Industrial robot dynamic path planning learning method and system

Abstract

The invention is suitable for the technical field of dynamic path planning, and particularly relates to an industrial robot dynamic path planning learning method and system, and the method comprises the steps: S100, delimiting a working region of an industrial robot, selecting the deployment positions of a plurality of identification lamps in each industrial robot, setting the color of each identification lamp, and generating a combined code, wherein the combined codes of all the industrial robots are different, video monitoring equipment deployed in a working area in advance is utilized to collect video monitoring data containing all the industrial robots, a plurality of snapshots are intercepted according to a preset step length, and the positions of the industrial robots are positioned through the combined codes; and S200, carrying out grid division on the working area, and selecting a reference point. By defining the conflict line, the incremental planning of the industrial robot can be realized, the moving route can be dynamically adjusted, the obstacle change can be quickly adapted, and the obstacle avoidance efficiency of the industrial robot is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of dynamic path planning, and in particular to a dynamic path planning learning method and system for industrial robots. Background Art

[0002] Industrial robots are often used in industrial production, such as logistics handling robots, material distribution robots, and automatic guided transport robots.

[0003] In the process of executing production tasks, positioning is generally carried out through QR code landmarks, lidar and visual cameras; however, these positioning methods are based on the individual 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 can easily lead to congestion and collisions, greatly affecting the work efficiency of industrial robots.

[0004] Therefore, “how to use identification lights to perform global perception of industrial robots” is the technical problem that the present invention needs to solve. Summary of the Invention

[0005] The purpose of the present invention is to provide an industrial robot dynamic path planning learning method and system to solve the problem of "how to use identification lights to perform global perception of industrial robots" raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: An industrial robot dynamic path planning learning method, the method comprising: S100: Delineating a working area for the industrial robots, selecting the deployment locations of several identification lights for each industrial robot, setting the color of each identification light, and generating a combination code, wherein the combination code is different for each industrial robot. Using video surveillance equipment pre-deployed in the working area, video surveillance data of all industrial robots is collected, and several snapshots are captured according to a preset step size. The position of the industrial robot is then located using the combination code. S200: Gridding the work area, selecting reference points, and constructing a coordinate system, receiving a production task uploaded by a preset terminal, finding a target robot to perform the production task, locating the initial coordinates of the target robot, and traversing the end point coordinates from the production task to generate a movement route, wherein the movement route is composed of a plurality of grid lines of the same length, obtaining at least a first grid line and a second grid line, and calibrating 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, based on the position and the length of the grid line, calculate the estimated arrival time of the second grid line, generate a query table, wherein the query table consists of the line coordinate items and the estimated arrival time items of the second grid line, establish a correspondence between the target robot and the query table, determine whether there are identical items in all query tables, and if so, define the second grid line corresponding to the identical item as a conflict line, use the nearest neighbor algorithm to find a replacement route for the conflict line, and update the movement route.

[0007] Furthermore, the steps of defining the working area of ​​the industrial robot, selecting the deployment positions of several identification lights in each industrial robot, and setting the color of each identification light include: Formulate numbering rules and determine the number of each industrial robot; The numbers and combination codes are integrated to generate a comparison table.

[0008] Furthermore, the step of generating the combined code includes: Configure the flashing frequency of each marker light, record the flashing time, and dynamically update the position; The production tasks are clustered into several types, and the combination coding is adjusted.

[0009] Furthermore, the steps of dividing the working area into grids, selecting reference points, and constructing a coordinate system, and receiving the production task uploaded by the preset terminal include: Setting a priority for each production task, wherein the priority includes at least: high, medium, and low; Identify the priority corresponding to each identical item and sort them in descending order of priority, defining the identical item that comes first in the order as the priority item; Access to conflicting lines is granted to the priority item.

[0010] Furthermore, the steps of locating the initial coordinates of the target robot, traversing the end coordinates from the production task, and generating a moving route include: defining two endpoints of the grid line as grid points; Based on the configuration data and the production task, an estimated time for the target robot to reach each grid point in the moving route is estimated, and based on the position, the estimated time is corrected.

