AGV robot scheduling management method and system

Abstract

The invention discloses an AGV robot scheduling management method and system, and relates to the technical field of robot scheduling, and the method comprises the steps: calculating a task priority score Pi based on the task data of an AGV robot, generating a candidate path set Ri through employing a breadth-first search BFS in combination with an AGV robot operation environment topological graph G (V, E), carrying out the preliminary screening of the candidate path set Ri through employing a greedy algorithm, and carrying out the scheduling of the AGV robot. An initial path of the AGV is generated, an adaptive large neighborhood search ALNS is used, an objective function is set for iteration, and an optimal initial solution is output; and performing reverse annealing based on the optimal initial solution generated by the ALNS, and outputting an AGV robot scheduling management scheme in combination with neighborhood operation. According to the method, the candidate path set is preliminarily screened by using the greedy algorithm, the initial path of the AGV is generated, the ALNS is used for iterative optimization, the optimal initial solution is output, reverse annealing is combined, and an AGV scheduling management method is output, so that global optimal management of AGV robot scheduling is realized, and the intelligence and flexibility of AGV robot scheduling are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of robot scheduling, and in particular to an AGV robot scheduling management method and system. Background Art

[0002] With the rapid development of automation technology and intelligent manufacturing, automated guided vehicles (AGVs) are increasingly used in modern industrial and logistics systems. As an intelligent device that can autonomously perform handling and material distribution, AGV robots have played a key role in reducing labor costs, improving efficiency, and realizing unmanned factories. Traditional AGV scheduling systems mainly rely on preset path planning algorithms. This method may be inefficient or unable to adapt to dynamic changes in some complex operating environments. With the advancement of Internet of Things technology, artificial intelligence, and big data processing technology, intelligent management of AGV robot scheduling has become a new research hotspot. It is expected that more flexible scheduling strategies can be used to optimize task execution and thus improve the work efficiency of the entire system.

[0003] However, the existing technology has many shortcomings in the scheduling and management of AGV robots. First, most traditional scheduling algorithms use static optimization methods, which cannot effectively respond to real-time changes in the working environment, such as path blockage, machine failure, and power exhaustion. Unforeseen events; second, most existing AGV scheduling systems ignore the importance of machine power management, causing the AGV to stop working due to insufficient power in the middle of the operation, affecting the continuity of the overall production process. In addition, the current AGV scheduling method is prone to scheduling conflicts in large-scale, multi-task concurrent situations, and it is difficult to adjust the scheduling plan in time according to task priority. With the complexity of AGV application scenarios, how to achieve efficient multi-task scheduling and smarter energy management has become an urgent problem to be solved. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing AGV robot scheduling management method and system, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that the existing AGV robot scheduling management cannot effectively cope with real-time changes in the working environment, and the AGV robot scheduling management method is prone to scheduling conflicts in large-scale and multi-task concurrency situations, and it is difficult to adjust the scheduling plan in time according to task priority.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a scheduling and management method for an AGV robot, comprising: collecting AGV robot operation data, and establishing an AGV robot operation environment topology map G(V, E) based on the collected AGV robot operation data; setting the critical power threshold of the AGV robot, and monitoring the power status of the AGV robot in real time according to the collected AGV robot operation data; calculating the task priority score Pi based on the task data of the AGV robot, and combining the AGV robot operation environment topology map G(V, E), using breadth-first search BFS to generate a candidate path set Ri, using a greedy algorithm to preliminarily screen the candidate path set Ri, generating an initial path for the AGV, and using an adaptive large neighborhood search ALNS to set up an objective function for iteration, and outputting an optimal initial solution; based on the optimal initial solution generated by ALNS, performing reverse annealing and combining neighborhood operations to output an AGV robot scheduling and management solution; encrypting the AGV robot operation data using an asymmetric encryption algorithm, and storing the encrypted AGV robot operation data in a database.

[0007] As a preferred solution of the AGV robot scheduling management method of the present invention, wherein: the collecting of AGV robot operation data and establishing the AGV robot operation environment topology map G(V, E) based on the collected AGV robot operation data includes:

[0008] Collect AGV robot operating environment data, task data and battery data;

[0009] The collecting of AGV robot working environment data refers to deploying LiDAR sensors, high-definition cameras, inertial measurement units (IMUs) and high-precision GPS on the AGV robot to collect the AGV robot working environment data, wherein the AGV robot working environment data includes 3D point cloud data of the robot working environment, static and dynamic object data on the AGV robot driving path, GPS position data of the AGV robot, and acceleration data and angular velocity data of the AGV robot;

[0010] Based on the collected AGV robot working environment data, a synchronous localization and mapping algorithm SLAM is used to generate an environmental topology map G(V, E) according to the 3D point cloud data and GPS position data in the working environment. The AGV robot working environment topology map includes a node set V and an edge set E.

