Working parameter automatic deployment method and device of industrial robot and industrial robot

Abstract

The invention relates to an industrial robot technology, and discloses an automatic deployment method and device for working parameters of an industrial robot and the industrial robot. Analyzing the surrounding environment image based on a visual detection technology to obtain a relative position relation between the industrial robot and the surrounding environment object; according to the relative position relation, the movement range of the mechanical arm is limited in a kinematics model of the mechanical arm of the industrial robot; generating an acquisition target of the image sensor; generating operation flow data of the operation component; generating operation attitude data, matched with the operation process data, of the mechanical arm; and according to the operation process data, the operation attitude data and the collection target, deploying working parameters of the industrial robot for operation of each workpiece conveyed to a preset area by a workpiece assembly line. The invention further discloses a computer readable storage medium. The invention aims to improve the deployment efficiency, precision and flexibility of the industrial robot.

Description

Technical Field

[0001] The present application relates to the technical field of industrial robots, and in particular to an automatic deployment method for working parameters of an industrial robot, a control device, an industrial robot, and a computer-readable storage medium. Background Art

[0002] In today's highly automated and intelligent industrial production field, industrial robots have become a key tool for many companies to improve production efficiency, ensure product quality and reduce labor costs due to their high efficiency, precision and stability. Industrial robots are widely used in many industries such as automobile manufacturing, electronic assembly, food processing, etc., and can complete complex and diverse tasks such as welding, handling, assembly, spraying, etc., which greatly promotes the development of industrial production towards intelligence and automation.

[0003] At present, the deployment of working parameters of industrial robots mainly relies on manual settings. Technicians need to input and adjust various working parameters one by one in the control system of industrial robots based on the specific application scenarios, working tasks and surrounding environment of industrial robots, combined with their own professional knowledge and experience.

[0004] Manually setting working parameters is a tedious and time-consuming process. Technicians need to spend a lot of time on-site measurement, data calculation and parameter debugging. Especially when faced with complex operating tasks and changing surrounding environments, the difficulty and workload of parameter setting will increase significantly.

[0005] And with the continuous expansion of industrial production scale and the continuous improvement of automation, enterprises often need to use multiple industrial robots to work together at the same time. In this case, manually setting parameters for each robot is not only a huge workload, but also prone to parameter inconsistency problems, affecting the collaborative work efficiency of the entire production line.

[0006] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0007] The main purpose of this application is to provide an automatic deployment method for the working parameters of an industrial robot, a control device, an industrial robot and a computer-readable storage medium, aiming to improve the deployment efficiency, accuracy and flexibility of the industrial robot.

[0008] To achieve the above objectives, the present application provides a method for automatically deploying working parameters of an industrial robot, comprising the following steps: When the industrial robot receives the deployment instruction, it obtains the image of the surrounding environment based on the image sensor; Analyze the surrounding environment image based on visual detection technology to obtain the relative position relationship between the industrial robot and the surrounding environment objects; wherein the surrounding environment objects at least include the workpiece assembly line; According to the relative position relationship, the range of motion of the robot arm is limited in a kinematic model of the robot arm of the industrial robot; wherein the kinematic model is pre-constructed based on the structure of the robot arm and the kinematic principle; Read the workpiece image, the preset area of ​​the workpiece assembly line, the type of workpiece at the end of the robot arm, and the type of work task; Generate an acquisition target of the image sensor according to the workpiece image and the preset area; and generate operation process data of the operation component according to the workpiece image, the type of the operation component and the type of the operation task; and generate operation posture data of the robot arm adapted to the operation process data based on the defined kinematic model; According to the operation process data, the operation posture data and the acquisition target, the industrial robot is deployed to perform operation parameters on each workpiece transmitted by the workpiece assembly line to a preset area.

[0009] To achieve the above object, the present application also provides a control device, comprising: The acquisition module is used to obtain the surrounding environment image based on the image sensor when the industrial robot receives the deployment instruction; An analysis module, used to analyze the surrounding environment image based on visual detection technology to obtain the relative position relationship between the industrial robot and the surrounding environment objects; wherein the surrounding environment objects at least include a workpiece assembly line; A constraint module, used for limiting the range of motion of the mechanical arm in a kinematic model of the mechanical arm of the industrial robot according to the relative position relationship; wherein the kinematic model is pre-constructed based on the structure of the mechanical arm and the kinematic principle; A reading module is used to read the workpiece image, the preset area of ​​the workpiece assembly line, the type of the working part at the end of the robot arm, and the type of the working task; A generation module is used to generate a collection target of an image sensor according to a workpiece image and a preset area; and to generate operation process data of an operation component according to the workpiece image, the type of the operation component and the type of the operation task; and to generate operation posture data of a robot arm adapted to the operation process data based on the defined kinematic model; A deployment module is used to deploy the working parameters of the industrial robot to perform operations on each workpiece transmitted to a preset area by the workpiece assembly line according to the work process data, the work posture data and the collection target.

[0010] To achieve the above-mentioned objectives, the present application also provides an industrial robot, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method for automatically deploying working parameters of the industrial robot as described above.

[0011] To achieve the above objectives, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for automatically deploying working parameters of an industrial robot are implemented.

[0012] The automatic deployment method, control device, industrial robot and computer-readable storage medium of the working parameters of the industrial robot provided by the present application can obtain the surrounding environment information and workpiece information of the industrial robot in real time by using image sensors and visual detection technology, and automatically generate and deploy working parameters based on this information, effectively overcoming the shortcomings of the prior art, improving the deployment efficiency, accuracy and flexibility of the industrial robot, realizing the automation of the whole process from environmental perception to parameter deployment, and automatically completing the deployment of working parameters for the industrial robot to transmit the workpiece assembly line to each workpiece in the preset area for operation. The whole process does not require manual intervention in the setting of various complex parameters, which not only reduces labor costs, but also avoids the errors that may be caused by human operation, ensures that the industrial robot always operates in the best state, improves production efficiency and product quality, and enhances the stability and reliability of industrial production. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a schematic diagram of the steps of a method for automatically deploying working parameters of an industrial robot in one embodiment of the present application; Figure 2 This is a schematic diagram of a control device in an embodiment of the present application; Figure 3 Schematic diagram of the internal structure of an industrial robot according to an embodiment of the present application.

