, inverse dynamics control, robust sliding-mode control, and adaptive control. These various motion control schemes can be easily implemented in joint space or operational space using a MATLAB/Simulink real-time interface. By adding a simple 2-DOF force sensor to the end-effector, the robot can also be used to showcase a variety of force control techniques including impedance control, admittance control, and hybrid force/position control. The 2-DOF robots can also be used in pairs to demonstrate control architectures for multi-arm coordination and master/slave teleoperation. This paper will describe the 2-DOF robot and control hardware/software, illustrate the spectrum of robot control methods that can be implemented, and show sample results from these experiments.

scholarly journals A real-time system for robot manipulator inverse dynamics computation

1988 ◽  
Vol 14 ◽  
pp. 63-68 ◽  
Author(s):  
J.A.T Machado ◽  
J.L.M de Carvalho ◽  
J.A.S Matos ◽  
A.M.C Costa
Keyword(s):  
Real Time ◽  
Inverse Dynamics ◽  
Robot Manipulator ◽  
Time System ◽  
Real Time System

Hybrid Position and Force Control Without Force Sensor

1996 ◽  
Vol 8 (3) ◽  
pp. 226-234
Author(s):  
Kiyoshi Ohishi ◽  
◽  
Masaru Miyazaki ◽  
Masahiro Fujita ◽  
Keyword(s):  
Degrees Of Freedom ◽  
Inverse Dynamics ◽  
Hybrid Control ◽  
Robot Manipulator ◽  
Reaction Force ◽  
Force Sensor ◽  
Force Estimation ◽  
Estimation System ◽  
Dynamics Calculation ◽  
Torque Observer

Generally, hybrid control is realized by sensor signal feedback of position and force. However, some robot manipulators do not have a force sensor due to the environment. Moreover, a precise force sensor is very expensive. In order to overcome these problems, we propose the estimation system of reaction force without using a force sensor. This system consists of the torque observer and the inverse dynamics calculation. Using both this force estimation system and <I>H</I>∞ acceleration controller which is based on <I>H</I>∞ control theory, it takes into account the frequency characteristics of both sensor noise effect and disturbance rejection. The experimental results in this paper illustrate the fine hybrid control of the three tested degrees-of-freedom DD robot manipulator without force sensor.

Porosity from artificial neural network inversion for Bermejo Field, Ecuador

2001 ◽  
Author(s):  
Qiang Sun ◽  
Mohamed Eissa ◽  
John Castagna ◽  
Dario Sergio Cersosimo ◽  
Shengjie Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Neural Network Inversion ◽  
Artificial Neural

Dynamics and Trajectory Tracking Control of a Two-Link Robot Manipulator

2004 ◽  
Vol 10 (10) ◽  
pp. 1415-1440 ◽  
Author(s):  
Anthony Green ◽  
Jurek Z. Sasiadek
Keyword(s):  
Fuzzy Logic ◽  
Time Delay ◽  
Inverse Dynamics ◽  
Position Control ◽  
Robot Manipulator ◽  
Phase Response ◽  
Control Law ◽  
Minimum Phase ◽  
Linear Quadratic ◽  
Trajectory Tracking Control

Operational problems with robot manipulators in space relate to several factors, most importantly, structural flexibility and subsequent difficulties with their position control. In this paper we present control methods for endpoint tracking of a 12.6 × 12.6m2 trajectory by a two-link robot manipulator. Initially, a manipulator with rigid links is modeled using inverse dynamics, a linear quadratic regulator and fuzzy logic schemes actuated by a Jacobian transpose control law computed using dominant cantilever and pinned-pinned assumed mode frequencies. The inverse dynamics model is pursued further to study a manipulator with flexible links where nonlinear rigid-link dynamics are coupled with dominant assumed modes for cantilever and pinned-pinned beams. A time delay in the feedback control loop represents elastic wave travel time along the links to generate non-minimum phase response. A time delay acting on control commands ameliorates non-minimum phase response. Finally, a fuzzy logic system outputs a variable to adapt the control law in response to elastic deformation inputs. Results show greater endpoint position control accuracy using a flexible inverse dynamics robot model combined with a fuzzy logic adapted control law and time delays than could be obtained for the rigid dynamics models.

Sign in / Sign up

Export Citation Format

Share Document