Photographing Path Planning Method, Device, Medium and Equipment for Quality Inspection

Abstract

This application relates to the field of computer technology and discloses a method, device, medium, and equipment for photographing path planning for quality inspection. The method includes: obtaining a number of first poses of the end of the robotic arm based on the position information of the object to be inspected; respectively performing collision detection based on each of the first poses and the position information of the obstacles to obtain a number of second poses that do not collide with the obstacles; sequentially using each of the second poses as the target pose, and using the second poses other than the target pose as the current pose, respectively determining the target current pose that matches the target pose from each current pose to determine the matching pose that matches each second pose; planning to obtain the target photographing path based on each of the second poses and the matching pose that matches each of the second poses. The photographing path planned in this application will not collide with obstacles, improving the photographing efficiency and making the photographing data more stable.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial quality inspection, and particularly relates to a photographing path planning method, device, medium and equipment for quality inspection. Background Art

[0002] In the field of industrial vision inspection, multi-angle photographing is required for the surface defect inspection of workpieces to be inspected. However, the traditional single fixed photographing position often cannot meet the requirements of the appearance inspection of the quality inspection system. Therefore, the flying shooting device came into being. By using the flying shooting device, the flying shooting robotic arm can be controlled to drive the camera to take pictures in the real scene, so as to collect the photographing data of multiple angles of the workpiece to be inspected, providing guarantee for subsequent appearance inspection.

[0003] However, in the shooting process of the existing flying shooting device, it is easy to collide with obstacles, resulting in problems such as low shooting efficiency and unstable shooting data. Summary of the Invention

[0004] In view of this, the present invention provides a photographing path planning method, device, medium and equipment for quality inspection, mainly aiming at the problems that in the shooting process of the flying shooting device, it is easy to collide with obstacles, resulting in low shooting efficiency and unstable shooting data.

[0005] To solve the above problems, the present application provides a photographing path planning method for quality inspection, including:

[0006] Obtaining a plurality of first poses of the end of the robotic arm based on the position information of the object to be detected;

[0007] Performing collision detection respectively based on each of the first poses and the position information of the obstacle, and obtaining a plurality of second poses that do not collide with the obstacle;

[0008] Sequentially taking each of the second poses as the target pose, and taking the second poses except the target pose as the current pose, respectively determining the target current pose that matches the target pose from each of the current poses, so as to determine the matching pose that matches each of the second poses;

[0009] Planning a target shooting path based on each of the second poses and the matching pose that matches each of the second poses.

[0010] Optionally, the performing collision detection respectively based on each of the first poses and the position information of the obstacle, and obtaining a plurality of second poses that do not collide with the obstacle includes:

[0011] Performing inverse solution calculation on each of the first poses based on the pre-established kinematic model of the robotic arm to determine whether there is a corresponding inverse solution of the robotic arm for each of the first poses;

[0012] In the case where the inverse kinematics solution of the robotic arm exists for the first pose, calculate the poses of the joints of the robotic arm in space based on the first pose;

[0013] Based on the poses of the joints in space corresponding to the same first pose and the position information of the obstacles, perform collision detection on the first pose to obtain a number of second poses that do not collide with the obstacles.

[0014] Optionally, the step of respectively determining a target current pose that matches the target pose from each current pose to determine a matching pose that matches each second pose includes:

[0015] Based on the target pose and each current pose in sequence, use a predetermined matching function to calculate the matching degree corresponding to each current pose respectively;

[0016] Based on the matching degrees corresponding to each current pose, determine a target current pose that matches the target pose from each current pose to determine a matching pose that matches each second pose.

[0017] Optionally, the matching function is:

[0018]

[0019] where R t represents the matching degree;

[0020] S t represents the current pose;

[0021] Y represents the target pose;

[0022] e is a constant.

[0023] Optionally, the step of planning a target shooting path based on each of the second poses and the matching poses that match each of the second poses includes:

[0024] Determine any second pose from each of the second poses as the original shooting pose;

[0025] Based on the original shooting pose, the matching pose corresponding to the original shooting pose, and the matching poses corresponding to each of the remaining second poses, sequentially determine a number of target second poses from the remaining second poses;

[0026] Based on the original shooting pose and the target second poses, construct the target shooting path.