[0014] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0015] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0016] In addition, if the descriptions of "first", "second", etc. are involved in this application, they are only used for descriptive purposes (such as for distinguishing the same or similar features), and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0017] Reference Figure 1 In one embodiment, a method for automatically deploying working parameters of an industrial robot includes: Step S10: When the industrial robot receives the deployment instruction, it obtains the surrounding environment image based on the image sensor; Step S20: Analyze the surrounding environment image based on visual detection technology to obtain the relative position relationship between the industrial robot and the surrounding environment objects; wherein the surrounding environment objects at least include the workpiece assembly line; Step S30: According to the relative position relationship, the range of motion of the robotic arm is limited in a kinematic model of the robotic arm of the industrial robot; wherein the kinematic model is pre-constructed based on the structure of the robotic arm and the kinematic principle; Step S40, reading the workpiece image, the preset area of ​​the workpiece assembly line, the type of the working component at the end of the robot arm, and the type of the working task; Step S50, generating a collection target of the image sensor according to the workpiece image and the preset area; and generating operation process data of the operation component according to the workpiece image, the type of the operation component and the type of the operation task; and generating operation posture data of the robot arm adapted to the operation process data based on the defined kinematic model; Step S60: deploying the industrial robot to perform work parameters on each workpiece in a preset area transmitted by the workpiece assembly line according to the work process data, the work posture data and the acquisition target.

[0018] In this embodiment, the execution terminal of the embodiment may be an industrial robot, or a system or device (such as a control device) for controlling the industrial robot.

[0019] As described in step S10, the industrial robot will start the subsequent automatic deployment process only after receiving the deployment instruction. This deployment instruction may come from an instruction issued by an operator through a human-machine interface, or may be an instruction automatically sent by a production control system according to a production plan.

[0020] Industrial robots are equipped with image sensors, which can be cameras and other devices. The image sensor will capture the environment around the industrial robot to obtain images of the surrounding environment. These images contain information about various objects around the industrial robot, such as workpiece assembly lines, other equipment, obstacles, etc.

[0021] As described in step S20, the collected surrounding environment image may be interfered by noise, affecting subsequent analysis and processing. Therefore, the image can be filtered first, and the optional filtering methods include mean filtering, median filtering, Gaussian filtering, etc. In order to improve the clarity and contrast of the image and facilitate subsequent feature extraction and target recognition, the image can also be enhanced. The optional image enhancement methods include histogram equalization, grayscale transformation, etc.

[0022] Use edge detection algorithms to extract edge information of objects in images, and use corner detection algorithms to extract corners.

[0023] Optionally, if the template image of the surrounding environment object (such as the workpiece assembly line) is known, a template matching algorithm can be used to find the target matching the template image in the collected surrounding environment image. Commonly used template matching methods include matching methods based on normalized cross-correlation and matching methods based on shape. For example, in the matching method based on normalized cross-correlation, the normalized cross-correlation coefficients of the template image and each area in the image to be matched are calculated, and the area with the largest coefficient is found as the matching result.

[0024] On the image plane, determine the pixel coordinates of the feature points or areas of the industrial robot and surrounding objects (such as workpiece assembly lines). By analyzing the results of target recognition, find the feature points of the industrial robot and surrounding objects and record their pixel positions in the image.

[0025] The pixel coordinates on the image plane are converted into three-dimensional coordinates in the real world coordinate system using the intrinsic and extrinsic parameters obtained by camera calibration. Based on the principle of triangulation, combined with the camera's imaging model and known camera parameters, the positions of the industrial robot and surrounding objects in three-dimensional space are calculated.

[0026] After obtaining the three-dimensional coordinates of the industrial robot and the surrounding objects, the relative position relationship between the industrial robot and the surrounding objects is obtained by calculating the vector difference between them. For example, the distance, angle and other information between the coordinates of the industrial robot and the coordinates of the workpiece assembly line are calculated to determine the position and posture of the industrial robot relative to the workpiece assembly line.

[0027] Of course, if the surrounding environment objects include other objects (such as robot station fences, robots at other stations) in addition to the workpiece assembly line, the same method is used to obtain the relative position relationship between the industrial robot and these objects.

[0028] As described in step S30, the kinematic model is pre-built based on the structure and kinematic principles of the robotic arm. The robotic arm is usually composed of multiple joints and connecting rods, and the movement of each joint will affect the position and posture of the end effector of the robotic arm. The kinematic principle involves the mathematical description of the movement of these joints. By establishing a coordinate system and motion equations, the position and posture of the robotic arm at different joint angles can be accurately calculated.

[0029] Among them, the kinematic model can use a homogeneous transformation matrix to describe the relative position and posture relationship between the links of the robotic arm.

[0030] The surrounding environment objects at least include workpiece assembly lines, and may also include other equipment, obstacles, etc. In step S20, the relative position relationship between the industrial robot and these surrounding environment objects, such as distance, angle, etc., has been obtained through visual detection technology.

[0031] Optionally, based on the relative position relationship, a dangerous area where the robot arm may collide with surrounding objects during movement is determined.

[0032] In the kinematic model, the range of motion of the robot arm is limited by limiting the angle range of each joint of the robot arm. For example, if the normal range of motion of a joint is 0~180°, but considering the limitations of the surrounding environment, its range of motion can be reduced to 30°~120° to prevent the robot arm from entering the dangerous area.

[0033] In addition to joint angle constraints, you can also directly constrain the position and posture of the end effector of the robot arm. For example, set the maximum movement distance of the end effector in certain directions, or limit the range of its posture change within a specific area.

[0034] The above joint angle restrictions and position and posture constraints are converted into mathematical expressions and integrated into the pre-built kinematic model. In this way, in the subsequent motion planning and control, the kinematic model will automatically consider these restrictions to ensure that the movement of the robot arm does not exceed the limited range of activity.

[0035] Optionally, in order to further ensure that the robot arm does not collide with surrounding objects during movement, a certain safety margin can be considered when determining the range of motion. For example, when determining the danger zone, the actual collision boundary is extended outward by a certain distance as a safety boundary. The range of motion of the robot arm will be limited outside the safety boundary, thereby reducing the risk of collision.

[0036] Optionally, the size of the safety margin needs to be determined according to the specific application scenario and the motion accuracy of the robot. If the motion accuracy is set higher, the safety margin will be smaller. That is, if the motion accuracy of the robot is high, the safety margin can be relatively small; conversely, if the motion accuracy is low, the safety margin needs to be appropriately increased.

[0037] As described in step S40, the workpiece image contains information such as the appearance features, size, shape, surface texture, etc. of the workpiece. Such information is essential for the industrial robot to accurately identify the workpiece and determine its position and posture. For example, in a machining scenario, the workpiece image can be used to identify features such as holes and slots on the workpiece so that the robot arm can accurately perform operations such as drilling and milling.

[0038] The workpiece image can be a collection of images taken from multiple angles or a three-dimensional engineering image to provide more comprehensive workpiece information and ensure that the industrial robot can accurately identify the workpiece in different working scenarios.

[0039] The preset area defines the specific position range of the workpiece on the assembly line and is the target area for the industrial robot to operate. This area can be precisely set according to the production process and operation requirements. For example, it may be a fixed length area on the assembly line, or a rectangular area defined by specific coordinate points.

[0040] The setting of the preset area should take into account factors such as the conveying speed of the workpiece, the operating time and movement range of the robot arm, so as to ensure that the industrial robot can operate in a timely and accurate manner when the workpiece reaches the area.

