A battery cell grabbing method, system, device, equipment and storage medium

Abstract

The embodiments of the present application provide a method, system, device, equipment and storage medium for grasping battery cells, which relate to the field of robotics technology. The specific implementation scheme is: obtaining an image of a designated area where battery cells are placed, which is taken by a camera above the designated area, as an image to be used; identifying the posture of each battery cell in the image to be used; based on the posture of each battery cell and the designated array size, detecting whether there are missing battery cells in the designated area; if there are no missing battery cells, dividing each battery cell into multiple units to be grasped; for each unit to be grasped, based on the posture of each battery cell contained in the unit to be grasped, determining the grasping posture of the manipulator grasping the unit to be grasped, and controlling the manipulator to grasp the battery cells included in the unit to be grasped as a whole according to the determined grasping posture, until all battery cells in the designated area are fully grasped. It can be seen that through this scheme, the grasping efficiency of battery cells can be improved.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to a method, system, device, equipment, and storage medium for grasping a battery cell. Background Art

[0002] At present, in the battery cell production process, in order to reduce labor costs, robots are usually used to automatically grab the battery cells from the production line, or grab them from the side of the production line to the production line.

[0003] The end of a robot arm used to grasp battery cells is typically equipped with multiple grippers, each designed to grasp a single cell, allowing the arm to grasp multiple cells simultaneously. If any gripper fails to grasp a cell during the grasping process, the arm will generate an alarm and halt the current production process. This requires manual intervention, resulting in lower cell grasping efficiency.

[0004] Therefore, how to improve the efficiency of grabbing battery cells has become a technical problem that needs to be solved urgently. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a battery cell grabbing method, system, device, equipment, and storage medium to improve the battery cell grabbing efficiency. The specific technical solution is as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for grabbing a battery cell, the method comprising:

[0007] Acquire an image of the designated area where the battery cells are placed, captured by a camera above the designated area, as the image to be used;

[0008] Identifying the position and posture of each battery cell in the image to be used;

[0009] Based on the position of each battery cell and the specified array size, detecting whether there is a missing battery cell in the specified area; wherein, when there is no missing battery cell in the specified area, the arrangement of the battery cells in the specified area meets the specified array size;

[0010] If there are no missing cells, the cells are divided into a plurality of cells to be picked up; wherein each cell to be picked up includes a predetermined number of adjacent cells arranged in rows or columns, and the cells in each of the cells to be picked up are arranged in the same manner;

[0011] For each unit to be grasped, based on the posture of each battery cell contained in the unit to be grasped, the grasping posture of the manipulator to grasp the unit to be grasped is determined, and the manipulator is controlled to grasp the battery cells included in the unit to be grasped as a whole according to the determined grasping posture until all battery cells in the designated area are grasped.

[0012] In a second aspect, an embodiment of the present application provides a battery cell grasping system, including a camera, a control device, and a manipulator;

[0013] The camera is used to capture an image of a designated area where the battery cells are placed;

[0014] The control device is used to execute any of the above-mentioned battery cell grabbing methods;

[0015] The manipulator is used to grab the battery cell under the control of the control device.

[0016] In a third aspect, an embodiment of the present application provides a battery cell grabbing device, the device comprising:

[0017] an acquisition module, configured to acquire an image of the designated area where the battery cells are placed, taken by a camera above the designated area, as an image to be used;

[0018] A recognition module, configured to recognize the position and posture of each battery cell in the image to be used;

[0019] a detection module, configured to detect whether there are missing cells in the designated area based on the positions of the individual cells and the designated array size; wherein, when there are no missing cells in the designated area, the arrangement of the cells in the designated area satisfies the designated array size;

[0020] a division module, configured to divide each battery cell into a plurality of to-be-grabbed units if no battery cell is missing; wherein each to-be-grabbed unit includes a predetermined number of adjacent battery cells arranged in rows or columns, and the battery cells in each of the divided to-be-grabbed units are arranged in the same manner;

[0021] The grasping module is used to determine the grasping posture of the manipulator grasping the unit to be grasped based on the posture of each battery cell contained in the unit to be grasped, and control the manipulator to grasp the battery cells included in the unit to be grasped as a whole according to the determined grasping posture until all battery cells in the designated area are grasped.

[0022] In a fourth aspect, an embodiment of the present application provides an electronic device, including:

[0023] Memory for storing computer programs;

[0024] The processor is configured to implement any of the above-mentioned cell grabbing methods when executing a program stored in the memory.

[0025] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the battery cell grabbing method described in any one of the above items is implemented.

[0026] In a sixth aspect, an embodiment of the present application provides a computer program product, which includes executable instructions. When the executable instructions are executed on a computer, the computer executes any one of the above-mentioned battery cell grabbing methods.

[0027] Beneficial effects of the embodiments of the present application:

[0028] The solution provided by the embodiment of the present application, before grasping the battery cells, uses the posture of each battery cell identified in the image to be used and the specified array size to detect whether there are missing batteries in the specified area, and if there are no missing batteries, the battery cells are divided into multiple units to be grasped. Then, for each unit to be grasped, based on the posture of each battery cell contained in the unit to be grasped, the grasping posture of the manipulator to grasp the unit to be grasped is determined, and the manipulator is controlled to grasp the battery cells included in the unit to be grasped as a whole according to the determined grasping posture until all the battery cells in the specified area are completely grasped. It can be seen that this solution grasps the battery cells only after detecting that there are no missing batteries in the specified area. Compared with the direct grasping of the battery cells in the prior art, it reduces the probability that a gripper cannot grasp the battery cell due to the missing battery cell during grasping, thereby causing an alarm and stopping the current production process, thereby improving the grasping efficiency of the battery cells. In addition, since the probability of alarming and stopping the current production process is reduced, the production efficiency of the battery cells can be further improved.

[0029] Of course, it is not necessary to achieve all the advantages described above at the same time when implementing any product or method of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0031] Figure 1 A flow chart of a battery cell grabbing method provided in an embodiment of the present application;

[0032] Figure 2A A schematic diagram of a plurality of units to be grasped obtained by division provided in an embodiment of the present application;

[0033] Figure 2BA schematic diagram of multiple units to be grasped obtained by another division provided in an embodiment of the present application;

[0034] Figure 3 A flowchart for implementing step S103 in the cell grabbing method provided in an embodiment of the present application;

[0035] Figure 4 A flowchart for implementing step S105 in the battery cell grabbing method provided in an embodiment of the present application;

[0036] Figure 5 A schematic structural diagram of a battery cell grabbing system provided in an embodiment of the present application;

[0037] Figure 6 A flowchart of a photographing process in a specific example of the battery cell grabbing method provided in an embodiment of the present application;

[0038] Figure 7 A detection flow chart of a specific example of the battery cell grabbing method provided in an embodiment of the present application;

[0039] Figure 8 A flowchart of a specific example of a cell grabbing method provided in an embodiment of the present application;

[0040] Figure 9 A schematic structural diagram of a battery cell grabbing device provided in an embodiment of the present application;

[0041] Figure 10 A block diagram of an electronic device for implementing the battery cell grabbing method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field based on this application are within the scope of protection of this application.

[0043] First, the professional terms involved in the embodiments of this application are introduced.

[0044] Manipulator: A manipulator is an automated device that imitates certain movement functions of human hands and arms. It can grasp, move objects or operate tools according to fixed procedures. It is a type of industrial robot.

[0045] Battery cell: The most basic component of a battery, an electrochemical device encapsulated in a metal shell. It is a unit that stores and releases electrical energy, converting chemical energy into electrical energy through chemical reactions.

[0046] Pose Merge: Merge multiple poses into one pose.

[0047] Next, a battery cell grabbing method provided in an embodiment of the present application is introduced.

