A method and system for optimizing AGV routes based on big data

Abstract

The present invention relates to the technical field of route optimization, and specifically discloses an AGV route optimization method and system based on big data, comprising the following steps: step S1: obtaining a driving route in a warehouse and dividing it into a plurality of conveying sections; setting a driving speed and direction, and calculating the energy consumption of completing each conveying section; step S2: determining the end point and departure point of the task according to specific conveying task requirements; calculating the total energy consumption by analyzing the conveying path, and selecting the path with the minimum total energy consumption as the optimal path; step S3: allocating tasks within each cycle; checking whether different optimal paths have a common conveying section; analyzing the estimated arrival time, and identifying potential collision paths; step S4: selecting a plurality of paths for adjustment for the detected collision paths; reallocating tasks for the current cycle, checking again whether there are still collision paths, and repeating this process until there are no collision paths within the current cycle.

Description

Technical Field

[0001] The present invention relates to the technical field of route optimization, and in particular to an AGV route optimization method and system based on big data. Background Art

[0002] AGV (Automated Guided Vehicle) routes travel and operate according to preset guidance paths; these routes can be planned and set in a variety of ways, depending on the type of AGV, application scenario and technical implementation.

[0003] In the current technological context, route planning for automated guided vehicles (AGVs) faces some challenges. Due to the lack of optimized path planning algorithms, AGVs often need to follow preset fixed routes, which are often not the shortest or most energy-efficient options. In addition, as the demand for internal logistics in warehouses increases, the number of AGVs is also growing, leading to congestion during certain busy periods and areas. This congestion not only reduces the speed of a single AGV, but also affects the transportation efficiency of the entire system. In order to solve this problem, it is necessary to develop more intelligent and flexible path planning algorithms. Summary of the invention

[0004] The purpose of the present invention is to provide an AGV route optimization method and system based on big data to solve the above technical problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A method for optimizing AGV routes based on big data, comprising the following steps: Step S1: Obtain all driving routes of the automatic guided vehicle in the warehouse, and divide all driving routes into a number of conveying sections; set the driving speed and driving direction, and obtain the energy consumed by the automatic guided vehicle when it completes the conveying section at the driving speed and driving direction, which is recorded as the energy consumption of the conveying section; Step S2: Obtain a transport task, and obtain a transport destination according to the transport task; obtain a departure point of an automatic guided vehicle, and obtain a complete transport path of the transport task according to the departure point and the destination; obtain all transport sections included in the transport path and the driving direction of each transport section, obtain the energy consumption of each transport section, and obtain the total energy consumption of the transport path; select the transport path with the minimum total energy consumption as the optimal path for the transport task; Step S3: obtaining the working time of the automated guided vehicle, dividing the working time into a number of transport cycles, obtaining the starting time of the transport cycle, and recording it as the departure time of the transport cycle; obtaining the maximum number n of departures in the transport cycle, and assigning n transport tasks to all automated guided vehicles in the transport cycle, with each automated guided vehicle corresponding to one transport task; Obtain the best path for each transport task within the transport cycle, determine whether there is a common transport section between the best paths, and record several best paths with the same transport section as intersecting paths, and record the same transport section between the intersecting paths as the same transport section; Obtain the section length of each transport section, and obtain the estimated arrival time of each transport section in the intersecting path according to the departure time, driving speed and section length; determine whether the estimated arrival times of the same transport sections between the intersecting paths are close, and if so, record the intersecting paths with the same transport section having close estimated arrival times as collision paths; Step S4: Obtain the total number m of collision paths within the transport cycle, select m-1 collision paths as transfer paths, and replace the transport tasks corresponding to the transfer paths to the next transport cycle for allocation; and re-obtain m-1 transport tasks to the current transport cycle, and re-determine whether there is a collision path within the current transport cycle; and so on, until there is no collision path within the transport cycle.

[0006] As a further solution of the present invention: the process of dividing the conveying section includes: The intersection points in all driving routes are obtained, wherein the intersection points include a departure point and an end point; a transport section is obtained from every two adjacent intersection points, and finally a plurality of transport sections are obtained.

