A programming method and system for welding robots
By establishing a basic model point set and non-rigid point set registration technology for similar workpieces, the weld seam trajectory and auxiliary trajectory point cloud are obtained, solving the problem of low programming efficiency of existing welding robots and realizing automatic programming and efficient welding of similar workpieces.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANDONG UNIV
- Filing Date
- 2023-11-20
- Publication Date
- 2026-05-26
AI Technical Summary
Existing welding robot programming technology is inefficient when dealing with complex and non-standard workpieces, requires complex operation and professional skills, and is difficult to adapt to workpieces of different sizes and deformations, resulting in extended welding cycles.
By establishing a basic model point set for similar workpieces, and using non-rigid point set registration technology, the weld seam trajectory and auxiliary trajectory point cloud of the workpiece to be welded are obtained. The welding torch pose is planned in combination with the dense point cloud to generate the operating program of the welding robot.
It enables automatic programming of similar workpieces, simplifies weld seam trajectory planning, improves the programming efficiency of welding robots, and is applicable to similar workpieces of different sizes and deformations, avoiding repetitive programming.
Smart Images
Figure CN117428773B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of robot trajectory planning and programming, and particularly relates to a programming method and system for a welding robot. Background Technology
[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.
[0003] Welding, a manufacturing process and technology that joins metals or other thermoplastic materials such as plastics by heating, high temperature, or high pressure, is a very important processing method in industrial production. Because high temperature or high pressure methods are often used, the welding process involves factors such as fumes, arc light, and metal spatter, all of which can harm the health of welding workers. The welding working environment is also very harsh, and the quality of the weld has a decisive impact on product quality. Compared with manual welding, welding robots offer high stability, high efficiency, and high weld quality, ensuring the consistency of the welding process. The use of welding robots can improve workers' working conditions and increase labor productivity; therefore, welding robots are widely used in industry.
[0004] Currently, the main methods for using robots to complete welding operations are traditional teach-in programming and offline programming. Teach-in programming requires operating the robot and planning its pose point by point, which is not only cumbersome but also requires the robot to be occupied, resulting in low efficiency. In contrast, offline programming technology realizes the pose planning of the welding robot in a virtual 3D environment, and is widely used due to its advantages such as not requiring the robot to be occupied.
[0005] When welding complex workpieces, the trajectory planning of the welding robot's end effector is complex and tedious, whether using existing offline programming techniques or teach-in programming methods. Furthermore, highly skilled personnel are required to complete the pose planning and programming of the robot's end effector. Finally, for the same type of workpiece, different dimensions or deformations often necessitate reprogramming the welding robot, lengthening the entire welding cycle. While parametric equations can solve the trajectory planning for some typical workpieces, such as pipe-to-pipe and ball-to-pipe welding, current trajectory planning and programming techniques remain complex and time-consuming for the welding of more prevalent non-standard workpieces. Summary of the Invention
[0006] To overcome the shortcomings of the prior art, this invention provides a programming method and system for welding robots. By establishing a basic model point set for similar workpieces, the welding robot can automatically program similar workpieces (different specifications and sizes), simplifying the weld trajectory planning of complex workpieces and improving the programming efficiency of welding robots.
[0007] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:
[0008] The first aspect of this invention provides a programming method for a welding robot.
[0009] A programming method for a welding robot, comprising:
[0010] Obtain the edge feature point cloud and dense point cloud of the workpiece to be welded;
[0011] Based on the structural similarity of similar workpieces, the pre-built basic model point set is non-rigidly registered with the edge feature point cloud of the workpiece to be welded to obtain the weld seam trajectory point cloud and auxiliary trajectory point cloud of the workpiece to be welded.
[0012] Based on the weld trajectory point cloud, auxiliary trajectory point cloud and dense point cloud of the workpiece to be welded, the welding gun pose is generated by setting the welding gun pose process parameters. After pose transformation between coordinate systems, the weld trajectory planning is completed.
