Implementation method of mobile robot with intelligent behavior

Abstract

The invention discloses a method for realizing a mobile robot with intelligent behaviors, which comprises the following steps of: firstly, establishing a feature database of a workpiece to be processed manually or by a robot, and then, sending a task instruction comprising task data, a target machine tool, an equipment number and processing time to the robot by a workshop digital management system through a group control scheduling system; and the robot autonomously recognizes the to-be-machined workpiece according to the instruction, if recognition fails, the next to-be-machined workpiece continues to be scanned, and if recognition succeeds, a route is autonomously planned, and the to-be-machined workpiece is transferred to the target machine tool to be machined. Compared with the prior art, the method has the advantages that the robot is endowed with self-judgment and self-behavior generation capabilities under certain constraint conditions, and efficient and autonomous operation tasks can be realized; the robot has the intelligent capability, so that the robot does not depend on scheduling of a group control scheduling system when executing the operation task, the scheduling system is mostly in a monitoring state, a behavior track of the robot is monitored and the like, and the robot is endowed with more intelligent characteristics.

Description

Technical Field

[0001] The present invention relates to the field of automated processing and manufacturing, and in particular to a method for realizing an embodied intelligent behavior mobile robot. Background Art

[0002] With the increasing number of mobile robot application scenarios, especially in the civil and industrial fields, the requirements for their intelligence are also increasing. In complex scenarios, mobile robots need to rely on their own perception capabilities to make autonomous decisions, form autonomous behaviors, and complete various tasks. This requires mobile robots to not only have strong scene perception capabilities, but also to be able to make autonomous decisions based on task requirements and form corresponding movement and operation behaviors based on this perception capability. For example, mobile composite robots need to perform autonomous operations under different working conditions to achieve the expected task objectives.

[0003] However, current mobile robot technology still has obvious deficiencies in achieving self-decision-making capabilities based on self-perception. Although mobile robots can obtain environmental information through sensing devices, they often need to rely on the unified scheduling and command of the robot scheduling system in the process of autonomous decision-making and behavior generation. The autonomous decision-making capabilities of mobile robots under existing technologies are relatively low, and it is difficult for them to complete tasks independently in complex and changing environments. Therefore, mobile robots urgently need to be further improved in terms of autonomy and intelligence to overcome the deficiencies of existing technologies in the process of autonomous decision-making and behavior generation, and truly achieve efficient and intelligent autonomous operation capabilities. Summary of the invention

[0004] In view of this, the present invention discloses a method for realizing an embodied intelligent behavior mobile robot, which enables the robot to have self-judgment ability under the constraints of limited conditions, realize the generation of self-behavior, and meet the requirements of the task. The technical solution of the present invention is implemented as follows:

[0005] The present invention discloses a method for realizing an embodied intelligent behavior mobile robot, comprising the following steps:

[0006] S1. Establish the feature database of the workpiece to be processed manually or by robot;

[0007] S2, the workshop digital management system sends task instructions to the robot through the group control scheduling system;

[0008] S3, the task instruction includes the task data, the target machine tool, the equipment number and the processing time;

[0009] S4, the robot autonomously identifies the workpiece to be processed according to the task instructions;

[0010] Specifically, the robot extracts feature data of the workpiece to be processed and compares it with target features to see whether it matches;

[0011] Specifically, the robot extracts the feature data of the workpiece to be processed and uploads it to the group control scheduling system, and compares it with the target feature to see whether it matches;

[0012] S5. If the recognition is unsuccessful, the robot continues to scan the next workpiece to be processed;

[0013] S6. If the recognition is successful, the robot will autonomously plan the route and transfer the workpiece to be processed to the target machine tool;

[0014] Specifically, the robot transfers the workpiece to be processed to the target machine tool, and cooperates with the target machine tool to complete the installation and preparation of the workpiece to be processed.

[0015] S7, the target machine tool processes the workpiece;

[0016] In the steps S3 to S7, the group control dispatching system is in a state of monitoring the robot;

[0017] The steps S1 to S7 also include a mutual avoidance method of the robots, which includes the following steps:

[0018] N1. When two robots enter a certain distance range, they establish a mutual communication relationship and send a handshake signal;

[0019] N2. The two robots determine the avoidance plan based on the interactive driving route and direction. One of the robots needs to make a decision by performing priority calculation and transmit the decision information to the other robot.