[0027] To solve the above problems, the present application provides a photographing path planning device for quality inspection, including:

[0028] An acquisition module, configured to acquire a plurality of first poses of the end of a robotic arm based on the position information of an object to be detected;

[0029] A detection module, configured to perform collision detection respectively based on each of the first poses and the position information of an obstacle, and obtain a plurality of second poses that do not collide with the obstacle;

[0030] A matching module, configured to sequentially use each of the second poses as a target pose, and use the second poses other than the target pose as the current poses, and respectively determine an optimal current pose that matches the target pose from each of the current poses, so as to determine an optimal pose that matches each of the second poses;

[0031] A planning module, configured to plan and obtain a target shooting path based on each of the second poses and the optimal pose that matches each of the second poses.

[0032] Optionally, the detection module is specifically configured to:

[0033] Based on a pre-established kinematic model of the robotic arm, perform inverse kinematics calculation on each of the first poses to determine whether there is a corresponding inverse solution of the robotic arm for each of the first poses;

[0034] When there is a corresponding inverse solution of the robotic arm for a first pose, calculate the pose of each joint axis of the robotic arm in space based on the first pose;

[0035] Based on the pose of each joint axis in space corresponding to the same first pose and the position information of the obstacle, perform collision detection on the first pose, and obtain a plurality of second poses that do not collide with the obstacle.

[0036] Optionally, the matching module is specifically configured to:

[0037] Based on the target pose and each current pose in sequence, use a predetermined matching function to calculate the matching degree corresponding to each current pose respectively;

[0038] Based on the matching degree corresponding to each current pose, determine a target current pose that matches the target pose from each current pose, so as to determine a matching pose that matches each of the second poses.

[0039] To solve the above problems, the present application provides a storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for planning a photographing path for quality inspection are implemented.

[0040] To solve the above problems, the present application provides an electronic device, which at least includes a memory and a processor. A computer program is stored on the memory, and when the processor executes the computer program on the memory, the steps of the method for photographing path planning for quality inspection described in any one of the above are implemented.

[0041] In the method, device, medium and equipment for photographing path planning for quality inspection in the present application, by obtaining a plurality of first poses and performing collision detection on the first poses, the photographing poses that collide with obstacles can be filtered out, so that the photographing path obtained by subsequent planning will not collide with obstacles, improving the photographing efficiency and making the photographing data more stable. At the same time, by matching the corresponding optimal poses for each second pose, the target photographing path planned can be made more reasonable and accurate, avoiding the problem of redundant photographing data caused by the tortuous and detoured path obtained by planning.

[0042] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention are specifically given below. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0044] Figure 1 is a flowchart of a method for photographing path planning for quality inspection according to an embodiment of the present application;

[0045] Figure 2 is a structural block diagram of a device for photographing path planning for quality inspection according to another embodiment of the present application;

[0046] Figure 3 is a structural block diagram of an electronic device according to another embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] Reference is made herein to the various aspects and features of the present application with reference to the drawings.

[0048] It should be understood that various modifications can be made to the embodiments applied herein. Therefore, the above description should not be regarded as a limitation, but only as an example of the embodiments. Those skilled in the art will think of other modifications within the scope and spirit of the present application.

[0049] The drawings included in and forming a part of the specification illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, are used to explain the principles of the present application.

[0050] These and other features of the present application will become apparent from the following description of the preferred forms of the embodiments given by way of non-limiting example with reference to the drawings.

[0051] It should also be understood that although the present application has been described with reference to some specific examples, those skilled in the art can surely implement many other equivalent forms of the present application.

[0052] When combined with the drawings, the above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description.

[0053] Specific embodiments of the present application will be described hereinafter with reference to the drawings; however, it should be understood that the embodiments claimed are merely examples of the present application and can be implemented in various ways. Well-known and / or repetitive functions and structures are not described in detail to avoid obscuring the present application with unnecessary or redundant details. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but are merely used as a basis and representative basis for the claims to teach those skilled in the art to use the present application in substantially any suitable detailed structure in a variety of ways.

