scholarly journals Predicting Positioning Error and Finding Features for Large Industrial Robots Based on Deep Learning

2021 ◽  
Vol 15 (2) ◽  
pp. 206-214
Author(s):  
Daiki Kato ◽  
Kenya Yoshitsugu ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
Kenichi Takahashi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Computer Aided Design ◽  
Joint Angle ◽  
Industrial Robot ◽  
Movement Time ◽  
Vertical Axis ◽  
Industrial Robots ◽  
Positioning Error ◽  
Design Data ◽  
End Effector

In this study, we evaluated the motion accuracy of a large industrial robot and its compensation method and constructed an off-line teaching operation based on three-dimensional computer aided design data. In this experiment, we used a laser tracker to measure the coordinates of the end effector of the robot. Simultaneously, the end-effector coordinates, each joint angle, the maximum current of the motors attached to each joint, and rotation speed of each joint were measured. This servo information was converted into image data as visible information. For each robot movement path, an image was created; the horizontal axis represented the movement time of the robot and the vertical axis represented the servo information. A convolutional neural network (CNN), a type of deep learning, was used to predict the positioning error with high accuracy. Subsequently, to identify the features of the positioning error, the image was divided into several analysis areas, one of which was filled with various colors and analyzed by the CNN. If the prediction accuracy of the CNN decreased, then the analysis area would be identified as a feature. Thus, the features of the Y-axis positioning error were observed for teaching each joint angle in the opposite direction just after the start of the motion, overshoot of the rotational joint current, and the change in the swivel joint current.

Finding Features of Positioning Error for Large Industrial Robots Based on Convolutional Neural Network

2021 ◽  
Author(s):  
Daiki Kato ◽  
Kenya Yoshitugu ◽  
Naoki Maeda ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Production Systems ◽  
Industrial Robot ◽  
Three Dimensional ◽  
Industrial Robots ◽  
Numerical Control ◽  
Robot Motion ◽  
Positioning Error ◽  
End Effector

Abstract Most industrial robots are taught using the teaching playback method; therefore, they are unsuitable for use in variable production systems. Although offline teaching methods have been developed, they have not been practiced because of the low accuracy of the position and posture of the end-effector. Therefore, many studies have attempted to calibrate the position and posture but have not reached a practical level, as such methods consider the joint angle when the robot is stationary rather than the features during robot motion. Currently, it is easy to obtain servo information under numerical control operations owing to the Internet of Things technologies. In this study, we propose a method for obtaining servo information during robot motion and converting it into images to find features using a convolutional neural network (CNN). Herein, a large industrial robot was used. The three-dimensional coordinates of the end-effector were obtained using a laser tracker. The positioning error of the robot was accurately learned by the CNN. We extracted the features of the points where the positioning error was extremely large. By extracting the features of the X-axis positioning error using the CNN, the joint 1 current is a feature. This indicates that the vibration current in joint 1 is a factor in the X-axis positioning error.

scholarly journals Positioning Error Calibration of Industrial Robots Based on Random Forest

2021 ◽  
Vol 15 (5) ◽  
pp. 581-589
Author(s):  
Daiki Kato ◽  
Kenya Yoshitsugu ◽  
Naoki Maeda ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
...  
Keyword(s):  
Random Forest ◽  
Industrial Robot ◽  
Industrial Robots ◽  
Target Point ◽  
Calibration Model ◽  
Positioning Error ◽  
End Effector ◽  
Positioning Errors ◽  
Random Forest Method ◽  
Kinematic Errors