[0007] As a further solution of the present invention: the process of setting the driving direction includes: Two intersection points at both ends of the transport section are obtained and marked as P1 and P2 respectively; then two driving directions of the transport section are obtained, namely, P1 points to P2 and P2 points to P1.

[0008] As a further solution of the present invention: the process of obtaining the total energy consumption of the transport path is: Obtain the energy consumption of each transport section {W1, W2, ..., W k}, where W1 represents the energy consumption of the first transport section, k is the total number of transport sections included in the transport path, and the total energy consumption is , where i∈[1,k], W i Represents the energy consumption of the i-th transmission section.

[0009] As a further solution of the present invention: the process of dividing the transport cycle includes: Obtain historical transportation records, wherein the historical transportation records include the consumption time of each transportation task, and the consumption time is the time consumed to complete the transportation task; obtain the average value of all consumption times in the historical transportation records, recorded as the consumption time average; use the consumption time average as the time interval threshold, and within the working time, select a node every time interval threshold, and each two adjacent nodes constitute a transportation cycle; the node includes the starting time and the ending time of the working time.

[0010] As a further solution of the present invention: the process of determining whether there is a common transport section between the optimal paths includes: All the transport sections in the warehouse are numbered, the numbers of the transport sections included in the optimal path are obtained, and the numbering sequence of the optimal path is obtained; if there are two optimal paths, the numbering sequences of the two optimal paths are obtained, and it is determined whether the two numbering sequences have an intersection. If there is an intersection, the two optimal paths have the same transport section; if there is no intersection, the two optimal paths do not have the same transport section.

[0011] As a further solution of the present invention: the process of determining whether the estimated arrival times of the same transport sections between the intersecting paths are close comprises: If there are two intersecting paths, for any identical transport section between the two intersecting paths, obtain the estimated arrival time of the identical transport section and record them as t1 and t2 respectively; set the difference threshold Ct, if |t1-t2|∈Ct, then there is an identical transport section with a similar estimated arrival time between the two intersecting paths; otherwise, there is no identical transport section with a similar estimated arrival time between the two intersecting paths.

[0012] As a further solution of the present invention: the process of selecting the transfer path includes: The generation time of the transport task corresponding to each collision path is obtained, where the generation time is the moment when the transport task is generated; all generation times are sorted in order of precedence, and the collision paths corresponding to the last m-1 generation times are selected as the transfer paths.

[0013] As a further solution of the present invention: an AGV route optimization system based on big data, comprising: Energy consumption collection module: obtain all driving routes of the automatic guided vehicle in the warehouse, divide all driving routes into several conveying sections; set the driving speed and driving direction, obtain the energy consumed by the automatic guided vehicle when it completes the conveying section at the driving speed and driving direction, and record it as the energy consumption of the conveying section; Path determination module: obtain the transport task, and obtain the transport destination according to the transport task; obtain the departure point of the automatic guided vehicle, and obtain the entire transport path of the transport task according to the departure point and the destination; obtain all the transport sections included in the transport path and the driving direction of each transport section, obtain the energy consumption of each transport section, and obtain the total energy consumption of the transport path; select the transport path with the minimum total energy consumption as the optimal path for the transport task; Collision judgment module: obtain the working time of the automatic guided vehicle, divide the working time into several transport cycles, obtain the starting time of the transport cycle, and record it as the departure time of the transport cycle; obtain the maximum number n of departures in the transport cycle, and assign n transport tasks to all automatic guided vehicles in the transport cycle, with each automatic guided vehicle corresponding to one transport task; Obtain the best path for each transport task within the transport cycle, determine whether there is a common transport section between the best paths, and record several best paths with the same transport section as intersecting paths, and record the same transport section between the intersecting paths as the same transport section; Obtain the section length of each transport section, and obtain the estimated arrival time of each transport section in the intersecting path according to the departure time, driving speed and section length; determine whether the estimated arrival times of the same transport sections between the intersecting paths are close, and if so, record the intersecting paths with the same transport section having close estimated arrival times as collision paths; Delivery time adjustment module: obtain the total number m of collision paths within the transportation cycle, select m-1 collision paths as transfer paths, and replace the transportation tasks corresponding to the transfer paths to the next transportation cycle for allocation; and re-acquire m-1 transportation tasks to the current transportation cycle, and re-determine whether there is a collision path within the current transportation cycle; and so on, until there is no collision path within the transportation cycle.