[0011] Furthermore, the step of defining the second grid line corresponding to the same item as a conflict line includes: defining two ends of the conflict line as a first node and a second node; The first node is used as a starting point and the second node is used as an end point. The grid points and the nearest neighbor algorithm are used to connect the starting point and the end point to obtain an alternative route.

[0012] Furthermore, the method further comprises: Using sensor equipment pre-deployed in the work area to collect sensor data, wherein the sensor equipment at least includes: an RFID receiver and a laser radar; Based on the sensing data and configuration data, it is determined whether there is an obstacle object within the preset range of the target robot. If so, a pre-built avoidance mechanism is triggered.

[0013] Furthermore, the system includes: The positioning module is used to delineate the working area of ​​the industrial robots. For each industrial robot, the deployment positions of several identification lights are selected, the colors of each identification light are set, and a combination code is generated. The combination code is different for each industrial robot. Video surveillance equipment pre-deployed in the working area is used to collect video surveillance data including all industrial robots. Several snapshots are taken according to a preset step size. The position of the industrial robot is located using the combination code. a calibration module, configured to grid the work area, select reference points, and construct a coordinate system; receive a production task uploaded by a preset terminal; find a target robot to perform the production task; locate the initial coordinates of the target robot; and traverse the end coordinates from the production task to generate a movement route, wherein the movement route is composed of a plurality of grid lines of the same length, obtaining at least a first grid line and a second grid line, and calibrating the line coordinates of each grid line; An update module is configured to obtain configuration data of a target robot, calculate an estimated arrival time of a second grid line based on the position and the length of the grid line when the target robot reaches the first grid line, generate a lookup table consisting of line coordinate items and estimated arrival time items of the second grid line, establish a correspondence between the target robot and the lookup table, determine whether identical items exist in all lookup tables, and if so, define the second grid line corresponding to the identical item as a conflict line, use a nearest neighbor algorithm to find an alternative route for the conflict line, and update the movement route.

[0014] Furthermore, the positioning module includes: A formulation unit is used to formulate numbering rules and determine the number of each industrial robot; A generating unit, configured to integrate the numbers and combination codes to generate a comparison table; A recording unit configured to configure the flashing frequency of each marker 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 combination code.

[0015] Furthermore, the calibration module includes: A setting unit, configured to set a priority for each production task, wherein the priority includes at least: high, medium, and low; An identification unit is used to identify the priority corresponding to 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 opening unit, configured to open the right to use the conflicting line to the priority item; An initial definition unit, used to define 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 moving route based on the configuration data and the production task, and correct the estimated time based on the position.

[0016] Compared with the prior art, the present invention has the following beneficial effects: By deploying color identification lights on industrial robots, the identity of the industrial robots can be identified and visual positioning can be quickly performed, which greatly improves the abnormal monitoring efficiency of industrial robots. By obtaining video surveillance data, the industrial robots can be globally perceived, avoidance strategies can be planned in advance, and the collaborative work efficiency of multiple robots can be improved. By generating grid lines, the positioning efficiency and navigation accuracy of global perception can be further improved, which facilitates dynamic planning and adjustment of paths. By defining conflict lines, incremental planning of industrial robots can be achieved, thereby dynamically adjusting the moving routes, facilitating rapid adaptation to changes in obstacles, and greatly improving the obstacle avoidance efficiency of industrial robots. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of a dynamic path planning learning method for an industrial robot provided by an embodiment of the present invention; Figure 2 A block diagram of the first sub-process of the industrial robot dynamic path planning learning method provided by an embodiment of the present invention; Figure 3 A block diagram of the second sub-process of the industrial robot dynamic path planning learning method provided by an embodiment of the present invention; Figure 4 A block diagram of the third sub-process of the industrial robot dynamic path planning learning method provided by an embodiment of the present invention; Figure 5 A block diagram of the industrial robot dynamic path planning learning system provided by an embodiment of the present invention; Figure 6A block diagram of the positioning module in the industrial robot dynamic path planning learning system provided by an embodiment of the present invention; Figure 7 A block diagram of the composition of the calibration module in the industrial robot dynamic path planning learning system provided by an embodiment of the present invention; Figure 8 This is a block diagram of the composition of the update module in the industrial robot dynamic path planning learning system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present 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 only used to explain the present invention and are not intended to limit the present invention.

