Sample testing method, device, equipment and medium

Abstract

The embodiment of the invention provides a sample testing method, device and equipment and a medium, which are used for solving the problem that the consistency of drop tests of samples with unified specifications cannot be ensured in the related technology. The electronic equipment determines target position information of a central point of the top surface of the sample, sends the target position information to the grabbing equipment, so that the grabbing equipment adsorbs the sample based on the target position information, determines gravity center position information of the sample according to a torque value acquired by the torque sensor, determines a target edge corresponding to the test task, and sends the target edge to the test equipment; determining a target rotation angle based on the gravity center position information and the target edge; the grabbing equipment rotates by the target rotation angle based on the target edge, so that the gravity line of the sample can pass through the gravity center and the target edge, the sample is subjected to a drop test, a user does not need to place the sample in the process, target position information and the target rotation angle can be determined, the consistency of drop tests of samples of unified specifications can be ensured, and the test efficiency is improved. And the accuracy of sample testing is improved.

Description

Technical Field

[0001] The present application relates to the field of experimental testing technology, and in particular to a sample testing method, device, equipment and medium. Background Art

[0002] During the product development process, product outer packaging strength testing is also an essential test item. Drop test is one of the main methods to test the strength of samples such as packaging boxes. Drop test can intuitively reflect the impact resistance of the package when subjected to vertical impact and the protection ability of the package to the contents. Therefore, various types of drop test equipment corresponding to it have also been developed. According to the drop test method of GB / T4857.5-92 for packaging, the outer packaging needs to be tested for planes, edges and corners. It also stipulates that when the surface falls or the edges fall, the maximum angle between the sample falling surface, edge and horizontal plane shall not exceed 2°; when the corner falls, the angle error between the specified surface on the sample and the horizontal plane shall not exceed ±5°, and no matter what state and shape of the test sample, the gravity line of the test sample should pass through the dropped surface, line and point. The ISTA test standard also stipulates that products of different weights should correspond to different drop heights. The above regulations indicate that the placement of samples must be accurate when performing drop tests. Only when samples fall correctly can we objectively and accurately reflect the impact strength of the sample packaging and the protection of the packaging to the contents. The current sample testing method cannot guarantee the accuracy of the sample placement, and artificial placement of samples cannot guarantee the consistency of the drop test of samples of uniform specifications. Summary of the invention

[0003] The embodiments of the present application provide a sample testing method, device, equipment and medium, which are used to solve the problem in the related art that the consistency of drop tests on samples of uniform specifications cannot be guaranteed.

[0004] In a first aspect, an embodiment of the present application provides a sample testing method, the method comprising: Determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the collected image in the world coordinate system; send the target position information to the grasping device so that the grasping device absorbs the sample based on the target position information; Obtain the current test task and the center of gravity position information of the sample determined based on the torque value obtained by the torque sensor. If the test task is determined to be an edge test or a corner test, determine the target edge corresponding to the test task, determine a straight line passing through the center of gravity position information and the target edge and perpendicular to the target edge, and determine the angle between the straight line and the current gravity line as the target rotation angle; The position information of each vertex of the target edge and the acquired target rotation angle are sent to the grasping device, so that the grasping device rotates the sample based on the received target edge and the target rotation angle to perform a drop test on the sample.

[0005] Further, determining the center of gravity position information of the sample based on the torque value obtained by the torque sensor includes: Obtaining the torque value collected by the torque sensor in each preset direction; determining the offset of the center of gravity of the sample in each preset direction according to the ratio of the torque value in each preset direction to the weight of the sample; Determine the center position information of the center point of the sample in the world coordinate system according to the position information of each vertex of the sample in the world coordinate system; The center of gravity position information of the sample is determined according to the center position information and the offset in each preset direction.

[0006] Further, if it is determined that the test task is a test corner, determining a target edge corresponding to the test task includes: If it is determined that the test task is to test the angle, any vertex of the sample is obtained, and any two lines containing the vertex are determined as target edges corresponding to the test task; Sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device includes: If the determined target edge includes multiple edges, the position information of the vertex of each determined target edge and the target rotation angle obtained based on each target edge are sent to the grasping device.

[0007] Further, if it is determined that the test task is an edge test, determining a target edge corresponding to the test task includes: If it is determined that the test task is an edge test, then obtaining untested edges according to pre-saved tested edges and a pre-built modeling body of the sample; Identify the graphic features in the image and determine the target surface corresponding to the graphic features in the modeling body; when determining that the top surface of the sample is the target surface of the modeling body, the edge corresponding to the untested edge is the target edge corresponding to the test task.

[0008] Furthermore, the method further comprises: If the drop test is currently being performed on the sample for the first time, identifying graphic features of the sample in the image; Repeat the following steps until the graphic features of each surface of the sample are obtained: Sending a flipping instruction to the gripping device so that the gripping device flips the sample based on a preset flipping method, and obtains the flipped image captured by the image acquisition device; identifying graphic features of the sample in the image; According to the pre-saved flipping method and each acquired graphic feature, three-dimensional modeling is performed on the sample to obtain a modeled body of the sample.

[0009] Furthermore, after sending the target position information to the grasping device and before sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device, the method further includes: Obtaining the weight of the sample acquired by the torque sensor; obtaining the target height saved for the weight; The step of sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device includes: The target height, the position information of each vertex of the target edge, and the acquired target rotation angle are sent to a gripping device, so that the gripping device performs a drop test on the sample when moving the sample to the target height.

[0010] Furthermore, after acquiring the image captured by the image acquisition device, before determining the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the image in the world coordinate system, the method further includes: If the image contains at least two samples, obtaining the area where the sample to be tested is located according to the stage of the current sample test; Obtain a sub-region saved for the region in the image; based on the sub-region, perform subsequent steps to determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the image in the world coordinate system.

[0011] Furthermore, the method further comprises: After the grabbing device controls the sample to fall for a preset time, acquiring graphic features of the sample in the collected falling image; Determine the similarity between the graphic feature and each graphic feature of the sample saved in advance; if any similarity is lower than a threshold, determine that the sample is damaged; if each similarity is not lower than the threshold, determine that the sample is not damaged.

[0012] In a second aspect, an embodiment of the present application further provides a sample testing device, the device comprising: A processing module, used to determine the target position information of the center point of the top surface of the sample according to the position information of each vertex of the top surface of the sample in the collected image in the world coordinate system; send the target position information to the grasping device so that the grasping device adsorbs the sample based on the target position information; obtain the current test task and the center of gravity position information of the sample determined based on the torque value obtained by the torque sensor, if the test task is determined to be an edge test or a corner test, then determine the target edge corresponding to the test task, determine the straight line that passes through the center of gravity position information and the target edge and is perpendicular to the target edge, and determine the angle between the straight line and the current gravity line as the target rotation angle; The sending module is used to send the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device, so that the grasping device rotates the sample based on the received target edge and the target rotation angle to perform a drop test on the sample.

[0013] Furthermore, the processing module is specifically used to obtain the torque value collected by the torque sensor in each preset direction; determine the offset of the center of gravity of the sample in each preset direction according to the ratio of the torque value in each preset direction to the weight of the sample; determine the center position information of the center point of the sample in the world coordinate system according to the position information of each vertex of the sample in the world coordinate system; determine the center of gravity position information of the sample according to the center position information and the offset in each preset direction.

[0014] Furthermore, the processing module is specifically used to obtain any vertex of the sample and determine any two edges including the vertex as target edges corresponding to the test task if it is determined that the test task is a test angle; The sending module is specifically configured to send the position information of the vertices of each determined target edge and the target rotation angle obtained based on each target edge to the grasping device if the determined target edge includes multiple edges.

