Robot machining feasibility judgment method and device

Abstract

The invention relates to a robot machining feasibility judgment method and device, and belongs to the technical field of robot machining.The method comprises the steps that a robot kinematics model is established, and the robot kinematics model is converted into a robot connecting rod model through a preset matrix conversion relation; generating an approximate working space of the robot by using the robot connecting rod model, and determining the reachability of a robot processing task in the approximate working space; in the machining process, a tool holder minimum bounding box and a neighborhood workpiece point cloud minimum bounding box are determined, and the collisiveness of the robot machining task is determined based on the projection of the tool holder minimum bounding box and the projection of the neighborhood workpiece point cloud minimum bounding box on the coordinate axis; and determining the feasibility of the robot processing task according to the accessibility and collisiveness of the robot processing task. By efficiently judging the feasibility of the machining task, the calculated amount of large non-regular component robot machining planning is reduced, and the planning efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of robot processing technology, and in particular to a robot processing feasibility judgment method and device. Background Art

[0002] With the continuous development of robot technology and the gradual reduction of mechanical manufacturing costs and component costs, robots have gradually penetrated from the industrial field into our daily lives. And with the continuous popularization of service robots, people's acceptance of robots has increased. The robots on the market have gradually expanded from single food delivery and express delivery robots to robots with rich functions such as medical care, interpretation and guidance. This also puts higher requirements on the stability, functionality and practicality of robots.

[0003] In the process of robot processing, the planning of grinding paths is still a difficult point. Large irregular components often face problems such as inability to reach some processing tasks and tool collisions due to their huge size and complex surface.

[0004] Therefore, how to perform complex planning for robots of large irregular workpieces in order to efficiently evaluate the processing feasibility of the planning scheme is an urgent problem to be solved. Summary of the invention

[0005] In view of this, it is necessary to provide a method and device for judging the feasibility of robot processing, which can be used to efficiently judge the feasibility of the robot's processing tasks, reduce the calculation amount of robot processing planning for large irregular components, and improve planning efficiency.

[0006] In order to achieve the above object, in a possible implementation, the present invention provides a robot processing feasibility judgment method, comprising: Establishing a robot kinematics model, and converting the robot kinematics model into a robot link model using a preset matrix conversion relationship; Generate an approximate workspace of the robot using the robot linkage model, and determine the reachability of the robot processing task in the approximate workspace; During the machining process, the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud are determined, and the collision of the robot machining task is determined based on the projection of the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud on the coordinate axis; The feasibility of the robot processing task is determined based on the reachability and collision of the robot processing task.

[0007] In a possible implementation, establishing the robot kinematic model includes: The robot's terminal posture matrix and joint angles are obtained, and the robot's kinematic model is established based on the robot's terminal posture matrix and joint angles.

[0008] In a possible implementation, the generating an approximate workspace of the robot using the robot link model includes: Determining a robot joint angle combination, wherein the robot joint angle combination includes randomly generated joint angles; The robot joint angle combination is substituted into the robot link model to obtain randomly generated coordinates, and the robot approximate workspace is generated using the coordinates.

[0009] In a possible implementation, determining the reachability of the robot processing task in the approximate workspace includes: The distance from each robot processing task point to a preset bounding sphere is calculated, and the reachability of the robot processing task is determined based on the distance.

[0010] In a possible implementation, determining the reachability of the robot processing task based on the distance includes: The distance is input into a preset reachability formula. If the formula result is greater than 0, the robot processing task can be reached. If the formula result is less than 0, the robot processing task cannot be reached.

[0011] In a possible implementation, determining the minimum bounding box of the tool and the minimum bounding box of the neighboring workpiece point cloud during the machining process includes: Determine the first extreme value coordinates of the tool handle, and generate a minimum bounding box of the tool handle based on the first extreme value coordinates; The neighborhood workpiece point cloud is determined based on the tool center coordinates and the preset distance, the second extreme value coordinates of the domain workpiece point cloud are determined, and the minimum bounding box of the neighborhood workpiece point cloud is generated based on the second extreme value coordinates.

[0012] In a possible implementation, the determining of the collision of the robot machining task based on the projection of the tool handle minimum bounding box and the neighborhood workpiece point cloud minimum bounding box on the coordinate axis includes: Determine the mark position where the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud overlap on the coordinate axis; If the value of the flag bit is 1, the robot processing task will collide, and if the value of the flag bit is 0, the robot processing task will not collide.

