Deviation rectification control method, system, equipment and medium

Abstract

The invention discloses a deviation rectification control method, system and device and a medium, and the method comprises the steps: responding to a first sensor, detecting that a target object reaches a taking-out position of a mechanical arm, and sending a control signal to control the mechanical arm to clamp the target object according to a preset track and then move the target object to a preset position; in response to the fact that the second sensor detects that the target object reaches the preset position, starting camera equipment to obtain image information of the preset position; identifying a target object from the image information, and calculating position coordinates of the target object according to a calibration coordinate system of a current visual angle of the camera device; comparing an error between the target coordinate and the position coordinate, and if the error meets a preset requirement, controlling the mechanical arm to place the target object; and if the error does not meet the preset requirement, the mechanical arm is controlled to move to the target coordinate according to the difference value between the target coordinate and the position coordinate, and then the mechanical arm is controlled to place the target object. Accurate execution of the packaging process is achieved, and the production efficiency and the automation level are improved.

Description

Technical Field

[0001] The present invention relates to the field of visual correction technology, and in particular to a correction control method, system, equipment and medium. Background Art

[0002] In the overall process of glass production, packaging plays a vital role. It is not only related to the final presentation and protection of the product, but also the terminal process in the entire production chain, which plays an important role in ensuring product quality and improving market competitiveness. However, in actual operation, a common challenge occurs when the robot arm places the glass on the stand: due to various factors (such as the positioning accuracy of the robot arm, the consistency of the glass size, and the slight vibration during the operation, etc.), it is often difficult to keep the left and right sides of the glass neatly arranged when stacking, which directly leads to the packaging not meeting the established process standards.

[0003] In order to deal with this problem, in the prior art, one method is to rely on manual secondary adjustments, that is, after the robot arm has been initially placed, the workers manually rearrange the glass to ensure that it meets the packaging requirements. Although this approach solves the problem of neatness to a certain extent, it undoubtedly adds extra working hours, seriously affecting the effective packaging time of the glass, and thus slowing down the overall production efficiency. The second method is to use vision to calculate the glass deviation, and then control the robot arm to correct the deviation; such as the visual correction method in the gluing process of special-shaped glass substrates disclosed in publication number CN114604628A, which uses the degree of reflection blur of each pixel point to judge the error size. The disadvantage is that a large amount of calculations are required, which increases operating costs and affects the rapid production of automatic production lines.

[0004] Therefore, it is particularly urgent to develop a control method that can automatically correct the deviation of glass packaging, aiming to fundamentally solve the problem of uneven glass stacking and ensure the precise execution of the packaging process, thereby greatly improving production efficiency and automation level. Summary of the invention

[0005] The embodiments of the present invention at least partially solve the technical problem of uneven glass stacking in the prior art by providing a deviation correction control method, system, equipment and medium, achieve accurate execution of the packaging process, and improve production efficiency and automation level.

[0006] In the first aspect, to solve the above technical problems, the embodiments of the present invention provide the following technical solutions:

[0007] A deviation correction control method, comprising:

[0008] In response to the first sensor detecting that the target object has reached the removal position of the robot arm, a control signal is sent to control the robot arm to grasp the target object according to a preset trajectory and then move it to a preset position;

[0009] In response to the second sensor detecting that the target object has reached the preset position, starting a camera device to acquire image information of the preset position;

[0010] Identify the target object from the image information, and calculate the position coordinates of the target object according to the calibration coordinate system of the current viewing angle of the camera device;

[0011] Compare the error between the target coordinates and the above-mentioned position coordinates. If the above-mentioned error meets the preset requirements, control the above-mentioned robotic arm to place the above-mentioned target object; if the above-mentioned error does not meet the preset requirements, control the above-mentioned robotic arm to move to the above-mentioned target coordinates according to the difference between the above-mentioned target coordinates and the above-mentioned position coordinates, and then control the above-mentioned robotic arm to place the above-mentioned target object.