[0014] Beneficial effects of the present invention: The present invention reduces energy consumption by optimizing the driving route of AGV and reducing unnecessary driving and waiting time. This helps to extend the operating time of AGV and reduce the charging frequency, thereby improving the overall energy utilization efficiency. By selecting the transportation path with the lowest total energy consumption as the optimal path, the driving distance and time of AGV in the warehouse can be reduced, thereby increasing the delivery speed of goods and reducing order processing time. The present invention also reduces congestion and potential collision risks by predicting and managing the optimal path of AGV to avoid multiple AGVs using the same section of road at the same time. The optimized route planning can ensure that AGV can operate efficiently during peak hours, reduce delays or downtime caused by route conflicts, and improve the stability and reliability of the entire logistics system. Using big data analysis to guide AGV route selection and task allocation can achieve more intelligent and automated operations, reduce human intervention, and improve the accuracy and efficiency of decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below in conjunction with the accompanying drawings.

[0016] Figure 1 It is a flow chart of an AGV route optimization method based on big data in the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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.

[0018] See also Figure 1 As shown, the present invention is an AGV route optimization method based on big data, comprising the following steps: Step S1: Obtain all driving routes of the automatic guided vehicle in the warehouse, and divide all driving routes into a number of conveying sections; set the driving speed and driving direction, and obtain the energy consumed by the automatic guided vehicle when it completes the conveying section at the driving speed and driving direction, which is recorded as the energy consumption of the conveying section; It is understandable that it is necessary to obtain comprehensive route data for all AGVs in the warehouse; this includes the movement paths of AGVs in various areas of the warehouse; this data can be collected through sensors, GPS or other positioning technologies; all collected route data is divided into several specific conveying sections; each section represents a specific movement interval of the AGV in the warehouse, such as from one shelf to another, or from one workstation to another; for each conveying section, the AGV's travel speed and direction are set; then, based on these parameters, the energy consumed by the AGV when completing the section is calculated; this calculation process may need to consider a variety of factors, such as the road conditions, slope and curvature of the conveying section; in this way, the energy consumption data of each conveying section can be obtained; As a preferred embodiment of the present invention, the process of dividing the transport section includes: Obtaining intersections in all driving routes, wherein the intersections include a departure point and an end point; obtaining a transport section from every two adjacent intersections, and finally obtaining a plurality of transport sections; The process of setting the driving direction includes: Obtain two intersection points at both ends of the transport section and mark them as P1 and P2 respectively; then obtain two driving directions of the transport section, which are P1 pointing to P2 and P2 pointing to P1 respectively; It should be noted that the intersection is a key position in the route where the AGV needs to make a direction choice or change the driving path; every two adjacent intersections are connected to form a specific conveying section; this process will be repeated until all the intersections are connected, thereby obtaining several conveying sections in the entire warehouse; through the above steps, a complete conveying section network can be obtained, which covers all possible driving paths of the AGV in the warehouse; It can be understood that each transport section has two driving directions, and each of the two driving directions corresponds to one energy consumption, so each transport section has two energy consumptions; Step S2: Obtain a transport task, and obtain a transport destination according to the transport task; obtain a departure point of an automatic guided vehicle, and obtain a complete transport path of the transport task according to the departure point and the destination; obtain all transport sections included in the transport path and the driving direction of each transport section, obtain the energy consumption of each transport section, and obtain the total energy consumption of the transport path; select the transport path with the minimum total energy consumption as the optimal path for the transport task; It should be noted that the transport task generally refers to the specific work of moving items from one location to another in a logistics or production environment; It can be understood that each conveying path can be further refined into several specific conveying sections, and the driving direction of each section is obtained according to the action direction of the AGV in the conveying path; As a preferred embodiment of the present invention, the process of obtaining the total energy consumption of the transport path is: Obtain the energy consumption of each transport section {W1, W2, ..., W k}, where W1 represents the energy consumption of the first transport section, k is the total number of transport sections included in the transport path, and the total energy consumption is , where i∈[1,k], W i represents the energy consumption of the i-th transmission section; It can be understood that the energy consumption of all conveying sections is accumulated to obtain the total energy consumption of each conveying path; among all calculated conveying paths, the path with the smallest total energy consumption is selected as the optimal path; this ensures that the AGV can reduce energy consumption as much as possible while completing the task; Step S3: obtaining the working time of the automated guided vehicle, dividing the working time into a number of transport cycles, obtaining the starting time of the transport cycle, and recording it as the departure time of the transport cycle; obtaining the maximum number n of departures in the transport cycle, and assigning n transport tasks to all automated guided vehicles in the transport cycle, with each automated guided vehicle corresponding to one transport task; Obtain the best path for each transport task within the transport cycle, determine whether there is a common transport section between the best paths, and record several best paths with the same transport section as intersecting paths, and record the same transport section between the intersecting paths as the same transport section; Obtain the section length of each transport section, and obtain the estimated arrival time of each transport section in the intersecting path according to the departure time, driving speed and section length; determine whether the estimated arrival times of the same transport sections between the intersecting paths are close, and if so, record the intersecting paths with the same transport section having close estimated arrival times as collision paths; It is understandable that the total working time of the AGV in a day or a