[0015] Furthermore, the processing module is specifically used to obtain untested edges based on pre-saved tested edges and a pre-constructed modeling body of the sample if it is determined that the test task is an edge test; identify graphic features in the image and determine the target surface corresponding to the graphic features in the modeling body; and when determining that the top surface of the sample is the target surface of the modeling body, the edge corresponding to the untested edge is the target edge corresponding to the test task.

[0016] Furthermore, the processing module is also used to identify the graphic features of the sample in the image if this is the first time that the sample is drop tested; and repeatedly perform the following steps until the graphic features of each surface of the sample are acquired: sending a flipping instruction to the grasping device so that the grasping device flips the sample based on a preset flipping method, and acquires the flipped image acquired by the image acquisition device; identifying the graphic features of the sample in the image; and performing three-dimensional modeling of the sample according to the pre-saved flipping method and each acquired graphic feature to acquire a modeled body of the sample.

[0017] Furthermore, the processing module is further used to obtain the weight of the sample obtained by the torque sensor; obtain the target height saved for the weight; The sending module is specifically used to send the target height, the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device, so that the grasping device performs a drop test on the sample when moving the sample to the target height.

[0018] Furthermore, the processing module is also used to obtain the area where the sample to be tested is located according to the stage of the current sample test if the image contains at least two samples; obtain the sub-area saved for the area in the image; and based on the sub-area, perform subsequent steps to determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the image in the world coordinate system.

[0019] Furthermore, the processing module is also used to obtain the graphic features of the sample in the collected falling image a preset time after the grabbing device controls the sample to fall; determine the similarity between the graphic features and each graphic feature of the sample saved in advance; if any similarity is lower than a threshold, it is determined that the sample is damaged; if each similarity is not lower than the threshold, it is determined that the sample is not damaged.

[0020] In a third aspect, an embodiment of the present application further provides an electronic device, the electronic device comprising a processor, the processor being configured to implement the steps of any of the above-mentioned sample testing methods when executing a computer program stored in a memory.

[0021] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which implements the steps of any of the above-mentioned sample testing methods when executed by a processor.

[0022] In an embodiment of the present application, the electronic device determines the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the captured image in the world coordinate system, and sends the target position information to the grasping device so that the grasping device adsorbs the sample based on the target position information, and determines the center of gravity position information of the sample according to the torque value obtained by the torque sensor, determines the target edge corresponding to the test task, and determines the target rotation angle based on the center of gravity position information and the target edge; the position information of each vertex of the target edge and the target rotation angle are sent to the grasping device so that the grasping device rotates the target rotation angle based on the target edge, so that the gravity line of the sample can pass through the center of gravity and the target edge, thereby performing a drop test on the sample. This process does not require the user to place the sample, and can determine the target position information and the target rotation angle, which can ensure the consistency of the drop test of samples of uniform specifications and improve the accuracy of sample testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 A schematic diagram of a sample testing method provided in an embodiment of the present application; Figure 2 A schematic diagram of a sample provided in an embodiment of the present application; Figure 3 A schematic diagram of a sample provided in an embodiment of the present application; Figure 4 A schematic diagram of a drop test provided in an embodiment of the present application; Figure 5 A schematic diagram of a gripping device provided in an embodiment of the present application; Figure 6 Another schematic diagram of a gripping device provided in an embodiment of the present application; Figure 7 A schematic diagram of the structure of a sample drop test device provided in an embodiment of the present application; Figure 8 A schematic diagram of a grabbing device grabbing a sample provided in an embodiment of the present application; Fig. 9 A schematic diagram of another grabbing device grabbing a sample provided in an embodiment of the present application; Fig.10 A schematic diagram of another grabbing device grabbing a sample provided in an embodiment of the present application; Fig.11A schematic diagram of a rotated sample provided in an embodiment of the present application; Fig.12 A schematic diagram of the posture of a sample before a drop test provided in an embodiment of the present application; Fig.13 A schematic diagram of a modeling body provided in an embodiment of the present application; Fig.14 A schematic diagram of another posture of a sample before a drop test provided in an embodiment of the present application; Fig.15 A detailed schematic diagram of a sample test process provided in an embodiment of the present application; Fig.16 A structural diagram of a sample testing device provided in an embodiment of the present application; Fig.17 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. 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.

[0026] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0027] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0028] The words "connected", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "plurality" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and subsequent associated objects are in an "or" relationship. The terms "first", "second", "third" and the like involved in this application are merely used to distinguish similar objects, and do not represent a specific ordering of objects.

[0029] In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0030] In order to ensure the consistency of drop tests on samples of uniform specifications and to accurately and effectively perform drop tests on samples, the embodiments of the present application provide a sample testing method, device, equipment and medium.

[0031] The sample testing method includes: an electronic device determines the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the world coordinate system in the collected image; the target position information is sent to a grasping device so that the grasping device adsorbs the sample based on the target position information; the current test task and the center of gravity position information of the sample determined based on the torque value obtained by the torque sensor are obtained, if the test task is determined to be an edge test or a corner point test, the target edge corresponding to the test task is determined, a straight line passing through the center of gravity position information and the target edge and perpendicular to the target edge is determined, and the angle between the straight line and the current gravity line is determined as the target rotation angle; the position information of each vertex of the target edge and the obtained target rotation angle are sent to the grasping device so that the grasping device rotates the sample based on the received target edge and target rotation angle to perform a drop test on the sample. Embodiment 1:

[0032] Figure 1 A schematic diagram of a sample testing process provided in an embodiment of the present application, the process includes the following steps: S101: Determine target position information of the center point of the top surface according to position information of each vertex of the top surface of the sample in the acquired image in the world coordinate system; send the target position information to a gripping device so that the gripping device adsorbs the sample based on the target position information.

[0033] The sample testing method provided in the embodiment of the present application is applied to an electronic device, which may be a smart device such as a PC or a server.

[0034] The sample provided in the embodiment of the present application may be a packaging box or other samples. In order to accurately and effectively test the sample, the electronic device can control the image acquisition device to acquire images, wherein the sample is subjected to a drop test in a fixed area of ​​the actual scene, and the sample after the drop will also fall in the fixed area, and the image acquisition device is set at a position where the fixed area can be fully acquired, wherein the image acquisition device can be a 3D camera, and after acquiring the image, the image acquisition device sends the acquired image to the electronic device.

[0035] After acquiring the captured image, the electronic device can determine the position information of each vertex of the top surface of the sample in the captured image in the world coordinate system, wherein the sample is placed horizontally, and the top surface refers to the surface of the sample away from the ground. In a possible implementation, the electronic device can input the image into a pre-trained position recognition model to obtain the position information of each vertex of the top surface of the sample output by the recognition model in the world coordinate system; in a possible implementation, the electronic device can also input the image into a pre-trained vertex recognition model to obtain the position information of each vertex in the image output by the vertex recognition model. The electronic device will use a pre-established and saved mapping table or conversion algorithm, which records the conversion relationship between the position information in the image and the corresponding position in the world coordinate system. This conversion relationship may be calculated based on the internal parameters (such as focal length, optical center position, etc.) and external parameters (such as the rotation and translation matrix of the image acquisition device relative to the world coordinate system) of the image acquisition device. By applying these parameters, the electronic device can convert the position information of each vertex from the image coordinate system to the world coordinate system, thereby obtaining the position information of each vertex in the world coordinate system; in another possible implementation, if the image acquisition device is a 3D camera, the electronic device can directly use the depth information and image data captured by the 3D camera for three-dimensional reconstruction or 3D modeling. The 3D camera is usually able to provide a depth value for each pixel, which allows the electronic device to build a three-dimensional model containing detailed geometric information of the object surface. After the 3D modeling is completed, the electronic device can identify and extract the vertices of the top surface of the sample through a model analysis algorithm. This usually involves geometric processing of the model, such as edge detection, surface smoothing, and feature point extraction, to accurately locate the vertices on the top surface of the sample. Once these vertices are identified, the electronic device can directly read the position information of these vertices in the world coordinate system from the 3D model.

