Industrial part localization and grasping using a robotic arm guided by 2D monocular vision

2018 ◽  
Vol 45 (6) ◽  
pp. 794-804 ◽  
Author(s):  
Zhaohui Zheng ◽  
Yong Ma ◽  
Hong Zheng ◽  
Yu Gu ◽  
Mingyu Lin
Keyword(s):  
Camera Calibration ◽  
High Precision ◽  
Calibration Method ◽  
Monocular Vision ◽  
Robotic Arm ◽  
Robot Arm ◽  
Content Type ◽  
Calibration Algorithm ◽  
Target Locating ◽  
Practical Implications

Purpose The welding areas of the workpiece must be consistent with high precision to ensure the welding success during the welding of automobile parts. The purpose of this paper is to design an automatic high-precision locating and grasping system for robotic arm guided by 2D monocular vision to meet the requirements of automatic operation and high-precision welding. Design/methodology/approach A nonlinear multi-parallel surface calibration method based on adaptive k-segment master curve algorithm is proposed, which improves the efficiency of the traditional single camera calibration algorithm and accuracy of calibration. At the same time, the multi-dimension feature of target based on k-mean clustering constraint is proposed to improve the robustness and precision of registration. Findings A method of automatic locating and grasping based on 2D monocular vision is provided for robot arm, which includes camera calibration method and target locating method. Practical implications The system has been integrated into the welding robot of an automobile company in China. Originality/value A method of automatic locating and grasping based on 2D monocular vision is proposed, which makes the robot arm have automatic grasping function, and improves the efficiency and precision of automatic grasp of robot arm.

Camera Calibration Method Based on Circle Plane Board

2013 ◽  
Vol 475-476 ◽  
pp. 184-187
Author(s):  
Wen Guo Li ◽  
Shao Jun Duan
Keyword(s):  
Camera Calibration ◽  
Calibration Method ◽  
Lens Distortion ◽  
Edge Extraction ◽  
Circle Plane ◽  
Circle Centre ◽  
Extraction Algorithm ◽  
Calibration Algorithm ◽  
Characteristic Points ◽  
Distortion Parameters

We present a camera calibration method based on circle plane board. The centres of circles on plane are regarded as the characteristic points, which are used to implement camera calibration. The proposed calibration is more accurate than many previous calibration algorithm because of the merit of the coordinate of circle centre being obtained from thousand of of edge pionts of ellipse, which is very reliable to image noise caused by edge extraction algorithm. Experiments shows the proposed algorithm can obtain high precise inner parameters, and lens distortion parameters.

The vibratory alignment of the parts in robotic assembly

2017 ◽  
Vol 44 (6) ◽  
pp. 720-729 ◽  
Author(s):  
Bronius Baksys ◽  
Jolanta Baskutiene ◽  
Saulius Baskutis
Keyword(s):  
Design Methodology ◽  
Robotic Assembly ◽  
Mathematical Approach ◽  
Robot Arm ◽  
Content Type ◽  
Pressing Force ◽  
Passive Compliance ◽  
Alignment Process ◽  
Assembly Operations ◽  
Practical Implications

Purpose This paper aims to consider the experimental and theoretical investigation of the vibratory alignment of the peg-hole, when the peg is fixed in the remote centre compliance (RCC) device, and the vibrations are provided either to the hole or to the peg. Design/methodology/approach The experimental analysis of the circular and rectangular peg-hole vibratory alignment using the attached to the robot arm RCC device, under vibratory excitation of the hole, has been performed. The parameters of the vibratory excitation and the part-to-part pressing force influence on the alignment process have been analysed. The mathematical approach of the vibratory alignment using the passive compliance device with the vibrations provided to the peg has been proposed, and the simulation has been carried out. Findings The research has approved the applicability of the RCC device for both of the vibratory alignments of the non-chamfered peg-hole parts either circular or rectangular ones. The compensation of the axial misalignments has been resulted by the directional displacement of the peg supported compliantly. To perform the successful alignment of the parts, it has been necessary to adjust the frequency and the amplitude of the vibrations, the pressing force, the lateral, as well as the angular stiffness of the device. Research limitations/implications The experiments on the vibratory alignment of the rectangular peg-hole parts have been carried out considering only the translational misalignment moved into one direction. The non-impact regime of the vibratory alignment has been analysed. Practical implications The obtained results can be applied in designing the reliable and efficient devices of the vibratory assembly for the alignment of the non-chamfered peg-hole parts, as well as for chamfered ones, if the axial misalignment exceeds the width of the chamfer. The vibratory technique and passive compliance provide possibility to accomplish the assembly operations using the non-expensive low accuracy robots. Originality/value The new method and the mathematical approach of the vibratory assembly using the RCC device can ensure the reliable alignment of the non-chamfered parts, chamfered circular and the rectangular ones, in case the axial misalignment exceeds the assembly clearance, and prevent jamming and wedging.