[0048] The battery cell grabbing method provided in the embodiments of the present application is applied to a control device, which can be various electronic devices, such as personal computers, servers, and other devices with data processing capabilities. Furthermore, it is understood that the battery cell grabbing method provided in the embodiments of the present application can be implemented through software, hardware, or a combination of software and hardware.

[0049] Among them, a battery cell grabbing method provided in an embodiment of the present application may include:

[0050] Acquire an image of the designated area where the battery cells are placed, taken by a camera above the designated area, as the image to be used;

[0051] Identify the position and posture of each battery cell in the image to be used;

[0052] Based on the position of each battery cell and the specified array size, detect whether there is a missing battery cell in the specified area; wherein, when there is no missing battery cell in the specified area, the arrangement of the battery cells in the specified area meets the specified array size;

[0053] If there are no missing cells, the cells are divided into a plurality of cells to be picked up; wherein each cell to be picked up includes a predetermined number of adjacent cells arranged in rows or columns, and the cells in each of the cells to be picked up are arranged in the same manner;

[0054] For each unit to be grasped, the gripping posture of the manipulator to grasp the unit to be grasped is determined based on the posture of each battery cell contained in the unit to be grasped, and the manipulator is controlled to grasp the battery cells included in the unit to be grasped as a whole according to the determined gripping posture until all battery cells in the specified area are grasped.

[0055] The solution provided by the embodiment of the present application, before grasping the battery cells, uses the posture of each battery cell identified in the image to be used and the specified array size to detect whether there are missing batteries in the specified area, and if there are no missing batteries, the battery cells are divided into multiple units to be grasped. Then, for each unit to be grasped, based on the posture of each battery cell contained in the unit to be grasped, the grasping posture of the manipulator to grasp the unit to be grasped is determined, and the manipulator is controlled to grasp the battery cells included in the unit to be grasped as a whole according to the determined grasping posture until all the battery cells in the specified area are completely grasped. It can be seen that this solution grasps the battery cells only after detecting that there are no missing batteries in the specified area. Compared with the direct grasping of the battery cells in the prior art, it reduces the probability that a gripper cannot grasp the battery cell due to the missing battery cell during grasping, thereby causing an alarm and stopping the current production process, thereby improving the grasping efficiency of the battery cells. In addition, since the probability of alarming and stopping the current production process is reduced, the production efficiency of the battery cells can be further improved.

[0056] The following describes the battery cell grabbing method provided in the embodiments of the present application in conjunction with the accompanying drawings.

[0057] like Figure 1 The battery cell grabbing method provided in the embodiment of the present application includes steps S101-S105:

[0058] S101, acquiring an image of the designated area where the battery cells are placed, captured by a camera above the designated area, as an image to be used;

[0059] In this embodiment, the designated area is the area where the battery cells to be grasped by the robot are placed. For example, in actual applications, the designated area can be the area on the production line where the process of grasping the battery cells by the robot is located, or a working area on the production line where the robot to be used grasps the battery cells. In addition, the camera is installed above the designated area to capture an image of the designated area downward to obtain an image to be used. In actual applications, the camera can be fixedly installed at a fixed position above the designated area, or installed on the robot, which is reasonable.

[0060] Optionally, in one implementation, the camera is mounted on an end effector of the manipulator;

[0061] It can be understood that by installing the camera on the end picker of the robot, when there is no condition for fixed installation of the camera in the production scene, the robot can be used to move the camera installed on the end picker to the top of the specified area to capture the image of the specified area.

[0062] Accordingly, in this implementation, step S101 obtains an image of the designated area where the cells to be grabbed are placed, captured by a camera above the designated area, as the image to be used, and includes steps A1-A2:

[0063] A1, controls the robot to move to each of the multiple preset points above the designated area in sequence, so that the camera takes a picture at each point to obtain multiple images;

[0064] A2, performing image stitching processing on the obtained multiple images to obtain an image to be used.

[0065] It is understandable that the end picker of the manipulator is a device on the end of the manipulator that directly performs the grasping work. When the camera is installed on the end picker of the manipulator, the camera's field of view is small and cannot cover the entire designated area. At this time, in order to obtain an image of the complete designated area, the manipulator can be controlled to move to each of the multiple preset points above the designated area in turn, so as to drive the camera installed on the end picker of the manipulator to move to each point in turn and take pictures, thereby obtaining multiple images. Among them, the multiple preset points can be multiple coordinate positions set by relevant staff based on experience, and the multiple coordinate positions enable the multiple images taken by the camera at the multiple coordinate positions to be combined into an image containing the complete designated area.

[0066] After obtaining multiple images captured by the camera at multiple preset points, since each image only contains a part of the specified area, in order to obtain an image containing the complete specified area, the multiple images are subjected to image stitching processing. Exemplarily, image stitching and fusion algorithms such as SIFT (Scale Invariant Feature Transform) algorithm and SURF (Speeded Up Robust Features) algorithm can be used to stitch multiple images to obtain an image containing the complete specified area. The image containing the complete specified area is the image to be used. It should be noted that the embodiment of the present application does not limit the method of image stitching processing.

[0067] S102, identifying the position and posture of each battery cell in the image to be used;

[0068] After obtaining the image to be used, the coordinate value and rotation angle of each battery cell in the image can be used to represent the position and posture of the battery cell. For example, the coordinate value of each battery cell can be the coordinate value of the center point of the battery cell, or the coordinate value of a corner point, etc.; the rotation angle of each battery cell can be the angle between the long side or short side of the battery cell and a predetermined reference direction in the image. The predetermined reference direction can be the positive direction of the X axis or the positive direction of the Y axis of the image coordinate system in the image to be used, etc.

[0069] For example, target detection algorithms such as R-CNN (Region-based Convolutional Neural Networks) and SSD (Single Shot MultiBox Detector) can be used to identify the battery cells in the image to be used, and obtain the detection frame corresponding to each battery cell. Then, the coordinate values ​​and rotation angles of each detection frame in the image to be used are determined. For example, for each detection frame, the coordinate value of the center point of the detection frame can be calculated as the coordinate value of the detection frame; and the angle between the long side of the detection frame and the positive direction of the Y-axis of the image coordinate system in the image to be used is calculated as the rotation angle of the detection frame to obtain the posture of each detection frame. The posture of each detection frame is used as the posture of the battery cell corresponding to the detection frame, thereby obtaining the posture of each battery cell.

[0070] S103, based on the positions of the individual battery cells and the specified array size, detecting whether there are missing battery cells in the specified area; wherein, when there are no missing battery cells in the specified area, the arrangement of the battery cells in the specified area satisfies the specified array size;

[0071] In this embodiment, the designated array size is a preset size for a designated area, the size of the array formed by the cells when no cells are missing. For example, the designated array size may be 5*5, 6*8, etc. In actual applications, the designated array size is determined by relevant personnel based on the actual production conditions in the designated area.

[0072] It can be understood that, since the posture of the battery cell includes the coordinate value indicating its position, the battery cells belonging to the same row and the battery cells belonging to the same column, as well as the distance between two adjacent battery cells in the same row or the same column can be determined based on the posture of each battery cell identified. Whether there is a missing battery cell between the two adjacent battery cells can be determined based on the distance between the two adjacent battery cells in the same row or the same column. Exemplarily, the distance between two adjacent battery cells in the same row can be calculated based on the coordinate values ​​of each battery cell. If the distance between two adjacent battery cells in any row exceeds the distance threshold set for the row, it is determined that there is a missing battery cell in the row; similarly, the distance between two adjacent battery cells in the same column is calculated. If the distance between two adjacent battery cells in any column exceeds the distance threshold set for the column, it is determined that there is a missing battery cell in the column.