[0013] Based on the planned weld seam trajectory, the operating program of the welding robot is generated;
[0014] The basic model point set consists of edge feature point clouds, weld trajectory point clouds, and auxiliary trajectory point clouds of the basic workpiece. A simple prototype workpiece of the same type is selected as the basic workpiece, and the three-dimensional model, weld trajectory, and auxiliary trajectory of the basic workpiece are processed into point clouds to obtain the edge feature point clouds, weld trajectory point clouds, and auxiliary trajectory point clouds of the basic model point set.
[0015] Furthermore, the acquisition of the edge feature point cloud and dense point cloud of the workpiece to be welded specifically involves:
[0016] Obtain the 3D model of the workpiece to be welded, and process the 3D model of the workpiece to be welded into point cloud to obtain the edge feature point cloud and dense point cloud of the workpiece to be welded.
[0017] Furthermore, the acquisition of the edge feature point cloud and dense point cloud of the workpiece to be welded specifically involves:
[0018] The sensor acquires a dense point cloud of the workpiece to be welded, and the edge feature point cloud of the workpiece to be welded is extracted from the dense point cloud.
[0019] Furthermore, obtaining the weld seam trajectory point cloud and auxiliary trajectory point cloud of the workpiece to be welded specifically involves:
[0020] The edge feature point cloud of the workpiece to be welded is non-rigidly registered with the edge feature point cloud of the base workpiece and the weld trajectory point cloud in the base model point set to obtain the weld trajectory point cloud S of the workpiece to be welded. T ;
[0021] By utilizing the one-to-one correspondence between the weld trajectory point cloud and the auxiliary trajectory point cloud, a non-rigid transformation is applied from the weld trajectory point cloud of the basic model point set to the weld trajectory point cloud of the workpiece to be welded. This transformation is then applied to the auxiliary trajectory point cloud of the basic model point set to obtain the auxiliary trajectory point cloud of the workpiece to be welded.
[0022] Furthermore, it also includes smoothing the weld trajectory point cloud and auxiliary trajectory point cloud of the workpiece to be welded. Specifically, the weld trajectory point cloud and auxiliary trajectory point cloud of the workpiece to be welded are curve fitted and then interpolated to generate new weld trajectory point cloud and auxiliary trajectory point cloud.
[0023] Furthermore, the generation of the welding torch pose is based on each point s in the weld trajectory point cloud. i Perform the following procedure:
[0024] Dense point clouds located at s i Project the points inside a cube with a preset side length centered on the current welding point onto the welding plane to obtain the set of projection points;
[0025] Based on the set of projection points, the coordinate system of the current weld point is obtained by solving the problem;
[0026] The welding torch pose of the current weld point is obtained by transforming the coordinate system of the current weld point to the coordinate system of the welding torch tip.
[0027] Furthermore, after the pose transformation between coordinate systems, the weld seam trajectory planning is completed, specifically as follows:
[0028] By transforming the pose between the current weld point coordinate system, the workpiece coordinate system, and the robot's basic coordinate system, the welding robot can complete the welding torch trajectory planning for the workpiece to be welded.
[0029] A second aspect of the present invention provides a programming system for a welding robot.
[0030] A programming system for a welding robot includes a point cloud acquisition module, a trajectory registration module, a trajectory planning module, and a program generation module.
[0031] The point cloud acquisition module is configured to acquire the edge feature point cloud and dense point cloud of the workpiece to be welded.
[0032] The trajectory registration module is configured to: based on the structural similarity of similar workpieces, perform non-rigid point set registration between the pre-built basic model point set and the edge feature point cloud of the workpiece to be welded, so as to obtain the weld trajectory point cloud and auxiliary trajectory point cloud of the workpiece to be welded.
[0033] The trajectory planning module is configured to generate the welding gun pose based on the weld trajectory point cloud, auxiliary trajectory point cloud and dense point cloud of the workpiece to be welded, through the setting of welding gun pose process parameters, and complete the weld trajectory planning after pose transformation between coordinate systems.
[0034] The program generation module is configured to generate the operating program of the welding robot based on the planned weld seam trajectory.
