Device and method for automatically grasping and placing planar objects based on visual positioning

Abstract

The present invention provides a device and method for automatically grasping and placing planar objects based on visual positioning, comprising a conveyor belt, a computer display screen, an area array CCD, an LED light source, a ring encoder, a support frame, a robot, a robot control cabinet, a placement table, and a control box. The control box contains a computer host, a power supply, and the like. The computer host displays the image captured by the area array CCD camera on the computer display screen in real time. The captured image is subjected to camera calibration, image processing, and planar object positioning using an algorithm program written in C++ to obtain the spatial coordinates of the center of the planar object. The value of the ring encoder is simultaneously read and sent to a host computer for processing. The algorithm then tracks the movement of the planar object on the conveyor belt and calculates the position coordinates of the center point of the planar object, which are fed back to the robot control cabinet, which then guides the robot to grasp the planar object. The present invention has a reasonable design, high efficiency, and high precision, and can grasp and place planar objects on the conveyor belt in real time.

Description

Technical Field

[0001] The present invention relates to the field of machine vision and robotics technology, and in particular to a device and method for automatically grasping and placing planar objects based on visual positioning. Background Art

[0002] The assembly line handling of flat objects is a crucial component of industrial production. During the handling process, the objects must be neatly arranged. Traditionally, this arrangement is manual. However, with the booming manufacturing industry, the manufacturing capabilities of modern factories have greatly increased, and manual arrangement is no longer sufficient to meet the demands of automated production. Furthermore, long-term work can cause eye fatigue and affect placement accuracy. With the continued maturity of machine vision inspection theories and algorithms, and the continuous improvement of hardware facilities such as high-pixel industrial cameras and lenses, it has become possible to replace traditional manual operations with automated positioning and placement. By leveraging the spatial perception capabilities of machine vision and the spatial handling capabilities of robots, it is possible to automatically grasp and place flat objects. This relieves workers of burdens, improves the accuracy of flat object placement, and significantly increases efficiency. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a device and method for automatically grasping and placing planar objects based on visual positioning to solve the problems listed above. The present invention has a reasonable design, complete functions, is easy and reliable to use, and has high precision and high efficiency.

[0004] A device for automatically grasping and placing planar objects based on visual positioning, comprising a conveying device 1, a computer display screen 2, an array CCD 3, an LED strip light source 4, a ring encoder 5, a device support frame 6, a robot 7, a robot control cabinet 8, a placement table 9, a control box 10 and a base 11. The device support frame 6 is a rectangular frame member, comprising a vertically arranged fixed frame, the lower end of the fixed frame is fixed on the base 11, and the upper end of the fixed frame is provided with a first crossbeam 61, a second crossbeam 62 and a third crossbeam 63, which are convenient for installing other components. The conveying device 1 is installed on the base, and a part is arranged in the device support frame 6, and the other part is located outside the device support frame 6, and is arranged along the length direction of the lower surface of the rectangular parallelepiped; the conveying device 1 has a conveyor belt 12, and the conveyor belt 12 also extends along the longitudinal direction of the lower surface of the rectangular parallelepiped. It is arranged along the length direction of the lower surface of the cuboid, the first beam 61 is located on the width of the other part of the upper surface of the cuboid close to the conveying device 1, the second beam 62 is located on the long side of the upper surface of the cuboid, and the two ends of the third beam 63 are respectively fixed on the two widths of the upper surface of the cuboid. The control box 10 includes a computer host and a power supply; the robot 7 is installed directly above the conveyor belt 12 and is fixed on the third beam 63 of the device support frame 6; the computer display screen 2 is fixed on the second beam 62 of the device support frame 6; the annular encoder 5 is on one side of the conveyor belt 12, on the same side as the second beam 62, and records the value of the annular encoder 5 in real time and feeds back the value to the upper computer for processing. The display table 9 is on the other side of the conveyor belt 12.

[0005] Furthermore, the area array CCD3 is installed directly above the conveyor belt 12 and is fixed on the first crossbeam 61 of the device support frame 6 .

[0006] Furthermore, the LED strip light sources 4 are symmetrically distributed on both sides of the conveyor belt 12 and installed at a 45-degree angle. The length of the strip light sources is 1.5 to 2 times the length of the planar object to be grasped, and assists the area array CCD3 in shooting and lighting.

[0007] Furthermore, the control box 10 is below the conveyor belt 12, and the computer host in the control box 10 is connected to the area array CCD 3 and the robot control cabinet 8 respectively.

[0008] Furthermore, the robot control cabinet 8 and the control box 10 are placed side by side and connected to the robot 7 .

[0009] Furthermore, the robot 7 is used to receive instructions from the host computer and then grab the planar objects on the conveyor belt 12.