Because most industrial robots are taught using the direct teaching and playback method, they are unsuitable for variable production systems. Alternatively, the offline teaching method has limited applications because of the low accuracy of the position and posture of the end-effector. Therefore, many studies have been conducted to calibrate the position and posture. Positioning errors of robots can be divided into kinematic and non-kinematic errors. In some studies, kinematic errors are calibrated by kinematic models, and non-kinematic errors are calibrated by neural networks. However, the factor of the positioning errors has not been identified because the neural network is a black box. In another machine learning method, a random forest is constructed from decision trees, and its structure can be visualized. Therefore, we used a random forest method to construct a calibration model for the positioning errors and to identify the positioning error factors. The proposed calibration method is based on a simulation of many candidate points centered on the target point. A large industrial robot was used, and the 3D coordinates of the end-effector were obtained using a laser tracker. The model predicted the positioning error from end-effector coordinates, joint angles, and joint torques using the random forest method. As a result, the positioning error was predicted with a high accuracy. The random forest analysis showed that joint 2 was the primary factor of the X- and Z-axis errors. This suggests that the air cylinder used as an auxiliary to the servo motor of joint 2, which is unique to large industrial robots, is the error factor. With the proposed calibration, the positioning error norm was reduced at all points.

scholarly journals Research of Calibration Method for Industrial Robot Based on Error Model of Position

2021 ◽  
Vol 11 (3) ◽  
pp. 1287
Author(s):  
Tianyan Chen ◽  
Jinsong Lin ◽  
Deyu Wu ◽  
Haibin Wu
Keyword(s):  
Coordinate System ◽  
Industrial Robot ◽  
Calibration Method ◽  
Error Model ◽  
Position Error ◽  
Industrial Robots ◽  
Positioning Error ◽  
Robot Position ◽  
General Measurement ◽  
Parameter Error

Based on the current situation of high precision and comparatively low APA (absolute positioning accuracy) in industrial robots, a calibration method to enhance the APA of industrial robots is proposed. In view of the "hidden" characteristics of the RBCS (robot base coordinate system) and the FCS (flange coordinate system) in the measurement process, a comparatively general measurement and calibration method of the RBCS and the FCS is proposed, and the source of the robot terminal position error is classified into three aspects: positioning error of industrial RBCS, kinematics parameter error of manipulator, and positioning error of industrial robot end FCS. The robot position error model is established, and the relation equation of the robot end position error and the industrial robot model parameter error is deduced. By solving the equation, the parameter error identification and the supplementary results are obtained, and the method of compensating the error by using the robot joint angle is realized. The Leica laser tracker is used to verify the calibration method on ABB IRB120 industrial robot. The experimental results show that the calibration method can effectively enhance the APA of the robot.

scholarly journals Modular fastening system and tool–holder working unit for incremental forming

2019 ◽  
Vol 299 ◽  
pp. 05005
Author(s):  
Melania Tera ◽  
Claudia–Emilia Gîrjob ◽  
Cristina–Maria Biriș ◽  
Mihai Crenganiș
Keyword(s):  
Machine Tools ◽  
Incremental Forming ◽  
Industrial Robot ◽  
Industrial Robots ◽  
Cnc Milling ◽  
End Effector ◽  
Tool Holder ◽  
Cnc Milling Machine ◽  
Milling Machines ◽  
Sheet Metal Workpiece

Incremental forming can be usually unfolded either on CNC milling machine–tools or serial industrial robots. The approach proposed in this paper tackles the problem of designing a modular fastening system, which can be adapted for both above mentioned technological equipment. The fastening system of the sheet–metal workpiece is composed of a fixing plate and a retaining plate. The fixing and retaining plates will be made up of different individual elements, which can be easily repositioned to obtain different sizes of the part. Moreover, the fastening system has to be able to be positioned either horizontally (to be fitted on CNC milling machines) or vertically (to be fitted on industrial robots. The paper also presents the design of a tool–holder working unit which will be fitted on KUKA KR 210 industrial robot. The working unit will be mounted as end–effector of the robot and will bear the punch, driving it on the processing toolpaths.

scholarly journals Online pose correction of an industrial robot using an optical coordinate measure machine system

