• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.10a
• /
• pp.131-136
• /
• 1999

This paper proposes the robot inverse calibration method using a neural networks. A highorder networks called Pi-Sigma networks has been used. The Pi-Sigma networks uses linear summing units in the hidden layer and product unit in output layer. The inverse calibration model which compensates the difference of joint variables only between measuring value and analytic value about the desired pose(position, orientation) of a robot is proposed. The compensated values are determined by using the weights obtained from the learning process of the neural networks previously. To prove the reasonableness, the SCARA type direct drive robot(4-DOF) and anthropomorphic robot(6-DOF) are simulated. It shows that the proposed calibration method can reduce the errors of the joint variables from $\pm$2$^{\circ}$to $\pm$ 0.1$^{\circ}$.

• The Journal of Korea Robotics Society
• /
• v.17 no.2
• /
• pp.183-190
• /
• 2022

Accurate kinematic parameters of mobile robots are essential because inaccurate kinematic model produces considerable uncertainties on its odometry and control. Especially, kinematic parameters of caster type mobile robots are important due to their complex kinematic model. Despite the importance of accurate kinematic parameters for caster type mobile robots, few research dealt with the calibration of the kinematic model. Previous study proposed a calibration method that can only calibrate double-wheeled caster type mobile robot and requires direct-measuring of robot center point and distance between casters. This paper proposes a calibration method based on geometric approach that can calibrate single-wheeled caster type mobile robot with two or more casters, does not require direct-measuring, and can successfully acquire all kinematic parameters required for control and odometry. Simulation and hardware experiments conducted in this paper validates the proposed calibration method and shows its performance.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1832-1835
• /
• 1997

Off-line programming systems are widely spread in assembly lines of minute electronic products to huge offshore structures. Any OLP system has to be calibrated before the on-line robot tasks are performed because there are inherent differences between the CAD model on OLP and the real robot workspace. This paper uses simple geometric expressions to propose a calibration method applicable to an OLP for SCARA robots. A positioning task on the two-dimensional horizontal surface was used in the error analysis of a SCARA robot and the anaysis shows that the inaccuracy results from the two error sources non-zero offset angles of two rotational joints at the zero return and differences in link lengths. Pen marks on a sheet of plotting paper are used to determine the accurate data on the joint centers and link dimensions. The calculated offset angles and link lengths are fed back to the OLP for the calibration of the CAD model of the robot and task environments.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.285-286
• /
• 2011

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.7
• /
• pp.66-72
• /
• 1999

Robot calibration is very important to improve the accuracy of robot manipulators. However, the calibration procedure is very time consuming and laborious work for users. In this paper, we propose a method of relative error compensation to make the calibration procedure easier. The method is completed by a Pi-Sigma network architecture which has sufficient capability to approximate the relative relationship between the accuracy compensations and robot configurations while maintaining an efficient network learning ability. By experiment of 4-DOF SCARA robot, KIRO-3, it is shown that both the error of joint angles and the positioning error of end effector are drop to 15$\%$. These results are similar to those of other calibration methods, but the number of measurement is remarkably decreased by the suggested compensation method.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.12
• /
• pp.86-94
• /
• 1997

This paper proposes the robot inverse calibration method using a neural networks. A high-order networks called Pi-Sigma networks has been used. The Pi-Sigma networks uses linear summing units in the hidden layer and product unit in output layer. The inverse calibration model which compensates the diff- erence of joint variables only between measuring value and analytic value about the desired pose(position, orientation) of a robot is proposed. The compensated values are determined by using the weights obtained from the learning process of the neural networks previously. To prove the reasonableness, the SCARA type direct drive robot(4-DOF) and anthropomorphic robot(6-DOF) are simulated. It shows that the proposed calibration method can reduce the errors of the joint variables from .+-. 5 .deg. to .+-. 0.1 .deg. .

• International Journal of Precision Engineering and Manufacturing
• /
• v.4 no.1
• /
• pp.43-48
• /
• 2003

A linear laser-vision sensor called ‘Perception TriCam Contour' is mounted on an industrial robot and often used for various application of the robot such as the position correction and the inspection of a part. In this paper, a sensor center position calibration is presented for the most accurate use of the robot-Perceptron system. The obtained algorithm is suitable for on-site calibration in an industrial application environment. The calibration algorithm requires the joint sensor readings, and the Perceptron sensor measurements on a specially devised jig which is essential for this calibration process. The algorithm is implemented on the Hyundai 7602 AP robot, and Perceptron's measurement accuracy is increased up to less than 1.4mm.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.5
• /
• pp.777-787
• /
• 1995

This paper presents a new method for automatically calibrating robot link (Kinematic) parameters during the process of estimating motion parameters of a moving object. The motion estimation is performed based on stereo cameras mounted on the end-effector of a robot manipulator. This approach significantly differs from other calibration approaches in that the calibration is achieved by simply observing the motion of the moving object (without resorting to any other external calibrating tools) at numerous and widely varying joint-angle configurations. A differential error model, which expresses the measurement errors of a robot in terms of robot link parameter errors and motion parameters, is developed. And then a measurement equation representing the true measurement values is derived. By estimating the above two kinds of parameters minimizing the difference between the measurement equations and the true moving pattern, the calibration of the robot link parameters and the estimation of the motion parameters are accomplished at the same time.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.05a
• /
• pp.199-204
• /
• 1999

The robot inverse calibration method using a neural networks is proposed in this paper. A high-order networks has been used in this study. The Pi-Sigma networks uses linear summing units in the hidden layer and product unit in output layer. The inverse calibration model which compensates the difference of joint variables only between measuring value and analytic value about the desired pose(position orientation) of a robot is proposed. The compensated values are determined by using the weights obtained from the learning process of the neural networks previously. To prove the reasonableness, the selected compliance automatic robot arm type direct drive robot and anthropomorphic robot are simulated. It shows that the proposed calibration method can reduce the errors of the joint variables from ${\pm}$0.15$^{\circ}$to ${\pm}$0.12$^{\circ}$.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.11a
• /
• pp.241-242
• /
• 2010