[0073] Furthermore, since the designated area does not contain missing cells, the arrangement of the cells in the designated area satisfies the specified array size. Therefore, whether the designated area contains missing cells can be determined based on whether the rows and columns of the cells identified in the image to be used satisfy the specified array size. If the rows and columns of the cells do not meet the specified array size, it is determined that there are missing cells in the designated area.

[0074] It is understandable that by comprehensively considering the position of each cell and the specified array size, it is possible to accurately detect whether a cell is missing. It should be noted that for the sake of clarity, the specific implementation method for detecting whether a cell is missing in a specified area is introduced below and will not be repeated here.

[0075] S104: If no battery cells are missing, divide the battery cells into a plurality of units to be picked up; wherein each unit to be picked up includes a predetermined number of adjacent battery cells arranged in rows or columns, and the battery cells in each of the divided units to be picked up are arranged in the same manner;

[0076] It is understandable that in actual applications, the number of battery cells that the manipulator can grab at one time is determined by the number of grippers provided at the end of the manipulator. Therefore, when grabbing battery cells, the battery cells in the designated area can be divided into multiple units to be grabbed, each unit to be grabbed contains a predetermined number of adjacent battery cells, and the predetermined number is the number of grippers at the end of the manipulator. For example, if the number of grippers at the end of the manipulator is 3, then each unit to be grabbed includes 3 adjacent battery cells. In addition, the method of dividing each unit to be grabbed is also determined according to the grabbing method of the manipulator used in actual production. For example, if the manipulator grabs by rows, the arrangement method of the battery cells in each unit to be grabbed is arranged in rows. If the manipulator grabs by columns, the arrangement method of the battery cells in each unit to be grabbed is arranged in columns. It should be noted that in a complete grabbing process for all battery cells in a designated area, the grabbing method of the manipulator is the same, that is, all grab by rows, or all grab by columns.

[0077] For example, if there is no missing cell, the position of each cell in the specified area is as follows: Figure 2A As shown, the designated area is filled with 2*6 cells, and the number of grippers at the end of the manipulator is 2. The manipulator grabs by row, so it can be determined that Figure 2A Each row of cells needs to be picked up three times. Figure 2A If there is no missing cell, the position of each cell in the specified area is as follows: Figure 2BAs shown, the designated area is filled with 2*6 cells, and the number of grippers at the end of the manipulator is 2. The manipulator's grasping method is to grasp by column. Figure 2B Each row of cells needs to be picked up once. At this time, each cell to be picked up is as follows: Figure 2B As shown in a dotted box in .

[0078] It is worth mentioning that in actual production, in order to avoid the situation where there is no battery cell at the gripping position of a certain gripper during a grip, the specified array size set for the specified area usually satisfies the following requirements: if the robot grips by rows, the number of columns in the specified array size is an integer multiple of the number of grippers at the end of the robot; if the robot grips by columns, the number of rows in the specified array size is an integer multiple of the number of grippers at the end of the robot.

[0079] S105, for each unit to be grasped, based on the posture of each battery cell contained in the unit to be grasped, determine the grasping posture of the manipulator to grasp the unit to be grasped, and control the manipulator to grasp the battery cells included in the unit to be grasped as a whole according to the determined grasping posture until all battery cells in the specified area are grasped.

[0080] It is understandable that since the posture of each battery cell contained in the unit to be grasped affects the position of each gripper when the robot grasps the unit to be grasped as a whole, the grasping posture of the robot grasping the unit to be grasped can be determined based on the posture of each battery cell contained in the unit to be grasped. The grasping posture of the robot is the posture of the end of the robot when grasping the battery cell.

[0081] For example, according to the posture of each battery cell contained in each unit to be grasped, the conversion relationship between the posture of the battery cell contained in the unit to be grasped and the grasping posture of the manipulator can be used to determine the grasping posture of the manipulator grasping the unit to be grasped. It should be noted that in order to clarify the layout of the scheme, the specific implementation method of determining the grasping posture of the manipulator grasping the unit to be grasped based on the posture of each battery cell contained in the unit to be grasped is introduced in the following embodiment, and it will not be repeated here.

[0082] After determining the gripping posture of the manipulator for gripping each unit to be gripped, the manipulator can be controlled to grip each unit to be gripped as a whole in sequence according to the determined gripping posture until all the battery cells in the specified area are gripped.

[0083] The solution provided by the embodiment of the present application, before grasping the battery cells, uses the posture of each battery cell identified in the image to be used and the specified array size to detect whether there are missing batteries in the specified area, and if there are no missing batteries, the battery cells are divided into multiple units to be grasped. Then, for each unit to be grasped, based on the posture of each battery cell contained in the unit to be grasped, the grasping posture of the manipulator to grasp the unit to be grasped is determined, and the manipulator is controlled to grasp the battery cells included in the unit to be grasped as a whole according to the determined grasping posture until all the battery cells in the specified area are completely grasped. It can be seen that this solution grasps the battery cells only after detecting that there are no missing batteries in the specified area. Compared with the direct grasping of the battery cells in the prior art, it reduces the probability that a gripper cannot grasp the battery cell due to the missing battery cell during grasping, thereby causing an alarm and stopping the current production process, thereby improving the grasping efficiency of the battery cells. In addition, since the probability of alarming and stopping the current production process is reduced, the production efficiency of the battery cells can be further improved.

[0084] Optionally, in another embodiment of the present application, Figure 1 Based on the embodiment shown, Figure 3 As shown, the above step S103 detects whether there are missing cells in the specified area based on the posture of each cell and the specified array size, including steps S1031-S1032:

[0085] S1031, determining the battery cells belonging to the same row and the battery cells belonging to the same column in the designated area based on the positions of the battery cells;

[0086] It is understandable that after obtaining the position and posture of each battery cell, the coordinate position of each battery cell can be determined, and thus, based on the coordinate position, it can be determined whether each battery cell belongs to the same row or the same column.

[0087] For example, in one embodiment, the position of each battery cell includes a center point coordinate value for indicating the position of each battery cell. Then, among the center point coordinate values, the battery cells represented by the center point coordinate values ​​having the same X-axis coordinate value or within a predetermined error range are determined to be in the same column of battery cells, and the battery cells represented by the center point coordinate values ​​having the same Y-axis coordinate value or within a predetermined error range are determined to be in the same column of battery cells. The predetermined error range can be 1 / 5, 1 / 10, etc. of the width of the battery cell itself. It should be noted that the embodiments of the present application do not limit the method for determining the same row or column of battery cells.

[0088] S1032, when at least one of the preset detection conditions is met, determining that a cell is missing in the designated area; otherwise, determining that no cell is missing in the designated area;

[0089] If the robot grasps by row, the preset detection conditions include:

[0090] The distance between two adjacent battery cells in any row of battery cells is greater than a first preset threshold;

[0091] The number of cells in any row is less than the number of columns in the specified array size;

[0092] The number of rows of cells determined is less than the number of rows in the specified array size;

[0093] If the robot grasps by column, the preset detection conditions include:

[0094] The distance between two adjacent battery cells in any column of battery cells is greater than a second preset threshold;

[0095] The number of cells in any column is less than the number of rows in the specified array size;

[0096] The determined number of columns of cells is less than the number of columns in the specified array size.

[0097] It is understandable that when the robot grasps by rows, if there are missing cells in any row, or the number of rows of cells is less than the number of rows in the specified array size, the robot's gripper may miss the cells when grasping them. Similarly, when the robot grasps by columns, if there are missing cells in any column, or the number of columns of cells is less than the number of columns in the specified array size, the robot's gripper may miss the cells when grasping them. Therefore, when detecting whether there are missing cells in a specified area, if the robot grasps by rows, it is necessary to detect whether there are missing cells in each row; if the robot grasps by columns, it is necessary to detect whether there are missing cells in each column.