[0041] The type of workpiece determines the function and purpose of the robot arm end effector. Common workpieces include fixtures, suction cups, spray guns, welding guns, etc. Different workpieces are suitable for different work tasks. For example, fixtures are used to grab and carry workpieces, spray guns are used for spraying operations, and welding guns are used for welding operations.

[0042] The task type describes the specific work that the industrial robot needs to complete, such as grasping, placing, assembling, processing, testing, etc. Different tasks have different requirements on the motion trajectory of the robot arm, the operation method and force of the operating parts, etc.

[0043] Optionally, these data can be pre-stored in the local memory of the industrial robot. For example, the workpiece image can be acquired and saved by the image acquisition device during the robot debugging phase, and the information such as the preset area of ​​the workpiece assembly line, the type of workpiece, and the type of work task can be manually input and stored locally by the operator according to the production plan and process requirements.

[0044] Alternatively, the control system can dynamically adjust and provide data such as preset areas, work component types, and work task types of the workpiece assembly line based on production scheduling and real-time feedback information to adapt to different production needs.

[0045] Among them, the type of the working part can also be directly obtained by reading the programmable chip of the working part connected to the end of the robot arm.

[0046] As described in step S50, based on the read workpiece image, the features of the workpiece, such as shape, color, texture, key identification points, etc., are analyzed. These features will serve as an important basis for image recognition. Then, the preset area of ​​the workpiece assembly line is considered to clarify the possible position and posture range of the workpiece in the area. The preset area defines the spatial range that the image sensor needs to focus on.

[0047] The acquisition target includes specific workpiece features and their position information within a preset area. For example, if the workpiece is a circular part with a specific mark, the acquisition target may be to identify the specific position and angle of the mark within the preset area.

[0048] Optionally, the workpiece image provides the actual state of the workpiece, the workpiece type determines the executable operation mode, and the work task type clarifies the final goal to be achieved. For example, for a workpiece that needs to be welded, the specific work process is planned by combining the shape of the workpiece and the weld position (obtained from the workpiece image), the workpiece type (welding gun) and the welding work task type.

[0049] Determine the starting and ending points of the job. For example, when grabbing a workpiece, the starting point may be the posture of the robot arm in the initial position, and the ending point is the posture after successfully grabbing the workpiece and moving it to the specified position.

[0050] Plan the operation content and sequence of each step in detail. For example, in a welding operation, it may include approaching the workpiece, adjusting the welding gun angle, starting welding, the movement path during welding, and the finishing action after welding.

[0051] Optionally, for each operation step, corresponding operation parameters are determined. For grasping operations, the operation parameters may include grasping force, grasping position, etc.; for spraying operations, the operation parameters may include spraying pressure, spraying speed, spraying distance, etc. The determination of these parameters needs to take into account factors such as the material, shape, and operation requirements of the workpiece.

[0052] In step S30, the kinematic model of the robot arm has been limited in its range of motion according to the relative positional relationship between the industrial robot and the surrounding objects. At this time, the limited kinematic model is used to generate the working posture data to ensure that the movement of the robot arm will not collide with the surrounding environment.

[0053] Optionally, according to the requirements of each step in the workflow data, the angles that each joint of the robot arm needs to reach are determined through inverse kinematics calculation of the kinematic model. Inverse kinematics is the process of solving the angles of each joint when the position and posture of the end effector of the robot arm are known. For example, when grasping a workpiece, the position and posture of the grasping point are known, and the angles of each joint of the robot arm are calculated through inverse kinematics, so that the robot arm can accurately reach the position and grasp with a suitable posture.

[0054] It is necessary not only to determine the joint angles corresponding to each operation step, but also to plan the motion trajectory of the robot from one posture to another. The planning of the motion trajectory needs to consider factors such as the robot's motion speed, acceleration, and smoothness to ensure that the robot moves smoothly and efficiently. Common motion trajectory planning methods include linear interpolation, circular interpolation, etc.

[0055] Optionally, when generating the operation posture data, the continuity of the operation can also be considered. That is, after completing one operation step, the robot arm can smoothly transition to the next operation step to avoid unnecessary pauses or large posture adjustments. For example, when performing a series of assembly operations, the posture changes of the robot arm should be coherent to improve the operation efficiency.

[0056] As described in step S60, the working parameters of the industrial robot are key settings to ensure its normal operation and completion of the task, mainly covering image sensor parameters, work process control parameters, and robot arm motion posture parameters, etc. The accurate deployment of these parameters directly affects the working efficiency, accuracy and safety of the robot.

[0057] Accurately map the generated image sensor acquisition targets to the image sensor settings. This means identifying the workpiece features that the sensor needs to focus on, their specific locations within the preset area, and the related acquisition requirements. For example, if the acquisition target is to identify the position and angle of a specific mark on the workpiece, you need to set the sensor to focus on the area where the mark is likely to appear and adjust the relevant parameters to clearly capture the mark information.

[0058] Optionally, fine-tune the parameters of the image sensor according to the acquisition target. These parameters include but are not limited to resolution, frame rate, exposure time, contrast, brightness, etc. If high-precision recognition of tiny features is required, increase the resolution; if the workpiece moves quickly on the assembly line, increase the frame rate to ensure clear image capture. At the same time, adjust the exposure time, contrast, and brightness according to the ambient light conditions to obtain high-quality image data.

[0059] Optionally, after completing the parameter setting, perform a test acquisition to observe whether the acquired image meets the acquisition target requirements. If the image is blurry, too dark, too bright, etc., calibrate and optimize the parameters in time until the acquired image can accurately reflect the relevant information of the workpiece.

[0060] Optionally, the generated operation process data is accurately imported into the control system of the industrial robot. The operation process data specifies in detail the operation steps, sequence, and specific operation content and operation parameters of each step. For example, in a welding operation, it includes steps such as approaching the workpiece, adjusting the welding gun angle, starting welding, the moving path during welding, and the finishing action after welding, as well as the corresponding operation parameters such as welding current, voltage, and welding speed for each step.

[0061] Optionally, the logic control part in the industrial robot control system is set according to the operation process data. Ensure that the robot can perform the operation tasks according to the predetermined steps and sequence, and can make corresponding logical judgments and operations according to different conditions. For example, if a defective workpiece is detected during the operation, the robot can automatically skip the workpiece or execute a specific processing procedure.

[0062] Optionally, a comprehensive error handling mechanism can be established so that when an abnormal situation occurs in the operation process, such as operation failure, equipment failure, etc., the robot can take corresponding measures in time, such as stopping the operation, issuing an alarm, recording error information, etc., to ensure the safety and stability of the operation.

[0063] Optionally, the generated robot arm operation posture data is loaded into the robot's motion control system. The operation posture data includes the angles that each joint of the robot arm needs to reach in different operation steps and the motion trajectory planning from one posture to another. By loading this data, the robot can accurately control the movement of the robot arm so that it reaches the specified position and performs the operation in a suitable posture.