[0010] Furthermore, the host computer in the control box 10 is connected to the image acquisition card of the area array CCD3, and processes the image information in real time through the host computer and sends instructions to the robot control cabinet 8.

[0011] A method for automatically grasping and placing planar objects based on visual positioning includes the following steps:

[0012] S1: Turn on the area array CCD3, LED strip light source 4, ring encoder 5 and robot control power supply. The area array CCD3 collects the calibration image for camera calibration to obtain the calibration matrix M.

[0013] S2: Read the value m1 of the ring encoder 5, turn on the conveyor belt 12 and move the distance D, read the value m2 of the ring encoder 5 at this time, and calculate the encoder coefficient S by (m2-m1) / D. The moving distance D of the conveyor belt 12 is 15 cm to 20 cm;

[0014] S3: Turn on the conveyor belt 12, and the area array CCD3 collects images in real time. When a planar object enters the recognition area of ​​the area array CCD3, the planar object is located using an algorithm written in C++, and the pixel coordinates of the center of the planar object are obtained. The pixel coordinates are converted to world coordinates (x, y) using the calibration matrix M;

[0015] S4: Read the value m of the ring encoder 5 in real time, and use (m-m1)*S+x to track the motion of the plane object in real time and calculate the position coordinates of the plane object. m1 is the value of the ring encoder 5 first read in step S2;

[0016] S5: The position coordinates of the planar object obtained in S4 are sent to the robot 7 in real time. When the planar object enters the grasping area of ​​the robot 7, the robot 7 grasps and places the planar object according to the coordinate values.

[0017] Furthermore, the calibration matrix M is as follows:

[0018]

[0019] Among them, u and v are the pixel coordinates of the calibration point image, X w , Y w , Z w The world coordinates of the calibration point.

[0020] The beneficial effects brought about by the technical solution provided by the present invention are:

[0021] (1) The present invention provides a device for grabbing and placing planar objects, which can grab and place planar objects on a conveyor belt with a relatively fast response speed and high placement accuracy, significantly improving placement efficiency, and has the advantages of fast placement speed and high placement accuracy;

[0022] (2) The planar object grabbing and placing device based on visual positioning described in the present invention also has the advantages of simple structure and easy operation;

[0023] (3) The device and method for grasping and placing planar objects based on visual positioning described in the present invention can adapt to various working environments, can still work stably under high temperature, dark conditions, etc., and can maintain high placement accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a structural diagram of a device and method for automatically grasping and placing planar objects based on visual positioning according to the present invention;

[0025] Figure 2 This is a flow chart of a device and method for automatically grabbing and placing planar objects based on visual positioning according to the present invention;

[0026] Figure 3 This is a side view structural diagram of a device and method for automatically grasping and placing planar objects based on visual positioning according to the present invention;

[0027] In the figure: 1-transmission device, 2-computer display screen, 3-area array CCD, 4-LED light source, 5-ring encoder, 6-device support frame, 61-first beam, 62-second beam, 63-third beam, 7-robot, 8-robot control cabinet, 9-display table, 10-control box, 11-base, 12-conveyor belt. DETAILED DESCRIPTION

[0028] To make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0029] Please refer to Figure 1 and Figure 3The present invention provides a device and method for automatically grasping and placing planar objects based on visual positioning. The device and method include a device for automatically grasping and placing planar objects based on visual positioning, including a conveyor 1, a computer display 2, a surface array CCD 3, an LED strip light source 4, a ring encoder 5, a device support frame 6, a robot 7, a robot control cabinet 8, a placement table 9, a control box 10 and a base 11. The device support frame 6 is a rectangular frame member, including a vertically arranged fixing frame, the lower end of the fixing frame is fixed on the base 11, and the upper end of the fixing frame is provided with a first crossbeam. 61, the second crossbeam 62 and the third crossbeam 63 are convenient for installing other components. The conveying device 1 is installed on the base, and a part is arranged in the device support frame 6, and the other part is located outside the device support frame 6, and is arranged along the length direction of the lower surface of the rectangular parallelepiped; the conveying device 1 has a conveyor belt 12, and the conveyor belt 12 is also arranged along the length direction of the lower surface of the rectangular parallelepiped. The first crossbeam 61 is located on the width of the other part of the upper surface of the rectangular parallelepiped close to the conveying device 1, the second crossbeam 62 is located on the long side of the upper surface of the rectangular parallelepiped, and the two ends of the third crossbeam 63 are respectively fixed on the two widths of the upper surface of the rectangular parallelepiped.

[0030] The control box 10 includes a computer host and a power supply; the robot 7 is installed directly above the conveyor belt 12 and fixed on the third beam 63 of the device support frame 6; the computer display screen 2 is fixed on the second beam 62 of the device support frame 6; the ring encoder 5 is on one side of the conveyor belt 12, on the same side as the second beam 62, and records the value of the ring encoder 5 in real time and feeds back the value to the host computer for processing. The display table 9 is on the other side of the conveyor belt 12.

