Production and transportation system based on intelligent AGV

Abstract

The invention belongs to the field of production and transportation, and discloses a production and transportation system based on an intelligent AGV, and the system comprises a statistical module, a map generation module, a path planning module, and an AGV transport vehicle. The statistics module is used for acquiring transportation time periods and predicting the number of transportation tasks in each transportation time period, and the transportation tasks comprise a starting point, an ending point, starting time, estimated ending time and transportation articles; the map generation module is used for calculating the side length of a square grid of a grid map based on the transportation time period and the predicted number of transportation tasks in the transportation time period, and determining the grid map for path planning in each transportation time period based on the side length; the path planning module is used for generating a transportation path of the AGV for executing the transportation task according to the transportation task; and the AGV transport vehicle is used for transporting the transport articles contained in the transport task based on the transport path. According to the invention, the transportation efficiency is ensured.

Description

Technical Field

[0001] This invention relates to the field of production transportation, and more particularly to a production transportation system based on intelligent AGVs. Background Art

[0002] The intelligent AGV-based production and transportation system is an intelligent production material solution that uses Automated Guided Vehicles (AGVs) as its core and combines artificial intelligence, navigation technology, and the Internet of Things. Through autonomous navigation, dynamic scheduling, and collaborative operations, it achieves precise handling and optimized transportation of materials in the production process.

[0003] AGV (Automated Guided Vehicle) transportation path planning is typically based on a grid map. The AGV's workspace is first divided into multiple uniformly sized grids. Once the AGV's start and end points on the grid map are determined, these are input into a path planning algorithm (such as the A* algorithm) to obtain the transportation path. In existing technologies, the grid cells are usually squares, with the side length of the square set to a fixed value greater than the AGV's body length. Fixed-size grids have the following drawbacks: when a large number of AGVs are operating simultaneously, it cannot provide a more refined path to allow more AGVs to pass through the same area, affecting transportation efficiency; conversely, when a small number of AGVs are operating simultaneously, it cannot effectively increase the AGV's operating speed to further improve transportation efficiency, because the grid side length limits the upper limit of the AGV's turning speed. The smaller the grid side length, the smaller the turning speed. If the speed is too high, the current AGV is likely to exceed the boundary of the transportation path, encroaching on the boundary of other AGVs' transportation paths, leading to an increased probability of collision. Summary of the Invention

[0004] The purpose of this invention is to disclose a production and transportation system based on intelligent AGVs, and to solve the technical problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] This invention provides a production and transportation system based on intelligent AGVs, including a statistics module, a map generation module, a path planning module, and an AGV transport vehicle;

[0007] The statistics module is used to obtain transportation time periods and predict the number of transportation tasks within each transportation time period. The transportation task includes the origin, destination, start time, estimated end time and transported goods.

[0008] The map generation module is used to calculate the side length of the square grid of the raster map based on the transportation time period and the number of expected transportation tasks within the transportation time period, and to determine the raster map used for route planning within each transportation time period based on the side length.

[0009] The route planning module is used to generate transportation routes for AGV transport vehicles to perform transportation tasks based on the transportation tasks.

[0010] AGV transport vehicles are used to transport items included in a transport task based on a transport route.

[0011] Furthermore, obtain the transportation time period, including:

[0012] Get the set K of historical transportation tasks whose start time falls within the set time interval;

[0013] Obtain the actual end time of each historical transportation task in set K;

[0014] Calculate the transportation time for each historical transportation task in set K;

[0015] The duration of the transportation period is calculated based on the transportation time.

[0016] Clustering the start times of historical transportation tasks yields multiple cluster centers;

[0017] The transportation time period is determined based on the duration of the transportation time period and the cluster center.

[0018] Furthermore, the transportation time for each historical transportation task in set K is calculated, including:

[0019] use This represents the k-th historical transportation task in set K. The start time and actual end time are respectively expressed as: and ;

[0020] Transportation time The calculation formula is:

[0021] - .

[0022] Furthermore, the duration of the transportation period is calculated based on the transportation time, including:

[0023] Calculate the duration of the transportation period using the following formula. :

[0024]

[0025] NK represents the number of historical transport tasks in set K. Let be the transportation duration of the i-th historical transportation task.