[0011] The node set V refers to the key nodes in the AGV robot scheduling environment, including the locations where the AGV robot needs to perform tasks, the path intersections and turning points that the AGV robot needs to pass during driving;

[0012] The edge set E refers to the connected paths between nodes;

[0013] The collecting of AGV robot task data refers to obtaining the task path using the node set and edge set in the environment topology graph G(V,E), collecting the load weight w of the current task through sensors, and setting the urgency of each task so as to give priority to the characteristics of each task in the scheduling process;

[0014] The collecting of AGV robot battery data refers to real-time monitoring of the AGV robot battery data through a power monitor installed on the AGV robot.

[0015] As a preferred solution of the AGV robot scheduling management method of the present invention, wherein: the setting of the critical power threshold of the AGV robot and real-time monitoring of the power status of the AGV robot based on the collected AGV robot operation data include:

[0016] Based on the collected AGV robot operation data, the battery consumption of the AGV robot operation task is calculated;

[0017]

[0018] Among them, E d is the battery consumption of each AGV robot task, is the battery consumption per unit distance traveled by the AGV robot, d i，j is the distance of the AGV robot from node i to node j, v is the driving speed of the AGV robot, w is the load weight of the AGV robot, W max is the maximum load weight of the AGV robot;

[0019] According to the calculated battery consumption E of the AGV robot task d and the current battery charge E of the AGV robot c , calculate the remaining power E of the AGV robot performing the current task after completing the task r ;

[0020] Set critical power threshold b c , and the remaining power E after the AGV robot completes the task r Make comparative judgments;

[0021] If E r >b c , then continue to execute the task;

[0022] If E r ≤ b c , then go to the nearest charging station to charge.

[0023] As a preferred solution of the AGV robot scheduling management method of the present invention, wherein: based on the task data of the AGV robot, the task priority score Pi is calculated, combined with the AGV robot working environment topology map G(V,E), the breadth-first search BFS is used to generate the candidate path set Ri, the candidate path set Ri is preliminarily screened using the greedy algorithm, the initial path of the AGV is generated, and the adaptive large neighborhood search ALNS is used to set up the objective function for iteration, and the optimal initial solution is output, including,

[0024] Based on the collected AGV robot task data, calculate the task priority Pi:

[0025]

[0026] Among them, T i d is the time limit for completing the task, T i c is the current time;

[0027] Based on the AGV robot working environment topology G(V,E), a breadth-first search BFS is used to generate all feasible candidate paths R for each AGV robot from the starting position to the target position. i :

[0028] R i = {r i1 ,r i2 ,Λr in},

[0029] Among them, i is the i-th AGV robot, n is the n feasible paths of the i-th AGV robot;

[0030] Establish ALNS objective function:

[0031]

[0032] Among them, f ALNS (q) is the total cost of the current path selection solution q, i is the i-th AGV robot, N is the total number of AGV robots, n is the number of paths that the i-th AGV robot can choose, and d i，j is the total distance traveled by AGV robot i choosing path j, C i，j (t) is the path r ij The congestion at time t, that is, the ratio of the number of AGV robots existing on the path at time t to the maximum number of AGV robots allowed on the path, T is the total time to complete the task, w1 and w2 are the weight coefficients of path length and path congestion respectively, q i，j is a binary decision variable indicating whether AGV robot i chooses path rij.i，j =1, it means that AGV robot i has selected the jth path. If q i，j =0, the path is not selected, β is the conflict penalty coefficient, which is used to ensure that each AGV robot only selects one path;

[0033] Use the greedy algorithm to select the candidate path set R i Perform a preliminary screening and set the screening criteria to give priority to the current shortest path r ij ;

[0034] The shortest path r obtained based on the greedy algorithm ij , generating candidate solutions by using the neighborhood operation of the adaptive large neighborhood search ALNS algorithm, wherein the neighborhood operation refers to path replacement and path adjustment;

[0035] Use the objective function to calculate the objective function value f of the current solution ALNS (q) c , and calculate the objective function value f of the candidate solution after the neighborhood operation ALNS (q) cl , for comparison;

[0036] If f ALNS (q) cl <f ALNS (q) c , ALNS accepts the new solution and continues to iterate until the preset maximum number of iterations is reached and the current optimal solution is obtained;

[0037] If f ALNS (q) cl ≥f ALNS (q) c , the iteration stops.

