Industrial robot dynamic path planning learning method and system

Abstract

The application is suitable for the technical field of dynamic path planning, and particularly relates to an industrial robot dynamic path planning learning method and system.The method comprises the following steps: S100: demarcating a working area of an industrial robot, selecting a deployment position of a plurality of marker lights in each industrial robot, setting the color of each marker light, and generating a combined code, wherein the combined code of each industrial robot is different; collecting video monitoring data containing all industrial robots by using a video monitoring device pre-deployed in the working area; according to a preset step, a plurality of snapshots are intercepted, and the position of the industrial robot is located through the combined code; and S200: grid division is performed on the working area, and a reference point is selected.The application can realize incremental planning of the industrial robot by defining a conflict line, can dynamically adjust the moving route, is convenient for quickly adapting to changes in obstacles, and greatly improves the obstacle avoidance efficiency of the industrial robot.

Description

Technical Field

[0001] This invention relates to the field of dynamic path planning technology, and more particularly to a dynamic path planning learning method and system for industrial robots. Background Technology

[0002] Industrial robots are frequently used in industrial production, such as logistics handling robots, material delivery robots, and automated guided vehicles (AGVs).

[0003] During the execution of production tasks, positioning is generally achieved through methods such as QR code landmarks, LiDAR, and vision cameras. However, these positioning methods are based on individual units and cannot observe the overall situation in real time. When industrial robots approach each other during movement, they use braking to avoid each other. This avoidance method is prone to congestion and collisions, which greatly affects the working efficiency of industrial robots.

[0004] Therefore, "how to use indicator lights to achieve global perception of industrial robots" is the technical problem that this invention aims to solve. Summary of the Invention

[0005] The purpose of this invention is to provide a dynamic path planning learning method and system for industrial robots, in order to solve the problem of "how to use indicator lights to achieve global perception of industrial robots" mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A dynamic path planning learning method for industrial robots, the method comprising:

[0008] S100: Define the working area of ​​the industrial robots. In each industrial robot, select the deployment positions of several indicator lights, set the color of each indicator light, and generate a combination code. The combination code of each industrial robot is different. Use video monitoring equipment pre-deployed in the working area to collect video monitoring data containing all industrial robots. According to the preset step size, extract several snapshots and locate the position of the industrial robot through the combination code.

[0009] S200: Divide the work area into grids, select reference points, and construct a coordinate system. Receive production tasks uploaded by a preset terminal, locate the target robot that will execute the production task, determine the initial coordinates of the target robot, and traverse the endpoint coordinates from the production task to generate a movement route. The movement route consists of several grid lines of the same length, with at least a first grid line and a second grid line obtained. Mark the line coordinates of each grid line.

[0010] S300: Obtain the configuration data of the target robot. When the target robot reaches the first grid line, calculate the estimated arrival time of the second grid line based on the position and the length of the grid line, and generate a lookup table. The lookup table consists of the line coordinates of the second grid line and the estimated arrival time. Establish the correspondence between the target robot and the lookup table. Determine whether there are any identical items in all lookup tables. If so, define the second grid line corresponding to the identical item as a conflict line. Use the nearest neighbor algorithm to find the alternative route of the conflict line and update the movement route.

[0011] Furthermore, the steps of defining the working area of ​​the industrial robot, selecting deployment positions for several indicator lights within each industrial robot, and setting the color of each indicator light include:

[0012] Establish numbering rules to determine the number of each industrial robot;

[0013] Integrate the numbering and combined codes to generate a lookup table.

[0014] Furthermore, the step of generating the combined code includes:

[0015] Configure the flashing frequency of each indicator light, record the flashing time, and dynamically update the position.

[0016] The production tasks are clustered into several types, and the combined coding is adjusted.

[0017] Furthermore, the steps of dividing the work area into a grid, selecting reference points, constructing a coordinate system, and receiving production tasks uploaded by a preset terminal include:

[0018] Set the priority for each production task, wherein the priorities include at least: high, medium and low;

[0019] Identify the priority of each identical item and sort them in descending order of priority, defining the first identical item in the sort as the priority item;

[0020] Grant access to the conflict line to the aforementioned priority item.

[0021] Furthermore, the steps of locating the initial coordinates of the target robot and traversing the endpoint coordinates from the production task to generate the movement route include:

[0022] Define the two endpoints of the grid line as grid points;

[0023] Based on the configuration data and production tasks, the estimated time for the target robot to reach each grid point in the movement route is estimated, and the estimated time is corrected based on the location.

