A method and system based on intelligent assisted transportation control

Abstract

The present invention discloses a method and system based on intelligent auxiliary transportation control, wherein the method includes: obtaining work task information based on a cloud platform, and establishing a global map based on the work task information; generating a work task allocation plan based on the work task information using a particle swarm algorithm; planning and optimizing a transportation path based on the work task information and the global map using a fuzzy logic algorithm; allocating a corresponding auxiliary transport vehicle based on the work task allocation plan and the optimized transportation path, and selecting a working mode for the auxiliary transport vehicle; transporting using an early warning device built into the auxiliary transport vehicle based on the working mode, the early warning device being used to collect real-time images of the transportation process, analyzing the real-time images based on the cloud platform, and adjusting the transportation route based on the analysis results. The present invention can not only effectively improve the management and control efficiency of transportation, greatly reduce the investment in labor costs, and improve the reliability of the transportation process, meeting the high requirements of users for the transportation process.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a method and system based on intelligent assisted transportation control. Background Art

[0002] Nowadays, in order to meet people's travel needs, various rail transit modes have also become popular rapidly. However, for some people with limited mobility and people carrying a large number of large luggage packages, there are still travel transportation problems. In rail transit stations, for the travel transportation of people with limited mobility and people carrying a large number of large luggage packages, some people use manual assistance methods, but manual assistance methods are not only inefficient, but also have too high manpower costs; some people use auxiliary transportation equipment instead of manual assistance methods to provide travel transportation assistance. Although this method improves transportation efficiency to a certain extent, due to the lack of reasonable management and control of auxiliary transportation equipment, there may be problems of management and control chaos, which leads to the inability to effectively improve work efficiency. Summary of the Invention

[0003] The purpose of the present invention is to overcome the shortcomings of the existing technology. The present invention provides a method and system based on intelligent assisted transportation control, which can not only effectively improve the management and control efficiency of transportation, greatly reduce the investment in manpower costs, but also improve the reliability of the transportation process and meet the high requirements of users for the transportation process.

[0004] In order to solve the above technical problems, the present invention provides a method based on intelligent assisted transportation control, the method comprising:

[0005] Acquire work task information based on the cloud platform, and establish a global map based on the work task information;

[0006] Based on the work task information, a particle swarm algorithm is used to allocate work tasks to obtain a work task allocation plan;

[0007] Based on the work task information and the global map, a fuzzy logic algorithm is used to perform path planning to obtain an optimized transportation path;

[0008] Allocate corresponding auxiliary transport vehicles based on the work task allocation plan and the optimized transport route, and select a working mode for the corresponding auxiliary transport vehicles;

[0009] Based on the working mode, transportation is carried out using the built-in early warning equipment of the auxiliary transport vehicle. The early warning equipment is used to collect real-time images of the transportation process. The real-time images transmitted by the early warning equipment are analyzed based on the cloud platform, and the transportation route is adjusted based on the analysis results.

[0010] Optionally, obtaining work task information based on a cloud platform and establishing a global map based on the work task information includes:

[0011] Acquiring work task information based on the cloud platform, wherein the work task information includes: the working status of the auxiliary transport vehicle, the corresponding supporting facility information, and the positioning information of the auxiliary transport vehicle in the working state;

[0012] A global map is established based on the working status of the auxiliary transport vehicle, the corresponding supporting facility information and the positioning information of the auxiliary transport vehicle in the working state.

[0013] Optionally, the using a particle swarm algorithm to allocate work tasks based on the work task information to obtain a work task allocation plan includes:

[0014] Generate an initial particle population using an encoding method based on the work task information, and calculate a first fitness value for each particle in the initial particle population and a first population extreme value of the initial particle population;

[0015] performing an optimization and updating process on the initial particle population to obtain an optimized particle population;

[0016] Calculating a second population extreme value of the optimized particle population and a second fitness value of each particle in the optimized particle population;

[0017] Comparing the second population extreme value of the optimized particle population with the first population extreme value of the initial particle population, wherein, if the second population extreme value of the optimized particle population is greater than the first population extreme value of the initial particle population, then using the optimized particle population as the new initial particle population to continue iterative optimization and update processing to a preset number of iterations to obtain a global optimized particle population;

[0018] If the second population extreme value of the optimized particle population is less than or equal to the first population extreme value of the initial particle population, the particles in the initial particle population are compared with the particles in the optimized particle population, and all particles in the optimized particle population whose second fitness value is greater than the first fitness value are replaced with the corresponding particles in the initial particle population to obtain a new initial particle population. The new initial particle population is further iterated and optimized and updated to a preset number of iterations to obtain a global optimized particle population, and the global optimized particle population is used as the initial work task deployment plan;

[0019] Based on the coordination strategy, it is determined whether the initial work task allocation plan needs to be adjusted, and the work task allocation plan is generated based on the determination result.