[0054] This specification may use the phrases "in one embodiment", "in another embodiment", "in yet another embodiment" or "in other embodiments", all of which may refer to one or more of the same or different embodiments according to the present application.

[0055] An embodiment of the present application provides a photographing path planning method for quality inspection, which can be specifically applied to electronic devices such as terminals and servers, such as Figure 1 As shown, the photographing path planning method in this embodiment includes the following steps:

[0056] Step S101, obtaining a plurality of first poses of the end of the robotic arm based on the position information of the object to be detected;

[0057] In the specific implementation process of this step, a kinematic model of the robotic arm can be specifically established, and then combined with the position information of the object to be detected in space, a plurality of first poses for photographing the object to be detected are determined. That is, when the end of the robotic arm moves to the first pose, the object to be detected can be photographed, thereby obtaining the photographing data for appearance inspection.

[0058] Step S102, respectively performing collision detection based on each of the first poses and the position information of the obstacle, and obtaining a plurality of second poses that do not collide with the obstacle;

[0059] In this step, when the robotic arm moves to the first pose, it may collide with obstacles. Therefore, it is necessary to perform collision detection on each first pose to filter out several second poses that do not collide with obstacles.

[0060] In this step, when performing collision detection, the position of each joint axis on the robotic arm in space can be determined. Thus, when the robotic arm moves, the positions of the joint axis points on the robotic arm in space will also move accordingly. After calculating the positions of the joint axis points on the robotic arm in space, it is possible to calculate whether there is an overlap between it and the obstacle in space. If there is an overlap, it can be determined that there will be a collision with the obstacle. If there is no overlap, it is determined that there will be no collision with the obstacle.

[0061] Step S103: Sequentially use each of the second poses as the target pose, and use the second poses other than the target pose as the current pose. Respectively determine the target current pose that matches the target pose from each current pose to determine the matching pose that matches each second pose.

[0062] In the specific implementation process of this step, it is possible to sequentially calculate the matching degree corresponding to each current pose based on the target pose and each current pose using a predetermined matching function; then, based on the matching degrees corresponding to each current pose, determine the target current pose that matches the target pose from each current pose to determine the matching pose that matches each second pose.

[0063] Step S104: Based on each of the second poses and the optimal pose that matches each of the second poses, plan to obtain the target shooting path.

[0064] In the specific implementation process of this step, specifically, any second pose can be determined from each second pose as the original shooting pose; then, based on the original shooting pose, the matching pose corresponding to the original shooting pose, and the matching poses corresponding to each remaining second pose, several target second poses are sequentially determined from the remaining second poses; finally, based on the original shooting pose and each target second pose, the target shooting path is constructed.

[0065] The method for planning a photographing path for quality inspection in this embodiment can filter out the photographing poses that collide with obstacles by obtaining several first poses and performing collision detection on the first poses, so that the subsequently planned photographing path will not collide with obstacles, improving the shooting efficiency and making the shooting data more stable; at the same time, by matching the corresponding optimal pose for each second pose, the planned target shooting path can be made more reasonable and accurate, avoiding the problem of redundant shooting data caused by the planned path being tortuous and roundabout.

[0066] Based on the above embodiments, another embodiment of the present application provides a photographing path planning method for quality inspection, including the following steps:

[0067] Step S201, obtaining a plurality of first poses of the end of the robotic arm based on the position information of the object to be detected;

[0068] Step S202, based on the pre-established kinematic model of the robotic arm, performing inverse kinematic solution calculations on each of the first poses to determine whether there is a corresponding inverse kinematic solution for each of the first poses; if there is an inverse solution, execute Step S203; if there is no inverse solution, adjust the first pose to obtain an adjusted first pose, and re-perform the inverse kinematic solution calculation based on the adjusted first pose;

