Mobile flexible docking platform, method and equipment based on visual guidance and storage medium

Abstract

The invention provides a movable flexible docking platform, method and equipment based on visual guidance and a storage medium, and relates to the field of automatic auxiliary assembly. The docking platform comprises an AGV trolley, a six-degree-of-freedom platform erected in the middle of the upper portion of the AGV trolley, and a binocular vision system erected on the rear side of the upper portion of the AGV trolley. The binocular vision system provides real-time vision guidance in the advancing process of the AGV; a butt joint workpiece A is placed on a six-degree-of-freedom platform, and a butt joint workpiece B which has an assembly relation with the butt joint workpiece A is placed on a working table at a target position; and the AGV transports the butt joint workpiece A to the target position, and butt joint of the butt joint workpiece A and the butt joint workpiece B is completed. According to the invention, the six-degree-of-freedom parallel platform is arranged on the AGV trolley, so that the pose fine adjustment of the assembled workpiece is realized, the pose of the workpiece can be continuously adjusted in the transportation process to keep balance, and the workpiece transportation and high-precision butt joint can be realized.

Description

Technical Field

[0001] The present invention relates to the field of automated auxiliary assembly, and in particular to a mobile flexible docking platform, method, device and storage medium based on visual guidance. Background Art

[0002] With the rapid development of the global economy, the manufacturing industry is facing growing market demand. The traditional manual assembly method is not only inefficient, but also difficult to ensure the consistency of product quality. In order to improve production efficiency, reduce costs and improve product quality, the manufacturing industry urgently needs an automated assembly solution, and assembly robots have become an ideal choice.

[0003] Assembly is an important part of the manufacturing industry. Nowadays, the assembly industry in the fields of aerospace, marine equipment, etc. generally uses a gantry to lift large objects to be assembled. The workers operate the controller through the installed slide rails to make the assembled objects reach the target position, and then perform manual assembly. There are some inevitable problems with this assembly method. Manual operation requires extremely high operating skills of workers, the process is relatively cumbersome, and there will always be large errors in manual operation. If the assembled object is too heavy, there may be certain dangers. Once the object falls, it will threaten the safety of the object and the worker. At the same time, the gantry requires a large space, high cost, and poor flexibility.

[0004] In order to improve the above situation, it is urgent to invent and design a mobile flexible docking platform with a large working range, high flexibility and low use cost. Summary of the invention

[0005] Purpose of the invention: In view of the deficiencies in the prior art, a mobile flexible docking platform based on vision guidance is provided, and further a flexible docking method for assembled workpieces is provided to solve the above-mentioned problems raised by the prior art.

[0006] The first aspect of the present invention proposes a mobile flexible docking platform based on vision guidance, including an AGV cart, a six-degree-of-freedom platform mounted at the middle position of the upper part of the AGV cart, and a binocular vision system mounted at the rear side position of the upper part of the AGV cart.

[0007] The bottom of the AGV is provided with two sets of driving wheels and a plurality of universal wheels; the two sets of driving wheels are distributed on both sides with the positive direction of the AGV as the central axis; each set of driving wheels is controlled separately, and the steering of the AGV is achieved by the differential speed of the two driving wheels;

[0008] The binocular vision system provides real-time visual guidance during the movement of the AGV;

[0009] The docking workpiece A is placed on a six-degree-of-freedom platform, and a docking workpiece B having an assembly relationship with the docking workpiece A is placed on the work surface at the target position;

[0010] The AGV trolley transports the docking workpiece A to the target position and completes the docking with the docking workpiece B; the person on duty at the work surface completes the subsequent assembly work of the docking workpiece A and the docking workpiece B.