[0035] The basic model point set consists of edge feature point clouds, weld trajectory point clouds, and auxiliary trajectory point clouds of the basic workpiece. A simple prototype workpiece of the same type is selected as the basic workpiece, and the three-dimensional model, weld trajectory, and auxiliary trajectory of the basic workpiece are processed into point clouds to obtain the edge feature point clouds, weld trajectory point clouds, and auxiliary trajectory point clouds of the basic model point set.
[0036] A third aspect of the present invention provides a computer-readable storage medium having a program stored thereon that, when executed by a processor, implements the steps of a programming method for a welding robot as described in the first aspect of the present invention.
[0037] A fourth aspect of the present invention provides an electronic device including a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in a programming method for a welding robot as described in the first aspect of the present invention.
[0038] The above one or more technical solutions have the following beneficial effects:
[0039] 1) Strong universality: This invention establishes a basic model point set for similar workpieces, and realizes the extraction of weld seam trajectory point cloud and generation of weld seam auxiliary trajectory of the workpiece to be welded through non-rigid registration. Then, it combines the dense point cloud of the workpiece to be welded to realize the welding gun pose planning. This method is applicable to various similar welding workpieces.
[0040] 2) Effectively reduces the difficulty of weld trajectory planning; For some workpieces with complex weld trajectories among similar workpieces, it is difficult to use parameterization for weld trajectory planning, while teaching programming is very cumbersome; Based on the structural similarity of similar workpieces, this invention extracts the weld trajectory through non-rigid point set registration, and only requires the dense point cloud and feature point cloud of the workpiece to be welded to automatically complete the weld trajectory planning of the workpiece to be welded.
[0041] 3) Significantly improves the programming efficiency of welding robots; after the basic model is established, for similar workpieces of different sizes or different deformations, only the dense point cloud and feature point cloud of the workpiece to be welded need to be input to automatically complete the weld trajectory planning of the workpiece to be welded, which can effectively avoid repeated programming of similar workpieces and significantly improve the programming efficiency of welding robots.
[0042] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description
[0043] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.
[0044] Figure 1 This is a flowchart of the method in the first embodiment.
[0045] Figure 2 This is a schematic diagram of the workpiece to be welded in the first embodiment.
[0046] Figure 3 This is a flowchart of the welding robot trajectory planning and programming method in the first embodiment.
[0047] Figure 4 A schematic diagram is provided for establishing the basic model of the first embodiment.
[0048] Figure 5 This is a schematic diagram of the weld seam auxiliary trajectory for the first embodiment.
[0049] Figure 6 This is a schematic diagram of the extraction of weld seam trajectory point set for the workpiece to be welded in the first embodiment.
[0050] Figure 7 A schematic diagram of solving the Z-axis for the current weld point in the first embodiment.
[0051] Figure 8 This is a schematic diagram illustrating the transformation from the current weld point coordinate system to the welding torch end coordinate system in the first embodiment. Detailed Implementation
[0052] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of this application. Unless otherwise specified, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.
[0053] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.
[0054] This invention addresses the shortcomings of current welding robot programming technology by proposing a modular programming approach. By establishing a basic model point set for similar workpieces, it enables the welding robot to automatically program similar workpieces (different specifications and sizes). Specifically:
[0055] First, a simple prototype (model) workpiece of the same type is selected as the base workpiece. Using the 3D model of the base workpiece, the weld seam trajectory is selected. Based on the information from both sides of the weld seam trajectory, the welding torch posture is planned, thus generating the weld seam auxiliary trajectory. The 3D model of the base workpiece is processed into a point cloud to generate the edge feature point cloud of the base workpiece. The edge feature point cloud of the base workpiece, the weld seam trajectory point cloud, and the auxiliary trajectory point cloud are combined to generate the base model point set. Then, the 3D model of the target (to be welded) workpiece is processed into a point cloud or the target workpiece point cloud is acquired through sensors. Based on the structural similarity of similar workpieces, the base model point set and the target workpiece point cloud are non-rigidly registered. This yields the weld seam trajectory and weld seam auxiliary lines in the target workpiece. The welding torch posture is planned using the dense point cloud of the target workpiece, the weld seam trajectory, and the weld seam auxiliary trajectory. Finally, the programming task for the welding robot to be welded is completed.