[0026] Furthermore, clustering was performed on the start times of historical transportation tasks, resulting in multiple cluster centers, including:

[0027] The elbow rule is used to calculate the number of cluster centers for historical transportation tasks.

[0028] Clustering is performed based on the number of cluster centers to determine the start time of historical transportation tasks, resulting in multiple cluster centers.

[0029] Furthermore, the transportation time period is determined based on the duration of the transportation time period and the cluster center, including:

[0030] The first step is to sort the cluster centers in order from earliest to latest to obtain sequence Q1;

[0031] The second step involves the first and second cluster centers in sequence Q1. and ,like The value is less than the duration of the transportation period. Then proceed to the third step; if The value is greater than or equal to the duration of the transportation period. Then proceed to step four;

[0032] The third step is to Delete from sequence Q1, determine whether sequence Q1 contains only one cluster center. If so, store the cluster center in Q into sequence Q2 and proceed to step 5; otherwise, proceed to step 2.

[0033] Step 4; Store sequence Q2, Remove from sequence Q1 and proceed to step two;

[0034] Fifth, sort the cluster centers in sequence Q2 in ascending order to obtain sequence Q3;

[0035] Step 6: Obtain the transportation time period based on sequence Q3:

[0036] The first transportation time slot starts at 0:00:00 and ends at [time missing]. The second before, It is the first cluster center in Q3;

[0037] The z-th transportation time period is z∈[2,NQ3], where NQ3 represents the number of cluster centers in Q3;

[0038] The start time of the NQ3+1th transportation period is , It is the last cluster center in Q3, and the end time is 23:59:59.

[0039] Furthermore, the estimated number of transport tasks within each transport period includes:

[0040] Obtain time-series data on the number of historical transportation tasks within each transportation time period;

[0041] The time series data corresponding to each transportation period is input into a pre-trained prediction model for calculation to obtain the expected number of transportation tasks in each transportation period.

[0042] Furthermore, the side length of the square grid cells in the raster map is calculated based on the transportation time period and the expected number of transportation tasks within that time period, including:

[0043] For the v-th transportation time period, use This represents the number of transport tasks expected within the v-th transport time period;

[0044] use This represents the actual number of transport tasks within the (v-1)th transport time period;

[0045] Then the side length of the square cell in the raster map for the v-th transportation time period. The calculation formula is:

[0046]

[0047] This indicates the maximum preset side length. This represents the upper limit of the expected number of AGV transport vehicles operating simultaneously; NML represents normalization. This represents the average speed of the AGV transport vehicle performing the transport task during the (v-1)th transport time period. This indicates the maximum design speed of the AGV transport vehicle; , and These are the first, second, and third impact values, respectively. For trend values, if If greater than 0, then The value is 0.5, otherwise The value is 1.

[0048] Furthermore, based on the side lengths, the raster map used for route planning within each transportation time period is determined, including:

[0049] Obtain a floor plan of the AGV transport vehicle's workspace;

[0050] The planar graph is divided into multiple grids based on the side lengths;

[0051] If there is an obstacle in a grid cell, the area containing that grid cell is marked as an impassable area, and grid cells without obstacles are marked as passable areas, thus obtaining a grid map.

[0052] Furthermore, based on the transportation task, a transportation route is generated for the AGV transport vehicle used to perform the transportation task, including:

[0053] The starting point and ending point of the transportation task are input into the path planning algorithm to obtain the transportation path of the AGV transport vehicle used to perform the transportation task.

[0054] Beneficial effects:

[0055] In generating transportation routes using a grid map, this invention does not use fixed values ​​for the side length of square grids. Instead, it divides the day into multiple transportation time periods and then determines the side length of the grid within each time period based on the expected number of transportation tasks and the transportation time period. This allows the grid side length to adaptively change based on the expected value and the time period. When there are more estimated transportation tasks, i.e., more AGVs operating in the same time period, this invention can provide smaller grids for transportation route planning, thereby ensuring transportation efficiency. When there are fewer AGVs, the grid size is increased to allow AGVs to transport goods at a higher average speed while reducing the probability of encroaching on other transportation routes. Attached Figure Description

[0056] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a schematic diagram of a production and transportation system based on intelligent AGV according to the present invention. Detailed Implementation

[0058] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] This invention provides a production and transportation system based on intelligent AGVs, including a statistics module, a map generation module, a path planning module, and an AGV transport vehicle;

[0060] The statistics module is used to obtain transportation time periods and predict the number of transportation tasks within each transportation time period. The transportation task includes the origin, destination, start time, estimated end time and transported goods.