[0020] Optionally, judging whether the initial work task allocation plan needs to be adjusted based on the coordination strategy, and generating the work task allocation plan based on the judgment result, includes:

[0021] Determine whether the number of tasks assigned to the auxiliary transport vehicle in the initial work task allocation plan is greater than the task load upper limit of the auxiliary transport vehicle, wherein, if the number of tasks assigned to the auxiliary transport vehicle in the initial work task allocation plan is greater than the task load upper limit of the auxiliary transport vehicle, then calculate the number of tasks greater than the task load upper limit of the auxiliary transport vehicle, and readjust and allocate the tasks greater than the task load upper limit of the auxiliary transport vehicle to obtain a work task allocation plan; if the number of tasks assigned to the auxiliary transport vehicle in the initial work task allocation plan is less than or equal to the task load upper limit of the auxiliary transport vehicle, then the initial work task allocation plan does not need to be adjusted.

[0022] Optionally, performing path planning based on the work task information and the global map using a fuzzy logic algorithm to obtain an optimized transportation path includes:

[0023] Establishing a global coordinate system using the global map based on the work task information;

[0024] Set the starting point and end point of the transport path in the global coordinate system, and use the A-star algorithm to generate the initial transport path based on the starting point and end point of the transport path;

[0025] The initial transport path is subjected to fuzzy inference processing based on a preset fuzzy controller to obtain an optimized transport path.

[0026] Optionally, the generating of the initial transport path using an A-star algorithm based on the start point and the end point of the transport path includes:

[0027] Randomly generate several transport path points based on the starting and ending points of the transport path;

[0028] A heuristic function based on the A-star algorithm searches for several transport path points to obtain several optimized path points, and generates an initial transport path based on the several optimized path points, the start point and the end point of the transport path.

[0029] Optionally, allocating corresponding auxiliary transport vehicles based on the work task allocation plan and the optimized transport route, and selecting a working mode for the corresponding auxiliary transport vehicles, includes:

[0030] Marking the corresponding auxiliary transport vehicles based on the work task deployment plan and the optimized transport path, and deploying the marked auxiliary transport vehicles based on the cloud platform;

[0031] The type of transported item is obtained, and a working mode is selected for the corresponding auxiliary transport vehicle based on the type of transported item.

[0032] Optionally, the transport is performed using a built-in early warning device in the auxiliary transport vehicle based on the working mode, the early warning device is used to collect real-time images of the transport process, the real-time images transmitted by the early warning device are analyzed based on the cloud platform, and the transport route is adjusted based on the analysis results, including:

[0033] The auxiliary transport vehicle performs transportation based on the corresponding working mode, wherein, during the transportation process of the auxiliary transport vehicle, a built-in warning device of the auxiliary transport vehicle is used to obtain real-time images of the transportation process, and the real-time images are transmitted to the cloud platform;

[0034] The cloud platform analyzes the real-time image based on an image detection algorithm and adjusts the transportation route based on the analysis results.

[0035] Optionally, the cloud platform analyzes the real-time image based on an image detection algorithm, including:

[0036] Performing binarization processing on the real-time image to obtain a binarized real-time image;

[0037] Inputting the binarized real-time image into a preset target detection model to obtain the obstacle outline;

[0038] The obstacle outline is marked with an area based on a preset icon to obtain obstacle area marking information.

[0039] In addition, the present invention also provides a system based on intelligent assisted transportation control, the system comprising:

[0040] A task acquisition and global map module is used to acquire work task information based on the cloud platform and establish a global map based on the work task information;

[0041] A work task allocation module, configured to allocate work tasks using a particle swarm algorithm based on the work task information to obtain a work task allocation plan;

[0042] A path planning module, configured to perform path planning based on the work task information and a global map using a fuzzy logic algorithm to obtain an optimized transportation path;

[0043] A dispatching module, configured to dispatch corresponding auxiliary transport vehicles based on the work task dispatching plan and the optimized transport route, and select a working mode for the corresponding auxiliary transport vehicles;

[0044] The transportation and real-time analysis module is used to carry out transportation based on the working mode using the early warning equipment built into the auxiliary transport vehicle. The early warning equipment is used to collect real-time images of the transportation process, analyze the real-time images transmitted by the early warning equipment based on the cloud platform, and adjust the transportation route based on the analysis results.

[0045] In an embodiment of the present invention, work task information is obtained and a global map is established through a cloud platform, which can unify management tasks and better control auxiliary transport vehicles. Work task allocation is performed through a particle swarm algorithm, which can complete the allocation of work tasks in a faster time, and path planning is performed through a fuzzy logic algorithm, which can quickly and accurately plan the transportation route. According to the work task allocation plan and the optimized transportation route, the corresponding auxiliary transport vehicle is selected for the working mode to meet the transportation requirements of different scenarios and different types of transported items. During the transportation process of the auxiliary transport vehicle, images can be collected and analyzed in real time, and the transportation route can be adjusted according to the analysis results to effectively avoid obstacles and achieve better obstacle avoidance effects. The present invention can not only effectively improve the management and control efficiency of transportation, greatly reduce the investment in labor costs, and improve the reliability of the transportation process, meeting the high requirements of users for the transportation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 is a flow chart of a method based on intelligent assisted transportation control in an embodiment of the present invention;

[0048] Figure 2 Schematic diagram of the structure of a system based on intelligent assisted transportation control in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0050] Example 1

[0051] See also Figure 1 , Figure 1 It is a flowchart of a method based on intelligent assisted transportation control in an embodiment of the present invention.