[0056] This invention enables weld seam trajectory planning and welding robot programming for similar workpieces without requiring complex workpiece parameters as input, thus simplifying weld seam trajectory planning for complex workpieces and improving the programming efficiency of welding robots.
[0057] Example 1
[0058] One embodiment of this disclosure provides a programming method for a welding robot, such as... Figure 1 As shown, it includes the following steps:
[0059] Step S1: Obtain the edge feature point cloud and dense point cloud of the workpiece to be welded;
[0060] Step S2: Based on the structural similarity of similar workpieces, the pre-built basic model point set is non-rigidly registered with the edge feature point cloud of the workpiece to be welded to obtain the weld trajectory point cloud and auxiliary trajectory point cloud of the workpiece to be welded.
[0061] Step S3: Based on the weld trajectory point cloud, auxiliary trajectory point cloud and dense point cloud of the workpiece to be welded, the welding gun pose is generated by setting the welding gun pose process parameters. After pose transformation between coordinate systems, the weld trajectory planning is completed.
[0062] Step S4: Based on the planned weld seam trajectory, generate the operating program for the welding robot;
[0063] The basic model point set consists of edge feature point clouds, weld trajectory point clouds, and auxiliary trajectory point clouds of the basic workpiece. A simple prototype workpiece of the same type is selected as the basic workpiece, and the three-dimensional model, weld trajectory, and auxiliary trajectory of the basic workpiece are processed into point clouds to obtain the edge feature point clouds, weld trajectory point clouds, and auxiliary trajectory point clouds of the basic model point set.
[0064] The following is based on Figure 2 Taking a typical 3D model of a stiffener fillet weld workpiece as an example, this embodiment provides a detailed explanation of the implementation process of a welding robot programming method, including the welding trajectory planning of the stiffener fillet weld workpiece and the programming process of the welding robot. Figure 3 As shown, specifically:
[0065] Step 1: Select the weld trajectory in the basic workpiece 3D model, and generate the auxiliary weld trajectory based on the surface information adjacent to the weld trajectory. The workpiece coordinate system is defined as X. W Y W Z W .
[0066] Select a simple prototype (model) workpiece from the same type of workpiece as the base workpiece, such as... Figure 4 As shown, taking a point in the weld trajectory as an example, the coordinate system of the current weld point is defined as X. S Y S Z S The current weld point is defined as s i (that is, the origin O of the current weld coordinate system) S Based on the direction of the welding torch's movement on the weld trajectory curve, the tangent vector of the weld trajectory curve is taken as the direction of travel and defined as X. S Axis, with X S It is a normal vector that passes through point s i The plane is defined as the welding plane, and the normal vector of the tangent planes on both sides of the weld. and It can be calculated from a 3D model, therefore it can be obtained through the normal vector. and Determine Z S Axial direction.
[0067] like Figure 5 As shown, the weld trajectory point s iCorresponding weld auxiliary point s i Located in Z S Above and with s i The distance between them is l = 20 mm.
[0068] The 3D model of the basic workpiece, the weld trajectory, and the auxiliary trajectory are processed into point clouds to obtain the edge feature point cloud P. M Weld seam trajectory point cloud S M and its auxiliary trajectory point cloud S' M In this process, points identical to the weld trajectory are removed from the edge feature point cloud, and the weld trajectory point cloud S... M With weld seam auxiliary trajectory point cloud S' M The points in the model correspond one-to-one, and these three point sets form the basic model point set.
[0069] Step 2: Obtain the edge feature point cloud Q of the workpiece to be welded T and dense point cloud Q' T .
[0070] This embodiment provides two optional acquisition methods:
[0071] (1) Obtain the edge feature point cloud and dense point cloud of the workpiece to be welded from the 3D model of the workpiece to be welded.