week needs to be determined; this time is usually determined based on production demand and logistics planning; in each transportation cycle, n transportation tasks are assigned to n AGVs according to the number of AGVs and task requirements; each AGV is responsible for completing a specific transportation task; check whether there are the same transportation sections between all the best paths; if so, mark these paths as intersecting paths and record the same transportation sections; for the same transportation section in each intersecting path, calculate the estimated time for the AGV to arrive at the section based on the departure time, driving speed and section length; compare whether the estimated arrival times of the same transportation sections between the intersecting paths are close; if close, mark these paths as collision paths. This means that during these time periods, multiple AGVs may meet on the same section, causing congestion on the transportation section, and corresponding measures need to be taken to avoid conflicts; It is worth noting that the process of obtaining the estimated arrival time includes: Obtain the optimal path, renumber all the transport paths within the optimal path according to the driving order of the AGV, and obtain the time T = L / v consumed by the AGV to complete each transport path in turn, where L is the length of the transport path section and v is the driving speed. The estimated delivery time of the i-th transport path is , where T0 is the departure time, T x Indicates the time it takes for the AGV to complete the xth conveying path; As a preferred embodiment of the present invention, the process of dividing the transport cycle includes: Obtain historical transport records, wherein the historical transport records include the consumption time of each transport task, and the consumption time is the time consumed to complete the transport task; obtain the average value of all consumption times in the historical transport records, recorded as the consumption time average; take the consumption time average as the time interval threshold, and within the working time, select a node every time interval threshold, and each two adjacent nodes constitute a transport cycle; the node includes the starting time and the ending time of the working time; It is understandable that it is necessary to collect and organize the records of transportation tasks in the past period of time; these records should include detailed information on each transportation task, especially the time consumed to complete each task; extract the consumption time of all tasks from the historical transportation records, and calculate the average value of these times; this average value can reflect the typical time required to complete a transportation task under normal working conditions; use the calculated average consumption time as the time interval threshold for dividing the transportation cycle; this means that a new transportation cycle will start every this average time; each adjacent two nodes constitute a transportation cycle; the entire working time is divided into multiple consecutive transportation cycles, and the length of each cycle is equal to the average consumption time; As a preferred embodiment of the present invention, the process of determining whether there is a common transport section between the optimal paths includes: Numbering all the transport sections in the warehouse, obtaining the numbers of the transport sections included in the optimal path, and obtaining the numbering sequence of the optimal path; if there are two optimal paths, obtaining the numbering sequences of the two optimal paths, and determining whether the two numbering sequences have an intersection, if there is an intersection, the two optimal paths have the same transport section; if there is no intersection, the two optimal paths do not have the same transport section; It can be understood that if there are two or more optimal paths, the numbering sequences of these paths are obtained and checked whether there is an intersection between them; if the two numbering sequences have common elements, it means that the two optimal paths overlap in some sections; according to the intersection of the numbering sequences, it can be determined which optimal paths have the same transport section; if there is an intersection, it means that these paths share at least one section of the same route; if there is no intersection, it means that these paths do not overlap at all in space; As a preferred embodiment of the present invention, the process of determining whether the estimated arrival times of the same transport sections between the intersecting paths are close includes: If there are two intersecting paths, for any common transport section between the two intersecting paths, obtain the estimated arrival time of the same transport section and record them as t1 and t2 respectively; set the difference threshold Ct, if |t1-t2|∈Ct, there is a common transport section with a similar estimated arrival time between the two intersecting paths; otherwise, there is no common transport section with a similar estimated arrival time between the two intersecting paths; It can be understood that in order to determine whether two times are close, a difference threshold Ct needs to be set; this threshold can be set according to actual needs and experience, and it represents the maximum allowable difference between two time points; the estimated arrival times of two intersecting paths on the same transport section are compared; if the absolute value of the difference between the two times is less than or equal to the set difference threshold Ct, the two times are considered to be close; otherwise, they are not close; Step S4: Obtain the total number m of the collision paths in the transport cycle, select m-1 collision paths as transfer paths, and replace the transport tasks corresponding to the transfer paths to the next transport cycle for allocation; and re-obtain m-1 transport tasks to the current transport cycle, and re-determine whether there is a collision path in the current transport cycle; and so on, until there is no collision path in the transport cycle; It is understandable that the transport tasks corresponding to the selected transfer path are postponed to the next transport cycle for allocation; this means that these tasks will not be executed immediately, but will wait for the next cycle to be processed; after removing the tasks corresponding to the transfer path, recalculate the number of transport tasks in the current transport cycle and ensure that it matches the number of AGVs; after updating the tasks of the current cycle, check again whether there are still collision paths; if there are still, repeat the above steps until there are no more collision paths in the current transport cycle; As a preferred embodiment of the present invention, the process of selecting the transfer path includes: Obtain the generation time of the transport task corresponding to each collision path, where the generation time is the moment when the transport task is generated; sort all the generation times according to the order of precedence, and select the collision paths corresponding to the last m-1 generation times as the transfer paths; It is understandable that all collected generation times are sorted in order of chronological order; this helps to determine which tasks are created earlier, so that the transfer of the tasks created earlier can be given priority.

