Wavelet Based Neural Network Solution for Forward Kinematics Problem of HEXA Parallel Robot

Dehghani, M.; Ahmadi, Mahdi; Khayatian, Alireza; Eghtesad, Mohammad

doi:10.1109/ines.2008.4481271

Cited by 6 publications

(3 citation statements)

References 30 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dynamic model of the robot was studied by the Lagrange method (Ahmadi et al, 2008). Then, because forward kinematics of parallel robots is a highly nonlinear problem and often needs numerical techniques, a neural networks-based method (Dehghani et al, 2008a) was employed to find its solution; the solution was then modified by using wavelets as the basis of the training process (Dehghani et al, 2008b).…”

Section: Mechanism Descriptionmentioning

confidence: 99%

Vision-based calibration of a Hexa parallel robot

Dehghani

Ahmadi

Khayatian

et al. 2014

Industrial Robot: An International Journal

View full text Add to dashboard Cite

Purpose – The purpose of this paper is to present a vision-based method for the kinematic calibration of a six-degrees-of-freedom parallel robot named Hexa using only one Universal Serial Bus (USB) camera and a chess pattern installed on the robot's mobile platform. Such an approach avoids using any internal sensors or complex three-dimensional measurement systems to obtain the pose (position/orientation) of the robot's end-effector or the joint coordinates. Design/methodology/approach – The setup of the proposed method is very simple; only one USB camera connected to a laptop computer is needed and no contact with the robot is necessary during the calibration procedure. For camera modeling, a pinhole model is used; it is then modified by considering some distortion coefficients. Intrinsic and extrinsic parameters and the distortion coefficients are found by an offline minimization algorithm. The chess pattern makes image corner detection very straightforward; this detection leads to finding the camera and then the kinematic parameters. To carry out the calibration procedure, several trajectories are run (the results of two of them are presented here) and sufficient specifications of the poses (positions/orientations) are calculated to find the kinematic parameters of the robot. Experimental results obtained when applying the calibration procedure on a Hexa parallel robot show that vision-based kinematic calibration yields enhanced and efficient positioning accuracy. After successful calibration and addition of an appropriate control scheme, the robot has been considered as a color-painting prototype robot to serve in relevant industries. Findings – Experimental results obtained when applying the calibration procedure on a Hexa parallel robot show that vision-based kinematic calibration yields enhanced and efficient positioning accuracy. Originality/value – The enhanced results show the advantages of this method in comparison with the previous calibration methods.

show abstract

Section: Mechanism Descriptionmentioning

confidence: 99%

Vision-based calibration of a Hexa parallel robot

Dehghani

Ahmadi

Khayatian

et al. 2014

Industrial Robot: An International Journal

View full text Add to dashboard Cite

show abstract

“…WNNs-based control systems have been adopted widely for control of complex dynamical systems owing to their fast learning properties and good generalization capability [10,11]. Moreover, recurrent wavelet neural networks (RWNNs), which combine properties such as dynamic response of recurrent neural networks (RNNs) and the fast convergence of a WNN, have been proposed to identify and control nonlinear systems [14][15][16][17][18]. An intelligent control system using recurrent wavelet-based Elman neural network for position control of a permanent-magnet synchronous motor servo drive was proposed in [19].…”

Section: Introductionmentioning

confidence: 99%

Decentralized Identification and Control in Real-Time of a Robot Manipulator via Recurrent Wavelet First-Order Neural Network

Vázquez

Jurado

Alanís

2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A decentralized recurrent wavelet first-order neural network (RWFONN) structure is presented. The use of a wavelet Morlet activation function allows proposing a neural structure in continuous time of a single layer and a single neuron in order to identify online in a series-parallel configuration, using the filtered error (FE) training algorithm, the dynamics behavior of each joint for a two-degree-of-freedom (DOF) vertical robot manipulator, whose parameters such as friction and inertia are unknown. Based on the RWFONN subsystem, a decentralized neural controller is designed via backstepping approach. The performance of the decentralized wavelet neural controller is validated via real-time results.

show abstract

“…Many efforts have been made on applications of Neural Networks to various types of parallel manipulators [9][10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network Based Forward Kinematics Solution for Planar Parallel Manipulators Passing through Singular Configuration

Showaib¹

2013

Adv Robot Autom

View full text Add to dashboard Cite

It is well known that, the main drawback of parallel manipulators is the existence of singularities within its workspace, an Artificial Neural Network (ANN) based solution is proposed in this paper. The proposed approach can certainly learn the input-output data and discover the non-linear relationships which are inherent in the training data. Additionally, the proposed approach can provide solution of the forward kinematic problem with reasonable errors at and in the vicinity of kinematic singularities. The approach is implemented for the 3-RPR, 3-PRR, and 3-RRR planar parallel manipulators.

show abstract

Wavelet Based Neural Network Solution for Forward Kinematics Problem of HEXA Parallel Robot

Cited by 6 publications

References 30 publications

Vision-based calibration of a Hexa parallel robot

Vision-based calibration of a Hexa parallel robot

Decentralized Identification and Control in Real-Time of a Robot Manipulator via Recurrent Wavelet First-Order Neural Network

Artificial Neural Network Based Forward Kinematics Solution for Planar Parallel Manipulators Passing through Singular Configuration

Contact Info

Product

Resources

About