[0069] In the specific implementation of this step, the inverse kinematic solution process is as follows: establish the forward kinematic equation of the rigid robotic arm according to the DH (Denavit-Hartenberg) convention, and use θ i , a i , d i , α i to represent the parameters related to link i and joint i, that is, θ i represents the link length, a i represents the link twist, d i represents the link offset, and α i represents the joint angle. The homogeneous matrix A i represents the transformation matrix for link i to rotate around joint i, and A i can be obtained by the product of 4 basic transformations, which is specifically expressed as follows:

[0070]

[0071] In this step, the forward kinematic equation of the robotic arm can be expressed as where Θ = [θ1, θ2, θ3, …… θ n represents the angle values of the n joint axes of the robotic arm.

[0072] The problem of finding the inverse kinematic solution of the robotic arm can be expressed as a non-linear least squares problem. By optimizing the angle values Θ of the joint axes, the L2 norm of F(Θ) - Y is minimized, and the optimization function is as follows:

[0073]

[0074] where Y is the homogeneous matrix representation of the target pose of the end of the robotic arm. In this step, by establishing the above forward kinematic equation, it lays a foundation for subsequent inverse kinematic solution calculations of the pose of the end of the robotic arm using this equation to obtain the values of the joint axes of the robotic arm.

[0075] Step S203: Calculate the poses of the joints of the robotic arm in space based on the first pose.

[0076] In the specific implementation of this step, after obtaining the inverse kinematics solution of the robotic arm, the joint angle values Θ in the inverse kinematics solution can be used as the poses of the joints in space.

[0077] Step S204: Perform collision detection on the first pose based on the poses of the joints in space corresponding to the same first pose and the position information of the obstacle, and obtain a number of second poses that do not collide with the obstacle.

[0078] Step S205: Sequentially use each of the second poses as the target pose, use the second poses other than the target pose as the current pose, and sequentially calculate the matching degrees corresponding to each current pose based on the target pose and each current pose using a predetermined matching function.

[0079] In this step, for any two poses, that is, for the target pose Y and the current pose S t , the matching degree of these two poses can be calculated through the following formula:

[0080]

[0081] where R t represents the matching degree; S t represents the current pose; Y represents the target pose; and e is a constant.

[0082] Step S206: Based on the matching degrees corresponding to each current pose, determine the target current pose that matches the target pose from each current pose to determine the matching poses that match each second pose.

[0083] In this step, after calculating the matching degrees corresponding to each current pose, several matching poses that match the target pose (any second pose) can be determined. Specifically, based on the high and low of the matching degrees, the top three current poses can be determined as the matching poses in descending order, or the current poses with matching degrees greater than a predetermined matching degree threshold can be determined as the matching poses by comparing the matching degrees with the predetermined matching degree threshold.

[0084] Step S207: Determine any second pose from each second pose as the original shooting pose; based on the original shooting pose, the matching pose corresponding to the original shooting pose, and the matching poses corresponding to each remaining second pose, sequentially determine several target second poses from the remaining second poses; based on the original shooting pose and the target second poses, construct the target shooting path.

[0085] In this step, after determining the matching poses corresponding to each second pose, based on the original shooting pose, the first target second pose corresponding to the original shooting pose can be determined from the remaining second poses, and then based on the first target second pose, the second target second pose corresponding to the first target second pose can be determined from the remaining second poses, and so on, until the m-th target second pose is the original shooting pose, obtaining m - 1 target second poses. Subsequently, based on the original shooting pose and the m - 1 target second poses, a shooting path can be constructed. That is, for n second poses, based on the original shooting pose, the first target second pose corresponding to the original shooting pose can be determined from the remaining n - 1 second poses, and then based on the first target second pose, the second target second pose corresponding to the first target second pose can be determined from the remaining n - 2 second poses, and so on, until the m-th target second pose is the original shooting pose, obtaining m - 1 target second poses.

[0086] In this embodiment, after obtaining the target shooting path, based on the inverse solutions corresponding to each target second pose in the target shooting path, the poses of each joint axis point corresponding to each target second pose in space can be determined. That is, the action A (Θ in the forward and inverse kinematic models of the robotic arm) is determined through the target second pose state S, so as to control the robotic arm to perform corresponding movements to control the robotic arm to move to the corresponding target second pose.