[0098] If the distance between two adjacent cells in any row is greater than a first preset threshold, there is a missing cell between the two adjacent cells. Similarly, if the distance between two adjacent cells in any column is greater than a second preset threshold, there is a missing cell between the two adjacent cells. For example, the first preset threshold can be the same as or different from the second preset threshold. If the position of each cell in the specified area is as follows Figure 2A As shown, the distance between two adjacent battery cells in a row can be represented by the difference between the X-axis coordinates of the center point coordinate values ​​of the two battery cells, and the distance between two adjacent battery cells in a column can be represented by the difference between the Y-axis coordinates of the center point coordinate values ​​of the two battery cells. The first preset threshold value can be 1.2 times, 1.5 times, etc. of the width of the battery cell itself, and the second preset threshold value can be 1.1 times, 1.2 times, etc. of the length of the battery cell itself.

[0099] Since the method of detecting whether there are missing cells between two adjacent cells cannot identify whether there are missing cells on the edge, and when there are no missing cells in the specified area, the arrangement of the cells in the specified area meets the specified array size, it is also possible to determine whether the number of cells in any row is less than the number of columns in the specified display size. If so, there are missing cells in the row. Similarly, if the number of cells in any column is less than the number of rows in the specified array size, there are missing cells in the column.

[0100] In addition, it is also possible to detect whether the determined number of rows of cells is less than the number of rows in the specified array size. If so, it is determined that an entire row of cells is missing in the specified area. Similarly, if the determined number of columns of cells is less than the number of columns in the specified array size, it is determined that an entire column of cells is missing in the specified area. If none of the above preset detection conditions are met, it is determined that no cells are missing in the specified area.

[0101] It can be seen that through this solution, the situation of missing battery cells in the specified area can be accurately and comprehensively identified, so that it can be accurately judged whether there are missing battery cells in the specified area, and then the battery cells can be grabbed when it is detected that there are no missing battery cells, which can further improve the grabbing efficiency.

[0102] Optionally, in another embodiment of the present application, the identified position and posture of each battery cell is the position and posture of each battery cell in the image coordinate system of the image to be used;

[0103] Accordingly, in this embodiment, Figure 4 As shown, in the above step S105, for each unit to be grasped, based on the posture of each battery cell contained in the unit to be grasped, the grasping posture of the manipulator grasping the unit to be grasped is determined, including steps S401-S403:

[0104] S401, based on the conversion relationship between the world coordinate system and the image coordinate system, convert the position and posture of each identified battery cell in the image coordinate system to obtain the position and posture of each battery cell in the specified area in the world coordinate system;

[0105] It can be understood that through the conversion relationship between the image coordinate system and the camera coordinate system and the conversion relationship between the camera coordinate system and the world coordinate system, the conversion relationship between the image coordinate system and the world coordinate system can be obtained, so that the conversion relationship between the image coordinate system and the world coordinate system can be used to convert the position of each identified battery cell in the image coordinate system into the world coordinate system.

[0106] For example, the position of the battery cell in the image coordinate system can be converted to the camera coordinate system based on the intrinsic parameter matrix and extrinsic parameter matrix of the camera, that is, the coordinates of each point in the image are first converted into normalized coordinates using the intrinsic parameter matrix of the camera, and then the obtained normalized coordinates are converted into coordinates in the camera coordinate system using the extrinsic parameter matrix, so that the position of the battery cell in the image coordinate system can be converted to the camera coordinate system. Then, the position of the battery cell in the camera coordinate system can be converted to the world coordinate system based on the conversion matrix obtained by the hand-eye calibration of the manipulator. Among them, the origin of the world coordinate system can be the center of the manipulator base, or the center of the end of the manipulator, and so on.

[0107] S402: For each group of battery cells in the specified area, perform pose merging on the pose of the group of battery cells in the world coordinate system to obtain a first fitted object pose corresponding to the group of battery cells; wherein, if the battery cells in the unit to be grasped are arranged in rows, a group of battery cells represents battery cells belonging to the same row in the specified area; and if the battery cells in the unit to be grasped are arranged in columns, a group of battery cells represents battery cells belonging to the same column in the specified area;

[0108] In this embodiment, if the cells in the unit to be grasped are arranged in rows, the cells in the specified area are grouped by row, with each group of cells forming a row of cells. At this point, the pose of each row of cells in the world coordinate system is merged to obtain the first fitting object pose corresponding to each row of cells. If the cells in the unit to be grasped are arranged in columns, the cells in the specified area are grouped by column, with each group of cells forming a column of cells. At this point, the pose of each column of cells in the world coordinate system is merged to obtain the first fitting object pose corresponding to each column of cells.

[0109] Optionally, in one implementation, the position and posture of each battery cell in the world coordinate system includes: a coordinate value representing the position of the battery cell in the world coordinate system, and a rotation angle representing the posture of the battery cell in the world coordinate system;

[0110] In this implementation, the coordinate value of each battery cell can be the coordinate value of the center point of the battery cell, or the coordinate value of the corner point, etc.; the rotation angle of each battery cell can be the angle between the long side or short side of the battery cell and the predetermined reference direction in the image, and the predetermined reference direction can be the positive direction of the X-axis, the positive direction of the Y-axis, etc. of the image coordinate system in the image to be used.

[0111] Accordingly, in this implementation, in step S402, the poses of the group of battery cells in the world coordinate system are merged to obtain the first fitting object pose corresponding to the group of battery cells, including:

[0112] Calculate the average value of the coordinate values ​​of the group of battery cells in the world coordinate system as the coordinate value after the pose is merged, and calculate the average value of the rotation angle of the group of battery cells in the world coordinate system as the rotation angle after the pose is merged, and obtain the first fitting object pose corresponding to the group of battery cells.

[0113] In this implementation, the average value of the coordinate values ​​included in the posture of each group of battery cells is used as the coordinate value of the overall position of the group of battery cells, and the average value of the rotation angles included in the posture of each group of battery cells is used as the rotation angle of the entire group of battery cells, thereby obtaining the first fitting object posture corresponding to each group of battery cells. It should be noted that the above method of calculating the first fitting object posture is only an example and should not constitute a limitation of this application. For example, different weights can be assigned to battery cells at different positions in a group, and then the weighted sum of the coordinate values ​​and rotation angles included in the posture of each battery cell is calculated separately as the coordinate value and rotation angle of the first fitting object posture corresponding to the group. This is all reasonable.

[0114] S403, for each unit to be grasped in each group of battery cells in the specified area, based on the first fitting object posture corresponding to the group of battery cells and the pre-recorded specified conversion relationship, determine the grasping posture corresponding to the sorting position of the unit to be grasped in the group of battery cells, as the grasping posture of the manipulator grasping the unit to be grasped; wherein the specified conversion relationship is: in the world coordinate system, the conversion relationship between the fitting object posture of a group of battery cells and the grasping posture corresponding to the units to be grasped at each sorting position in the group of battery cells.

[0115] For example, Figure 2A As shown in the figure, each dotted box is a unit to be grasped, a group of cells is a row of cells, and the ordering position of each unit to be grasped in each group of cells can be from left to right or from right to left. For example, in one embodiment, the ordering position of the unit to be grasped consisting of the two cells on the leftmost side of the figure is 1, the ordering position of the unit to be grasped consisting of the two cells in the middle is 2, and the ordering position of the unit to be grasped consisting of the two cells on the rightmost side is 3.

[0116] It can be understood that since the conversion relationship between the fitting object pose of a group of battery cells in the world coordinate system and the grasping pose corresponding to the units to be grasped at each sorting position in the group of battery cells is pre-recorded, for each unit to be grasped in each group of battery cells, the grasping pose corresponding to the sorting position of each unit to be grasped in the group of battery cells can be determined based on the first fitting object pose corresponding to the group of battery cells and the pre-recorded specified conversion relationship.