[0064] After loading the posture data, the motion trajectory of the robot arm is further optimized. Factors such as the robot arm's motion speed, acceleration, and smoothness are considered to avoid jitter, jamming, or collision during the movement of the robot arm. Some optimization algorithms, such as trajectory optimization algorithms based on dynamic models, can be used to improve the motion performance of the robot arm.

[0065] Before actual operation, the robot simulation software is used to simulate the movement of the robot arm. Through simulation, the movement process of the robot arm can be observed intuitively to check whether there are problems such as motion interference and collision. If problems are found, the posture data and motion trajectory are adjusted and corrected in time to ensure the safety and reliability of the robot arm in actual operation.

[0066] Optionally, after all working parameters are deployed, the industrial robot can be tested. The robot is allowed to perform a complete task according to the deployed parameters, and the operation of the robot is observed, including the acquisition effect of the image sensor, the execution of the working process, and the motion posture of the robot arm.

[0067] Optionally, evaluate various performance indicators during the trial run, such as operation accuracy, operation efficiency, stability, etc. By comparing with the expected performance indicators, find out the existing problems and deficiencies.

[0068] Optionally, the working parameters can be fine-tuned based on the results of the performance evaluation. For example, if the operating accuracy is found to be unsatisfactory, the acquisition parameters of the image sensor or the motion posture parameters of the robot arm can be further adjusted; if the operating efficiency is low, the operating process control parameters or motion trajectory planning can be optimized. After multiple tests and adjustments, the industrial robot can reach the best working state.

[0069] In one embodiment, by using image sensors and visual detection technology, it is possible to obtain the surrounding environment information and workpiece information of the industrial robot in real time, and automatically generate and deploy working parameters based on this information, effectively overcoming the shortcomings of the existing technology, improving the deployment efficiency, accuracy and flexibility of the industrial robot, realizing the automation of the entire process from environmental perception to parameter deployment, and automatically completing the work parameter deployment of the industrial robot for each workpiece in the preset area for the workpiece assembly line to be transferred. The entire process does not require manual intervention in the setting of various complex parameters, which not only reduces labor costs, but also avoids errors that may be caused by human operation, ensuring that the industrial robot always operates in the best state, improving production efficiency and product quality, and enhancing the stability and reliability of industrial production.

[0070] In one embodiment, based on the above embodiment, the step of reading the workpiece image, the preset area of ​​the workpiece assembly line, the type of the working component at the end of the robot arm and the type of the working task further includes: Setting a standby position for the working parts before operation outside the preset area; Based on the standby position, the pending position of the workpiece in the preset area and the position of the working part after operation, combined with the limited kinematic model, a posture trajectory generation strategy is deployed for the robotic arm to control the working part to move back and forth between the standby position and the preset area before and after the operation.

[0071] In this embodiment, it is necessary to set a standby position of the working component before operation outside the preset area.

[0072] Setting the standby position outside the preset area can prevent the working parts from colliding with the workpieces or other peripheral equipment running on the assembly line when not working, reducing the risk of equipment damage and safety accidents. A reasonable standby position allows the working parts to quickly move to the preset area to start working after receiving the work instruction, reducing unnecessary movement time and improving overall work efficiency. The standby position will not interfere with the normal operation of the workpiece assembly line, ensuring the smoothness of the production line.

[0073] Wherein, the standby position is a fixed value; the standby position of the workpiece in the preset area and the position of the working part after operation are variables.

[0074] In industrial production scenarios, presetting and keeping the standby position of the working parts constant before operation helps simplify the robot arm motion planning process. For example, the standby position can be set at a specific point that does not affect the normal operation of the assembly line and allows the robot arm to quickly reach the preset area, and the working parts return to this fixed point before each operation cycle starts.

[0075] The reason why the pending position of the workpiece in the preset area is a variable is that although the workpiece will be transported to the preset area, its specific position will fluctuate within a certain range due to factors such as the accuracy of the assembly line transmission and the placement differences of the workpiece itself.

[0076] The position of the workpiece after operation is also a variable, which depends on the specific operation task. For example, in a handling task, if there are multiple target placement positions or a certain tolerance range, the position after operation will be different; in a processing task, the processing process may cause the workpiece position to be fine-tuned, and the position of the workpiece after operation will also change accordingly.

[0077] Optionally, based on the fixed standby position and the defined kinematic model, a basic trajectory template is constructed starting from the standby position. This template describes the general motion pattern of the robot arm from the standby position to the approximate range of the preset area, including the basic change law of the angle of each joint of the robot arm over time and the posture change trend of the end working part. For example, the robot arm approaches the preset area in a smooth curve motion, and the working part maintains a specific initial posture during the approach process.

[0078] Optionally, when the workpiece is detected to have entered the preset area, the basic trajectory is adjusted in real time according to the specific position information of the workpiece obtained in real time. The kinematic model is used to calculate the required joint angle change of the robot arm from the current position on the basic trajectory to the actual position of the workpiece, thereby dynamically modifying the motion trajectory of the robot arm to ensure that the working parts can accurately reach the workpiece position. For example, if the workpiece position is to the left than expected, the robot arm will adjust the motion path to the left accordingly.

[0079] Optionally, before the operation is completed, the target position of the work component after the operation is determined according to the specific operation task. This position is a variable, and the trajectory adjustment plan of the robot arm from the operation position to the target position is also calculated based on the kinematic model. For example, in a handling operation, if the target placement position changes, the robot arm will re-plan the return path and adjust the posture of the work component to adapt to the new placement requirements.

[0080] During the entire trajectory adjustment process, the constraints brought by the limited kinematic model must always be considered to ensure that the movement of the robot arm does not exceed the safe range of activity. At the same time, the dynamic characteristics of the robot arm, such as speed and acceleration limits, must also be considered to avoid vibration, collision or damage to the equipment due to excessive movement. For example, when adjusting the trajectory, the movement speed and acceleration of each joint of the robot arm should be reasonably controlled to ensure the smoothness and safety of the movement.

[0081] In this way, it can adapt to the uncertainty of the workpiece position and the diversity of the position after the operation, so that the industrial robot can flexibly respond to different production situations, enhancing the versatility and practicality of the system; building a basic trajectory template based on a fixed standby position reduces the trajectory planning time before each operation, while real-time adjustment of the trajectory can ensure accurate operation, which improves the overall operating efficiency of the industrial robot; strictly following the kinematic constraints in the trajectory generation and adjustment process reduces the risk of collision between the robot arm and surrounding objects, and ensures the safety of equipment and personnel.