[0013] The present invention also provides a robot processing task feasibility judgment device, comprising: A model building module, used to build a robot kinematic model and convert the robot kinematic model into a robot connecting rod model using a preset matrix conversion relationship; a reachability determination module, configured to generate an approximate workspace of the robot using the robot link model, and determine the reachability of the robot processing task in the approximate workspace; A collision determination module is used to determine the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud during the machining process, and determine the collision of the robot machining task based on the projection of the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud on the coordinate axis; The feasibility determination module is used to determine the feasibility of the robot processing task according to the reachability and collision of the robot processing task.

[0014] The beneficial effects of the present invention are as follows: the present invention proposes a method for judging the feasibility of robot processing of large irregular surface components, firstly generates an approximate robot workspace to judge whether all processing tasks are reachable, then generates a minimum bounding box of the tool handle and a minimum bounding box of the neighborhood workpiece point cloud to judge whether the tool collides with the workpiece, and efficiently judges the feasibility of the processing task from the two dimensions of accessibility and collision, thereby reducing the computational complexity of robot processing planning of large irregular components and improving planning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for determining the feasibility of robot processing provided by the present invention; Figure 2 A schematic diagram of a connecting rod model provided in one embodiment of the present invention; Figure 3 A schematic diagram of determining the reachability of a processing task in one embodiment of the present invention; Figure 4 This is a schematic diagram of collision judgment in one embodiment of the present invention; Figure 5 A schematic structural diagram of an embodiment of a robot processing feasibility judgment device provided by the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0018] In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more. The descriptions of "first", "second", etc. involved in the embodiments of the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0019] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places 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 skilled in the art that the embodiments described herein may be combined with other embodiments.

[0020] The specific embodiments are described in detail below: See also Figure 1 , Figure 1 A schematic flow chart of an embodiment of a method for determining the feasibility of robot processing provided by the present invention. A specific embodiment of the present invention discloses a method for determining the feasibility of robot processing, comprising: Step S101: establishing a robot kinematics model, and converting the robot kinematics model into a robot link model using a preset matrix conversion relationship; Step S102: Generate an approximate workspace of the robot using the robot link model, and determine the reachability of the robot processing task in the approximate workspace; Step S103: determining the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud during the machining process, and determining the collision of the robot machining task based on the projections of the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud on the coordinate axis; Step S104: Determine the feasibility of the robot processing task according to the reachability and collision of the robot processing task.

[0021] The present invention proposes a method for judging the feasibility of robot machining of large irregular surface components. Firstly, the Monte Carlo method and the minimum bounding sphere algorithm are used to generate an approximate robot workspace to judge whether all machining tasks are reachable. Then, a local minimum bounding box algorithm is used to generate a minimum bounding box of a tool handle and a minimum bounding box of a neighborhood workpiece point cloud to judge whether a tool collides with a workpiece. The feasibility of the machining task is efficiently judged, the calculation amount of robot machining planning of large irregular components is reduced, and the planning efficiency is improved.

[0022] In one embodiment of the present invention, establishing a robot kinematic model includes: The robot's terminal posture matrix and joint angles are obtained, and the robot's kinematic model is established based on the robot's terminal posture matrix and joint angles.

[0023] Specifically, the DH (Denavit-Hartenberg, characteristic parameter) method is used to establish the kinematic model of the robot: ,in, is the robot end posture matrix, ( ) is the robot joint angle.

[0024] Furthermore, the robot kinematic model is converted into a robot linkage model: ,in, is the robot posture matrix with end effector, is the preset matrix transformation relationship, that is, the transformation matrix from the robot end effector to the robot end. Figure 2 , Figure 2 A schematic diagram of a connecting rod model provided in one embodiment of the present invention.

[0025] In one embodiment of the present invention, generating an approximate workspace of a robot using a robot link model includes: Determine a robot joint angle combination, wherein the robot joint angle combination includes randomly generated joint angles; The robot joint angle combination is substituted into the robot linkage model to obtain randomly generated coordinates, and the coordinates are used to generate the robot's approximate workspace.

[0026] Among them, the robot's joint angle combination can be generated using the Monte Carlo method, specifically: ,in, is the randomly generated nth joint angle, is the minimum value of the i-th joint angle, is the maximum value of the i-th joint angle, is a random number between [0-1]. Then the randomly generated joint angle is brought into the robot link model to obtain the randomly generated coordinates: , by inputting the six joint angles of the nth point, we get the TCP end coordinates ( ) and the rotation angle relative to the base coordinate system ( ). For randomly generated coordinates, use the minimum bounding sphere algorithm to generate the robot's approximate operating space: ,in,( ) generates the minimum bounding sphere coordinates, is the radius of the minimum enclosing sphere, [ ] is a set of random coordinate points of the robot. In a specific embodiment, a total of 10,000 robot joint angle combinations are generated. The calculated coordinates of the sphere center are (-1.274 mm, -0.297 mm, 767.353 mm) and the radius is 3128.01 mm.

