Robot Calibration combining Kinematic Model and Neural Network for enhanced Positioning and Orientation Accuracy

Robot calibration is used to improve the accuracy of the kinematic model to achieve the higher positioning accuracy within the workspace. Due to some nongeometrical reasons such as joint and link flexibility, the errors are unevenly distributed in the workspace. In this case, it is difficult for the existing methods used to improve the absolute positioning accuracy to achieve good results in each region, especially for robots with large self-weights. In this paper, a novel calibration method is proposed, which deals with joint deflection dependent errors to enhance the robot positioning accuracy in the whole workspace. Firstly, the joint angle workspace is divided into several local regions according to the mass distribution of the robot. Then, its geometric parameters are modeled and identified using the Denavit–Hartenberg (DH) model in each region and in the whole workspace separately. Since the nongeometric error sources are difficult to model correctly, an artificial neural network (ANN) is applied to compensate for the nongeometric errors. Finally, the experiments using an 8 degree-of-freedom (DOF) engineering robot are conducted to demonstrate the validity of the proposed method. The combination of the joint angle division and ANN could be an effective solution for the robot calibration, especially for one with a large self-weight.

Download Full-text

SCREW KINEMATIC MODEL FOR ROBOT CALIBRATION WITH PC-ROBOT COMMUNICATION OVERVIEW

10.26678/abcm.cobem2017.cob17-0355 ◽

2017 ◽

Author(s):

Lucas Kato ◽

Tiago Pinto ◽

Henrique Simas ◽

Daniel Martins

Keyword(s):

Kinematic Model ◽

Robot Calibration ◽

Robot Communication

Download Full-text

A Sensitivity Analysis Based Method for Robot Calibration

22nd Biennial Mechanisms Conference: Robotics, Spatial Mechanisms, and Mechanical Systems ◽

10.1115/detc1992-0206 ◽

1992 ◽

Author(s):

S. Kaizerman ◽

B. Benhabib ◽

R. G. Fenton ◽

G. Zak

Keyword(s):

Sensitivity Analysis ◽

Kinematic Model ◽

Calibration Procedure ◽

Inverse Kinematic ◽

Model Parameters ◽

Robot Calibration ◽

Adjoint Sensitivity ◽

Analysis Methods ◽

The Matrix ◽

Direct Sensitivity

Abstract A new robot kinematic calibration procedure is presented. The parameters of the kinematic model are estimated through a relationship established between the deviations in the joint variables and the deviations in the model parameters. Thus, the new method can be classified as an inverse calibration procedure. Using suitable sensitivity analysis methods, the matrix of the partial derivatives of joint variables with respect to robot parameters is calculated without having explicit expressions of joint variables as a function of task space coordinates (closed inverse kinematic solution). This matrix provides the relationship between the changes in the joint variables and the changes in the parameter values required for the calibration. Two deterministic sensitivity analysis methods are applied, namely the Direct Sensitivity Approach and the Adjoint Sensitivity Method. The new calibration procedure was successfully tested by the simulated calibrations of a two degree of freedom revolute-joint planar manipulator.

Download Full-text

Optimization of the Robot Calibration Process

22nd Biennial Mechanisms Conference: Robotics, Spatial Mechanisms, and Mechanical Systems ◽

10.1115/detc1992-0256 ◽

1992 ◽

Author(s):

G. Zak ◽

R. G. Fenton ◽

B. Benhabib

Keyword(s):

Optimization Problem ◽

Kinematic Model ◽

Optimization Procedure ◽

Calibration Procedure ◽

Residual Error ◽

Industrial Robots ◽

Multiple Objective Optimization ◽

Robot Calibration ◽

Calibration Process ◽

The Cost

Abstract Most industrial robots cannot be off-line programmed to carry out a task accurately, unless their kinematic model is suitably corrected through a calibration procedure. However, proper calibration is an expensive and time-consuming procedure due to the highly accurate measurement equipment required and due to the significant amount of data that must be collected. To improve the efficiency of robot calibration, an optimization procedure is proposed in this paper. The objective of minimizing the cost of the calibration is combined with the objective of minimizing the residual error after calibration in one multiple-objective optimization. Prediction of the residual error for a given calibration process presents the main difficulty for implementing the optimization. It is proposed that the residual error is expressed as a polynomial function. This function is obtained as a result of fitting a response surface to either experimental or simulated sample estimates of the residual error. The optimization problem is then solved by identifying a reduced set of possible solutions, thus greatly simplifying the decision maker’s choice of an effective calibration procedure. An application example of this method is also included.