[0024] Furthermore, the step of defining the second grid line corresponding to the same item as a conflict line includes:

[0025] Define the two ends of the conflict line as the first node and the second node;

[0026] Starting from the first node and ending at the second node, the replacement route is obtained by connecting the starting point and the ending point using the grid point and nearest neighbor algorithm.

[0027] Furthermore, the method also includes:

[0028] Sensor data is collected using sensing devices pre-deployed in the work area, wherein the sensing devices include at least: RFID receivers and lidar;

[0029] Based on the sensor data and configuration data, it is determined whether there are obstacles within the preset range of the target robot. If so, a pre-built avoidance mechanism is triggered.

[0030] Furthermore, the system includes:

[0031] The positioning module is used to delineate the working area of ​​the industrial robot. In each industrial robot, the deployment positions of several indicator lights are selected, the color of each indicator light is set, and a combination code is generated. The combination code of each industrial robot is different. Using video monitoring equipment pre-deployed in the working area, video monitoring data containing all industrial robots is collected. According to a preset step size, several snapshots are extracted, and the position of the industrial robot is located through the combination code.

[0032] The calibration module is used to divide the work area into grids, select reference points, and construct a coordinate system. It receives production tasks uploaded by a preset terminal, finds the target robot that executes the production task, locates the initial coordinates of the target robot, and traverses the endpoint coordinates from the production task to generate a movement route. The movement route consists of several grid lines of the same length, with at least a first grid line and a second grid line obtained. The line coordinates of each grid line are calibrated.

[0033] The update module is used to acquire the configuration data of the target robot. When the target robot reaches the first grid line, it calculates the estimated arrival time of the second grid line based on the position and the length of the grid line, and generates a lookup table. The lookup table consists of the line coordinates of the second grid line and the estimated arrival time. It establishes a correspondence between the target robot and the lookup table, and determines whether there are any identical entries in all lookup tables. If so, the second grid line corresponding to the identical entry is defined as a conflict line. The nearest neighbor algorithm is used to find the alternative route for the conflict line and update the movement route.

[0034] Furthermore, the positioning module includes:

[0035] The designation unit is used to define numbering rules and determine the number of each industrial robot;

[0036] A generation unit is used to integrate the numbering and combined coding to generate a lookup table;

[0037] The recording unit is used to configure the flashing frequency of each indicator light, record the flashing time, and dynamically update the position.

[0038] An adjustment unit is used to cluster the production tasks into several types and adjust the combined encoding.

[0039] Furthermore, the calibration module includes:

[0040] The setting unit is used to set the priority of each production task, wherein the priority includes at least: high, medium and low;

[0041] The identification unit is used to identify the priority of each identical item and sort them in descending order of priority, defining the identical item at the top of the sort as the priority item.

[0042] An open unit is used to grant access to the conflict line to the priority item;

[0043] An initial definition unit is used to define the two endpoints of the grid line as grid points;

[0044] The correction unit is used to estimate the estimated time for the target robot to reach each grid point in the movement route based on the configuration data and production task, and to correct the estimated time based on the location.

[0045] Compared with the prior art, the beneficial effects of the present invention are:

[0046] By deploying color-coded marker lights on industrial robots, their identities can be identified, enabling rapid visual positioning and significantly improving the efficiency of anomaly detection. Acquiring video surveillance data allows for global perception of the robots, enabling advance planning of obstacle avoidance strategies and enhancing the collaborative work efficiency of multiple robots. Generating grid lines further improves the positioning efficiency and navigation accuracy of global perception, facilitating dynamic path planning and adjustment. Defining conflict lines enables incremental planning for industrial robots, allowing for dynamic adjustments to their movement routes and rapid adaptation to obstacle changes, thus greatly improving obstacle avoidance efficiency. Attached Figure Description

[0047] Figure 1A flowchart illustrating the dynamic path planning and learning method for industrial robots provided in this embodiment of the invention;

[0048] Figure 2 This is a first sub-flowchart of the dynamic path planning and learning method for industrial robots provided in an embodiment of the present invention;

[0049] Figure 3 This is a second sub-flowchart of the dynamic path planning and learning method for industrial robots provided in an embodiment of the present invention;

[0050] Figure 4 The third sub-flowchart of the dynamic path planning and learning method for industrial robots provided in this embodiment of the invention;

[0051] Figure 5 This is a block diagram of the industrial robot dynamic path planning and learning system provided in an embodiment of the present invention.