[0012] In some embodiments, a reference mark is provided on the same plane as the position where the mechanical arm is placed, the reference mark is located within the field of view of the camera device, and the reference mark includes a reference coordinate system and a vertical member perpendicular to the reference coordinate system;

[0013] The steps after starting the camera device to obtain the image information of the preset position specifically include:

[0014] After the camera device is turned on, the reference coordinate system and the vertical member are identified according to preset color features;

[0015] The X-axis and Y-axis are established with the reference coordinate system, and the Y-axis is established with the direction of the vertical member on the image to establish a three-dimensional calibration coordinate system.

[0016] In some embodiments, a reference mark is provided on the same plane as the position where the mechanical arm is placed, the reference mark is located within the field of view of the camera device, and the reference mark includes a reference coordinate system;

[0017] The steps after starting the camera device to obtain the image information of the preset position specifically include:

[0018] After the camera device is turned on, the reference coordinate system is identified according to the preset color features;

[0019] Establish a plane coordinate system according to the reference coordinate system, and calculate the corresponding normal vector based on the plane of the plane coordinate system;

[0020] A three-dimensional calibration coordinate system is established according to the above plane coordinate system and the above normal vector.

[0021] In some embodiments, the reference mark further includes a plurality of preset points located in the reference coordinate system, and the actual distances between the plurality of preset points and the origin of the reference coordinate system are known;

[0022] The step of calculating the position coordinates of the target object specifically includes:

[0023] Acquire a corresponding scale diagram according to the actual distance and the image distance of each of the preset points in the image information;

[0024] The position coordinates of the target object are calculated based on the scale diagram and the direction of each axis of the reference coordinate system.

[0025] In some embodiments, after calculating the position coordinates of the target object, the method further includes:

[0026] According to each coordinate point of the above position coordinates, the area of ​​each surface of the above target object is calculated. If the area of ​​any surface exceeds the corresponding preset range, a prompt message indicating that the product is defective is sent.

[0027] In some embodiments, it further comprises a laser marker, wherein the laser marker emits a plurality of lasers to form a placement area for the robotic arm;

[0028] After controlling the robot arm to move to the target coordinates, the method further includes:

[0029] Compare the error between the target coordinates and the above position coordinates again, and if the above error does not meet the preset requirement, turn on the above laser marker;

[0030] According to the above-mentioned scale drawing and the direction of each axis of the above-mentioned reference coordinate system, the coordinate points of each corner within the visible range of the above-mentioned placement area are calculated and updated to the new target coordinates, and the above-mentioned robotic arm is controlled to move to the above-mentioned new target coordinates.

[0031] In some embodiments, after controlling the robotic arm to place the target object, the method further includes:

[0032] The robot arm is controlled to return to an initial position, and waits for a return signal from the first sensor.

[0033] In a second aspect, a correction control system is provided, comprising:

[0034] The taking-out module sends a control signal in response to the first sensor detecting that the target object reaches the taking-out position of the robot arm, so as to control the robot arm to grasp the target object according to a preset trajectory and then move it to a preset position;

[0035] An image acquisition module, in response to the second sensor detecting that the target object has reached the preset position, starts a camera to acquire image information of the preset position;

[0036] A position coordinate calculation module, used to identify the target object from the image information and calculate the position coordinates of the target object according to the calibration coordinate system of the current viewing angle of the camera device;

[0037] The correction module is used to compare the error between the target coordinates and the above-mentioned position coordinates. If the above-mentioned error meets the preset requirements, the above-mentioned robotic arm is controlled to place the above-mentioned target object; if the above-mentioned error does not meet the preset requirements, the above-mentioned robotic arm is controlled to move to the above-mentioned target coordinates according to the difference between the above-mentioned target coordinates and the above-mentioned position coordinates, and then the above-mentioned robotic arm is controlled to place the above-mentioned target object.

[0038] In a third aspect, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps corresponding to the method of the first aspect when executing the computer program.

[0039] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps corresponding to the above method in the first aspect are implemented.