[0020] N3. The low-priority robot performs the avoidance action. After the avoidance action is completed, the two robots resume normal driving.

[0021] Specifically, S1, manually or robotically establishes a feature database of the workpiece to be processed, including:

[0022] A human handheld visual device takes a picture of the workpiece to be processed to extract feature data and establish the feature database, or a robot takes a picture of the workpiece to be processed by a visual camera device it carries to extract feature data and establish the feature database.

[0023] Preferably, the robot takes pictures of the workpiece by using a visual camera device it carries to extract feature data and establish the feature database.

[0024] Specifically, the feature database includes feature data of all types of workpieces to be processed.

[0025] Specifically, all types of workpieces to be processed can be processed by all types of machine tools.

[0026] A method for implementing an embodied intelligent behavior mobile robot, further comprising a mutual avoidance method of the robots, wherein the priority calculation rules in the N2 step include:

[0027] Task time and cycle priority rules: the robot with the shortest remaining task time or production cycle has a high priority and enjoys the right of way. The other robot has a low priority and performs avoidance actions.

[0028] The shortest remaining distance priority rule: the robot with the shortest remaining distance has a high priority and enjoys the right of way. The other robot has a low priority and performs an avoidance action.

[0029] Calculate the avoidance rules of the impact factor. The two robots assume that the other party does not avoid, calculate the time it takes to reach the target point when they perform the avoidance, and calculate the impact factor of this avoidance on subsequent driving and operation. The robot with a small impact factor has a low priority and performs the avoidance action. The robot with a large impact factor has a high priority and enjoys the right of way.

[0030] Other rules designate certain robots as high priority and other robots as low priority, and low priority robots avoid designated high priority robots.

[0031] Specifically, the calculation formula in the avoidance rule for calculating the impact factor is as follows:

[0032] λ=(T0-T1) / T1

[0033] Among them, T0 is the time to reach the target point due to the avoidance action, and T1 is the scheduled time for this task;

[0034] λ represents the impact factor. A robot with a high λ value is a high-priority robot, and a robot with a low λ value is a low-priority robot.

[0035] Based on this invention, the mobile robot can rely on its own intelligent control system to autonomously move and operate under the "weak" scheduling of the scheduling system, thereby completing the designated tasks. This intelligent control system enables the robot to make independent judgments and decisions, improving the autonomy and flexibility of operation. In addition, with the improvement of the intelligence level of the robot, the scheduling task burden of the group control scheduling system is reduced, so that the scheduling system no longer needs cumbersome centralized control. This burden-reducing effect greatly optimizes the operating efficiency of the scheduling system. In actual applications, multiple robots can coordinate operations more efficiently in the same operating scenario, significantly improving overall operating efficiency and productivity. In this way, the mobile robot not only has a higher level of autonomous operation capabilities, but also shows stronger adaptability and collaboration capabilities in complex and changing environments, promoting the further improvement of the level of industrial automation. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only one embodiment of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A flowchart of a method for implementing an embodied intelligent behavior mobile robot disclosed in the present invention in a scenario where digital and intelligent management of a raw material warehouse is not achieved;

[0038] Figure 2 for Figure 1 Method for establishing feature database;

[0039] Figure 3 A mutual avoidance method of robots in the present invention;

[0040] Figure 4 In the scenario where the robot autonomously searches for suitable raw materials according to a task order, the present invention discloses a method for implementing an embodied intelligent behavior mobile robot. DETAILED DESCRIPTION

[0041] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention and the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by technicians in the technical field to which the present invention belongs; the terms used in the specific implementation methods are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the terms "including" and "having" in the specification and claims of the present invention and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0043] In the description of the specific implementation methods of the present invention, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present invention, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0044] Reference to "embodiments" in the present invention means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in the present invention may be combined with other embodiments.

[0045] In the description of the embodiments of the present invention, the term "and / or" is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0046] It should be noted that, for the convenience of description, in the following embodiments, all identical technical features are marked with the same symbols.

[0047] With the increasing number of mobile robot application scenarios, especially in the civil and industrial fields, the requirements for their intelligence are also increasing. In complex scenarios, mobile robots need to rely on their own perception capabilities to make autonomous decisions, form autonomous behaviors, and complete various tasks. This requires mobile robots to not only have strong scene perception capabilities, but also to be able to make autonomous decisions based on task requirements and form corresponding movement and operation behaviors based on this perception capability. For example, mobile composite robots need to perform autonomous operations under different working conditions to achieve the expected task objectives.