2018 ◽  
Vol 15 (4) ◽  
pp. 172988141878791 ◽  
Author(s):  
Sepehr Gharaaty ◽  
Tingting Shu ◽  
Ahmed Joubair ◽  
Wen Fang Xie ◽  
Ilian A Bonev
Keyword(s):  
Root Mean Square ◽  
Spot Welding ◽  
Industrial Robot ◽  
Industrial Robots ◽  
Mean Square ◽  
End Effector ◽  
Proportional Integral ◽  
Accuracy Requirement ◽  
Robot Controller ◽  
Correction Scheme

In this article, a dynamic pose correction scheme is proposed to enhance the pose accuracy of industrial robots. The dynamic pose correction scheme uses the dynamic pose measurements as feedback to accurately guide the robot end-effector to the desired pose. The pose is measured online with an optical coordinate measure machine, that is, C-Track 780 from Creaform. A root mean square method is proposed to filter the noise from the pose measurements. The dynamic pose correction scheme adopts proportional-integral-derivaitve controller and generates commands to the FANUC robot controller. The developed dynamic pose correction scheme has been tested on two industrial robots, FANUC LR Mate 200iC and FANUC M20iA. The experimental results on both robots demonstrate that the robots can reach the desired pose with an accuracy of ±0.050 mm for position and ±0.050° for orientation. As a result, the developed pose correction can make the industrial robots meet higher accuracy requirement in the applications such as riveting, drilling, and spot welding.

scholarly journals Compensation for absolute positioning error of industrial robot considering the optimized measurement space

2020 ◽  
Vol 17 (2) ◽  
pp. 172988142092164
Author(s):  
Junde Qi ◽  
Bing Chen ◽  
Dinghua Zhang
Keyword(s):  
Industrial Robot ◽  
Measurement Data ◽  
Joint Space ◽  
Industrial Robots ◽  
Positioning Error ◽  
Positioning Accuracy ◽  
Decoupling Method ◽  
Absolute Positioning ◽  
Motion Characteristics ◽  
High Flexibility

Industrial robots are getting widely applied due to their low use-cost and high flexibility. However, the low absolute positioning accuracy limits their expansion in the area of high-precision manufacturing. Aiming to improve the positioning accuracy, a compensation method for the positioning error is put forward in terms of the optimization of the experimental measurement space and accurate modelling of the positioning error. Firstly, the influence of robot kinematic performance on the measurement accuracy is analysed, and a quantitative index describing the performance is adopted. On this basis and combined with the joints motion characteristics, the optimized measurement space in joint space as well as Cartesian space is obtained respectively, which can provide accurate measurement data to the error model. Then the overall model of the positioning error is constructed based on modified Denavit–Hartenberg method, in which the geometric errors and compliance errors are considered comprehensively, and an error decoupling method between them is carried out based on the error-feature analyses. Experiments on the KUKA KR210 robot are carried out finally. The mean absolute positioning accuracy of the robot increases from 1.179 mm to 0.093 mm, which verifies the effectiveness of the compensation methodology in this article.

Development of Recreating Space Technology for Pipe Joint Manufacturing System With a Dual Industrial Robot

2014 ◽  
Author(s):  
Sosuke Kuroyanagi ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
Shinya Omori ◽  
Koichi Mori ◽  
...  
Keyword(s):  
Computer Aided Design ◽  
Manufacturing System ◽  
Industrial Robot ◽  
Space Technology ◽  
Robot System ◽  
Design Data ◽  
Teaching Mode ◽  
Tool Motion ◽  
Aided Design ◽  
Pipe Joint

A technology has been developed for recreating in a pipe joint manufacturing plant the measurement space in the field. A dual industrial robot system checks whether each manufactured joint matches the measured positions and orientations of the two pipes to be connected before the joint is sent for installation. The accuracy of robot motion is estimated using off-line robot teaching control provided by a program based on computer-aided design data. A double ball bar (DBB) method is used to frequently check the accuracy of machine tool motion. Testing showed that the developed technology is sufficiently accurate once the positions used in the off-line teaching mode are revised on the basis of the errors in motion obtained with the DBB method.

