Industrial robot motion control method, system, device and medium

Abstract

The present application provides an industrial robot motion control method, system, device, and medium. The method extracts the jitter characteristics of each motion joint of an industrial robot arm from historical motion data, and determines the coordination error between each motion joint in the industrial robot arm by combining all the jitter characteristics with the coupling relationship between each adjacent motion joint in the industrial robot arm during transmission. The method also determines multiple trajectory offset points of the end effector, and determines the guidance deviation of the end effector under sudden motion perception based on the offset trend characteristics of all trajectory offset points. The method also determines the coordination compensation amount of each motion joint in the industrial robot arm under sudden motion based on the coordination error and the guidance deviation under sudden motion perception. The method also guides the corresponding motion joints in the industrial robot arm to perform coordinated motion based on each coordination compensation amount. By adopting the scheme of the present application, stable motion control of the industrial robot in a high-intensity industrial environment can be achieved based on the coordinated compensation of each motion joint of the industrial robot arm under sudden motion.

Description

Technical Field

[0001] The present application relates to the field of industrial robot control technology, and more specifically, to an industrial robot motion control method, system, device and medium. Background Art

[0002] An industrial robot is an automated, multi-degree-of-freedom programmable mechanical device used to perform repetitive, 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. It is an important part of intelligent manufacturing.

[0003] With the development of industrial automation, the requirements for the motion accuracy and adaptability of industrial robots are becoming increasingly higher. In order to achieve precise motion trajectories, industrial robot motion control methods are constantly evolving, mainly involving technologies such as path planning, trajectory tracking, servo control, and force and position coordinated control. However, in the existing technology, industrial robots need to frequently perform high-speed and precise operations in high-intensity industrial environments. In the process of performing high-intensity industrial tasks, industrial robots often face various emergencies, which leads to asynchronous motion of the various motion joints in the industrial robot arm, which in turn causes abnormal motion of the industrial robot arm. In addition, there is error transmission between the various motion joints. When a motion error occurs in a motion joint due to inertia, friction or load changes, the motion error will accumulate in the entire industrial robot arm structure, causing the trajectory of the industrial robot end effector to deviate from the expected one, thereby affecting the smoothness of the overall motion 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 high-intensity industrial environments based on coordinated compensation of the various motion joints of the industrial robot arm under sudden motion has become a difficult problem faced by the industry. Summary of the Invention

[0004] The present application provides an industrial robot motion control method, system, device and medium, which 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 robot arm under sudden motion.

[0005] In a first aspect, the present application provides an industrial robot motion control method, comprising the following steps:

[0006] Acquiring historical motion data of an industrial robotic arm, wherein the industrial robotic arm has multiple motion joints;

[0007] Extracting jitter characteristics of each motion joint of the industrial robot arm from the historical motion data, and determining the coordination error between the motion joints of the industrial robot arm by combining all the jitter characteristics with the coupling relationship of each adjacent motion joint in the industrial robot arm during transmission;

[0008] The industrial robotic arm is activated, and a real-time trajectory tracking is performed on the end effector of the industrial robotic arm to obtain multiple trajectory offset points of the end effector. The guidance deviation of the end effector under sudden change perception is determined based on the offset trend characteristics of all trajectory offset points and the sudden movement of the industrial robotic arm under visual feedback;

[0009] Determining the coordination compensation amount of each moving joint in the industrial robot arm under sudden motion according to the coordination error between each moving joint and the guidance deviation of the end effector under sudden motion perception;

[0010] Based on each coordinated compensation amount, the corresponding motion joints in the industrial robot arm are guided to perform coordinated motion.

[0011] In some embodiments, extracting the jitter characteristics of each motion joint of the industrial robot arm from the historical motion data specifically includes:

[0012] Extracting motion state data of each motion joint from the historical motion data;

[0013] Selecting a motion joint of the industrial robot arm as a selected motion joint;

[0014] generating a vibration trajectory of the selected motion joint based on the motion state data of the selected motion joint;

[0015] determining a jitter characteristic of a selected motion joint from the vibration trajectory;

[0016] Continue to determine the jitter characteristics of the remaining motion joints of the industrial robot arm.

[0017] In some embodiments, determining the coordination error between the motion joints in the industrial robot arm by combining all the jitter characteristics with the coupling relationship of each adjacent motion joint in the industrial robot arm during transmission specifically includes:

[0018] Determine the coupling relationship between each adjacent motion joint in the industrial robot arm during transmission through kinematic equations;

[0019] Determining an error transmission model between the motion joints in the industrial robot arm based on the coupling relationship between all adjacent motion joints during transmission;

[0020] The coordination errors between the motion joints in the industrial robot arm are determined based on the error transfer model between the motion joints and all the jitter characteristics.

[0021] In some embodiments, performing real-time trajectory tracking on the end effector of the industrial robot arm to obtain multiple trajectory offset points of the end effector specifically includes:

[0022] Obtaining a theoretical trajectory of the end effector of the industrial robot arm;

[0023] Collecting the real-time actual trajectory of the end effector of the industrial robot arm;

[0024] The real-time actual trajectory is compared point by point with the theoretical trajectory to obtain a plurality of trajectory offset points of the end effector.