[0072] (2) Obtain dense point cloud from the workpiece to be welded through the sensor, and then extract edge feature point cloud through dense point cloud.
[0073] Step 3: Edge feature point cloud Q of the workpiece to be welded T Edge feature point cloud P in the base model point set M and weld seam trajectory point cloud S M Perform non-rigid registration to obtain the weld seam trajectory point cloud S of the workpiece to be welded. T .
[0074] like Figure 6 As shown, the feature point cloud Q of the workpiece to be welded T The edge feature point cloud P of the basic workpiece in the basic model point set M and weld seam trajectory point cloud S M Perform non-rigid registration. Based on the non-rigid registration results, find the feature point cloud Q of the workpiece to be welded. T S and the point cloud of the weld trajectory M By matching (registering) points, the weld trajectory point cloud S of the workpiece to be welded is obtained. T .
[0075] Step 4: Since there is a one-to-one correspondence between the weld trajectory point cloud and the weld auxiliary trajectory point cloud, the basic model points are concentrated into the weld trajectory point cloud S. M To the trajectory point set S of the workpiece to be weldedT Non-rigid transformation S T =f sim (S M +V), applied to the auxiliary trajectory point cloud S' of the weld seam in the basic model point set. M It can obtain the auxiliary trajectory point cloud S' of the weld seam of the workpiece to be welded. T .
[0076] Step 5: To ensure the smoothness of the trajectory, the point cloud S of the weld seam trajectory of the workpiece to be welded... T Weld seam auxiliary trajectory point cloud S' T After curve fitting, interpolation is performed to generate a new weld trajectory point cloud S. T Weld seam auxiliary trajectory point cloud S' T .
[0077] Step 6: Using the point cloud S of the weld seam trajectory of the workpiece to be welded T Weld seam auxiliary trajectory point cloud S' T and dense point cloud Q' T Implement welding torch position planning.
[0078] Specifically, based on the weld seam trajectory point cloud S T The order of the midpoints can be used to calculate the X value of the current welding point. S Axial direction; with a point s in the weld trajectory i For example, with its X S The plane whose normal vector is along the axial direction is the welding plane; such as Figure 7 As shown, the dense point cloud Q' T Located in the middle of s i Centered on a side with length l p Points within a 10mm cube are projected onto the welding plane of the current welding point; passing through point s i and point s i The straight line '' divides the projected points into point set A and point set B; calculate and count the relationship between each point in point set A and point s. i , point s i The included angle ∠a formed by ′ j s i s i According to the histogram of points formed by increasing angles, the projection points in the first peak are located on the intersection line between the tangent plane A and the welding plane. Therefore, the welding point s can be determined through these projection points. i The direction vector of the straight line of the intersection of one side tangent plane A and the welding plane The same method can be used to find vectors. Since the direction vector of the intersection line between the lateral cutting plane and the welding plane is perpendicular to the normal vector of the cutting plane, therefore... and It can solve for the Z-axis of the current weld point coordinate system.S Axial direction; according to X S Axial direction and Z S The axial direction can be used to calculate the Y-axis of the current welding point coordinate system. S Axial direction.
[0079] Step 7: Define the coordinate system of the welding torch tip as X T Y T Z T ,like Figure 8 As shown, the Z-axis of the welding torch end coordinate system T Align with the welding torch axis and point towards the current weld point s. i And with Z S With the axes in opposite directions, the distance between the origin of the welding torch coordinate system and the current welding point is the length of the welding wire extending out of the welding torch (also known as the dry extension).
[0080] Y S Axis and X T The included angle between the shafts is defined as ω = 90°, and the length of the welding wire extending out of the welding gun (conductive tip) is defined as l. w =12mm; Based on the above information, the pose relationship between the current weld point coordinate system and the welding torch can be determined. The homogeneous transformation matrix between the current weld point coordinate system and the welding torch end coordinate system is defined as follows:
[0081] Step 8: The coordinate system of the current weld point on the workpiece to be welded is compared with the workpiece coordinate system X. W Y W Z W The homogeneous transformation matrix between them is Workpiece coordinate system and robot coordinate system X B Y B Z B The homogeneous transformation matrix between them is
[0082] The welding torch pose of the current weld point can be obtained by transforming the coordinate system of the current weld point to the coordinate system of the welding torch tip.