[0019] In Example 1, Figure 1 The implementation process of the dynamic path planning learning method for an industrial robot provided by an embodiment of the present invention is shown and described in detail below: S100: Delineate the working area of ​​the industrial robots, select the deployment positions of several identification lights in each industrial robot, set the color of each identification light, and generate a combination code, wherein the combination code of each industrial robot is different. Utilize the video surveillance equipment pre-deployed in the working area to collect video surveillance data of all industrial robots, and take out several snapshots according to the preset step length. The position of the industrial robot is located through the combination code.

[0020] Demarcate the area where industrial robots perform cargo transfer, known as the work area. Industrial robots in this context include logistics handling robots, material delivery robots, and automated guided transport robots. Several deployment locations are identified on the top or side of the industrial robots. These locations are selected by the industrial robot's management personnel. These locations are primarily used to deploy identification lights, which are multi-color, controllable indicators. Each identification light is preset with a different color (such as red, green, blue, and yellow). The color states of the identification lights installed on each industrial robot are combined to create a combination code, which can represent key information such as the industrial robot's current position, operating status, mission phase, or path planning status. For example, in daily operation, the combination code corresponding to industrial robot A is "red-blue-blue." When A enters a high-risk area, one of its identification lights turns red, and the combination code changes to "red-red-blue," indicating that A needs to slow down or wait for obstacle avoidance. It should be noted that each industrial robot has a unique combination code. This facilitates identification of the industrial robot and improves its positioning efficiency. Obtain access to video surveillance equipment installed in the work area and collect video surveillance data. The video surveillance data should include all industrial robots. If there are blind spots in monitoring, they can be eliminated by deploying multiple video surveillance devices. According to a preset step size (such as 1 second), multiple snapshots are captured from the video surveillance data, and the position of each industrial robot in the current snapshot is identified using image recognition algorithms (such as color extraction, target detection, and deep learning models). Furthermore, by determining the position changes of the industrial robot in adjacent snapshots, the industrial robot can be tracked and monitored. This positioning method does not require reliance on additional positioning hardware and is suitable for large-scale centralized management of industrial robots. It effectively realizes global perception and adjusts the movement route of the industrial robot in advance through an "omniscient perspective". The positioning methods such as lidar and GPS in existing technologies all start from the individual, and the early obstacle avoidance effect is poor.

[0021] S200: Divide the working area into grids, select reference points, and construct a coordinate system. Receive the production task uploaded by the preset terminal, find the target robot that executes the production task, locate the initial coordinates of the target robot, and traverse the end point coordinates from the production task to generate a moving route, wherein the moving route is composed of several grid lines of the same length, at least a first grid line and a second grid line are obtained, and the line coordinates of each grid line are calibrated.

[0022] Divide the work area into a grid, dividing the work area into multiple small grid units, each grid unit represents a specific spatial area; for example, divide the work area into a square grid with a side length of 50 cm; select a reference point (such as a corner or center position of the work area), and use this reference point as the origin to construct a coordinate system, and receive the production task uploaded by the preset terminal (such as the operator terminal or production control system). The production task should include: the object performing the task, the goods to be transferred, the starting coordinates and the end coordinates, etc.; define the object performing the task in the production task as the target robot; determine the position of the target robot according to the positioning method in S100, and read the initial coordinates; it should be noted that if the position of the target robot is on the grid line rather than the grid point, the coordinates of the grid point closest to it can be used as its initial coordinates; use the initial coordinates and the end coordinates in the production task to generate a movement route.

[0023] The moving route is refined into several grid lines. A grid line refers to a line segment consisting of two grid points and their connecting line. Starting from the initial coordinates, the first grid line in the refined moving route 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 out, where the line coordinates are composed of the coordinates of the two endpoints of the grid line.