[0025] In some embodiments, determining the guidance deviation of the end effector under sudden change perception by combining the deviation trend characteristics of all trajectory deviation points with the sudden movement of the industrial robot arm under visual feedback specifically includes:

[0026] Determine the deviation trend characteristics of all trajectory deviation points;

[0027] Extract the sudden movement of the industrial robot under visual feedback from the interaction information between the industrial robot and the industrial environment;

[0028] Determining the motion offset of the end effector under sudden change perception through the sudden movement of the industrial robot arm under visual feedback;

[0029] The guidance deviation of the end effector under sudden change perception is determined based on the motion offset under sudden change perception and the offset trend feature.

[0030] In some embodiments, determining the coordination compensation amount of each moving joint in the industrial robot arm under sudden motion based on the coordination error between each moving joint and the guidance deviation of the end effector under sudden motion perception specifically includes:

[0031] Determining drift characteristics of each moving joint of the industrial robot arm during movement based on the coordination errors between the moving joints and the guidance deviation of the end effector under sudden change perception;

[0032] The coordinated compensation amount of each moving joint in the industrial robot arm under sudden motion is determined by the drift characteristics of each moving joint during the motion process.

[0033] In some embodiments, determining the coordination compensation amount of each moving joint in the industrial robot arm under sudden motion based on the drift characteristics of each moving joint during motion specifically includes:

[0034] Selecting a motion joint of the industrial robot arm as a selected motion joint;

[0035] determining a contribution of a selected motion joint to the abnormal swing of the industrial robot arm;

[0036] Determining a coordination compensation amount of a selected motion joint in the industrial robot arm under sudden motion based on a drift characteristic of the selected motion joint during motion and the contribution;

[0037] Continue to determine the coordination compensation amount of the remaining moving joints in the industrial robot arm under the sudden movement.

[0038] In a second aspect, the present application provides an industrial robot motion control system, comprising:

[0039] an acquisition module, configured to acquire historical motion data of an industrial robotic arm, wherein the industrial robotic arm has a plurality of motion joints;

[0040] a processing module, configured to extract jitter characteristics of each motion joint of the industrial robot arm from the historical motion data, and determine the coordination error between the motion joints of the industrial robot arm by combining all the jitter characteristics with the coupling relationship between each adjacent motion joint of the industrial robot arm during transmission;

[0041] The processing module is further configured to start the industrial robot arm, perform real-time trajectory tracking on the end effector of the industrial robot arm, obtain multiple trajectory offset points of the end effector, and determine the guidance deviation of the end effector under sudden change perception based on the offset trend characteristics of all trajectory offset points and the sudden movement of the industrial robot arm under visual feedback;

[0042] The processing module is further configured to determine a coordination compensation amount of each moving joint in the industrial robot arm under sudden motion according to the coordination error between each moving joint and the guidance deviation of the end effector under sudden motion perception;

[0043] The execution module is used to guide the corresponding motion joints in the industrial robot arm to perform coordinated motion based on each coordinated compensation amount.

[0044] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein 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.

[0045] 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 implements the above-mentioned industrial robot motion control method when executed.

[0046] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0047] In the present application, historical motion data of an industrial robot arm is obtained, wherein the industrial robot arm has multiple motion joints; jitter characteristics of each motion joint of the industrial robot arm are extracted from the historical motion data, and the coordination error between each motion joint in the industrial robot arm is determined by combining all the jitter characteristics with the coupling association relationship of each adjacent motion joint in the industrial robot arm during transmission; the industrial robot arm is started, and the end effector of the industrial robot arm is tracked in real time to obtain multiple trajectory offset points of the end effector, and the guidance deviation of the end effector under sudden motion perception is determined by combining the offset trend characteristics of all trajectory offset points with the sudden motion of the industrial robot arm under visual feedback; the coordination compensation amount of each motion joint in the industrial robot arm under sudden motion is determined based on the coordination error between each motion joint and the guidance deviation of the end effector under sudden motion perception; and the corresponding motion joints in the industrial robot arm are guided to perform coordinated motion based on each coordination compensation amount.