[0011] In a further embodiment of the first aspect, the six-degree-of-freedom platform includes an upper platform, a lower platform, six electric cylinders, a horizontal Hooke's joint, and six servo motors;

[0012] Among them, the upper platform is a dynamic platform, used to carry the workpiece to be assembled; the lower platform is a static platform, fixed on the upper surface of the AGV trolley;

[0013] The upper platform and the lower platform are supported by an electric cylinder, and the upper and lower platforms and the electric cylinder are connected and fixed by a horizontal Hooke's hinge; one electric cylinder constitutes an independently moving motion unit, and six motion units are connected to the upper platform and the lower platform, with a total of six degrees of freedom;

[0014] The electric cylinder is driven by a servo motor, and the motor controls the lead screw inside the cylinder body to realize the extension and retraction of the electric cylinder. The six electric cylinders work together to realize the precise control of the lifting and lowering and other postures of the upper platform.

[0015] In a further embodiment of the first aspect, an inclined block is provided between the upper platform and the horizontal Hooke's joint for compensating for the rotation angle of the horizontal Hooke's joint.

[0016] In a further embodiment of the first aspect, the binocular vision system is installed at the upper end of the AGV cart, and includes two CCD cameras; the two CCD cameras are respectively fixed on both sides of the bracket with Y-shaped fixing plates; and a ring fill light is fixed at the front end of each CCD camera.

[0017] The second aspect of the present invention provides a method for flexible docking of assembly workpieces based on vision guidance, which is implemented based on the mobile flexible docking platform disclosed in the first aspect. The method for flexible docking of assembly workpieces includes the following steps:

[0018] Install and fix the docking workpiece A on the six-degree-of-freedom platform, and install and fix the docking workpiece B on the work surface at the target position;

[0019] Two QR codes with different ID numbers are attached to docking workpiece A and docking workpiece B. The conversion matrix between the coordinate system of the QR code and docking workpiece A is H1, and the conversion matrix between the coordinate system of the QR code and docking workpiece B is H2;

[0020] Two CCD cameras simultaneously recognize the QR code, and obtain the left CCD camera image and the right CCD camera image respectively; the four corner points of the QR code are used as feature points, and the pixel coordinates of four feature points are detected in each CCD camera image;

[0021] According to the position difference between the pixel coordinates of the feature points in the left CCD camera image and the pixel coordinates of the feature points in the right CCD camera image, the three-dimensional coordinates of the four feature points are calculated using the triangulation principle;

[0022] By integrating and analyzing the three-dimensional coordinates of the four feature points, the rigid body coordinate systems of docking workpiece A and docking workpiece B are obtained, which are

[0023] Guide the six-degree-of-freedom platform so that the rigid body coordinate system Overlap, thereby completing the docking of docking workpiece A and docking workpiece B.

[0024] In a further embodiment of the second aspect, the pixel coordinates of the feature point in the left CCD camera image are defined as (C ixl ,C iyl ); the pixel coordinates of the feature points in the CCD camera image on the right are defined as (C ixr ,C iyr );

[0025] Among them, i represents the serial number of the corner point; the subscript l represents the pixel coordinates of the left CCD camera image; the subscript r represents the pixel coordinates of the same corner point in the right CCD camera image.

[0026] In a further embodiment of the second aspect, the process of calculating the three-dimensional coordinates of the four feature points using the triangulation principle specifically includes:

[0027] Define the baseline distance between the two CCD cameras as T, the focal length of the camera as f, and the distance from the left edge of the image plane of the left CCD camera and the right CCD camera to the projection position of the corner point i as x l and x r ; Parallax d of corner point i i =x l ―x r ; Define the pixel coordinates of the center point of the left CCD camera as (o x ,o y );

[0028] The coordinate value of corner point i in the binocular vision reference coordinate system is calculated according to the following formula:

[0029]

[0030] In the formula, (c ix* ,c iy*) is the pixel coordinate of the corner point, * is l or r, corresponding to the pixel coordinate of the feature point in the left CCD camera image or the pixel coordinate of the feature point in the right CCD camera image, respectively.