[0040] The solution provided in the embodiments of the present invention has at least the following technical effects or advantages:

[0041] The present invention realizes precise control and adjustment of the process of glass placement by the robot arm. By processing the image information, the target object is identified, and the actual position coordinates of the target object are calculated using the calibration coordinate system of the camera equipment. If the error is within the preset requirement range, the robot arm will directly place the target object, ensuring the continuity and efficiency of the operation. If the error exceeds the preset requirement, the method can intelligently adjust the movement path of the robot arm according to the difference between the target coordinates and the actual position coordinates, so that it can accurately move to the target coordinates and then place the object. This deviation correction mechanism effectively solves the technical problem of uneven glass stacking in the prior art, which not only ensures the accurate execution of the packaging process, but also significantly improves the production efficiency and automation level, making the entire operation process more efficient and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 A flow chart of a deviation correction control method provided by the present invention;

[0044] Figure 2 It is a schematic diagram of the structure of the mechanical arm and reference marks in the present invention;

[0045] Figure 3 It is a schematic diagram of a scale diagram in the present invention;

[0046] Figure 4 A schematic structural diagram of a deviation correction control system provided by the present invention.

[0047] Figure numerals: 1. Robotic arm; 2. Target object; 3. Reference mark; 31. Reference coordinate system; 32. Vertical member; 33. Preset point; 4. Laser marker. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0049] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0051] In the description of the present invention, it should also be noted that, unless otherwise clearly specified and limited, the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0052] It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solutions of the present application, rather than limitations of the technical solutions of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments may be combined with each other.

[0053] In an embodiment of the present invention, there is provided Figure 1 and Figure 2 A deviation correction control method is shown, the method comprising steps S101 to S104:

[0054] S101, in response to the first sensor detecting that the target object 2 reaches the removal position of the robot arm 1, a control signal is sent to control the robot arm 1 to grasp the target object 2 according to a preset trajectory and then move it to a preset position.

[0055] Specifically, when the production data is downloaded through the touch screen, the operator presses the automatic start button, and the controller will then instruct the robot arm 1 to start from its origin and accurately move to the pre-set position for gripping the glass. In this process, the first sensor connected to the main controller (the sensor can be a distance sensor or a travel switch) plays a key role. It is responsible for detecting whether the robot arm 1 has accurately reached the specified position and confirming that the target object 2 (i.e., the glass to be gripped) is in a ready state. Once these conditions are met, the main controller will send a clear control signal to the robot arm 1 system, instructing it to grip the target object 2 steadily and move it safely to the preset position according to the pre-planned trajectory.

[0056] S102: In response to the second sensor detecting that the target object 2 has reached a preset position, starting a camera device to acquire image information of the preset position.

[0057] Specifically, the second sensor can be a distance sensor or a travel switch, which is intended to detect whether the target object 2 has reached a preset position, that is, the robot arm 1 transports the glass to a certain distance directly above the target coordinates to ensure the safety of the glass. Then the camera device is started to obtain image information of the preset position to check for possible deviations of the glass.

[0058] In some embodiments, a reference mark 3 is provided on the same plane as the placement position of the robot arm 1. The reference mark 3 is located within the field of view of the camera device. The reference mark 3 includes a reference coordinate system 31 and a vertical piece 32 perpendicular to the reference coordinate system 31.

[0059] Among them, the present invention deliberately sets a reference mark 3 on the operating plane of the robot arm 1, and the mark is located within the monitoring range of the camera device to facilitate accurate visual positioning. The reference mark 3 consists of two parts: one is a reference coordinate system 31, which is used to define and refer to the directions of the X-axis and the Y-axis; the other is a vertical member 32 perpendicular to the reference coordinate system 31, which serves as a reference for the Z-axis. The core purpose of this design is to optimize the position acquisition of the target object 2 during the visual correction process. Traditional technology usually relies on the built-in coordinate system of the camera device for complex position conversion, which involves multi-step calculations from image coordinates to internal coordinates of the device, and then further converted to world coordinates. The process is cumbersome and computationally intensive.

[0060] In order to overcome this drawback, the present invention innovatively introduces the reference mark 3 to directly construct an intuitive world coordinate system within the camera field of view. In this way, the camera device can instantly capture the reference information directly corresponding to the world coordinates, without the need for cumbersome secondary coordinate conversion, thereby significantly reducing the amount of calculation, speeding up the processing speed, and improving the overall production efficiency. In addition, this method also gives the camera device great flexibility in installation, because it allows the device to be installed at any angle, and it only needs to simply adjust the direction of its XYZ axis according to the reference mark 3, which greatly enhances the adaptability and wide application of the system.

