Industrial robot motion control system and motion path control method thereof

Abstract

The present application provides an industrial robot motion control system and a motion path control method thereof, which extracts the path control set of the industrial robot motion in the navigation path information, determines the visual path coordinates when the industrial robot motion path is adjusted, and determines the correction response value of the industrial robot during path tracking by the deviation feature domain; determines the path planning information of the industrial robot during motion according to the speed constraint boundary and the current position of the industrial robot, and then determines the speed compensation value of the industrial robot in the global static path planning by the path planning information; determines the path planning cost of the industrial robot during motion according to the correction response value and the speed compensation value, and dynamically adjusts the motion path of the industrial robot according to the path planning cost. The above scheme controls the motion path of the industrial robot based on path recognition planning, and improves the progressive control capability of the motion path control of the industrial robot.

Description

Technical Field

[0001] The present application relates to the technical field of robot path control, and more specifically, to an industrial robot motion control system and a motion path control method thereof. Background Art

[0002] Robot path control refers to controlling the robot's motion path through a series of algorithms, sensor data processing and actuator operations, so that it can adaptively complete specific tasks along a predetermined path. Path control involves multidisciplinary knowledge such as kinematics, dynamics, control theory, artificial intelligence, etc., and aims to ensure that the robot can autonomously or semi-autonomously perform established tasks in various complex environments with high precision and efficiency.

[0003] In the prior art, the process of motion path control of industrial robots usually includes four main steps: path planning, path generation, control execution and feedback adjustment. First, path planning is performed according to task requirements and working environment to determine the spatial points or curves that the robot needs to pass through. Then, a specific motion path is generated, including parameters such as position, speed and acceleration. Then, the control system drives the robot to move according to the generated path instructions, and uses sensors to obtain real-time data for feedback control and correct deviations. Finally, through continuous path adjustment and error compensation, it is ensured that the robot can accurately and smoothly complete the predetermined task. However, in the motion path control of industrial robots, since industrial robots are difficult to cope with the challenges of dynamic environmental changes and complex tasks, they are affected by various factors such as path errors, environmental interference, and speed constraints in actual operation. In the control process of the motion path of industrial robots, the tracking and adjustment of the motion path has the problem of limited reconstruction, which makes the continuous trajectory planning of the motion path of the industrial robot unstable, resulting in uncoordinated motion path control, thereby reducing the progressive control ability of the motion path control of the industrial robot. Therefore, how to control the motion path of the industrial robot under the interference of limited reconstruction of the tracking and adjustment of the motion path, so as to improve the progressive control ability of the motion path control of the industrial robot, has become a problem faced by the industry. Summary of the invention

[0004] The present application provides an industrial robot motion control system and a motion path control method thereof, which can control the motion path of the industrial robot under the interference of limited reconstruction of the tracking adjustment of the motion path, thereby improving the progressive control capability of the motion path control of the industrial robot.

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

[0006] Monitor the motion path of the industrial robot and obtain the navigation path information of the industrial robot on the target navigation path;

[0007] Determine the global path points during the movement of the industrial robot through the navigation path information;

[0008] Determine the visual path coordinates when the motion path of the industrial robot is adjusted, determine the deviation feature domain of the motion path of the industrial robot through the visual path coordinates and the global path points, and then determine the correction response value of the industrial robot during path tracking through the deviation feature domain;

[0009] Obtaining a speed constraint boundary of the industrial robot during motion path matching, determining path planning information of the industrial robot during motion according to the speed constraint boundary and the current position of the industrial robot, and then determining a speed regulation compensation value of the industrial robot in global static path planning according to the path planning information;

[0010] The path planning cost during the movement of the industrial robot is determined according to the correction response value and the speed regulation compensation value, and the movement path of the industrial robot is dynamically adjusted according to the path planning cost.

[0011] In some embodiments, determining the global path point during the motion of the industrial robot through the navigation path information specifically includes:

[0012] Extracting a path control set of the industrial robot movement from the navigation path information;

[0013] Determining a navigation path marking coefficient during the motion of the industrial robot according to the path control set;

[0014] Determine the global path membership during the motion of an industrial robot;

[0015] A global path point is determined according to the navigation path marking coefficient and the global path membership.

[0016] In some embodiments, extracting the path control set of the industrial robot movement in the navigation path information specifically includes:

[0017] Determine the path control nodes of the industrial robot's motion path;

[0018] Determine the control feature quantity in the navigation path information according to the path control node;

[0019] The path control set of the industrial robot motion is determined based on all control characteristic quantities.

[0020] In some embodiments, determining the deviation characteristic domain of the motion path of the industrial robot through the visual path coordinates and the global path point specifically includes:

[0021] Determine the disordered recognition prediction quantity of the motion path of the industrial robot according to the visual path coordinates;

[0022] Obtain the total amount of ordered recognition of the motion path of the industrial robot;

[0023] Determine the identification deviation characteristics of the motion path of the industrial robot according to the global path point;

[0024] A deviation feature domain is determined based on the disordered recognition prediction quantity, the ordered recognition total quantity and the recognition deviation feature.

[0025] In some embodiments, determining the path planning information of the industrial robot during the motion process according to the speed constraint boundary and the current position of the industrial robot specifically includes:

[0026] Determining path planning characteristics during the motion of the industrial robot according to the speed constraint boundary;

[0027] Determine the path allocation amount during the movement of the industrial robot through the current position of the industrial robot;

[0028] Path planning information during the movement of the industrial robot is determined according to the path planning characteristics and the path allocation amount.

[0029] In some embodiments, determining the path planning cost of the industrial robot during movement according to the corrected response value and the speed regulation compensation value specifically includes:

[0030] Determine first path planning information during the movement of the industrial robot according to the corrected response value;

[0031] Determine second path planning information during the movement of the industrial robot according to the speed regulation compensation value;

[0032] The path planning cost during the movement of the industrial robot is determined by using the first path planning information and the second path planning information.

