Industrial robot motion control method, system, equipment and medium

Abstract

The invention provides an industrial robot motion control method, system and device and a medium. Jitter features of all motion joints of an industrial mechanical arm are extracted from historical motion data; according to all the shaking characteristics and the coupling incidence relation of every two adjacent movement joints in the industrial mechanical arm during transmission, the cooperative error between the movement joints in the industrial mechanical arm is determined; a plurality of track offset points of the end effector are determined, and the guide deviation of the end effector under sudden change sensing is determined according to the offset trend characteristics of all the track offset points; according to the cooperative error and the guide deviation under the sudden change perception, the cooperative compensation amount of each motion joint in the industrial mechanical arm under the sudden change motion is determined; and corresponding movement joints in the industrial mechanical arm are guided to conduct cooperative movement based on all the coordination compensation amounts. By the adoption of the scheme, stable motion control of the industrial robot in the high-intensity industrial environment can be achieved based on coordinated compensation of all the motion joints of the industrial mechanical arm under sudden-change motion.

Description

Technical Field

[0001] This application relates to the technical field of industrial robot control. More specifically, this application relates to a method, system, device, and medium for controlling the movement of an industrial robot. Background Art

[0002] An industrial robot is an automated, multi-degree-of-freedom programmable mechanical device used to perform repetitive and high-precision industrial tasks such as welding, assembly, handling, spraying, cutting, etc. Its core function is to improve production efficiency, enhance product quality, reduce labor costs, and adapt to complex or dangerous environments, and it is an important part of intelligent manufacturing.

[0003] With the development of industrial automation, the requirements for the movement accuracy and adaptability of industrial robots are getting higher and higher. In order to achieve accurate movement trajectories, industrial robot motion control methods have been continuously evolving, mainly involving technologies such as path planning, trajectory tracking, servo control, force and position coordination control, etc. However, in the existing technology, industrial robots need to frequently perform high-speed precision operations in a high-intensity industrial environment. During the process of industrial robots performing high-intensity industrial tasks, due to various emergencies often faced, the movement joints in the industrial robotic arm are prone to asynchronous movement, which in turn causes abnormal movement of the industrial robotic arm. Moreover, there is error transmission between the movement joints. When a movement joint generates a movement error due to inertia, friction, or load change, this movement error will accumulate in the entire industrial robotic arm structure, resulting in the trajectory of the end effector of the industrial robot deviating from the expected value, thereby affecting the smoothness of the overall movement trajectory of the industrial robot and reducing the applicability of the industrial robot in high-precision tasks. Therefore, how to achieve stable motion control of industrial robots in a high-intensity industrial environment based on the coordinated compensation of each movement joint of the industrial robotic arm under sudden movements has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides a method, system, device, and medium for controlling the movement of an industrial robot, which can achieve stable motion control of an industrial robot in a high-intensity industrial environment based on the coordinated compensation of each movement joint of the industrial robotic arm under sudden movements.

[0005] In a first aspect, this application provides a method for controlling the movement of an industrial robot, including the following steps: Obtain the historical movement data of the industrial robotic arm, where the industrial robotic arm has multiple movement joints; Extract the jitter characteristics of each movement joint of the industrial robotic arm from the historical movement data, and determine the collaborative error between the movement joints in the industrial robotic arm by combining all the jitter characteristics with the coupling correlation relationship between each adjacent movement joint in the industrial robotic arm during transmission; Start the industrial robotic arm, perform real-time trajectory tracking on the end effector of the industrial robotic arm to obtain multiple trajectory offset points of the end effector, and determine the guiding deviation of the end effector under mutation perception by combining the offset trend characteristics of all trajectory offset points with the sudden movement of the industrial robotic arm under visual feedback; Determine the coordination compensation amount of each moving joint in the industrial robotic arm under mutation movement based on the collaborative error between each moving joint and the guiding deviation of the end effector under mutation perception; Guide the corresponding moving joints in the industrial robotic arm to perform collaborative movement based on each coordination compensation amount.

[0006] In some embodiments, extracting the jitter characteristics of each moving joint of the industrial robotic arm from the historical motion data specifically includes: Extract the motion state data of each moving joint in the historical motion data; Select one moving joint of the industrial robotic arm as the selected moving joint; Generate the vibration trajectory of the selected moving joint based on the motion state data of the selected moving joint; Determine the jitter characteristics of the selected moving joint from the vibration trajectory; Continue to determine the jitter characteristics of the remaining moving joints of the industrial robotic arm.

[0007] In some embodiments, determining the collaborative error between each moving joint in the industrial robotic arm by combining all the jitter characteristics with the coupling correlation relationship between each adjacent moving joint in the industrial robotic arm during transmission specifically includes: Determine the coupling correlation relationship between each adjacent moving joint in the industrial robotic arm during transmission through the kinematic equation; Determine the error transfer model between each moving joint in the industrial robotic arm based on the coupling correlation relationship between all adjacent moving joints during transmission; Determine the collaborative error between each moving joint in the industrial robotic arm from the error transfer model between each moving joint and all the jitter characteristics.

[0008] In some embodiments, performing real-time trajectory tracking on the end effector of the industrial robotic arm to obtain multiple trajectory offset points of the end effector specifically includes: Obtain the theoretical trajectory of the end effector of the industrial robotic arm; Collect the real-time actual trajectory of the end effector of the industrial robotic arm; Compare the real-time actual trajectory with the theoretical trajectory point by point to obtain multiple trajectory offset points of the end effector.