[0038] As a preferred solution of the AGV robot scheduling management method of the present invention, wherein: the optimal initial solution generated based on ALNS is reverse annealed and combined with neighborhood operations to output the AGV robot scheduling management solution including:

[0039] Use the optimal initial solution generated by ALNS as the initial solution for reverse annealing, set the initial temperature T0 for reverse annealing, and increase the annealing temperature after each iteration;

[0040] In each iteration of reverse annealing, the neighborhood operation is used to locally adjust the current solution, and the objective function value of the new solution after the neighborhood operation is calculated;

[0041] If the objective function value of the new solution is less than the objective function value of the current solution, the new solution is directly accepted;

[0042] If the objective function value of the new solution is ≥ the objective function value of the current solution, the inferior solution is accepted according to the annealing probability P;

[0043] When the maximum number of iterations is reached, the iteration is stopped, and the current objective function value after the reverse annealing is selected as the final solution. Based on the objective function value of the final solution, the AGV robot scheduling plan is output and the AGV robot scheduling operation is executed.

[0044] As a preferred solution of the AGV robot scheduling management method of the present invention, wherein: the encrypting of the AGV robot operation data using an asymmetric encryption algorithm includes:

[0045] During the AGV robot scheduling and path planning process, the asymmetric encryption algorithm RSA is used to generate a unique public key and private key for each AGV robot, and the public key and private key are stored in the key database. The public key is used to encrypt the AGV robot operation data. When the data needs to be accessed, the private key in the key database is used to decrypt it.

[0046] As a preferred solution of the AGV robot scheduling management method of the present invention, wherein: the storing of the encrypted AGV robot operation data in the database includes:

[0047] Select PostgreSQL database as the AGV robot operation database and set the access control mechanism. After the AGV robot operation data is encrypted, it is transmitted to the AGV robot operation database through the secure transmission protocol TLS, and the data backup operation is performed. The backed-up data is stored in the remote database and cloud database.

[0048] Another object of the present invention is to provide an AGV robot scheduling management system, which comprises:

[0049] The data collection module is used to collect the AGV robot operation data and establish the AGV robot operation environment topology map G (V, E);

[0050] The charging detection module is used to calculate the battery consumption of the AGV robot's operation task and perform charging operations;

[0051] Task scheduling and path planning module, used for AGV robot task scheduling and path planning;

[0052] The data encryption storage module is used to encrypt the AGV robot operation data and store it in the database.

[0053] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of an AGV robot scheduling management method when executing the computer program.

[0054] A computer-readable storage medium stores a computer program, which implements the steps of an AGV robot scheduling management method when executed by a processor.

[0055] The beneficial effects of the present invention are as follows: the present invention uses a greedy algorithm to preliminarily screen the candidate path set, generates the initial path of the AGV, uses ALNS for iterative optimization, outputs the optimal initial solution, combines reverse annealing, and finally outputs the AGV scheduling management method, thereby realizing the global optimal management of AGV robot scheduling, significantly improving the intelligence and flexibility of AGV scheduling, and ensuring the efficient operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0057] Figure 1 This is a flowchart of the AGV robot scheduling management method.

[0058] Figure 2 This is a structural diagram of the AGV robot scheduling and management system. DETAILED DESCRIPTION

[0059] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0061] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0062] Example 1

[0063] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides an AGV robot scheduling management method, the AGV robot scheduling management method includes:

[0064] S1. Collect AGV robot operation data, and establish an AGV robot operation environment topology map G(V,E) based on the collected AGV robot operation data;

[0065] Furthermore, the AGV robot operation data is collected, and based on the collected AGV robot operation data, an AGV robot operation environment topology map G (V, E) is established, including:

[0066] Collect AGV robot operating environment data, task data and battery data;

[0067] The collecting of AGV robot working environment data refers to deploying LiDAR sensors, high-definition cameras, inertial measurement units (IMUs) and high-precision GPS on the AGV robot to collect the AGV robot working environment data, wherein the AGV robot working environment data includes 3D point cloud data of the robot working environment, static and dynamic object data on the AGV robot driving path, GPS position data of the AGV robot, and acceleration data and angular velocity data of the AGV robot;

[0068] Based on the collected AGV robot working environment data, a synchronous localization and mapping algorithm SLAM is used to generate an environmental topology map G(V, E) according to the 3D point cloud data and GPS position data in the working environment. The AGV robot working environment topology map includes a node set V and an edge set E.

[0069] The node set V refers to the key nodes in the AGV robot scheduling environment, including the location where the AGV robot needs to perform tasks, the path intersection points and turning points that the AGV robot needs to pass during driving;

[0070] The edge set E refers to the connected paths between nodes;

[0071] The collecting of AGV robot task data refers to obtaining the task path using the node set and edge set in the environment topology graph G(V,E), collecting the load weight w of the current task through sensors, and setting the urgency of each task so as to give priority to the characteristics of each task in the scheduling process;

[0072] The collecting of AGV robot battery data refers to real-time monitoring of the AGV robot battery data through a power monitor installed on the AGV robot.