[0061] Therefore, the steps for establishing the calibration coordinate system specifically include:

[0062] After the camera is turned on, the reference coordinate system 31 and the vertical member 32 are identified according to the preset color features. That is, a high contrast or bright color is used so that the camera can quickly identify the reference mark 3. Then, the X-axis and Y-axis are established with the reference coordinate system 31, and the Y-axis is established with the direction of the vertical member 32 on the image, and a three-dimensional calibration coordinate system is established.

[0063] In addition to the aforementioned setting of a mark containing a three-dimensional reference on the operating plane of the robot arm 1, there is also a more concise implementation scheme, that is, setting only a two-dimensional reference coordinate system 31 on the same plane where the robot arm 1 is placed, and the reference coordinate system 31 is located within the field of view of the camera device. The steps of establishing the calibration coordinate system specifically include:

[0064] The specific steps to implement this solution are as follows: First, when the camera device is started and in working state, it will automatically identify and locate the two-dimensional reference coordinate system 31 according to the preset color characteristics. Once successfully identified, the camera device will establish a plane coordinate system based on the reference coordinate system 31. Next, by calculating the normal vector corresponding to the plane of the plane coordinate system, we can indirectly determine the direction of the Z axis. Although a vertical piece 32 perpendicular to the plane is not directly set at this time, a complete three-dimensional calibration coordinate system can still be constructed using mathematical calculations.

[0065] It is worth noting that although this embodiment is simpler in physical structure and lacks the vertical member 32, it can still effectively provide positioning information in three-dimensional space. This is undoubtedly a more economical and practical choice for customers who want to reduce material costs or face production line space constraints. Therefore, in actual applications, customers can choose the most suitable implementation plan according to their specific needs and conditions.

[0066] S103, identifying the target object 2 from the image information, and calculating the position coordinates of the target object 2 according to the calibration coordinate system of the current viewing angle of the camera device.

[0067] Specifically, image preprocessing is performed first. The purpose of this step is to improve image quality and reduce noise and interference so that the subsequent target detection step can more accurately identify the target object2. Preprocessing may include grayscale, filtering, binarization and other operations, depending on the characteristics of the image and the requirements of subsequent processing.

[0068] Next, target detection is performed. In this step, image processing algorithms (such as edge detection, template matching, deep learning models, etc.) are used to identify the target object 2 in the image. The purpose of target detection is to determine the position and range of the target object 2 in the image, usually expressed in the form of a bounding box.

[0069] After target detection is completed, feature extraction is performed. Although target detection has given the approximate position of the target object 2, in order to more accurately calculate its position coordinates, it is usually necessary to extract some key feature points (corner points, edge points of glass, etc.). These feature points will be used for subsequent coordinate calculations.

[0070] Finally, the coordinates of the calibration coordinate system are calculated. The calibration parameters of the camera device are obtained, including internal parameters (focal length, optical center, etc.) and external parameters (the posture and position of the camera device). These parameters are usually obtained through calibration experiments and used to measure the mapping angles at different positions.

[0071] In some embodiments, the reference mark 3 further includes a plurality of preset points 33 located in the reference coordinate system 31, and the actual distances between the plurality of preset points 33 and the origin of the reference coordinate system 31 are known; therefore, the step of calculating the position coordinates of the target object 2 can be performed in the following manner:

[0072] The corresponding scale diagram is acquired according to the actual distance and the image distance of each preset point 33 in the image information, and the position coordinates of the target object 2 are calculated according to the scale diagram and the direction of each axis of the reference coordinate system 31 .

[0073] Specifically, in the above-mentioned robot arm 1 positioning or image recognition system, the reference mark 3 is not just a simple two-dimensional reference coordinate system 31, but also includes a plurality of preset points 33, which are distributed in a straight line on the reference coordinate system 31, and their actual physical distances from the origin of the reference coordinate system 31 are accurately measured and known in advance. This design greatly enhances the positioning accuracy and reliability of the system.