[0048] It can be seen that in this application, firstly, the coordination error between the motion joints in the industrial robot arm is determined by combining all the jitter characteristics with the coupling correlation relationship of each adjacent motion joint in the industrial robot arm during transmission, and the jitter characteristics of each motion joint are extracted by analyzing the historical motion data, which can effectively reduce the motion instability caused by error accumulation, ensure long-term stable operation in a high-intensity industrial environment, and provide an accurate basis for subsequent compensation; secondly, the offset trend characteristics of all trajectory offset points are combined with the sudden movement of the industrial robot arm under visual feedback to determine the guidance deviation of the end effector under sudden change perception, and the adaptability of the industrial robot arm to sudden external interference (such as collision, load change) during the execution of the task is enhanced through real-time trajectory tracking and visual feedback, which can reduce the impact of sudden factors on the motion trajectory of the industrial robot and improve the stability of task execution; then, the industrial robot is determined based on the coordination error between the motion joints and the guidance deviation of the end effector under sudden change perception. The coordinated compensation amount of each moving joint in the arm under sudden motion can enable the industrial robot arm to effectively adjust each moving joint according to the coordinated compensation amount when sudden motion occurs during the execution of the task, which can ensure that the subsequent compensation strategy can take into account both overall and local accuracy, and thus avoid the overall instability of the industrial robot arm due to sudden errors of individual moving joints in a high-intensity environment, improve the anti-interference ability of the industrial robot, and enable it to maintain precise control in high-dynamic tasks; finally, based on each coordinated compensation amount, the corresponding moving joints in the industrial robot arm are guided to move in coordination, and the coordinated compensation amount is used to synchronously adjust each moving joint, thereby ensuring the motion consistency of the industrial robot arm and ensuring that the motion trajectory of the industrial robot arm is smooth and continuous during long-term high-load work, so that it still has efficient and precise motion control capabilities under complex tasks; in summary, this scheme can realize stable motion control of the industrial robot in a high-intensity industrial environment based on the coordinated compensation of each moving joint of the industrial robot arm under sudden motion. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0050] Figure 1 is an exemplary flow chart of an industrial robot motion control method according to some embodiments of the present application;

[0051] Figure 2 is an exemplary flow chart of determining a coordination error according to some embodiments of the present application;

[0052] Figure 3 is an exemplary flow chart for determining trajectory offset points according to some embodiments of the present application;

[0053] Figure 4 is a schematic structural diagram of an industrial robot motion control system according to some embodiments of the present application;

[0054] Figure 5 It is a structural diagram of a computer device for implementing an industrial robot motion control method according to some embodiments of the present application. DETAILED DESCRIPTION

[0055] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0056] refer to Figure 1 , which is an exemplary flow chart of an industrial robot motion control method according to some embodiments of the present application. The industrial robot motion control method 100 mainly includes the following steps:

[0057] In step 101 , historical motion data of an industrial robot arm is obtained, wherein the industrial robot arm has multiple motion joints.

[0058] In specific implementation, the motion state records of the industrial robot arm in the past six months can be obtained from the industrial cloud platform of the industrial robot arm. The motion state records may include: motion state data of each motion joint of the industrial robot arm (for example, motion parameters such as joint angle, speed, acceleration and joint torque corresponding to different time points), motion trajectory data of the end effector (for example, position coordinates, direction posture, speed and acceleration corresponding to different time points, etc.) and interaction information with the industrial environment (for example, load changes, collision or interference information, visual feedback, etc. corresponding to different time points), and then the collection of all obtained motion state records is used as the historical motion data of the industrial robot arm; wherein, the industrial cloud platform stores the long-term motion data of the industrial robot arm, mainly covering motion data such as motion state data, motion trajectory data and environmental interaction information of each motion joint of the industrial robot arm during historical operation, wherein; in other embodiments, other methods can also be used for acquisition, which is not specifically limited here.

[0059] It should be noted that the historical motion data in this application represents a collection of motion state records of the industrial robot arm during its past motion processes.

[0060] In step 102, the jitter characteristics of each moving joint of the industrial robot arm are extracted from the historical motion data, and the coordination error between the moving joints in the industrial robot arm is determined by combining all the jitter characteristics with the coupling relationship between each adjacent moving joint in the industrial robot arm during transmission.

[0061] In some embodiments, extracting the jitter characteristics of each motion joint of the industrial robot arm from the historical motion data can be achieved by using the following steps:

[0062] Extracting motion state data of each motion joint from the historical motion data;

[0063] Selecting a motion joint of the industrial robot arm as a selected motion joint;

[0064] generating a vibration trajectory of the selected motion joint based on the motion state data of the selected motion joint;

[0065] determining a jitter characteristic of a selected motion joint from the vibration trajectory;

[0066] Continue to determine the jitter characteristics of the remaining motion joints of the industrial robot arm.

[0067] In specific implementation, the motion state data of each motion joint in the historical motion data can be extracted in the following manner, namely, the motion state data of each motion joint can be separated from the historical motion data by an existing classification method (for example, support vector machine, K-means clustering, etc.). In other embodiments, other methods can also be used for extraction, which are not limited here; the vibration trajectory of the selected motion joint based on the motion state data of the selected motion joint can be generated in the following manner, namely, the motion state data of the selected motion joint (for example, joint angle, speed, acceleration corresponding to different time points) can be generated by a numerical integration method (such as Simpson integration, trapezoidal integration). speed and joint torque, etc.) to generate a vibration trajectory of the selected motion joint, wherein each data point in the vibration trajectory reflects the vibration degree of the selected motion joint at the corresponding time point. In other embodiments, other methods can also be used to generate it, which is not limited here; determining the jitter characteristics of the selected motion joint from the vibration trajectory can be achieved in the following manner, namely: the root mean square value of all data points in the vibration trajectory can be calculated by a time domain feature analysis method, the root mean square value measures the fluctuation amplitude of the vibration trajectory, and the fluctuation amplitude corresponding to the calculated root mean square value is used as the jitter characteristic of the selected motion joint. In other embodiments, other methods can also be used to determine it, which is not limited here.

