A mechanical arm control method for motor production

Abstract

The present application relates to the field of automation production, and more particularly to a mechanical arm control method for motor production, the present application obtains point cloud data of motor accessories conveyed by a conveying belt through a data acquisition unit, determines the category of the motor accessories, and subsequently performs grabbing interference analysis and constructs a grabbing stress observation body to construct a plurality of profile surface observation groups based on the grabbing stress observation body, determines the curvature features and symmetric distribution difference features in each profile surface observation group, determines the grabbing influence category of the motor accessories, and finally controls the carrying mechanical arm to grab the motor accessories based on the adaptability of the grabbing influence category. The present application realizes the control of the mechanical arm based on the specific adaptability of the motor accessories, adjusts the grabbing strategy, improves the grabbing success rate, improves the processing capacity for different forms of materials, ensures the grabbing speed, improves the grabbing reliability, and optimizes the reliability of the system under complex working conditions.

Description

Technical Field

[0001] This invention relates to the field of automated production, and more particularly to a robotic arm control method for motor production. Background Technology

[0002] In the field of automated production, the use of robotic arms to grasp parts is a key step. By working together with robotic arms, end effectors, and sensing systems, materials can be identified, located, grasped, and placed. For example, in the field of motor manufacturing, to achieve efficient production, robotic arms can grasp motor parts to enable subsequent handling, assembly, and other actions. Automated robotic arms can improve motor production efficiency. Based on this, control systems for robotic arms have become increasingly important.

[0003] For example, Chinese Patent Publication No. CN117958979A discloses a control method, device, and robotic arm for a robotic arm. The method includes: monitoring a first state of the robotic arm at a first moment based on the position sensor and the torque sensor; acquiring a second state of the robotic arm at a second moment, where the second moment is the previous moment of the first moment; and adjusting the joint parameters of the robotic arm if the first state differs from the second state. Using this method, the motion and force state of the robotic arm can be automatically monitored, and when a change in the state of the robotic arm is detected, the relevant joint parameters can be adjusted in a timely manner, thereby achieving automatic control of the robotic arm.

[0004] However, the following problems still exist in the existing technology:

[0005] 1. Existing technologies do not adequately consider the gripping requirements of irregularly shaped materials. This leads to problems such as unstable gripping, material slippage, or surface damage when the robotic arm grasps materials of various shapes. The system has poor adaptability to different materials, affecting gripping efficiency and success rate.

[0006] 2. In the existing technology, the optimization of the grasping process based on the shape characteristics is not considered, which makes it impossible for the system to adaptively adjust the grasping strategy of the robotic arm according to the actual three-dimensional model of the material. It is difficult to achieve dynamic trade-off and optimal selection between operating speed and success rate, resulting in the system being unable to maintain high operating efficiency while ensuring grasping success rate when dealing with materials of different shapes. Summary of the Invention

[0007] Therefore, the present invention provides a robotic arm control method for motor production, which overcomes the problems in the prior art that the grasping requirements of irregularly shaped materials are not fully considered and the robotic arm grasping process is not optimized based on morphological characteristics, resulting in low success rate and low efficiency when grasping materials of different shapes.

[0008] To achieve the above objectives, the present invention provides a robotic arm control method for motor production, comprising:

[0009] The point cloud data of the motor components conveyed by the conveyor belt is acquired through the data acquisition unit;

[0010] A 3D model is constructed based on point cloud data, and grasping interference analysis is performed. This includes constructing a grasping force observation body within the 3D model, constructing several contour surface observation groups based on the grasping force observation body, and determining the curvature characteristics and symmetry distribution difference characteristics within each contour surface observation group.

[0011] The grasping influence characterization value is calculated based on the curvature characteristics and symmetric distribution difference characteristics of each contour surface observation group, and the grasping influence category of the motor accessory is determined based on the optimal grasping influence characterization value.