[0117] For example, if the specified transformation relationship includes: the coordinate values ​​in the fitted object pose of a group of battery cells are (x, y) and the rotation angle is α; the coordinate values ​​in the grasping pose corresponding to the unit to be grasped at sorting position 1 in the group of battery cells are (x-10, y) and the rotation angle is α; the coordinate values ​​in the grasping pose corresponding to the unit to be grasped at sorting position 2 in the group of battery cells are (x, y) and the rotation angle is α; the coordinate values ​​in the grasping pose corresponding to the unit to be grasped at sorting position 1 in the group of battery cells are (x+10, y) and the rotation angle is α. Then, based on the specified transformation relationship and the first fitted object pose corresponding to the group of battery cells, the grasping pose corresponding to the unit to be grasped at each sorting position in the group of battery cells can be determined, that is, the grasping pose corresponding to each sorting position of the unit to be grasped in the group of battery cells.

[0118] Optionally, in one implementation, in the above step S403, for each unit to be grasped in each group of battery cells in the designated area, a grasping posture corresponding to the sorting position of the unit to be grasped in the group of battery cells is determined from a pre-recorded designated conversion relationship, and before the manipulator grasps the unit to be grasped as the grasping posture, steps B1-B4 are further included:

[0119] B1, obtaining the poses of a specified number of sample cells pre-placed in a specified area in the world coordinate system, and merging the obtained poses to obtain a second fitted object pose; wherein the sample cells are placed in the specified area according to the arrangement of the cells in the unit to be grasped; the specified number is the number of cells contained in a group of cells;

[0120] In this implementation, a specified number of sample cells can be placed in a specified area in advance, and the specified number is the number of cells contained in a group of cells. For example, in actual application, if the robot grabs by row, the sample cells are placed in a row arrangement in the specified area and the specified number is the number of columns in the specified array size preset for the specified area. If the robot grabs by column, the sample cells are placed in a column arrangement in the specified area and the specified number is the number of rows in the specified array size preset for the specified area. In addition, when placing the specified number of sample cells, the specified number of sample cells can be placed according to the spacing between the cells placed in the specified area during production.

[0121] The method for obtaining the pose of each of the specified number of sample cells pre-placed in the specified area in the world coordinate system can be: first obtain an image of the specified area where the specified number of sample cells are placed, and then identify the pose of each cell from the acquired image. The method for identifying the pose of the cell from the image can refer to the relevant description of step S102 above and will not be repeated here. In addition, the method for merging the acquired poses to obtain the second fitted object pose can refer to the description of step S402 above and will not be repeated here.

[0122] B2, dividing the specified number of sample cells into a plurality of sample units, and determining the sorting position of each sample unit in the specified number of sample cells; wherein each first sample unit includes a predetermined number of adjacent cells;

[0123] In this implementation, the method of dividing the specified number of sample cells into a plurality of sample units can refer to the relevant description of the above step S104, which will not be repeated here.

[0124] The method for determining the ranking position of each sample unit among the specified number of sample cells can be: if the cells in each sample unit are arranged in a row arrangement, the X-axis coordinates of the cells contained in each sample unit can be compared, for example, the sample units can be sorted from small to large according to the average value of the X-axis coordinates of the cells contained in each sample unit, and the ranking position of each sample unit among the specified number of sample cells can be obtained. If the cells in each sample unit are arranged in a column arrangement, the Y-axis coordinates of the cells contained in each sample unit can be compared, for example, the sample units can be sorted from small to large according to the average value of the Y-axis coordinates of the cells contained in each sample unit, and the ranking position of each sample unit among the specified number of sample cells can be obtained.

[0125] B3, for each sample unit, by adjusting the position of the manipulator to obtain the grasping position when the manipulator can grasp the sample unit as a whole;

[0126] In this implementation, for each sample unit, the robot can be grasped by continuously adjusting the posture of the robot to obtain the posture when the robot can grasp the sample unit as a whole. For example, in actual application, the robot can be taught to grasp using a teaching pendant, and teaching is required for each sample unit. That is, for each sample unit, the parameters in the teaching pendant are adjusted so that the robot can grasp the sample unit as a whole, and the grasping posture when the robot can grasp the sample unit as a whole is obtained. Among them, the teaching pendant is a robot auxiliary device that teaches the robot the operating steps to perform various tasks by manually controlling the kinematic parameters and movements of the robot.

[0127] B4. For each sorting position, determine a conversion relationship between the grasping posture corresponding to the sample unit at the sorting position and the second fitting object posture, and record it as a designated conversion relationship.

[0128] It can be understood that for each sorting position, the conversion relationship between the grasping posture corresponding to the sample unit at the sorting position and the second fitting object posture can be determined based on the difference between the grasping posture corresponding to the sample unit at the sorting position and the second fitting object posture.

[0129] For example, if the coordinate value in the second fitting object pose is (10, 20), the rotation angle is β, the coordinate value in the grasping pose corresponding to the sample unit with sorting position 1 is (0, 20), and the rotation angle is 10°; the coordinate value in the grasping pose corresponding to the sample unit with sorting position 2 is (10, 20), and the rotation angle is 10°; the coordinate value in the grasping pose corresponding to the sample unit with sorting position 3 is (20, 20), and the rotation angle is 10°; the conversion relationship between the second fitting object pose and the grasping pose at each sorting position can be determined as follows: if the coordinate value in the second fitting object pose is (x, y), and the rotation angle is α, then the coordinate value in the grasping pose corresponding to sorting position 1 is (x-10, y), and the rotation angle is α; the coordinate value in the grasping pose corresponding to sorting position 2 is (x, y), and the rotation angle is α; the coordinate value in the grasping pose corresponding to sorting position 3 is (x+10, y), and the rotation angle is α.

[0130] It can be understood that after obtaining the conversion relationship between the grasping posture corresponding to the sample unit at each sorting position and the second fitting object posture, the conversion relationship can be used as the conversion relationship between the fitting object posture of a group of battery cells and the grasping posture corresponding to the units to be grasped at each sorting position in the group of battery cells in the world coordinate system, that is, as a specified conversion relationship, and the specified conversion relationship is recorded so that the specified conversion relationship can be used later to determine the grasping posture corresponding to each unit to be grasped in each group of battery cells during actual grasping.

[0131] It is understandable that this embodiment only requires merging the positions of the battery cells by row or column. If the number of grippers in the robot changes during actual production, it is only necessary to redefine the designated transformation relationship according to the above steps B1-B4. Compared with merging the positions of each sample unit in a group of battery cells and determining the gripping position based on the position of each sample unit, the operation is simpler.

[0132] It can be seen that through this scheme, the conversion relationship between the fitted object posture of a group of battery cells and the grasping posture corresponding to each sorting position in the group of battery cells can be accurately obtained, so that the grasping posture corresponding to each unit to be grasped can be accurately calculated using this conversion relationship, thereby improving the grasping stability.

[0133] Optionally, in another embodiment of the present application, before identifying the posture of each battery cell in the image to be used in the above step S102, the following steps are further included:

[0134] Detect the positive and negative polarity directions of each battery cell in the image to be used;

[0135] Accordingly, in this embodiment, the step S102 of identifying the position and posture of each battery cell in the image to be used includes:

[0136] If the positive and negative pole directions of each battery cell in the image to be used are consistent, the position and posture of each battery cell in the image to be used are identified.

[0137] For example, an image recognition algorithm based on deep learning can be used to identify the positive and negative pole directions of each battery cell. It should be noted that the battery cells are usually placed with the surface with the positive and negative pole markings facing upwards. Figure 2A As shown in the figure Indicates the positive electrode, Indicates the negative electrode, Figure 2A The positive and negative directions of the battery cells are "positive at the top and negative at the bottom." Furthermore, if the battery cells are placed upside down and the surface with the positive and negative markings is not recognized, it is determined that the positive and negative directions of the battery cells in the image to be used are inconsistent.