[0031] In a further embodiment of the second aspect, the rigid body coordinate system of the docking workpiece A and the docking workpiece B is obtained by integrating and analyzing the three-dimensional coordinates of the four feature points, specifically including:

[0032] Fit the spatial plane Ax+By+Cz+D=0 according to the coordinates of the four corner points, thereby obtaining the normal vector of the spatial plane as the Z-axis direction vector;

[0033] Project the coordinates of the four corner points to the fitted spatial plane Ax+By+Cz+D=0, and select the direction vector between the projection coordinates of the first corner point and the projection coordinates of the second corner point as the X-axis; the direction vector of the Y-axis is calculated by the cross product of the X-axis and the Z-axis;

[0034] Select the non-projected coordinates of the first corner point as the coordinate origin to construct coordinate system T1. Similarly, obtain the coordinate system T2 of another QR code.

[0035] Combining the coordinate system of the QR code with the transformation matrices H1 and H2 of the contact surface of the docking workpieces, the rigid body coordinate system of the two docking workpieces is calculated as follows: and

[0036] If the two docking workpieces are docked, guide the six-degree-of-freedom platform to work, and the guiding target is the rigid body coordinate system T1 and coincide.

[0037] The mobile flexible docking platform based on vision guidance disclosed in the first aspect and the flexible docking method for assembled workpieces disclosed in the second aspect can be applied to industrial assembly links with high precision requirements.

[0038] According to a third aspect of the present invention, an electronic device is provided, comprising a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the method for flexible docking of assembly workpieces based on vision guidance disclosed in the first aspect and its further embodiments is implemented.

[0039] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, which stores at least one executable instruction. When the executable instruction is executed on an electronic device, the electronic device executes the method for flexible docking of assembly workpieces based on vision guidance disclosed in the first aspect and its further embodiments.

[0040] Beneficial effects: The present invention discloses a mobile flexible docking platform based on visual guidance, which uses an AGV trolley to realize the transfer of workpieces and uses binocular vision for real-time calibration of workpiece docking. By equipping the AGV trolley with a six-degree-of-freedom parallel platform, the position and posture of the assembled workpiece can be fine-tuned. During transportation, the posture of the object can be continuously adjusted to maintain balance, and the binocular vision system can realize the positioning of the object. The present invention can realize large-scale transportation and high-precision assembly of industrial assembly. At the same time, the device also has the advantages of simple operation and low cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is an overall schematic diagram of a mobile flexible docking platform in an embodiment of the present invention.

[0042] Figure 2 It is a bottom structural diagram of the AGV trolley of the present invention.

[0043] Figure 3 It is an upper side view of the AGV trolley of the present invention.

[0044] Figure 4 It is a structural diagram of the Stewart six-degree-of-freedom parallel platform of the present invention.

[0045] Figure 5 It is a structural diagram of the binocular vision system of the present invention.

[0046] The reference numerals in the figure are: AGV trolley 1, trolley bottom plate 100, A driving wheel 101, B driving wheel 102, navigation device 103, A universal wheel 104, B universal wheel 105, C universal wheel 106, D universal wheel 107, display screen 108, fixing device 109, buzzer 110, manual / automatic switch 111, start button 112, binocular vision system installation area 113, emergency stop button 114, custom button 115, A warning light 116, B warning light 117, C warning light 118, D warning light 1 19. Six-degree-of-freedom platform 2. upper platform 201. lower platform 202. horizontal Hook hinge 203. servo motor 204. A electric cylinder 205. B electric cylinder 206. C electric cylinder 207. D electric cylinder 208. E electric cylinder 209. F electric cylinder 210. binocular vision system 3. left CCD camera 301. right CCD camera 302. left annular fill light 303. right annular fill light 304. left Y-shaped bracket 305. right Y-shaped bracket 306. cross bar 307. main bracket 308. fixed bottom plate 309. DETAILED DESCRIPTION

[0047] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features known in the art are not described.