[0009] In some embodiments, determining the guiding deviation of the end effector under mutation perception by combining the offset trend features of all trajectory offset points with the sudden movement of the industrial robotic arm under visual feedback specifically includes: Determining the offset trend features of all trajectory offset points; Extracting the sudden movement of the industrial robotic arm under visual feedback from the interaction information between the industrial robotic arm and the industrial environment; Determining the movement offset amount of the end effector under mutation perception through the sudden movement of the industrial robotic arm under visual feedback; Determining the guiding deviation of the end effector under mutation perception from the movement offset amount under mutation perception and the offset trend features.

[0010] In some embodiments, determining the coordination compensation amount of each movement joint in the industrial robotic arm under sudden movement based on the collaborative error between each movement joint and the guiding deviation of the end effector under mutation perception specifically includes: Determining the drift characteristics of each movement joint in the industrial robotic arm during the movement process based on the collaborative error between each movement joint and the guiding deviation of the end effector under mutation perception; Determining the coordination compensation amount of each movement joint in the industrial robotic arm under sudden movement through the drift characteristics of each movement joint during the movement process.

[0011] In some embodiments, determining the coordination compensation amount of each movement joint in the industrial robotic arm under sudden movement through the drift characteristics of each movement joint during the movement process specifically includes: Selecting a movement joint of the industrial robotic arm as the selected movement joint; Determining the contribution degree of the selected movement joint to the abnormal swing of the industrial robotic arm; Determining the coordination compensation amount of the selected movement joint in the industrial robotic arm under sudden movement based on the drift characteristics of the selected movement joint during the movement process and the contribution degree; Continuing to determine the coordination compensation amount of the remaining movement joints in the industrial robotic arm under sudden movement.

[0012] In a second aspect, the present application provides an industrial robot motion control system, including: An acquisition module, configured to acquire the historical motion data of the industrial robotic arm, where the industrial robotic arm has multiple movement joints; A processing module, configured to extract the jitter characteristics of each movement joint of the industrial robotic arm from the historical motion data, and determine the collaborative error between each movement joint in the industrial robotic arm by combining all the jitter characteristics with the coupling correlation relationship between each adjacent movement joint in the industrial robotic arm during transmission; The processing module is further configured to start the industrial robotic arm, perform real-time trajectory tracking on the end effector of the industrial robotic arm, obtain multiple trajectory offset points of the end effector, and determine the guiding deviation of the end effector under mutation perception by combining the offset trend features of all the trajectory offset points with the sudden movement of the industrial robotic arm under visual feedback; The processing module is further configured to determine the coordination compensation amount of each moving joint in the industrial robotic arm under sudden movement according to the coordination error between the moving joints and the guiding deviation of the end effector under mutation perception; The execution module is configured to guide the corresponding moving joints in the industrial robotic arm to perform coordinated movement based on each coordination compensation amount.

[0013] In a third aspect, the present application provides a computer device, which includes a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned industrial robot motion control method.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer is caused to execute the above-mentioned industrial robot motion control method.

[0015] The technical solution provided by the disclosed embodiments of the present application has the following beneficial effects: In the present application, by acquiring the historical motion data of the industrial robotic arm, where the industrial robotic arm has multiple moving joints; extracting the jitter features of each moving joint of the industrial robotic arm from the historical motion data, and determining the coordination error between the moving joints in the industrial robotic arm by combining all the jitter features with the coupling correlation relationship between each adjacent moving joint in the industrial robotic arm during transmission; starting the industrial robotic arm, performing real-time trajectory tracking on the end effector of the industrial robotic arm, obtaining multiple trajectory offset points of the end effector, and determining the guiding deviation of the end effector under mutation perception by combining the offset trend features of all the trajectory offset points with the sudden movement of the industrial robotic arm under visual feedback; determining the coordination compensation amount of each moving joint in the industrial robotic arm under sudden movement according to the coordination error between the moving joints and the guiding deviation of the end effector under mutation perception; guiding the corresponding moving joints in the industrial robotic arm to perform coordinated movement based on each coordination compensation amount.