[0052] like Figure 1 As shown, a method based on intelligent assisted transportation control, the method comprising:

[0053] S11: Acquire work task information based on the cloud platform, and establish a global map based on the work task information;

[0054] In the specific implementation process of the present invention, the work task information is obtained based on the cloud platform, and a global map is established based on the work task information, including: obtaining work task information based on the cloud platform, wherein the work task information includes: the working status of the auxiliary transport vehicle, the corresponding supporting facilities information and the positioning information of the auxiliary transport vehicle in the working state; establishing a global map based on the working status of the auxiliary transport vehicle, the corresponding supporting facilities information and the positioning information of the auxiliary transport vehicle in the working state.

[0055] Specifically, work task information is obtained based on the cloud platform, and the work task information includes: the working status of the auxiliary transport vehicle, the corresponding supporting facilities information and the positioning information of the auxiliary transport vehicle in working state; the cloud platform is responsible for receiving and managing all work task information, so as to be able to coordinate the work of all auxiliary transport vehicles; a global map is established based on the working status of the auxiliary transport vehicle, the corresponding supporting facilities information and the positioning information of the auxiliary transport vehicle in working state, and according to the working status of the auxiliary transport vehicle, it can be known which auxiliary transport vehicles are in working state and which auxiliary transport vehicles are in standby state; the corresponding supporting facilities information and the positioning information of the auxiliary transport vehicle in working state can be marked on the map, and a global map can be established by combining the map of the application scenario. The fixed facility locations and the working transportation positioning of the auxiliary transport vehicle can be known through the global map, paving the way for subsequent path planning.

[0056] S12: Based on the work task information, a particle swarm algorithm is used to allocate work tasks to obtain a work task allocation plan;

[0057] In the specific implementation process of the present invention, the work task allocation is performed based on the work task information using the particle swarm algorithm to obtain a work task allocation plan, including: generating an initial particle population based on the work task information using a coding method, and calculating a first fitness value for each particle in the initial particle population and calculating a first population extreme value of the initial particle population; performing an optimization and update process on the initial particle population to obtain an optimized particle population; calculating a second population extreme value of the optimized particle population and a second fitness value for each particle in the optimized particle population; comparing the second population extreme value of the optimized particle population with the first population extreme value of the initial particle population, wherein, if the second population extreme value of the optimized particle population is greater than the first population extreme value of the initial particle population, then the optimized particle population is used as a new initial particle population. The initial particle population continues to be iteratively optimized and updated for a preset number of iterations to obtain a globally optimized particle population; if the second population extreme value of the optimized particle population is less than or equal to the first population extreme value of the initial particle population, the particles in the initial particle population are compared with the particles in the optimized particle population, and all particles in the optimized particle population whose second fitness value is greater than the first fitness value are replaced with the corresponding particles in the initial particle population to obtain a new initial particle population, and the new initial particle population continues to be iteratively optimized and updated for a preset number of iterations to obtain a globally optimized particle population, and the globally optimized particle population is used as the initial work task allocation plan; based on the coordination strategy, it is determined whether the initial work task allocation plan needs to be adjusted, and a work task allocation plan is generated based on the determination result.

[0058] Furthermore, the coordination strategy is based on determining whether the initial work task allocation plan needs to be adjusted, and generating a work task allocation plan based on the determination result, including: determining whether the number of tasks allocated to the auxiliary transport vehicle in the initial work task allocation plan is greater than the task load upper limit of the auxiliary transport vehicle, wherein, if the number of tasks allocated to the auxiliary transport vehicle in the initial work task allocation plan is greater than the task load upper limit of the auxiliary transport vehicle, then calculating the number of tasks greater than the task load upper limit of the auxiliary transport vehicle, and reallocating the tasks greater than the task load upper limit of the auxiliary transport vehicle to obtain a work task allocation plan; if the number of tasks allocated to the auxiliary transport vehicle in the initial work task allocation plan is less than or equal to the task load upper limit of the auxiliary transport vehicle, then the initial work task allocation plan does not need to be adjusted.