[0048] Embodiment 1:

[0049] Figure 1 The overall structure of the mobile flexible docking platform disclosed in this embodiment is shown. The flexible docking platform mainly includes an AGV trolley 1, a line patrol device, a binocular vision system 3 and a six-degree-of-freedom platform 2. The AGV trolley 1 has two electric drive wheels in the middle to provide power and four universal wheels in the front and back to provide support. Five line patrol sensors are installed at the bottom of the front side of the AGV trolley 1 to control the forward direction of the AGV trolley 1 to ensure that it moves along the predetermined trajectory. The trolley realizes the steering of the trolley through the differential speed of the two power wheels. During the assembly process, the AGV trolley 1 is mainly responsible for delivering the object from the starting point to the target position.

[0050] The six-degree-of-freedom platform 2 is fixed in the middle of the AGV trolley 1, and is composed of an upper platform 201, a lower platform 202, six electric cylinders, a horizontal Hook's hinge 203, and six servo motors 204. Among them, the upper platform 201 is a dynamic platform for carrying the workpiece to be assembled; the lower platform 202 is a static platform, fixed on the upper surface of the AGV trolley 1; the upper platform 201 and the lower platform 202 are supported by electric cylinders, and the upper and lower platforms 202 and the electric cylinders are connected and fixed by horizontal Hook's hinges 203. In order to compensate for the insufficient rotation angle of the horizontal Hook's hinge 203 of the upper platform 201, an inclined block is placed between the upper platform 201 and the horizontal Hook's hinge 203. One electric cylinder constitutes an independently moving motion unit, and the six motion units are connected to the upper and lower platforms 202 by bolts, with a total of six degrees of freedom; the electric cylinder is driven by a servo motor 204, and the motor realizes the extension and retraction of the electric cylinder by controlling the screw rod inside the cylinder body. The six electric cylinders can cooperate at the same time to achieve precise control of the lifting and lowering and other postures of the upper platform 201. After the AGV 1 moves to the target point, the six-degree-of-freedom platform 2 controls the posture of the assembled workpiece to achieve precise docking.

[0051] The binocular vision system 3 is installed at the end of the upper surface of the AGV trolley 1 and fixed by a bracket. Two annular fill lights are fixed in front of the camera to supplement the lack of ambient light. Two CCD cameras are fixed on both sides of the bracket with Y-shaped fixing plates respectively, and the annular fill light is fixed in front of the camera through a Y-shaped bracket so that the camera lens is just in the middle of the ring.

[0052] Embodiment 2:

[0053] See Figures 2 to 5 , the mobile flexible docking platform disclosed in this embodiment is specifically described below.

[0054] The visually guided mobile flexible docking platform consists of three parts, namely, the AGV 1, the Stewart six-degree-of-freedom platform 2 and the binocular vision system 3. The AGV 1 is used as a movable chassis for long-distance transportation. The bottom structure of the AGV 1 is shown in Figure 2 As shown (the end equipped with the line patrol sensor is the front side of the AGV trolley 1, and the other side is the tail of the trolley), after the trolley bottom plate 100 is installed, it can prevent the wires inside the trolley from leaking out and tripping during the operation of the trolley, and also make the trolley look neater; the two middle electric drive wheels (A drive wheel 101, B drive wheel 102) provide the AGV trolley 1 with power for moving forward, backward and turning, and the front and rear two universal wheels (A universal wheel 104, B universal wheel 105, C universal wheel 106, D universal wheel 107) provide support for it to maintain the balance of the AGV trolley 1. The navigation device of the car consists of five infrared line-following sensors installed on the middle front side of the two universal wheels at the front. The signals received by the line-following sensors are transmitted to the computer of the car through the RS485 bus. After calculation, the computer sends a rotation speed signal to the power wheel. If the signals with the same direction and speed are sent to the two power wheels, the car can move forward and backward. If the signals with opposite directions but the same speed are sent, the car can turn on the spot. If the two wheels have the same direction but different speeds, turning can be achieved during the forward and backward process.