[0036] After acquiring the position information of each vertex on the top surface of the sample in the world coordinate system, the electronic device may determine the target position information of the center point of the top surface according to the position information of each vertex in the world coordinate system.

[0037] After determining the target position information of the center point of the top surface of the sample, the electronic device sends the acquired target position information to the gripping device, and the gripping device can adsorb the sample based on the target position information.

[0038] Figure 2 A schematic diagram of a sample provided in an embodiment of the present application.

[0039] Depend on Figure 2 It can be seen that the sample contains a total of 6 surfaces, among which surface 1 is the top surface, surface 2 is the left side (the left and right described here refer to the left and right in the actual scene), surface 3 is the front surface, surface 4 is the right surface (the left and right described here refer to the left and right in the actual scene), surface 5 is the back surface, and surface 6 is the bottom surface. Figure 2 Point P is the center point of the top surface. Points J, H, F and E are each vertex of the top surface, and points A, B, C and D are each vertex of the bottom surface, where point G is the center of gravity of the sample.

[0040] S102: Obtain the current test task and the center of gravity position information of the sample determined based on the torque value obtained by the torque sensor. If the test task is determined to be an edge test or a corner test, determine the target edge corresponding to the test task, determine a straight line passing through the center of gravity position information and the target edge and perpendicular to the target edge, and determine the angle between the straight line and the current gravity line as the target rotation angle.

[0041] It should be noted that the grasping device includes a robot and a torque sensor. Specifically, the robot of the grasping device grasps the sample. A torque sensor is arranged at the end of the robot. After the robot grasps the sample, the torque sensor can obtain the torque value. The electronic device can determine the center of gravity position information of the sample based on the obtained torque value. The electronic device can also obtain the current test task, wherein the test task includes surface test, edge test and corner point test.

[0042] Specifically, the grasping device consists of a robot, a torque sensor, and a sponge suction cup. The robot is responsible for movement, grasping samples, and positioning the samples for falling. The sponge suction cup is used to absorb the samples, and the torque sensor is used to calculate the center of gravity and weight of the samples during the process of the robot grasping the samples.

[0043] If the test task is determined to be an edge test, the electronic device can determine the target edge corresponding to the test task, wherein the edge that has not been tested during the test process of the sample is the target edge corresponding to the test task, and the edge drop requires that the falling edge is parallel to the ground, and the plumb line with the center of gravity vertically downward passes through the target edge of the drop test. In order to accurately and effectively perform the drop test of the target edge, the electronic device can determine a straight line that passes through the center position information and the target edge and is perpendicular to the target edge, and determines the angle between the straight line and the current gravity line as the target rotation angle.

[0044] Figure 3 A schematic diagram of a sample provided in an embodiment of the present application.

[0045] by Figure 3 For example, the edge between the middle surface 3 and the surface 6 is the target edge, recorded as edge AB, and the target rotation angle can be calculated by the following formula:

[0046] Among them, θ is the target rotation angle, n1 is the distance from the center of gravity to surface 6, n2 is the distance from the center of gravity to surface 3, m is the width of the sample, x is the height of the sample, Lz-h is the offset between the center of gravity and the sample adsorption surface, h is the thickness of the sponge suction cup, and Lx is the offset of the center of gravity in the direction of the sample width.

[0047] in, Figure 3 The α in Figure 3 When the middle edge BC is the target edge, the target rotation angle is determined. Figure 3 The β in Figure 3 When the middle edge BF is the target edge, the target rotation angle is determined.

[0048] It should be noted that if the current test task is an edge test, the electronic device can perform drop tests on three adjacent edges AB, BC, and BF in sequence to complete the edge test process.

[0049] If the test task is a corner point test, the electronic device may determine each edge including the corner point to be tested as a target edge, and use the above method to respectively determine the target rotation angle corresponding to each edge.

[0050] S103: Sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device, so that the grasping device rotates the sample based on the target edge and the target rotation angle, and performs a drop test on the sample.

[0051] The electronic device sends the target position information of each vertex of the target edge and the target rotation angle to the grasping device. The grasping device can rotate the target rotation angle based on the target edge as the rotation axis. The specific direction in which the grasping device rotates is not restricted, and then a drop test is performed on the sample.

[0052] Figure 4 A schematic diagram of a drop test provided in an embodiment of the present application.

[0053] The target edge Figure 3 Taking AB shown in the figure as an example, after grabbing the sample, the grabbing device takes AB as the rotation axis, and after rotating by an angle θ, the center of gravity G reaches above the edge AB in the vertical direction. The grabbing device then lifts the edge AB vertically upward to a certain height, and then releases it for a drop test.

[0054] Figure 5 A schematic diagram of a gripping device provided in an embodiment of the present application.

[0055] Figure 6 Another schematic diagram of the gripping device provided in an embodiment of the present application.

[0056] Depend on Figure 5 and Figure 6 It can be seen that the grasping device includes a robot 21, a torque sensor 22, and a sponge suction cup 23. The robot 21 is responsible for movement, grasping samples, and positioning the sample for falling. The sponge suction cup 23 is used to absorb the sample.

[0057] Based on samples Figure 2 Take the sample shown as an example, if the test task is a surface test, and the grasping device grasps surface 1 at the beginning, the falling surface is usually surface 6; grasping surface 2, the falling surface is surface 4; grasping surface 3, the falling surface is surface 5; grasping surface 4, the falling surface is surface 2; grasping surface 5, the falling surface is surface 3; grasping surface 6, the falling surface is surface 1. Grasping surface 1 to surface 6 once and dropping can complete the drop test of 6 surfaces (if after falling, the surface of the sample facing up is the surface that has been grasped, the electronic device can control the grasping device to grasp the sample and then flip it so that the surface that has not been grasped faces up, place the sample on the ground, and then re-grasp the surface that has not been grasped.

[0058] In the method provided in the embodiment of the present application, the center of gravity measured by the electronic device is combined with the size of the sample measured by the 3D camera and the position information of each vertex of the top surface in the world coordinate system to calculate the angle at which the sample should be placed when the edge falls and the corner falls. The function of the 3D camera is to collect the image of the sample, and then analyze and process the position information and size of the sample through the visual software, and calculate the posture angle of the sample before it falls. Then the electronic device calculates the path of the gripping device, and then sends the planned path parameters to the robot controller, and the controller drives the gripping device to move to grab the sample for the drop test.

[0059] Figure 7 A schematic structural diagram of a sample drop test device provided in an embodiment of the present application.