[0073] By collecting AGV robot operation data and establishing the AGV robot operation environment topology map G(V,E) based on this data, this step realizes an accurate description of the entire AGV working environment. This topology map not only reflects the real-time dynamic changes in the AGV operation process, but also is an important basis for subsequent path planning and scheduling management. The established AGV operation environment topology map provides a global perspective for the system, which can more clearly understand the position relationship of AGV in the operation environment and the complexity of task execution, reveal the potential bottlenecks and obstacles in the AGV operation environment, and provide support for subsequent path planning. In addition, it can provide clear boundaries and directions for algorithms such as breadth-first search in task allocation and path planning, making the algorithm's calculation efficiency higher. The rate is significantly improved. Secondly, the dynamic update characteristics of the topology map can greatly improve the system's adaptability in the face of complex and changing environments, reduce potential path conflicts and task delays, and provide a structured data basis for AGV task optimization. In subsequent steps, such as task priority calculation, candidate path generation, and the application of optimization algorithms, they all need to rely on the global information provided by the topology map. Therefore, this step not only enhances the visualization capability of the system, but also provides accurate environmental modeling for subsequent algorithm processing, ensuring the accuracy of path planning and the rationality of task scheduling, improving the overall efficiency and accuracy of path planning, and greatly improving the intelligence level and operating efficiency of the entire system.

[0074] S2. Set the critical power threshold of the AGV robot and monitor the power status of the AGV robot in real time based on the collected AGV robot operation data;

[0075] Furthermore, the critical power threshold of the AGV robot is set, and the power status of the AGV robot is monitored in real time based on the collected AGV robot operation data, including:

[0076] Based on the collected AGV robot operation data, the battery consumption of the AGV robot operation task is calculated;

[0077]

[0078] Among them, E d is the battery consumption of each AGV robot task, is the battery consumption per unit distance traveled by the AGV robot, d i，j is the distance of the AGV robot from node i to node j, v is the driving speed of the AGV robot, w is the load weight of the AGV robot, W max is the maximum load weight of the AGV robot;

[0079] According to the calculated battery consumption E of the AGV robot task dand the current battery charge E of the AGV robot c , calculate the remaining power E of the AGV robot performing the current task after completing the task r ;

[0080] Set critical power threshold b c , and the remaining power E after the AGV robot completes the task r Make comparative judgments;

[0081] If E r >b c , then continue to execute the task;

[0082] If E r ≤ b c , then go to the nearest charging station to charge.

[0083] By setting the critical power threshold of the AGV robot and monitoring the power status in real time, the system can accurately calculate the battery consumption required for each task, comprehensively consider the driving distance, speed and load of the AGV robot, and accurately evaluate the power demand of the task. This refined calculation enables the system to dynamically predict the remaining power E after the AGV completes the task. r and the preset critical power threshold b c For comparison. r Greater than b c When E r Less than or equal to b c When the AGV robot is in a state of emergency, it will automatically go to the nearest charging station for charging to avoid task interruption due to power exhaustion, thus realizing the continuity of AGV task execution and intelligent power management, avoiding the risk of downtime due to insufficient power and improving the overall efficiency and reliability of the system.

[0084] S3, based on the task data of the AGV robot, calculate the task priority score Pi, combine the AGV robot working environment topology map G(V,E), use breadth-first search BFS to generate a candidate path set Ri, use the greedy algorithm to preliminarily screen the candidate path set Ri, generate the initial path of the AGV, and use the adaptive large neighborhood search ALNS to set up the objective function for iteration, and output the optimal initial solution;

[0085] Furthermore, based on the task data of the AGV robot, the task priority score Pi is calculated, and combined with the AGV robot working environment topology map G(V,E), the breadth-first search BFS is used to generate the candidate path set Ri, and the greedy algorithm is used to preliminarily screen the candidate path set Ri to generate the initial path of the AGV, and the adaptive large neighborhood search ALNS is used to set up the objective function for iteration, and the optimal initial solution is output, including,

[0086] Based on the collected AGV robot task data, calculate the task priority Pi:

[0087]

[0088] Among them, T i d is the time limit for completing the task, T i c is the current time;

[0089] Based on the AGV robot working environment topology G(V,E), a breadth-first search BFS is used to generate all feasible candidate paths R for each AGV robot from the starting position to the target position. i :

[0090] R i = {r i1 ,r i2 ,Λr in},

[0091] Among them, i is the i-th AGV robot, n is the n feasible paths of the i-th AGV robot;

[0092] Establish ALNS objective function:

[0093]