[0082] In one embodiment, based on the above embodiment, the step of deploying the robot arm to control the posture trajectory generation strategy of the working component to go back and forth between the standby position and the preset area before and after the operation includes: According to the defined kinematic model, constraining the pre-deployed posture trajectory generation model; The standby position and the pending position of the workpiece in the preset area are set as input factors for the posture trajectory generation model to generate a first posture trajectory; and the standby position and the position of the working component after operation are set as input factors for the posture trajectory generation model to generate a second posture trajectory; Among them, the first posture trajectory is the posture trajectory of the robot arm before the operation; the second posture trajectory is the posture trajectory of the robot arm after the operation.

[0083] In this embodiment, a posture trajectory generation model is pre-trained and deployed.

[0084] Optionally, during the data preparation stage, collect the kinematic data of the robot arm under different working conditions, including the angle, speed, acceleration, etc. of each joint. This can be done by installing sensors (such as encoders, gyroscopes, etc.) on the robot arm to collect these data in real time; record the standby position, different positions of the workpiece in the preset area, and various possible positions of the working parts after operation (which can be simulated and generated). These position data can be obtained through visual sensors (such as cameras) or laser radar and other devices; obtain the posture information of the working parts at the end of the robot arm in different positions and during movement, such as pitch angle, yaw angle, roll angle, etc.

[0085] Remove noise and outliers from the collected data, such as erroneous data points caused by sensor failure or external interference. Standardize the data so that different types of data have the same scale to facilitate model learning. Label each sample data with the corresponding expected posture trajectory as the target of model training.

[0086] Optionally, choose Convolutional Neural Network as the base model.

[0087] The preprocessed data is divided into training set, validation set and test set, with an optional ratio of 70%:15%:15%. The training set is used for model parameter learning, the validation set is used to evaluate the performance of the model during training and adjust hyperparameters, and the test set is used to finally evaluate the generalization ability of the model.

[0088] The mean square error loss is used as the loss function to measure the error between the generated trajectory and the true trajectory; other loss terms, such as regularization terms, can also be combined to prevent model overfitting.

[0089] Initialize the model parameters, then input the training set data into the model for forward propagation to calculate the predicted posture trajectory. Calculate the loss value based on the predicted trajectory and the true trajectory, and calculate the gradient of the loss function with respect to the model parameters through the back propagation algorithm. Use the optimization algorithm to update the model parameters, and continuously iterate the training process until the loss function converges or the preset number of training rounds is reached.

[0090] Optionally, use a variety of evaluation metrics to evaluate the performance of the model, such as mean square error, mean absolute error, trajectory similarity, etc. These metrics can measure the degree of deviation between the generated trajectory and the true trajectory.

[0091] Optionally, the model's hyperparameters, such as learning rate, number of hidden layer neurons, number of training rounds, etc., can be adjusted through grid search, random search, etc. to improve the model's performance. Fusion of multiple different models, such as weighted averaging of the prediction results of the neural network model and the decision tree model, may yield a more accurate posture trajectory.

[0092] Build the model running environment in the control system of the industrial robot, install the required software libraries and drivers, and ensure that the model can run normally on the actual hardware platform.

[0093] Optionally, the trained posture trajectory generation model is integrated into the control system of the industrial robot, so that it can receive the position, kinematics and other data of the robot arm in real time, and generate posture trajectories based on these data to control the movement of the robot arm.

[0094] Optionally, during the actual operation, the output of the model and the motion state of the robot arm are monitored in real time to collect feedback data. If problems are found in the trajectory generated by the model, the model is adjusted and optimized in a timely manner to ensure the operation quality and safety of the industrial robot.

[0095] Through the above complete pre-training and deployment process, the posture trajectory generation model can provide accurate and reliable posture trajectories for industrial robots, enabling the robotic arm to control the working parts to efficiently travel back and forth between the standby position and the preset area before and after the operation.

[0096] The following will describe in detail the specific process of deploying the posture trajectory generation strategy of the robot arm to control the working parts to and from the standby position and the preset area before and after the operation based on the above posture trajectory generation model: The restricted kinematic model describes the feasible range and rules of motion of each joint of the robot arm after considering the relative position relationship of the surrounding objects. This model is the basis for ensuring the safe and effective motion of the robot arm.

[0097] Apply the restricted kinematic model to the pre-deployed posture trajectory generation model. For example, the posture trajectory generation model may originally generate some trajectories that exceed the physical limits of the robot or collide with surrounding objects. Through the constraints of the kinematic model, these infeasible trajectory solutions are removed. Specifically, for each possible robot posture and trajectory point output by the posture trajectory generation model, check whether it meets the conditions such as the joint angle range and speed limit specified by the kinematic model. If not, the posture or trajectory point is corrected or discarded to ensure that the final generated trajectory is within the actual feasible range of the robot.

[0098] Through this constraint, dangerous movements of the robot arm during movement can be avoided, the safety and reliability of industrial robot operations can be improved, and at the same time, the generated trajectory can be ensured to be consistent with the actual movement capabilities of the robot arm, thereby improving movement efficiency.

[0099] The standby position and the pending position of the workpiece in the preset area are set as input factors for the posture trajectory generation model to generate the first posture trajectory. The standby position is a fixed position where the working part waits before operation, and the pending position of the workpiece in the preset area may change due to factors such as assembly line transmission. Based on these two input factors and its own rules that have been constrained, the posture trajectory generation model calculates the posture and trajectory of the robot arm moving from the standby position to the pending position of the workpiece. The model will consider the kinematic characteristics of the robot arm, such as the range of motion, movement speed and acceleration of the joints, to generate an optimal path so that the robot arm can reach the workpiece position smoothly and accurately. For example, the model may use a path planning algorithm to find the shortest or smoothest path while satisfying the kinematic constraints.

[0100] The first posture trajectory is the posture trajectory of the robot arm before operation. It ensures that the robot arm can move quickly and accurately from the standby state to the operation preparation position, prepare for subsequent operation, and improve the starting efficiency of the operation.

[0101] The standby position and the position of the working part after the operation are set as input factors for the posture trajectory generation model to generate the second posture trajectory. The position of the working part after the operation varies according to the specific work task. Based on these two input factors, the posture trajectory generation model also combines the constraints to calculate the posture and trajectory of the robot arm returning from the work completion position to the standby position. Similar to the generation of the first posture trajectory, the model will comprehensively consider the kinematic characteristics of the robot arm and the constraints of the surrounding environment to generate a suitable return path. For example, when generating the return trajectory, it is also necessary to consider the posture of the working part after the operation to ensure that the robot arm will not interfere with surrounding objects during the return process.

[0102] The second posture trajectory is the posture trajectory of the robot arm after the operation. It ensures that the robot arm can return to the standby position safely and efficiently after completing the operation, prepare for the next operation cycle, and make the operation process of the industrial robot form a complete and orderly closed loop.

[0103] Through the above steps, the industrial robot can automatically generate a reasonable robotic arm posture trajectory based on different position information and kinematic constraints, and realize the safe and efficient round-trip of the working parts between the standby position and the preset area, thereby improving the degree of automation and production efficiency of the entire industrial production process.