[0060] like Figure 7 The device consists of a 3D vision component 1, a gripping device 2, and a drop test work area 3. The 3D vision component 1 consists of a column 11, a crossbar 12, and a 3D camera 13. The main function of the 3D camera 13 is to collect images of samples. The column 11 is installed on the ground as the main support, the crossbar 12 is installed and connected to the column 11, and the 3D camera 13 is connected to the crossbar 12; the gripping device 2 consists of a robot 21, a torque sensor 22, and a sponge suction cup 23. The robot 21 is responsible for movement, grabbing samples, and positioning the sample to fall. The sponge suction cup 23 is used to absorb the sample. The robot 21 is installed on the bottom plate 31 of the drop test work area 3, the torque sensor 22 is installed at the end of the robot 21, and the sponge suction cup 23 is installed on the torque sensor 22; the bottom plate 31 of the drop test work area 3 is composed of a baffle 32. The main function of the baffle 32 is to separate the drop test work area 3 and prevent the falling sample from exceeding the machine working range. The bottom plate 31 is installed on the ground, and the baffle 32 is installed on the bottom plate 31, dividing the drop test working area 3 into areas, namely the test area 33, which is used to stack the samples to be tested. One or more samples can be placed, and the size is not fixed. The drop test area 34 is mainly used for drop test of samples, which needs to be tested on 6 planes, 3 edges and 1 vertex of the sample. The tested area 35 is used to stack the samples that have finished the test.

[0061] In the specific drop test process, the test sample is placed in the test area 33, the sample drop height is set, the 3D camera 13 captures an image containing the sample, the electronic device determines the sample position and size, plans the movement path of the grabbing device and sends it to the controller of the grabbing device, the controller drives the grabbing device 21 to move to the test area 33 to grab the sample, the electronic device determines the center of gravity of the sample based on the information measured by the torque sensor 22, and if the test task is an edge test or a corner test, the corresponding rotation angle is determined, the controller of the grabbing device rotates the sample based on the rotation angle, and moves it to the corresponding height above the drop test area 34, the 3D camera 13 can also capture whether the height posture of the sample is correct, if the posture is correct, release the suction cup and let the sample fall freely. Until the drop test of the sample's six planes, three edges, and one vertex is completed, the electronic device controls the grabbing device to grab the sample to the tested area 35 for stacking, and the next sample drop test begins.

[0062] The method provided in the embodiment of the present application uses vision as a motion guide to realize unmanned automated drop test, saving labor costs. By using a grabbing device to grab samples, it can be applied to samples of any size under specific conditions, where the specific conditions refer to the sample weight not exceeding the machine load capacity and the size not exceeding the arm span of the grabbing device, thereby achieving the flexibility of placing the sample at any angle.

[0063] The present invention can also identify the position of the sample after it falls, automatically pick up the sample, and identify and adjust the posture of the sample before it falls to ensure that the sample falls in a uniform and accurate posture. By using the method of real-time visual detection, the effectiveness of the test can be improved by 40% and the test efficiency can be improved. At the same time, this method can store the test results and processes through visual video recording, which is convenient for the subsequent review, review and analysis of the falling process of the damaged sample. The embodiment of the present application protects an automated drop test method based on visual control, and protects the method and ideas for combining visual cameras, torque sensors and robots for automated drop tests. The listed calculation ideas and steps are only one of the methods. The present application protects the calculation principle process of the center of gravity and posture of the sample drop test, including but not limited to changing the method steps or using other calculation methods, visual schemes, and torque sensor perception schemes to achieve the same effect. Methods and ideas; and, protect a drop test structure device that uses a 3D camera as a motion guide, combines a torque sensor to measure the weight and center of gravity of the sample, and uses a robot as an execution component, including but not limited to using other visual tools, such as 2D cameras, binocular cameras, etc., or using other types of robots to achieve the same purpose of the test device.

[0064] In an embodiment of the present application, the electronic device determines the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the captured image in the world coordinate system, and sends the target position information to the grasping device so that the grasping device adsorbs the sample based on the target position information, and determines the center of gravity position information of the sample according to the torque value obtained by the torque sensor, determines the target edge corresponding to the test task, and determines the target rotation angle based on the center of gravity position information and the target edge; the position information of each vertex of the target edge and the target rotation angle are sent to the grasping device so that the grasping device rotates the target rotation angle based on the target edge, so that the gravity line of the sample can pass through the center of gravity and the target edge, thereby performing a drop test on the sample. This process does not require the user to place the sample, and can determine the target position information and the target rotation angle, which can ensure the consistency of the drop test of samples of uniform specifications and improve the accuracy of sample testing. Embodiment 2:

[0065] In order to determine the center of gravity position information of the sample, based on the above embodiment, in the embodiment of the present application, the center of gravity position information of the sample is determined based on the torque value obtained by the torque sensor, including: Obtaining the torque value collected by the torque sensor in each preset direction; determining the offset of the center of gravity of the sample in each preset direction according to the ratio of the torque value in each preset direction to the weight of the sample; Determine the center position information of the center point of the sample in the world coordinate system according to the position information of each vertex of the sample in the world coordinate system; The center of gravity position information of the sample is determined according to the center position information and the offset in each preset direction.

[0066] In order to determine the center of gravity position information of the sample, the torque sensor can obtain the torque value of the sample in each preset direction. It should be noted that the torque sensor is installed at the end of the robot of the grasping device, and the sponge suction cup is installed below the torque sensor, and the center is aligned. When the robot of the grasping device grasps the sample, the sponge suction cup adsorbs the sample surface, and the center of the sponge suction cup coincides with the sample adsorption point, that is, the center point of the top surface of the sample. In the process of grasping the sample, the torque sensor can directly measure the mass of the sample and the torque value of the torque sensor in each preset direction.

[0067] After obtaining the mass of the sample and the torque value of the torque sensor in each preset direction, the offset of the center of gravity of the sample in each preset direction can be determined according to the ratio of the torque value in each preset direction to the weight of the sample. The formula representing the relationship between the offset of the center of gravity of the sample in each preset direction and the torque value in each preset direction is:

[0068] Wherein, Fx, Fy and Fz are the torque values ​​in each preset direction respectively, m is the mass of the sample, Lx, Ly and Lz are the displacements of the sample at the center of gravity in each preset direction respectively.

[0069] In order to determine the position information of the center of gravity of the sample, the electronic device can calculate the average position of the vertices according to the position information of each vertex of the sample in the world coordinate system to obtain the center position information of the center point of the sample in the world coordinate system. This step usually involves summing up the X, Y, and Z coordinates of all vertices, and then dividing each by the total number of vertices to obtain the center position information of the center point.

[0070] Then, for each preset direction, the electronic device calculates the center of gravity position information of the center of gravity based on the position information (Xc, Yc, Zc) of the center point and the offset in the preset direction through vector addition or specific algorithm adjustment. This process may involve iterative calculation for each direction, and each iteration considers the impact of the offset in the current direction on the center of gravity position.

[0071] Figure 8 A schematic diagram of a grasping device grasping a sample provided in an embodiment of the present application.

[0072] Fig. 9 A schematic diagram of another grasping device grasping a sample provided in an embodiment of the present application.

[0073] Fig.10 A schematic diagram of another grasping device grasping a sample provided in an embodiment of the present application.

[0074] Figure 8 , Fig. 9 and Fig.10 It is a schematic diagram of different directions when the grabbing device grabs the sample. Figure 8 , Fig. 9 and Fig.10 It can be seen that a torque sensor 22 is provided at the end of the robot of the grasping device, and a sponge suction cup 23 is installed below the torque sensor. The torque sensor can obtain the torque values ​​Fx, Fy and Fz in each preset direction, and, Figure 8 , Fig. 9 and Fig.10 Contains the offsets Lx, Ly and Lz of the sample at the center of gravity in each preset direction. Fig. 9 The h shown is the thickness of the sponge suction cup. Embodiment 3:

[0075] In order to accurately and effectively perform the drop test, based on the above embodiments, in the embodiment of the present application, if the test task is determined to be a test angle, the target edge corresponding to the test task is determined, including: If it is determined that the test task is to test the angle, any vertex of the sample is obtained, and any two edges including the vertex are determined as target edges corresponding to the test task; Sending the target edge and the acquired target rotation angle to a grasping device includes: If the determined target edge includes multiple edges, each determined target edge and the target rotation angle obtained based on each target edge are sent to the grasping device.