[0033] In some embodiments, the industrial robot is a handling robot.

[0034] In a second aspect, the present application provides an industrial robot motion control system, comprising:

[0035] A monitoring module is used to monitor the motion path of the industrial robot and obtain navigation path information of the industrial robot on the target navigation path;

[0036] A processing module, used to determine the global path points during the movement of the industrial robot through the navigation path information;

[0037] The processing module is further used to determine the visual path coordinates when the motion path of the industrial robot is adjusted, determine the deviation feature domain of the motion path of the industrial robot through the visual path coordinates and the global path point, and then determine the correction response value of the industrial robot during path tracking through the deviation feature domain;

[0038] The processing module is further used to obtain a speed constraint boundary of the industrial robot when matching a motion path, determine path planning information of the industrial robot during motion according to the speed constraint boundary and the current position of the industrial robot, and further determine a speed regulation compensation value of the industrial robot in global static path planning according to the path planning information;

[0039] The execution module is used to determine the path planning cost of the industrial robot during the movement according to the correction response value and the speed regulation compensation value, and dynamically adjust the movement path of the industrial robot according to the path planning cost.

[0040] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned industrial robot motion path control method.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for controlling the motion path of an industrial robot is implemented.

[0042] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0043] The industrial robot motion control system and motion path control method provided by the present application first monitor the motion path of the industrial robot to obtain navigation path information of the industrial robot on the target navigation path; secondly, determine the global path points of the industrial robot during motion through the navigation path information; then, determine the visual path coordinates when the motion path of the industrial robot is adjusted, determine the deviation feature domain of the motion path of the industrial robot through the visual path coordinates and the global path points, and then determine the correction response value of the industrial robot during path tracking from the deviation feature domain; then, obtain the speed constraint boundary of the industrial robot during motion path matching, determine the path planning information of the industrial robot during motion according to the speed constraint boundary and the current position of the industrial robot, and then determine the speed compensation value of the industrial robot in global static path planning from the path planning information; finally, determine the path planning cost of the industrial robot during motion according to the correction response value and the speed compensation value, and dynamically adjust the motion path of the industrial robot according to the path planning cost.

[0044] It can be seen that in the present application, the motion path of the industrial robot can be controlled under the interference of limited reconstruction of the tracking adjustment of the motion path, thereby improving the progressive control ability of the motion path control of the industrial robot; first, in the motion control of the industrial robot, in order to correct the output of the industrial robot motion control system to compensate for the deviation between the actual path and the expected path, the correction response value of the industrial robot during path tracking is determined by the deviation characteristic domain; secondly, in order to control how the industrial robot moves according to the set path when matching the motion path, to ensure smooth and safe path tracking under the constraints of speed and acceleration, and then determine the speed compensation value of the industrial robot in the global static path planning by the path planning information, the actual speed can be adjusted by addition or subtraction to compensate for the difference between the speed requirement set in the path planning and the actual motion conditions, thereby optimizing the robot. motion performance and path tracking accuracy; then, in the motion control system of the industrial robot, it is also necessary to consider the path changes and adjustment requirements introduced by the correction response value in the path tracking process and the speed adjustment requirements introduced by the speed compensation value in the path planning and their impact on the path. Therefore, the path planning cost of the industrial robot in the motion process is determined according to the correction response value and the speed compensation value to measure the control complexity and adjustment degree required for path tracking, and further adjust the difficulty of motion control, control accuracy, complexity of speed compensation, and details of path correction; finally, the motion path of the industrial robot is dynamically adjusted according to the path planning cost; in summary, the technical solution provided by the present application can realize the control of the motion path of the industrial robot under the interference of limited reconstruction of the tracking adjustment of the motion path, thereby improving the progressive control capability of the motion path control of the industrial robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is an exemplary flow chart of an industrial robot motion path control method according to some embodiments of the present application;

[0046] Figure 2 is a schematic diagram of an exemplary process of a visual coordinate system according to some embodiments of the present application;

[0047] Figure 3 is an exemplary flow chart of the principle of measuring the pose points of a robot target object in a motion image according to some embodiments of the present application;

[0048] Figure 4 is a schematic diagram of exemplary hardware and / or software of an industrial robot motion control system according to some embodiments of the present application;

[0049] Figure 5It is a structural schematic diagram of a computer device for implementing an industrial robot motion path control method according to some embodiments of the present application. DETAILED DESCRIPTION

[0050] The core of this application is to first monitor the motion path of the industrial robot and obtain the navigation path information of the industrial robot on the target navigation path; secondly, determine the global path points of the industrial robot during the motion process through the navigation path information; then, determine the visual path coordinates when the motion path of the industrial robot is adjusted, determine the deviation feature domain of the motion path of the industrial robot through the visual path coordinates and the global path points, and then determine the correction response value of the industrial robot during path tracking from the deviation feature domain; then, obtain the speed constraint boundary of the industrial robot during motion path matching, determine the path planning information of the industrial robot during the motion process according to the speed constraint boundary and the current position of the industrial robot, and then determine the speed compensation value of the industrial robot in the global static path planning from the path planning information; finally, determine the path planning cost of the industrial robot during the motion process according to the correction response value and the speed compensation value, and dynamically adjust the motion path of the industrial robot according to the path planning cost. The above scheme controls the motion path of the industrial robot based on path recognition planning, and improves the progressive control capability of the motion path control of the industrial robot.

[0051] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of an industrial robot motion path control method according to some embodiments of the present application. The industrial robot motion path control method 100 mainly includes the following steps:

[0052] In step 101, the motion path of the industrial robot is monitored to obtain navigation path information of the industrial robot on a target navigation path.