[0012] The robotic arm for grasping motor parts is controlled based on the influence category of the grasping effect, including:

[0013] Based on the optimal grasping influence characterization value, the optimal contour surface observation group is determined to determine the grasping coordinates, the grasping parameters of the handling robot arm are adjusted, and the handling robot arm is controlled to grasp the motor parts to the corresponding category of grasping bin at the corresponding grasping coordinates.

[0014] Alternatively, determine the shortest movement path between the handling robotic arm and the motor component, and control the handling robotic arm to grab the motor component to the corresponding category of gripping bin.

[0015] Furthermore, the process of constructing a grasping force observation body within the 3D model, and constructing several contour surface observation groups within the grasping force observation body, includes:

[0016] Determine the geometric center of the three-dimensional model, construct a cylinder through the geometric center, and define the cylinder as the force observation body;

[0017] Identify the two contour surfaces that the two ends of the force-observed object penetrate through the three-dimensional model, and define the two contour surfaces as the contour surface observation group;

[0018] The object under force is rotated in all directions with the geometric center as a reference to construct several contour surface observation groups.

[0019] Furthermore, based on the observation groups of each contour surface, the curvature characteristics within each group and the differences in symmetry distribution were determined, including:

[0020] Calculate the total average curvature of the contour surfaces within each contour surface observation group as the curvature feature within the corresponding contour surface observation group; calculate the shape difference between two contour surfaces within the contour surface observation group as the symmetry distribution difference feature of the corresponding contour surface observation group.

[0021] Furthermore, the process of calculating the impact representation value includes,

[0022] The ratio of the curvature feature within the group to the preset curvature threshold is calculated to obtain the first grasping influence parameter;

[0023] The ratio of the symmetrical distribution difference feature to the preset symmetrical distribution difference feature threshold is calculated to obtain the second grasping influence parameter;

[0024] The weighted sum of the curvature features within the group and the symmetric distribution difference features yields the capture influence characterization value.

[0025] Furthermore, the process of determining the gripping influence category of the motor component based on the optimal gripping influence characterization value includes,

[0026] Determine the grasping influence characterization value for each contour surface observation group, and then select the optimal grasping influence characterization value with the smallest grasping influence characterization value;

[0027] If the optimal grasping impact value is less than the preset impact threshold, the corresponding motor part will be identified as an easy-to-grab type.

[0028] If the optimal grasping impact value is greater than or equal to the preset impact threshold, the corresponding motor component will be classified as a difficult-to-grasp type.

[0029] Furthermore, the robotic arm is controlled to grasp motor parts based on the grasping influence category, including:

[0030] If the motor parts are difficult to grasp, then the optimal contour surface observation group is determined based on the optimal grasping influence characterization value, so as to determine the grasping coordinates, adjust the grasping parameters of the handling robot arm, and control the handling robot arm to grasp the motor parts to the corresponding category of grasping bin at the corresponding grasping coordinates.

[0031] If the motor parts are easy to grasp, then determine the shortest movement path between the handling robot arm and the motor parts, and control the handling robot arm to grasp the motor parts to the corresponding grasping bin at the corresponding grasping coordinates.

[0032] Furthermore, the center coordinates corresponding to the contour surfaces in the optimal contour surface observation group are determined as the grab coordinates.

[0033] Furthermore, adjusting the gripping parameters of the handling robot arm includes: determining a speed adjustment coefficient based on the ratio of the optimal gripping influence characterization value to a preset influence threshold; and adjusting the basic operating speed of the handling robot arm according to the speed adjustment coefficient.

[0034] Furthermore, it also includes identifying the gripping bins corresponding to the motor components, wherein,

[0035] Collect and identify the feature codes on motor parts; determine the target gripping bin corresponding to the motor parts based on the feature codes and mapping rules;

[0036] The mapping rule is a pre-determined mapping relationship between feature codes and target capture binaries.

[0037] Furthermore, it also includes establishing an association between the point cloud data of the motor components and the feature code, and then storing it in a database.