[0052] Figure 6 A block diagram of the localization module in the dynamic path planning and learning system for industrial robots provided in an embodiment of the present invention;

[0053] Figure 7 A block diagram showing the composition of the calibration module in the dynamic path planning and learning system for industrial robots provided in this embodiment of the invention;

[0054] Figure 8 This is a block diagram of the update module in the dynamic path planning and learning system for industrial robots provided in an embodiment of the present invention. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0056] In Example 1, Figure 1 The implementation flow of the dynamic path planning learning method for industrial robots provided in this embodiment of the invention is illustrated below, and is described in detail below:

[0057] S100: Define the working area of ​​the industrial robots. In each industrial robot, select the deployment positions of several indicator lights, set the color of each indicator light, and generate a combination code. The combination code of each industrial robot is different. Using video monitoring equipment pre-deployed in the working area, collect video monitoring data containing all industrial robots. According to a preset step size, extract several snapshots. The position of the industrial robot is located through the combination code.

[0058] The work area, or "work zone," is designated for industrial robots to transfer goods. These robots include logistics handling robots, material delivery robots, and automated guided vehicles (AGVs). Several deployment positions are identified on the top or sides of the industrial robots. These positions are selected by the robot management personnel and are primarily used to deploy indicator lights, which are multi-color controllable indicator lights. Each indicator light has a preset color (e.g., red, green, blue, and yellow). Combining the color states of the indicator lights on each industrial robot creates a combined code. This combined code represents key information such as the robot's current position, operating status, task stage, or path planning status. For example, in daily operation, the combined code for industrial robot A is "red-blue-blue." When A enters a high-risk area, one of the indicator lights turns red, changing the combined code to "red-red-blue," indicating that A needs to slow down or wait to avoid obstacles. It's important to note that each industrial robot has a unique combined code. This facilitates robot identification and improves positioning efficiency.

[0059] Access to video surveillance equipment installed within the work area is granted, and video surveillance data is collected. This data should include all industrial robots. If blind spots exist, multiple video surveillance devices can be deployed to eliminate them. Multiple snapshots are extracted from the video surveillance data at preset intervals (e.g., 1 second). Image recognition algorithms (e.g., color extraction, object detection, and deep learning models) are used to identify the position of each industrial robot in the current snapshot. Furthermore, by determining the positional changes of industrial robots in adjacent snapshots, tracking and monitoring of the robots can be achieved. This positioning method does not rely on additional positioning hardware, is suitable for large-scale centralized management of industrial robots, and effectively achieves global perception. It allows for advance adjustment of the robot's movement path through an "omniscient perspective," whereas existing positioning methods such as LiDAR and GPS operate on an individual basis, resulting in poor obstacle avoidance capabilities.

[0060] S200: Divide the work area into grids, select reference points, and construct a coordinate system. Receive production tasks uploaded by a preset terminal, locate the target robot that will execute the production task, determine the initial coordinates of the target robot, and traverse the endpoint coordinates from the production task to generate a movement route. The movement route consists of several grid lines of the same length, with at least a first grid line and a second grid line obtained. Mark the line coordinates of each grid line.

[0061] The work area is divided into grids, with each grid unit representing a specific spatial region. For example, the work area can be divided into square grids with sides of 50 cm. A reference point (such as a corner or center of the work area) is selected, and a coordinate system is constructed using this reference point as the origin. Production tasks uploaded by preset terminals (such as operator terminals or production control systems) are received. The production tasks should include: the object performing the task, the goods to be transferred, the starting coordinates, and the ending coordinates. The object performing the task in the production task is defined as the target robot. The position of the target robot is determined according to the positioning method in S100, and the initial coordinates are read. It should be noted that if the target robot is located on a grid line rather than a grid point, the coordinates of the nearest grid point can be used as its initial coordinates. The movement route is generated using the initial coordinates and the ending coordinates in the production task.

[0062] The movement path is refined into several grid lines. A grid line is a line segment consisting of two grid points and their connecting line. Starting from the initial coordinates, the first grid line in the refined movement path is defined as the first grid line, and so on, to obtain the nth grid line. Using the coordinate system, the line coordinates of each grid line are read, where the line coordinates are composed of the coordinates of the two endpoints of the grid line.