[0053] In specific implementation, the industrial robot can be a handling robot, and in practice it can also be a cleaning robot, etc., which is not specifically limited here. In this application, the industrial robot is usually equipped with a variety of sensors, such as lidar, camera, inertial measurement unit (IMU), global positioning system (GPS), etc. These sensors collect environmental and position information in real time, and fuse this information together to generate accurate navigation path information and store it in the data storage unit of the industrial robot. The navigation path information of the industrial robot on the target navigation path can be obtained by reading the data storage unit of the industrial robot. For example, the lidar can measure the distance between the robot and the surrounding obstacles, the GPS can provide geographic location information, and the IMU can detect the posture and motion state of the robot. In specific application scenarios, the navigation path may be pre-defined, such as a fixed walking route on a production line. The industrial robot loads this pre-defined path information from the control system or database, and then tracks and adjusts the path according to the feedback information from the sensor.

[0054] It should be noted that the navigation path information in this application refers to the path data obtained by the industrial robot from sensors, control systems or real-time path planning to guide its movement. These data are used to define the robot's route from the starting point to the end point and include key positions and actions on the path.

[0055] In step 102, the global path points of the industrial robot during its movement are determined by using the navigation path information.

[0056] It should be noted that in the motion path control of industrial robots, the visual coordinate system is the basis for the global path control of industrial robots. It consists of three parts: the horizontal axis, the vertical axis and the spatial axis. Figure 2 As shown in FIG. 1 , this figure is an exemplary flow diagram of a visual coordinate system according to some embodiments of the present application. In the motion navigation plane during the motion of the industrial robot, a travel route is determined by two path nodes, so the number of horizontal axes and vertical axes in the visual coordinate system is two. As the motion direction of the industrial robot changes, its spatial position will also change accordingly. Therefore, a visual coordinate system only contains one spatial axis ( Figure 2 However, in order to accurately obtain the spatial path navigation coordinates in other directions, it is also necessary to determine the corresponding projection point coordinates of the axis origin in other directions. Figure 2 As shown (O 0 , O 1 , O 2 ).

[0057] In some embodiments, determining the global path points during the motion of the industrial robot through the navigation path information may be achieved by using the following steps:

[0058] Extracting a path control set of the industrial robot movement from the navigation path information;

[0059] Determining a navigation path marking coefficient during the motion of the industrial robot according to the path control set;

[0060] Determine the global path membership during the motion of an industrial robot;

[0061] A global path point is determined according to the navigation path marking coefficient and the global path membership.

[0062] In the specific implementation, first, the parameters related to the key nodes of the path are extracted from the path control set, such as the steering angle, the speed change amplitude, the acceleration and deceleration ratio, etc. These parameters are used to calculate the navigation path marking coefficient, and the navigation path marking coefficient of each path control node is calculated using a mathematical model or algorithm, such as a weighted average model, a fuzzy logic model, etc., which are not limited here; then, by analyzing the key nodes in the path control set, the contribution of these nodes to the global path is calculated, and the contribution of the nodes to the global path is used as the global path membership. Among them, common calculation methods include fuzzy logic, weighted average, etc., and then according to the key nodes in the path (such as turning points, acceleration points, etc.), the global path membership is calculated. Speed ​​point, obstacle avoidance point), assign membership to these nodes, determine their weights in the global path, the higher the membership, the greater the importance of the node in path planning; finally, in order to make the navigation path marking coefficient and the global path membership comparable, the two can be standardized to the same magnitude. The commonly used standardization method is minimum-maximum standardization. The standardized navigation path marking coefficient and the global path membership are weighted summed to calculate the comprehensive score of each drop point, where the weight in the weighted summation is determined according to expert experience or industrial robot path planning control parameters, and then sorted according to the size of the comprehensive score, and the nodes with the highest scores are selected as global path points. Usually a threshold is set, and all nodes with scores exceeding the threshold are selected as global path points. For example, an industrial robot reaches the end point from the starting point, and there are multiple nodes on the path. The navigation path marking coefficient of a node A is calculated to be 0.8, the global path membership is 0.9, and the comprehensive score is 0.85. After sorting, the comprehensive score of node A ranks in the top few, so it is selected as a global path point. In other embodiments, other methods can also be used to determine the global path point, which is not limited here.

[0063] It should be noted that the navigation path marking coefficient in the present application represents the parameters of the importance of the node and the intensity of the path change when the industrial robot performs an operation on the path control node. It reflects the degree of influence of a certain node on the overall effect of the navigation path in path planning; the global path affiliation represents the parameter of the importance or contribution of the path control node to the entire path planning. It is used to measure the criticality of the node in the global path and determines the priority of the node when the robot executes path planning; the global path points represent the key positions that the industrial robot must pass on the motion path. After calculation and planning, these positions are determined as the points that the robot needs to reach accurately during the path execution process to ensure the overall accuracy and effectiveness of the path.

[0064] In some embodiments, extracting the path control set of the industrial robot movement in the navigation path information may be implemented by the following steps:

[0065] Determine the path control nodes of the industrial robot's motion path;

[0066] Determine the control feature quantity in the navigation path information according to the path control node;

[0067] The path control set of the industrial robot motion is determined based on all control characteristic quantities.