[0068] It should be noted that the jitter feature in the present application represents the degree of irregular movement of the moving joint caused by jitter during the movement process. The larger the numerical value corresponding to the jitter feature, the greater the degree of irregular movement of the moving joint caused by jitter during the movement process. The smaller the numerical value corresponding to the jitter feature, the smaller the degree of irregular movement of the moving joint caused by jitter during the movement process. In addition, the motion state data in the present application represents a set of motion parameters of the moving joint at different time points. The vibration trajectory in the present application is a trajectory curve that describes the non-stationary motion of the moving joint during the movement process.

[0069] In some embodiments, reference Figure 2 As shown in FIG. 1 , this figure is an exemplary flow chart for determining the coordination error in some embodiments of the present application. The coordination error between the motion joints in the industrial robot arm is determined by combining all the jitter characteristics with the coupling relationship between each adjacent motion joint in the industrial robot arm during transmission. The following steps can be used:

[0070] First, the coupling relationship between each adjacent motion joint in the industrial robot arm during transmission is determined through kinematic equations;

[0071] Then, an error transmission model between the motion joints in the industrial robot arm is determined based on the coupling relationship between all adjacent motion joints during transmission;

[0072] Finally, the coordination errors between the motion joints in the industrial robot arm are determined based on the error transfer model between the motion joints and all the jitter characteristics.

[0073] It should be noted that, in this application, two adjacent motion joints in an industrial robot arm are referred to as adjacent motion joints.

[0074] In a specific implementation, the coupling relationship between each adjacent motion joint in the industrial robot arm during transmission is determined by the kinematic equation, which can be implemented in the following manner: based on the kinematic equation, the transmission torque between each adjacent motion joint is calculated, and the transmission torque is used to evaluate the interaction relationship between the motion joints, and then the calculated transmission torques are used as the coupling relationship between each adjacent motion joint in the industrial robot arm during transmission. Based on the coupling relationship of all adjacent motion joints during transmission, the error transfer model between each motion joint in the industrial robot arm can be implemented in the following manner, namely: first, a linear error transfer matrix (Error Transfer A machine learning model is established based on the ETM (Electronic Math Matrix), which linearizes the dynamic equations of the industrial robot arm (based on the Lagrange equation or the Newton-Euler equation) to establish an error propagation path. For example, when a motion joint vibrates or has a positioning deviation, the vibration or positioning deviation will affect other joints through the connection structure and drive between the motion joints, forming an error coupling effect. The error coupling effect is the error propagation path. Furthermore, Monte Carlo simulation can be used to take the vibration characteristics of each motion joint of the industrial robot arm in the historical experimental data as the input of the learning machine for model training, and the coupling correlation relationship of all adjacent motion joints during transmission is used as the optimization parameter of the machine learning model. Finally, the optimization The obtained machine learning model is used as the error transfer model between the various moving joints in the industrial robot arm. Other methods can also be used to determine it in other embodiments, which is not limited here. The collaborative error between the various moving joints in the industrial robot arm determined by the error transfer model between the various moving joints and all jitter characteristics can be achieved in the following manner, namely: all jitter characteristics can be input into the error transfer model, and the error transfer model is used to analyze how the errors caused by the jitter characteristics propagate and accumulate between the various moving joints in the industrial robot arm, and finally the output of the error transfer model is used as the collaborative error between the various moving joints in the industrial robot arm. Other methods can also be used to determine it in other embodiments, which is not limited here.

[0075] It should be noted that the coordination error in this application represents the degree of incoordination of the industrial robot arm movement caused by the error transmission between the moving joints. The larger the coordination error, the greater the degree of incoordination of the industrial robot arm movement caused by the error transmission between the moving joints, and the smaller the coordination error, the smaller the degree of incoordination of the industrial robot arm movement caused by the error transmission between the moving joints. The error transmission model in this application is a machine learning model for describing the propagation path of the error between the moving joints, wherein the error is caused by the jitter characteristics of each moving joint of the industrial robot arm. The coupling association relationship in this application represents the interaction relationship between adjacent moving joints during the movement process. The interaction relationship is: how one of the adjacent moving joints affects the movement state of another moving joint, which will not be repeated here.

[0076] In step 103, the industrial robot arm is started, and the real-time trajectory tracking of the end effector of the industrial robot arm is performed to obtain multiple trajectory offset points of the end effector. The offset trend characteristics of all trajectory offset points are combined with the sudden movement of the industrial robot arm under visual feedback to determine the guidance deviation of the end effector under sudden change perception.

[0077] In some embodiments, reference Figure 3 As shown in FIG. 1 , this figure is an exemplary flow chart for determining trajectory offset points in some embodiments of the present application. In this embodiment, real-time trajectory tracking is performed on the end effector of the industrial robot arm, and obtaining multiple trajectory offset points of the end effector can be achieved by using the following steps:

[0078] First, in step 1031 , a theoretical trajectory of the end effector of the industrial robot arm is obtained;

[0079] Next, in step 1032 , the real-time actual trajectory of the end effector of the industrial robot arm is collected;

[0080] Finally, in step 1033 , the real-time actual trajectory is compared point by point with the theoretical trajectory to obtain a plurality of trajectory offset points of the end effector.