[0094] Among them, f ALNS (q) is the total cost of the current path selection solution q, i is the i-th AGV robot, N is the total number of AGV robots, n is the number of paths that the i-th AGV robot can choose, and d i，j is the total distance traveled by AGV robot i choosing path j, C i，j (t) is the path r ij The congestion at time t, that is, the ratio of the number of AGV robots existing on the path at time t to the maximum number of AGV robots allowed on the path, T is the total time to complete the task, w1 and w2 are the weight coefficients of path length and path congestion, respectively, which are set by experts based on historical experience and customer requirements, q i，j is a binary decision variable indicating whether AGV robot i chooses path rij. i，j=1, it means that AGV robot i has selected the jth path. If q i，j =0, the path is not selected, β is the conflict penalty coefficient, which is used to ensure that each AGV robot only selects one path;

[0095] In actual production scenarios, multiple AGVs working simultaneously will increase the complexity of path scheduling. If each AGV robot does not have an intelligent path selection mechanism, multiple AGVs will choose the same path, increasing the task completion time and even causing conflicts. i,j The introduction of can effectively avoid this situation, so that each AGV can perform tasks on the optimal path. When multiple AGV robots work at the same time, it is necessary to plan the paths of different AGV robots at the same time to avoid conflicts and congestion. The ALNS objective function analyzes and weighs the path selection of each AGV robot, which improves the applicability of the system in multi-vehicle scheduling. By introducing the path length d i，j and congestion C i，j The two parameters (t) can dynamically adjust the path selection according to the actual situation at the current time. Especially when the task completion time limit (T) is set, the system can evaluate the feasibility of the path in real time to ensure that the AGV can complete the task within the specified time. The conflict penalty coefficient β is introduced to limit the situation where multiple AGVs choose the same path, prevent delays caused by path overlap and reduce the overall efficiency of the system, so that the AGV scheduling system can avoid congested paths more intelligently and further improve the operation efficiency.

[0096] Use the greedy algorithm to select the candidate path set R i Perform a preliminary screening and set the screening criteria to give priority to the current shortest path r ij ;

[0097] The shortest path r obtained based on the greedy algorithm ij , generating candidate solutions by using the neighborhood operation of the adaptive large neighborhood search ALNS algorithm, wherein the neighborhood operation refers to path replacement and path adjustment;

[0098] The path replacement refers to replacing the path selected by the greedy algorithm to avoid conflicts when the path is congested in the subsequent period;

[0099] The path adjustment means that the path selected by the greedy algorithm will be longer, and a shorter alternative path is found in the neighborhood through ALNS;

[0100] Use the objective function to calculate the objective function value f of the current solution ALNS (q) c , and calculate the objective function value f of the candidate solution after the neighborhood operation ALNS (q) cl, for comparison;

[0101] If f ALNS (q) cl <f ALNS (q) c , ALNS accepts the new solution and continues to iterate until the preset maximum number of iterations is reached and the current optimal solution is obtained;

[0102] If f ALNS (q) cl ≥f ALNS (q) c , the iteration stops.

[0103] By calculating the task priority score Pi, the system can dynamically adjust the urgency of the task based on the task completion deadline and the current time, and realize the accurate division of different task priorities. In this way, the AGV robot can be reasonably scheduled according to the importance and urgency of the task to ensure that high-priority tasks are executed in a timely manner, thereby improving the efficiency of task management. Based on the AGV operating environment topology graph G(V,E), the breadth-first search BFS is used to generate the candidate path set Ri, which provides a comprehensive path selection for the AGV and avoids traffic congestion and delays caused by too few paths. The breadth exploration feature of BFS ensures the balanced consideration of all possible paths, laying the foundation for subsequent screening and optimization. In addition, the greedy algorithm is used to give priority to the shortest path, and a path that meets the efficiency requirements is initially generated. The fast screening capability of the greedy algorithm reduces the computational complexity and improves the response speed of the system, allowing the AGV to quickly obtain in the operating environment. An executable initial path is obtained. However, the greedy algorithm may produce a local optimal solution. Therefore, the adaptive large neighborhood search ALNS is introduced to further optimize the path. ALNS realizes dynamic optimization of the path through neighborhood operations, such as path replacement and path adjustment, so that the path is not only effective at the beginning, but also can adapt to environmental changes during the operation, such as the occurrence of congestion. This step ensures the flexibility of path planning and reduces the risk of delays caused by path congestion of AGV. Finally, ALNS outputs the optimal initial solution through iterative calculation and comparison of the objective function value, and through repeated adjustments and iterations, it ensures that the path selected by AGV is optimal under the comprehensive evaluation of total cost, time and congestion. This process greatly improves the scheduling accuracy and resource utilization efficiency of AGV, while reducing conflicts between AGVs, optimizing the path selection of AGV, improving the efficiency of task execution, and ensuring that the system maintains efficient and stable operation in a complex environment.