[0068] In the specific implementation, first, the motion path of the industrial robot is analyzed, that is, the overall motion path of the industrial robot is analyzed, and the path is decomposed into multiple segments, each of which may include a straight path, a turning path, an uphill or downhill path, etc. Through path decomposition, the key positions in the path can be identified, and these positions often require the robot to perform operations such as turning, speed adjustment, and stopping. On the basis of path decomposition, the path control nodes in the path are further determined. For example, turning points, intersections, obstacle avoidance points, speed change points, etc. are used as path control nodes, where path analysis and path control node selection can be implemented using machine learning algorithms, which are not limited here; then, according to the path control nodes, the navigation path information is extracted The control feature quantity corresponding to each node usually includes parameters such as angle, speed, acceleration, direction, etc. These feature quantities determine the specific operation behavior of the robot at each node; finally, the control feature quantities of all path control nodes are combined together (which can be implemented using a linear fitting algorithm) to form a complete path control set, that is, the path control set for the industrial robot's movement. The path control set contains all the key operation instructions of the robot on the entire path. The generated path control set is then verified through simulation or actual testing to ensure that the robot can successfully complete the task according to the control set in the actual environment. If deviations or problems are found, the control set needs to be adjusted, such as correcting the path node position or optimizing the feature quantity parameters.

[0069] It should be noted that the path control node in the present application represents the specific location where the industrial robot needs to perform key operations on the motion path. These nodes are usually important turning points, speed adjustment points or stopping points in the robot path, such as turning points, intersections, obstacle avoidance points, etc.; the control feature quantity represents the set of parameters in the navigation path information used to describe the specific operations performed by the industrial robot on the path control node. These parameters include turning angle, speed, acceleration, direction, turning radius, etc. The control feature quantity is intended to provide specific operation instructions for each path control node to guide the robot on how to adjust its behavior when matching the motion path, so as to accurately complete the key actions in path planning; the path control set represents the set of all control operations that the industrial robot needs to perform on the motion path. The motion control of the industrial robot is based on the control feature quantity of the path control node, including turning, acceleration, deceleration, stopping and other actions.

[0070] In step 103, the visual path coordinates of the industrial robot during motion path adjustment are determined, the deviation characteristic domain of the industrial robot motion path is determined by the visual path coordinates and the global path points, and then the correction response value of the industrial robot during path tracking is determined by the deviation characteristic domain.

[0071] It should be noted that the reference Figure 3 As shown, this figure is an exemplary flow chart of the robot target object pose point measurement principle in the motion image shown in some embodiments of the present application. In the visual path recognition and judgment of the industrial robot, the target object pose point measurement standard in the motion image is recognized by the host as the motion trajectory measurement standard that meets the motion control conditions; in the plane perpendicular to the center of the optical axis of the visual camera, a motion image can be used to realize real-time detection and tracking of the target object (motion path) in the plane. When the motion behavior of the optical axis center plane is known, the three-dimensional position of any industrial robot motion trajectory node in the space can be calculated using the target object pose points that can be matched in the motion image and the visual camera plane; wherein, the motion image and the visual camera plane are respectively located at the two ends of the optical axis center plane. After the optical axis center plane aggregation processing, the motion trajectory path in the visual camera plane is completely displayed in the motion image, so that the host can obtain the target object in the path to be moved by the industrial robot. The principle of the robot target object pose point measurement principle in the specific motion image is referenced. Figure 3 As shown, in Figure 3 In the visual camera plane, the pose point coordinates are (X 0 , Y 0 , Z 0 ), the coordinates of the pose point in the motion image plane are (X 1 , Y 1 , Z 1 ), and X 0 ≠X 1 , Y0 ≠Y 1 , Z 0 ≠Z 1 .

[0072] In specific implementation, the visual path coordinates of the industrial robot when adjusting its motion path can be determined in the following manner, namely: a camera is installed on the front of the robot, and a suitable lens and resolution are configured to ensure that the path and obstacles in front can be clearly captured. When the robot matches the motion path, the camera collects images in the workshop in real time, and the image processing algorithm detects the navigation marks and obstacle positions on the workshop floor. The edge detection algorithm is used to identify the boundary of the path, and the identification result is matched with the predefined path model to extract the key points on the path. The path feature points in the visual coordinate system are converted to the robot coordinate system through a transformation matrix, and the actual coordinates of the path points are calculated, that is, the visual path coordinates of the industrial robot when adjusting its motion path are obtained. In other embodiments, other methods can also be used to determine the visual path coordinates of the industrial robot when adjusting its motion path, which are not limited here.

[0073] It should be noted that the visual path coordinates in the present application represent the position coordinates of each key point on the path that the industrial robot needs to follow during the navigation process, which are obtained by the visual sensor.

[0074] In some embodiments, determining the deviation characteristic domain of the motion path of the industrial robot by using the visual path coordinates and the global path points can be implemented by the following steps:

[0075] Determine the disordered recognition prediction quantity of the motion path of the industrial robot according to the visual path coordinates;

[0076] Obtain the total amount of ordered recognition of the motion path of the industrial robot;

[0077] Determine the identification deviation characteristics of the motion path of the industrial robot according to the global path point;

[0078] A deviation feature domain is determined based on the disordered recognition prediction quantity, the ordered recognition total quantity and the recognition deviation feature.

[0079] In specific implementation, the prediction information related to the path is extracted from the path coordinates obtained by the visual sensor. The disordered recognition prediction includes the predicted position, distance, angle, etc. of the path points in the recognition process. Then, the prediction corresponding to each visual path coordinate is calculated, that is, the visual path coordinates are matched with the global path points, the predicted path point positions are obtained, and the distance and angle differences between the visual path coordinates and the global path points are calculated to obtain the disordered recognition prediction. The distance formula in the plane can be used to determine the disordered recognition prediction, which is not limited here. Secondly, all the path point data in the recognition process are summarized and sorted to form an ordered recognition total, which usually includes all visual path coordinates and corresponding recognition information. Among them, calculating the ordered recognition total includes: The recognition data is standardized to ensure the comparative consistency between different path points, and then the statistics of each point in the visual path coordinates are performed to calculate the overall recognition value, such as the total distance, total error, etc.; then, based on the global path points and the visual path coordinates, the recognition deviation characteristics of each path point are calculated. These characteristics usually include the error between path points, deviation, change in path curvature, etc., and the deviation characteristics are extracted using image processing and statistical analysis methods, that is, the recognition deviation characteristics of the motion path of the industrial robot are obtained. Common methods include calculating the average deviation and maximum deviation of the path points; finally, the deviation feature domain is determined by weighted summation, statistical analysis and other methods, that is: the maximum and minimum values ​​of the recognition deviation characteristics of all path points are divided by the number of path points, and the quotient obtained is used as the deviation feature domain. In other embodiments, other methods can also be used to determine the deviation feature domain, which is not limited here.

