Hybrid calibration and detection approach for mobile robotic manufacturing systems

Abstract

<jats:sec> <jats:title content-type="abstract-subheading">Purpose</jats:title> <jats:p>The purpose of this paper is to present a visual detection approach to predict the poses of target objects placed in arbitrary positions before completing the corresponding tasks in mobile robotic manufacturing systems.</jats:p> </jats:sec> <jats:sec> <jats:title content-type="abstract-subheading">Design/methodology/approach</jats:title> <jats:p>A hybrid visual detection approach that combines monocular vision and laser ranging is proposed based on an eye-in-hand vision system. The laser displacement sensor is adopted to achieve normal alignment for an arbitrary plane and obtain depth information. The monocular camera measures the two-dimensional image information. In addition, a robot hand-eye relationship calibration method is presented in this paper.</jats:p> </jats:sec> <jats:sec> <jats:title content-type="abstract-subheading">Findings</jats:title> <jats:p>First, a hybrid visual detection approach for mobile robotic manufacturing systems is proposed. This detection approach is based on an eye-in-hand vision system consisting of one monocular camera and three laser displacement sensors and it can achieve normal alignment for an arbitrary plane and spatial positioning of the workpiece. Second, based on this vision system, a robot hand-eye relationship calibration method is presented and it was successfully applied to a mobile robotic manufacturing system designed by the authors’ team. As a result, the relationship between the workpiece coordinate system and the end-effector coordinate system could be established accurately.</jats:p> </jats:sec> <jats:sec> <jats:title content-type="abstract-subheading">Practical implications</jats:title> <jats:p>This approach can quickly and accurately establish the relationship between the coordinate system of the workpiece and that of the end-effector. The normal alignment accuracy of the hand-eye vision system was less than 0.5° and the spatial positioning accuracy could reach 0.5 mm.</jats:p> </jats:sec> <jats:sec> <jats:title content-type="abstract-subheading">Originality/value</jats:title> <jats:p>This approach can achieve normal alignment for arbitrary planes and spatial positioning of the workpiece and it can quickly establish the pose relationship between the workpiece and end-effector coordinate systems. Moreover, the proposed approach can significantly improve the work efficiency, flexibility and intelligence of mobile robotic manufacturing systems.</jats:p> </jats:sec>

Research on visual recognition and positioning of industrial robots based on big data technology

“…However, with the strategies of "Industry 4.0" and "Made in China 2025" being proposed one after another, the research of robot vision technology in China has gradually entered the right track, and several robot manufacturers and domestic research institutes have already started to explore this technology [12][13]. The literature [14] combined the SIFT operator to characterize the features and selected SVM as a classifier to perform an exhaustive search in the position and scale space to determine the size and position of the target in the image. The literature [15] obtained the gradient direction histogram by calculating the gradient variation of each pixel point in the statistical image and the edge variation trend, which constitutes the final overall feature description.…”

Extended Kalman Filter Calibration Method Based on Lightweight Robotic Arm

“…In [2], a unit octet hand-eye calibration algorithm is also put forward. In [3], calibration method is presented which is based on the vision system consisting of camera and laser sensors. All of the above achieve high-precision calibration effects through high-precision measuring devices.…”

“…However, lightweight robotic arm for simple tasks often do not require excessive calibration accuracy, and it is not cost-effective to use high-precision sensors. As pointed out in [4,5], the extended-Kalman-filter-based method can not only estimate the visual calibration parameters, but also possesses relatively low computational complexity compared with [1][2][3]. It can be applied to the calibration of lightweight robotic arms.…”