Camera Calibration Method Based on Halcon

2013 ◽  
Vol 385-386 ◽  
pp. 518-522
Author(s):  
Zhi Xian Zhang ◽  
Li Liang ◽  
Yong Deng
Keyword(s):  
Computer Vision ◽  
Camera Calibration ◽  
Ccd Camera ◽  
Calibration Method ◽  
Geometrical Model ◽  
Accuracy Analysis ◽  
Calibration Algorithm ◽  
Cross Platform ◽  
Computation Speed

Aiming at the applications of computer vision,a nonlinear image geometrical model for array CCD camera was build and the interior parameters and exterior parameters as well were analyzed.By applying Halcon calibration board with circular targets plane of matrix gridding type and functions library,a camera calibration algorithm and accuracy analysis were given.Experiments indicated that the parameters were accurate and this method is simple and it improves the calibration precision and computation speed, and has a good cross-platform portability.

scholarly journals Monocular Vision Ranging and Camera Focal Length Calibration

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Lixia Xue ◽  
Meian Li ◽  
Liang Fan ◽  
Aixia Sun ◽  
Tian Gao
Keyword(s):  
Camera Calibration ◽  
Polynomial Regression ◽  
Focal Length ◽  
Three Dimensional ◽  
Calibration Method ◽  
Monocular Vision ◽  
Field Of Vision ◽  
Average Accuracy ◽  
Ground Object ◽  
The Relationship

The camera calibration in monocular vision represents the relationship between the pixels’ units which is obtained from a camera and the object in the real world. As an essential procedure, camera calibration calculates the three-dimensional geometric information from the captured two-dimensional images. Therefore, a modified camera calibration method based on polynomial regression is proposed to simplify. In this method, a parameter vector is obtained by pixel coordinates of obstacles and corresponding distance values using polynomial regression. The set of parameter’s vectors can measure the distance between the camera and the ground object in the field of vision under the camera’s posture and position. The experimental results show that the lowest accuracy of this focal length calibration method for measurement is 97.09%, and the average accuracy was 99.02%.

The Projector Calibration Based on ZHANG’s Self-Calibration Method

2014 ◽  
Vol 981 ◽  
pp. 364-367
Author(s):  
Guang Yu ◽  
Bo Yang Yu ◽  
Shu Cai Yang ◽  
Li Wen ◽  
Wen Fei Dong ◽  
...  
Keyword(s):  
Camera Calibration ◽  
Dimensional Space ◽  
Three Dimensional ◽  
Calibration Method ◽  
Linear Calibration ◽  
Self Calibration ◽  
Operation Process ◽  
Projector Calibration ◽  
Calibration Algorithm ◽  
Relationship Of

Projector calibration can be seen as a special case of the camera calibration. It can establish the relationship of the three dimensional space coordinates for points and projector image coordinates for points DMD by using a projector to project coding pattern. In camera calibration, ZHANG’s self-calibration was conducted in the maximum likelihood linear refinement. Operation process takes the lens distortion factors into account finding out the camera internal and external parameters finally. Using this algorithm to the projector calibration can solve the traditional linear calibration algorithm which is complex and poor robustness. Otherwise, it can improve the practicability of calibration method. This method can both calibrate the internal and external parameters of projector, which can solve the problem of independently inside or outside calibration.