[0016] It can be seen that in this application, first, the collaborative error between the motion joints of the industrial robotic arm is determined by combining all the jitter features with the coupling correlation relationship during transmission of each adjacent motion joint in the industrial robotic arm. By analyzing the historical motion data to extract the jitter features of each motion joint, the motion instability caused by error accumulation can be effectively reduced, ensuring stable operation for a long time in a high-intensity industrial environment and providing an accurate basis for subsequent compensation. Second, the guiding deviation of the end effector under mutation perception is determined by combining the deviation trend features of all trajectory offset points with the sudden motion of the industrial robotic arm under visual feedback. By real-time trajectory tracking and visual feedback, the adaptability of the industrial robotic arm to sudden external disturbances (such as collisions and load changes) during task execution can be enhanced, reducing the impact of sudden factors on the motion trajectory of the industrial robot and improving the stability of task execution. Then, based on the collaborative error between the motion joints and the guiding deviation of the end effector under mutation perception, the coordinated compensation amount of each motion joint in the industrial robotic arm under sudden motion is determined. This enables the industrial robotic arm to effectively adjust each motion joint according to the coordinated compensation amount when sudden motion occurs during task execution, ensuring that the subsequent compensation strategy can take into account both integrity and local accuracy, and thus avoiding overall instability of the industrial robotic arm caused by sudden errors of individual motion joints in a high-intensity environment and improving the anti-interference ability of the industrial robot, enabling it to still maintain precise control in high-dynamic tasks. Finally, based on each coordinated compensation amount, the corresponding motion joints in the industrial robotic arm are guided to perform collaborative motion, and each motion joint is synchronously adjusted using the coordinated compensation amount, ensuring the motion consistency of the industrial robotic arm and ensuring that the motion trajectory of the industrial robotic arm is smooth and continuous during long-term high-load operation, enabling it to still possess efficient and precise motion control capabilities under complex tasks. In summary, this solution can achieve stable motion control of the industrial robot in a high-intensity industrial environment based on the coordinated compensation of each motion joint of the industrial robotic arm under sudden motion. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following-described drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 is an exemplary flowchart of an industrial robot motion control method shown according to some embodiments of the present application; Figure 2 is an exemplary flowchart of determining collaborative error shown according to some embodiments of the present application; Figure 3An exemplary flowchart for determining a trajectory offset point as shown in some embodiments of the present application; Figure 4 A schematic structural diagram of an industrial robot motion control system as shown in some embodiments of the present application; Figure 5 A schematic structural diagram of a computer device for implementing an industrial robot motion control method as shown in some embodiments of the present application. Detailed implementation manners

[0019] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0020] Refer to Figure 1 , which is an exemplary flowchart of an industrial robot motion control method as shown in some embodiments of the present application. The industrial robot motion control method 100 mainly includes the following steps: In step 101, historical motion data of an industrial robotic arm is obtained, where the industrial robotic arm has multiple motion joints.

[0021] Specifically, the motion state records of the industrial robotic arm in the past six months can be obtained from the industrial cloud platform of the industrial robotic arm. The motion state records may include: motion state data of each motion joint of the industrial robotic arm (for example, motion parameters such as joint angles, speeds, accelerations, and joint torques corresponding to different time points), motion trajectory data of the end effector (for example, position coordinates, direction postures, speeds, and accelerations corresponding to different time points), and interaction information with the industrial environment (for example, load changes, collision or interference information, visual feedback, etc. corresponding to different time points). Then, the set of all obtained motion state records is used as the historical motion data of the industrial robotic arm; where the industrial cloud platform stores the long-term motion data of the industrial robotic arm, mainly covering motion data such as the motion state data of each motion joint, motion trajectory data, and environmental interaction information during the historical operation of the industrial robotic arm. In other embodiments, other methods can also be used for acquisition, which is not specifically limited here.

[0022] It should be noted that the historical motion data in the present application represents a set of motion state records of the industrial robotic arm during past motion.

[0023] In step 102, the jitter characteristics of each motion joint of the industrial robotic arm are extracted from the historical motion data, and the collaborative error between the motion joints in the industrial robotic arm is determined by combining all the jitter characteristics with the coupling correlation relationship between each adjacent motion joint during transmission in the industrial robotic arm.

[0024] In some embodiments, the extraction of the jitter characteristics of each motion joint of the industrial robotic arm from the historical motion data can be implemented by the following steps: Extract the motion state data of each motion joint in the historical motion data; Select a motion joint of the industrial robotic arm as the selected motion joint; Generate the vibration trajectory of the selected motion joint based on the motion state data of the selected motion joint; Determine the jitter characteristics of the selected motion joint from the vibration trajectory; Continue to determine the jitter characteristics of the remaining motion joints of the industrial robotic arm.

[0025] In specific implementation, the extraction of the motion state data of each motion joint in the historical motion data can be implemented in the following way, that is: the motion state data of each motion joint can be separated from the historical motion data through existing classification methods (such as: support vector machine, K-means clustering, etc.), and in other embodiments, other methods can also be used for extraction, which is not limited here; the generation of the vibration trajectory of the selected motion joint based on the motion state data of the selected motion joint can be implemented in the following way, that is: the vibration trajectory of the selected motion joint can be generated through numerical integration methods (such as Simpson integration, trapezoidal integration) based on the motion state data of the selected motion joint (such as: joint angles, speeds, accelerations, and joint torques corresponding to different time points), where each data point in the vibration trajectory reflects the vibration degree of the selected motion joint at the corresponding time point, and in other embodiments, other methods can also be used for generation, which is not limited here; the determination of the jitter characteristics of the selected motion joint from the vibration trajectory can be implemented in the following way, that is: the root mean square value of all data points in the vibration trajectory can be calculated through time domain feature analysis methods, and the fluctuation amplitude corresponding to the calculated root mean square value is used as the jitter characteristics of the selected motion joint, and in other embodiments, other methods can also be used for determination, which is not limited here.

[0026] It should be noted that the jitter feature in this application represents the degree of irregular motion caused by jitter during the motion of a moving joint. The larger the value corresponding to the jitter feature, the greater the degree of irregular motion caused by jitter during the motion of the moving joint; the smaller the value corresponding to the jitter feature, the smaller the degree of irregular motion caused by jitter during the motion of the moving joint. In addition, the motion state data in this application represents a set of motion parameters of the moving joint at different time points; the vibration trajectory in this application is a trajectory curve describing the non-stationary motion of the moving joint during the motion.