[0031] The area array CCD3 is installed directly above the conveyor belt 12 and is fixed on the first crossbeam 61 of the device support frame 6 .

[0032] The LED strip light sources 4 are symmetrically distributed on both sides of the conveyor belt 12 and are installed at a 45-degree angle. The length of the strip light sources is 1.5 to 2 times the length of the planar object to be grasped, and assists the area array CCD 3 in shooting and lighting.

[0033] The display table 9 is located on the side of the conveyor belt 12 close to the robot 7; the control box 10 is located below the conveyor belt 12, and the computer host in the control box 10 is connected to the area array CCD3 and the robot control cabinet 8 respectively.

[0034] The robot control cabinet 8 and the control box 10 are placed side by side and connected to the robot 7 .

[0035] The robot 7 is used to receive instructions from a host computer and then grab the planar objects on the conveyor belt 12. In this embodiment, the host computer is client processing software on a computer.

[0036] The host computer in the control box 10 is connected to the image acquisition card of the area array CCD3, and processes the image information in real time through the host computer and sends instructions to the robot control cabinet 8.

[0037] The specific operation steps are as follows: First, turn on the power of the control box, and the conveyor device 1, the area array CCD3, the LED strip light source 4, the ring encoder 5, the robot body 7 and the robot control cabinet 8 start working. Place the flat object on the conveyor belt 12 and move it along the conveyor belt 12. When the flat object enters the shooting field of view of the area array CCD3, the computer host displays the image captured by the area array CCD3 in real time on the computer display 2. The collected image will also be sent to the host computer for processing to obtain the spatial coordinates of the center of the flat object. At the same time, the value of the ring encoder 5 is read in real time and sent to the host computer software for processing. Then, the host computer tracks the movement of the flat object on the conveyor belt 12 and calculates the position coordinates of the center point of the flat object and feeds them back to the robot control cabinet 8, guiding the robot 7 in real time to automatically grasp and place the flat object.

[0038] A method for automatically grasping and placing planar objects based on visual positioning, such as Figure 2 As shown, the following steps are included:

[0039] S1: Turn on the area array CCD3, LED strip light source 4, ring encoder 5 and robot control power supply. The area array CCD3 collects the calibration image for camera calibration and obtains the calibration matrix M as follows:

[0040]

[0041] Among them, u and v are the pixel coordinates of the calibration point image, X w , Y w , Z w The world coordinates of the calibration point.

[0042] During camera calibration, a checkerboard calibration plate is used. The plate is placed in the center of the area CCD3's field of view, with its X-axis and Y-axis parallel to the horizontal and vertical directions of the area CCD3's field of view, respectively. The captured calibration image should be clearly visible. To simplify the camera calibration process, this example uses a modified nine-point calibration method. Nine points on the checkerboard grid in the calibration image are randomly selected, and the actual coordinates of these nine points on the checkerboard grid are recorded for matrix calculation.

[0043] S2: Read the value m1 of the ring encoder 5, turn on the conveyor belt 12 and move the distance D, read the value m2 of the ring encoder 5 at this time, and calculate the encoder coefficient S by (m2-m1) / D. The moving distance D of the conveyor belt 12 is 15 cm to 20 cm;

[0044] S3: Turn on the conveyor belt 12, and the area array CCD3 collects images in real time. When a planar object enters the recognition area of ​​the area array CCD3, the planar object is located using an algorithm written in C++, and the pixel coordinates of the center of the planar object are obtained. The pixel coordinates are converted to world coordinates (x, y) using the calibration matrix M;

[0045] The recognition area of ​​the area array CCD 3 can be pre-set. The recognition area is set to be smaller than the shooting field of view of the area array CCD 3 and completely include the wide side of the conveyor belt 12. In this embodiment, the image processing algorithm can be threshold segmentation, contour extraction, etc. The specific image processing algorithm used is not limited to a unique embodiment of the present invention.

[0046] S4: Read the value m of the ring encoder 5 in real time, and use m-m1*S+x to track the motion of the plane object in real time and calculate the position coordinates of the plane object. m1 is the value of the ring encoder 5 first read in step S2;

[0047] S5: The position coordinates of the planar object obtained in S4 are sent to the robot 7 in real time. When the planar object enters the grasping area of ​​the robot 7, the robot 7 grasps and places the planar object according to the coordinate values.

[0048] In this step, the robot's gripping area can be pre-set. The gripping area is set to be smaller than the robot's maximum arm span. In addition, the gripping area completely includes the conveyor belt width. The robot's placement can be set arbitrarily.