Download Full-text

Three-Dimensional Occupancy Grids With the Use of Vision and Proximity Sensors in a Robotic Workcell

Dynamic Systems and Control, Parts A and B ◽

10.1115/imece2004-59593 ◽

2004 ◽

Cited By ~ 4

Author(s):

Manish Kumar ◽

Devendra P. Garg

Keyword(s):

Neural Network ◽

Stereo Matching ◽

Three Dimensional ◽

Positional Information ◽

Feedforward Neural Network ◽

Robot Calibration ◽

Proximity Sensor ◽

Vision Sensors ◽

Robot Wrist ◽

Occupancy Grids

This paper discusses the use of multiple vision sensors and a proximity sensor to obtain three-dimensional occupancy profile of robotic workspace, identify key features, and obtain a 3-D model of the objects in the work space. The present research makes use of three identical vision sensors. Two of these sensors are mounted on a stereo rig on the sidewall of the robotic workcell. The third vision sensor is located above the workcell. The vision sensors on the stereo rig provide information about three-dimensional position of any point in the robotic workspace. The camera to robot calibration for these vision sensors in stereo configuration has been obtained with the help of a three-layered feedforward neural network. Squared Sum of Difference (SSD) algorithm has been used to obtain the stereo matching. Similarly, camera to robot transformation for the camera located above the work cell has been obtained with the help of a three-layered feedforward neural network. Three-dimensional positional information from vision sensors on stereo rig and two-dimensional positional information from a camera located above the workcell and a proximity sensor mounted on the robot wrist have been fused with the help of Bayesian technique to obtain more accurate positional information about locations in workspace.

Download Full-text

Determination of the Optimum Cost-Residual Error Trade-off in Robot Calibration

Journal of Mechanical Design ◽

10.1115/1.2919360 ◽

1994 ◽

Vol 116 (1) ◽

pp. 28-35 ◽

Cited By ~ 1

Author(s):

G. Zak ◽

R. G. Fenton ◽

B. Benhabib

Keyword(s):

Kinematic Model ◽

Optimization Procedure ◽

Calibration Procedure ◽

Residual Error ◽

Industrial Robots ◽

Multiple Objective Optimization ◽

Robot Calibration ◽

Optimum Cost ◽

The Cost

Most industrial robots cannot be off-line programmed to carry out a task accurately, unless their kinematic model is suitably corrected through a calibration procedure. However, proper calibration is an expensive and time-consuming procedure due to the highly accurate measurement equipment required and due to the significant amount of data that must be collected. To improve the efficiency of robot calibration, an optimization procedure is proposed in this paper. The objective of minimizing the cost of the calibration is combined with the objective of minimizing the residual error after calibration in one multiple-objective optimization. Prediction of the residual error for a given calibration process presents the main difficulty for implementing the optimization. It is proposed that the residual error is expressed as a polynomial function. This function is obtained as a result of fitting a response surface to either experimental or simulated sample estimates of the residual error. The optimization problem is then solved by identifying a reduced set of possible solutions, thus greatly simplifying the decision maker’s choice of an effective calibration procedure. An application example of this method is also included.