[0038] Compared with existing technologies, this invention acquires point cloud data of motor components conveyed by a conveyor belt through a data acquisition unit, determines the category of the motor components, performs grasping interference analysis, constructs a grasping force observation body, and builds several contour surface observation groups based on the grasping force observation body. Based on each contour surface observation group, the curvature characteristics and symmetry distribution differences within the group are determined to identify the grasping influence category of the motor components. Finally, a control robot arm adaptively controls the grasping of the motor components based on the grasping influence category. This invention realizes a control robot arm based on the specific adaptability of motor components, adjusting the grasping strategy, improving the grasping success rate, enhancing the handling capacity for materials of different shapes, ensuring grasping speed, improving grasping reliability, and optimizing the system reliability under complex working conditions.

[0039] In particular, this invention considers the calculation of the grasping influence characterization value. By establishing a multi-dimensional evaluation system based on intra-group curvature characteristics and symmetrical distribution difference characteristics, the system can quantify the grasping difficulty and stability of grasping motor parts. In practice, the shape of an object affects the force applied by the handling robot arm during grasping, leading to detachment or unstable grasping. Intra-group curvature characteristics reflect the overall protrusion of the contour surface, while symmetrical distribution difference characteristics reflect the morphological differences of the contour surface. The grasping influence characterization value calculated based on intra-group curvature characteristics and symmetrical distribution difference characteristics is the core basis for subsequent grasping planning decisions, providing a scientific foundation for grasping strategy formulation. In practical applications, the system can select the optimal grasping scheme based on quantitative data rather than empirical judgment, thereby improving the accuracy and reliability of decision-making.

[0040] In particular, this invention calculates the grasping influence characterization value of each contour surface observation group through a weighted fusion algorithm, and classifies the grasping influence category of motor parts according to the optimal grasping influence characterization value, so as to characterize the influence of shape on grasping motor parts. For the difficult-to-grasp category, it indicates that the shape of the motor parts has a greater influence on grasping, and it is easy to fall off or be unstable. For the easy-to-grasp category, it indicates that the shape of the motor parts has a smaller influence on grasping, and the grasping is relatively stable, thereby improving the system's ability to handle irregularly shaped materials and achieving an optimized balance between grasping speed and success rate.

[0041] In particular, for difficult-to-grip motor parts, this invention appropriately adjusts the gripping parameters of the robotic arm and determines the gripping coordinates. A speed adjustment coefficient is calculated based on the ratio of the optimal gripping influence characteristic value to a preset influence threshold, and the robotic arm's operating speed is dynamically reduced according to this coefficient. This speed adjustment mechanism ensures the stability of difficult-to-grip objects during the gripping process and avoids unnecessary efficiency losses through precise speed control. In practical applications, it significantly improves the success rate of gripping irregularly shaped, fragile, and special materials, while maintaining the overall operational efficiency of the system. Attached Figure Description

[0042] Figure 1 A schematic diagram illustrating the steps of a robotic arm control method for motor production according to an embodiment of the invention;

[0043] Figure 2 A logic block diagram for determining the grasping influence category of motor accessories in an embodiment of the invention;

[0044] Figure 3 This is a logic block diagram of a robotic arm for grasping motor parts based on the grasping influence category control, as an embodiment of the invention.

[0045] Figure 4 This is a logic block diagram for screening the kinematic feasibility of candidate motion paths according to an embodiment of the invention. Detailed Implementation

[0046] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0047] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0048] It should be noted that in the description of this invention, terms such as "one side" and "both sides" indicate the direction or positional relationship based on the direction or positional relationship shown in the drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0049] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0050] Please see Figure 1 As shown, Figure 1 This is a schematic diagram illustrating the steps of a robotic arm control method for motor production according to an embodiment of the invention. The robotic arm control method for motor production according to an embodiment of the invention includes:

[0051] Step S1: Obtain point cloud data of the motor components conveyed by the conveyor belt through the data acquisition unit;

[0052] Step S2: Construct a three-dimensional model based on point cloud data and perform grasping interference analysis, including: constructing a grasping force observation body in the three-dimensional model, constructing several contour surface observation groups based on the grasping force observation body, and determining the curvature characteristics and symmetry distribution difference characteristics within each contour surface observation group.