[0081] It should be noted that the industrial robot arm end effector in this application refers to the front-end component of the industrial robot arm, such as: manipulator, welding gun, spray nozzle, etc., which is used to perform specific operations of the industrial robot; in addition, the theoretical trajectory in this application represents the ideal motion path of the industrial robot arm end effector. In some embodiments, the path along which the industrial robot arm end effector should move can be calculated based on task planning and robot arm kinematics through a trajectory planning algorithm, and the calculated path motion is used as the theoretical trajectory of the industrial robot arm end effector, wherein the theoretical trajectory is represented by a time-space position sequence, and each trajectory point in the theoretical trajectory contains the position, posture, velocity and acceleration information of the corresponding time point. In other embodiments, other methods may also be used to obtain the information, which is not specifically limited here.

[0082] It should also be noted that the real-time actual trajectory in this application represents the actual motion path of the end effector of the industrial robot arm; in specific implementation, the real-time actual trajectory of the end effector of the industrial robot arm can be collected in the following manner, namely: after the industrial robot arm enters the working state, the real-time actual trajectory of the end effector of the industrial robot arm is collected in real time through the 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 the position, posture, velocity and acceleration information of the corresponding time point. In other embodiments, other methods can also be used for collection, which is not specifically limited here.

[0083] In a specific implementation, the real-time actual trajectory is compared point by point with the theoretical trajectory to obtain multiple trajectory offset points of the end effector. This can be achieved in the following manner: a least squares fitting method can be used based on the position, posture, velocity and acceleration information of each trajectory point in the theoretical trajectory at a corresponding time point and the position, posture, velocity and acceleration information of each trajectory point in the real-time actual trajectory at a corresponding time point to compare the trajectory points with the theoretical trajectory. All trajectory points with offsets are used as trajectory offset points of the end effector, thereby obtaining multiple trajectory offset points of the end effector, wherein the quantized 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 is not limited here.

[0084] 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 robot arm.

[0085] In some embodiments, determining the guidance deviation of the end effector under sudden motion perception by combining the deviation trend characteristics of all trajectory deviation points with the sudden motion of the industrial robot arm under visual feedback can be achieved by the following steps:

[0086] Determine the deviation trend characteristics of all trajectory deviation points;

[0087] Extract the sudden movement of the industrial robot under visual feedback from the interaction information between the industrial robot and the industrial environment;

[0088] Determining the motion offset of the end effector under sudden change perception through the sudden movement of the industrial robot arm under visual feedback;

[0089] The guidance deviation of the end effector under sudden change perception is determined based on the motion offset under sudden change perception and the offset trend feature.

[0090] It should be noted that the offset trend feature in this application represents the centralized trend of the offset of the trajectory offset point; in this application, the sudden movement of the industrial robot arm under visual feedback refers to the sudden movement behavior generated by the industrial robot arm in response to the visual feedback of the industrial environment changes in the process of performing the task, wherein the visual feedback refers to the industrial environment change information experienced by the industrial robot arm in the process of performing the task.

[0091] In specific implementation, determining the offset trend characteristics of all trajectory offset points can be achieved in the following manner, namely: obtaining the deviation amount corresponding to each trajectory offset point, and then taking the average value of all deviation amounts as the offset trend characteristics 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 robot arm under visual feedback from the interaction information between the industrial robot arm and the industrial environment can be achieved in the following manner, namely: first, the interaction information between the industrial robot arm and the industrial environment can be obtained through the artificial intelligence vision system. The interaction information includes environmental data information such as obstacles, workbenches, workpiece offsets, fixtures, and lighting changes in the industrial environment that affect the motion trajectory of the end effector of the industrial robot arm. Then, environmental data information about changes in the industrial environment is extracted from the interaction information as visual feedback. Finally, the movement generated by the industrial robot arm under the visual feedback is extracted through the artificial intelligence vision system as the sudden movement of the industrial robot arm under visual feedback. In other embodiments, other methods can also be used for implementation, which is not limited here.

[0092] In a specific implementation, the motion offset of the end effector under sudden change perception can be determined by the sudden movement of the industrial robot arm under visual feedback in the following manner, namely: Visual SLAM (Visual The SLAM method calculates the change in motion vector of the end effector before and after the industrial environment changes based on the sudden motion of the industrial robot arm under visual feedback, and quantifies the change in motion vector as the motion offset of the end effector under sudden change perception. In other embodiments, other methods may be used for determination, which is not limited here. Determining the guidance deviation of the end effector under sudden change perception from the motion offset under sudden change perception and the offset trend feature can be achieved in the following manner, namely, weighted fusion of the motion offset under sudden change perception and the offset trend feature can be performed using an existing fusion algorithm (such as an attention mechanism fusion algorithm). For example, a weighted summation of the modulus of the motion offset and the value corresponding to the offset trend feature is performed, and the final result is used as the guidance deviation of the end effector under sudden change perception. The weights of the two can be assigned based on historical experimental experience (such as the degree of influence of each on the motion deviation of the industrial robot arm end effector in historical data), and the sum of the weights of the two is 1. In other embodiments, other methods may be used for implementation, which is not limited here.