[0048] However, current mobile robot technology still has obvious deficiencies in achieving self-decision-making capabilities based on self-perception. Although mobile robots can obtain environmental information through sensing devices, they often need to rely on the unified scheduling and command of the robot scheduling system in the process of autonomous decision-making and behavior generation. The autonomous decision-making capabilities of mobile robots under existing technologies are relatively low, and it is difficult for them to complete tasks independently in complex and changing environments. Therefore, mobile robots urgently need to be further improved in terms of autonomy and intelligence to overcome the deficiencies of existing technologies in the process of autonomous decision-making and behavior generation, and truly achieve efficient and intelligent autonomous operation capabilities.

[0049] Therefore, the present invention discloses a method for realizing embodied intelligent behavior of a mobile robot, so that the robot can have self-judgment ability under the constraints of limited conditions, realize the generation of self-behavior, and meet the requirements of the work task. The following will gradually and progressively explain through embodiments, and finally realize the embodied intelligent behavior capability of the mobile robot applied in industrial manufacturing scenarios.

[0050] Example 1

[0051] In the scenario where the raw material warehouse has not achieved digital and intelligent management, such as Figure 1 and Figure 2 As shown, a method for implementing an embodied intelligent behavior mobile robot includes the following steps:

[0052] S1. Establish the feature database of the workpiece to be processed manually or by robot;

[0053] S2, the robot takes visual photos and identifies the workpiece;

[0054] S3, the robot extracts the feature data of the workpiece to be processed and uploads it to the robot group control system;

[0055] S4, the robot group control system issues instructions for processing the workpiece to be processed into a finished part or a semi-finished part according to the uploaded feature data, and determines the corresponding machine tool type and quantity;

[0056] S5. The workshop digital system specifies the machine tool for processing the workpiece to be processed based on the feedback from the robot group control system. The robot performs the transfer task and moves the workpiece to the machine tool.

[0057] S6. The robot group control system controls the machine tool to process the workpiece into a finished part or a semi-finished part;

[0058] S7, after the workpiece is processed, the robot group control system controls the robot to take out the finished part or semi-finished part;

[0059] S8, the robot transfers the finished parts to the finished product warehouse, or transfers the semi-finished parts to the next machine tool for further processing;

[0060] In the above settings, the typical characteristics of the scenario targeted by the embodiment are that the raw material warehouse has not achieved digital and intelligent management, the raw materials are placed in disorder, and the robot picks them up randomly, requiring identification and decision-making.

[0061] Through the above settings, the present invention is applied in industrial manufacturing workshop scenarios, mainly facing the production lines of production workshops. The robot has certain requirements and time rhythms when operating in this environment. There are certain certainties, but also many uncertainties. Therefore, the robot needs to have embodied intelligence and be able to self-judge and adjust things, the environment, and its own behavior to ensure smooth operation and execution of tasks.

[0062] In this embodiment, the group control scheduling system only serves as an intermediary platform for the robot's task execution data. In most cases, it monitors the robot by collecting operation data, rather than continuously remotely controlling, scheduling or planning the robot's driving route like a traditional scheduling system.

[0063] In this embodiment, S4, the robot group control system determines the corresponding machine tool type according to the uploaded feature data, and the specific steps are as follows:

[0064] S4.1. The robot group control system compares the uploaded feature data of the workpiece to be processed with the data number of the feature database established in S1, obtains the corresponding feature data number, and then determines the corresponding workshop machine tool type.

[0065] In this embodiment, S5, the workshop digital system specifies the machine tool for processing according to the feedback of the robot group control system, and the robot performs the transfer task to move the workpiece to be processed to the machine tool. The specific steps are as follows:

[0066] S5.1. After the machine tool for processing is specified, the information is transmitted to the robot group control system. The robot group control system issues instructions, and the robot and the specified machine tool establish a communication relationship through the machine tool communication module;

[0067] S5.2. The robot transfers the workpiece to be processed to the designated machine tool and cooperates with the machine tool to complete the installation and preparation of the workpiece.

