Automated Tool Coordinate Calibration System of an Industrial Robot

Due to the widespread use of industrial robots in market, its application has extended to welding, painting, and freight handling. And tool coordinate calibration is regularly modified after tool replacement due to collision accident or routine maintenance. After tool replacement, operators often rebuild tool coordinates. This is the traditional mode of operation in the current industrial practices. However, smart factory will make artificial intelligence method replace manual method. This paper presents a system independent method for automatic calibration of the tool coordinate system which is faster, simpler, cheaper and more effective than the manual method. The proposed method required images to be captured using two “eye to hand” cameras and one “eye in hand” camera. Tool position data is then acquired through CamShift and MeanShift algorithm for image trajectory tracking along with coordinate system conversion, several methods like PCA, LDA can deal with the vision data. Optimal Deep Neural Network (DNN) method error compensation of a robot allows the tool to automatically run with the calibration system functions. We have developed a 6 degrees of freedom(DoF) industrial robot for this experiment. Nine different kinds of DNN models are built and finally with suitable tool coordinate error compensation for the current robot, tool calibration can be achieved adaptively and efficiently.

I. Introduction

In modern industrial applications, robots have high repeatability. With emerging sensors, there are more indexes of unknown parameters can be measured, leading to higher calibration accuracy[1]. But additional sensors would also increase the cost and complexity of the system. In recent years, in the study of robot tool coordinate calibration, the main sources of inaccuracies include mechanical and structural deformation, thermal expansion or inadvertent errors due to human operation[2]. Laser sensors and cameras are included in the measurements for tool coordinate calibration, such as in modeling and calibration of a structured light scanner[3], and automatic calibration using a 3D vision-based measurement system with a single camera[4]. However, accuracy is limited by the accuracy of the device, external measurement process error and other accidental errors[5]. The accuracy of the tests often cannot reach or are very close to the measurement instrument accuracy[6]. Many large robot manufacturers have a specification of only 0.1 mm accuracy in their Tool Coordinate Calibration Hence, the process of eliminating system errors and accidental errors from tool coordinate calibration is a hot topic for research. Nine deep neural network models based method for tool coordinate calibration are proposed in this paper that can adaptively achieve higher accuracy with tool specific error compensation. The correct calculation will ensure that the robot's end effector has a reliable position repeatability precision.