[0093] It should be noted that the mutation perception in this application refers to the motion response of the industrial robot arm under sudden environmental changes; the motion offset in this application represents the motion change of the end effector due to environmental changes; the guidance deviation in this application refers to the motion deviation of the end effector of the industrial robot arm due to sudden environmental changes. Therefore, by determining the guidance deviation, the motion strategy of the industrial robot arm can be adjusted in time to avoid collision or task failure, and improve the system's adaptability and safety. It will not be repeated here.

[0094] In step 104 , the coordination compensation amount of each moving joint in the industrial robot arm under sudden motion is determined according to the coordination error between each moving joint and the guidance deviation of the end effector under sudden motion perception.

[0095] In some embodiments, determining the coordination compensation amount of each moving joint in the industrial robot arm under sudden motion based on the coordination error between each moving joint and the guidance deviation of the end effector under sudden motion perception can be achieved by using the following steps:

[0096] Determining drift characteristics of each moving joint of the industrial robot arm during movement based on the coordination errors between the moving joints and the guidance deviation of the end effector under sudden change perception;

[0097] The coordinated compensation amount of each moving joint in the industrial robot arm under sudden motion is determined by the drift characteristics of each moving joint during the motion process.

[0098] In specific implementation, the drift characteristics of each moving joint of the industrial robot arm during the movement process are determined based on the coordination error between each moving joint and the guidance deviation of the end effector under sudden change perception, which can be achieved in the following manner, namely: the degree of posture deviation of each moving joint of the industrial robot arm during the movement process can be calculated based on the coordination error between each moving joint and the end effector through a kinematic inverse algorithm (such as an analytical method or a numerical method), and the value obtained after quantifying each posture deviation degree is used as the corresponding drift characteristic of each moving joint of the industrial robot arm during the movement process. In other embodiments, other methods can also be used for determination, which is not limited here.

[0099] It should be noted that the drift feature in this application represents the degree of posture drift of the moving joints of the industrial robot arm during the movement process. The larger the value corresponding to the drift feature, the greater the degree of posture drift of the moving joints of the industrial robot arm during the movement process. Conversely, the smaller the value corresponding to the drift feature, the smaller the degree of posture drift of the moving joints of the industrial robot arm during the movement process. No further details will be given here.

[0100] It should also be noted that the sudden motion in this application refers to the short-term discontinuous motion of the industrial robot arm caused by changes in the working environment during the execution of the task.

[0101] In some embodiments, determining the coordination compensation amount of each moving joint in the industrial robot arm under sudden motion by the drift characteristics of each moving joint during motion can be achieved by the following steps:

[0102] Selecting a motion joint of the industrial robot arm as a selected motion joint;

[0103] determining a contribution of a selected motion joint to the abnormal swing of the industrial robot arm;

[0104] Determining a coordination compensation amount of a selected motion joint in the industrial robot arm under sudden motion based on a drift characteristic of the selected motion joint during motion and the contribution;

[0105] Continue to determine the coordination compensation amount of the remaining moving joints in the industrial robot arm under the sudden movement.

[0106] In specific implementation, determining the contribution of the selected motion joint to the abnormal swing of the industrial robot arm can be achieved in the following manner, namely: based on error regression analysis combined with the analysis framework of the kinematic-dynamic coupling model, the influence ratio of the motion error of the selected motion joint on the abnormal swing of the industrial robot arm can be calculated through simulation, and the obtained influence ratio is used as the contribution of the selected motion joint to the abnormal swing of the industrial robot arm. In other embodiments, other methods can also be used for determination, which is not limited here; determining the coordination compensation amount of the selected motion joint in the industrial robot arm under sudden motion based on the drift characteristics of the selected motion joint during motion and the contribution can be achieved in the following manner, namely: a model predictive control or deep reinforcement learning method can be used to calculate the drift characteristics of the selected motion joint during motion and the contribution to calculate the angle, torque and speed correction values ​​for adjusting the motion error of the selected motion joint when the industrial robot arm swings abnormally, and the set of all obtained correction values ​​is used as the coordination compensation amount of the selected motion joint in the industrial robot arm under sudden motion.

[0107] It should be noted that the coordination compensation amount in this application represents a correction index for adjusting the motion joints of the industrial robot arm to perform coordinated motion; in addition, the contribution degree in this application represents the degree of influence of the motion error of the motion joint on the abnormal swing of the industrial robot arm. The higher the contribution degree, the greater the influence of the motion error of the motion joint on the abnormal swing of the industrial robot arm. Conversely, the lower the contribution degree, the smaller the influence of the motion error of the motion joint on the abnormal swing of the industrial robot arm.