[0019] An AGV route optimization system based on big data, comprising: Energy consumption collection module: obtain all driving routes of the automatic guided vehicle in the warehouse, divide all driving routes into several conveying sections; set the driving speed and driving direction, obtain the energy consumed by the automatic guided vehicle when it completes the conveying section at the driving speed and driving direction, and record it as the energy consumption of the conveying section; Path determination module: obtain the transport task, and obtain the transport destination according to the transport task; obtain the departure point of the automatic guided vehicle, and obtain the entire transport path of the transport task according to the departure point and the destination; obtain all the transport sections included in the transport path and the driving direction of each transport section, obtain the energy consumption of each transport section, and obtain the total energy consumption of the transport path; select the transport path with the minimum total energy consumption as the optimal path for the transport task; Collision judgment module: obtain the working time of the automatic guided vehicle, divide the working time into several transport cycles, obtain the starting time of the transport cycle, and record it as the departure time of the transport cycle; obtain the maximum number n of departures in the transport cycle, and assign n transport tasks to all automatic guided vehicles in the transport cycle, with each automatic guided vehicle corresponding to one transport task; Obtain the best path for each transport task within the transport cycle, determine whether there is a common transport section between the best paths, and record several best paths with the same transport section as intersecting paths, and record the same transport section between the intersecting paths as the same transport section; Obtain the section length of each transport section, and obtain the estimated arrival time of each transport section in the intersecting path according to the departure time, driving speed and section length; determine whether the estimated arrival times of the same transport sections between the intersecting paths are close, and if so, record the intersecting paths with the same transport section having close estimated arrival times as collision paths; Delivery time adjustment module: obtain the total number m of collision paths within the transportation cycle, select m-1 collision paths as transfer paths, and replace the transportation tasks corresponding to the transfer paths to the next transportation cycle for allocation; and re-acquire m-1 transportation tasks to the current transportation cycle, and re-determine whether there is a collision path within the current transportation cycle; and so on, until there is no collision path within the transportation cycle.