[0076] If the test task is to test the angle, the electronic device can obtain any vertex of the sample and determine any two edges containing the vertex as the target edges corresponding to the test task. In a possible implementation, two edges close to the ground can be determined as the target edges corresponding to the test task. The vertex angle selected for the vertex drop test can be the angle formed by the three edges of the edge drop test. Figure 2 Take the sample shown in the figure as an example. If the edge is selected in the edge drop test Figure 2 If there are edges AB, BC and BF in the figure, the vertex angle selected can be ∠B.

[0077] During the corner drop test, the line connecting the center of gravity and the top angle of the sample is required to be perpendicular to the ground, that is, the gravity line passes through the center of gravity and the corner of the sample. Therefore, the electronic device can send each target edge determined and the target rotation angle obtained based on each target edge to the grasping device. After grasping the sample, the robot of the grasping device uses each target edge as the rotation axis and rotates the target rotation angle determined based on the target edge. Figure 2 Taking the sample shown in the figure as an example, the robot of the gripping device can first rotate by an angle of θ with edge AB as the rotation axis, then rotate by an angle of α with edge BC as the rotation axis (BC is the BC before rotation), then lift the sample, and then release it for a drop test.

[0078] Fig.11 A schematic diagram of a rotated sample provided in an embodiment of the present application.

[0079] Fig.11 Schematic diagram of the sample after rotation by angle θ with edge AB as the rotation axis. Figure 2 C shown ’ and D ’ are vertices C and D before rotation.

[0080] Fig.12A schematic diagram of the posture of a sample before a drop test provided in an embodiment of the present application.

[0081] Depend on Fig.12 It can be seen that when conducting a corner drop test, the gravity line passes through the center of gravity G and the test vertex angle, that is, the straight line formed by the center of gravity G and the test vertex angle is perpendicular to the ground, and the height between the test vertex angle of the sample and the ground is height K. Embodiment 4:

[0082] In order to accurately and effectively perform the drop test, on the basis of the above embodiments, in the embodiment of the present application, if it is determined that the test task is an edge test, determining the target edge corresponding to the test task includes: If it is determined that the test task is an edge test, then obtaining untested edges according to pre-saved tested edges and a pre-built modeling body of the sample; Identify the graphic features in the image and determine the target surface corresponding to the graphic features in the modeling body; when determining that the top surface of the sample is the target surface of the modeling body, the edge corresponding to the untested edge is the target edge corresponding to the test task.

[0083] If the test task is an edge test, some edges of the sample may have been tested. Since there is no need to drop the same edge multiple times during the sample test, the electronic device can obtain the untested edges as the target edges corresponding to the test task.

[0084] Specifically, in order to accurately test the sample, the electronic device pre-builds a three-dimensional model of the sample, that is, a modeling body, and the electronic device stores the edges of the sample that have been tested during the test process. If the test task is an edge test, the electronic device can retrieve and identify the edges that have not been tested based on the tested edges and the pre-built modeling body of the sample. And use image recognition technology to identify the graphic features in the image, wherein the identified graphic features are the graphic features of the top surface of the sample, so as to determine the specific surface corresponding to the top surface of the sample in the modeling body. In particular, when it is identified that the top surface of the sample matches a target surface in the modeling body, it can be confirmed that the edge associated with the top surface and previously marked as untested is the target edge that needs to be tested for the current test task. Embodiment 5:

[0085] In order to perform the drop test accurately and effectively, based on the above embodiments, in the embodiment of the present application, the method further includes: If the drop test is currently being performed on the sample for the first time, identifying graphic features of the sample in the image; Repeat the following steps until the graphic features of each surface of the sample are obtained: Sending a flipping instruction to the gripping device so that the gripping device flips the sample based on a preset flipping method, and obtains the flipped image captured by the image acquisition device; identifying graphic features of the sample in the image; According to the pre-saved flipping method and each acquired graphic feature, three-dimensional modeling is performed on the sample to obtain a modeled body of the sample.

[0086] In order to conduct a drop test accurately and effectively, the electronic device can perform three-dimensional modeling of the sample when performing a drop test on the sample for the first time. Specifically, if it is the first time that the sample is drop tested, the electronic device can identify the graphic features of the sample in the acquired image, and repeat the following steps until the graphic features of each surface of the sample are acquired: the electronic device can send a flipping instruction to the grabbing device, and after receiving the flipping instruction, the grabbing device can flip the sample based on a preset flipping method. After the grabbing device flips the sample, the image acquisition device captures the image and sends the captured image to the electronic device, and the electronic device recognizes the graphic features of the sample in the image.

[0087] After acquiring the graphic features of each surface, the electronic device can perform three-dimensional modeling on the sample according to the pre-saved flipping method and each acquired graphic feature to acquire a modeled body of the sample.

[0088] It should be noted that, in this process, the electronic device can also determine the center of gravity of the sample based on the torque value of each preset direction obtained by the torque sensor. That is, the sample is sampled and modeled by the 3D camera and the torque sensor. The 3D camera mainly measures the sample's external dimensions and shapes, and the torque sensor mainly measures the sample's weight and center of gravity.

[0089] Fig.13 A schematic diagram of a modeling body provided in an embodiment of the present application.

[0090] At the beginning, the image acquisition device photographs the sample, and the electronic device performs preliminary modeling of the shape characteristics (length, width, and height) of the sample, including the eight vertices A (xA, yA, zA), B (xB, yB, zB), C (xC, yC, zC), D (xD, yD, zD), E (xE, yE, zE), F (xF, yF, zF), H (xH, yH, zH), and I (xI, yI, zI). The graphic features of the top surface are recorded and saved. If the patterns are the same, other feature marks can be added artificially to make the graphic features of the six surfaces different, which is recorded as surface 1. At the same time, the point P adsorbed by the suction cup is calculated. P is the center point of the top surface of the sample, and the position information of the center point can be calculated based on the position information of the top angles E, F, H, and I. The position information of the adsorption point P is sent to the grabbing device, and the grabbing device moves to adsorb and grab the sample. After grabbing, the grabbing device flips its posture so that the 3D camera can record all the graphic features of the other five planes of the sample, which are recorded as surface 2, surface 3, surface 4, surface 5, and surface 6. Embodiment 6: In order to accurately and effectively perform the drop test, based on the above embodiments, in the embodiment of the present application,

[0091] After sending the target position information to the grasping device, and before sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device, the method further includes: Obtaining the weight of the sample acquired by the torque sensor; obtaining the target height saved for the weight; The step of sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device includes: The target height, the position information of each vertex of the target edge, and the acquired target rotation angle are sent to a gripping device, so that the gripping device performs a drop test on the sample when moving the sample to the target height.

[0092] Since samples of different weights have different corresponding drop test heights when performing a drop test on the sample, the electronic device can obtain the weight of the sample and determine the drop test height based on the weight of the sample.

[0093] Specifically, the electronic device can obtain the weight of the sample obtained by the torque sensor, and the electronic device locally stores the corresponding height for different weights. The electronic device can obtain the target height stored for the weight, and send the target position information of the center point of the top surface of the sample, the target height, the position information of each vertex of the target edge, and the obtained target rotation angle to the gripping device. The gripping device can perform a drop test on the sample when the sample is moved to the target height. Among them, moving the sample to the target height means moving the tested surface, the tested edge, or the tested corner point to the target height.