[0027] In some embodiments, referring to Figure 2 As shown, this figure is an exemplary flowchart for determining the collaborative error in some embodiments of this application. The collaborative error between the moving joints in the industrial robotic arm can be determined by combining all the jitter features with the coupling correlation relationship during the transmission of each adjacent moving joint in the industrial robotic arm, which can be achieved by the following steps: First, determine the coupling correlation relationship during the transmission of each adjacent moving joint in the industrial robotic arm through the kinematic equation; Then, based on the coupling correlation relationship during the transmission of all adjacent moving joints, determine the error transfer model between the moving joints in the industrial robotic arm; Finally, determine the collaborative error between the moving joints in the industrial robotic arm from the error transfer model between the moving joints and all the jitter features.

[0028] It should be noted that in this application, two adjacent moving joints in the industrial robotic arm are regarded as adjacent moving joints.

[0029] In specific implementation, the coupling correlation relationship between each adjacent motion joint in the industrial robotic arm during transmission can be determined through the kinematic equation in the following manner, i.e., calculating the transmission torque between each adjacent motion joint based on the kinematic equation, where the transmission torque is used to evaluate the interaction relationship between the motion joints. Then, the calculated transmission torques are respectively regarded as the coupling correlation relationship between each adjacent motion joint in the industrial robotic arm during transmission. To determine the error transfer model between the motion joints in the industrial robotic arm based on the coupling correlation relationship between all adjacent motion joints during transmission, the following method can be adopted, i.e., first, a machine learning model can be established using a linear error transfer matrix (Error Transfer Matrix, ETM). This machine learning model linearizes the dynamic equation (based on Lagrange equation or Newton-Euler equation) of the industrial robotic arm to establish an error propagation path. For example, when a motion joint jitters or has a positioning deviation, the jitter or positioning deviation will affect other joints through the connection structure and drive between the motion joints, forming an error coupling effect, which is the error propagation path. Furthermore, Monte Carlo simulation can be used to train the model with the jitter characteristics of each motion joint of the industrial robotic arm in the historical experimental data as the input of the learning machine, and the coupling correlation relationship between all adjacent motion joints during transmission as the optimization parameter of the machine learning model. Finally, the optimized machine learning model is used as the error transfer model between the motion joints in the industrial robotic arm. In other embodiments, other methods can also be used for determination, which is not limited here; to determine the collaborative error between the motion joints in the industrial robotic arm from the error transfer model between the motion joints and all the jitter characteristics, the following method can be adopted, i.e., all the jitter characteristics can be input into the error transfer model, and the error transfer model is used to analyze how the error caused by the jitter characteristics propagates and accumulates among the motion joints in the industrial robotic arm. Finally, the output of the error transfer model is used as the collaborative error between the motion joints in the industrial robotic arm. In other embodiments, other methods can also be used for determination, which is not limited here.

[0030] It should be noted that the collaborative error in this application represents the degree of incoordination of the movement of the industrial robotic arm caused by the error transmission between the moving joints. The larger the collaborative error, the greater the degree of incoordination of the movement of the industrial robotic arm caused by the error transmission between the moving joints, and the smaller the collaborative error, the smaller the degree of incoordination of the movement of the industrial robotic arm caused by the error transmission between the moving joints. The error transmission model in this application is a machine learning model used to describe the propagation path of errors between the moving joints, where the error is caused by the jitter characteristics of each moving joint of the industrial robotic arm. The coupling correlation relationship in this application represents the interaction relationship between adjacent moving joints during the movement process, that is, how one moving joint in the adjacent moving joints affects the movement state of the other moving joint, which will not be elaborated here.

[0031] In step 103, start the industrial robotic arm, perform real-time trajectory tracking on the end effector of the industrial robotic arm, obtain multiple trajectory offset points of the end effector, and determine the guiding deviation of the end effector under mutation perception by combining the offset trend characteristics of all trajectory offset points with the sudden movement of the industrial robotic arm under visual feedback.

[0032] In some embodiments, refer to Figure 3 As shown, this figure is an exemplary flowchart for determining trajectory offset points in some embodiments of this application. In this embodiment, performing real-time trajectory tracking on the end effector of the industrial robotic arm to obtain multiple trajectory offset points of the end effector can be achieved by the following steps: First, in step 1031, obtain the theoretical trajectory of the end effector of the industrial robotic arm. Secondly, in step 1032, collect the real-time actual trajectory of the end effector of the industrial robotic arm. Finally, in step 1033, compare the real-time actual trajectory with the theoretical trajectory point by point to obtain multiple trajectory offset points of the end effector.

[0033] It should be noted that the end effector of the industrial robotic arm in this application refers to the component at the very front of the industrial robotic arm, such as a mechanical hand, a welding gun, a spraying nozzle, etc., which is used to perform the specific operations of the industrial robot. In addition, the theoretical trajectory in this application represents the ideal movement path of the end effector of the industrial robotic arm. In some embodiments, the path that the end effector of the industrial robotic arm should follow can be calculated based on task planning and robotic arm kinematics through a trajectory planning algorithm, and the calculated path movement is used as the theoretical trajectory of the end effector of the industrial robotic arm. Among them, the theoretical trajectory is represented by a time-space position sequence, and each trajectory point in the theoretical trajectory contains position, attitude, speed, and acceleration information corresponding to the time point. In other embodiments, other methods can also be used to obtain it, which is not specifically limited here.