Download Full-text

Kinematic model and metrology system for modular robot calibration

IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 ◽

10.1109/robot.2004.1307500 ◽

2004 ◽

Cited By ~ 2

Author(s):

Seong-Ho Kang ◽

M.W. Pryor ◽

D. Tesar

Keyword(s):

Kinematic Model ◽

Modular Robot ◽

Robot Calibration ◽

Metrology System

Download Full-text

Workspace Generation for a 2 - DOF Parallel Mechanism Using Neural Networks

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.162.121 ◽

2012 ◽

Vol 162 ◽

pp. 121-130 ◽

Cited By ~ 4

Author(s):

Emilia Campean ◽

Tiberiu Pavel Itul ◽

Ionela Tanase ◽

Adrian Pisla

Keyword(s):

Neural Network ◽

Neural Networks ◽

Parallel Mechanism ◽

Degrees Of Freedom ◽

Kinematic Model ◽

Inverse Kinematic ◽

Two Degrees Of Freedom ◽

Initial Testing ◽

Network Application ◽

Satellite Dish

The main purpose of the paper is to develop a neural network application destined to the workspace generation of a parallel mechanism, as an performant alternative to the workspace representation based on inverse kinematic model. The paper describes both algorithms. The initial testing was made for a parallel mechanism with two degrees of freedom that could be applied for the orientation of different systems like a TV satellite dish antennas, sun trackers, telescopes, cameras, radars etc.

Download Full-text

Study of Neural-Kinematics Architectures for Model-Less Calibration of Industrial Robots

Journal of Robotics and Mechatronics ◽

10.20965/jrm.2021.p0158 ◽

2021 ◽

Vol 33 (1) ◽

pp. 158-171

Author(s):

Monica Tiboni ◽

◽

Giovanni Legnani ◽

Nicola Pellegrini

Keyword(s):

Degrees Of Freedom ◽

Industrial Robot ◽

Kinematic Model ◽

Back Propagation ◽

Simulated Data ◽

Industrial Robots ◽

Robot Calibration ◽

Feed Forward Neural Network ◽

Comparative Performance ◽

Order Of Magnitude

Modeless industrial robot calibration plays an important role in the increasing employment of robots in industry. This approach allows to develop a procedure able to compensate the pose errors without complex parametric model. The paper presents a study aimed at comparing neural-kinematic (N-K) architectures for a modeless non-parametric robotic calibration. A multilayer perceptron feed-forward neural network, trained in a supervised manner with the back-propagation learning technique, is coupled in different modes with the ideal kinematic model of the robot. A comparative performance analysis of different neural-kinematic architectures was executed on a two degrees of freedom SCARA manipulator, for direct and inverse kinematics. Afterward the optimal schemes have been identified and further tested on a three degrees of freedom full SCARA robot and on a Stewart platform. The analysis on simulated data shows that the accuracy of the robot pose can be improved by an order of magnitude after compensation.

Download Full-text

Application of the Weighted Least Squares Parameter Estimation Method to the Robot Calibration

Journal of Mechanical Design ◽

10.1115/1.2919465 ◽

1994 ◽

Vol 116 (3) ◽

pp. 890-893 ◽

Cited By ~ 22

Author(s):

G. Zak ◽

B. Benhabib ◽

R. G. Fenton ◽

I. Saban

Keyword(s):

Parameter Estimation ◽

Least Squares ◽

Weighted Least Squares ◽

Kinematic Model ◽

Measurement Data ◽

Estimation Method ◽

Kinematic Parameter ◽

Measuring System ◽

Parameter Estimates ◽

Robot Calibration

Significant attention has been paid recently to the topic of robot calibration. To improve the robot’s accuracy, various approaches to the measurement of the robot’s position and orientation (pose) and correction of its kinematic model have been proposed. Little attention, however, has been given to the method of estimation of the kinematic parameters from the measurement data. Typically, a least-squares solution method is used to estimate the corrections to the parameters of the model. In this paper, a method of kinematic parameter estimation is proposed where a standard least-squares estimation procedure is replaced by weighted least-squares. The weighting factors are calculated based on all the a priori available statistical information about the robot and the pose-measuring system. By giving greater weight to the measurements made where the standard deviation of the noise in the data is expected to be lower, a significant reduction in the error of the kinematic parameter estimates is made possible. The improvement in the calibration results was verified using a calibration simulation algorithm.

Download Full-text