[0104] S4, based on the optimal initial solution generated by ALNS, reverse annealing is performed and combined with neighborhood operations to output the AGV robot scheduling management plan;

[0105] Furthermore, based on the optimal initial solution generated by ALNS, reverse annealing is performed and combined with neighborhood operations to output the AGV robot scheduling management solution, including:

[0106] Use the optimal initial solution generated by ALNS as the initial solution for reverse annealing, set the initial temperature T0 for reverse annealing, and increase the annealing temperature after each iteration. By increasing the annealing temperature, the system gradually shifts from local search to a wider area in the solution space, and can escape the trap of local optimal solution.

[0107] Reverse annealing is a special annealing algorithm that is used to gradually expand the search range and perform further optimization based on an existing better solution. Its main feature is that it starts from a local solution and then explores a wider solution space by gradually increasing the temperature, and finally approaches the global optimal solution. Different from the classic simulated annealing, reverse annealing starts from a better solution and gradually increases the randomness of the search and the range of the solution space.

[0108] In each iteration of reverse annealing, the neighborhood operation is used to locally adjust the current solution, and the objective function value of the new solution after the neighborhood operation is calculated;

[0109] If the objective function value of the new solution is less than the objective function value of the current solution, the new solution is directly accepted;

[0110] If the objective function value of the new solution is ≥ the objective function value of the current solution, the inferior solution is accepted according to the annealing probability P;

[0111] Although the new solution is inferior to the current solution, as the temperature gradually increases, reverse annealing may accept these inferior solutions to jump out of the local optimum, gradually expand the search range, and increase the chance of finding the global optimal solution. This approach helps the algorithm expand from an already optimized solution to a wider solution space and jump out of possible local optimal solutions.

[0112] When the maximum number of iterations is reached, the iteration is stopped, and the current objective function value after the reverse annealing is selected as the final solution. Based on the objective function value of the final solution, the AGV robot scheduling plan is output and the AGV robot scheduling operation is performed; the AGV robot scheduling plan refers to the AGV robot scheduling plan with the minimum total path length, the lowest congestion and no conflict.

[0113] By combining the reverse annealing algorithm with neighborhood operations, the AGV scheduling scheme can be further optimized based on the existing optimal initial solution. Reverse annealing starts from the optimal solution generated by ALNS, sets a lower initial temperature, and gradually increases the temperature, so that the search is expanded from the local optimal area to a wider solution space, effectively jumping out of the trap of the local optimal solution. This feature is different from the classic simulated annealing. Reverse annealing starts from a better solution. As the temperature increases, the probability of accepting an inferior solution increases, thereby expanding the search range of the solution space. In each iteration, the neighborhood operation is used to fine-tune the current solution and determine whether it is based on the objective function value of the new solution. Accept the new solution. If the new solution is better than the current solution, accept it directly; if the new solution is inferior, accept it according to the annealing probability P to increase the chance of finding the global optimal solution. This approach can not only jump out of the local optimum, but also as the annealing temperature gradually increases, the algorithm will gradually approach the global optimal solution. Finally, when the maximum number of iterations is reached, the current objective function value is selected as the final solution, and the optimal AGV scheduling plan is output. This plan includes the shortest total path length, the lowest congestion and the scheduling plan to avoid conflicts, ensuring that the AGV can perform tasks efficiently, reduce path overlap and task conflicts, and greatly improve the operating efficiency and resource utilization of the entire system.

[0114] S5. Encrypt the AGV robot operation data using an asymmetric encryption algorithm, and store the encrypted AGV robot operation data in a database;

[0115] Furthermore, the AGV robot operation data is encrypted using an asymmetric encryption algorithm including:

[0116] During the AGV robot scheduling and path planning process, the asymmetric encryption algorithm RSA is used to generate a unique public key and private key for each AGV robot, and the public key and private key are stored in the key database. The public key is used to encrypt the AGV robot operation data. When the data needs to be accessed, the private key in the key database is used to decrypt it.

[0117] By introducing the asymmetric encryption algorithm RSA in the AGV robot scheduling and path planning process, and generating a unique public key and private key for each AGV robot, the system can effectively ensure the security of each AGV robot's operating data. The public key is used to encrypt the AGV robot's operating data, while the private key is stored in the key database and is used to decrypt the data when it is needed. This not only improves the security of data transmission and storage, but also ensures data integrity and permission control, effectively improving the overall security level of the system and meeting the high requirements for data security and privacy protection in complex industrial environments.

[0118] Furthermore, the encrypted AGV robot operation data is stored in the database including:

[0119] Select PostgreSQL database as the AGV robot operation database and set the access control mechanism. After the AGV robot operation data is encrypted, it is transmitted to the AGV robot operation database through the secure transmission protocol TLS, and the data backup operation is performed. The backed-up data is stored in the remote database and cloud database.