[0108] In step 105 , corresponding motion joints in the industrial robot arm are guided to perform coordinated motion based on the respective coordinated compensation amounts.

[0109] In a specific implementation, guiding the corresponding motion joints in the industrial robot arm to perform coordinated motion based on each coordinated compensation amount can be achieved in the following manner, namely: first, a distributed control architecture can be used to decompose each coordinated compensation amount into a PID control parameter increment of the motor of the corresponding motion joint through adaptive neural network control. For example, the control task of each motion joint of the industrial robot arm is first dispersed to multiple control nodes, and each control node is responsible for controlling a motion joint of the industrial robot arm. Then, the adaptive neural network uses nonlinear approximation capability and adaptive learning capability to further decompose each coordinated compensation amount into a PID control parameter increment of the motor of each motion joint. Then, the decomposed PID control parameter increment is synchronously sent to the joint driver of the corresponding motion joint through a real-time communication protocol (such as Ethernet EtherCAT for control automation technology). The joint driver dynamically adjusts the rotation angle or displacement of the motor of the corresponding motion joint according to the received PID control parameter increment, thereby guiding the various motion joints in the industrial robot arm to perform coordinated motion, so as to achieve motion stability and high-precision motion control of the industrial robot arm.

[0110] In addition, in another aspect of the present application, in some embodiments, the present application provides an industrial robot motion control system, referring to Figure 4 , which is a schematic diagram of the structure of an industrial robot motion control system 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:

[0111] Acquisition module 401, in this application, acquisition module 401 is mainly used to acquire historical motion data of an industrial robot arm, wherein the industrial robot arm has multiple motion joints;

[0112] Processing module 402, in this application, is mainly used to extract the jitter characteristics of each motion joint of the industrial robot arm from the historical motion data, and determine the coordination error between the motion joints in the industrial robot arm by combining all the jitter characteristics with the coupling relationship between each adjacent motion joint in the industrial robot arm during transmission;

[0113] The processing module 402 in the present application is further configured to start the industrial robot arm, perform real-time trajectory tracking on the end effector of the industrial robot arm, obtain multiple trajectory offset points of the end effector, and determine the guidance deviation of the end effector under sudden change perception based on the offset trend characteristics of all trajectory offset points and the sudden movement of the industrial robot arm under visual feedback;

[0114] The processing module 402 in the present application is further configured to determine the coordination compensation amount of each moving joint in the industrial robot arm under sudden motion according to the coordination error between each moving joint and the guidance deviation of the end effector under sudden motion perception;

[0115] The execution module 403 in this application is mainly used to guide the corresponding motion joints in the industrial robot arm to perform coordinated motion based on each coordinated compensation amount.

[0116] The above describes in detail the examples of the industrial robot motion control method, system, device and medium provided by the embodiments of the present application. It can be understood that the corresponding device includes a hardware structure and / or software module corresponding to the execution of each function in order to realize the above functions. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0117] In some embodiments, the present 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.

[0118] In some embodiments, reference Figure 5 , the dotted line in the figure indicates that the unit or module is optional, and the figure is a structural diagram of a computer device for implementing the industrial robot motion control method of the present application. The industrial robot motion control method in the above embodiment can be Figure 5 The computer device 500 is implemented as shown, and 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.

[0119] The processor 501 may be a general-purpose processor or a special-purpose processor. For example, the processor 501 may be a central processing unit (CPU), which may be used to control the computer device 500, execute software programs, and process data from the software programs. The computer device 500 may also include a communication unit 505 for inputting (receiving) and outputting (transmitting) signals.

[0120] For example, the computer device 500 may be a chip, the communication unit 505 may be an input and / or output circuit of the chip, or the communication unit 505 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other device.

[0121] For another example, the computer device 500 may be a terminal device or a server, and 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.

[0122] The computer device 500 may include one or more memories 502, on which a program 504 is stored. The program 504 can be executed by the processor 501 to generate instructions 503, so that the processor 501 executes the method described in the above method embodiment according to the instructions 503. Optionally, data (such as a target audit model) can also be stored in the memory 502. Optionally, the processor 501 can also read data stored in the memory 502. The data can be stored at the same storage address as the program 504, or at a different storage address from the program 504.

[0123] The processor 501 and the memory 502 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of a terminal device.

[0124] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or software-based instructions in the processor 501. The processor 501 can 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, such as discrete gates, transistor logic devices, or discrete hardware components.

[0125] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] For example, in some embodiments, the present application also provides a computer-readable storage medium, which stores instructions or codes. When the instructions or codes are run on a computer, the computer implements the above-mentioned industrial robot motion control method when executing.