[0020] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An AGV route optimization method based on big data, characterized in that: The following steps are involved: Step S1: Obtain all driving routes of the automatic guided vehicle in the warehouse, and divide all driving routes into a number of conveying sections; set the driving speed and driving direction, and obtain the energy consumed by the automatic guided vehicle when it completes the conveying section at the driving speed and driving direction, which is recorded as the energy consumption of the conveying section; Step S2: Obtain a transport task, and obtain a transport destination according to the transport task; obtain a departure point of an automatic guided vehicle, and obtain a complete transport path of the transport task according to the departure point and the destination; obtain all transport sections included in the transport path and the driving direction of each transport section, obtain the energy consumption of each transport section, and obtain the total energy consumption of the transport path; select the transport path with the minimum total energy consumption as the optimal path for the transport task; Step S3: obtaining the working time of the automated guided vehicle, dividing the working time into a number of transport cycles, obtaining the starting time of the transport cycle, and recording it as the departure time of the transport cycle; obtaining the maximum number n of departures in the transport cycle, and assigning n transport tasks to all automated guided vehicles in the transport cycle, with each automated guided vehicle corresponding to one transport task; Obtain the best path for each transport task within the transport cycle, determine whether there is a common transport section between the best paths, and record several best paths with the same transport section as intersecting paths, and record the same transport section between the intersecting paths as the same transport section; Obtaining the section length of each transport section, and obtaining the estimated arrival time of each transport section in the intersecting path according to the departure time, driving speed and section length; Determine whether the estimated arrival times of the same transport sections between the intersecting paths are close, and if so, record the intersecting paths with the same transport section having the same estimated arrival times as collision paths; Step S4: Obtain the total number m of the collision paths in the transport cycle, select m-1 collision paths as transfer paths, and replace the transport tasks corresponding to the transfer paths to the next transport cycle for allocation; and re-obtain m-1 transport tasks to the current transport cycle, and re-determine whether there is a collision path in the current transport cycle; And so on, until there is no collision path in the transportation cycle.

2. The AGV route optimization method based on big data according to claim 1, characterized in that: In step S1, the process of dividing the transport section includes: The intersection points in all driving routes are obtained, wherein the intersection points include a departure point and an end point; a transport section is obtained from every two adjacent intersection points, and finally a plurality of transport sections are obtained.

3. The AGV route optimization method based on big data according to claim 2 is characterized in that: In step S1, the process of setting the driving direction includes: Two intersection points at both ends of the transport section are obtained and marked as P1 and P2 respectively; then two driving directions of the transport section are obtained, namely, P1 points to P2 and P2 points to P1.

4. The AGV route optimization method based on big data according to claim 1, characterized in that: In step S2, the total energy consumption of the transport path is obtained as follows: Obtain the energy consumption of each transport section {W1, W2, ..., W k }, where W1 represents the energy consumption of the first transport section, k is the total number of transport sections included in the transport path, and the total energy consumption is , where i∈[1,k], W i Represents the energy consumption of the i-th transmission section.