[0120] By selecting PostgreSQL database as the storage platform for AGV robot operation data and setting a strict access control mechanism, the system ensures the security and controllability of data during the storage process. The encrypted AGV data is transmitted to the database through the secure transmission protocol TLS to prevent the data from being stolen or tampered with during the transmission process, further improving the security of the system. Performing data backup operations not only effectively prevents data loss or damage, but also enhances data redundancy and reliability by storing backup data in off-site databases and cloud databases. In the event of disaster recovery or system failure, the system can quickly restore data through multiple backup mechanisms to ensure the integrity and availability of AGV robot operation data. Through this solution, not only is efficient protection of sensitive data achieved, but it also provides strong support for long-term storage and global data scheduling, ultimately ensuring the stable operation of the system and high data security.

[0121] Example 2

[0122] Reference Figure 2 , which is the second embodiment of the present invention, which is different from the previous embodiment and provides an AGV robot scheduling management system, including:

[0123] The data collection module is used to collect the AGV robot operation data and establish the AGV robot operation environment topology map G (V, E);

[0124] The charging detection module is used to calculate the battery consumption of the AGV robot's operation task and perform charging operations;

[0125] Task scheduling and path planning module, used for AGV robot task scheduling and path planning;

[0126] The data encryption storage module is used to encrypt the AGV robot operation data and store it in the database.

[0127] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0128] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0129] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0130] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0131] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for scheduling and managing an AGV robot, characterized in that: include, Collect AGV robot operation data, and establish an AGV robot operation environment topology map G(V,E) based on the collected AGV robot operation data; Set the critical power threshold of the AGV robot and monitor the power status of the AGV robot in real time based on the collected AGV robot operation data; Based on the task data of the AGV robot, the task priority score Pi is calculated. Combined with the topological graph of the AGV robot's working environment G(V,E), the breadth-first search BFS is used to generate the candidate path set Ri. The greedy algorithm is used to preliminarily screen the candidate path set Ri to generate the initial path of the AGV, and the adaptive large neighborhood search ALNS is used to set up the objective function for iteration to output the optimal initial solution. Based on the optimal initial solution generated by ALNS, reverse annealing is performed and combined with neighborhood operations to output the AGV robot scheduling management solution; The AGV robot operation data is encrypted using an asymmetric encryption algorithm, and the encrypted AGV robot operation data is stored in a database.

2. The AGV robot scheduling management method according to claim 1, characterized in that: The collecting of AGV robot operation data and establishing the AGV robot operation environment topology map G(V, E) based on the collected AGV robot operation data includes: Collect AGV robot operating environment data, task data and battery data; The collecting of AGV robot working environment data refers to deploying LiDAR sensors, high-definition cameras, inertial measurement units (IMUs) and high-precision GPS on the AGV robot to collect the AGV robot working environment data, wherein the AGV robot working environment data includes 3D point cloud data of the robot working environment, static and dynamic object data on the AGV robot driving path, GPS position data of the AGV robot, and acceleration data and angular velocity data of the AGV robot; Based on the collected AGV robot working environment data, a synchronous localization and mapping algorithm SLAM is used to generate an environmental topology map G(V, E) according to the 3D point cloud data and GPS position data in the working environment. The AGV robot working environment topology map includes a node set V and an edge set E. The node set V refers to the key nodes in the AGV robot scheduling environment, including the locations where the AGV robot needs to perform tasks, the path intersections and turning points that the AGV robot needs to pass during driving; The edge set E refers to the connected paths between nodes; The collecting of AGV robot task data refers to obtaining the task path using the node set and edge set in the environment topology graph G(V,E), collecting the load weight w of the current task through sensors, and setting the urgency of each task so as to give priority to the characteristics of each task in the scheduling process; The collecting of AGV robot battery data refers to real-time monitoring of the AGV robot battery data through a power monitor installed on the AGV robot.

3. The AGV robot scheduling management method according to claim 2, characterized in that: The setting of the critical power threshold of the AGV robot and real-time monitoring of the power status of the AGV robot based on the collected AGV robot operation data include: Based on the collected AGV robot operation data, the battery consumption of the AGV robot operation task is calculated; Among them, E d is the battery consumption of each AGV robot task, is the battery consumption per unit distance traveled by the AGV robot, d i，j is the distance of the AGV robot from node i to node j, v is the driving speed of the AGV robot, w is the load weight of the AGV robot, W max is the maximum load weight of the AGV robot; According to the calculated battery consumption E of the AGV robot task d and the current battery charge E of the AGV robot c , calculate the remaining power E of the AGV robot performing the current task after completing the task r ; Set critical power threshold b c , and the remaining power E after the AGV robot completes the task r Make comparative judgments; If E r >b c , then continue to execute the task; If E r ≤ b c , then go to the nearest charging station to charge.