[0027] In one embodiment of the present invention, determining the reachability of a robot machining task in an approximate workspace includes; The distance from each robot processing task point to the preset enclosing sphere is calculated, and the reachability of the robot processing task is determined based on the distance.

[0028] Among them, the default bounding sphere is the minimum bounding sphere, such as Figure 3 As shown, Figure 3 This is a schematic diagram of determining the reachability of a processing task in one embodiment of the present invention. The distance from each processing task point to the center of the minimum enclosing sphere is: , is the distance from the i-th task point to the center of the minimum enclosing sphere, ( ) is the coordinate of the i-th task point.

[0029] Determine the reachability of robot processing tasks based on distance, including: Enter the distance into the preset reachability formula. If the formula result is greater than 0, the robot processing task can reach it. If the formula result is less than 0, the robot processing task cannot reach it.

[0030] Among them, the preset reachability formula is: , is a unit step function, which is 1 when it is greater than 0 and 0 when it is less than 0. It is the task reachability judgment. When it is 1, all tasks are reachable. When it is 0, the tasks are unreachable.

[0031] In one embodiment of the present invention, determining the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud during the machining process includes: Determine the first extreme value coordinates of the tool handle, and generate a minimum bounding box of the tool handle based on the first extreme value coordinates; The neighborhood workpiece point cloud is determined based on the tool center coordinates and the preset distance, the second extreme value coordinates of the domain workpiece point cloud are determined, and the minimum bounding box of the neighborhood workpiece point cloud is generated based on the second extreme value coordinates.

[0032] It is understandable that whether a robot processing task collides can be determined by generating the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud, wherein the formula of the minimum bounding box of the tool handle is: , ( ) is to determine the six coordinate extreme values ​​of the eight vertices of the minimum bounding box of the handle, ( ) is the input tool handle 3D point coordinate set.

[0033] like Figure 4 As shown, Figure 4 This is a schematic diagram of collision judgment in an embodiment of the present invention. Since the tool handle used is stepped, two minimum bounding boxes are generated.

[0034] The formula for extracting the tool neighborhood point cloud set is: ,in, is the workpiece coordinate point cloud set, ( ) is the tool center coordinate, is the distance threshold, is the extracted neighborhood workpiece point cloud set. Therefore, the minimum bounding box of the generated neighborhood point cloud is: , in,( ) is used to determine the coordinate extreme values ​​of the eight vertices of the minimum bounding box of the neighborhood workpiece point cloud.

[0035] In one embodiment of the present invention, the collision of the robot machining task is determined based on the projection of the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud on the coordinate axis, including: Determine the mark position where the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud overlap on the coordinate axis; If the flag value is 1, the robot processing task will collide; if the flag value is 0, the robot processing task will not collide.

[0036] Determine whether the projections of the tool handle and the minimum bounding box of the neighboring workpiece point cloud on the coordinate axis overlap: , [ ] is a flag to determine whether the projection of the minimum bounding box on the coordinate axis overlaps. When the value is 1, it means there is overlap, and when the value is 0, there is no overlap. Finally, based on the overlap of the projection of the minimum bounding box on the coordinate axis, determine whether a collision will occur: , It is the collision judgment flag. When the value is 1, it means a collision will occur. When the value is 0, no collision will occur.

[0037] Finally, the feasibility of the robot processing task of large non-regular components is judged, where the feasibility of the processing task is judged as follows: .in, It is the flag bit for judging the feasibility of the processing task. When the value is 1, it means that the processing task is feasible, and when the value is 0, it means that the processing task is not feasible.

[0038] Compared with the prior art, the present invention proposes a method for judging the feasibility of robot processing of large irregular surface components. First, the Monte Carlo method and the minimum bounding sphere algorithm are used to generate an approximate robot workspace to determine whether all processing tasks are reachable. Then, the local minimum bounding box algorithm is used to generate the minimum bounding box of the tool handle and the minimum bounding box of the neighborhood workpiece point cloud to determine whether the tool collides with the workpiece. The feasibility of the processing task is efficiently judged, the calculation amount of robot processing planning of large irregular components is reduced, and the planning efficiency is improved.