[0104] In one embodiment, based on the above embodiment, the method for automatically deploying working parameters of the industrial robot further includes: If the first posture trajectory includes multiple stage trajectories, the movement speed of the robot arm in the last stage trajectory is less than the movement speed of the previous stage trajectory.

[0105] In this embodiment, when the robot arm approaches the workpiece, a higher positioning accuracy is required. If the movement speed is kept high, due to factors such as the inertia of the robot arm itself and the gap in the transmission system, it will be difficult for the robot arm to accurately stop the working part at the target position, which is prone to positioning errors. Reducing the movement speed of the trajectory in the final stage can reduce the influence of inertia, allowing the robot arm to reach the pending position of the workpiece more accurately, thereby improving the accuracy of the operation.

[0106] In the process of approaching the workpiece, the distance between the robot arm and the workpiece gradually decreases, and the risk of collision increases. The lower movement speed can provide more reaction time for the operator or control system. Once an abnormal situation is found, measures can be taken in time to stop the movement of the robot arm, avoid collision accidents, and protect the safety of the robot arm, workpiece and surrounding equipment.

[0107] Therefore, when the posture trajectory generation model generates the first posture trajectory, the corresponding motion speed is pre-set according to the different stages of the trajectory. For example, the first posture trajectory is divided into the initial approach stage, the intermediate transition stage and the final approach stage. In the trajectory planning algorithm, a lower speed parameter is set for the final stage trajectory, while a relatively higher speed parameter is set for the previous stage trajectory.

[0108] Optionally, during the actual movement of the robot arm, the control system monitors the trajectory stage of the robot arm in real time. When the robot arm enters the final stage trajectory, the control system automatically adjusts the output power of the drive motors of each joint of the robot arm to reduce the movement speed. This function can be achieved by a speed controller, which can accurately control the movement speed of the robot arm according to a preset speed curve.

[0109] Accurate positioning and reduced collision risk directly contribute to improving the quality of industrial robot operations. For example, in assembly operations, the robot arm can grasp and place workpieces more accurately, avoiding poor assembly problems caused by inaccurate positioning; in processing operations, the workpiece can be processed more accurately, improving processing accuracy.

[0110] This speed setting method makes the movement of industrial robots more stable and reliable, reducing downtime caused by motion errors and collisions. It improves the reliability and stability of the entire industrial production system and ensures the continuity and efficiency of production.

[0111] In one embodiment, based on the above embodiment, the end of the robot arm is further integrated with a distance detection sensor, and the distance detection sensor is used to detect the real-time distance between the end of the robot arm and the workpiece; The posture trajectory generation strategy also includes adjusting the movement speed of the robotic arm based on the final stage trajectory based on the real-time distance; The smaller the real-time distance is, the smaller the movement speed is.

[0112] In this embodiment, the distance detection sensor is integrated at the end of the robot arm, and its core function is to detect the distance between the end of the robot arm and the workpiece in real time. This real-time distance data is crucial for the precise operation of the robot arm, allowing the control system to understand the relative position relationship between the robot arm and the workpiece at any time, providing a key basis for subsequent speed adjustment. Optional distance detection sensors include laser distance sensors, ultrasonic distance sensors, etc.

[0113] When the robot arm approaches the workpiece in the final stage of the trajectory, as the real-time distance to the workpiece gradually decreases, the movement speed also decreases accordingly. This is because when the distance is small, the risk of collision of the robot arm increases sharply, and the positioning accuracy requirement is higher. By reducing the movement speed, the influence of inertia can be reduced, so that the robot arm has more time to make fine adjustments, so as to reach the target position more accurately and avoid collisions or inaccurate positioning problems caused by excessive speed. For example, when the robot arm is performing fine assembly operations, after approaching the workpiece to a certain distance, the slow speed can ensure that the parts are installed accurately and correctly.

[0114] Optionally, a set of speed adjustment rules can be pre-set according to the actual operation requirements and the performance characteristics of the robot arm. For example, a distance-speed mapping table can be established to clarify the movement speed corresponding to different real-time distances. When the distance detection sensor obtains the real-time distance, the control system automatically adjusts the movement speed of the robot arm according to the mapping table.

[0115] Optionally, a feedback control algorithm, such as a proportional-integral-differential (PID) control algorithm, is used to input the real-time distance as a feedback signal into the control system. The control system calculates the speed value that needs to be adjusted based on the deviation between the set target distance and the current real-time distance, and dynamically adjusts the movement speed of the robot arm in real time to ensure that the robot arm can stably and accurately approach the workpiece.

[0116] By adjusting the speed in real time according to the distance, the robot arm can perform more precise motion control when approaching the workpiece. When the distance is small, the robot arm moves at a very low speed, which enables the robot arm to reach the target position more accurately and meet the requirements of high-precision operations, which is of great significance in scenes with extremely high precision requirements, such as the assembly of electronic chips.

[0117] As the real-time distance decreases, the speed is reduced, providing more buffer time for the robot arm. Once an unexpected situation occurs, such as a slight change in the position of the workpiece, the lower speed allows the robot arm to stop in time to avoid collision with the workpiece, protecting the safety of the robot arm and the workpiece, and reducing equipment damage and production losses caused by collision.

[0118] Different operating scenarios and workpieces may have different requirements for the approach speed of the robot arm. The speed adjustment method based on real-time distance can be dynamically adjusted according to the actual situation, so that the robot arm can complete tasks flexibly and efficiently in various complex operating environments, improving the versatility and adaptability of industrial robots.

[0119] In one embodiment, based on the above embodiment, the step of generating the operation posture data of the robot arm adapted to the operation process data based on the defined kinematic model includes: Based on the defined kinematic model, traverse a plurality of posture combinations to generate a plurality of groups of operation posture data of the robot arm adapted to the operation process data; The collection of multiple groups of working posture data is used as the initial population of the bio-inspired algorithm, and the multi-factor fitness function of the bio-inspired algorithm is set based on the maximum motion efficiency, minimum joint activity, and minimum energy consumption of the robot arm; The biologically inspired algorithm is used to iteratively optimize the data in the collection and continuously update the population until the optimal result is found as the final working posture data.

[0120] In this embodiment, the kinematic model describes the relationship between the joint motion of the robot arm and the position and posture of the end effector. After being limited, the model takes into account the physical limitations of the robot arm (such as the range of joint motion, maximum speed, etc.), and by traversing multiple posture combinations, this model is used to calculate the possibility of the robot arm executing the work process in different postures, thereby generating multiple sets of work posture data adapted to the work process data. For example, for a robot arm with multiple joints, each joint has a certain range of motion angles. By combining different angles within these ranges, the various possible situations in which the end effector of the robot arm can reach various target positions and postures in the work process are calculated.