4. The AGV robot scheduling management method according to claim 3, characterized in that: The task data based on the AGV robot is used to calculate the task priority score Pi, and combined with the AGV robot working environment topology map G(V,E), the breadth-first search BFS is used to generate the candidate path set Ri, and the candidate path set Ri is preliminarily screened using the greedy algorithm to generate the initial path of the AGV, and the adaptive large neighborhood search ALNS is used to set up the objective function for iteration, and the optimal initial solution is output, including: Based on the collected AGV robot task data, calculate the task priority Pi: in, is the time limit for completing the task. is the current time; Based on the AGV robot working environment topology G(V,E), a breadth-first search BFS is used to generate all feasible candidate paths R for each AGV robot from the starting position to the target position. i : R i ={r i1 ,r i2 ,Λr in }, Among them, i is the i-th AGV robot, n is the n feasible paths of the i-th AGV robot; Establish ALNS objective function: Among them, f ALNS (q) is the total cost of the current path selection solution q, i is the i-th AGV robot, N is the total number of AGV robots, n is the number of paths that the i-th AGV robot can choose, and d i，j is the total distance traveled by AGV robot i choosing path j, C i，j (t) is the path r ij The congestion at time t, that is, the ratio of the number of AGV robots existing on the path at time t to the maximum number of AGV robots allowed on the path, T is the total time to complete the task, w1 and w2 are the weight coefficients of path length and path congestion respectively, q i，j is a binary decision variable indicating whether AGV robot i chooses path rij. i，j =1, it means that AGV robot i has selected the jth path. If q i，j =0, the path is not selected, β is the conflict penalty coefficient, which is used to ensure that each AGV robot only selects one path; Use the greedy algorithm to select the candidate path set R i Perform a preliminary screening and set the screening criteria to give priority to the current shortest path r ij ; The shortest path r obtained based on the greedy algorithm ij , generating candidate solutions by using the neighborhood operation of the adaptive large neighborhood search ALNS algorithm, wherein the neighborhood operation refers to path replacement and path adjustment; Use the objective function to calculate the objective function value f of the current solution ALNS (q) c , and calculate the objective function value f of the candidate solution after the neighborhood operation ALNS (q) cl , for comparison; If f ALNS (q) cl <f ALNS (q) c , ALNS accepts the new solution and continues to iterate until the preset maximum number of iterations is reached and the current optimal solution is obtained; If f ALNS (q) cl ≥f ALNS (q) c , the iteration stops.

5. The AGV robot scheduling management method according to claim 4, characterized in that: The optimal initial solution generated based on ALNS is subjected to reverse annealing and combined with neighborhood operations to output the AGV robot scheduling management solution, including: Use the optimal initial solution generated by ALNS as the initial solution for reverse annealing, set the initial temperature T0 for reverse annealing, and increase the annealing temperature after each iteration; In each iteration of reverse annealing, the neighborhood operation is used to locally adjust the current solution, and the objective function value of the new solution after the neighborhood operation is calculated; If the objective function value of the new solution is less than the objective function value of the current solution, the new solution is directly accepted; If the objective function value of the new solution is ≥ the objective function value of the current solution, the inferior solution is accepted according to the annealing probability P; When the maximum number of iterations is reached, the iteration is stopped, and the current objective function value after the reverse annealing is selected as the final solution. Based on the objective function value of the final solution, the AGV robot scheduling plan is output and the AGV robot scheduling operation is executed.

6. The AGV robot scheduling management method according to claim 5, characterized in that: The AGV robot operation data is encrypted using an asymmetric encryption algorithm including: During the AGV robot scheduling and path planning process, the asymmetric encryption algorithm RSA is used to generate a unique public key and private key for each AGV robot, and the public key and private key are stored in the key database. The public key is used to encrypt the AGV robot operation data. When the data needs to be accessed, the private key in the key database is used to decrypt it.

7. The AGV robot scheduling management method according to claim 6, characterized in that: storing the encrypted AGV robot operation data in the database includes: Select PostgreSQL database as the AGV robot operation database and set the access control mechanism. After the AGV robot operation data is encrypted, it is transmitted to the AGV robot operation database through the secure transmission protocol TLS, and the data backup operation is performed. The backed-up data is stored in the remote database and cloud database.

8. An AGV robot scheduling management system based on the AGV robot scheduling management method according to any one of claims 1 to 7, characterized in that: include, The data collection module is used to collect the AGV robot operation data and establish the AGV robot operation environment topology map G (V, E); The charging detection module is used to calculate the battery consumption of the AGV robot's operation task and perform charging operations; Task scheduling and path planning module, used for AGV robot task scheduling and path planning; The data encryption storage module is used to encrypt the AGV robot operation data and store it in the database.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the AGV robot scheduling management method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the AGV robot scheduling management method described in any one of claims 1 to 7 are implemented.

Images