[0068] In the above settings, the robot group control system compares the uploaded feature data of the workpiece to be processed with the data in the feature database to obtain the matching feature data number, for example, the feature data number is k. This means that the feature data number corresponding to the workpiece to be processed currently taken by the robot is k in the database. In the robot group control system, a mapping relationship between the feature data number and the workshop machine tool type number has been established. For example, feature data number k corresponds to machine tool type k. Different machine tool types indicate different workpieces to be processed, and there may be multiple machine tool equipment with the same or similar processing tasks under the same machine tool type. The specific machine tool to which the workpiece to be processed is assigned for processing is determined and allocated by the factory digital system.

[0069] After the factory digital system determines the specific machine tool for processing the workpiece, it transmits the information to the robot group control system. The group control system sends instructions to the robot, and the robot establishes a communication relationship with the corresponding machine tool through the machine tool communication module. When the robot transfers the workpiece to the vicinity of the machine tool, based on this two-way communication relationship, the robot and the machine tool collaborate to complete the installation and preparation of the workpiece.

[0070] It should be noted that the workpiece to be processed from which feature data is extracted does not necessarily correspond to a certain type of machine tool, but may correspond to other types of machine tools, depending on the specific type of processing task of the workpiece.

[0071] In this embodiment, the instruction in step S5.1 includes task data, target machine tool, equipment number and processing time.

[0072] In this embodiment, the feature database in step S1 includes feature data of all types of workpieces to be processed.

[0073] In this embodiment, all types of workpieces to be processed can be processed by all types of machine tools.

[0074] In the above settings, for a certain production workshop, the type and number of machine tools are fixed, so the type of workpiece to be processed is also determined. Based on this, different types of workpieces to be processed (such as shape, size and other characteristic data) can be pre-determined according to these characteristic parameters. The corresponding processing task requirements and the corresponding machine tool type can be determined in advance. This can effectively optimize the production process and improve processing efficiency.

[0075] In this embodiment, a visual camera is used to visually photograph all types of workpieces to be processed and identify and extract feature data.

[0076] In this embodiment, a manual handheld visual device is used to take photos and extract feature data, or a visual camera device carried by a robot is used to take photos and extract feature data.

[0077] For example, various workpieces can be placed in line in sequence, and a mobile robot can complete the pre-library construction work by walking and taking pictures, or a human handheld visual camera can take pictures one by one to establish a database.

[0078] To explain further, for example, a workshop has 300 machine tools of 10 types. The types of workpieces to be processed may be 10, or less or more than 10 (depending on the type of machine tool and the type of workpieces to be produced). No matter how many types of workpieces there are, they can be completed by these 300 machine tools of 10 types.

[0079] In the process of establishing a database, the initial database construction work is done manually or by robots. Manually or by robots take out each type of workpiece, scan and take pictures with a visual camera to generate feature data, and establish a mapping relationship between it and the appropriate machine tool type, gradually establishing a database. In subsequent production, when the robot takes a workpiece from the material warehouse, it uses its own visual camera to take pictures to extract feature information and upload it to the robot group control system, which can automatically identify which machine tool should be used to process the workpiece.

[0080] like Figure 3 As shown, a method for implementing an embodied intelligent behavior mobile robot also includes a mutual avoidance method of the robots, and the specific steps are as follows:

[0081] First, when two robots enter a certain distance range, they establish a mutual communication relationship and send a handshake signal;

[0082] Secondly, the two robots determine the avoidance plan based on the interactive driving routes and directions. One of the robots needs to make a decision by performing priority calculations and transmit the decision information to the other robot.

[0083] The low-priority robot starts avoidance driving, reaches the avoidance area or completes the avoidance action, the high-priority robot continues driving, and the low-priority robot continues driving.

[0084] In the above settings, the high and low priority calculation and judgment rules are as follows:

[0085] 1. Task time and rhythm priority principle

[0086] The robot with the shortest remaining task execution time or production cycle has a higher priority and has the right of way, requiring the other robot to perform avoidance action.

[0087] 2. The principle of shortest remaining distance first

[0088] The robot with the shortest remaining driving distance has a higher priority and has the right of way, requiring the other robot to perform an avoidance action.

[0089] 3. Avoidance rules based on impact factor calculation

[0090] The two robots each assume that the other does not avoid the other and calculate the time to reach the target point under the premise of avoiding the other. They calculate the impact factor of this avoidance on their subsequent driving and operation actions and exchange them with the other. The one with the smaller impact factor performs the avoidance action. The larger the impact factor, the greater the impact of this avoidance on their subsequent execution of tasks.