[0121] The generated sets of multiple work posture data are used as the initial population of the biological heuristic algorithm. In the biological heuristic algorithm, the population represents a set of possible solutions. Each set of work posture data here is equivalent to an individual. The initial population contains a variety of different posture combination solutions, providing a rich search space for subsequent optimization.

[0122] In order to select the best solution from a large number of working posture data, a fitness function needs to be set to evaluate the pros and cons of each individual. A multi-factor fitness function is set based on the three factors of the robot's highest motion efficiency, minimum joint range of motion, and minimum energy consumption.

[0123] Among them, the highest motion efficiency means that the robot arm can complete the operation process in the shortest time, reduce the production cycle and improve production efficiency. For example, by optimizing the posture, the length of the robot arm's motion path can be reduced, thereby speeding up the operation.

[0124] Among them, the minimum joint range of motion can reduce unnecessary joint movement, reduce wear and fatigue of the robot arm, and extend the service life of the robot arm. At the same time, a smaller joint range of motion also helps to improve the stability and accuracy of movement.

[0125] Among them, reducing the energy consumption of the robot arm can reduce production costs and meet the requirements of energy conservation and environmental protection. By choosing a suitable posture, the energy consumed by the robot arm during movement can be minimized.

[0126] The fitness function takes these three factors into consideration and calculates a fitness value for each job posture data. The higher the fitness value, the better the posture data.

[0127] Biological heuristic algorithms (such as genetic algorithms and particle swarm algorithms) iteratively optimize the initial population by simulating the mechanism of biological evolution or group behavior. In each iteration, the algorithm evaluates the fitness value of each individual in the population according to the fitness function, and then generates a new population through operations such as selection, crossover, and mutation. The selection operation will retain individuals with higher fitness values, the crossover operation will combine some features of excellent individuals, and the mutation operation will introduce new features to increase the diversity of the population. Through continuous iteration, the individuals in the population gradually evolve in a better direction.

[0128] The iteration process will continue until the termination condition is met. Usually, the termination condition can be reaching the preset number of iterations, or the fitness value of the optimal result found is no longer significantly improved. When the iteration is completed, the work posture data corresponding to the individual with the highest fitness value is the final work posture data adopted.

[0129] Through the multi-factor fitness function, multiple factors such as the robot's motion efficiency, joint mobility and energy consumption are comprehensively considered, and an operating posture solution with excellent performance in multiple indicators can be found, rather than just optimizing a single indicator.

[0130] The bio-inspired algorithm has a strong global search capability and can find the optimal solution in a large search space. By iteratively optimizing multiple posture combinations, it can avoid falling into the local optimal solution and increase the possibility of finding the global optimal working posture.

[0131] In this way, the parameters of the kinematic model and fitness function can be flexibly adjusted according to different operation process data and the characteristics of the robotic arm. It has strong adaptability and versatility and is suitable for various types of industrial robot operation scenarios.

[0132] In one embodiment, based on the above embodiment, the method for automatically deploying working parameters of the industrial robot further includes: According to the average fitness difference between the previous two iterations, the crossover probability of the current iteration is adjusted; The greater the average fitness difference is, the greater the adjusted crossover probability is.

[0133] In this embodiment, in the biological heuristic algorithm, the crossover operation is a key means to generate new individuals and explore the solution space. The average fitness difference reflects the evolutionary effectiveness of the algorithm in two adjacent iterations. When the average fitness difference is large, it indicates that the algorithm is rapidly evolving in the direction of improving fitness, and the current search direction is very promising. At this time, increasing the crossover probability can accelerate the generation of more new individuals that inherit excellent characteristics and speed up the process of convergence to the optimal solution. When the average fitness difference is small, it means that the algorithm evolves slowly and may fall into a local optimum. At this time, the crossover probability can be maintained or moderately reduced, and the mutation operation can be used to expand the search range.

[0134] Optionally, after each round of iteration, the average fitness of the population in this round and the previous round is calculated respectively. The difference in average fitness between the first two iteration rounds is calculated by subtracting the average fitness of the previous iteration round from the average fitness of the previous round.

[0135] The value range of the crossover probability is pre-set, namely the minimum crossover probability P1 and the maximum crossover probability P2. Then the crossover probability P3 of the current iteration round is adjusted according to the average fitness difference f. The adjustment rules are as follows: P3=P1+f×(P2-P1) / F; Among them, F is the maximum expected value of the pre-set average fitness difference f, which is used to normalize the average fitness difference f to the interval [0,1] to ensure that the adjusted crossover probability P3 is within the range [P1,P2].

[0136] When performing a crossover operation in the current iteration round, the adjusted crossover probability P3 is used to decide which individuals to crossover.

[0137] By dynamically adjusting the crossover probability based on the average fitness difference between the first two iterations, the automatic deployment method for industrial robot working parameters can better balance the global search and local search capabilities. It can accelerate convergence when the algorithm evolves rapidly and expand the search range when the evolution is slow, thereby improving algorithm performance and finding better industrial robot working parameters.

[0138] In addition, refer to Figure 2 In an embodiment of the present application, a control device Z10 is further provided, comprising: The acquisition module Z11 is used to acquire the surrounding environment image based on the image sensor when the industrial robot receives the deployment instruction; The analysis module Z12 is used to analyze the surrounding environment image based on the visual detection technology to obtain the relative position relationship between the industrial robot and the surrounding environment objects; wherein the surrounding environment objects at least include the workpiece assembly line; A constraint module Z13, used for limiting the range of motion of the mechanical arm in a kinematic model of the mechanical arm of the industrial robot according to the relative position relationship; wherein the kinematic model is pre-constructed based on the structure of the mechanical arm and the kinematic principle; The reading module Z14 is used to read the workpiece image, the preset area of ​​the workpiece assembly line, the type of the working part at the end of the robot arm, and the type of the working task; A generating module Z15 is used to generate a collection target of an image sensor according to a workpiece image and a preset area; and to generate operation process data of an operation component according to the workpiece image, the type of the operation component and the type of the operation task; and to generate operation posture data of a robot arm adapted to the operation process data based on the defined kinematic model; The deployment module Z16 is used to deploy the working parameters of the industrial robot to perform operations on each workpiece transmitted to a preset area by the workpiece assembly line according to the work process data, the work posture data and the collection target.

[0139] Optionally, the control device Z10 may be a virtual control device (such as a virtual machine) or a physical device (such as a physical device other than an industrial robot that can execute the corresponding method).

[0140] In addition, an industrial robot is also provided in an embodiment of the present application. The internal structure of the industrial robot can be as follows: Figure 3 As shown, it includes a processor, a memory, a communication interface and an input interface connected by a system bus. Among them, the processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database is used to store data called by the computer program. The communication interface is used to communicate data with an external terminal. The input interface is used to receive a signal input by an external device. When the computer program is executed by the processor, a method for automatically deploying the working parameters of an industrial robot as described in the above embodiment is implemented.