[0074] When the position coordinates of the target object 2 in the three-dimensional space need to be calculated, the system first uses the camera to capture the image information containing these preset points 33. Then, a key step is to generate a scale map (such as ) based on the image distances between these preset points 33 and the corresponding points in the image formed by the camera, and the known actual distances between them and the origin of the reference coordinate system 31. Figure 3 This ratio diagram is actually a scaling map, which reflects the transformation relationship from the actual space to the image space.

[0075] With this scale map as a reference, the system can further accurately calculate the position coordinates of the target object 2 in three-dimensional space based on the directions of each axis of the reference coordinate system 31 (these directions are also identifiable in the image because they are related to the layout of the preset points 33) and the relative position of the target object 2 in the image. This method is not only simple and intuitive, but also effectively improves the accuracy and efficiency of position coordinate calculation by utilizing known actual distances and image information.

[0076] S104, compare the error between the target coordinates and the position coordinates. If the error meets the preset requirements, control the robotic arm 1 to place the target object 2; if the error does not meet the preset requirements, control the robotic arm 1 to move to the target coordinates according to the difference between the target coordinates and the position coordinates, and then control the robotic arm 1 to place the target object 2.

[0077] Specifically, the comparison between the target coordinates and the position coordinates is intended to evaluate the error between the two, that is, the difference between the current position of the target object 2 and the ideal position where it should be placed. If the system determines that the error is within the preset allowable range (that is, the error meets the preset requirements), then it can be considered that the target object 2 is close enough to its target position. At this time, the system will trigger the robot arm 1 to perform the placement action and accurately place the target object 2 at the predetermined position.

[0078] However, if the system detects that the error exceeds the preset allowable range (that is, the error does not meet the preset requirements), this indicates that there is a significant deviation between the current position of the target object 2 and the ideal position where it should be placed. In this case, the system calculates the specific direction and distance that the robot arm 1 needs to move based on the difference between the target coordinates and the current position coordinates. Subsequently, the system controls the robot arm 1 to move along the calculated path until it reaches the precise position specified by the target coordinates. Once the robot arm 1 reaches this position, the system triggers the placement action again to ensure that the target object 2 can be accurately placed at the predetermined position.

[0079] In some embodiments, after calculating the position coordinates of the target object 2, the method further includes:

[0080] According to each coordinate point of the position coordinate, the area of ​​each surface of the target object 2 is calculated. If the area of ​​any surface exceeds the corresponding preset range, a prompt message indicating that the product is defective is sent.

[0081] Specifically, after the position coordinates of the target object 2 are calculated, the automated processing or detection process does not end immediately. Instead, the system will further use these position coordinate data for deeper analysis and judgment. Specifically, the system will calculate the area of ​​each face of the target object 2 based on the precise position information of each coordinate point in the position coordinates.

[0082] After calculating the area of ​​each side of the target object 2, the system will compare these areas with the preset corresponding ranges. These preset ranges are set according to product quality standards and design specifications to ensure that each side of the product meets the established size requirements. If the system detects that the area of ​​any side of the target object 2 exceeds its corresponding preset range, it means that the product may have a problem with its size, such as being too large or too small, which is usually regarded as a signal of a defective product.

[0083] In this case, the system will automatically trigger a prompt message to inform relevant personnel that the product has a defective condition. This prompt message can help the production team quickly locate the source of the problem and take necessary corrective measures to prevent defective products from entering the market, thereby maintaining the company's reputation and customer satisfaction.

[0084] In some embodiments, a laser marker 4 is further included, and the laser marker 4 emits a plurality of lasers to form a placement area of ​​the robot arm 1. After controlling the robot arm 1 to move to the target coordinate, the following is further included:

[0085] Compare the errors between the target coordinates and the position coordinates again. If the errors do not meet the preset requirements, turn on the laser marker 4. According to the scale diagram and the direction of each axis of the reference coordinate system 31, calculate the coordinate points of each corner within the visible range of the placement area, and update them to the new target coordinates, and control the robot arm 1 to move to the new target coordinates.