[0061] The map generation module is used to calculate the side length of the square grid of the raster map based on the transportation time period and the number of expected transportation tasks within the transportation time period, and to determine the raster map used for route planning within each transportation time period based on the side length.

[0062] The route planning module is used to generate transportation routes for AGV transport vehicles to perform transportation tasks based on the transportation tasks.

[0063] AGV transport vehicles are used to transport items included in a transport task based on a transport route.

[0064] This invention, when generating transportation routes using a grid map, abandons fixed-side-length square grids and instead dynamically adjusts the grid size based on the estimated number of transportation tasks and the time period. Specifically, a day is first divided into multiple transportation time periods, and then the corresponding grid side length is determined based on the estimated number of transportation tasks in each time period. When there are many estimated transportation tasks, the number of AGVs operating in the same time period is also large. In this case, smaller grids are generated for planning transportation routes to improve transportation efficiency. Conversely, when there are few estimated transportation tasks and few AGVs, the grid size is increased, allowing AGVs to increase their average speed while reducing the probability of encroaching on other transportation routes.

[0065] Furthermore, the estimated end time equals the start time plus the average of the actual transport times of historical transport tasks from the previous day.

[0066] Furthermore, the transport completion time can be estimated based on the quantity of goods being transported and the distance between the origin and destination:

[0067] First, train an end time estimation model. After obtaining a transportation task, input the start time, end time, and characteristics of the transported goods into the end time estimation model to obtain the estimated transportation duration. Add the start time to the estimated transportation duration to get the estimated end time.

[0068] Multi-view graph neural network models or decision tree models can be used as end-time estimation models.

[0069] Furthermore, obtain the transportation time period, including:

[0070] Get the set K of historical transportation tasks whose start time falls within the set time interval;

[0071] Obtain the actual end time of each historical transportation task in set K;

[0072] Calculate the transportation time for each historical transportation task in set K;

[0073] The duration of the transportation period is calculated based on the transportation time.

[0074] Clustering the start times of historical transportation tasks yields multiple cluster centers;

[0075] The transportation time period is determined based on the duration of the transportation time period and the cluster center.

[0076] The time interval set in this invention can be the month preceding the current time. For example, if the current time is April 1, then the time interval set is from March 1 to March 31.

[0077] The actual end time refers to the length of time recorded by the AGV transport vehicle from the starting point to the end point.

[0078] Furthermore, the transportation time for each historical transportation task in set K is calculated, including:

[0079] use This represents the k-th historical transportation task in set K. The start time and actual end time are respectively expressed as: and ;

[0080] Transportation time The calculation formula is:

[0081] - .

[0082] Furthermore, the duration of the transportation period is calculated based on the transportation time, including:

[0083] Calculate the duration of the transportation period using the following formula. :

[0084]

[0085] NK represents the number of historical transport tasks in set K. Let be the transportation duration of the i-th historical transportation task.

[0086] This invention uses the average transportation time of historical transportation tasks within a set time interval as the length of the transportation time period, thereby avoiding the transportation time period being too long or too short. This allows the transportation time period to change with the actual transportation time, thus further ensuring the implementation effect of this invention.

[0087] Furthermore, clustering was performed on the start times of historical transportation tasks, resulting in multiple cluster centers, including:

[0088] The elbow rule is used to calculate the number of cluster centers for historical transportation tasks.

[0089] Clustering is performed based on the number of cluster centers to determine the start time of historical transportation tasks, resulting in multiple cluster centers.