[0034] It should also be noted that the real-time actual trajectory in this application represents the actual movement path of the end effector of the industrial robotic arm; specifically, when implemented, the real-time actual trajectory of the end effector of the industrial robotic arm can be collected in the following manner, that is: after the industrial robotic arm enters the working state, the real-time actual trajectory of the end effector of the industrial robotic arm is collected in real time through an inertial measurement unit. The real-time actual trajectory is stored in the form of a time-space position sequence. Each trajectory point in the real-time actual trajectory also includes position, attitude, speed, and acceleration information corresponding to the time point. In other embodiments, other methods can also be used for collection, which will not be specifically limited here.

[0035] Specifically, when implemented, comparing the real-time actual trajectory with the theoretical trajectory point by point to obtain multiple trajectory offset points of the end effector can be achieved in the following manner, that is: the least squares fitting method can be used to compare the position, attitude, speed, and acceleration information corresponding to the time point of each trajectory point in the theoretical trajectory and the position, attitude, speed, and acceleration information corresponding to the time point of each trajectory point in the real-time actual trajectory, and the trajectory points where there is an offset between the real-time actual trajectory and the theoretical trajectory are compared. All trajectory points with offsets are used as the trajectory offset points of the end effector, so as to obtain multiple trajectory offset points of the end effector. Among them, the quantified offset between the trajectory points with offsets is used as the offset of the corresponding trajectory offset point. In other embodiments, other methods can also be used for determination, which will not be limited here.

[0036] It should be noted that the trajectory offset point in this application represents the deviation point between the actual position and the expected position of the end effector of the industrial robotic arm.

[0037] In some embodiments, determining the guiding deviation of the end effector under mutation perception by combining the offset trend characteristics of all trajectory offset points with the sudden movement of the industrial robotic arm under visual feedback can be achieved by the following steps: Determine the offset trend characteristics of all trajectory offset points; Extract the sudden movement of the industrial robotic arm under visual feedback from the interaction information between the industrial robotic arm and the industrial environment; Determine the movement offset amount of the end effector under mutation perception through the sudden movement of the industrial robotic arm under visual feedback; Determine the guiding deviation of the end effector under mutation perception from the movement offset amount under mutation perception and the offset trend characteristics.

[0038] It should be noted that the offset trend feature in this application represents the central tendency of the offset of the trajectory offset points; in this application, the sudden movement of the industrial robotic arm under visual feedback refers to the sudden movement behavior generated by the industrial robotic arm in response to the visual feedback of industrial environment changes during the task execution process, where the visual feedback refers to the industrial environment change information experienced by the industrial robotic arm during the task execution process.

[0039] In specific implementation, the offset trend feature of all trajectory offset points can be determined in the following way, that is: obtain the deviation amounts corresponding to each trajectory offset point, and then take the average value of all deviation amounts as the offset trend feature of all trajectory offset points. In other embodiments, other methods can also be used for determination, which is not limited here; extracting the sudden movement of the industrial robotic arm under visual feedback from the interaction information between the industrial robotic arm and the industrial environment can be implemented in the following way, that is: First, the interaction information between the industrial robotic arm and the industrial environment can be obtained through an artificial intelligence vision system. This interaction information includes environmental data information such as obstacles, workbenches, workpiece offsets, fixtures, and lighting changes in the industrial environment that affect the movement trajectory of the end effector of the industrial robotic arm. Then, extract the environmental data information about the industrial environment change from the interaction information as visual feedback. Finally, extract the movement generated by the industrial robotic arm under this visual feedback through the artificial intelligence vision system as the sudden movement of the industrial robotic arm under visual feedback. In other embodiments, other methods can also be used for implementation, which is not limited here.

[0040] In specific implementation, determining the movement offset amount of the end effector under mutation perception through the sudden movement of the industrial robotic arm under visual feedback can be implemented in the following way, that is: The Visual SLAM (Visual SLAM) method can be used to calculate the change in the movement vector of the end effector before and after the industrial environment change based on the sudden movement of the industrial robotic arm under visual feedback, and quantify this movement vector change as the movement offset amount of the end effector under mutation perception. In other embodiments, other methods can also be used for determination, which is not limited here; determining the guiding deviation of the end effector under mutation perception from the movement offset amount under mutation perception and the offset trend feature can be implemented in the following way, that is: The existing fusion algorithm (such as: attention mechanism fusion algorithm) can be used to perform weighted fusion on the movement offset amount under mutation perception and the offset trend feature. For example: perform weighted summation on the norm of this movement offset amount and the corresponding value of this offset trend feature, and take the finally obtained result as the guiding deviation of the end effector under mutation perception. Among them, the weights of the two can be allocated according to historical experimental experience (such as: the influence degree of each of the two on the movement deviation of the end effector of the industrial robotic arm in historical data), and the sum of the weights of the two is 1. In other embodiments, other methods can also be used for implementation, which is not limited here.