[0080] It should be noted that in the present application, the unordered recognition prediction quantity represents a parameter used to measure the deviation between each path point and the actual expected path in the visual navigation of the industrial robot; the ordered recognition total is a quantity used to measure the recognition quality and accuracy of the industrial robot in the path tracking process. A higher ordered recognition total indicates that the overall performance of the path recognition is good, which helps to optimize the path planning and correction strategy and improve the navigation stability and reliability of the system; the recognition deviation feature represents a parameter that reflects the deviation or error between each path point and the expected path in the path recognition process, which is used to describe and quantify the actual deviation of the robot in path tracking; the deviation feature domain represents the overall deviation distribution and range of the industrial robot in path tracking, and is used to identify and quantify inconsistencies in path execution.

[0081] In some embodiments, determining the correction response value of the industrial robot during path tracking by the deviation feature domain can be implemented by the following steps:

[0082] Determining the tracking accuracy of the industrial robot during path tracking according to the deviation feature domain;

[0083] Determine the correction coefficient when the industrial robot performs path tracking correction;

[0084] A correction response value of the industrial robot during path tracking is determined according to the tracking accuracy and the correction coefficient.

[0085] In specific implementation, first, key deviation information is extracted from the deviation feature domain, including the distribution range, maximum value and average value of the deviation, and then the accuracy of path tracking is calculated, which usually involves evaluating the degree of matching between the actual path and the expected path, which can be completed by analyzing the data distribution in the deviation feature domain, such as calculating the standard deviation or average value within the deviation range to evaluate the overall tracking accuracy, that is, obtaining the tracking accuracy of the industrial robot when tracking the path; then, the correction coefficient of the industrial robot when performing path tracking correction can be set according to the tracking accuracy and the information in the deviation feature domain. For example, a constant for path tracking correction is set according to expert experience, and then the tracking accuracy is quantified to between 0 and 1, and the tracking accuracy is subtracted from 1 and multiplied by the constant for path tracking correction, and the product is used as the correction coefficient of the industrial robot when performing path tracking correction. In other embodiments, other methods can also be used to determine the correction coefficient of the industrial robot when performing path tracking correction, which is not limited here; finally, the correction response value of the industrial robot when tracking the path is determined according to the product of the tracking accuracy and the correction coefficient, that is, the product of the tracking accuracy and the correction coefficient is used as the correction response value of the industrial robot when tracking the path, which will not be repeated here.

[0086] It should be noted that the tracking accuracy in this application refers to the degree of match between the actual path and the expected path during the path tracking process. It measures the deviation between the actual position and the target path point when the robot actually executes the path; the correction coefficient refers to the parameter used to adjust the robot motion control quantity during the path tracking control process. The correction coefficient can adjust the behavior of the robot control system according to the deviation between the actual path and the expected path, thereby improving the accuracy and stability of path tracking; the corrected response value refers to the adjustment parameter calculated according to the tracking accuracy and the correction coefficient during the path tracking process, which is used to correct the output of the robot motion control system to compensate for the deviation between the actual path and the expected path.

[0087] In step 104, the speed constraint boundary of the industrial robot during motion path matching is obtained, and the path planning information of the industrial robot during the motion process is determined according to the speed constraint boundary and the current position of the industrial robot, and then the speed compensation value of the industrial robot in the global static path planning is determined according to the path planning information.

[0088] In specific implementation, obtaining the speed constraint boundary of the industrial robot during motion path matching can be achieved in the following manner, namely: consulting the technical specification document provided by the robot manufacturer to obtain the maximum allowable speed and acceleration of the industrial robot, and determining the mechanical structure limitations of the robot in different motion modes; then, using the robot forward kinematics and inverse kinematics models to calculate the motion speed and end effector speed, and then obtaining the motion speed and the maximum speed constraint of the end effector, for example: calculating the linear velocity and angular velocity of the end effector through the forward kinematics model, and then calculating the corresponding motion speed limit through inverse kinematics; finally, considering the influence of dynamic load and acceleration on the speed, calculating the speed limit under different load conditions, and using the dynamic model to evaluate the speed constraint boundary when the load changes, that is, obtaining the speed constraint boundary of the industrial robot during motion path matching. In other embodiments, other methods can also be used to determine the speed constraint boundary of the industrial robot during motion path matching, which is not limited here.

[0089] It should be noted that the speed constraint boundary in this application refers to the maximum allowable speed range for each moving part (such as joints, end effectors) of the industrial robot during its movement, and characterizes the speed limit of the industrial robot during operation to avoid exceeding the capabilities of its mechanical structure, transmission system, and the safety and performance standards set by the environment or task requirements.

[0090] In some embodiments, determining the path planning information of the industrial robot during the motion process according to the speed constraint boundary and the current position of the industrial robot can be implemented by the following steps:

[0091] Determining path planning characteristics during the motion of the industrial robot according to the speed constraint boundary;

[0092] Determine the path allocation amount during the movement of the industrial robot through the current position of the industrial robot;

[0093] Path planning information during the movement of the industrial robot is determined according to the path planning characteristics and the path allocation amount.