[0090] In this invention, the process of using the elbow rule to calculate the number of cluster centers for historical transportation tasks is roughly as follows:

[0091] Standardize the start time to eliminate the impact of dimensional differences on distance calculation;

[0092] Traverse different ranges of cluster center counts (typically from 1 to 10), fit the data using the K-Means algorithm, and record the WCSS;

[0093] Draw a line graph showing how WCSS changes with the number of cluster centers, with the number of cluster centers on the X-axis and WCSS on the Y-axis.

[0094] In the line graph, calculate the rate of change of values ​​between two adjacent WCSS values:

[0095]

[0096] The rate of change of the numerical values ​​between the (u-1)th and uth adjacent WCSSs; u is greater than or equal to 1 and less than the maximum value of the cluster centers traversed;

[0097] The maximum number of cluster centers when the rate of change of the numerical value is less than a set rate threshold is taken as the final number of cluster centers.

[0098] The rate threshold set in this invention can be 0.2.

[0099] WCSS is the sum of squares within a cluster.

[0100] Furthermore, the transportation time period is determined based on the duration of the transportation time period and the cluster center, including:

[0101] The first step is to sort the cluster centers in order from earliest to latest to obtain sequence Q1;

[0102] The second step involves the first and second cluster centers in sequence Q1. and ,like The value is less than the duration of the transportation period. Then proceed to the third step; if The value is greater than or equal to the duration of the transportation period. Then proceed to step four;

[0103] The third step is to Delete from sequence Q1, determine whether sequence Q1 contains only one cluster center. If so, store the cluster center in Q into sequence Q2 and proceed to step 5; otherwise, proceed to step 2.

[0104] Step 4; Store sequence Q2, Remove from sequence Q1 and proceed to step two;

[0105] Fifth, sort the cluster centers in sequence Q2 in ascending order to obtain sequence Q3;

[0106] Step 6: Obtain the transportation time period based on sequence Q3:

[0107] The first transportation time slot starts at 0:00:00 and ends at [time missing]. The second before, It is the first cluster center in Q3;

[0108] The z-th transportation time period is z∈[2,NQ3], where NQ3 represents the number of cluster centers in Q3;

[0109] The start time of the NQ3+1th transportation period is , It is the last cluster center in Q3, and the end time is 23:59:59.

[0110] The above process makes the transportation time no longer a fixed value, and can minimize the possibility of the transportation time being less than a certain value. This increases the probability that transportation tasks can be completed within the same transportation time period. In this way, the impact of unfinished transportation tasks in the previous transportation time period on the transportation route planning process in the next transportation time period can be reduced, and the length of the transportation route planned in the next transportation time period can be effectively reduced.

[0111] In this invention, since the cluster center is time, the cluster centers can be sorted according to the order of time from early to late.

[0112] Furthermore, the estimated number of transport tasks within each transport period includes:

[0113] Obtain time-series data on the number of historical transportation tasks within each transportation time period;

[0114] The time series data corresponding to each transportation period is input into a pre-trained prediction model for calculation to obtain the expected number of transportation tasks in each transportation period.

[0115] Furthermore, time-series data on the number of historical transportation tasks within each transportation time period are obtained, including:

[0116] For transportation time period b, within the set time interval, the number of historical transportation tasks whose start time and actual end time fall within the range of transportation time period b is obtained, thus producing time series data. .

[0117] For example, if the set time interval has a total of 5 days, then the time series data will be... , arrive This indicates the number of historical transportation tasks whose start time and actual end time fall within the range of transportation time period b, from the first to the fifth day of the set time interval.

[0118] Furthermore, the pre-trained prediction model can be LSTM, SVM, etc.

[0119] Furthermore, the side length of the square grid cells in the raster map is calculated based on the transportation time period and the expected number of transportation tasks within that time period, including:

[0120] For the v-th transportation time period, use This represents the number of transport tasks expected within the v-th transport time period;

[0121] use This represents the actual number of transport tasks within the (v-1)th transport time period;

[0122] Then the side length of the square cell in the raster map for the v-th transportation time period. The calculation formula is:

[0123]

[0124] This indicates the maximum preset side length. This represents the upper limit of the expected number of AGV transport vehicles operating simultaneously; NML represents normalization. This represents the average speed of the AGV transport vehicle performing the transport task during the (v-1)th transport time period. This indicates the maximum design speed of the AGV transport vehicle (e.g., 2 meters per second). , and These are the first, second, and third impact values, respectively. For trend values, if If greater than 0, then The value is 0.5, otherwise The value is 1.