[0024] S300: Obtain the configuration data of the target robot. When the target robot reaches the first grid line, based on the position and the length of the grid line, calculate the estimated arrival time of the second grid line, generate a query table, wherein the query table consists of the line coordinate items and the estimated arrival time items of the second grid line, establish a correspondence between the target robot and the query table, determine whether there are identical items in all query tables, and if so, define the second grid line corresponding to the identical item as a conflict line, use the nearest neighbor algorithm to find a replacement route for the conflict line, and update the movement route.

[0025] Obtain the configuration data of the target robot, where the configuration data includes: speed and movement ability. When the target robot reaches one of the endpoints of the first grid line, estimate the expected time for the target robot to reach the second grid line, i.e., the estimated arrival time, based on the length of the grid line and the moving speed of the target robot; use the line coordinates of each grid line and the corresponding estimated arrival time to create a query table, which is mainly used to store the time when the industrial robot arrives at the next grid line; by constructing the query table, incremental planning can be used to avoid obstacles in advance; each industrial robot corresponds to a query table, and the query tables corresponding to all industrial robots are integrated to find out whether there are the same items. If they exist, it means that two or more industrial robots are about to pass. The same grid line has a collision risk; the same grid line mentioned above is defined as a conflict line, and the two endpoints of the conflict line are determined. The two endpoints are reconnected using the nearest neighbor algorithm to obtain an alternative route; further, when two industrial robots are about to pass through the same grid line (assuming it is the Xth grid line), the priority of the industrial robots is determined based on the priority of the production tasks corresponding to the two. The industrial robot with the higher priority continues to move from the Xth grid line, while the other industrial robot moves from the alternative route; when multiple industrial robots are about to pass through the same grid line, the industrial robot with the highest priority is found. The industrial robot with the highest priority continues to move from the Xth grid line, while the remaining industrial robots move from their respective alternative routes.

[0026] In Example 2, Figure 2 The implementation process of the dynamic path planning learning method for industrial robots provided by an embodiment of the present invention is shown. The following details the steps of defining the working area of ​​the industrial robots, selecting the deployment positions of several identification lights on each industrial robot, and setting the color of each identification light. S101: Establish numbering rules and determine the number of each industrial robot.

[0027] Each industrial robot is numbered according to a numbering rule, wherein the numbering rule is formulated by the manager of the industrial robot, and the number of each industrial robot is different.

[0028] S102: Integrate the serial numbers and combination codes to generate a comparison table.

[0029] Each industrial robot corresponds to a unique combination code, and the number of each industrial robot is also different. A corresponding relationship between the industrial robot, the number and the combination code is established, and the corresponding relationship is stored in a comparison table.

[0030] In Example 3, Figure 2 The implementation process of the dynamic path planning learning method for an industrial robot provided by an embodiment of the present invention is shown. The steps of generating the combination code are described in detail below: S103: Configure the flashing frequency of each identification light, record the flashing time, and dynamically update the position.

[0031] The flashing frequency of each identification light is determined, the flashing time of each identification light is recorded, and the position of the industrial robot is updated when the identification light flashes.

[0032] In actual production, the moving speed of industrial robots is generally between 0.5m / s and 1.5m / s, which is not too fast. In a short period of time, the position of the industrial robot will not change drastically. Therefore, the industrial robot can be intermittently positioned by setting the flashing frequency to reduce the amount of data processing. For example, there are three industrial robots A, B and C. The flashing frequency of A is 5s / time, B is 3s / time and C is 1s / time. From the video surveillance data, snapshots are taken at intervals of 1s. In the snapshot of the 1st second, only one industrial robot can be identified, and there is no need to identify the combination code at this time. In the snapshot of the 3rd second, two industrial robots can be identified, and the combination number identification is required at this time, but this will also reduce the amount of data processing and improve the obstacle avoidance efficiency of the industrial robot.

[0033] S104: Clustering the production tasks into several types, and adjusting the combination codes.