[0094] In the specific implementation, first, a machine learning algorithm is used to identify the impact of speed constraint boundaries on path planning, including the maximum allowable speed and acceleration limits. These limits will determine the complexity and feasibility of path planning. Then, the path planning features are calculated based on the speed constraint boundaries, such as the maximum curvature of the path, the turning radius, and the acceleration range. This feature can determine the shape of the path and the adjustment strategy to ensure that the speed of the robot does not exceed the constraint range when matching the motion path. For example, if the speed constraint boundary limits the maximum acceleration of the robot to 2m / s², the path planning feature may need to consider the deceleration strategy at the turn to meet this limitation.

[0095] It should be noted that the path planning features in this application represent the key parameters and attributes used to describe and define the path during the path planning process. They are intended to control how the industrial robot moves according to the set path when matching the motion path, ensuring smooth and safe path tracking under speed and acceleration constraints.

[0096] In addition, in the specific implementation, the current position data of the robot is first obtained in real time, including joint angles, end effector positions, etc., and then based on the current position data, the allocation amount of each path segment when the robot matches the motion path is calculated, which includes calculating the length, required time and speed of each path segment to ensure that the path planning is feasible under the given speed constraint. The calculation process can be executed by a computer program, such as an industrial robot motion control model, a motion control model, etc. For example: the path length from the current position of the industrial robot to the target position is 10 meters, and the maximum allowable speed is 1m / s, then the path allocation amount may include dividing the path into 10 segments, each 1 meter, and calculating the time requirement for each segment, which will not be repeated here.

[0097] It should be noted that the path allocation amount in the present application represents the quantitative parameters required to divide the entire motion path into several sub-paths or sections during the path planning process. The parameters include the length of each sub-path, the required time, speed and acceleration requirements, etc., which are used to ensure that the robot moves smoothly according to the planned path when the motion path is matched, and meets the constraints of speed and acceleration.

[0098] In addition, in the specific implementation, the path planning characteristics and path allocation are first combined to define the path planning information, which is usually the basic component of path planning, such as path segments, control points or navigation nodes, and then the specific parameters of each path planning information are calculated, including position, speed, acceleration requirements, etc. These parameters will be used to control the robot to follow the predetermined path during actual movement. For example: according to the previous path allocation, the entire path is divided into several path planning information, and the speed and acceleration of each unit meet the speed constraint boundary. If the planning unit of a path segment includes a straight path from position A to position B, its speed is set to 0.8m / s to ensure safe operation within the maximum speed limit of 1m / s.

[0099] It should be noted that the path planning information in the present application represents the basic components or modules into which the motion path is divided during the path planning process. The units may be path segments, control points, navigation nodes, etc. Each unit has specific spatial position, speed requirements, acceleration limits and other parameters. The path planning information can decompose complex path planning tasks so that it can be managed and adjusted according to predetermined control strategies and constraints during the actual motion process.

[0100] In some embodiments, determining the speed compensation value of the industrial robot in the global static path planning from the path planning information can be implemented by the following steps:

[0101] Determining the speed control characteristics of the industrial robot when matching the motion path through the path planning information;

[0102] Determine the speed adaptation index of industrial robots in global static path planning;

[0103] A speed regulation compensation value of the industrial robot in global static path planning is determined according to the speed control feature and the speed adaptation index.

[0104] In the specific implementation, first, the path in the path planning information is divided into multiple sub-path segments, and the speed requirement and acceleration limit of each segment are used as part of the speed control feature. Then, the speed change in the path segment is calculated according to the curvature and turning radius of the path. The geometric parameters of the path (such as the curvature radius R) and the speed formula v= (a*R) can be used, where a is the acceleration. Then, the speed limit of each path segment is extracted from the robot control system or kinematic model. The maximum value of the speed limit can be used as the speed control feature of the industrial robot when matching the motion path. In other embodiments, other methods can also be used to determine the speed control features of the industrial robot when matching the motion path, which are not limited here.

[0105] It should be noted that the speed control characteristics of the industrial robot during motion path matching in the present application represent the key parameters that the industrial robot needs to follow during motion path matching, including maximum speed, minimum speed, acceleration limit and speed variation range. This feature can ensure that the robot can stably and accurately control its motion speed according to the planning requirements.

[0106] In addition, in the specific implementation, the speed adaptation index of the industrial robot in the global static path planning can be determined in the following manner: the speed adaptation index of the industrial robot in the global static path planning is determined according to the ratio of the actual speed to the target speed, that is, the ratio of the actual speed to the target speed is used as the speed adaptation index of the industrial robot in the global static path planning. For example, the current speed of the industrial robot is 1.2m / s, and the target speed is 1.5m / s, then the speed adaptation index of the industrial robot in the global static path planning is 1.2 / 1.5=0.8. In other embodiments, other methods can also be used to determine the speed adaptation index of the industrial robot in the global static path planning, which is not limited here.

[0107] It should be noted that the speed adaptation index of the industrial robot in the global static path planning in this application represents a measure of the degree of matching between the actual speed of the industrial robot and the target speed, and aims to evaluate whether the current speed of the robot meets the planning requirements and ensure that the robot can effectively adjust its movement speed to achieve the desired goal when executing global static path planning.

[0108] In addition, in the specific implementation, the speed compensation value of the industrial robot in the global static path planning can be determined according to the speed control characteristics and the speed adaptation index. It can be achieved in the following way: speed compensation value = (the current actual movement speed of the robot - the target speed set according to the path control characteristics) * speed adaptation index. Then, it is necessary to ensure that the calculated compensation amount is within the maximum and minimum speed range set by the speed control characteristics, that is: the minimum speed in the speed control characteristics ≤ the current actual movement speed of the robot + the speed compensation value ≤ the maximum speed in the speed control characteristics. Then, the calculated compensation amount is applied to the robot control system, the control instructions are adjusted to make the robot speed meet the target value, and the actual speed is monitored to ensure that the actual speed is stable at the target speed after compensation. I will not go into details here.