[0087] The method for photographing path planning for quality inspection in this embodiment can filter out the photographing poses that collide with obstacles by obtaining several first poses and performing collision detection on the first poses, so that the subsequent planned photographing path will not collide with obstacles, improving the photographing efficiency and making the photographing data more stable. At the same time, by matching the corresponding optimal poses for each second pose, the planned target photographing path can be made more reasonable and accurate, avoiding the problem of redundant photographing data caused by the tortuous and circuitous path obtained by planning. The method in this embodiment can complete the path planning and collision detection work of the photographing points of the robotic arm, thereby realizing multi-angle photographing of the workpiece to be measured, effectively improving the quality inspection efficiency and accuracy. In the field of industrial manufacturing, the application of the present invention will greatly promote the development of quality control technology and provide a more reliable and efficient quality inspection means for industrial production.

[0088] Another embodiment of the present application provides a photographing path planning device for quality inspection, as Figure 2 shown, including:

[0089] An acquisition module 11, configured to acquire several first poses of the end of the robotic arm based on the position information of the object to be detected;

[0090] The detection module 12 is configured to perform collision detection respectively based on each of the first poses and the position information of the obstacle, and obtain a plurality of second poses that do not collide with the obstacle.

[0091] The matching module 13 is configured to sequentially use each of the second poses as a target pose, and use the second poses other than the target pose as the current poses, and respectively determine a target current pose that matches the target pose from each of the current poses, so as to determine a matching pose that matches each of the second poses.

[0092] The planning module 14 is configured to plan and obtain a target shooting path based on each of the second poses and the optimal pose that matches each of the second poses.

[0093] In the specific implementation process of this embodiment, the detection module is specifically configured to: perform inverse kinematic solution calculation on each of the first poses based on a pre-established kinematic model of the robotic arm to determine whether there is a corresponding inverse kinematic solution for each of the first poses; in the case where there is a corresponding inverse kinematic solution for the first pose, calculate the poses of each joint axis of the robotic arm in space based on the first pose; perform collision detection on the first pose based on the poses of each joint axis in space corresponding to the same first pose and the position information of the obstacle, and obtain a plurality of second poses that do not collide with the obstacle.

[0094] In the specific implementation process of this embodiment, the matching module is specifically configured to: sequentially calculate the matching degree corresponding to each current pose by using a predetermined matching function based on the target pose and each current pose; determine a target current pose that matches the target pose from each of the current poses based on the matching degree corresponding to each current pose, so as to determine a matching pose that matches each of the second poses.

[0095] In the specific implementation process of this embodiment, the matching function is:

[0096]

[0097] where R t represents the matching degree; S t represents the current pose; Y represents the target pose; and e is a constant.

[0098] In the specific implementation process of this embodiment, the planning module is specifically configured to: determine any second pose from each of the second poses as the original shooting pose; sequentially determine a plurality of target second poses from the remaining second poses based on the original shooting pose, the matching pose corresponding to the original shooting pose, and the matching poses corresponding to each of the remaining second poses; and construct the target shooting path based on the original shooting pose and the target second poses.

[0099] The photographing path planning device for quality inspection in this embodiment can filter out the photographing poses that collide with obstacles by obtaining several first poses and performing collision detection on the first poses, so that the subsequent planned photographing path will not collide with obstacles, improving the photographing efficiency and making the photographing data more stable. At the same time, by matching corresponding optimal poses for each second pose, the target photographing path planned can be made more reasonable and accurate, avoiding the problem of redundant photographing data caused by the tortuous and circuitous path obtained by planning. The device in this embodiment can complete the path planning and collision detection of the robot arm photographing points, so as to realize multi-angle photographing of the workpiece to be measured, effectively improving the quality inspection efficiency and accuracy. In the field of industrial manufacturing, the application of the present invention will greatly promote the development of quality control technology and provide a more reliable and efficient quality inspection means for industrial production.