[0091] 4. Based on other rules

[0092] Certain robots are designated as having high priority, and other robots need to give way in most scenarios.

[0093] Furthermore, the calculation formula in the avoidance rule for calculating the impact factor is as follows:

[0094] λ=(T0-T1) / T1

[0095] Among them, T0 is the time to reach the target point due to the avoidance action, and T1 is the scheduled time for this task;

[0096] λ represents the influence factor. The robot with a high λ value is a high-priority robot, and the robot with a low λ value is a low-priority robot. The low-priority robot will perform the avoidance.

[0097] Example 2

[0098] In the scenario of realizing digital and intelligent management of the original material library, a method for realizing an embodied intelligent behavior mobile robot includes the following steps:

[0099] S1. The workshop digital management platform issues task instructions;

[0100] S2. The robot group control system controls a robot to go to the raw material warehouse to fetch materials;

[0101] S3. The robot takes the material and transfers it to the designated machine tool.

[0102] In the above settings, each link is carried out under the dispatching command and control of the workshop digital management platform and the robot group control system. The original material library has realized digital and intelligent management, and can provide corresponding original materials according to the instructions of the workshop digital platform.

[0103] Example 3

[0104] like Figure 4 As shown, in a scenario where the robot autonomously searches for suitable raw materials according to a task order, a method for implementing an embodied intelligent behavior mobile robot includes the following steps:

[0105] S1. Establish the feature database of the workpiece to be processed manually or by robot;

[0106] S2, the workshop digital management system sends task instructions to the robot through the group control scheduling system;

[0107] S3, the task instruction includes the task data, the target machine tool, the equipment number and the processing time;

[0108] S4, the robot autonomously identifies the workpiece 1 to be processed according to the task instruction;

[0109] Specifically, the robot extracts feature data of the workpiece 1 to be processed and compares it with the target feature to see whether it matches;

[0110] Specifically, the robot extracts feature data of the workpiece 1 to be processed and uploads it to the group control scheduling system, and compares it with the target feature to see if it matches;

[0111] S5. If the recognition is unsuccessful, the robot continues to scan the next workpiece to be processed, such as workpieces 2, 3, and 4;

[0112] S6. If the recognition is successful, the robot plans the route autonomously and transfers the workpiece 1 to the target machine tool;

[0113] Specifically, the robot transfers the workpiece 1 to the target machine tool, and cooperates with the target machine tool to complete the installation and preparation of the workpiece 1.

[0114] S7, the target machine tool processes the workpiece 1;

[0115] In steps S3 to S7, the group control scheduling is in a listening state to monitor the status of the robot;

[0116] The steps S1 to S7 also include a mutual avoidance method of the robots, including the following steps:

[0117] N1. When two robots enter a certain distance range, they establish a mutual communication relationship and send a handshake signal;

[0118] N2. The two robots determine the avoidance plan based on the interactive driving route and direction. One of the robots needs to make a decision by performing priority calculation and transmit the decision information to the other robot.

[0119] N3. The low-priority robot performs the avoidance action. After the avoidance action is completed, the two robots resume normal driving.

[0120] Specifically, S1, manually or robotically establishes a feature database of the workpiece to be processed, including:

[0121] A human handheld visual device takes a picture of the workpiece to extract feature data and establish a feature database, or a robot takes a picture of the workpiece through a visual camera device it carries to extract feature data and establish a feature database.

[0122] Preferably, the robot takes pictures of the workpiece by using a visual camera device it carries to extract feature data and establish a feature database.

[0123] Specifically, the feature database includes feature data of all types of workpieces to be processed.

[0124] Specifically, all types of workpieces to be machined can be machined by all types of machine tools.

[0125] With this configuration, scene maps and feature data mapping databases are stored in the robot's internal controller. After receiving the task data, the robot calculates the entire process from identifying the appropriate workpiece to determining the target machine tool position, including route planning and operation action implementation. During this period, the group control scheduling system is only in a listening state, monitoring the robot's behavior trajectory, without performing traditional driving trajectory scheduling and command, thereby reducing the computing burden of the scheduling system.