[0063] S300: Obtain the configuration data of the target robot. When the target robot reaches the first grid line, calculate the estimated arrival time of the second grid line based on the position and the length of the grid line, and generate a lookup table. The lookup table consists of the line coordinates of the second grid line and the estimated arrival time. Establish the correspondence between the target robot and the lookup table. Determine whether there are any identical items in all lookup tables. If so, define the second grid line corresponding to the identical item as a conflict line. Use the nearest neighbor algorithm to find the alternative route of the conflict line and update the movement route.

[0064] The process involves acquiring the target robot's configuration data, including its speed and mobility. When the target robot reaches one endpoint of the first grid line, the estimated arrival time (ERT) is calculated based on the grid line length and the robot's speed. A lookup table is created using the line coordinates of each grid line and its corresponding ERT. This lookup table stores the robot's arrival time at the next grid line. By constructing this lookup table, incremental planning can be used to proactively avoid obstacles. Each industrial robot corresponds to a lookup table. By integrating all the lookup tables, duplicate entries are checked. If duplicates are found, it indicates that two or more industrial robots are about to pass through. The same grid line poses a collision risk. We define the same grid line as a conflict line, identify its two endpoints, and reconnect them using the nearest neighbor algorithm to obtain an alternative route. Furthermore, when two industrial robots are about to cross the same grid line (let's say grid line X), their priorities are determined based on the priorities of their respective production tasks. The robot with the higher priority continues to move along grid line X, while the other robot moves along the alternative route. When multiple industrial robots are about to cross the same grid line, we identify the highest-priority robot, which continues to move along grid line X, while the remaining robots move along their respective alternative routes.

[0065] In Example 2, Figure 2 The implementation flow of the dynamic path planning learning method for industrial robots provided by an embodiment of the present invention is illustrated. The following details the steps of defining the working area of ​​the industrial robot, selecting the deployment positions of several marker lights in each industrial robot, and setting the color of each marker light:

[0066] S101: Establish numbering rules and determine the number of each industrial robot.

[0067] Each industrial robot is assigned a unique number according to a numbering system established by the industrial robot management personnel.

[0068] S102: Integrate the number and combined code to generate a lookup table.

[0069] Each industrial robot corresponds to a unique combination code, and each industrial robot's serial number is also different. Establish a correspondence between industrial robots, serial numbers, and combination codes, and store this correspondence using a lookup table.

[0070] In Example 3, Figure 2The implementation flow of the dynamic path planning learning method for industrial robots provided by an embodiment of the present invention is illustrated below. The steps for generating combined codes are described in detail below:

[0071] S103: Configure the flashing frequency of each indicator light, record the flashing time, and dynamically update the position.

[0072] The flashing frequency of each indicator light is determined, and the flashing time of each indicator light is recorded. When the indicator light flashes, the position of the industrial robot is updated.

[0073] In actual production, the moving speed of industrial robots is generally between 0.5m / s and 1.5m / s. This speed is not particularly fast, and the position of the industrial robot does not change drastically in a short period. Therefore, intermittent positioning of the industrial robot can be achieved by setting a flashing frequency to reduce the amount of data processing. For example, given three industrial robots A, B, and C, with A flashing at 5 seconds / time, B at 3 seconds / time, and C at 1 second / time, snapshots are taken from video surveillance data at 1-second intervals. In the first second snapshot, only one industrial robot can be identified, so there is no need for combined coding identification. In the third second snapshot, two industrial robots can be identified, requiring combined coding identification. However, this also reduces the amount of data processing and improves the obstacle avoidance efficiency of the industrial robots.

[0074] S104: Cluster the production tasks into several types and adjust the combined coding.

[0075] To improve the recognition efficiency of combined codes, production tasks are clustered into multiple types, with each type corresponding to a feature in the combined code. For example, if three types of goods, A, B, and C, need to be transported to a designated location, the production tasks are divided into three types. The industrial robot performing production task A has its combined code starting with red, further improving the recognition and positioning accuracy of the industrial robot.

[0076] In Example 4, Figure 3 The implementation flow of the dynamic path planning learning method for industrial robots provided by an embodiment of the present invention is illustrated. The following details the steps of dividing the work area into a grid, selecting reference points, constructing a coordinate system, and receiving production tasks uploaded by a preset terminal:

[0077] S201: Set the priority for each production task, wherein the priority includes at least: high, medium and low.