[0059] Specifically, an initial particle population is generated according to the work task information using an encoding method, the dimension of the particle is the number of tasks, and the particle dimension is used for processing according to the preset processing node and the particle encoding expression to generate the initial particle population, and a first fitness value and a first population extreme value of the initial particle population are calculated for each particle in the initial particle population, and a first fitness value is calculated for each particle in the initial particle population, and a fitness function is defined. The fitness function is a mathematical function that converts the characteristics of each particle into a fitness value, and each particle in the initial particle population is converted into a binary data string expression, and the binary data string is mapped to the solution space, and the quality of each particle is evaluated in the solution space according to the fitness function. Estimate, calculate the first fitness value of each particle according to the evaluation of the degree of quality, the higher the fitness value, the stronger the adaptability of the particle, calculate the first population extreme value of the initial particle population, the population extreme value is the overall objective function value of the deployment position of all particles in the particle population, add the preset constraint conditions to the objective function, calculate the objective function value of the deployment position of each particle in the particle population according to the objective function, combine the objective function values ​​of each particle, calculate the overall value of the initial particle population, and obtain the first population extreme value of the initial particle population; optimize and update the initial particle population. The optimization update of the initial particle population is actually the exchange of the particle deployment position in the particle population. The purpose of optimization update is to avoid the algorithm from falling into local optimization, which causes the final result to fail to meet the requirements. After optimization update, the optimized particle population is obtained; similarly, the second fitness value of each particle in the optimized particle population is calculated, and the fitness function is defined. Each particle in the optimized particle population is converted into a binary data string expression, and the binary data string is mapped to the solution space. According to the fitness function, the quality of each particle in the solution space is evaluated, and the second fitness value of each particle is calculated based on the evaluation of the quality. The second population extreme value of the optimized particle population is calculated, and the preset constraints are added to the objective function. According to the objective function, the new deployment position of each particle in the optimized particle population is calculated. The objective function value of each particle is combined to calculate the overall value of the optimized particle population and obtain the second population extreme value of the optimized particle population; the second population extreme value of the optimized particle population is compared with the first population extreme value of the initial particle population. If the second population extreme value of the optimized particle population is greater than the first population extreme value of the initial particle population, it means that the deployment position and task allocation of the optimized particle population can better meet the requirements than the initial particle population. Then the optimized particle population is used as the new initial particle population to continue iterative optimization and update to the preset number of iterations. The particles in the optimized particle population are continuously deployed and exchanged until the preset number of iterations is reached before the processing is terminated to obtain the global optimized particle population.If the second population extreme value of the optimized particle population is less than or equal to the first population extreme value of the initial particle population, it means that the update of the optimized particle population has not achieved the overall deployment optimization, but there are particles in the optimized particle population that achieve individual deployment optimization after optimization update, then the particles in the initial particle population are compared with the particles in the optimized particle population, and all particles in the optimized particle population whose second fitness value is greater than the first fitness value are replaced with the corresponding particles in the initial particle population, and these particles that achieve individual optimization are replaced with the corresponding particles to obtain a new initial particle population, and the new initial particle population is also iteratively optimized and updated to the preset number of iterations to achieve global deployment optimization, obtain a global optimized particle population, and use the global optimized particle population as the initial work task deployment plan; obtain the initial After the initial work task allocation plan is determined, the coordination strategy is used to determine whether the initial work task allocation plan needs to be adjusted. Taking into account the task load limit of the auxiliary transport vehicle, the work task allocation plan needs to be adjusted. It is determined whether the number of tasks assigned to the auxiliary transport vehicle in the initial work task allocation plan exceeds the task load limit of the auxiliary transport vehicle. If so, the number of tasks that exceed the task load limit of the auxiliary transport vehicle is calculated and these tasks are reallocated. These tasks are allocated to auxiliary transport vehicles that have not reached the task load limit. After reallocation, the work task allocation plan is obtained. If the task load limit is less than the task load limit, no adjustment is required. Using the particle swarm algorithm for work task allocation can effectively improve the efficiency of controlling the transportation tasks of the auxiliary transport vehicles and complete the work task allocation in a faster time.

[0060] S13: performing path planning using a fuzzy logic algorithm based on the work task information and the global map to obtain an optimized transportation path;

[0061] In the specific implementation process of the present invention, the path planning is performed based on the work task information and the global map using a fuzzy logic algorithm to obtain an optimized transportation path, including: establishing a global coordinate system based on the work task information using the global map; setting the starting point and end point of the transportation path in the global coordinate system, and generating an initial transportation path based on the starting point and end point of the transportation path using the A-star algorithm; and performing fuzzy inference processing on the initial transportation path based on a preset fuzzy controller to obtain an optimized transportation path.

[0062] Furthermore, the initial transport path is generated based on the starting point and the end point of the transport path using the A-star algorithm, including: randomly generating a number of transport path points based on the starting point and the end point of the transport path; searching the number of transport path points based on the heuristic function of the A-star algorithm to obtain a number of optimized path points, and generating the initial transport path based on the number of optimized path points and the starting point and the end point of the transport path.