[0100] Another embodiment of the present application provides a storage medium, which stores a computer program. When the computer program is executed by a processor, the following method steps are implemented:

[0101] Step 1: Obtain several first poses of the end of the robot arm based on the position information of the object to be detected;

[0102] Step 2: Based on each of the first poses and the position information of the obstacle, perform collision detection respectively to obtain several second poses that do not collide with the obstacle;

[0103] Step 3: Successively use each of the second poses as the target pose, and use the second poses other than the target pose as the current pose, and respectively determine the target current pose that matches the target pose from each current pose to determine the matching pose that matches each second pose;

[0104] Step 4: Based on each of the second poses and the matching poses that match each of the second poses, plan to obtain the target photographing path.

[0105] For the specific implementation process of the above method steps, reference can be made to the embodiments of any of the above photographing path planning methods for quality inspection, and this embodiment will not be repeated here.

[0106] The storage medium in this application can filter out the photographing poses that collide with obstacles by obtaining several first poses and performing collision detection on the first poses, so that the subsequent planned photographing path will not collide with obstacles, improving the photographing efficiency and making the photographing data more stable. At the same time, by matching the corresponding optimal poses for each second pose, the planned target photographing path can be made more reasonable and accurate, avoiding the problem of redundant photographing data caused by the tortuous and detoured path obtained by the plan. The storage medium in this embodiment can complete the path planning and collision detection of the photographing points of the robotic arm, so as to achieve multi-angle photographing of the workpiece to be measured, effectively improving the quality inspection efficiency and accuracy. In the field of industrial manufacturing, the application of the present invention will greatly promote the development of quality control technology and provide a more reliable and efficient quality inspection means for industrial production.

[0107] Another embodiment of this application provides an electronic device, as Figure 3 shown, including at least a memory 1 and a processor 2. A computer program is stored on the memory 1, and when the processor 2 executes the computer program on the memory 1, the following method steps are implemented:

[0108] Step 1: Obtain several first poses at the end of the robotic arm based on the position information of the object to be detected;

[0109] Step 2: Based on each of the first poses and the position information of the obstacle, perform collision detection respectively to obtain several second poses that do not collide with the obstacle;

[0110] Step 3: Sequentially use each of the second poses as the target pose, and use the second poses other than the target pose as the current pose, and respectively determine the target current pose that matches the target pose from each current pose to determine the matching pose that matches each second pose;

[0111] Step 4: Based on each of the second poses and the matching poses that match each of the second poses, plan to obtain the target photographing path.

[0112] For the specific implementation process of the above method steps, reference can be made to the embodiments of any of the above photographing path planning methods for quality inspection, and this embodiment will not be repeated here.

[0113] The electronic device in this application can filter out the photographing poses that collide with obstacles by obtaining a number of first poses and performing collision detection on the first poses, so that the subsequent planned photographing path will not collide with obstacles, improving the photographing efficiency and making the photographing data more stable. At the same time, by matching the corresponding optimal poses for each second pose, the planned target photographing path can be made more reasonable and accurate, avoiding the problem of redundant photographing data caused by the tortuous and circuitous path obtained by the plan. The electronic device in this embodiment can complete the path planning and collision detection of the robotic arm photographing points, thereby realizing multi-angle photographing of the workpiece to be measured, effectively improving the quality inspection efficiency and accuracy. In the field of industrial manufacturing, the application of the present invention will greatly promote the development of quality control technology and provide a more reliable and efficient quality inspection means for industrial production.

[0114] The above embodiments are only exemplary embodiments of this application and are not used to limit this application. The protection scope of this application is defined by the claims. Those skilled in the art can make various modifications or equivalent replacements to this application within the essence and protection scope of this application, and such modifications or equivalent replacements should also be regarded as falling within the protection scope of this application.