[0055] See also Figure 1 , the Stewart six-degree-of-freedom platform 2 is installed on the AGV trolley 1 and fixed to the trolley by screws. Figure 4The Stewart six-degree-of-freedom platform 2 is composed of an upper platform 201, a lower platform 202, six electric cylinders (see A electric cylinder 205, B electric cylinder 206, C electric cylinder 207, D electric cylinder 208, E electric cylinder 209, F electric cylinder 210 in the figure) and a horizontal Hook's hinge 203. The upper platform 201 is a dynamic platform, and the assembled objects are placed on the dynamic platform during transportation. The lower platform 202 is a static platform. The Stewart six-degree-of-freedom platform 2 is fixed to the AGV trolley 1 through the static platform. The dynamic platform and the static platform are supported and connected by electric cylinders and Hook's hinges. Six horizontal Hook's hinges 203 are fixed on the surface of the upper platform 201 and the lower platform 202. The electric cylinder supports the upper platform 201 by connecting with the front section of the horizontal Hook's hinge 203. The driving device of the electric cylinder is a 4.4kW servo motor 204. The servo motor 204 controls the lead screw inside the electric cylinder to realize the extension and retraction of the electric cylinder. The six electric cylinders are combined in a "W-shape" to form a six-degree-of-freedom platform. The six electric cylinders realize the posture control of the upper platform 201 by cooperating with the extension and retraction to maintain the balance of the assembled objects and to fine-tune their posture during assembly. If the horizontal Hooke's hinge 203 of the upper platform 201 is directly installed on the upper platform 201, the platform will not be able to descend. Therefore, an inclined block is added between the upper platform 201 and the horizontal Hooke's hinge 203 to compensate for the rotation angle of the Hooke's hinge.

[0056] See also Figure 3 , which is an upper side observation view of the AGV trolley 1, it can be seen that the AGV trolley 1 is provided with a display screen 108, a fixing device 109, a buzzer 110, a manual / automatic switch 111, a start button 112, an emergency stop button 114, a custom button 115, and a number of warning lights on both sides.

[0057] Some specific configuration operations can be performed on the trolley on the display screen 108. When the trolley encounters special situations during its advancement, a buzzer 110 will sound to alert the staff; the manual / automatic switch 111 of the trolley can be switched to manual when manual operation is required; when a special situation requires immediate parking, pressing the emergency stop button 114 can stop the trolley immediately; the function of the button can be defined on the display screen 108 through the custom button 115; the binocular vision system 3 is fixed through two screw holes on the surface of the binocular vision system 3 installation area 113; the A warning light 116, the B warning light 117, the C warning light 118, and the D warning light 119 will flash throughout the operation of the trolley.

[0058] See also Figure 5, the binocular vision system 3 is installed at the tail of the AGV trolley 1. The binocular vision system 3 consists of a left CCD camera 301, a right CCD camera 302, a left annular fill light 303, a right annular fill light 304, a left Y-shaped bracket 305, a right Y-shaped bracket 306, a crossbar 307, a main bracket 308, and a fixed bottom plate 309. The three-dimensional spatial position of the object is identified by two groups of CCD cameras. During assembly, the binocular vision system 3 is responsible for positioning the object. The annular fill light is used to fill light when the ambient light is insufficient to avoid the situation where the object features cannot be measured. The fill light is installed at the front end of the Y-shaped bracket and the end of the bracket is installed on the crossbar 307. The CCD camera is installed on the Y-shaped bracket, and the crossbar 307 is installed on the main bracket 308. Finally, the main bracket 308 is fixed to the tail of the AGV trolley 1 with screws.