[0053] Step S3: Calculate the grasping influence characterization value based on the curvature characteristics and symmetry distribution difference characteristics of each contour surface observation group, and determine the grasping influence category of the motor accessory based on the optimal grasping influence characterization value;

[0054] Step S4: Based on the grasping influence category of the motor parts, control the handling robot arm to grasp the motor parts, including,

[0055] Based on the optimal grasping influence characterization value, the optimal contour surface observation group is determined to determine the grasping coordinates, the grasping parameters of the handling robot arm are adjusted, and the handling robot arm is controlled to grasp the motor parts to the corresponding category of grasping bin at the corresponding grasping coordinates.

[0056] Alternatively, determine the shortest movement path between the handling robotic arm and the motor component, and control the handling robotic arm to grab the motor component to the corresponding category of gripping bin.

[0057] Specifically, the data acquisition unit can be a depth photography device or a laser scanning device, as long as it can acquire point cloud data of the motor components.

[0058] Specifically, this also includes identifying the corresponding gripping bins for motor components, among which...

[0059] Collect and identify the feature codes on motor parts; determine the target gripping bin corresponding to the motor parts based on the feature codes and mapping rules;

[0060] The mapping rule is a pre-determined mapping relationship between feature codes and target capture binaries.

[0061] Specifically, there is no limitation on the form of the handling robot arm. It can be a multi-degree-of-freedom robot arm with a gripper at the end. Those skilled in the art can select the degree of freedom of the robot arm according to the actual use environment, which will not be elaborated here.

[0062] Specifically, the feature code is a barcode or QR code affixed to or printed on the outer surface of the motor accessory. The acquired image is processed to extract the goods information contained in the barcode or QR code. Based on the extracted information, a pre-stored mapping rule database is queried to determine the target grabbing bin corresponding to the motor accessory.

[0063] Specifically, the process of constructing a grasping force observation body within a 3D model, and constructing several contour surface observation groups within the grasping force observation body, includes:

[0064] Determine the geometric center of the three-dimensional model, construct a cylinder through the geometric center, and define the cylinder as the force observation body;

[0065] Identify the two contour surfaces that the two ends of the force-observed object penetrate through the three-dimensional model, and define the two contour surfaces as the contour surface observation group;

[0066] The object under force is rotated in all directions with the geometric center as a reference to construct several contour surface observation groups.

[0067] It is understandable that the object under force will penetrate different positions of the 3D model during rotation, thus obtaining several contour surface observation groups.

[0068] Specifically, based on the observation groups of each contour surface, the curvature characteristics within each group and the differences in symmetry distribution are determined, including:

[0069] Calculate the total average curvature of the contour surfaces within each contour surface observation group as the curvature feature within the corresponding contour surface observation group; calculate the shape difference between two contour surfaces within the contour surface observation group as the symmetry distribution difference feature of the corresponding contour surface observation group.

[0070] Specifically, there is no limitation on the method for determining the shape difference between contour surfaces. In practice, the difference ratio can be determined as the shape difference by calculating the difference ratio of the average curvature of the two contour surfaces.

[0071] The overall average curvature is the mean of the average curvatures of the two contour surfaces. This invention considers the calculation of the grasping influence characterization value. By establishing a multi-dimensional evaluation system based on intra-group curvature characteristics and symmetrical distribution difference characteristics, the system can quantify the grasping difficulty and stability of grasping motor parts. In practice, the shape of an object affects the force applied by the handling robot arm during grasping, leading to detachment or unstable grasping. Intra-group curvature characteristics reflect the overall protrusion of the contour surfaces, while symmetrical distribution difference characteristics reflect the morphological differences of the contour surfaces. The grasping influence characterization value calculated based on intra-group curvature characteristics and symmetrical distribution difference characteristics is the core basis for subsequent grasping planning decisions, providing a scientific basis for grasping strategy formulation. In practical applications, the system can select the optimal grasping scheme based on quantitative data rather than empirical judgment, thereby improving the accuracy and reliability of decision-making.