[0063] Specifically, a global coordinate system is established using a global map according to the work task information. The global coordinate system can intuitively show the coordinate information of each auxiliary transport vehicle and can set coordinate conditions for subsequent path planning; the starting point and end point of the transport path are set in the global coordinate system, and the initial transport path is generated based on the starting point and end point of the transport path using the A-star algorithm. The A-star algorithm is a commonly used path-finding algorithm. By searching for multiple target nodes in the coordinate system, a path that meets the requirements is obtained. First, a number of transport path points are randomly generated based on the starting point and end point of the transport path; a heuristic function based on the A-star algorithm is used to search for a number of transport path points to obtain a number of optimized path points. The heuristic function of the A-star algorithm is an evaluation function used for search. By calculating the cost evaluation value from transport path point to transport path point, and comparing the cost evaluation values, the minimum cost evaluation value is obtained. The two transport path points corresponding to the value are taken as the target path points. After obtaining the two target path points, the cost evaluation value of the next transport path point is calculated for the next target path point until all the target path points are obtained, that is, a number of optimized path points are obtained. The starting point, all optimized path points and the end point of the transport path are connected to generate an initial transport path; based on the preset fuzzy controller, the initial transport path is fuzzy inference processed, and the preset fuzzy controller is used to process the initial transport path to meet the fuzzy control requirements, and the processed initial transport path is scaled to determine its corresponding membership function. Fuzzy processing is performed according to the membership function to obtain the optimized transport path. The fuzzy logic algorithm is an algorithm that solves imprecise information and can accurately handle the problem of path planning logic. Path planning through the fuzzy logic algorithm can quickly and accurately plan the transport path.

[0064] S14: allocating corresponding auxiliary transport vehicles based on the work task allocation plan and the optimized transport route, and selecting a working mode for the corresponding auxiliary transport vehicles;

[0065] In the specific implementation process of the present invention, the corresponding auxiliary transport vehicles are deployed based on the work task deployment plan and the optimized transport path, and the working mode is selected for the corresponding auxiliary transport vehicles, including: marking the corresponding auxiliary transport vehicles based on the work task deployment plan and the optimized transport path, and deploying the marked auxiliary transport vehicles based on the cloud platform; obtaining the type of transported items, and selecting the working mode for the corresponding auxiliary transport vehicles based on the type of transported items.

[0066] Specifically, the corresponding auxiliary transport vehicles are marked according to the work task allocation plan and the optimized transport route, and the marked auxiliary transport vehicles are allocated according to the cloud platform. Marking the corresponding auxiliary transport vehicles can avoid allocation errors, and the cloud platform can track the corresponding auxiliary transport vehicles according to the marks; obtain the type of transported items, and select the working mode for the corresponding auxiliary transport vehicle according to the type of transported items. If a wheelchair is being transported, the wheelchair carrying mode is selected. If a large luggage package is being transported, the package transport mode is selected. Selecting different working modes can enhance the safety of the transportation process.

[0067] S15: Based on the working mode, the auxiliary transport vehicle is used to transport using the built-in early warning device, the early warning device is used to collect real-time images of the transportation process, the real-time images transmitted by the early warning device are analyzed based on the cloud platform, and the transportation route is adjusted based on the analysis results.

[0068] In the specific implementation process of the present invention, the transportation is carried out based on the working mode using the built-in early warning device of the auxiliary transport vehicle, the early warning device is used to collect real-time images of the transportation process, the real-time images transmitted by the early warning device are analyzed based on the cloud platform, and the transportation route is adjusted based on the analysis results, including: the auxiliary transport vehicle performs transportation based on the corresponding working mode, wherein, during the transportation process of the auxiliary transport vehicle, the built-in early warning device of the auxiliary transport vehicle is used to obtain real-time images of the transportation process, and the real-time images are transmitted to the cloud platform; the cloud platform analyzes the real-time images based on the image detection algorithm, and adjusts the transportation route based on the analysis results.

[0069] Furthermore, the cloud platform analyzes the real-time image based on an image detection algorithm, including: binarizing the real-time image to obtain a binarized real-time image; inputting the binarized real-time image into a preset target detection model to obtain an obstacle outline; and marking the area of ​​the obstacle outline based on a preset icon to obtain obstacle area identification information.

[0070] Specifically, the auxiliary transport vehicle performs transportation according to the corresponding working mode. During the transportation process, the built-in warning equipment of the auxiliary transport vehicle is used to obtain real-time images of the transportation process, and the real-time images are transmitted to the cloud platform; the cloud platform analyzes the real-time images based on the image detection algorithm, binarizes the real-time images, sets an initial threshold, and divides each pixel data of the real-time image into object pixel data and background pixel data according to the initial threshold, calculates the average value of the object pixel data and the background pixel data, and uses the average value as the new threshold to continue to divide other pixel data, repeats the above process until all pixel data of the real-time image are processed, and obtains a binarized real-time image; the binarized real-time image is input into the preset target detection model, and each layer structure in the preset target detection model performs binarization on the input. The image is subjected to feature discrimination extraction processing, and the extraction result is outputted finally, that is, the obstacle outline is obtained; after obtaining the obstacle outline, since the obstacle outline may be irregular in shape, the obstacle outline is regionally marked according to the preset icon, and a rectangular icon or a circular icon can be used to mark the obstacle outline and obtain the obstacle area identification information; the transportation route is adjusted in time according to the obstacle area identification information to avoid the obstacle; if after the obstacle avoidance operation is performed, the obstacle is still detected to be approaching the auxiliary transport vehicle, an alarm prompt is issued through the alarm system of the auxiliary transport vehicle; during the transportation process, the user can also manually control it through the screen on the auxiliary transport vehicle. When the auxiliary transport vehicle reaches the destination, the load balance platform extends forward to allow the wheelchair or package to leave the auxiliary transport vehicle smoothly.