[0078] The priority of each production task is determined, with the priority set by the industrial robot manager.

[0079] S202: Identify the priority of each identical item and sort them in descending order of priority, defining the first identical item in the sort as the priority item.

[0080] When multiple industrial robots arrive at the second grid line at the same time, the one with the highest priority is identified and defined as the priority item. The priority of an industrial robot refers to the priority of its corresponding production task.

[0081] S203: Grant the priority item permission to use the conflict line.

[0082] The conflict line is only open to industrial robots corresponding to the priority items, thus ensuring that high-priority production tasks can be executed smoothly.

[0083] In Example 5, Figure 3 The implementation flow of the dynamic path planning learning method for industrial robots provided by an embodiment of the present invention is illustrated below. The steps of locating the initial coordinates of the target robot, traversing the endpoint coordinates from the production task, and generating the movement route are described in detail below:

[0084] S204: Define the two endpoints of the grid line as grid points.

[0085] S205: Based on the configuration data and production task, estimate the estimated time for the target robot to reach each grid point in the movement route, and correct the estimated time based on the location.

[0086] Based on the configuration data of the industrial robots, the estimated time for the target robot to reach each grid point is calculated. The estimated time is then updated based on the real-time location of the target robot, making it easier for managers to schedule production more accurately.

[0087] In Example 6, Figure 4 The implementation flow of the dynamic path planning learning method for industrial robots provided by an embodiment of the present invention is shown below. The step of defining the second grid line corresponding to the same item as a conflict line is described in detail below:

[0088] S301: Define the two ends of the conflict line as the first node and the second node.

[0089] Define the grid points at both ends of the conflict line as the first node and the second node.

[0090] S302: Starting from the first node and ending at the second node, the replacement route is obtained by connecting the starting point and the ending point using the grid point and nearest neighbor algorithm.

[0091] Other grid points can be used to connect the starting point and the ending point, which are other optional paths in the target robot's path planning. Based on this, the nearest neighbor algorithm is used to select the grid point closest to the current node as the next moving point, starting from the starting point, and so on, until the ending point is reached. The resulting route is defined as the replacement route.

[0092] In Example 7, unlike Example 1, the method further includes:

[0093] Sensor data is collected using sensing devices pre-deployed in the work area, wherein the sensing devices include at least: RFID receivers and lidar;

[0094] Based on the sensor data and configuration data, it is determined whether there are obstacles within the preset range of the target robot. If so, a pre-built avoidance mechanism is triggered.

[0095] Using sensing devices, corresponding sensor data is collected to determine whether there are obstacles or potential collision risks in the area that the target robot is about to enter. If an obstacle is detected, an avoidance mechanism is immediately triggered. The avoidance mechanism is a supplement to the above-mentioned alternative route and is a collection of various avoidance methods, such as pausing forward. By triggering the avoidance mechanism, it can be ensured that the target robot can perform its task without collision.

[0096] Figure 5 This diagram illustrates the structural block diagram of an industrial robot dynamic path planning learning system provided in an embodiment of the present invention. The industrial robot dynamic path planning learning system 1 includes:

[0097] The positioning module 11 is used to delineate the working area of ​​the industrial robot. In each industrial robot, the deployment positions of several indicator lights are selected, the color of each indicator light is set, and a combination code is generated. The combination code of each industrial robot is different. Using video monitoring equipment pre-deployed in the working area, video monitoring data containing all industrial robots is collected. According to a preset step size, several snapshots are extracted, and the position of the industrial robot is located through the combination code.

[0098] The calibration module 12 is used to divide the work area into grids, select reference points, and construct a coordinate system. It receives production tasks uploaded by a preset terminal, finds the target robot that executes the production task, locates the initial coordinates of the target robot, and traverses the endpoint coordinates from the production task to generate a movement route. The movement route consists of several grid lines of the same length, at least obtaining the first grid line and the second grid line, and calibrating the line coordinates of each grid line.