[0072] Specifically, the process of calculating the impact representation value includes,

[0073] The ratio of the curvature feature within the group to the preset curvature threshold is calculated to obtain the first grasping influence parameter;

[0074] The ratio of the symmetrical distribution difference feature to the preset symmetrical distribution difference feature threshold is calculated to obtain the second grasping influence parameter;

[0075] The weighted sum of the curvature features within the group and the symmetric distribution difference features yields the capture influence characterization value.

[0076] In practice, the preset curvature threshold is predetermined. The total average curvature of several types of motor parts is collected in advance, the mean of the total average curvature is calculated, and the preset curvature threshold is set as the product of the mean of the average curvature and the error coefficient. The error coefficient is selected in the interval [1.2, 1.5].

[0077] The preset threshold for symmetrical distribution difference features is pre-set. Since the essence of symmetrical distribution difference features is the difference ratio, in order to characterize the case where the difference between two contour surfaces is large, the threshold for symmetrical distribution difference features should be greater than 0.3. In practice, it is preferred to be 0.4.

[0078] To comprehensively consider the influence parameters of the first and second crawling processes, the weights for both parameters are 0.5 when performing a weighted summation.

[0079] Please see Figure 2 As shown, Figure 2 The present invention provides a logic block diagram for determining the gripping influence category of a motor component according to an embodiment of the invention. The process of determining the gripping influence category of the motor component based on the optimal gripping influence characterization value includes,

[0080] Determine the grasping influence characterization value for each contour surface observation group, and then select the optimal grasping influence characterization value with the smallest grasping influence characterization value;

[0081] If the optimal grasping impact value is less than the preset impact threshold, the corresponding motor part will be identified as an easy-to-grab type.

[0082] If the optimal grasping impact value is greater than or equal to the preset impact threshold, the corresponding motor component will be classified as a difficult-to-grasp type.

[0083] Specifically, the preset influence threshold can be determined through simulation testing based on a mechanical model. The simulation software simulates the gripping process of numerous motor components under different gripping influence values. Whether the clamping force meets the static equilibrium condition and whether the material slips or rotates are used as criteria for successful gripping to determine the magnitude of the influence threshold. For example, the average value of the gripping influence values ​​under conditions of material slippage or rotation can be used as the influence threshold.

[0084] Specifically, please refer to Figure 3 As shown, Figure 3 This is a logic block diagram illustrating the control of a robotic arm for grasping motor parts based on the grasping influence category, according to an embodiment of the invention. The control of the robotic arm for grasping motor parts based on the grasping influence category includes:

[0085] If the motor parts are difficult to grasp, then the optimal contour surface observation group is determined based on the optimal grasping influence characterization value, so as to determine the grasping coordinates, adjust the grasping parameters of the handling robot arm, and control the handling robot arm to grasp the motor parts to the corresponding category of grasping bin at the corresponding grasping coordinates.

[0086] If the motor parts are easy to grasp, then determine the shortest movement path between the handling robot arm and the motor parts, and control the handling robot arm to grasp the motor parts to the corresponding grasping bin at the corresponding grasping coordinates.

[0087] This invention calculates the grasping influence characterization value of each contour surface observation group using a weighted fusion algorithm, and classifies the grasping influence category of motor parts according to the optimal grasping influence characterization value. This characterizes the influence of shape on grasping motor parts. For difficult-to-grasp categories, the shape of the motor parts has a greater influence on grasping, making them prone to falling off or becoming unstable. For easy-to-grasp categories, the shape of the motor parts has a smaller influence on grasping, resulting in relatively stable grasping. This improves the system's ability to handle irregularly shaped materials and achieves an optimized balance between grasping speed and success rate.

[0088] Specifically, the center coordinates corresponding to the contour surfaces in the optimal contour surface observation group are determined as the grab coordinates.