[0034] In order to improve the recognition efficiency of combination codes, production tasks are clustered into multiple types, each type corresponding to a feature in the combination number; for example, three types of goods A, B and C need to be transported to a designated location, and the production tasks are divided into three types. The industrial robot that performs production task A has the first digit of its combination code in red, which further improves the recognition and positioning accuracy of the industrial robot.

[0035] In Example 4, Figure 3 The implementation process of the dynamic path planning learning method for an industrial robot provided by an embodiment of the present invention is shown. The following details the steps of gridding the work area, selecting reference points, constructing a coordinate system, and receiving a production task uploaded by a preset terminal. S201: Setting a priority for each production task, wherein the priority includes at least: high, medium, and low.

[0036] Determine the priority of each production task, where the priority is set by the manager of the industrial robot.

[0037] S202: Identify the priority corresponding to 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.

[0038] When multiple industrial robots arrive at the second grid line at the same time, the one with the highest priority is found and defined as the priority item, where the priority of the industrial robot refers to the priority of the corresponding production task.

[0039] S203: Opening the right to use the conflicting line to the priority item.

[0040] The conflict line is only used by industrial robots corresponding to priority items to pass through, thus ensuring that high-priority production tasks can be executed smoothly.

[0041] In Example 5, Figure 3 The implementation process of the dynamic path planning learning method for an industrial robot provided by an embodiment of the present invention is shown. The steps of locating the initial coordinates of the target robot, traversing the end point coordinates from the production task, and generating the movement route are described in detail as follows: S204: defining two endpoints of the grid line as grid points.

[0042] S205: Based on the configuration data and the production task, estimate the time it takes for the target robot to reach each grid point in the moving route, and correct the estimated time based on the position.

[0043] Based on the configuration data of the industrial robot, the estimated time for the target robot to reach each grid point is calculated. The estimated time is updated according to the real-time position of the target robot, which facilitates management personnel to conduct production scheduling more accurately.

[0044] In Example 6, Figure 4 The implementation process of the dynamic path planning learning method for an industrial robot provided by an embodiment of the present invention is shown. The step of defining the second grid line corresponding to the same item as the conflict line is described in detail below: S301: defining two ends of the conflict line as a first node and a second node.

[0045] The grid points at both ends of the conflict line are defined as the first node and the second node.

[0046] S302: Taking the first node as the starting point and the second node as the end point, using the grid points and the nearest neighbor algorithm, connect the starting point and the end point to obtain an alternative route.

[0047] The starting point and the end point can be connected through other grid points, that is, other optional paths in the target robot path planning. On this basis, the nearest neighbor algorithm is used to start from the starting point and select the grid point closest to the current node as the next moving point, and so on until the end point is reached. The resulting route is defined as the replacement route.

[0048] In Example 7, different from Example 1, in this embodiment of the present invention, the method further includes: Using sensor equipment pre-deployed in the work area to collect sensor data, wherein the sensor equipment at least includes: an RFID receiver and a laser radar; Based on the sensing data and configuration data, it is determined whether there is an obstacle object within the preset range of the target robot. If so, a pre-built avoidance mechanism is triggered.

[0049] Utilize sensor equipment to collect corresponding sensor data and determine whether there are any obstacles or potential collision risks in the area the target robot is about to enter. If an obstacle is detected, the avoidance mechanism is immediately triggered. The avoidance mechanism is a supplement to the above-mentioned replacement route. The avoidance mechanism is a collection of multiple avoidance methods, such as pausing to move forward. By triggering the avoidance mechanism, the target robot can be guaranteed to perform the task without collision.