[0059] Embodiment 3:

[0060] The present embodiment discloses a method for flexible docking of assembly workpieces based on vision guidance, and the method is proposed on the basis of the structure of the mobile flexible docking platform disclosed in the above-mentioned embodiment 1 and / or embodiment 2. First, a CCD camera is used to extract features of the two images to find corresponding feature points. Then, according to the position difference of the feature points in the two images, the three-dimensional coordinates of the feature points are calculated using the triangulation principle. Finally, by integrating and analyzing the three-dimensional coordinates of multiple feature points, the rigid coordinate system of the two docking workpieces can be obtained. The six-degree-of-freedom platform 2 is guided so that the rigid coordinate systems of the two docking workpieces coincide, thereby completing the docking of the workpieces.

[0061] The following embodiment discloses a feasible solution for extracting features from two images using a CCD camera. It should be emphasized that the following solution is only one of the feasible solutions and does not represent a limitation of this patent.

[0062] Step 1: Fix the docking workpiece through AGV trolley 1 and Stewart six-degree-of-freedom platform 2, and fix another docking workpiece on the worktable.

[0063] Step 2: By fixing two QR codes with different ID numbers on the contact surface of the docking workpieces, the coordinate system of the QR code and the transformation matrix of the contact surface of the docking workpieces can be obtained through equipment such as a laser tracker, and the transformation matrices are defined as H1 and H2 respectively.

[0064] Step 3: Use two CCD cameras to identify the QR code, detect the four corner points of the QR code through the edge detection algorithm, and obtain the pixel coordinates of the four corner points. The coordinates are defined as (c ixl , c iyl), where i represents the serial number of the corner point, and the coordinates are based on the upper left corner of the image as the reference zero point. The subscript l represents the pixel coordinates of the image of the left CCD camera 301, and the subscript r represents the pixel coordinates of the same corner point in the image of the right CCD camera 302, that is, (c ixr , c iyr ).

[0065] Step 4: According to the definitions in steps 2 and 3, the corner coordinates of two QR codes with different ID numbers are defined as (c ix* , c iy* ) and (d ix* , d iy* ), where * represents l or r.

[0066] The following embodiment discloses a feasible solution for calculating the three-dimensional coordinates of feature points using the triangulation principle. It should be emphasized that the following solution is only one of the feasible solutions and does not represent a limitation of this patent.

[0067] Step 1: Define the baseline distance between the two CCD cameras as T, the focal length of the camera as f, and the pixel coordinates of the corner point i on the left and right cameras as (c ixl , c iyl ) and (c ixr , c iyr ), the distances from the left edge of the image plane of the left and right CCD cameras 302 to the projection position of the corner point i are x l and x r , then the disparity d of corner point i i =x l -x r The pixel coordinates of the center point of the left CCD camera 301 are defined as ( x , o y ).

[0068] Step 2: Based on the above definition, calculate the coordinate value of corner point i in the binocular vision reference coordinate system using the following formula:

[0069]

[0070] Similarly, the coordinate values ​​of other corner points of the QR code with the same ID number can be calculated. The coordinate values ​​of other corner points of the QR code with another ID number can also be calculated.

[0071] The following embodiment discloses a feasible solution for integrating and analyzing the three-dimensional coordinates of multiple feature points to obtain a rigid coordinate system of two docking workpieces. It should be emphasized that the following solution is only one of the feasible solutions and does not represent a limitation of this patent.

[0072] Step 1: Fit the spatial plane Ax+By+Cz+D=0 according to the coordinates of the four corner points; thereby obtaining the normal vector of the spatial plane as the Z-axis direction vector;

[0073] Step 2: Project the coordinates of the four corner points to the fitted spatial plane Ax+By+Cz+D=0, and select the direction vector between the projection coordinates of the first corner point and the projection coordinates of the second corner point as the X-axis; the direction vector of the Y-axis is calculated by the cross product of the X-axis and the Z-axis;

[0074] Step 3: Select the non-projected coordinates of the first corner point as the coordinate origin and construct the coordinate system T1. Similarly, the coordinate system T2 of another QR code can be obtained.