[0141] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the present application scheme, and does not constitute a limitation on the industrial robot to which the present application scheme is applied. For example, in some optional embodiments, the industrial robot may also include an output interface (not shown in the figure), and the output interface is also connected to the system bus and is used to output corresponding signals to the peripheral device.

[0142] In addition, the present application also proposes a computer-readable storage medium, the computer-readable storage medium including a computer program, and the computer program, when executed by a processor, implements the steps of the method for automatically deploying working parameters of an industrial robot as described in the above embodiment. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0143] In summary, the automatic deployment method, control device, industrial robot and computer-readable storage medium of the working parameters of the industrial robot provided in the embodiments of the present application can obtain the surrounding environment information and workpiece information of the industrial robot in real time by using image sensors and visual detection technology, and automatically generate and deploy working parameters based on this information, effectively overcoming the shortcomings of the prior art, improving the deployment efficiency, accuracy and flexibility of the industrial robot, realizing the automation of the whole process from environmental perception to parameter deployment, and automatically completing the deployment of working parameters for the industrial robot to each workpiece in the preset area for the workpiece assembly line to be transferred. The whole process does not require manual intervention in the setting of various complex parameters, which not only reduces labor costs, but also avoids errors that may be caused by human operation, ensures that the industrial robot always operates in the best state, improves production efficiency and product quality, and enhances the stability and reliability of industrial production.

[0144] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0145] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0146] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for automatically deploying working parameters of an industrial robot, characterized in that: include: When the industrial robot receives the deployment instruction, it obtains the image of the surrounding environment based on the image sensor; Analyze the surrounding environment image based on visual detection technology to obtain the relative position relationship between the industrial robot and the surrounding environment objects; wherein the surrounding environment objects at least include the workpiece assembly line; According to the relative position relationship, the range of motion of the robot arm is limited in a kinematic model of the robot arm of the industrial robot; wherein the kinematic model is pre-constructed based on the structure of the robot arm and the kinematic principle; Read the workpiece image, the preset area of ​​the workpiece assembly line, the type of workpiece at the end of the robot arm, and the type of work task; Generate an acquisition target of the image sensor according to the workpiece image and the preset area; and generate operation process data of the operation component according to the workpiece image, the type of the operation component and the type of the operation task; and generate operation posture data of the robot arm adapted to the operation process data based on the defined kinematic model; According to the operation process data, the operation posture data and the acquisition target, the industrial robot is deployed to perform operation parameters on each workpiece transmitted by the workpiece assembly line to a preset area.

2. The method for automatically deploying working parameters of an industrial robot according to claim 1, characterized in that: After the step of reading the workpiece image, the preset area of ​​the workpiece assembly line, the type of the working component at the end of the robot arm and the type of the working task, the following steps are further included: Setting a standby position for the working parts before operation outside the preset area; Based on the standby position, the pending position of the workpiece in the preset area and the position of the working part after operation, combined with the limited kinematic model, a posture trajectory generation strategy is deployed for the robotic arm to control the working part to move back and forth between the standby position and the preset area before and after the operation.

3. The method for automatically deploying working parameters of an industrial robot according to claim 2, characterized in that: The step of deploying a robot arm to control the working component to go back and forth between the standby position and the preset area before and after the operation to generate a posture trajectory strategy includes: According to the defined kinematic model, constraining the pre-deployed posture trajectory generation model; The standby position and the pending position of the workpiece in the preset area are set as input factors for the posture trajectory generation model to generate a first posture trajectory; and the standby position and the position of the working component after operation are set as input factors for the posture trajectory generation model to generate a second posture trajectory; Among them, the first posture trajectory is the posture trajectory of the robot arm before the operation; the second posture trajectory is the posture trajectory of the robot arm after the operation.

4. The method for automatically deploying working parameters of an industrial robot according to claim 3, characterized in that: The method for automatically deploying the working parameters of the industrial robot also includes: If the first posture trajectory includes multiple stage trajectories, the movement speed of the robot arm in the last stage trajectory is less than the movement speed of the previous stage trajectory.

5. The method for automatically deploying working parameters of an industrial robot according to claim 4, characterized in that: The end of the robot arm is also integrated with a distance detection sensor, which is used to detect the real-time distance between the end of the robot arm and the workpiece; The posture trajectory generation strategy also includes adjusting the movement speed of the robotic arm based on the final stage trajectory based on the real-time distance; The smaller the real-time distance is, the smaller the movement speed is.

6. The method for automatically deploying working parameters of an industrial robot according to claim 1, characterized in that: The step of generating the operation posture data of the robot arm adapted to the operation process data based on the defined kinematic model comprises: Based on the defined kinematic model, traverse a plurality of posture combinations to generate a plurality of groups of operation posture data of the robot arm adapted to the operation process data; The collection of multiple groups of working posture data is used as the initial population of the bio-inspired algorithm, and the multi-factor fitness function of the bio-inspired algorithm is set based on the maximum motion efficiency, minimum joint activity, and minimum energy consumption of the robot arm; The biologically inspired algorithm is used to iteratively optimize the data in the collection and continuously update the population until the optimal result is found as the final working posture data.

7. The method for automatically deploying working parameters of an industrial robot according to claim 6, characterized in that: The method for automatically deploying the working parameters of the industrial robot also includes: According to the average fitness difference between the previous two iterations, the crossover probability of the current iteration is adjusted; The greater the average fitness difference is, the greater the adjusted crossover probability is.

8. A control device, characterized in that: include: The acquisition module is used to obtain the surrounding environment image based on the image sensor when the industrial robot receives the deployment instruction; An analysis module, used to analyze the surrounding environment image based on visual detection technology to obtain the relative position relationship between the industrial robot and the surrounding environment objects; wherein the surrounding environment objects at least include a workpiece assembly line; A constraint module, used for limiting the range of motion of the mechanical arm in a kinematic model of the mechanical arm of the industrial robot according to the relative position relationship; wherein the kinematic model is pre-constructed based on the structure of the mechanical arm and the kinematic principle; A reading module is used to read the workpiece image, the preset area of ​​the workpiece assembly line, the type of the working part at the end of the robot arm, and the type of the working task; A generation module is used to generate a collection target of an image sensor according to a workpiece image and a preset area; and to generate operation process data of an operation component according to the workpiece image, the type of the operation component and the type of the operation task; and to generate operation posture data of a robot arm adapted to the operation process data based on the defined kinematic model; A deployment module is used to deploy the working parameters of the industrial robot to perform operations on each workpiece transmitted to a preset area by the workpiece assembly line according to the work process data, the work posture data and the collection target.

9. An industrial robot, characterized in that: The industrial robot includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the method for automatically deploying working parameters of the industrial robot as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for automatically deploying working parameters of an industrial robot according to any one of claims 1 to 7 are implemented.

Images