[0099] The update module 13 is used to acquire the configuration data of the target robot. When the target robot reaches the first grid line, it calculates the estimated arrival time of the second grid line based on the position and the length of the grid line, and generates a lookup table. The lookup table consists of the line coordinates of the second grid line and the estimated arrival time. It establishes a correspondence between the target robot and the lookup table, and determines whether there are any identical items in all the lookup tables. If so, the second grid line corresponding to the identical item is defined as a conflict line. The nearest neighbor algorithm is used to find the alternative route of the conflict line and update the movement route.

[0100] Figure 6 This diagram illustrates the structural block diagram of the industrial robot dynamic path planning learning system provided in an embodiment of the present invention. The positioning module 11 includes:

[0101] Unit 111 is used to formulate numbering rules and determine the number of each industrial robot;

[0102] Generation unit 112 is used to integrate the number and combined code to generate a lookup table;

[0103] The recording unit 113 is used to configure the flashing frequency of each indicator light, record the flashing time, and dynamically update the position.

[0104] The adjustment unit 114 is used to cluster the production tasks into several types and adjust the combined encoding.

[0105] Figure 7 This diagram illustrates the structural block diagram of the industrial robot dynamic path planning learning system provided in an embodiment of the present invention. The calibration module 12 includes:

[0106] Setting unit 121 is used to set the priority of each production task, wherein the priority includes at least: high, medium and low;

[0107] The identification unit 122 is used to identify the priority of each identical item and sort them in order of priority from high to low, and define the identical item at the top of the sort as the priority item.

[0108] Open unit 123 is used to grant access to the conflict line to the priority item;

[0109] Initial definition unit 124 is used to define the two endpoints of the grid line as grid points;

[0110] The correction unit 125 is used to estimate the estimated time for the target robot to reach each grid point in the movement route based on the configuration data and production task, and to correct the estimated time based on the location.

[0111] Figure 8This diagram illustrates the structural composition of the industrial robot dynamic path planning learning system provided in an embodiment of the present invention. The update module 13 includes:

[0112] The initial definition unit 131 is used to define the two ends of the conflict line as the first node and the second node;

[0113] Unit 132 is obtained, which is used to connect the starting point and the ending point with the first node as the starting point and the second node as the ending point, using the grid point and nearest neighbor algorithm to obtain the replacement route.

[0114] The positioning module 11 is mainly used to complete step S100, the calibration module 12 is mainly used to complete step S200, and the update module 13 is mainly used to complete step S300.

[0115] The formulating unit 111 is mainly used to complete step S101, the generating unit 112 is mainly used to complete step S102, the recording unit 113 is mainly used to complete step S103, and the adjusting unit 114 is mainly used to complete step S104.

[0116] The setting unit 121 is mainly used to complete step S201, the identification unit 122 is mainly used to complete step S202, the opening unit 123 is mainly used to complete step S203, the initial definition unit 124 is mainly used to complete step S204, and the correction unit 125 is mainly used to complete step S205.

[0117] The initial definition unit 131 is mainly used to complete step S301, and the obtained unit 132 is mainly used to complete step S302.

[0118] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0119] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0120] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A dynamic path planning learning method for industrial robots, characterized in that, The method includes: S100: Define the working area of ​​the industrial robots. In each industrial robot, select the deployment positions of several indicator lights, set the color of each indicator light, and generate a combination code. The combination code of each industrial robot is different. Use video monitoring equipment pre-deployed in the working area to collect video monitoring data containing all industrial robots. According to the preset step size, extract several snapshots and locate the position of the industrial robot through the combination code. S200: Divide the work area into grids, select reference points, and construct a coordinate system. Receive production tasks uploaded by a preset terminal, locate the target robot that will execute the production task, determine the initial coordinates of the target robot, and traverse the endpoint coordinates from the production task to generate a movement route. The movement route consists of several grid lines of the same length, with at least a first grid line and a second grid line obtained. Mark the line coordinates of each grid line. S300: Obtain the configuration data of the target robot. When the target robot reaches the first grid line, calculate the estimated arrival time of the second grid line based on the position and the length of the grid line, and generate a lookup table. The lookup table consists of the line coordinates of the second grid line and the estimated arrival time. Establish the correspondence between the target robot and the lookup table. Determine whether there are any identical items in all lookup tables. If so, define the second grid line corresponding to the identical item as a conflict line. Use the nearest neighbor algorithm to find the alternative route of the conflict line and update the movement route.