Claims

1. A method for photographing path planning for quality inspection, characterized in that, Including: Obtaining a plurality of first poses of the end of the robotic arm based on the position information of the object to be detected; Performing collision detection respectively based on each of the first poses and the position information of the obstacle, and obtaining a plurality of second poses that do not collide with the obstacle; Sequentially taking each of the second poses as the target pose, and taking the second poses other than the target pose as the current poses, respectively determining the target current pose that matches the target pose from each of the current poses, so as to determine the matching pose that matches each of the second poses; Planning to obtain a target shooting path based on each of the second poses and the matching poses that match each of the second poses.

2. The method according to claim 1, wherein The performing collision detection respectively based on each of the first poses and the position information of the obstacle, and obtaining a plurality of second poses that do not collide with the obstacle includes: Based on the pre-established kinematic model of the robotic arm, performing inverse solution calculation on each of the first poses to determine whether there is a corresponding inverse solution of the robotic arm for each of the first poses; In the case where there is a corresponding inverse solution of the robotic arm for the first pose, calculating the poses of each joint axis of the robotic arm in space based on the first pose; Performing collision detection on the first pose based on the poses of each joint axis in space corresponding to the same first pose and the position information of the obstacle, and obtaining a plurality of second poses that do not collide with the obstacle.

3. The method according to claim 1, characterized in that The respectively determining the target current pose that matches the target pose from each of the current poses, so as to determine the matching pose that matches each of the second poses includes: Sequentially based on the target pose and each of the current poses, using a predetermined matching function to calculate the matching degree corresponding to each of the current poses respectively; Based on the matching degrees corresponding to each of the current poses, determining the target current pose that matches the target pose from each of the current poses, so as to determine the matching pose that matches each of the second poses.

4. The method according to claim 3, wherein The matching function is: Among them, R t represents the matching degree; S t represents the current pose; Y represents the target pose; e is a constant.

5. The method according to claim 1, wherein The planning to obtain a target shooting path based on each of the second poses and the matching poses that match each of the second poses includes: Determining any second pose from each of the second poses as the original shooting pose; Based on the original shooting pose, the matching pose corresponding to the original shooting pose, and the matching poses corresponding to each of the remaining second poses, sequentially determining a plurality of target second poses from the remaining second poses; Constructing the target shooting path based on the original shooting pose and the target second poses.

6. A photographing path planning device for quality inspection, characterized in that, Including: An acquisition module, configured to obtain a plurality of first poses of the end of the robotic arm based on the position information of the object to be detected; A detection module, configured to perform collision detection respectively based on each of the first poses and the position information of the obstacle, and obtain a plurality of second poses that do not collide with the obstacle; A matching module, configured to sequentially take each of the second poses as the target pose, and take the second poses other than the target pose as the current poses, respectively determining the optimal current pose that matches the target pose from each of the current poses, so as to determine the optimal pose that matches each of the second poses; A planning module, configured to plan to obtain a target shooting path based on each of the second poses and the optimal poses that match each of the second poses.

7. The device according to claim 6, characterized in that, The detection module is specifically configured to: Based on the pre-established kinematic model of the robotic arm, perform inverse kinematic solution calculations for each of the first poses to determine whether there is a corresponding inverse solution of the robotic arm for each of the first poses; In the case where there is a corresponding inverse solution of the robotic arm for the first pose, calculate the poses of the joints of the robotic arm in space based on the first pose; Based on the poses of the joints corresponding to the same first pose in space and the position information of the obstacle, perform collision detection on the first pose to obtain a number of second poses that do not collide with the obstacle.

8. The device according to claim 6, characterized in that, The matching module is specifically configured to: Successively calculate the matching degrees corresponding to each current pose by using a predetermined matching function based on the target pose and each current pose; Based on the matching degrees corresponding to each current pose, determine a target current pose that matches the target pose from each current pose to determine a matching pose that matches each second pose.

9. A storage medium, characterized in that, The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for photographing path planning for quality inspection according to any one of claims 1-5 above are implemented.

10. An electronic device, characterized in that, At least including a memory and a processor, a computer program is stored on the memory, and when the processor executes the computer program on the memory, the steps of the method for photographing path planning for quality inspection according to any one of claims 1-5 above are implemented.

Images