[0050] Figure 5 The following is a structural block diagram of the industrial robot dynamic path planning learning system provided by an embodiment of the present invention. The industrial robot dynamic path planning learning system 1 includes: The positioning module 11 is used to define the working area of ​​the industrial robots. For each industrial robot, the deployment positions of several identification lights are selected, the colors of each identification light are set, and a combination code is generated. The combination code is different for each industrial robot. Video surveillance equipment pre-deployed in the working area is used to collect video surveillance data including all industrial robots. Several snapshots are taken according to a preset step size. The position of the industrial robot is located using the combination code. The calibration module 12 is configured to divide the work area into grids, select reference points, and construct a coordinate system. The calibration module 12 receives a production task uploaded by a preset terminal, finds a target robot to perform the production task, locates the initial coordinates of the target robot, and traverses the end coordinates from the production task to generate a movement route, wherein the movement route is composed of a plurality of grid lines of the same length, obtaining at least a first grid line and a second grid line, and calibrating the line coordinates of each grid line. An updating module 13 is configured to obtain configuration data of a target robot. When the target robot reaches a first grid line, the updating module 13 calculates an estimated arrival time of a second grid line based on the position and the length of the grid line, generates a lookup table consisting of line coordinate items and estimated arrival time items of the second grid line, establishes a correspondence between the target robot and the lookup table, determines whether identical items exist in all lookup tables, and if so, defines the second grid line corresponding to the identical item as a conflict line. Using a nearest neighbor algorithm, the updating module 13 finds an alternative route for the conflict line and updates the movement route.

[0051] Figure 6 The following is a structural block diagram of the industrial robot dynamic path planning learning system provided by an embodiment of the present invention. The positioning module 11 includes: A formulating unit 111 is used to formulate a numbering rule and determine the number of each industrial robot; A generating unit 112, configured to integrate the serial number and the combination code to generate a comparison table; The recording unit 113 is used to configure the flashing frequency of each marker light, record the flashing time, and dynamically update the position; The adjusting unit 114 is configured to cluster the production tasks into several types and adjust the combination codes.

[0052] Figure 7 The following is a structural block diagram of the industrial robot dynamic path planning learning system provided by an embodiment of the present invention. The calibration module 12 includes: A setting unit 121 is configured to set a priority for each production task, wherein the priority includes at least: high, medium, and low; The identification unit 122 is used to identify the priority corresponding to 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 opening unit 123, configured to open the use rights of the conflicting line to the priority item; An initial definition unit 124 is used to define two endpoints of the grid line as grid points; The correction unit 125 is configured to estimate the estimated time for the target robot to reach each grid point in the moving route based on the configuration data and the production task, and correct the estimated time based on the position.

[0053] Figure 8 The following is a structural block diagram of the industrial robot dynamic path planning learning system provided by an embodiment of the present invention. The update module 13 includes: A re-definition unit 131 is used to define two ends of the conflict line as a first node and a second node; The obtaining unit 132 is configured to use the first node as a starting point and the second node as an end point, and to connect the starting point and the end point using the grid points and the nearest neighbor algorithm to obtain an alternative route.

[0054] The positioning module 11 is mainly used to complete step S100, the calibration module 12 is mainly used to complete step S200, and the updating module 13 is mainly used to complete step S300; The formulation unit 111 is mainly used to complete step S101, the generation unit 112 is mainly used to complete step S102, the recording unit 113 is mainly used to complete step S103, and the adjustment unit 114 is mainly used to complete step S104; 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; The re-initialization unit 131 is mainly used to complete step S301, and the obtaining unit 132 is mainly used to complete step S302.

[0055] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned 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.

[0056] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0057] 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 in the scope of protection of the present invention.

Claims

1. A dynamic path planning learning method for industrial robots, characterized in that: The method comprises: S100: Delineating a working area for the industrial robots, selecting the deployment locations of several identification lights for each industrial robot, setting the color of each identification light, and generating a combination code, wherein the combination code is different for each industrial robot. Using video surveillance equipment pre-deployed in the working area, video surveillance data of all industrial robots is collected, and several snapshots are captured according to a preset step size. The position of the industrial robot is then located using the combination code. S200: Gridding the work area, selecting reference points, and constructing a coordinate system, receiving a production task uploaded by a preset terminal, finding a target robot to perform the production task, locating the initial coordinates of the target robot, and traversing the end point coordinates from the production task to generate a movement route, wherein the movement route is composed of a plurality of grid lines of the same length, obtaining at least a first grid line and a second grid line, and calibrating 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, based on the position and the length of the grid line, calculate the estimated arrival time of the second grid line, generate a query table, wherein the query table consists of the line coordinate items and the estimated arrival time items of the second grid line, establish a correspondence between the target robot and the query table, determine whether there are identical items in all query tables, and if so, define the second grid line corresponding to the identical item as a conflict line, use the nearest neighbor algorithm to find a replacement route for 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 robots, selecting the deployment positions of several identification lights in each industrial robot, and setting the color of each identification light include: Formulate numbering rules and determine the number of each industrial robot; The numbers and combination codes are integrated to generate a comparison table.