Auto-Calibration for Vision-Based 6-D Sensing System to Support Monitoring and Health Management for Industrial Robots

2021 ◽  
Author(s):  
Guixiu Qiao ◽  
Guangkun Li
Keyword(s):  
High Precision ◽  
Health Management ◽  
Calibration Method ◽  
Industrial Robots ◽  
Smart Manufacturing ◽  
Robot Arm ◽  
Sensing System ◽  
Robot Accuracy ◽  
Robot Machining ◽  
Machining Robot

Abstract Industrial robots play important roles in manufacturing automation for smart manufacturing. Some high-precision applications, for example, robot drilling, robot machining, robot high-precision assembly, and robot inspection, require higher robot accuracy compared with traditional part handling operations. The monitoring and assessment of robot accuracy degradation become critical for these applications. A novel vision-based sensing system for 6-D measurement (six-dimensional x, y, z, yaw, pitch, and roll) is developed at the National Institute of Standards and Technology (NIST) to measure the dynamic high accuracy movement of a robot arm. The measured 6-D information is used for robot accuracy degradation assessment and improvement. This paper presents an automatic calibration method for a vision-based 6-D sensing system. The stereo calibration is separated from the distortion calibration to speed up the on-site adjustment. Optimization algorithms are developed to achieve high calibration accuracy. The vision-based 6-D sensing system is used on a Universal Robots (UR5) to demonstrate the feasibility of using the system to assess the robot’s accuracy degradation.

Camera Calibration Method Based on Vanishing Point

2014 ◽  
Vol 513-517 ◽  
pp. 3719-3722
Author(s):  
Wen Guo Li ◽  
Shao Jun Duan
Keyword(s):  
Camera Calibration ◽  
Calibration Method ◽  
Experimental Results ◽  
Vanishing Point ◽  
Feature Points ◽  
Vanishing Points ◽  
Parallel Lines ◽  
Internal Parameters ◽  
The Matrix ◽  
Calibration Algorithm

We present a camera calibration method based on vanishing point, that is, the vanishing points of two groups of parallel lines on the target plane are used to achieve camera calibration. A series of known positions points on target plane are used as the feature points, and the target images are recorded, the image coordinates of feature points are used to calculate the coordinates of vanishing point, then the matrix between feature points and camera is used to obtain internal parameters of camera. Experimental results show that the proposed calibration algorithm is correct, simple and convenient.

A novel data glove using inertial and magnetic sensors for motion capture and robotic arm-hand teleoperation

2017 ◽  
Vol 44 (2) ◽  
pp. 155-165 ◽  
Author(s):  
Bin Fang ◽  
Fuchun Sun ◽  
Huaping Liu ◽  
Di Guo
Keyword(s):  
Motion Capture ◽  
Low Cost ◽  
Magnetic Measurement ◽  
Calibration Method ◽  
Magnetic Sensors ◽  
Robotic Arm ◽  
Input Device ◽  
Content Type ◽  
Data Glove ◽  
Accuracy Of Measurements

Purpose The purpose of this paper is to present a novel data glove which can capture the motion of the arm and hand by inertial and magnetic sensors. The proposed data glove is used to provide the information of the gestures and teleoperate the robotic arm-hand. Design/methodology/approach The data glove comprises 18 low-cost inertial and magnetic measurement units (IMMUs) which not only make up the drawbacks of traditional data glove that only captures the incomplete gesture information but also provide a novel scheme of the robotic arm-hand teleoperation. The IMMUs are compact and small enough to wear on the upper arm, forearm, palm and fingers. The calibration method is proposed to improve the accuracy of measurements of units, and the orientations of each IMMU are estimated by a two-step optimal filter. The kinematic models of the arm, hand and fingers are integrated into the entire system to capture the motion gesture. A positon algorithm is also deduced to compute the positions of fingertips. With the proposed data glove, the robotic arm-hand can be teleoperated by the human arm, palm and fingers, thus establishing a novel robotic arm-hand teleoperation scheme. Findings Experimental results show that the proposed data glove can accurately and fully capture the fine gesture. Using the proposed data glove as the multiple input device has also proved to be a suitable teleoperating robotic arm-hand system. Originality/value Integrated with 18 low-cost and miniature IMMUs, the proposed data glove can give more information of the gesture than existing devices. Meanwhile, the proposed algorithms for motion capture determine the superior results. Furthermore, the accurately captured gestures can efficiently facilitate a novel teleoperation scheme to teleoperate the robotic arm-hand.

Sign in / Sign up

Export Citation Format

Share Document