[0049] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for automatically grabbing and placing planar objects based on visual positioning, characterized in that: The invention comprises an automatic grabbing and placing device for planar objects, the device comprising a conveying device (1), a computer display screen (2), a CCD array (3), an LED strip light source (4), a ring encoder (5), a device support frame (6), a robot (7), a robot control cabinet (8), a placing table (9), a control box (10) and a base (11). The device support frame (6) is a rectangular parallelepiped frame member, comprising a vertically arranged fixing frame, the lower end of the fixing frame being fixed on the base (11), and the upper end of the fixing frame being provided with a first crossbeam (61), a second crossbeam (62) and a third crossbeam (63) for facilitating the installation of other components. The conveying device (1) is installed on the base, and a part of it is arranged in the device support frame (6), and the other part is located outside the device support frame (6), and is arranged along the length direction of the lower surface of the rectangular parallelepiped; the conveying device (1) has a conveyor belt (12), and the conveyor belt (12) is also provided. The arrangement is carried out along the length direction of the lower surface of the rectangular parallelepiped, the first crossbeam (61) is located on the width of the other part of the upper surface of the rectangular parallelepiped close to the conveying device (1), the second crossbeam (62) is located on the long side of the upper surface of the rectangular parallelepiped, and the two ends of the third crossbeam (63) are respectively fixed on the two widths of the upper surface of the rectangular parallelepiped, and the control box (10) includes a computer host and a power supply; the robot (7) is installed directly above the conveyor belt (12) and is fixed on the third crossbeam (63) of the device support frame (6); the computer display screen (2) is fixed on the second crossbeam (62) of the device support frame (6); the ring encoder (5) is on one side of the conveyor belt (12) and on the same side as the second crossbeam (62), and records the value of the ring encoder (5) in real time and feeds back the value to the host computer for processing, and the display table (9) is on the other side of the conveyor belt (12); The method for automatically grabbing and placing planar objects comprises the following steps: S1: Turn on the area array CCD (3), LED strip light source (4), ring encoder (5) and robot control power supply, the area array CCD (3) collects the calibration image to perform camera calibration, and obtains the calibration matrix M; S2: Read the value m1 of the ring encoder (5), turn on the conveyor belt (12) and move the distance D, read the value m2 of the ring encoder (5) at this time, and calculate the encoder coefficient S by (m2-m1) / D. The moving distance D of the conveyor belt (12) is 15 cm to 20 cm; S3: Turn on the conveyor belt (12), and the area array CCD (3) collects images in real time. When a planar object enters the recognition area of ​​the area array CCD (3), the planar object is located using an algorithm written in C++, and the pixel coordinates of the center of the planar object are obtained. The pixel coordinates are converted to world coordinates (x, y) using the calibration matrix M. The calibration matrix M is as follows: in, u and v is the pixel coordinate of the calibration point image, X w , Y w , Z w is the world coordinate of the calibration point; S4: Read the value m of the ring encoder (5) in real time, and use (m-m1)*S+x to track the motion of the plane object in real time and calculate the position coordinates of the plane object. m1 is the value of the ring encoder (5) read for the first time in step S2; S5: The position coordinates of the planar object obtained in S4 are sent to the robot (7) in real time. When the planar object enters the grasping area of ​​the robot (7), the robot (7) grasps and places the planar object according to the coordinate values.

2. The method for automatically grabbing and placing planar objects based on visual positioning according to claim 1, characterized in that: The area array CCD (3) is installed directly above the conveyor belt (12) and is fixed on the first crossbeam (61) of the device support frame (6).

3. The method for automatically grabbing and placing planar objects based on visual positioning according to claim 1, characterized in that: The LED strip light sources (4) are symmetrically distributed on both sides of the conveyor belt (12) and are installed at a 45-degree angle. The length of the strip light sources is 1.5 to 2 times the length of the planar object to be grasped, and assists the area array CCD (3) in shooting and lighting.

4. The method for automatically grabbing and placing planar objects based on visual positioning according to claim 1, characterized in that: The control box (10) is located below the conveyor belt (12), and the computer host in the control box (10) is connected to the area array CCD (3) and the robot control cabinet (8) respectively.

5. The method for automatically grabbing and placing planar objects based on visual positioning according to claim 1, characterized in that: The robot control cabinet (8) and the control box (10) are placed side by side and connected to the robot (7).

6. The method for automatically grabbing and placing planar objects based on visual positioning according to claim 1, characterized in that: The robot (7) is used to receive instructions from a host computer and then grasp the planar objects on the conveyor belt (12).

7. The method for automatically grabbing and placing planar objects based on visual positioning according to claim 1, characterized in that: The computer host in the control box (10) is connected to the image acquisition card of the area array CCD (3), and processes the image information in real time through the host computer and sends instructions to the robot control cabinet (8).

Images