[0075] Step 4: Combining the coordinate system of the QR code with the transformation matrices H1 and H2 of the contact surface of the docking workpieces, the rigid body coordinate system of the two docking workpieces can be calculated as and

[0076] Step 5: If the two docking workpieces are docked, the Stewart six degrees of freedom will be guided so that the rigid body coordinate system of the two docking workpieces is and coincide.

[0077] The method for flexible docking of assembled workpieces based on vision guidance disclosed in the above embodiments may be implemented in whole or in part through software, hardware, firmware or any other combination thereof.

[0078] When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center containing one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0079] The above-mentioned method for flexible docking of assembly workpieces based on vision guidance can be embedded in an electronic device for operation. The electronic device includes a processor, a memory, a communication interface and a communication bus. The processor, the memory and the communication interface communicate with each other through the communication bus. The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute all the process steps of the method for flexible docking of assembly workpieces based on vision guidance disclosed in the above-mentioned embodiment, which will not be described in detail here.

[0080] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may communicate with one or more devices that enable a user to interact with the electronic device, and / or may communicate with any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication may be performed through an input / output (I / O) interface. In addition, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter. The network adapter communicates with other modules of the electronic device through a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0081] As described above, although the present invention has been shown and described with reference to specific preferred embodiments, it should not be construed as limiting the present invention itself. Various changes may be made to it in form and detail without departing from the spirit and scope of the present invention as defined in the appended claims.

Claims

1. A mobile flexible docking platform based on vision guidance, characterized in that: It includes an AGV trolley, a six-degree-of-freedom platform installed at the middle position of the upper part of the AGV trolley, and a binocular vision system installed at the rear side of the upper part of the AGV trolley; The bottom of the AGV is provided with two sets of driving wheels and a plurality of universal wheels; the two sets of driving wheels are distributed on both sides with the positive direction of the AGV as the central axis; each set of driving wheels is controlled separately, and the steering of the AGV is achieved by the differential speed of the two driving wheels; The binocular vision system provides real-time visual guidance during the movement of the AGV; The docking workpiece A is placed on a six-degree-of-freedom platform, and a docking workpiece B having an assembly relationship with the docking workpiece A is placed on the work surface at the target position; The AGV transports the docking workpiece A to the target position and docks it with the docking workpiece B; The person on duty at the workbench completes the subsequent assembly work of the docking workpiece A and the docking workpiece B.

2. The mobile flexible docking platform according to claim 1, characterized in that: The six-degree-of-freedom platform includes an upper platform, a lower platform, six electric cylinders, a horizontal Hooke's hinge and six servo motors; Among them, the upper platform is a dynamic platform, used to carry the workpiece to be assembled; the lower platform is a static platform, fixed on the upper surface of the AGV trolley; The upper platform and the lower platform are supported by an electric cylinder, and the upper and lower platforms and the electric cylinder are connected and fixed by a horizontal Hooke's hinge; one electric cylinder constitutes an independently moving motion unit, and six motion units are connected to the upper platform and the lower platform, with a total of six degrees of freedom; The electric cylinder is driven by a servo motor, and the motor controls the lead screw inside the cylinder body to realize the extension and retraction of the electric cylinder. The six electric cylinders work together to realize the precise control of the lifting and lowering and other postures of the upper platform.

3. The mobile flexible docking platform according to claim 2, characterized in that: An inclined block for compensating the rotation angle of the horizontal Hooke's joint is provided between the upper platform and the horizontal Hooke's joint.

4. The mobile flexible docking platform according to claim 1, characterized in that: The binocular vision system is installed at the upper end of the AGV vehicle and includes two CCD cameras; The two CCD cameras are fixed on both sides of the bracket by Y-shaped fixing plates respectively; and a ring fill light is fixed on the front end of each CCD camera respectively.