[0094] In order to conduct the drop test accurately and effectively, after the grasping device moves to the target height and before the drop test is conducted, the electronic device can also control the image acquisition device to acquire images, and based on the acquired images, determine whether the height between the currently tested surface, edge or corner and the ground is the target height. If it is the target height, a release command is sent to the grasping device, and the grasping device releases the sample to conduct the drop test.

[0095] In the embodiment of the present application, a torque sensor is used to measure the weight and center of gravity of the sample, and the drop height can be automatically matched according to the weight of the sample. At the same time, the machine vision solution can be used to identify the shape and size of the sample, and lock the 6 planes, 3 edges and the vertex angle composed of the 3 edges of the sample. Combined with the center of gravity position information, the spatial posture of the sample when the drop test of 6 planes, 3 edges and 1 vertex can be calculated, wherein the spatial posture is the target rotation angle described in the embodiment of the present application. When the electronic device calculates the test task for the edge test and the corner test, the angle at which the sample should be placed when the sample falls. The role of the 3D camera 13 is to collect the picture of the sample, and then analyze and process the position information and size of the sample through the visual software, and calculate the posture angle of the sample before the sample falls, and then calculate the target position information of the grabbing device to grab, and the electronic device can calculate the path of the grabbing device according to the current position information of the grabbing device and the target position information, and then send the planned path parameters to the controller of the grabbing device, and the controller drives the grabbing device to move to grab the sample for the drop test.

[0096] Fig.14 A schematic diagram of the posture of another sample before a drop test provided in an embodiment of the present application.

[0097] Fig.14 This is a schematic diagram of the posture of the sample before the drop test when the test task is surface test. Fig.14 It can be seen that the height between the falling surface and the ground is the determined target height, wherein the falling surface is the bottom surface of the sample close to the ground. Embodiment 7:

[0098] In order to accurately and effectively grasp the sample, on the basis of the above embodiments, in the embodiment of the present application, after acquiring the image captured by the image acquisition device, before determining the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the image in the world coordinate system, the method further includes: If the image contains at least two samples, obtaining the area where the sample to be tested is located according to the stage of the current sample test; Obtain a sub-region saved for the region in the image; based on the sub-region, perform subsequent steps to determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the image in the world coordinate system.

[0099] During the test, the images captured by the image acquisition device may include samples waiting to be tested, samples being tested, and samples that have been tested. In order to accurately capture the samples being tested, if the image contains at least two samples, the electronic device can obtain the stage of the current sample test, where the stage of the sample test may be that the test has not started or that the test is being started. If the stage of the sample test is that the test has not started, the sample is placed in the area to be tested. If the stage of the sample test is that the test is being tested, the sample is placed in the drop test area. The electronic device can obtain the area where the sample to be tested is located according to the stage of the current sample test.

[0100] Since the image acquisition device is installed in a fixed position, the corresponding sub-regions are saved for the regions in the captured image. That is to say, for an object in a certain region, in the captured image, at the sub-region corresponding to the image, the electronic device can obtain the sub-region saved for the region in the image. The sample currently being tested is located in the sub-region. Based on the sub-region, the electronic device can execute subsequent steps to determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the image in the world coordinate system. Embodiment 8:

[0101] In order to perform the drop test accurately and effectively, based on the above embodiments, in the embodiment of the present application, the method further includes: After the grabbing device controls the sample to fall for a preset time, acquiring graphic features of the sample in the collected falling image; Determine the similarity between the graphic feature and each graphic feature of the sample saved in advance; if any similarity is lower than a threshold, determine that the sample is damaged; if each similarity is not lower than the threshold, determine that the sample is not damaged.

[0102] In order to perform drop tests accurately and efficiently, the electronic device can determine whether the sample is damaged based on the images collected after the drop.

[0103] Specifically, a preset time after the grabbing device controls the sample to fall, the electronic device obtains the graphic features of the sample in the collected falling image, and determines the similarity between the graphic features and each graphic feature of the sample saved in advance. If any determined similarity is lower than a threshold, it can be determined that the sample is damaged. At this time, the drop test of the sample can be ended, and the target position information of the center point of the top surface of the sample can be calculated, so that the grabbing device grabs the sample and stacks it in the measured area, and starts the drop test of the next sample. If each similarity is not lower than the threshold, it can be determined that the sample is not damaged, and the drop test on the sample continues until the sample completes each test task.

[0104] Fig.15 A detailed process diagram of a sample test provided in an embodiment of the present application.

[0105] S1501: Acquire an image captured by an image acquisition device.

[0106] S1502: Determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the acquired image in the world coordinate system.

[0107] S1503: Send the target position information to the gripping device, so that the gripping device adsorbs the sample based on the target position information.

[0108] S1504: Obtain the torque value and weight obtained by the torque sensor during the grasping process.

[0109] S1505: Based on the acquired torque value, determine the center of gravity position information of the sample center of gravity, and determine the target height saved for the weight.

[0110] S1506: Determine whether the test task is a surface test, if so, execute S1507, if not, execute S1508.

[0111] S1507: Send the target height to the gripping device so that the gripping device moves to the target height for a drop test, and execute S1510.

[0112] S1508: Determine the target edge corresponding to the test task, and determine the straight line that passes through the center of gravity position information and the target edge and is perpendicular to the target edge, determine the angle between the straight line and the current gravity line as the target rotation angle, and execute S1509.

[0113] S1509: Send the target position information and the target rotation angle of each vertex of the target edge to the grasping device, so that the grasping device rotates the target rotation angle with the target edge as the rotation axis, and executes S1510.

[0114] S1510: Determine whether the sample is damaged after falling, if so, execute S1512, if not, execute S1511.

[0115] S1511: Determine whether each test task has been executed for the sample. If so, execute S1512; if not, execute S1501.

[0116] Each test task includes surface test, edge test and corner test. Figure 2 Taking the sample shown as an example, the surface test needs to complete the test of 6 surfaces, the edge test needs to complete the test of 3 edges, and the corner point test needs to complete the test of one corner point.

[0117] S1512: Determine the target position information of the center point of the top surface of the sample so that the grasping device grasps the sample to the measured area. Embodiment 9:

[0118] Based on the same inventive concept, the present application embodiment provides a sample testing device. Fig.16 For a schematic diagram of a sample testing device structure provided in an embodiment of the present application, please refer to Fig.16 , the device comprises: Processing module 1601 is used to determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the collected image in the world coordinate system; send the target position information to the grasping device so that the grasping device adsorbs the sample based on the target position information; obtain the current test task and the center of gravity position information of the sample determined based on the torque value obtained by the torque sensor, if the test task is determined to be an edge test or a corner test, then determine the target edge corresponding to the test task, determine the straight line that passes through the center of gravity position information and the target edge and is perpendicular to the target edge, and determine the angle between the straight line and the current gravity line as the target rotation angle; The sending module 1602 is used to send the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device, so that the grasping device rotates the sample based on the target edge and the target rotation angle to perform a drop test on the sample.

[0119] In a possible implementation, the processing module 1601 is specifically used to obtain the torque value collected by the torque sensor in each preset direction; determine the offset of the center of gravity of the sample in each preset direction according to the ratio of the torque value in each preset direction to the weight of the sample; determine the center position information of the center point of the sample in the world coordinate system according to the position information of each vertex of the sample in the world coordinate system; determine the center of gravity position information of the sample according to the center position information and the offset in each preset direction.

[0120] In a possible implementation manner, the processing module 1601 is specifically configured to obtain any vertex of the sample and determine any two edges including the vertex as target edges corresponding to the test task if it is determined that the test task is a test angle; The sending module 1602 is specifically configured to send the position information of the vertices of each determined target edge and the target rotation angle obtained based on each target edge to the grasping device if the determined target edge includes multiple edges.