[0086] In addition to the basic control of the robot arm 1 and the calculation of the position coordinates of the target object 2, the present invention also integrates an auxiliary device, a laser marker 4, for the precise placement of the first glass. The laser marker 4 forms a clear frame in space that defines the placement area of ​​the robot arm 1 by emitting multiple laser beams. This function not only improves the accuracy of the operation, but also provides an intuitive visual reference for the operator, making the placement action of the robot arm 1 more accurate and correct.

[0087] When the robot 1 is controlled to move to the preliminarily calculated target coordinates, the system does not immediately perform the placement operation. Instead, it will again compare the error between the target coordinates and the actual position coordinates to ensure that the robot 1 has reached a sufficiently accurate position. If the comparison result shows that the error does not meet the preset accuracy requirements, the system will start the laser marker 4 and use the frame formed by the laser light to further accurately define the placement area.

[0088] At this point, the system will calculate the coordinate points of each corner within the visible range of the placement area based on the previously generated scale diagram and the direction of each axis of the reference coordinate system 31. These coordinate points represent the most accurate boundaries of the placement area, and the system will update the target coordinates based on these points to ensure that the robot 1 can move to a more precise position. Subsequently, the system will control the robot 1 again to move according to the updated new target coordinates until the robot 1 is accurately positioned at the optimal position of the placement area, and then perform the placement operation. This process significantly improves the accuracy and reliability of the placement operation of the robot 1 by introducing a laser marker 4 and multiple error comparisons.

[0089] In some embodiments, after controlling the robotic arm 1 to place the target object 2 , the method further includes: controlling the robotic arm 1 to return to an initial position and waiting for a return signal from the first sensor.

[0090] Specifically, when the robot arm 1 completes the calibration of the glass, it will first release the vacuum of the suction cup to place the glass steadily on the platform. At the same time, the touch screen interface will update and display the number of glasses that have been placed and the current status of various related signals in real time, ensuring that the operator can monitor the progress and status of the entire process at any time.

[0091] Once the glass is successfully placed, the robot arm 1 will automatically return to the preset position, which marks the end of the glass placement program. Subsequently, the system control will return to the main program and wait for the next instruction. At this time, the controller will drive the robot arm 1 to move from the current glass placement position back to the initial position. This initial position is the starting position of the robot arm 1 before the next operation, ensuring that each operation starts from the same reference point.

[0092] When the robot arm 1 reaches the initial position, the sensor connected to the controller will detect this state and confirm that the moving mechanism has been accurately positioned. At this time, the system will be in standby mode, waiting for the controller to send a signal to pick up the glass next time. Once the signal is received, the whole process will start again, and the robot arm 1 will move to the glass grabbing position again, performing a series of actions such as grabbing, moving, and placing, and so on. This cycle is repeated, realizing the automation and efficiency of glass processing.

[0093] Based on the same inventive concept, an embodiment of the present invention provides a correction control system, such as Figure 4Shown include:

[0094] The taking-out module 201 sends a control signal in response to the first sensor detecting that the target object 2 reaches the taking-out position of the robot arm 1, so as to control the robot arm 1 to grasp the target object 2 according to a preset trajectory and then move it to a preset position;

[0095] The image acquisition module 202 starts a camera to acquire image information of the preset position in response to the second sensor detecting that the target object 2 has reached the preset position;

[0096] A position coordinate calculation module 203 is used to identify the target object 2 from the image information and calculate the position coordinates of the target object 2 according to the calibration coordinate system of the current viewing angle of the camera device;

[0097] The correction module 204 is used to compare the error between the target coordinates and the position coordinates. If the error meets the preset requirements, the robot arm 1 is controlled to place the target object 2; if the error does not meet the preset requirements, the robot arm 1 is controlled to move to the target coordinates according to the difference between the target coordinates and the position coordinates, and then the robot arm 1 is controlled to place the target object 2.

[0098] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the above-mentioned deviation correction control method is implemented when the processor executes the computer program.

[0099] Based on the same inventive concept, this embodiment provides a computer-readable storage medium on which a computer program is stored, characterized in that the above-mentioned correction control method is implemented when the program is executed by a processor.