2. The industrial robot dynamic path planning learning method according to claim 1, characterized in that, The steps of defining the working area of ​​the industrial robot, selecting deployment positions for several indicator lights within each industrial robot, and setting the color of each indicator light include: Establish numbering rules to determine the number for each industrial robot; Integrate the numbering and combined codes to generate a lookup table.

3. The industrial robot dynamic path planning learning method according to claim 2, characterized in that, The step of generating the combined code includes: Configure the flashing frequency of each indicator light, record the flashing time, and dynamically update the position. The production tasks are clustered into several types, and the combined coding is adjusted.

4. The industrial robot dynamic path planning learning method according to claim 1, characterized in that, The steps of dividing the work area into grids, selecting reference points, constructing a coordinate system, and receiving production tasks uploaded by a preset terminal include: Set the priority for each production task, wherein the priorities include at least: high, medium and low; Identify the priority of each identical item and sort them in descending order of priority, defining the first identical item in the sort as the priority item; Grant access to the conflict line to the aforementioned priority item.

5. The industrial robot dynamic path planning learning method according to claim 4, characterized in that, The steps of locating the initial coordinates of the target robot and traversing the endpoint coordinates from the production task to generate the movement route include: Define the two endpoints of the grid line as grid points; Based on the configuration data and production tasks, the estimated time for the target robot to reach each grid point in the movement route is estimated, and the estimated time is corrected based on the location.

6. The industrial robot dynamic path planning learning method according to claim 5, characterized in that, The step of defining the second grid line corresponding to the same item as a conflict line includes: Define the two ends of the conflict line as the first node and the second node; Starting from the first node and ending at the second node, the replacement route is obtained by connecting the starting point and the ending point using the grid point and nearest neighbor algorithm.

7. The industrial robot dynamic path planning learning method according to claim 1, characterized in that, The method further includes: Sensor data is collected using sensing devices pre-deployed in the work area, wherein the sensing devices include at least: RFID receivers and lidar; Based on the sensor data and configuration data, it is determined whether there are obstacles within the preset range of the target robot. If so, a pre-built avoidance mechanism is triggered.

8. An industrial robot dynamic path planning learning system, characterized in that, The system includes: The positioning module is used to delineate the working area of ​​the industrial robot. In each industrial robot, the deployment positions of several indicator lights are selected, the color of each indicator light is set, and a combination code is generated. The combination code of each industrial robot is different. Using video monitoring equipment pre-deployed in the working area, video monitoring data containing all industrial robots is collected. According to a preset step size, several snapshots are extracted, and the position of the industrial robot is located through the combination code. The calibration module is used to divide the work area into grids, select reference points, and construct a coordinate system. It receives production tasks uploaded by a preset terminal, finds the target robot that executes the production task, locates the initial coordinates of the target robot, and traverses the endpoint coordinates from the production task to generate a movement route. The movement route consists of several grid lines of the same length, with at least a first grid line and a second grid line obtained. The line coordinates of each grid line are calibrated. The update module is used to acquire the configuration data of the target robot. When the target robot reaches the first grid line, it calculates the estimated arrival time of the second grid line based on the position and the length of the grid line, and generates a lookup table. The lookup table consists of the line coordinates of the second grid line and the estimated arrival time. It establishes a correspondence between the target robot and the lookup table, and determines whether there are any identical entries in all lookup tables. If so, the second grid line corresponding to the identical entry is defined as a conflict line. The nearest neighbor algorithm is used to find the alternative route for the conflict line and update the movement route.

9. The industrial robot dynamic path planning learning system according to claim 8, characterized in that, The positioning module includes: The designation unit is used to define numbering rules and determine the number of each industrial robot; A generation unit is used to integrate the numbering and combined coding to generate a lookup table; The recording unit is used to configure the flashing frequency of each indicator light, record the flashing time, and dynamically update the position. An adjustment unit is used to cluster the production tasks into several types and adjust the combined encoding.

10. The industrial robot dynamic path planning learning system according to claim 8, characterized in that, The calibration module includes: The setting unit is used to set the priority of each production task, wherein the priority includes at least: high, medium and low; The identification unit is used to identify the priority of each identical item and sort them in descending order of priority, defining the identical item at the top of the sort as the priority item. An open unit is used to grant access to the conflict line to the priority item; An initial definition unit is used to define the two endpoints of the grid line as grid points; The correction unit is used to estimate the estimated time for the target robot to reach each grid point in the movement route based on the configuration data and production task, and to correct the estimated time based on the location.

Images