[0071] In an embodiment of the present invention, work task information is obtained and a global map is established through a cloud platform, which can unify management tasks and better control auxiliary transport vehicles. Work task allocation is performed through a particle swarm algorithm, which can complete the allocation of work tasks in a faster time, and path planning is performed through a fuzzy logic algorithm, which can quickly and accurately plan the transportation route. According to the work task allocation plan and the optimized transportation route, the corresponding auxiliary transport vehicle is selected for the working mode to meet the transportation requirements of different scenarios and different types of transported items. During the transportation process of the auxiliary transport vehicle, images can be collected and analyzed in real time, and the transportation route can be adjusted according to the analysis results to effectively avoid obstacles and achieve better obstacle avoidance effects. The present invention can not only effectively improve the management and control efficiency of transportation, greatly reduce the investment in labor costs, and improve the reliability of the transportation process, meeting the high requirements of users for the transportation process.

[0072] Example 2

[0073] See also Figure 2 , Figure 2 Schematic diagram of the structure of a system based on intelligent assisted transportation control in an embodiment of the present invention.

[0074] like Figure 2 As shown, a system based on intelligent auxiliary transportation control, the system includes:

[0075] The task acquisition and global map module 21 is used to acquire work task information based on the cloud platform and establish a global map based on the work task information;

[0076] In the specific implementation process of the present invention, the work task information is obtained based on the cloud platform, and a global map is established based on the work task information, including: obtaining work task information based on the cloud platform, wherein the work task information includes: the working status of the auxiliary transport vehicle, the corresponding supporting facilities information and the positioning information of the auxiliary transport vehicle in the working state; establishing a global map based on the working status of the auxiliary transport vehicle, the corresponding supporting facilities information and the positioning information of the auxiliary transport vehicle in the working state.

[0077] Specifically, work task information is obtained based on the cloud platform, and the work task information includes: the working status of the auxiliary transport vehicle, the corresponding supporting facilities information and the positioning information of the auxiliary transport vehicle in working state; the cloud platform is responsible for receiving and managing all work task information, so as to be able to coordinate the work of all auxiliary transport vehicles; a global map is established based on the working status of the auxiliary transport vehicle, the corresponding supporting facilities information and the positioning information of the auxiliary transport vehicle in working state, and according to the working status of the auxiliary transport vehicle, it can be known which auxiliary transport vehicles are in working state and which auxiliary transport vehicles are in standby state; the corresponding supporting facilities information and the positioning information of the auxiliary transport vehicle in working state can be marked on the map, and a global map can be established by combining the map of the application scenario. The fixed facility locations and the working transportation positioning of the auxiliary transport vehicle can be known through the global map, paving the way for subsequent path planning.

[0078] Work task allocation module 22: configured to allocate work tasks based on the work task information using a particle swarm algorithm to obtain a work task allocation plan;

[0079] In the specific implementation process of the present invention, the work task allocation is performed based on the work task information using the particle swarm algorithm to obtain a work task allocation plan, including: generating an initial particle population based on the work task information using a coding method, and calculating a first fitness value for each particle in the initial particle population and calculating a first population extreme value of the initial particle population; performing an optimization and update process on the initial particle population to obtain an optimized particle population; calculating a second population extreme value of the optimized particle population and a second fitness value for each particle in the optimized particle population; comparing the second population extreme value of the optimized particle population with the first population extreme value of the initial particle population, wherein, if the second population extreme value of the optimized particle population is greater than the first population extreme value of the initial particle population, then the optimized particle population is used as a new initial particle population. The initial particle population continues to be iteratively optimized and updated for a preset number of iterations to obtain a globally optimized particle population; if the second population extreme value of the optimized particle population is less than or equal to the first population extreme value of the initial particle population, the particles in the initial particle population are compared with the particles in the optimized particle population, and all particles in the optimized particle population whose second fitness value is greater than the first fitness value are replaced with the corresponding particles in the initial particle population to obtain a new initial particle population, and the new initial particle population continues to be iteratively optimized and updated for a preset number of iterations to obtain a globally optimized particle population, and the globally optimized particle population is used as the initial work task allocation plan; based on the coordination strategy, it is determined whether the initial work task allocation plan needs to be adjusted, and a work task allocation plan is generated based on the determination result.