[0127] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0128] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A motion control method for an industrial robot, characterized in that: The steps include: Acquiring historical motion data of an industrial robotic arm, wherein the industrial robotic arm has multiple motion joints; Extracting jitter characteristics of each motion joint of the industrial robot arm from the historical motion data, and determining the coordination error between the motion joints of the industrial robot arm by combining all the jitter characteristics with the coupling relationship of each adjacent motion joint in the industrial robot arm during transmission; The industrial robotic arm is activated, and a real-time trajectory tracking is performed on the end effector of the industrial robotic arm to obtain multiple trajectory offset points of the end effector. The guidance deviation of the end effector under sudden change perception is determined based on the offset trend characteristics of all trajectory offset points and the sudden movement of the industrial robotic arm under visual feedback; Determining the coordination compensation amount of each moving joint in the industrial robot arm under sudden motion according to the coordination error between each moving joint and the guidance deviation of the end effector under sudden motion perception; Based on each coordinated compensation amount, the corresponding motion joints in the industrial robot arm are guided to perform coordinated motion.

2. The method according to claim 1, wherein Extracting the jitter characteristics of each motion joint of the industrial robot arm from the historical motion data specifically includes: Extracting motion state data of each motion joint from the historical motion data; Selecting a motion joint of the industrial robot arm as a selected motion joint; generating a vibration trajectory of the selected motion joint based on the motion state data of the selected motion joint; determining a jitter characteristic of a selected motion joint from the vibration trajectory; Continue to determine the jitter characteristics of the remaining motion joints of the industrial robot arm.

3. The method according to claim 1, wherein Determining the coordination error between the motion joints in the industrial robot arm by combining all the jitter characteristics with the coupling relationship of each adjacent motion joint in the industrial robot arm during transmission specifically includes: Determine the coupling relationship between each adjacent motion joint in the industrial robot arm during transmission through kinematic equations; Determining an error transmission model between the motion joints in the industrial robot arm based on the coupling relationship between all adjacent motion joints during transmission; The coordination errors between the motion joints in the industrial robot arm are determined based on the error transfer model between the motion joints and all the jitter characteristics.

4. The method according to claim 1, wherein Performing real-time trajectory tracking on the end effector of the industrial robot arm to obtain multiple trajectory offset points of the end effector specifically includes: Obtaining a theoretical trajectory of the end effector of the industrial robot arm; Collecting the real-time actual trajectory of the end effector of the industrial robot arm; The real-time actual trajectory is compared point by point with the theoretical trajectory to obtain a plurality of trajectory offset points of the end effector.

5. The method according to claim 1, wherein The guidance deviation of the end effector under sudden change perception is determined by combining the deviation trend characteristics of all trajectory deviation points with the sudden movement of the industrial robot arm under visual feedback, specifically including: Determine the deviation trend characteristics of all trajectory deviation points; Extract the sudden movement of the industrial robot under visual feedback from the interaction information between the industrial robot and the industrial environment; Determining the motion offset of the end effector under sudden change perception through the sudden movement of the industrial robot arm under visual feedback; The guidance deviation of the end effector under sudden change perception is determined based on the motion offset under sudden change perception and the offset trend feature.

6. The method according to claim 1, wherein Determining the coordination compensation amount of each motion joint in the industrial robot arm under sudden motion according to the coordination error between each motion joint and the guidance deviation of the end effector under sudden motion perception specifically includes: Determining drift characteristics of each moving joint of the industrial robot arm during movement based on the coordination errors between the moving joints and the guidance deviation of the end effector under sudden change perception; The coordinated compensation amount of each moving joint in the industrial robot arm under sudden motion is determined by the drift characteristics of each moving joint during the motion process.

7. The method according to claim 6, wherein Determining the coordinated compensation amount of each moving joint in the industrial robot arm under sudden motion by using the drift characteristics of each moving joint during motion specifically includes: Selecting a motion joint of the industrial robot arm as a selected motion joint; determining a contribution of a selected motion joint to the abnormal swing of the industrial robot arm; Determining a coordination compensation amount of a selected motion joint in the industrial robot arm under sudden motion based on a drift characteristic of the selected motion joint during motion and the contribution; Continue to determine the coordination compensation amount of the remaining moving joints in the industrial robot arm under the sudden movement.

8. An industrial robot motion control system, characterized in that: include: an acquisition module, configured to acquire historical motion data of an industrial robotic arm, wherein the industrial robotic arm has a plurality of motion joints; a processing module, configured to extract jitter characteristics of each motion joint of the industrial robot arm from the historical motion data, and determine the coordination error between the motion joints of the industrial robot arm by combining all the jitter characteristics with the coupling relationship between each adjacent motion joint of the industrial robot arm during transmission; The processing module is further configured to start the industrial robot arm, perform real-time trajectory tracking on the end effector of the industrial robot arm, obtain multiple trajectory offset points of the end effector, and determine the guidance deviation of the end effector under sudden change perception based on the offset trend characteristics of all trajectory offset points and the sudden movement of the industrial robot arm under visual feedback; The processing module is further configured to determine a coordination compensation amount of each moving joint in the industrial robot arm under sudden motion according to the coordination error between each moving joint and the guidance deviation of the end effector under sudden motion perception; The execution module is used to guide the corresponding motion joints in the industrial robot arm to perform coordinated motion based on each coordinated compensation amount.

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 The computer-readable storage medium stores instructions or codes, and when the instructions or codes are executed on a computer, the computer implements the industrial robot motion control method according to any one of claims 1 to 7.

Images