[0125] The side length of the grid in this invention can vary with the expected number of transport tasks, the average speed of the AGV transport vehicles performing transport tasks in the previous transport period, and the changing trend of the actual number of transport tasks. Therefore, when The larger the value, The larger the value and the more the actual number of transportation tasks increases, the smaller the side length of the square grid becomes. This means that the grid of the grid map in this invention not only changes based on the predicted number of transportation tasks, but also incorporates vehicle speed data and transportation task data from the two most recent transportation time periods for auxiliary calculation, which allows for more accurate grid side lengths and can effectively improve transportation efficiency.

[0126] Normalization can be achieved by using maximum value normalization.

[0127] Furthermore, the calculation process for the upper limit of the expected number of AGV transport vehicles operating simultaneously includes:

[0128] Let D1 and D2 represent the length and width of the AGV transport vehicle, respectively; let S represent the shortest braking distance of the AGV transport vehicle; and let NC represent the total number of cells marked as passable areas in the grid map. Then:

[0129]

[0130] sc represents the area of ​​a single cell in a raster map; This represents the control factor (e.g., 5).

[0131] In this invention, when calculating NRp, the area of ​​a single cell can be equal to the square of the length of the AGV transport vehicle. This invention calculates NRp using braking distance and control coefficients, enabling the estimation of the maximum value of the AGV transport vehicle under ideal conditions (where all vehicles travel at the same speed).

[0132] Furthermore, v∈[3,NV], where NV represents the total number of transport time periods. Therefore, the size of the grid cells in the raster map for the first and second time periods is a preset length, such as twice the length of the AGV transport vehicle.

[0133] Furthermore, the first, second, and third impact values ​​can be 0.5, 0.3, and 0.2, respectively.

[0134] Furthermore, the upper limit of the preset side length can be 10 times the length of the AGV transport vehicle.

[0135] Furthermore, based on the side lengths, the raster map used for route planning within each transportation time period is determined, including:

[0136] Obtain a floor plan of the AGV transport vehicle's workspace;

[0137] The planar graph is divided into multiple grids based on the side lengths;

[0138] If there is an obstacle in a grid cell, the area containing that grid cell is marked as an impassable area, and grid cells without obstacles are marked as passable areas, thus obtaining a grid map.

[0139] Furthermore, based on the transportation task, a transportation route is generated for the AGV transport vehicle used to perform the transportation task, including:

[0140] The starting point and ending point of the transportation task are input into a path planning algorithm (such as the A* algorithm) to obtain the transportation path of the AGV transport vehicle used to perform the transportation task.

[0141] The A* algorithm is used to calculate transport routes in a raster map. When calculating transport routes, it is necessary to avoid impassable areas.

[0142] Furthermore, transporting the goods included in the transportation task based on the transportation route includes:

[0143] The AGV transport vehicle travels from the parking point to the starting point of the transport task, loads the transported items, and then travels along the transport route to the destination of the transport task.

[0144] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A production and transportation system based on intelligent AGVs, characterized in that, It includes a statistics module, a map generation module, a path planning module, and an AGV transport vehicle; The statistics module is used to obtain transportation time periods and predict the number of transportation tasks within each transportation time period. The transportation task includes the origin, destination, start time, estimated end time and transported goods. The map generation module is used to calculate the side length of the square grid of the raster map based on the transportation time period and the number of expected transportation tasks within the transportation time period, and to determine the raster map used for route planning within each transportation time period based on the side length. The route planning module is used to generate transportation routes for AGV transport vehicles to perform transportation tasks based on the transportation tasks. AGV transport vehicles are used to transport items included in a transport task based on a transport route.

2. The production and transportation system based on intelligent AGV according to claim 1, characterized in that, Obtain the transportation time period, including: Get the set K of historical transportation tasks whose start time falls within the set time interval; Obtain the actual end time of each historical transportation task in set K; Calculate the transportation time for each historical transportation task in set K; The duration of the transportation period is calculated based on the transportation time. Clustering the start times of historical transportation tasks yields multiple cluster centers; The transportation time period is determined based on the duration of the transportation time period and the cluster center.