[0080] Furthermore, the coordination strategy is based on determining whether the initial work task allocation plan needs to be adjusted, and generating a work task allocation plan based on the determination result, including: determining whether the number of tasks allocated to the auxiliary transport vehicle in the initial work task allocation plan is greater than the task load upper limit of the auxiliary transport vehicle, wherein, if the number of tasks allocated to the auxiliary transport vehicle in the initial work task allocation plan is greater than the task load upper limit of the auxiliary transport vehicle, then calculating the number of tasks greater than the task load upper limit of the auxiliary transport vehicle, and reallocating the tasks greater than the task load upper limit of the auxiliary transport vehicle to obtain a work task allocation plan; if the number of tasks allocated to the auxiliary transport vehicle in the initial work task allocation plan is less than or equal to the task load upper limit of the auxiliary transport vehicle, then the initial work task allocation plan does not need to be adjusted.

[0081] Specifically, an initial particle population is generated according to the work task information using an encoding method, the dimension of the particle is the number of tasks, and the particle dimension is used for processing according to the preset processing node and the particle encoding expression to generate the initial particle population, and a first fitness value and a first population extreme value of the initial particle population are calculated for each particle in the initial particle population, and a first fitness value is calculated for each particle in the initial particle population, and a fitness function is defined. The fitness function is a mathematical function that converts the characteristics of each particle into a fitness value, and each particle in the initial particle population is converted into a binary data string expression, and the binary data string is mapped to the solution space, and the quality of each particle is evaluated in the solution space according to the fitness function. Estimate, calculate the first fitness value of each particle according to the evaluation of the degree of quality, the higher the fitness value, the stronger the adaptability of the particle, calculate the first population extreme value of the initial particle population, the population extreme value is the overall objective function value of the deployment position of all particles in the particle population, add the preset constraint conditions to the objective function, calculate the objective function value of the deployment position of each particle in the particle population according to the objective function, combine the objective function values ​​of each particle, calculate the overall value of the initial particle population, and obtain the first population extreme value of the initial particle population; optimize and update the initial particle population. The optimization update of the initial particle population is actually the exchange of the particle deployment position in the particle population. The purpose of optimization update is to avoid the algorithm from falling into local optimization, which causes the final result to fail to meet the requirements. After optimization update, the optimized particle population is obtained; similarly, the second fitness value of each particle in the optimized particle population is calculated, and the fitness function is defined. Each particle in the optimized particle population is converted into a binary data string expression, and the binary data string is mapped to the solution space. According to the fitness function, the quality of each particle in the solution space is evaluated, and the second fitness value of each particle is calculated based on the evaluation of the quality. The second population extreme value of the optimized particle population is calculated, and the preset constraints are added to the objective function. According to the objective function, the new deployment position of each particle in the optimized particle population is calculated. The objective function value of each particle is combined to calculate the overall value of the optimized particle population and obtain the second population extreme value of the optimized particle population; the second population extreme value of the optimized particle population is compared with the first population extreme value of the initial particle population. If the second population extreme value of the optimized particle population is greater than the first population extreme value of the initial particle population, it means that the deployment position and task allocation of the optimized particle population can better meet the requirements than the initial particle population. Then the optimized particle population is used as the new initial particle population to continue iterative optimization and update to the preset number of iterations. The particles in the optimized particle population are continuously deployed and exchanged until the preset number of iterations is reached before the processing is terminated to obtain the global optimized particle population.If the second population extreme value of the optimized particle population is less than or equal to the first population extreme value of the initial particle population, it means that the update of the optimized particle population has not achieved the overall deployment optimization, but there are particles in the optimized particle population that achieve individual deployment optimization after optimization update, then the particles in the initial particle population are compared with the particles in the optimized particle population, and all particles in the optimized particle population whose second fitness value is greater than the first fitness value are replaced with the corresponding particles in the initial particle population, and these particles that achieve individual optimization are replaced with the corresponding particles to obtain a new initial particle population, and the new initial particle population is also iteratively optimized and updated to the preset number of iterations to achieve global deployment optimization, obtain a global optimized particle population, and use the global optimized particle population as the initial work task deployment plan; obtain the initial After the initial work task allocation plan is determined, the coordination strategy is used to determine whether the initial work task allocation plan needs to be adjusted. Taking into account the task load limit of the auxiliary transport vehicle, the work task allocation plan needs to be adjusted. It is determined whether the number of tasks assigned to the auxiliary transport vehicle in the initial work task allocation plan exceeds the task load limit of the auxiliary transport vehicle. If so, the number of tasks that exceed the task load limit of the auxiliary transport vehicle is calculated and these tasks are reallocated. These tasks are allocated to auxiliary transport vehicles that have not reached the task load limit. After reallocation, the work task allocation plan is obtained. If the task load limit is less than the task load limit, no adjustment is required. Using the particle swarm algorithm for work task allocation can effectively improve the efficiency of controlling the transportation tasks of the auxiliary transport vehicles and complete the work task allocation in a faster time.