scholarly journals TRAJECTORY ERROR MINIMISATION METHOD DUE TO TRANSIENT REGIME VARIATION OF INDUSTRIAL ROBOTS KINEMATIC LINKS

2019 ◽  
Vol 25 (3) ◽  
Author(s):  
ANDREI LUNCANU ◽  
GHEORGHE STAN
Keyword(s):  
Industrial Robot ◽  
Transient Regime ◽  
Industrial Robots ◽  
End Effector ◽  
Trajectory Error ◽  
Transient Regimes ◽  
Method Of Measurement ◽  
The Difference

<p>In the current industry, industrial robots are gaining more and more ground to classical positioning methods, especially due to the ratio of workspace / volume of the industrial robot. For this reason, methods of minimization of trajectory errors are necessary. Among the multitudes of factors that affect the trajectory precision is the difference between the programmed transient regime and the measured transient regime of the kinematic link used in the structure of the industrial robots. In this paper is presented the method of measurement the transient regimes of the end-effector and a method of compensation of the trajectory error.</p>

scholarly journals Analysis of the Compliance Properties of an Industrial Robot with the Mozzi Axis Approach

Robotics ◽  
2019 ◽  
Vol 8 (3) ◽  
pp. 80 ◽  
Author(s):  
Doria ◽  
Cocuzza ◽  
Comand ◽  
Bottin ◽  
Rossi
Keyword(s):  
Industrial Robot ◽  
Industrial Robots ◽  
Robotic Assembly ◽  
Robot Arm ◽  
Machined Surface ◽  
End Effector ◽  
Chatter Vibrations ◽  
Modes Of Vibration ◽  
Machining Robot ◽  
Robot Performance

In robotic processes, the compliance of the robot arm plays a very important role. In some conditions, for example, in robotic assembly, robot arm compliance can compensate for small position and orientation errors of the end-effector. In other processes, like machining, robot compliance may generate chatter vibrations with an impairment in the quality of the machined surface. In industrial robots, the compliance of the end-effector is chiefly due to joint compliances. In this paper, joint compliances of a serial six-joint industrial robot are identified with a novel modal method making use of specific modes of vibration dominated by the compliance of only one joint. Then, in order to represent the effect of the identified compliances on robot performance in an intuitive and geometric way, a novel kinematic method based on the concept of “Mozzi axis” of the end-effector is presented and discussed.

scholarly journals Influence of Drift on Robot Repeatability and Its Compensation

2021 ◽  
Vol 11 (22) ◽  
pp. 10813
Author(s):  
Michal Vocetka ◽  
Zdenko Bobovský ◽  
Jan Babjak ◽  
Jiří Suder ◽  
Stefan Grushko ◽  
...  
Keyword(s):  
Thermal Expansion ◽  
Error Compensation ◽  
Entire Range ◽  
Industrial Robot ◽  
Positioning Error ◽  
Absolute Accuracy ◽  
End Effector ◽  
Repeatability Error ◽  
Compensation Principle ◽  
The Impact

This paper presents an approach to compensate for the effect of thermal expansion on the structure of an industrial robot and thus to reduce the repeatability difference of the robot in cold and warm conditions. In contrast to previous research in this area that deals with absolute accuracy, this article is focused on determining achievable repeatability. To unify and to increase the robot repeatability, the measurements with highly accurate sensors were performed under different conditions on an industrial robot ABB IRB1200, which was equipped with thermal sensors, mounted on a pre-defined position around joints. The performed measurements allowed to implement a temperature-based prediction model of the end effector positioning error. Subsequent tests have shown that the implemented model used for the error compensation proved to be highly effective. Using the methodology presented in this article, the impact of drift can be reduced by up to 89.9%. A robot upgraded with a compensation principle described in this article does not have to be warmed up as it works with the same low repeatability error in the entire range of the achievable temperatures.

Sign in / Sign up

Export Citation Format

Share Document