[0138] It is understandable that, since a series of rigorous tests are required to ensure quality during the production of battery cells, when short-circuit testing, charge-discharge testing, and other processes are required, it is necessary to ensure that the positive and negative poles of each battery cell are in the same direction. If they are not consistent, the testing process of the corresponding process will be affected, resulting in production suspension or other serious consequences. Therefore, in this implementation, before detecting whether a battery cell is missing, it is first detected whether the positive and negative poles of each battery cell are in the same direction. If the positive and negative poles of each battery cell in the image to be used are consistent, the above-mentioned step S102 and the subsequent capture process are executed.

[0139] Optionally, in one implementation, the method further includes:

[0140] If it is detected that the positive and negative pole directions of any battery cell are inconsistent with those of other battery cells, or if a battery cell is missing in the designated area, an alarm will be issued.

[0141] If it is detected that the positive and negative pole directions of any battery cell are inconsistent with those of other battery cells, or if there are battery cells missing in the designated area, an alarm will be issued so that the staff can promptly discover the problems in the production process and intervene to deal with them, thereby improving production efficiency.

[0142] In addition, it is understandable that in this solution, missing cells are detected before grabbing, and if a cell is missing, only one alarm is required. In contrast, when the existing technology directly grabs the cell, multiple missing cell detections and alarms may occur, seriously affecting the efficiency of cell grabbing and production. In addition, the alarm is issued before the cell is grabbed, rather than during the cell grabbing process, which avoids the situation where the same batch of cells in a designated area are dispersed to different locations due to the operation of the production line, thus affecting production.

[0143] It can be seen that through this solution, the battery cell grabbing efficiency and production efficiency can be further improved.

[0144] Corresponding to the above method embodiment, the present application embodiment also provides a battery cell grabbing system, such as Figure 5 As shown, it includes a camera 510, a control device 520 and a manipulator 530;

[0145] The camera 510 is used to capture an image of a designated area where the battery cells are placed;

[0146] The control device 520 is configured to execute any one of the above-mentioned battery cell grabbing methods;

[0147] The manipulator 530 is used to grab the battery cell under the control of the control device.

[0148] It should be noted that the specific functional implementation of each device involved in the above system has been introduced in the above method embodiment and will not be repeated here.

[0149] As can be seen, compared to the prior art of directly grasping the battery cells, this solution reduces the probability of a gripper failing to grasp a battery cell due to a missing battery cell, which would result in an alarm and stoppage of the current production process, thereby improving the battery cell grasping efficiency. In addition, since the probability of an alarm and stoppage of the current production process is reduced, the production efficiency of the battery cells can be further improved.

[0150] In order to better understand this solution, the battery cell grabbing method provided in the embodiment of the present application is described below with reference to a specific example.

[0151] The battery cell grasping method provided in this example requires the cooperation of a robot arm, a camera, and a control device. The camera is responsible for taking pictures, the robot arm is responsible for grasping the battery cell, and the control device is used to process the image captured by the camera to obtain the grasping posture of the battery cell and control the movement of the robot arm.

[0152] For example, a camera mounted on the end effector of a manipulator can be used. Because the camera's field of view is small and cannot cover the entire battery cell area (corresponding to the designated area above), the camera must be used to take multiple photos. Before each photo, the manipulator moves the camera to the appropriate position, captures images of a portion of the battery cell, and then combines these images to obtain an image covering the entire battery cell area. This combined image can be used to determine the position and pose of all the battery cells. Once the camera's field of view is large enough, a single photo capture is sufficient.

[0153] After taking the photo, the control device performs a series of tests on the image, and then calculates the grasping posture, and the robot arm completes the grasping.

[0154] like Figure 6 As shown, the camera photographing process may include steps S601-S605:

[0155] S601, the camera takes a photo at a photo location (corresponding to the preset point above);

[0156] After the battery cell is in place, the robot moves the camera to a photo taking position to take pictures.

[0157] S602, the camera sends a photo taking completion signal to the control device;

[0158] After the photo is taken, the camera sends a photo completion signal to the control device via TCP (Transmission Control Protocol).

[0159] S603, the control device determines whether all photo shooting positions have been completed; if so, execute S604; if not, execute S605;

[0160] S604: Control the device to merge the images obtained from each photo (corresponding to the image stitching process described above) to obtain an image containing the entire battery cell area.

[0161] S605, the robot moves and drives the camera to the next photo taking position;

[0162] If the image capture is not complete, the control device receives a signal and sends a movement command, controlling the robot arm to move the camera to the next image capture location. Steps S601-S603 are then repeated until all image capture locations are complete. After all image capture locations are complete, the images from each capture are merged, and the poses of the battery cells in the merged images are identified to determine the poses of all battery cells.

[0163] After taking the photo, the control device will perform battery cell detection. The detection process is as follows: Figure 7 As shown, it includes steps S701-S705:

[0164] S701, check whether the positive and negative poles of the battery cells are in the same direction; if so, execute S702, if not, execute S705;

[0165] S702: Sort the positions of the battery cells;

[0166] S703: Determine whether the row and column detection is normal; if so, execute S704; if not, execute S705;

[0167] S704: Determine whether the array detection is normal; if not, execute S705;

[0168] S705, alarm is issued;

[0169] If the judgment result of S704 is yes, the test passes and the test ends. That is, first, the positive and negative poles of the battery cell are detected. If the positive and negative poles on the upper side of the battery cell are inconsistent, an alarm will be issued; if they are consistent, the number of battery cells will be detected. Before the test, the posture sorting must be performed first to ensure that the battery cell posture is sorted according to the array (from left to right, from top to bottom, in row and column order); then the row and column detection is performed to detect whether there are missing batteries in each row / column, and whether the number of batteries in each row / column meets the minimum number of batteries. If any of the tests is abnormal, an alarm will be issued; then the array detection is performed to detect whether the number of each row / column is consistent and whether the minimum number of rows / columns is met. When skipping rows / columns is not supported, skipping rows / columns is also performed. Similar to the row and column detection, as long as one of the tests is abnormal, an alarm will be issued. Once all these tests are completed and passed, the battery cell grabbing can continue.

[0170] After the test is passed, the control device executes the process of cell grabbing, such as Figure 8 As shown, it includes steps S801-S804:

[0171] S801, performing pose fitting on the cells by row or column (corresponding to the pose merging mentioned above);

[0172] S802, determining each unit to be grasped and performing grasping teaching to obtain the actual grasping posture corresponding to each grasping unit;

[0173] S803, sending a grabbing instruction to the robot arm;

[0174] S804: Control the manipulator to grasp according to the actual grasping posture corresponding to each grasping unit in sequence until all battery cells are grasped.

[0175] It is understandable that the robot cannot grab all the battery cells at once and needs to grab them multiple times. First, the battery cell posture must be fitted, and the fitting is performed by row or column, that is, the entire row posture or the entire column posture is fitted into one posture, thereby obtaining multiple row / column postures (corresponding to the first fitting object posture mentioned above). After the fitting is completed, to perform grasping teaching, first determine how many times a row / column is to be grasped. Assuming that this number is N (N is a positive integer), a row / column must be taught N times, and finally N grasping postures in the row / column are obtained. After the posture is output, the robot completes the grasping in sequence.

[0176] It can be seen that through this solution, row and column detection is performed before grasping to avoid missing cells in the row / column, and array detection is performed before grasping to avoid missing entire rows / columns, thereby ensuring the effectiveness of grasping. Compared with the prior art of directly grasping the cells, the probability of a gripper failing to grasp a cell due to missing cells during grasping, resulting in an alarm and stopping the current production process, is reduced, thereby improving the grasping efficiency of the cells. In addition, since the probability of an alarm and stopping the current production process is reduced, the production efficiency of the cells can be further improved. In addition, the setting of the number of grasps makes the way of grasping a row / column more flexible, and the grasping plan can be arranged more flexibly.