[0126] It should be pointed out that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for implementing an embodied intelligent behavior mobile robot, characterized in that: The steps include: S1. Establish the feature database of the workpiece to be processed manually or by robot; S2, the workshop digital management system sends task instructions to the robot through the group control scheduling system; S3, the task instruction includes the task data, the target machine tool, the equipment number and the processing time; S4, the robot autonomously identifies the workpiece to be processed according to the task instructions; S5. If the recognition is unsuccessful, the robot continues to scan the next workpiece to be processed; S6. If the recognition is successful, the robot autonomously plans a route, transports the workpiece to be processed to the target machine tool, and autonomously installs the workpiece on the processing table of the target machine tool; S7, the target machine tool processes the workpiece; In the steps S3 to S7, the group control dispatching system is in a state of monitoring the robot; The steps S1 to S7 also include a mutual avoidance method of the robots, which includes the following steps: N1. When two robots enter a certain distance range, they establish a mutual communication relationship and send a handshake signal; N2. The two robots determine the avoidance plan based on the interactive driving route and direction. One of the robots needs to make a decision by performing priority calculation and transmit the decision information to the other robot. N3. The low-priority robot performs the avoidance action. After the avoidance action is completed, the two robots resume normal driving.

2. The method for implementing an embodied intelligent behavior mobile robot according to claim 1, characterized in that: S1. Establish the feature database of the workpiece to be processed manually or by robot, including: A human handheld visual device takes a picture of the workpiece to be processed to extract feature data and establish the feature database, or a robot takes a picture of the workpiece to be processed by a visual camera device it carries to extract feature data and establish the feature database.

3. The method for implementing an embodied intelligent behavior mobile robot according to claim 2, characterized in that: The robot takes pictures of the workpiece by using the visual camera device it carries to extract feature data and establish the feature database.

4. The method for implementing an embodied intelligent behavior mobile robot according to claim 3, characterized in that: The feature database includes feature data of all types of workpieces to be processed.

5. The method for implementing an embodied intelligent behavior mobile robot according to claim 4, characterized in that: All types of workpieces to be processed can be processed by all types of machine tools.

6. The method for implementing an embodied intelligent behavior mobile robot according to claim 1, characterized in that: S4. The robot autonomously identifies the workpiece to be processed according to the task instructions, including: The robot extracts feature data of the workpiece to be processed and compares it with target features to see if they match.

7. The method for implementing an embodied intelligent behavior mobile robot according to claim 1, characterized in that: S4. The robot autonomously identifies the workpiece to be processed according to the task instructions, including: The robot extracts feature data of the workpiece to be processed and uploads it to the group control scheduling system, and compares it with the target features to see if they match.

8. The method for implementing an embodied intelligent behavior mobile robot according to claim 1, characterized in that: S6. If the recognition is successful, the robot will autonomously plan the route and transfer the workpiece to be processed to the target machine tool, including: The robot transfers the workpiece to be processed to the target machine tool, and cooperates with the target machine tool to complete the installation and preparation of the workpiece to be processed.

9. The method for implementing an embodied intelligent behavior mobile robot according to claim 1, characterized in that: The rules for priority calculation in step N2 include: Task time and cycle priority rules: the robot with the shortest remaining task time or production cycle has a high priority and enjoys the right of way. The other robot has a low priority and performs avoidance actions. The shortest remaining distance priority rule: the robot with the shortest remaining distance has a high priority and enjoys the right of way. The other robot has a low priority and performs an avoidance action. Calculate the avoidance rules of the impact factor. The two robots assume that the other party does not avoid, calculate the time it takes to reach the target point when they perform the avoidance, and calculate the impact factor of this avoidance on subsequent driving and operation. The robot with a small impact factor has a low priority and performs the avoidance action. The robot with a large impact factor has a high priority and enjoys the right of way. Other rules designate certain robots as high priority and other robots as low priority, and low priority robots avoid designated high priority robots.

10. The method for implementing an embodied intelligent behavior mobile robot according to claim 9, characterized in that: The calculation formula in the avoidance rule for calculating the impact factor is as follows: λ=(T0-T1) / T1 Among them, T0 is the time to reach the target point due to the avoidance action, and T1 is the scheduled time for this task; λ represents the impact factor. A robot with a high λ value is a high-priority robot, and a robot with a low λ value is a low-priority robot.

Images