5. A method for flexible docking of assembly workpieces based on vision guidance, implemented based on the mobile flexible docking platform as described in any one of claims 1 to 4; characterized in that: The steps include: Install and fix the docking workpiece A on the six-degree-of-freedom platform, and install and fix the docking workpiece B on the work surface at the target position; Two QR codes with different ID numbers are attached to docking workpiece A and docking workpiece B. The conversion matrix between the coordinate system of the QR code and docking workpiece A is H1, and the conversion matrix between the coordinate system of the QR code and docking workpiece B is H2; Two CCD cameras simultaneously recognize the QR code, and obtain the left CCD camera image and the right CCD camera image respectively; the four corner points of the QR code are used as feature points, and the pixel coordinates of four feature points are detected in each CCD camera image; According to the position difference between the pixel coordinates of the feature points in the left CCD camera image and the pixel coordinates of the feature points in the right CCD camera image, the three-dimensional coordinates of the four feature points are calculated using the triangulation principle; By integrating and analyzing the three-dimensional coordinates of the four feature points, the rigid body coordinate systems of docking workpiece A and docking workpiece B are obtained, which are Guide the six-degree-of-freedom platform so that the rigid body coordinate system Overlap, thereby completing the docking of docking workpiece A and docking workpiece B.

6. The method for flexible docking of assembly workpieces based on vision guidance according to claim 5, characterized in that: The pixel coordinates of the feature points in the left CCD camera image are defined as (C ixl ,C iyl ); the pixel coordinates of the feature points in the CCD camera image on the right are defined as (C ixr ,C iyr ); Among them, i represents the serial number of the corner point; the subscript l represents the pixel coordinates of the left CCD camera image; the subscript r represents the pixel coordinates of the same corner point in the right CCD camera image.

7. The method for flexible docking of assembly workpieces based on vision guidance according to claim 5, characterized in that: The three-dimensional coordinates of the four feature points are calculated using the triangulation principle, specifically including: Define the baseline distance between the two CCD cameras as T, the focal length of the camera as f, and the distance from the left edge of the image plane of the left CCD camera and the right CCD camera to the projection position of the corner point i as x l and x r ; Parallax d of corner point i i =x l ―x r ; Define the pixel coordinates of the center point of the left CCD camera as (o x ,o y ); The coordinate value of corner point i in the binocular vision reference coordinate system is calculated according to the following formula: In the formula, (c ix* ,c iy* ) is the pixel coordinate of the corner point, * is l or r, corresponding to the pixel coordinate of the feature point in the left CCD camera image or the pixel coordinate of the feature point in the right CCD camera image, respectively.

8. The method for flexible docking of assembly workpieces based on vision guidance according to claim 5, characterized in that: The rigid body coordinate system of the docking workpiece A and the docking workpiece B is obtained by integrating and analyzing the three-dimensional coordinates of the four feature points, which specifically includes: Fit the spatial plane Ax+By+Cz+D=0 according to the coordinates of the four corner points, thereby obtaining the normal vector of the spatial plane as the Z-axis direction vector; Project the coordinates of the four corner points to the fitted spatial plane Ax+By+Cz+D=0, and select the direction vector between the projection coordinates of the first corner point and the projection coordinates of the second corner point as the X-axis; the direction vector of the Y-axis is calculated by the cross product of the X-axis and the Z-axis; Select the non-projected coordinates of the first corner point as the coordinate origin to construct coordinate system T1. Similarly, obtain the coordinate system T2 of another QR code. Combining the coordinate system of the QR code with the transformation matrices H1 and H2 of the contact surface of the docking workpieces, the rigid body coordinate system of the two docking workpieces is calculated as follows: and If the two docking workpieces are docked, guide the six-degree-of-freedom platform to work, and the guiding target is the rigid body coordinate system and coincide.

9. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the method for flexible docking of assembly workpieces based on vision guidance as claimed in any one of claims 5 to 8 is implemented.

10. A computer-readable storage medium, characterized in that: The storage medium stores at least one executable instruction. When the executable instruction is executed on the electronic device, the electronic device executes the method for flexible docking of assembly workpieces based on vision guidance as claimed in any one of claims 5 to 8.

Images