[0121] In a possible implementation, the processing module 1601 is specifically used to obtain untested edges based on pre-saved tested edges and a pre-constructed modeling body of the sample if the test task is determined to be an edge test; identify graphic features in the image and determine the target surface corresponding to the graphic features in the modeling body; and when determining that the top surface of the sample is the target surface of the modeling body, the edge corresponding to the untested edge is the target edge corresponding to the test task.

[0122] In a possible implementation, the processing module 1601 is also used to identify the graphic features of the sample in the image if this is the first time that the sample is drop tested; and repeatedly perform the following steps until the graphic features of each surface of the sample are acquired: sending a flipping instruction to the gripping device so that the gripping device flips the sample based on a preset flipping method, and acquires the flipped image acquired by the image acquisition device; identifying the graphic features of the sample in the image; and performing three-dimensional modeling of the sample according to the pre-saved flipping method and each acquired graphic feature to acquire a modeled body of the sample.

[0123] In a possible implementation manner, the processing module 1601 is further used to obtain the weight of the sample obtained by the torque sensor; obtain the target height saved for the weight; The sending module 1602 is specifically used to send the target height, the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device, so that the grasping device performs a drop test on the sample when moving the sample to the target height.

[0124] In a possible implementation, the processing module 1601 is also used to, if the image contains at least two samples, obtain the area where the sample to be tested is located according to the stage of the current sample test; obtain the sub-area saved for the area in the image; and based on the sub-area, perform subsequent steps to determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the image in the world coordinate system.

[0125] In a possible implementation, the processing module 1601 is also used to obtain the graphic features of the sample in the collected falling image a preset time after the grasping device controls the sample to fall; determine the similarity between the graphic features and each graphic feature of the sample saved in advance; if any similarity is lower than a threshold, it is determined that the sample is damaged; if each similarity is not lower than the threshold, it is determined that the sample is not damaged.

[0126] Embodiment 10: Based on the same inventive concept, an embodiment of the present application provides an electronic device, which can implement the steps of the sample testing method discussed above. Fig.17 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Fig.17 As shown, it includes: a processor 1701, a communication interface 1702, a memory 1703 and a communication bus 1704, wherein the processor 1701, the communication interface 1702, and the memory 1703 communicate with each other through the communication bus 1704; The memory 1703 stores a computer program. When the program is executed by the processor 1701, the processor 1701 performs the following steps: Determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the collected image in the world coordinate system; send the target position information to the grasping device so that the grasping device absorbs the sample based on the target position information; Obtain the current test task and the center of gravity position information of the sample determined based on the torque value obtained by the torque sensor. If the test task is determined to be an edge test or a corner test, determine the target edge corresponding to the test task, determine a straight line passing through the center of gravity position information and the target edge and perpendicular to the target edge, and determine the angle between the straight line and the current gravity line as the target rotation angle; The position information of each vertex of the target edge and the acquired target rotation angle are sent to the grasping device, so that the grasping device rotates the sample based on the target edge and the target rotation angle to perform a drop test on the sample.

[0127] In a possible implementation, determining the center of gravity position information of the sample based on the torque value obtained by the torque sensor includes: Obtaining the torque value collected by the torque sensor in each preset direction; determining the offset of the center of gravity of the sample in each preset direction according to the ratio of the torque value in each preset direction to the weight of the sample; Determine the center position information of the center point of the sample in the world coordinate system according to the position information of each vertex of the sample in the world coordinate system; The center of gravity position information of the sample is determined according to the center position information and the offset in each preset direction.

[0128] In a possible implementation manner, if it is determined that the test task is a test corner, determining a target edge corresponding to the test task includes: If it is determined that the test task is to test the angle, any vertex of the sample is obtained, and any two edges including the vertex are determined as target edges corresponding to the test task; Sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device includes: If the determined target edge includes multiple edges, the position information of the vertex of each determined target edge and the target rotation angle obtained based on each target edge are sent to the grasping device.

[0129] In a possible implementation manner, if it is determined that the test task is an edge test, determining a target edge corresponding to the test task includes: If it is determined that the test task is an edge test, then obtaining untested edges according to pre-saved tested edges and a pre-built modeling body of the sample; Identify the graphic features in the image and determine the target surface corresponding to the graphic features in the modeling body; when determining that the top surface of the sample is the target surface of the modeling body, the edge corresponding to the untested edge is the target edge corresponding to the test task.

[0130] In a possible implementation, the method further includes: If the drop test is currently being performed on the sample for the first time, identifying graphic features of the sample in the image; Repeat the following steps until the graphic features of each surface of the sample are obtained: Sending a flipping instruction to the gripping device so that the gripping device flips the sample based on a preset flipping method, and obtains the flipped image captured by the image acquisition device; identifying graphic features of the sample in the image; According to the pre-saved flipping method and each acquired graphic feature, three-dimensional modeling is performed on the sample to obtain a modeled body of the sample.

[0131] In a possible implementation, after sending the target position information to the grasping device and before sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device, the method further includes: Obtaining the weight of the sample acquired by the torque sensor; obtaining the target height saved for the weight; The step of sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device includes: The target height, the position information of each vertex of the target edge, and the acquired target rotation angle are sent to a gripping device, so that the gripping device performs a drop test on the sample when moving the sample to the target height.

[0132] In a possible implementation, after acquiring the image captured by the image acquisition device, before determining the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the image in the world coordinate system, the method further includes: If the image contains at least two samples, obtaining the area where the sample to be tested is located according to the stage of the current sample test; Obtain a sub-region saved for the region in the image; based on the sub-region, perform subsequent steps to determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the image in the world coordinate system.

[0133] In a possible implementation, the method further includes: After the grabbing device controls the sample to fall for a preset time, acquiring graphic features of the sample in the collected falling image; Determine the similarity between the graphic feature and each graphic feature of the sample saved in advance; if any similarity is lower than a threshold, determine that the sample is damaged; if each similarity is not lower than the threshold, determine that the sample is not damaged.

[0134] Since the principle of solving the problem by the above electronic device is similar to that of the sample testing method, the implementation of the above electronic device can refer to the embodiment of the method, and the repeated parts will not be repeated.

[0135] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0136] The communication interface 1702 is used for communication between the above electronic device and other devices. The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the above processor.

[0137] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (NP), etc.; it can also be a digital signal processing processor (DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0138] Embodiment 11: Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program executable by an electronic device. When the program runs on the electronic device, the electronic device implements the following steps when executing: Determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the collected image in the world coordinate system; send the target position information to the grasping device so that the grasping device absorbs the sample based on the target position information; Obtain the current test task and the center of gravity position information of the sample determined based on the torque value obtained by the torque sensor. If the test task is determined to be an edge test or a corner test, determine the target edge corresponding to the test task, determine a straight line passing through the center of gravity position information and the target edge and perpendicular to the target edge, and determine the angle between the straight line and the current gravity line as the target rotation angle; The position information of each vertex of the target edge and the acquired target rotation angle are sent to the grasping device, so that the grasping device rotates the sample based on the target edge and the target rotation angle to perform a drop test on the sample.

[0139] In a possible implementation, determining the center of gravity position information of the sample based on the torque value obtained by the torque sensor includes: Obtaining the torque value collected by the torque sensor in each preset direction; determining the offset of the center of gravity of the sample in each preset direction according to the ratio of the torque value in each preset direction to the weight of the sample; Determine the center position information of the center point of the sample in the world coordinate system according to the position information of each vertex of the sample in the world coordinate system; The center of gravity position information of the sample is determined according to the center position information and the offset in each preset direction.