[0089] It is understandable that the two ends of the object being observed pass through the two contour surfaces penetrated by the three-dimensional model. Therefore, the center coordinates of the two contour surfaces can be selected as the gripping coordinates so that the clamp can move to the corresponding gripping coordinates.

[0090] In practice, a symmetrical fixture can be selected, which provides clamping force through the relative movement of symmetrically distributed grippers. The grippers correspond to the clamping coordinates. In reality, there may be insufficient control precision, and a certain deviation between the gripping coordinates and the gripper coordinates is allowed. This will not be elaborated further.

[0091] Specifically, adjusting the gripping parameters of the handling robot arm includes: determining a speed adjustment coefficient based on the ratio of the influence threshold to the optimal gripping influence characterization value; and adjusting the basic operating speed of the handling robot arm according to the speed adjustment coefficient.

[0092] In practice, the product of the base operating speed and the speed adjustment coefficient is determined as the adjusted operating speed.

[0093] Since the optimal grasping influence value is greater than the influence threshold in the case of difficult-to-grasp classes, the speed adjustment coefficient is less than 1. Based on this, the basic operating speed of the handling robot is adaptively reduced.

[0094] The basic transport speed of the robotic arm is the moving speed of the robotic arm after it has grasped the material to be grasped.

[0095] For difficult-to-grip motor parts, this invention addresses the challenge of gripping them by appropriately adjusting the gripping parameters of the robotic arm and determining the gripping coordinates. A speed adjustment coefficient is calculated based on the ratio of the optimal gripping influence value to a preset influence threshold, and this coefficient is used to dynamically reduce the robotic arm's operating speed. This speed adjustment mechanism ensures the stability of the gripped object during the gripping process while avoiding unnecessary efficiency losses through precise speed control. In practical applications, it significantly improves the success rate of gripping irregularly shaped, fragile, and special materials, while maintaining the overall operational efficiency of the system.

[0096] Specifically, the determination of the shortest movement path adopts a multi-path selection-based planning strategy. The path planner for the handling robot arm generates several candidate paths that can move to the corresponding grasping coordinates based on the grasping coordinates. Then, kinematic feasibility screening is performed on each candidate path, including joint angle limitation detection and collision interference detection.

[0097] Please see Figure 4 As shown, Figure 4 This is a logic block diagram for screening the kinematic feasibility of candidate motion paths according to an embodiment of the invention. If a candidate path meets the motion constraint conditions, it is included in the set of feasible paths.

[0098] If a candidate path does not meet the motion constraints, it will be eliminated.

[0099] Select the shortest path from the set of feasible paths as the shortest movement path.

[0100] Specifically, the motion constraints include joint angles not exceeding limits and no collision interference.

[0101] Joint angle constraints are determined based on the robot arm's degrees of freedom and joint structure. Each joint angle must be less than the corresponding joint angle constraint. Collision interference detection is performed based on the environment set up by the robot arm to determine the coordinates of obstacles in the environment. If the candidate path does not interfere with the coordinates of obstacles, there is no risk of collision.

[0102] Specifically, it also includes establishing an association between the point cloud data of the motor components and the feature code, and then storing it in a database.

[0103] By establishing a correlation between the feature code and the point cloud data, it is possible to directly obtain the point cloud data of the corresponding motor parts through the feature code. In some cases, it can be used for defect detection, which will not be elaborated further.