[0177] Corresponding to the above method embodiment, the present application embodiment also provides a battery cell grabbing device, such as Figure 9 As shown, the device includes:

[0178] An acquisition module 910 is configured to acquire an image of the designated area where the battery cells are placed, taken by a camera above the designated area, as an image to be used;

[0179] Identification module 920, used to identify the position and posture of each battery cell in the image to be used;

[0180] A detection module 930 is configured to detect whether there are missing cells in the designated area based on the positions of the individual cells and the designated array size; wherein, when there are no missing cells in the designated area, the arrangement of the cells in the designated area satisfies the designated array size;

[0181] A division module 940 is configured to divide each battery cell into a plurality of to-be-grabbed units if no battery cell is missing; wherein each to-be-grabbed unit includes a predetermined number of adjacent battery cells arranged in rows or columns, and the battery cells in each of the divided to-be-grabbed units are arranged in the same manner;

[0182] The grasping module 950 is used to determine the grasping posture of the manipulator grasping the unit to be grasped based on the posture of each battery cell contained in the unit to be grasped, and control the manipulator to grasp the battery cells included in the unit to be grasped as a whole according to the determined grasping posture until all battery cells in the designated area are grasped.

[0183] Optionally, the detection module 930 includes:

[0184] A first determining submodule is configured to determine, based on the positions of the individual battery cells, battery cells belonging to the same row and battery cells belonging to the same column in the designated area;

[0185] A second determining submodule is configured to determine whether a cell is missing in the designated area when at least one of the preset detection conditions is met; otherwise, determine whether a cell is missing in the designated area;

[0186] If the manipulator grasps by row, the preset detection conditions include:

[0187] The distance between two adjacent battery cells in any row of battery cells is greater than a first preset threshold;

[0188] The number of cells in any row is less than the number of columns in the specified array size;

[0189] The determined number of rows of cells is less than the number of rows in the specified array size;

[0190] If the robot grasps by row, the preset detection conditions include:

[0191] The distance between two adjacent battery cells in any column of battery cells is greater than a second preset threshold;

[0192] The number of cells in any column is less than the number of rows in the specified array size;

[0193] The determined number of columns of battery cells is smaller than the number of columns in the specified array size.

[0194] Optionally, the identified position and posture of each battery cell is the position and posture of each battery cell in the image coordinate system of the image to be used;

[0195] The capture module 950 includes:

[0196] a conversion submodule, configured to convert the position and posture of each identified battery cell in the image coordinate system based on a conversion relationship between the world coordinate system and the image coordinate system, so as to obtain the position and posture of each battery cell in the designated area in the world coordinate system;

[0197] a merging submodule, configured to merge the poses of each group of battery cells in the specified area in the world coordinate system to obtain a first fitted object pose corresponding to the group of battery cells; wherein, if the battery cells in the unit to be grasped are arranged in rows, a group of battery cells represents the battery cells belonging to the same row in the specified area; and if the battery cells in the unit to be grasped are arranged in columns, a group of battery cells represents the battery cells belonging to the same column in the specified area;

[0198] The grasping posture determination submodule is used to determine, for each unit to be grasped in each group of battery cells in the specified area, based on the first fitting object posture corresponding to the group of battery cells and the pre-recorded specified conversion relationship, the grasping posture corresponding to the sorting position of the unit to be grasped in the group of battery cells, as the grasping posture of the manipulator grasping the unit to be grasped; wherein, the specified conversion relationship is: in the world coordinate system, the conversion relationship between the fitting object posture of a group of battery cells and the grasping posture corresponding to the units to be grasped at each sorting position in the group of battery cells.

[0199] Optionally, the position and posture of each battery cell in the world coordinate system includes: a coordinate value representing the position of the battery cell in the world coordinate system, and a rotation angle representing the posture of the battery cell in the world coordinate system;

[0200] The merging submodule is specifically used for:

[0201] Calculate the average value of the coordinate values ​​of the group of battery cells in the world coordinate system as the coordinate value after the pose is merged, and calculate the average value of the rotation angle of the group of battery cells in the world coordinate system as the rotation angle after the pose is merged, to obtain the first fitting object pose corresponding to the group of battery cells.

[0202] Optionally, the device further comprises:

[0203] A sample pose acquisition module is configured to determine, for each unit to be grasped in each group of battery cells in the designated area, a grasping pose corresponding to the sorting position of the unit to be grasped in the group of battery cells from a pre-recorded designated conversion relationship, and obtain the poses of a specified number of sample battery cells pre-placed in the designated area in the world coordinate system before the manipulator grasps the unit to be grasped as the grasping pose, and merge the obtained poses to obtain a second fitted object pose; wherein, the sample battery cells are placed in the designated area according to the arrangement of the battery cells in the unit to be grasped; and the specified number is the number of battery cells contained in a group of battery cells;

[0204] a sample unit division module, configured to divide the specified number of sample cells into a plurality of sample units and determine a sorting position of each sample unit in the specified number of sample cells; wherein each first sample unit includes the adjacent predetermined number of cells;

[0205] An adjustment module, configured to adjust the posture of the manipulator for each sample unit so as to obtain a grasping posture when the manipulator can grasp the sample unit as a whole;

[0206] The recording module is used to determine, for each sorting position, a conversion relationship between the grasping posture corresponding to the sample unit at the sorting position and the second fitting object posture, and record the conversion relationship as a designated conversion relationship.

[0207] Optionally, the device further comprises:

[0208] a positive and negative pole detection module, configured to detect the positive and negative pole directions of each battery cell in the image to be used before the recognition module 920 recognizes the posture of each battery cell in the image to be used;

[0209] The identification module 920 is specifically configured to:

[0210] If the positive and negative pole directions of the battery cells in the image to be used are consistent, the posture of the battery cells in the image to be used is identified.

[0211] Optionally, the device further comprises:

[0212] The alarm module is used to issue an alarm if it is detected that the positive and negative pole directions of any battery cell are inconsistent with those of other battery cells, or that a battery cell is missing in the designated area.

[0213] Optionally, the camera is mounted on an end effector of the manipulator; the acquisition module 910 includes:

[0214] a photographing submodule, configured to control the manipulator to sequentially move to each of a plurality of preset points above the designated area, so that the camera takes a photograph at each point to obtain a plurality of images;

[0215] The stitching submodule is used to stitch the multiple images obtained to obtain an image to be used.

[0216] In the technical solution of this application, the operations involved in acquiring, storing, using, processing, transmitting, providing and disclosing images are all carried out with the user's authorization.

[0217] The present application also provides an electronic device, such as Figure 10 Shown, including:

[0218] Memory 1001, used for storing computer programs;

[0219] The processor 1002 is configured to execute the program stored in the memory 1001 to implement the steps of any of the above-mentioned cell grabbing methods.

[0220] Furthermore, the electronic device may further include a communication bus and / or a communication interface, and the processor 1002, the communication interface, and the memory 1001 communicate with each other via the communication bus.

[0221] The communication bus mentioned in the electronic device mentioned above may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0222] The communication interface is used for communication between the above electronic device and other devices.

[0223] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0224] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0225] In another embodiment provided in the present application, a computer-readable storage medium is further provided, wherein a computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the steps of any of the above-mentioned battery cell grabbing methods are implemented.

[0226] In another embodiment provided in the present application, a computer program product including instructions is further provided, which, when executed on a computer, enables the computer to execute any of the cell grabbing methods in the above embodiments.

[0227] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it 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. When the computer program instructions are loaded and 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 device. 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 one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. 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 data center that includes one or more available media integrations. 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 solid-state drive (SSD).