[0109] It should be noted that the speed compensation value of the industrial robot in the global static path planning in the present application represents the speed value that needs to be adjusted to make the actual speed of the industrial robot consistent with the target speed in the global static path planning. The actual speed is added or subtracted to compensate for the difference between the speed requirement set in the path planning and the actual motion conditions, thereby optimizing the robot's motion performance and path tracking accuracy.

[0110] In step 105, the path planning cost of the industrial robot during its motion is determined according to the correction response value and the speed regulation compensation value, and the motion path of the industrial robot is dynamically adjusted according to the path planning cost.

[0111] In some embodiments, determining the path planning cost of the industrial robot during movement according to the correction response value and the speed adjustment compensation value can be achieved by using the following steps:

[0112] Determine first path planning information during the movement of the industrial robot according to the corrected response value;

[0113] Determine second path planning information during the movement of the industrial robot according to the speed regulation compensation value;

[0114] The path planning cost during the movement of the industrial robot is determined by using the first path planning information and the second path planning information.

[0115] In specific implementation, first, according to the correction response value, the correction requirement on the path is calculated, including fine-tuning of the path, adjusting route points, or adding additional path segments. The difference between the actual error and the expected error in path tracking can be used as the first path planning information during the movement of the industrial robot. For example, if the correction response value indicates that the robot needs to make additional turning adjustments in the path, the corrected path segment length and path angle change are calculated, and this information constitutes the first path planning information; then, according to the speed compensation value, the impact of the speed adjustment on the path planning is calculated, including determining in which path segments the speed needs to be increased or decreased and calculating the acceleration or deceleration interval required in the path to meet the speed requirement after compensation, and the acceleration or deceleration interval is used as the second path planning information during the movement of the industrial robot. In other embodiments, other methods can also be used to determine the second path planning information during the movement of the industrial robot, which is not limited here.

[0116] In addition, in the specific implementation, the path planning cost of the industrial robot during the movement process can be determined by the first path planning information and the second path planning information in the following manner, namely: the path planning cost of the industrial robot during the movement process = weight factor 1*(corrected path length-original path length)+weight factor 2*(time consumption after speed compensation-original time consumption), wherein weight factor 1 and weight factor 2 can be set according to expert experience or industrial robot control principles, and are not limited here. In addition, the corrected path length and the original path length belong to the first path planning information, and the time consumption after speed compensation and the original time consumption belong to the second path planning information, which will not be repeated here.

[0117] It should be noted that the first path planning information in the present application represents the path planning data generated according to the corrected response value during the movement of the industrial robot, and represents the path changes and adjustment requirements introduced by the corrected response value during the path tracking process; the second path planning information represents the path planning data generated according to the speed compensation value during the movement of the industrial robot, and represents the speed adjustment requirements introduced by the speed compensation value in the path planning and its impact on the path; the path planning cost represents the measure of the control complexity and degree of adjustment required to achieve effective path tracking during the path planning process, including the difficulty of path adjustment, the control accuracy requirements, the complexity of speed compensation, and the details of path correction.

[0118] In specific implementation, the dynamic adjustment of the motion path of the industrial robot according to the path planning cost can be determined in the following manner, namely: first, using a path optimization algorithm, such as the Dijkstra algorithm or the A* algorithm, to analyze the complexity of the path adjustment, and judging whether it is necessary to re-plan the path points or modify the path segments in the current path through the calculation results, wherein the control accuracy requirement in the path is evaluated by calculating the error between the actual path and the target path, for example, using the root mean square error (RMSE) to quantify the deviation; secondly, based on the speed adjustment compensation value, using a speed adjustment model (such as a PID control algorithm) to evaluate the adjustment complexity, including the analysis of the acceleration and deceleration requirements, and the impact of speed changes on the path; then , based on the evaluation results, use dynamic programming or optimization algorithms to recalculate the path points, for example, adjust the path points to reduce the correction amount or improve the path smoothness; finally, adjust the speed configuration by adjusting the speed curve and control parameters to meet the new speed compensation requirements, including replanning the speed curve, such as optimizing the speed distribution through Bezier curves or spline curves, and continuously monitor the robot path tracking effect, use real-time feedback mechanisms such as sensor data and control system output to ensure that the actual motion path matches the optimized path, and analyze real-time data such as path tracking error and speed matching to ensure the effectiveness of the adjustment and ensure that the actual motion path matches the optimized path, thereby improving the overall efficiency and control accuracy of path planning.

[0119] 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 exemplary hardware and / or software of an industrial robot motion control system according to some embodiments of the present application, the industrial robot motion control system 400 includes: a monitoring module 401, a processing module 402 and an execution module 403, which are described as follows:

[0120] An industrial robot motion control system, characterized by comprising:

[0121] Monitoring module 401, in this application, the monitoring module 401 is mainly used to monitor the motion path of the industrial robot and obtain the navigation path information of the industrial robot on the target navigation path;

[0122] Processing module 402, in this application, the processing module 402 is mainly used to determine the global path points during the movement of the industrial robot through the navigation path information;

[0123] The processing module 402 is further used to determine the visual path coordinates when the motion path of the industrial robot is adjusted, determine the deviation feature domain of the motion path of the industrial robot through the visual path coordinates and the global path point, and then determine the correction response value of the industrial robot during path tracking through the deviation feature domain;

[0124] The processing module 402 is further used to obtain a speed constraint boundary of the industrial robot during motion path matching, determine path planning information of the industrial robot during motion according to the speed constraint boundary and the current position of the industrial robot, and further determine a speed regulation compensation value of the industrial robot in global static path planning according to the path planning information;

[0125] The execution module 403 in the present application is mainly used to determine the path planning cost during the movement of the industrial robot according to the correction response value and the speed regulation compensation value, and dynamically adjust the movement path of the industrial robot according to the path planning cost.