[0083] Therefore, the pose planning of the welding robot's end-effector is achieved through homogeneous coordinate transformation between various coordinate systems as follows:
[0084]
[0085] Finally, the welding torch pose is converted into robot execution code, thus realizing the programming of the welding robot.
[0086] Example 2
[0087] One embodiment of this disclosure provides a programming system for a welding robot, including a point cloud acquisition module, a trajectory registration module, a trajectory planning module, and a program generation module:
[0088] The point cloud acquisition module is configured to acquire the edge feature point cloud and dense point cloud of the workpiece to be welded.
[0089] The trajectory registration module is configured to: based on the structural similarity of similar workpieces, perform non-rigid point set registration between the pre-built basic model point set and the edge feature point cloud of the workpiece to be welded, so as to obtain the weld trajectory point cloud and auxiliary trajectory point cloud of the workpiece to be welded.
[0090] The trajectory planning module is configured to generate the welding gun pose based on the weld trajectory point cloud, auxiliary trajectory point cloud and dense point cloud of the workpiece to be welded, through the setting of welding gun pose process parameters, and complete the weld trajectory planning after pose transformation between coordinate systems.
[0091] The program generation module is configured to generate the operating program of the welding robot based on the planned weld seam trajectory.
[0092] The basic model point set consists of edge feature point clouds, weld trajectory point clouds, and auxiliary trajectory point clouds of the basic workpiece. A simple prototype workpiece of the same type is selected as the basic workpiece, and the three-dimensional model, weld trajectory, and auxiliary trajectory of the basic workpiece are processed into point clouds to obtain the edge feature point clouds, weld trajectory point clouds, and auxiliary trajectory point clouds of the basic model point set.
[0093] Example 3
[0094] The purpose of this embodiment is to provide a computer-readable storage medium.
[0095] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in a programming method for a welding robot as described in Embodiment 1 of this disclosure.
[0096] Example 4
[0097] The purpose of this embodiment is to provide an electronic device.
[0098] An electronic device includes a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in a programming method for a welding robot as described in Embodiment 1 of this disclosure.
[0099] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A programming method for a welding robot, characterized in that, include: Obtain the edge feature point cloud and dense point cloud of the workpiece to be welded; Based on the structural similarity of similar workpieces, the pre-built basic model point set is non-rigidly registered with the edge feature point cloud of the workpiece to be welded to obtain the weld seam trajectory point cloud and auxiliary trajectory point cloud of the workpiece to be welded. Based on the weld trajectory point cloud, auxiliary trajectory point cloud and dense point cloud of the workpiece to be welded, the welding gun pose is generated by setting the welding gun pose process parameters. After pose transformation between coordinate systems, the weld trajectory planning is completed. Based on the planned weld seam trajectory, the operating program of the welding robot is generated; The basic model point set consists of the edge feature point cloud, weld trajectory point cloud, and auxiliary trajectory point cloud of the basic workpiece. A simple prototype workpiece of the same type is selected as the basic workpiece. The three-dimensional model, weld trajectory, and auxiliary trajectory of the basic workpiece are processed into point clouds to obtain the edge feature point cloud, weld trajectory point cloud, and auxiliary trajectory point cloud of the basic model point set. The specific steps for obtaining the weld seam trajectory point cloud and auxiliary trajectory point cloud of the workpiece to be welded are as follows: The edge feature point cloud of the workpiece to be welded is non-rigidly registered with the edge feature point cloud of the base workpiece and the weld trajectory point cloud in the base model point set to obtain the weld trajectory point cloud of the workpiece to be welded. ; By utilizing the one-to-one correspondence between the weld trajectory point cloud and the auxiliary trajectory point cloud, a non-rigid transformation is applied from the weld trajectory point cloud of the basic model point set to the weld trajectory point cloud of the workpiece to be welded. This transformation is then applied to the auxiliary trajectory point cloud of the basic model point set to obtain the auxiliary trajectory point cloud of the workpiece to be welded.