[0039] In order to better implement the robot processing feasibility judgment method in the embodiment of the present invention, based on the robot processing feasibility judgment method, correspondingly, Figure 5 As shown, the embodiment of the present invention further provides a robot processing feasibility judgment device, and the robot processing feasibility judgment device 500 includes: A model building module 501 is used to build a robot kinematics model and convert the robot kinematics model into a robot link model using a preset matrix conversion relationship; A reachability determination module 502, for generating an approximate workspace of the robot using a robot link model, and determining the reachability of the robot processing task in the approximate workspace; A collision determination module 503 is used to determine the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud during the machining process, and determine the collision of the robot machining task based on the projection of the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud on the coordinate axis; The feasibility determination module 504 is used to determine the feasibility of the robot processing task according to the reachability and collision of the robot processing task.

[0040] The robot processing feasibility judgment device 500 provided in the above embodiment can implement the technical solution described in the above robot processing feasibility judgment method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above robot processing feasibility judgment method embodiment, which will not be repeated here.

[0041] The above are only preferred specific implementations of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for determining the feasibility of a robot processing task, characterized in that: include: Establishing a robot kinematics model, and converting the robot kinematics model into a robot link model using a preset matrix conversion relationship; Generate an approximate workspace of the robot using the robot linkage model, and determine the reachability of the robot processing task in the approximate workspace; During the machining process, the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud are determined, and the collision of the robot machining task is determined based on the projection of the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud on the coordinate axis; The feasibility of the robot processing task is determined based on the reachability and collision of the robot processing task.

2. The method for determining the feasibility of a robot processing task according to claim 1, characterized in that: The establishing of the robot kinematic model comprises: The robot's terminal posture matrix and joint angles are obtained, and the robot's kinematic model is established based on the robot's terminal posture matrix and joint angles.

3. The method for determining the feasibility of a robot processing task according to claim 1, characterized in that: The method of generating an approximate robot workspace by using the robot link model comprises: Determining a robot joint angle combination, wherein the robot joint angle combination includes randomly generated joint angles; The robot joint angle combination is substituted into the robot link model to obtain randomly generated coordinates, and the robot approximate workspace is generated using the coordinates.

4. The method for determining the feasibility of a robot processing task according to claim 1, characterized in that: Determining the reachability of the robot processing task in the approximate workspace includes: The distance from each robot processing task point to a preset bounding sphere is calculated, and the reachability of the robot processing task is determined based on the distance.

5. The method for determining the feasibility of a robot processing task according to claim 4, characterized in that: Determining the reachability of the robot processing task based on the distance includes: The distance is input into a preset reachability formula. If the formula result is greater than 0, the robot processing task can be reached. If the formula result is less than 0, the robot processing task cannot be reached.

6. The method for determining the feasibility of a robot processing task according to claim 1, characterized in that: Determining the minimum bounding box of the tool and the minimum bounding box of the neighboring workpiece point cloud during the machining process includes: Determine a first extreme value coordinate of the tool handle, and generate a minimum bounding box of the tool handle based on the first extreme value coordinate; A neighborhood workpiece point cloud is determined based on the tool center coordinates and a preset distance, a second extreme value coordinate of the neighborhood workpiece point cloud is determined, and a minimum bounding box of the neighborhood workpiece point cloud is generated based on the second extreme value coordinates.

7. The method for determining the feasibility of a robot processing task according to claim 6, characterized in that: The method of determining the collision of the robot machining task based on the projection of the tool handle minimum bounding box and the neighboring workpiece point cloud minimum bounding box on the coordinate axis includes: Determine the mark position where the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud overlap on the coordinate axis; If the value of the flag bit is 1, the robot processing task will collide, and if the value of the flag bit is 0, the robot processing task will not collide.

8. A device for determining the feasibility of a robot processing task, characterized in that: include: A model building module, used to build a robot kinematic model and convert the robot kinematic model into a robot connecting rod model using a preset matrix conversion relationship; a reachability determination module, configured to generate an approximate workspace of the robot using the robot link model, and determine the reachability of the robot processing task in the approximate workspace; A collision determination module is used to determine the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud during the machining process, and determine the collision of the robot machining task based on the projection of the minimum bounding box of the tool handle and the minimum bounding box of the neighboring workpiece point cloud on the coordinate axis; The feasibility determination module is used to determine the feasibility of the robot processing task according to the reachability and collision of the robot processing task.

Images