[0041] It should be noted that the mutation perception in this application refers to the motion response of an industrial robotic arm under sudden environmental changes; the motion offset in this application represents the motion change of the end effector due to environmental changes; the guiding deviation in this application refers to the motion deviation of the end effector of the industrial robotic arm due to sudden environmental mutations. Therefore, by determining this guiding deviation, the motion strategy of the industrial robotic arm can be adjusted in a timely manner to avoid collisions or task failures, improving the adaptive ability and safety of the system, which will not be elaborated here.

[0042] In step 104, the coordination compensation amount of each motion joint of the industrial robotic arm under mutation motion is determined based on the coordination error between the motion joints and the guiding deviation of the end effector under mutation perception.

[0043] In some embodiments, the determination of the coordination compensation amount of each motion joint of the industrial robotic arm under mutation motion based on the coordination error between the motion joints and the guiding deviation of the end effector under mutation perception can be achieved by the following steps: Determine the drift characteristics of each motion joint of the industrial robotic arm during the motion process based on the coordination error between the motion joints and the guiding deviation of the end effector under mutation perception; Determine the coordination compensation amount of each motion joint of the industrial robotic arm under mutation motion through the drift characteristics of each motion joint during the motion process.

[0044] Specifically, when implemented, the determination of the drift characteristics of each motion joint of the industrial robotic arm during the motion process based on the coordination error between the motion joints and the guiding deviation of the end effector under mutation perception can be achieved in the following manner, that is: the kinematic inverse solution algorithm (such as the analytical method or the numerical method) can be used to calculate the pose deviation degree of each motion joint of the industrial robotic arm during the motion process based on the coordination error between the motion joints and the end effector, and the values obtained by quantifying each pose deviation degree are correspondingly used as the drift characteristics of each motion joint of the industrial robotic arm during the motion process. In other embodiments, other methods can also be used for determination, which is not limited here.

[0045] It should be noted that the drift characteristics in this application represent the pose drift degree of the motion joints of the industrial robotic arm during the motion process. The larger the value corresponding to the drift characteristics, the greater the pose drift degree of the motion joints of the industrial robotic arm during the motion process; conversely, the smaller the value corresponding to the drift characteristics, the smaller the pose drift degree of the motion joints of the industrial robotic arm during the motion process, which will not be elaborated here.

[0046] It should also be noted that the mutation movement in this application refers to the short-term discontinuous movement of an industrial robotic arm during the execution of tasks due to changes in the working environment.

[0047] Among them, in some embodiments, determining the coordination compensation amount of each moving joint in the industrial robotic arm under mutation movement based on the drift characteristics of each moving joint during movement can be achieved by the following steps: Select a moving joint of the industrial robotic arm as the selected moving joint; Determine the contribution degree of the selected moving joint to the abnormal swing of the industrial robotic arm; Based on the drift characteristics of the selected moving joint during movement and the contribution degree, determine the coordination compensation amount of the selected moving joint in the industrial robotic arm under mutation movement; Continue to determine the coordination compensation amount of the remaining moving joints in the industrial robotic arm under mutation movement.

[0048] Specifically, when implemented, determining the contribution degree of the selected moving joint to the abnormal swing of the industrial robotic arm can be achieved in the following manner, that is: based on the error regression analysis combined with the analysis framework of the kinematics-dynamics coupling model, calculate the influence ratio of the movement error of the selected moving joint on the abnormal swing of the industrial robotic arm through simulation, and use the obtained influence ratio as the contribution degree of the selected moving joint to the abnormal swing of the industrial robotic arm. In other embodiments, other methods can also be used for determination, which is not limited here; based on the drift characteristics of the selected moving joint during movement and the contribution degree, determining the coordination compensation amount of the selected moving joint in the industrial robotic arm under mutation movement can be achieved in the following manner, that is: the model predictive control or deep reinforcement learning method can be used to calculate the correction values of the angle, torque, and speed for adjusting the movement error of the selected moving joint when the industrial robotic arm has an abnormal swing based on the calculated drift characteristics of the selected moving joint during movement and the contribution degree, and use the set of all obtained correction values as the coordination compensation amount of the selected moving joint in the industrial robotic arm under mutation movement.

[0049] It should be noted that the coordination compensation amount in this application represents the correction index for adjusting the coordinated movement of the moving joints of the industrial robotic arm; in addition, the contribution degree in this application represents the influence degree of the movement error of the moving joint on the abnormal swing of the industrial robotic arm. The higher the contribution degree, the greater the influence degree of the movement error of the moving joint on the abnormal swing of the industrial robotic arm. On the contrary, the lower the contribution degree, the smaller the influence degree of the movement error of the moving joint on the abnormal swing of the industrial robotic arm.

[0050] In step 105, based on each coordination compensation amount, guide the corresponding moving joints in the industrial robotic arm to perform coordinated movement.