5. The AGV route optimization method based on big data according to claim 1, characterized in that: In step S3, the process of dividing the transport cycle includes: Obtain historical transportation records, wherein the historical transportation records include the consumption time of each transportation task, and the consumption time is the time consumed to complete the transportation task; obtain the average value of all consumption times in the historical transportation records, recorded as the consumption time average; use the consumption time average as the time interval threshold, and within the working time, select a node every time interval threshold, and each two adjacent nodes constitute a transportation cycle; the node includes the starting time and the ending time of the working time.

6. The AGV route optimization method based on big data according to claim 1, characterized in that: In step S3, the process of determining whether there is a common transport section between the optimal paths includes: All the transport sections in the warehouse are numbered, the numbers of the transport sections included in the optimal path are obtained, and the numbering sequence of the optimal path is obtained; if there are two optimal paths, the numbering sequences of the two optimal paths are obtained, and it is determined whether the two numbering sequences have an intersection. If there is an intersection, the two optimal paths have the same transport section; if there is no intersection, the two optimal paths do not have the same transport section.

7. The AGV route optimization method based on big data according to claim 1, characterized in that: In step S3, the process of determining whether the estimated arrival times of the same transport sections between the intersecting paths are close includes: If there are two intersecting paths, for any identical transport section between the two intersecting paths, obtain the estimated arrival time of the identical transport section and record them as t1 and t2 respectively; set the difference threshold Ct, if |t1-t2|∈Ct, then there is an identical transport section with a similar estimated arrival time between the two intersecting paths; otherwise, there is no identical transport section with a similar estimated arrival time between the two intersecting paths.

8. The AGV route optimization method based on big data according to claim 1, characterized in that: In step S4, the process of selecting the transfer path includes: The generation time of the transport task corresponding to each collision path is obtained, where the generation time is the moment when the transport task is generated; all generation times are sorted in order of precedence, and the collision paths corresponding to the last m-1 generation times are selected as the transfer paths.

9. An AGV route optimization system based on big data, characterized in that: include: Energy consumption collection module: obtains all driving routes of the automatic guided vehicles in the warehouse and divides all driving routes into several transportation sections; Setting a travel speed and a travel direction, obtaining the energy consumed by the automatic guided vehicle when it travels the transport section at the travel speed and the travel direction, and recording it as the energy consumption of the transport section; Path determination module: obtain the transport task, and obtain the transport destination according to the transport task; obtain the departure point of the automatic guided vehicle, and obtain the entire transport path of the transport task according to the departure point and the destination; obtain all the transport sections included in the transport path and the driving direction of each transport section, obtain the energy consumption of each transport section, and obtain the total energy consumption of the transport path; select the transport path with the minimum total energy consumption as the optimal path for the transport task; Collision judgment module: obtain the working time of the automatic guided vehicle, divide the working time into several transport cycles, obtain the starting time of the transport cycle, and record it as the departure time of the transport cycle; obtain the maximum number n of departures in the transport cycle, and assign n transport tasks to all automatic guided vehicles in the transport cycle, with each automatic guided vehicle corresponding to one transport task; Obtain the best path for each transport task within the transport cycle, determine whether there is a common transport section between the best paths, and record several best paths with the same transport section as intersecting paths, and record the same transport section between the intersecting paths as the same transport section; Obtaining the section length of each transport section, and obtaining the estimated arrival time of each transport section in the intersecting path according to the departure time, driving speed and section length; Determine whether the estimated arrival times of the same transport sections between the intersecting paths are close, and if so, record the intersecting paths with the same transport section having the same estimated arrival times as collision paths; Delivery time adjustment module: obtain the total number m of collision paths in the transportation cycle, select m-1 collision paths as transfer paths, and replace the transportation tasks corresponding to the transfer paths to the next transportation cycle for allocation; and re-acquire m-1 transportation tasks to the current transportation cycle, and re-determine whether there is a collision path in the current transportation cycle; And so on, until there is no collision path in the transportation cycle.

Images