[0228] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0229] Each embodiment in this specification is described in a related manner. Similar portions between the embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system and device embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For related portions, refer to the descriptions of the method embodiments.

[0230] The above description is only a preferred embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application are included in the scope of protection of the present application.

Claims

1. A method for grabbing a battery cell, characterized in that: The method comprises: Acquire an image of the designated area where the battery cells are placed, captured by a camera above the designated area, as the image to be used; Identifying the position and posture of each battery cell in the image to be used; Based on the position of each battery cell and the specified array size, detecting whether there is a missing battery cell in the specified area; wherein, when there is no missing battery cell in the specified area, the arrangement of the battery cells in the specified area meets the specified array size; If there are no missing cells, the cells are divided into a plurality of cells to be picked up; wherein each cell to be picked up includes a predetermined number of adjacent cells arranged in rows or columns, and the cells in each of the cells to be picked up are arranged in the same manner; For each unit to be grasped, based on the posture of each battery cell contained in the unit to be grasped, the grasping posture of the manipulator to grasp the unit to be grasped is determined, and the manipulator is controlled to grasp the battery cells included in the unit to be grasped as a whole according to the determined grasping posture until all battery cells in the designated area are grasped.

2. The method according to claim 1, characterized in that The detecting whether there is a missing cell in the specified area based on the position of each cell and the specified array size includes: Determining, based on the positions of the individual battery cells, battery cells belonging to the same row and battery cells belonging to the same column in the designated area; When at least one of the preset detection conditions is met, it is determined that there is a missing cell in the designated area; otherwise, it is determined that there is no missing cell in the designated area; If the manipulator grasps by row, the preset detection conditions include: The distance between two adjacent battery cells in any row of battery cells is greater than a first preset threshold; The number of cells in any row is less than the number of columns in the specified array size; The determined number of rows of cells is less than the number of rows in the specified array size; If the manipulator grasps by column, the preset detection conditions include: The distance between two adjacent battery cells in any column of battery cells is greater than a second preset threshold; The number of cells in any column is less than the number of rows in the specified array size; The determined number of columns of battery cells is smaller than the number of columns in the specified array size.

3. The method according to claim 1, characterized in that The identified position and posture of each battery cell is the position and posture of each battery cell in the image coordinate system of the image to be used; The method of determining, for each unit to be grasped, a grasping posture of the manipulator grasping the unit to be grasped based on the posture of each battery cell contained in the unit to be grasped, includes: Based on the conversion relationship between the world coordinate system and the image coordinate system, the position and posture of each identified battery cell in the image coordinate system are converted to obtain the position and posture of each battery cell in the designated area in the world coordinate system; For each group of battery cells in the specified area, perform pose merging on the group of battery cells in the world coordinate system to obtain a first fitted object pose corresponding to the group of battery cells; wherein, when the battery cells in the unit to be grasped are arranged in rows, a group of battery cells represents battery cells belonging to the same row in the specified area; when the battery cells in the unit to be grasped are arranged in columns, a group of battery cells represents battery cells belonging to the same column in the specified area; For each unit to be grasped in each group of battery cells in the specified area, based on the first fitting object posture corresponding to the group of battery cells and the pre-recorded specified conversion relationship, the grasping posture corresponding to the sorting position of the unit to be grasped in the group of battery cells is determined as the grasping posture of the manipulator grasping the unit to be grasped; wherein, the specified conversion relationship is: in the world coordinate system, the conversion relationship between the fitting object posture of a group of battery cells and the grasping posture corresponding to the units to be grasped at each sorting position in the group of battery cells.

4. The method according to claim 3, characterized in that The position and posture of each battery cell in the world coordinate system includes: a coordinate value representing the position of the battery cell in the world coordinate system, and a rotation angle representing the posture of the battery cell in the world coordinate system; Merging the poses of the group of battery cells in the world coordinate system to obtain a first fitting object pose corresponding to the group of battery cells includes: Calculate the average value of the coordinate values ​​of the group of battery cells in the world coordinate system as the coordinate value after the pose is merged, and calculate the average value of the rotation angle of the group of battery cells in the world coordinate system as the rotation angle after the pose is merged, to obtain the first fitting object pose corresponding to the group of battery cells.

5. The method according to claim 3, characterized in that For each unit to be grasped in each group of battery cells in the designated area, determining, from a pre-recorded designated conversion relationship, a grasping posture corresponding to the sorting position of the unit to be grasped in the group of battery cells, and using the grasping posture as the grasping posture for the manipulator to grasp the unit to be grasped, the method further includes: Obtaining the pose of each of a specified number of sample cells pre-placed in the specified area in the world coordinate system, and merging the obtained poses to obtain a second fitted object pose; wherein the sample cells are placed in the specified area according to the arrangement of the cells in the unit to be grasped; and the specified number is the number of cells included in a group of cells; Dividing the specified number of sample cells into a plurality of sample units, and determining a sorting position of each sample unit in the specified number of sample cells; wherein each first sample unit includes the adjacent predetermined number of cells; For each sample unit, the position and posture of the manipulator are adjusted to obtain a grasping posture when the manipulator can grasp the sample unit as a whole; For each sorting position, a conversion relationship between the grasping posture corresponding to the sample unit at the sorting position and the second fitting object posture is determined and recorded as a designated conversion relationship.

6. The method according to any one of claims 1 to 5, characterized in that Before identifying the position and posture of each battery cell in the image to be used, the method further includes: Detecting the positive and negative polarity directions of each battery cell in the image to be used; The identifying the position and posture of each battery cell in the image to be used includes: If the positive and negative pole directions of the battery cells in the image to be used are consistent, the posture of the battery cells in the image to be used is identified.

7. The method according to claim 6, characterized in that The method further comprises: If it is detected that the positive and negative pole directions of any battery cell are inconsistent with those of other battery cells, or if a battery cell is missing in the designated area, an alarm is issued.

8. The method according to any one of claims 1 to 5, characterized in that The camera is mounted on the end picker of the manipulator; the image of the designated area where the battery cells to be picked up are placed, taken by the camera above the designated area, is obtained as the image to be used, including: Controlling the manipulator to move sequentially to each of a plurality of preset points above the designated area, so that the camera takes a picture at each point to obtain a plurality of images; The obtained multiple images are stitched together to obtain an image to be used.

9. A battery cell grabbing system, characterized in that: Includes camera, control equipment and manipulator; The camera is used to capture an image of a designated area where the battery cells are placed; The control device is used to execute the method according to any one of claims 1 to 8; The manipulator is used to grab the battery cell under the control of the control device.

10. A battery cell grabbing device, characterized in that: The device comprises: an acquisition module, configured to acquire an image of the designated area where the battery cells are placed, taken by a camera above the designated area, as an image to be used; A recognition module, configured to recognize the position and posture of each battery cell in the image to be used; a detection module, configured to detect whether there are missing cells in the designated area based on the positions of the individual cells and the designated array size; wherein, when there are no missing cells in the designated area, the arrangement of the cells in the designated area satisfies the designated array size; a division module, configured to divide each battery cell into a plurality of to-be-grabbed units if no battery cell is missing; wherein each to-be-grabbed unit includes a predetermined number of adjacent battery cells arranged in rows or columns, and the battery cells in each of the divided to-be-grabbed units are arranged in the same manner; The grasping module is used to determine the grasping posture of the manipulator grasping the unit to be grasped based on the posture of each battery cell contained in the unit to be grasped, and control the manipulator to grasp the battery cells included in the unit to be grasped as a whole according to the determined grasping posture until all battery cells in the designated area are grasped.

11. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the method according to any one of claims 1 to 8 when executing a program stored in a memory.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

13. A computer program product, characterized in that The computer program product comprises executable instructions, and when the executable instructions are executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 8.

Images