[0126] In addition, the present application also provides a computer device, which includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned industrial robot motion path control method.

[0127] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device for implementing an industrial robot motion path control method according to some embodiments of the present application. The industrial robot motion path control method in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.

[0128] The processor 501 may be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC) or one or more for controlling the execution of the industrial robot motion path control method in the present application.

[0129] The communication bus 502 may be used to transmit information between the above-mentioned components.

[0130] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0131] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The motion path control method of the industrial robot in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0132] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0133] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0134] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0135] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned industrial robot motion path control method is implemented.

[0136] Although the preferred embodiments of the present application have been described, those skilled in the art may make other 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 falling within the scope of the present application.

[0137] 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 equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A motion path control method for an industrial robot, characterized in that: The steps include: Monitor the motion path of the industrial robot and obtain the navigation path information of the industrial robot on the target navigation path; Determine the global path points during the movement of the industrial robot through the navigation path information; Determine the visual path coordinates when the motion path of the industrial robot is adjusted, determine the deviation feature domain of the motion path of the industrial robot through the visual path coordinates and the global path points, and then determine the correction response value of the industrial robot during path tracking through the deviation feature domain; Obtaining a speed constraint boundary of the industrial robot during motion path matching, determining path planning information of the industrial robot during motion according to the speed constraint boundary and the current position of the industrial robot, and then determining a speed regulation compensation value of the industrial robot in global static path planning according to the path planning information; Determine the path planning cost of the industrial robot during its movement according to the corrected response value and the speed regulation compensation value, and dynamically adjust the movement path of the industrial robot according to the path planning cost; Wherein, determining the path planning cost during the motion of the industrial robot according to the correction response value and the speed regulation compensation value specifically includes: Determine first path planning information during the movement of the industrial robot according to the corrected response value; Determine second path planning information during the movement of the industrial robot according to the speed regulation compensation value; Determine the path planning cost during the movement of the industrial robot by using the first path planning information and the second path planning information; Among them, the path planning cost during the movement of the industrial robot = weight factor 1*(corrected path length - original path length) + weight factor 2*(time consumption after speed compensation - original time consumption). The corrected path length and the original path length belong to the first path planning information, and the time consumption after speed compensation and the original time consumption belong to the second path planning information.

2. The method according to claim 1, characterized in that Determining the global path point during the motion of the industrial robot through the navigation path information specifically includes: Extracting a path control set of the industrial robot movement from the navigation path information; Determining a navigation path marking coefficient during the movement of the industrial robot according to the path control set, wherein the navigation path marking coefficient is a parameter reflecting the degree of influence of a certain node on the overall effect of the navigation path in path planning; Determining a global path membership during the motion of the industrial robot, wherein the global path membership is used to measure the criticality of a node in the global path; A global path point is determined according to the navigation path marking coefficient and the global path membership.

3. The method according to claim 2, characterized in that Extracting the path control set of the industrial robot movement in the navigation path information specifically includes: Determine the path control nodes of the industrial robot's motion path; Determine the control feature quantity in the navigation path information according to the path control node; The path control set of the industrial robot motion is determined based on all control characteristic quantities.

4. The method according to claim 1, characterized in that The deviation feature domain of determining the motion path of the industrial robot through the visual path coordinates and the global path point specifically includes: Determining a disordered recognition prediction amount of the motion path of the industrial robot according to the visual path coordinates, wherein the disordered recognition prediction amount is a parameter used to measure the deviation between each path point and the actual expected path in the visual navigation of the industrial robot; Obtaining a total amount of ordered recognition of a motion path of the industrial robot, wherein the total amount of ordered recognition is a quantity used to measure the recognition quality and accuracy of the industrial robot during a path tracking process; Determine the identification deviation characteristics of the motion path of the industrial robot according to the global path point; A deviation feature domain is determined based on the disordered recognition prediction quantity, the ordered recognition total quantity and the recognition deviation feature.

5. The method according to claim 1, characterized in that Determining the path planning information during the motion of the industrial robot according to the speed constraint boundary and the current position of the industrial robot specifically includes: Determining path planning characteristics during the motion of the industrial robot according to the speed constraint boundary; Determine the path allocation amount during the movement of the industrial robot through the current position of the industrial robot; Path planning information during the movement of the industrial robot is determined according to the path planning characteristics and the path allocation amount.

6. The method according to claim 1, characterized in that The industrial robot is a handling robot.

7. An industrial robot motion control system, which uses the method according to any one of claims 1 to 6 to control the motion path of the industrial robot, characterized in that: The system includes: A monitoring module is used to monitor the motion path of the industrial robot and obtain navigation path information of the industrial robot on the target navigation path; A processing module, used to determine the global path points during the movement of the industrial robot through the navigation path information; The processing module is further used to determine the visual path coordinates when the motion path of the industrial robot is adjusted, determine the deviation feature domain of the motion path of the industrial robot through the visual path coordinates and the global path point, and then determine the correction response value of the industrial robot during path tracking through the deviation feature domain; The processing module is further used to obtain a speed constraint boundary of the industrial robot when matching a motion path, determine path planning information of the industrial robot during motion according to the speed constraint boundary and the current position of the industrial robot, and further determine a speed regulation compensation value of the industrial robot in global static path planning according to the path planning information; The execution module is used to determine the path planning cost of the industrial robot during the movement according to the correction response value and the speed regulation compensation value, and dynamically adjust the movement path of the industrial robot according to the path planning cost.

8. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the industrial robot motion path control method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the industrial robot motion path control method according to any one of claims 1 to 6 is implemented.

Images