[0140] In a possible implementation manner, if it is determined that the test task is a test corner, determining a target edge corresponding to the test task includes: If it is determined that the test task is to test the angle, any vertex of the sample is obtained, and any two edges including the vertex are determined as target edges corresponding to the test task; Sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device includes: If the determined target edge includes multiple edges, the position information of the vertex of each determined target edge and the target rotation angle obtained based on each target edge are sent to the grasping device.

[0141] In a possible implementation manner, if it is determined that the test task is an edge test, determining a target edge corresponding to the test task includes: If it is determined that the test task is an edge test, then obtaining untested edges according to pre-saved tested edges and a pre-built modeling body of the sample; Identify the graphic features in the image and determine the target surface corresponding to the graphic features in the modeling body; when determining that the top surface of the sample is the target surface of the modeling body, the edge corresponding to the untested edge is the target edge corresponding to the test task.

[0142] In a possible implementation, the method further includes: If the drop test is currently being performed on the sample for the first time, identifying graphic features of the sample in the image; Repeat the following steps until the graphic features of each surface of the sample are obtained: Sending a flipping instruction to the gripping device so that the gripping device flips the sample based on a preset flipping method, and obtains the flipped image captured by the image acquisition device; identifying graphic features of the sample in the image; According to the pre-saved flipping method and each acquired graphic feature, three-dimensional modeling is performed on the sample to obtain a modeled body of the sample.

[0143] In a possible implementation, after sending the target position information to the grasping device and before sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device, the method further includes: Obtaining the weight of the sample acquired by the torque sensor; obtaining the target height saved for the weight; The step of sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device includes: The target height, the position information of each vertex of the target edge, and the acquired target rotation angle are sent to a gripping device, so that the gripping device performs a drop test on the sample when moving the sample to the target height.

[0144] In a possible implementation, after acquiring the image captured by the image acquisition device, before determining the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the image in the world coordinate system, the method further includes: If the image contains at least two samples, obtaining the area where the sample to be tested is located according to the stage of the current sample test; Obtain a sub-region saved for the region in the image; based on the sub-region, perform subsequent steps to determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the image in the world coordinate system.

[0145] In a possible implementation, the method further includes: After the grabbing device controls the sample to fall for a preset time, acquiring graphic features of the sample in the collected falling image; Determine the similarity between the graphic feature and each graphic feature of the sample saved in advance; if any similarity is lower than a threshold, determine that the sample is damaged; if each similarity is not lower than the threshold, determine that the sample is not damaged.

[0146] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0147] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0148] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0149] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0150] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A sample testing method, characterized in that: The method comprises: Determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the collected image in the world coordinate system; send the target position information to the grasping device so that the grasping device absorbs the sample based on the target position information; Obtain the current test task and the center of gravity position information of the sample determined based on the torque value obtained by the torque sensor. If the test task is determined to be an edge test or a corner test, determine the target edge corresponding to the test task, determine a straight line passing through the center of gravity position information and the target edge and perpendicular to the target edge, and determine the angle between the straight line and the current gravity line as the target rotation angle; The position information of each vertex of the target edge and the acquired target rotation angle are sent to the grasping device, so that the grasping device rotates the sample based on the target edge and the target rotation angle to perform a drop test on the sample.

2. The method according to claim 1, characterized in that Determining the center of gravity position information of the sample based on the torque value obtained by the torque sensor includes: Obtaining the torque value collected by the torque sensor in each preset direction; determining the offset of the center of gravity of the sample in each preset direction according to the ratio of the torque value in each preset direction to the weight of the sample; Determine the center position information of the center point of the sample in the world coordinate system according to the position information of each vertex of the sample in the world coordinate system; The center of gravity position information of the sample is determined according to the center position information and the offset in each preset direction.

3. The method according to claim 1, characterized in that If it is determined that the test task is a test corner, determining a target edge corresponding to the test task includes: If it is determined that the test task is to test the angle, any vertex of the sample is obtained, and any two edges including the vertex are determined as target edges corresponding to the test task; Sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device includes: If the determined target edge includes multiple edges, the position information of the vertex of each determined target edge and the target rotation angle obtained based on each target edge are sent to the grasping device.

4. The method according to claim 1, characterized in that: If it is determined that the test task is an edge test, determining a target edge corresponding to the test task includes: If it is determined that the test task is an edge test, then obtaining untested edges according to pre-saved tested edges and a pre-built modeling body of the sample; Identify the graphic features in the image and determine the target surface corresponding to the graphic features in the modeling body; when determining that the top surface of the sample is the target surface of the modeling body, the edge corresponding to the untested edge is the target edge corresponding to the test task.

5. The method according to claim 4, characterized in that The method further comprises: If the drop test is currently being performed on the sample for the first time, identifying graphic features of the sample in the image; Repeat the following steps until the graphic features of each surface of the sample are obtained: Sending a flipping instruction to the gripping device so that the gripping device flips the sample based on a preset flipping method, and obtains the flipped image captured by the image acquisition device; identifying the graphic features of the sample in the image; According to the pre-saved flipping method and each acquired graphic feature, three-dimensional modeling is performed on the sample to obtain a modeled body of the sample.

6. The method according to claim 1, characterized in that After sending the target position information to the grasping device, and before sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device, the method further includes: Obtaining the weight of the sample acquired by the torque sensor; obtaining the target height saved for the weight; The step of sending the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device includes: The target height, the position information of each vertex of the target edge, and the acquired target rotation angle are sent to a gripping device, so that the gripping device performs a drop test on the sample when moving the sample to the target height.

7. The method according to claim 1, characterized in that After acquiring the image captured by the image acquisition device, before determining the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the image in the world coordinate system, the method further includes: If the image contains at least two samples, obtaining the area where the sample to be tested is located according to the stage of the current sample test; Obtain a sub-region saved for the region in the image; based on the sub-region, perform subsequent steps to determine the target position information of the center point of the top surface according to the position information of each vertex of the top surface of the sample in the image in the world coordinate system.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: After the grabbing device controls the sample to fall for a preset time, acquiring graphic features of the sample in the collected falling image; Determine the similarity between the graphic feature and each graphic feature of the sample saved in advance; if any similarity is lower than a threshold, determine that the sample is damaged; if each similarity is not lower than the threshold, determine that the sample is not damaged.

9. A sample testing device, characterized in that: The device comprises: A processing module, used to determine the target position information of the center point of the top surface of the sample according to the position information of each vertex of the top surface of the sample in the collected image in the world coordinate system; send the target position information to the grasping device so that the grasping device adsorbs the sample based on the target position information; obtain the current test task and the center of gravity position information of the sample determined based on the torque value obtained by the torque sensor, if the test task is determined to be an edge test or a corner test, then determine the target edge corresponding to the test task, determine the straight line that passes through the center of gravity position information and the target edge and is perpendicular to the target edge, and determine the angle between the straight line and the current gravity line as the target rotation angle; The sending module is used to send the position information of each vertex of the target edge and the acquired target rotation angle to the grasping device, so that the grasping device rotates the sample based on the target edge and the target rotation angle to perform a drop test on the sample.

10. An electronic device, characterized in that: The electronic device comprises a processor, and the processor is used to implement the steps of the sample testing method according to any one of claims 1 to 8 when executing a computer program stored in a memory.

11. A computer-readable storage medium, characterized in that: It stores a computer program, and when the computer program is executed by a processor, the steps of the sample testing method according to any one of claims 1 to 8 are implemented.

Images