[0051] In specific implementation, guiding the corresponding motion joints in the industrial robotic arm to perform collaborative motion based on each coordination compensation amount can be achieved in the following manner, that is: First, a distributed control architecture can be utilized. Through adaptive neural network control, each coordination compensation amount is decomposed into the PID control parameter increments of the motors of the corresponding motion joints. For example: First, the control tasks of each motion joint of the industrial robotic arm are dispersed to multiple control nodes, and each control node is responsible for controlling one motion joint of the industrial robotic arm. Then, the adaptive neural network further decomposes each coordination compensation amount into the PID control parameter increments of the motors of each motion joint by using its nonlinear approximation ability and adaptive learning ability. Then, through a real-time communication protocol (such as EtherCAT, an Ethernet for controlling automation technology), the decomposed PID control parameter increments are synchronously sent down to the joint drivers of the corresponding motion joints. The joint drivers dynamically adjust the rotation angle or displacement of the motors of the corresponding motion joints according to the received PID control parameter increments, thereby guiding the various motion joints in the industrial robotic arm to perform collaborative motion to achieve the motion stability and high-precision motion control of the industrial robotic arm.

[0052] In addition, on the other hand of the present application, in some embodiments, the present application provides an industrial robot motion control system. Refer to Figure 4 , which is a schematic structural diagram of an industrial robot motion control system shown according to some embodiments of the present application. The industrial robot motion control system 400 includes: an acquisition module 401, a processing module 402, and an execution module 403, which are described as follows: The acquisition module 401. In the present application, the acquisition module 401 is mainly used to acquire the historical motion data of the industrial robotic arm, where the industrial robotic arm has multiple motion joints; The processing module 402. In the present application, the processing module 402 is mainly used to extract the jitter characteristics of each motion joint of the industrial robotic arm from the historical motion data, and determine the collaborative error between the motion joints in the industrial robotic arm by combining all the jitter characteristics with the coupling correlation relationship between each adjacent motion joint in the industrial robotic arm during transmission; In the present application, the processing module 402 is further used to start the industrial robotic arm, perform real-time trajectory tracking on the end effector of the industrial robotic arm, obtain multiple trajectory offset points of the end effector, and determine the guiding deviation of the end effector under mutation perception by combining the offset trend characteristics of all the trajectory offset points with the sudden motion of the industrial robotic arm under visual feedback; In the present application, the processing module 402 is further used to determine the coordination compensation amount of each motion joint in the industrial robotic arm under mutation motion based on the collaborative error between the motion joints and the guiding deviation of the end effector under mutation perception; Execution module 403. In this application, the execution module 403 is mainly used to guide the corresponding motion joints in the industrial robotic arm to perform coordinated motion based on each coordination compensation amount.

[0053] The above has introduced in detail the examples of the industrial robot motion control method, system, device and medium provided by the embodiments of this application. It can be understood that, correspondingly, in order to implement the above functions, the device includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed in this article, this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but this implementation should not be considered to exceed the scope of this application.

[0054] In some embodiments, this application also provides a computer device, which includes a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned industrial robot motion control method.

[0055] In some embodiments, referring to Figure 5 In the figure, the dotted line indicates that the unit or the module is optional. This figure is a schematic structural diagram of a computer device for implementing the industrial robot motion control method of this application. The industrial robot motion control method in the above embodiments can be implemented by Figure 5 the computer device shown. The computer device 500 includes at least one processor 501, a memory 502, and at least one communication unit 505. The computer device 500 can be a terminal device, a server, or a chip.

[0056] The processor 501 can be a general-purpose processor or a dedicated processor. For example, the processor 501 can be a central processing unit (CPU). The CPU can be used to control the computer device 500, execute software programs, and process the data of software programs. The computer device 500 can also include a communication unit 505 for realizing the input (receiving) and output (sending) of signals.

[0057] For example, the computer device 500 can be a chip, and the communication unit 505 can be the input and / or output circuit of the chip, or the communication unit 505 can be the communication interface of the chip. The chip can be used as a component of a terminal device, a network device, or other devices.

[0058] For another example, the computer device 500 may be a terminal device or a server, the communication unit 505 may be a transceiver of the terminal device or the server, or the communication unit 505 may be a transceiver circuit of the terminal device or the server.

[0059] The computer device 500 may include one or more memories 502, on which a program 504 is stored. The program 504 can be run by the processor 501 to generate instructions 503, so that the processor 501 executes the method described in the above method embodiments according to the instructions 503. Optionally, data (such as a target audit model) may also be stored in the memory 502. Optionally, the processor 501 may also read the data stored in the memory 502. The data may be stored at the same storage address as the program 504, or the data may be stored at a different storage address from the program 504.

[0060] The processor 501 and the memory 502 may be provided separately or integrated together. For example, they may be integrated on a system on chip (SOC) of the terminal device.

[0061] It should be understood that the steps of the above method embodiments can be completed by a logic circuit in the form of hardware or instructions in the form of software in the processor 501. The processor 501 may be a CPU, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices. For example, discrete gates, transistor logic devices, or discrete hardware components.

[0062] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0063] For example, in some embodiments, the present application further provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer is caused to implement the above industrial robot motion control method when executed.

[0064] Although the preferred embodiments of the present application have been described, additional changes and modifications can be made to these embodiments by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0065] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. An industrial robot motion control method, characterized in that, The method includes the following steps: Obtain the historical motion data of an industrial robotic arm, where the industrial robotic arm has multiple motion joints; Extract the jitter characteristics of each motion joint of the industrial robotic arm from the historical motion data, and determine the collaborative error between the motion joints in the industrial robotic arm by combining all the jitter characteristics with the coupling correlation relationship between each adjacent motion joint in the industrial robotic arm during transmission; Start the industrial robotic arm, perform real-time trajectory tracking on the end effector of the industrial robotic arm to obtain multiple trajectory offset points of the end effector, and determine the guiding deviation of the end effector under mutation perception by combining the offset trend characteristics of all the trajectory offset points with the sudden motion of the industrial robotic arm under visual feedback; Determine the coordinated compensation amount of each motion joint in the industrial robotic arm under sudden motion based on the collaborative error between the motion joints and the guiding deviation of the end effector under mutation perception; Based on each coordinated compensation amount, guide the corresponding motion joints in the industrial robotic arm to perform collaborative motion.