[0104] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A robot control method for motor production, characterized by, include: The point cloud data of the motor components conveyed by the conveyor belt is acquired through the data acquisition unit; A 3D model is constructed based on point cloud data, and grasping interference analysis is performed. This includes constructing a grasping force observation body within a 3D model, constructing several contour surface observation groups based on the grasping force observation body, and determining the curvature characteristics and symmetry distribution difference characteristics within each contour surface observation group. The grasping influence characterization value is calculated based on the curvature characteristics and symmetric distribution difference characteristics of each contour surface observation group, and the grasping influence category of the motor accessory is determined based on the optimal grasping influence characterization value. The robotic arm for grasping motor parts is controlled based on the influence category of the grasping effect, including: Based on the optimal grasping influence characterization value, the optimal contour surface observation group is determined to determine the grasping coordinates, the grasping parameters of the handling robot arm are adjusted, and the handling robot arm is controlled to grasp the motor parts to the corresponding category of grasping bin at the corresponding grasping coordinates. Alternatively, determine the shortest movement path between the handling robotic arm and the motor component, and control the handling robotic arm to grab the motor component to the corresponding category of gripping bin; The process of constructing a grasping force observation body within a 3D model, and constructing several contour surface observation groups within the grasping force observation body, includes: Determine the geometric center of the three-dimensional model, construct a cylinder through the geometric center, and define the cylinder as the force observation body; Identify the two contour surfaces that the two ends of the force-observed object penetrate through the three-dimensional model, and define the two contour surfaces as the contour surface observation group; Among them, the force-observed body is rotated in each direction with the geometric center as a reference to construct several contour surface observation groups; Based on the observation groups of each contour surface, the curvature characteristics within each group and the differences in symmetry distribution were determined, including: Calculate the total average curvature of the contour surfaces within each contour surface observation group, and use it as the in-group curvature feature of the corresponding contour surface observation group. Calculate the shape difference between two contour surfaces within the contour surface observation group, which serves as the symmetrical distribution difference feature of the corresponding contour surface observation group.

2. The robot control method for motor production according to claim 1, wherein The process of calculating the impact representation value includes, The ratio of the curvature feature within the group to the preset curvature threshold is calculated to obtain the first grasping influence parameter; The ratio of the symmetrical distribution difference feature to the preset symmetrical distribution difference feature threshold is calculated to obtain the second grasping influence parameter; The weighted sum of the curvature features within the group and the symmetric distribution difference features yields the capture influence characterization value.

3. The method of claim 1, wherein, The process of determining the gripping influence category of the motor component based on the optimal gripping influence characterization value includes, Determine the grasping influence characterization value for each contour surface observation group, and then select the optimal grasping influence characterization value with the smallest grasping influence characterization value; If the optimal grasping impact value is less than the preset impact threshold, the corresponding motor part will be identified as an easy-to-grab type. If the optimal grasping impact value is greater than or equal to the preset impact threshold, the corresponding motor component will be classified as a difficult-to-grasp type.

4. The method of claim 1, wherein, The robotic arm for grasping motor parts is controlled based on the influence category of the grasping effect, including: If the motor parts are difficult to grasp, then the optimal contour surface observation group is determined based on the optimal grasping influence characterization value, so as to determine the grasping coordinates, adjust the grasping parameters of the handling robot arm, and control the handling robot arm to grasp the motor parts to the corresponding category of grasping bin at the corresponding grasping coordinates. If the motor parts are easy to grasp, then determine the shortest movement path between the handling robot arm and the motor parts, and control the handling robot arm to grasp the motor parts to the corresponding grasping bin at the corresponding grasping coordinates.

5. The robot control method for motor production according to claim 1, wherein The center coordinates corresponding to the contour surfaces in the optimal contour surface observation group are determined as the grab coordinates.

6. The robotic arm control method for motor production according to claim 5, characterized in that, Adjust the gripping parameters of the robotic arm, including: The speed adjustment coefficient is determined based on the ratio of the influence threshold to the optimal capture influence representation value; The basic operating speed of the handling robot arm is adjusted according to the speed adjustment coefficient.

7. The robot control method for motor production according to claim 1, wherein This also includes identifying the gripping bins corresponding to the motor components, among which, Collect and identify the feature codes on motor parts; Based on the feature code and mapping rules, the target gripping bin corresponding to the motor parts is determined; The mapping rule is a pre-determined mapping relationship between feature codes and target capture binaries.

8. The robot control method for motor production of claim 1, wherein, It also includes establishing an association between the point cloud data of the motor components and the feature code, and then storing it in a database.

Images