[0100] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0101] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A deviation correction control method, characterized in that: The method comprises: In response to the first sensor detecting that the target object has reached the removal position of the robot arm, a control signal is sent to control the robot arm to grasp the target object according to a preset trajectory and then move it to a preset position; In response to the second sensor detecting that the target object has reached the preset position, starting a camera device to acquire image information of the preset position; Identify the target object from the image information, and calculate the position coordinates of the target object according to the calibration coordinate system of the current viewing angle of the camera device; The error between the target coordinates and the position coordinates is compared. If the error meets the preset requirements, the robotic arm is controlled to place the target object. If the error does not meet the preset requirements, the robotic arm is controlled to move to the target coordinates according to the difference between the target coordinates and the position coordinates, and then the robotic arm is controlled to place the target object.

2. The method according to claim 1, characterized in that It also includes a reference mark provided on the same plane as the placement position of the mechanical arm, the reference mark is located within the field of view of the camera device, and the reference mark includes a reference coordinate system and a vertical member perpendicular to the reference coordinate system; The steps after starting the camera device to obtain the image information of the preset position specifically include: After the camera device is turned on, the reference coordinate system and the vertical member are identified according to preset color features; The X-axis and the Y-axis are established with the reference coordinate system, and the Y-axis is established with the direction of the vertical member on the image, so as to establish a three-dimensional calibration coordinate system.

3. The method according to claim 1, characterized in that It also includes providing a reference mark on the same plane as the position where the mechanical arm is placed, the reference mark is located within the field of view of the camera device, and the reference mark includes a reference coordinate system; The steps after starting the camera device to obtain the image information of the preset position specifically include: After the camera device is turned on, the reference coordinate system is identified according to a preset color feature; Establishing a plane coordinate system according to the reference coordinate system, and calculating a corresponding normal vector based on the plane of the plane coordinate system; A three-dimensional calibration coordinate system is established according to the plane coordinate system and the normal vector.

4. The method according to any one of claims 2 to 3, characterized in that: The reference identifier further includes a plurality of preset points located in the reference coordinate system, and actual distances between the plurality of preset points and the origin of the reference coordinate system are known; The step of calculating the position coordinates of the target object specifically includes: Acquire a corresponding scale diagram according to the actual distance and the image distance of each preset point in the image information; The position coordinates of the target object are calculated according to the scale map and the direction of each axis of the reference coordinate system.

5. The method according to claim 4, characterized in that After calculating the position coordinates of the target object, the method further includes: The area of ​​each surface of the target object is calculated according to each coordinate point of the position coordinates. If the area of ​​any surface exceeds the corresponding preset range, a prompt message indicating that the product is defective is sent.

6. The method according to claim 4, characterized in that Also included is a laser marker, which emits a plurality of lasers to form a placement area for the robot arm; After controlling the robot arm to move to the target coordinate, the method further includes: Comparing the error between the target coordinates and the position coordinates again, if the error does not meet the preset requirement, turning on the laser marker; According to the scale diagram and the direction of each axis of the reference coordinate system, the coordinate points of each corner within the visible range of the placement area are calculated and updated to new target coordinates, and the robotic arm is controlled to move to the new target coordinates.

7. The method according to claim 1, characterized in that After controlling the robotic arm to place the target object, the method further includes: The robot arm is controlled to return to an initial position and wait for a return signal from the first sensor.

8. A deviation correction control system, characterized in that: The system comprises: The taking-out module sends a control signal in response to the first sensor detecting that the target object reaches the taking-out position of the robot arm, so as to control the robot arm to grasp the target object according to a preset trajectory and then move it to a preset position; an image acquisition module, in response to the second sensor detecting that the target object has reached the preset position, starting a camera to acquire image information of the preset position; A position coordinate calculation module, used to identify the target object from the image information, and calculate the position coordinates of the target object according to the calibration coordinate system of the current viewing angle of the camera device; The correction module is used to compare the error between the target coordinates and the position coordinates. If the error meets the preset requirements, the robot arm is controlled to place the target object; if the error does not meet the preset requirements, the robot arm is controlled to move to the target coordinates according to the difference between the target coordinates and the position coordinates, and then the robot arm is controlled to place the target object.

9. An electronic device, characterized in that: The electronic device comprises: a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the method steps described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps corresponding to the method according to any one of claims 1 to 7 are implemented.

Images