3. A production and transportation system based on intelligent AGV according to claim 2, characterized in that, Calculate the transportation time for each historical transportation task in set K, including: use This represents the k-th historical transportation task in set K. The start time and actual end time are respectively expressed as: and ; Transportation time The calculation formula is: - 。 4. A production and transportation system based on intelligent AGV according to claim 3, characterized in that, The duration of the transportation period is calculated based on the transportation time, including: Calculate the duration of the transportation period using the following formula. : NK represents the number of historical transportation tasks in set K. Let be the transportation duration of the i-th historical transportation task.

5. A production and transportation system based on intelligent AGV according to claim 4, characterized in that, Clustering the start times of historical transportation tasks yields multiple cluster centers, including: The elbow rule is used to calculate the number of cluster centers for historical transportation tasks. Clustering is performed based on the number of cluster centers to determine the start time of historical transportation tasks, resulting in multiple cluster centers.

6. A production and transportation system based on intelligent AGV according to claim 5, characterized in that, The transportation time period is determined based on the duration of the transportation time period and the cluster center, including: The first step is to sort the cluster centers in order from earliest to latest to obtain sequence Q1; The second step involves the first and second cluster centers in sequence Q1. and ,like The value is less than the duration of the transportation period. Then proceed to the third step; if The value is greater than or equal to the duration of the transportation period. Then proceed to step four; The third step is to Delete from sequence Q1, determine whether sequence Q1 contains only one cluster center. If so, store the cluster center in Q into sequence Q2 and proceed to step 5; otherwise, proceed to step 2. Step 4; Store sequence Q2, Remove from sequence Q1 and proceed to step two; Fifth, sort the cluster centers in sequence Q2 in ascending order to obtain sequence Q3; Step 6: Obtain the transportation time period based on sequence Q3: The first transportation time slot starts at 0:00:00 and ends at [time missing]. The second before, It is the first cluster center in Q3; The z-th transportation time period is z∈[2,NQ3], where NQ3 represents the number of cluster centers in Q3; The start time of the NQ3+1th transportation period is , It is the last cluster center in Q3, and the end time is 23:59:

59.

7. A production and transportation system based on intelligent AGV according to claim 1, characterized in that, The estimated number of transport tasks in each transport period includes: Obtain time-series data on the number of historical transportation tasks within each transportation time period; The time series data corresponding to each transportation period is input into a pre-trained prediction model for calculation to obtain the expected number of transportation tasks in each transportation period.

8. A production and transportation system based on intelligent AGV according to claim 1, characterized in that, The side length of the square grid cells in the raster map is calculated based on the transportation time period and the expected number of transportation tasks within that time period, including: For the v-th transportation time period, use This represents the number of transport tasks expected within the v-th transport time period; use This represents the actual number of transport tasks within the (v-1)th transport time period; Then the side length of the square cell in the raster map for the v-th transportation time period. The calculation formula is: ; This indicates the maximum preset side length. This represents the upper limit of the expected number of AGV transport vehicles operating simultaneously; NML represents normalization. This represents the average speed of the AGV transport vehicle performing the transport task during the (v-1)th transport time period. This indicates the maximum design speed of the AGV transport vehicle; , and These are the first, second, and third impact values, respectively. For trend values, if If greater than 0, then The value is 0.5, otherwise The value is 1.

9. A production and transportation system based on intelligent AGV according to claim 1, characterized in that, Based on the side length, a raster map is determined for route planning within each transportation time period, including: Obtain a floor plan of the AGV transport vehicle's workspace; The planar graph is divided into multiple grids based on the side lengths; If there is an obstacle in a grid cell, the area containing that grid cell is marked as an impassable area, and grid cells without obstacles are marked as passable areas, thus obtaining a grid map.

10. A production and transportation system based on intelligent AGV according to claim 1, characterized in that, Based on the transportation task, a transportation route is generated for the AGV transport vehicle to perform the transportation task, including: The starting point and ending point of the transportation task are input into the path planning algorithm to obtain the transportation path of the AGV transport vehicle used to perform the transportation task.

Images