2. The method according to claim 1, wherein Specifically, extracting the jitter characteristics of each motion joint of the industrial robotic arm from the historical motion data includes: Extract the motion state data of each motion joint from the historical motion data; Select a motion joint of the industrial robotic arm as the selected motion joint; Generate a vibration trajectory of the selected motion joint based on the motion state data of the selected motion joint; Determine the jitter characteristics of the selected motion joint from the vibration trajectory; Continue to determine the jitter characteristics of the remaining motion joints of the industrial robotic arm.

3. The method according to claim 1, characterized in that, Specifically, determining the collaborative error between the motion joints in the industrial robotic arm by combining all the jitter characteristics with the coupling correlation relationship between each adjacent motion joint in the industrial robotic arm during transmission includes: Determine the coupling correlation relationship between each adjacent motion joint in the industrial robotic arm during transmission through the kinematic equation; Determine the error transfer model between the motion joints in the industrial robotic arm based on the coupling correlation relationship between all adjacent motion joints during transmission; Determine the collaborative error between the motion joints in the industrial robotic arm from the error transfer model between the motion joints and all the jitter characteristics.

4. The method according to claim 1, wherein Specifically, performing real-time trajectory tracking on the end effector of the industrial robotic arm to obtain multiple trajectory offset points of the end effector includes: Obtain the theoretical trajectory of the end effector of the industrial robotic arm; Collect the real-time actual trajectory of the end effector of the industrial robotic arm; Compare the real-time actual trajectory with the theoretical trajectory point by point to obtain multiple trajectory offset points of the end effector.

5. The method according to claim 1, characterized in that, Specifically, determining the guiding deviation of the end effector under mutation perception by combining the offset trend characteristics of all the trajectory offset points with the sudden motion of the industrial robotic arm under visual feedback includes: Determine the offset trend characteristics of all the trajectory offset points; Extract the sudden motion of the industrial robotic arm under visual feedback from the interaction information between the industrial robotic arm and the industrial environment; Determine the motion offset amount of the end effector under mutation perception from the sudden motion of the industrial robotic arm under visual feedback; Determine the guiding deviation of the end effector under mutation perception based on the motion offset under mutation perception and the offset trend feature.

6. The method according to claim 1, wherein Determining the coordinated compensation amounts of the respective motion joints of the industrial robotic arm during mutation motion based on the collaborative error between the motion joints and the guiding deviation of the end effector under mutation perception specifically includes: Determine the drift characteristics of the respective motion joints of the industrial robotic arm during the motion process based on the collaborative error between the motion joints and the guiding deviation of the end effector under mutation perception; Determine the coordinated compensation amounts of the respective motion joints of the industrial robotic arm during mutation motion based on the drift characteristics of the respective motion joints during the motion process.

7. The method according to claim 6, wherein Determining the coordinated compensation amounts of the respective motion joints of the industrial robotic arm during mutation motion based on the drift characteristics of the respective motion joints during the motion process specifically includes: Select a motion joint of the industrial robotic arm as the selected motion joint; Determine the contribution degree of the selected motion joint to the abnormal swing of the industrial robotic arm; Determine the coordinated compensation amount of the selected motion joint of the industrial robotic arm during mutation motion based on the drift characteristics of the selected motion joint during the motion process and the contribution degree; Continue to determine the coordinated compensation amounts of the remaining motion joints of the industrial robotic arm during mutation motion.

8. An industrial robot motion control system, characterized in that, Including: An acquisition module, configured to acquire historical motion data of an industrial robotic arm, where the industrial robotic arm has a plurality of motion joints; A processing module, configured to extract the jitter characteristics of the respective motion joints of the industrial robotic arm from the historical motion data, and determine the collaborative error between the motion joints of the industrial robotic arm by combining all the jitter characteristics with the coupling correlation relationship between each adjacent motion joint in the industrial robotic arm during transmission; The processing module is further configured to start the industrial robotic arm, perform real-time trajectory tracking on the end effector of the industrial robotic arm, obtain a plurality of trajectory offset points of the end effector, and determine the guiding deviation of the end effector under mutation perception by combining the offset trend characteristics of all the trajectory offset points with the sudden motion of the industrial robotic arm under visual feedback; The processing module is further configured to determine the coordinated compensation amounts of the respective motion joints of the industrial robotic arm during mutation motion based on the collaborative error between the motion joints and the guiding deviation of the end effector under mutation perception; An execution module, configured to guide the corresponding motion joints of the industrial robotic arm to perform collaborative motion based on the respective coordinated compensation amounts.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the industrial robot motion control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that Instructions or codes are stored in the computer-readable storage medium, and when the instructions or codes are run on a computer, the computer is caused to execute the industrial robot motion control method according to any one of claims 1 to 7.

Images