2. The programming method for a welding robot as described in claim 1, characterized in that, The acquisition of the edge feature point cloud and dense point cloud of the workpiece to be welded specifically involves: Obtain the 3D model of the workpiece to be welded, and process the 3D model of the workpiece to be welded into point cloud to obtain the edge feature point cloud and dense point cloud of the workpiece to be welded.
3. The programming method for a welding robot as described in claim 1, characterized in that, The acquisition of the edge feature point cloud and dense point cloud of the workpiece to be welded specifically involves: The sensor acquires a dense point cloud of the workpiece to be welded, and the edge feature point cloud of the workpiece to be welded is extracted from the dense point cloud.
4. The programming method for a welding robot as described in claim 1, characterized in that, It also includes smoothing the weld trajectory point cloud and auxiliary trajectory point cloud of the workpiece to be welded. Specifically, the weld trajectory point cloud and auxiliary trajectory point cloud of the workpiece to be welded are curve fitted and then interpolated to generate new weld trajectory point cloud and auxiliary trajectory point cloud.
5. The programming method for a welding robot as described in claim 1, characterized in that, The generated welding torch pose is obtained by analyzing each point in the weld trajectory point cloud. Perform the following procedure: Dense point clouds located in the following Project the points inside a cube with a preset side length centered on the current welding point onto the welding plane to obtain the set of projection points; Based on the set of projection points, the coordinate system of the current weld point is obtained by solving the problem; The welding torch pose of the current weld point is obtained by transforming the coordinate system of the current weld point to the coordinate system of the welding torch tip.
6. The programming method for a welding robot as described in claim 1, characterized in that, After the pose transformation between coordinate systems, the weld trajectory planning is completed, specifically as follows: By transforming the pose between the current weld point coordinate system, the workpiece coordinate system, and the robot's basic coordinate system, the welding robot can complete the welding torch trajectory planning for the workpiece to be welded.
7. A programming system for a welding robot, characterized in that, A programming method for a welding robot as described in any one of claims 1-6 includes a point cloud acquisition module, a trajectory registration module, a trajectory planning module, and a program generation module. The point cloud acquisition module is configured to acquire the edge feature point cloud and dense point cloud of the workpiece to be welded. The trajectory registration module is configured to: based on the structural similarity of similar workpieces, perform non-rigid point set registration between the pre-built basic model point set and the edge feature point cloud of the workpiece to be welded, so as to obtain the weld trajectory point cloud and auxiliary trajectory point cloud of the workpiece to be welded. The trajectory planning module is configured to generate the welding gun pose based on the weld trajectory point cloud, auxiliary trajectory point cloud and dense point cloud of the workpiece to be welded, through the setting of welding gun pose process parameters, and complete the weld trajectory planning after pose transformation between coordinate systems. The program generation module is configured to generate the operating program of the welding robot based on the planned weld seam trajectory. The basic model point set consists of edge feature point clouds, weld trajectory point clouds, and auxiliary trajectory point clouds of the basic workpiece. A simple prototype workpiece of the same type is selected as the basic workpiece, and the three-dimensional model, weld trajectory, and auxiliary trajectory of the basic workpiece are processed into point clouds to obtain the edge feature point clouds, weld trajectory point clouds, and auxiliary trajectory point clouds of the basic model point set.
8. An electronic device, characterized in that it comprises: Memory is used to store computer-readable instructions in a non-transitory manner. as well as Processor, for executing the computer-readable instructions, When the computer-readable instructions are executed by the processor, they perform the method described in any one of claims 1-6.
9. A storage medium characterized in that it non-transitory stores computer-readable instructions, wherein, When the non-transitory computer-readable instructions are executed by a computer, the instructions of the method according to any one of claims 1-6 are executed.