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

4. The industrial robot dynamic path planning learning method according to claim 1, characterized in that: The steps of dividing the working area into grids, selecting reference points, constructing a coordinate system, and receiving production tasks uploaded by a preset terminal include: Setting a priority for each production task, wherein the priority includes at least: high, medium, and low; Identify the priority corresponding to each identical item and sort them in descending order of priority, defining the identical item that comes first in the order as the priority item; Access to conflicting lines is granted to the 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, traversing the end coordinates from the production task, and generating a moving route include: defining two endpoints of the grid line as grid points; Based on the configuration data and the production task, an estimated time for the target robot to reach each grid point in the moving route is estimated, and based on the position, the estimated time is corrected.

6. The industrial robot dynamic path planning learning method according to claim 4, characterized in that: The step of defining the second grid line corresponding to the same item as the conflict line includes: defining two ends of the conflict line as a first node and a second node; The first node is used as a starting point and the second node is used as an end point. The grid points and the nearest neighbor algorithm are used to connect the starting point and the end point to obtain an alternative route.

7. The industrial robot dynamic path planning learning method according to claim 1, characterized in that: The method further comprises: Using sensor equipment pre-deployed in the work area to collect sensor data, wherein the sensor equipment at least includes: an RFID receiver and a laser radar; Based on the sensing data and configuration data, it is determined whether there is an obstacle object within the preset range of the target robot. If so, a pre-built avoidance mechanism is triggered.

8. Industrial robot dynamic path planning learning system, characterized by: The system comprises: The positioning module is used to delineate the working area of ​​the industrial robots. For each industrial robot, the deployment positions of several identification lights are selected, the colors of each identification light are set, and a combination code is generated. The combination code is different for each industrial robot. Video surveillance equipment pre-deployed in the working area is used to collect video surveillance data including all industrial robots. Several snapshots are taken according to a preset step size. The position of the industrial robot is located using the combination code. a calibration module, configured to grid the work area, select reference points, and construct a coordinate system; receive a production task uploaded by a preset terminal; find a target robot to perform the production task; locate the initial coordinates of the target robot; and traverse the end coordinates from the production task to generate a movement route, wherein the movement route is composed of a plurality of grid lines of the same length, obtaining at least a first grid line and a second grid line, and calibrating the line coordinates of each grid line; An update module is configured to obtain configuration data of a target robot, calculate an estimated arrival time of a second grid line based on the position and the length of the grid line when the target robot reaches the first grid line, generate a lookup table consisting of line coordinate items and estimated arrival time items of the second grid line, establish a correspondence between the target robot and the lookup table, determine whether identical items exist in all lookup tables, and if so, define the second grid line corresponding to the identical item as a conflict line, use a nearest neighbor algorithm to find an 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: A formulation unit is used to formulate numbering rules and determine the number of each industrial robot; A generating unit, configured to integrate the numbers and combination codes to generate a comparison table; A recording unit configured to configure the flashing frequency of each marker 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 combination code.

10. The industrial robot dynamic path planning learning system according to claim 8, characterized in that: The calibration module includes: A setting unit, configured to set a priority for each production task, wherein the priority includes at least: high, medium, and low; An identification unit is used to identify the priority corresponding to 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 opening unit, configured to open the right to use the conflicting line to the priority item; An initial definition unit, used to define 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 moving route based on the configuration data and the production task, and correct the estimated time based on the position.

Images