[0082] Path planning module 23: used to perform path planning based on the work task information and the global map using a fuzzy logic algorithm to obtain an optimized transportation path;

[0083] In the specific implementation process of the present invention, the path planning is performed based on the work task information and the global map using a fuzzy logic algorithm to obtain an optimized transportation path, including: establishing a global coordinate system based on the work task information using the global map; setting the starting point and end point of the transportation path in the global coordinate system, and generating an initial transportation path based on the starting point and end point of the transportation path using the A-star algorithm; and performing fuzzy inference processing on the initial transportation path based on a preset fuzzy controller to obtain an optimized transportation path.

[0084] Furthermore, the initial transport path is generated based on the starting point and the end point of the transport path using the A-star algorithm, including: randomly generating a number of transport path points based on the starting point and the end point of the transport path; searching the number of transport path points based on the heuristic function of the A-star algorithm to obtain a number of optimized path points, and generating the initial transport path based on the number of optimized path points and the starting point and the end point of the transport path.

[0085] Specifically, a global coordinate system is established using a global map according to the work task information. The global coordinate system can intuitively show the coordinate information of each auxiliary transport vehicle and can set coordinate conditions for subsequent path planning; the starting point and end point of the transport path are set in the global coordinate system, and the initial transport path is generated based on the starting point and end point of the transport path using the A-star algorithm. The A-star algorithm is a commonly used path-finding algorithm. By searching for multiple target nodes in the coordinate system, a path that meets the requirements is obtained. First, a number of transport path points are randomly generated based on the starting point and end point of the transport path; a heuristic function based on the A-star algorithm is used to search for a number of transport path points to obtain a number of optimized path points. The heuristic function of the A-star algorithm is an evaluation function used for search. By calculating the cost evaluation value from transport path point to transport path point, and comparing the cost evaluation values, the minimum cost evaluation value is obtained. The two transport path points corresponding to the value are taken as the target path points. After obtaining the two target path points, the cost evaluation value of the next transport path point is calculated for the next target path point until all the target path points are obtained, that is, a number of optimized path points are obtained. The starting point, all optimized path points and the end point of the transport path are connected to generate an initial transport path; based on the preset fuzzy controller, the initial transport path is fuzzy inference processed, and the preset fuzzy controller is used to process the initial transport path to meet the fuzzy control requirements, and the processed initial transport path is scaled to determine its corresponding membership function. Fuzzy processing is performed according to the membership function to obtain the optimized transport path. The fuzzy logic algorithm is an algorithm that solves imprecise information and can accurately handle the problem of path planning logic. Path planning through the fuzzy logic algorithm can quickly and accurately plan the transport path.

[0086] Allocation module 24: configured to allocate corresponding auxiliary transport vehicles based on the work task allocation plan and the optimized transport route, and select a working mode for the corresponding auxiliary transport vehicles;

[0087] In the specific implementation process of the present invention, the corresponding auxiliary transport vehicles are deployed based on the work task deployment plan and the optimized transport path, and the working mode is selected for the corresponding auxiliary transport vehicles, including: marking the corresponding auxiliary transport vehicles based on the work task deployment plan and the optimized transport path, and deploying the marked auxiliary transport vehicles based on the cloud platform; obtaining the type of transported items, and selecting the working mode for the corresponding auxiliary transport vehicles based on the type of transported items.

[0088] Specifically, the corresponding auxiliary transport vehicles are marked according to the work task allocation plan and the optimized transport route, and the marked auxiliary transport vehicles are allocated according to the cloud platform. Marking the corresponding auxiliary transport vehicles can avoid allocation errors, and the cloud platform can track the corresponding auxiliary transport vehicles according to the marks; obtain the type of transported items, and select the working mode for the corresponding auxiliary transport vehicle according to the type of transported items. If a wheelchair is being transported, the wheelchair carrying mode is selected. If a large luggage package is being transported, the package transport mode is selected. Selecting different working modes can enhance the safety of the transportation process.

[0089] Transportation and real-time analysis module 25: used to transport using the early warning device built into the auxiliary transport vehicle based on the working mode, the early warning device is used to collect real-time images of the transportation process, analyze the real-time images transmitted by the early warning device based on the cloud platform, and adjust the transportation route based on the analysis results.

[0090] In the specific implementation process of the present invention, the transportation is carried out based on the working mode using the built-in early warning device of the auxiliary transport vehicle, the early warning device is used to collect real-time images of the transportation process, the real-time images transmitted by the early warning device are analyzed based on the cloud platform, and the transportation route is adjusted based on the analysis results, including: the auxiliary transport vehicle performs transportation based on the corresponding working mode, wherein, during the transportation process of the auxiliary transport vehicle, the built-in early warning device of the auxiliary transport vehicle is used to obtain real-time images of the transportation process, and the real-time images are transmitted to the cloud platform; the cloud platform analyzes the real-time images based on the image detection algorithm, and adjusts the transportation route based on the analysis results.

[0091] Furthermore, the cloud platform analyzes the real-time image based on an image detection algorithm, including: binarizing the real-time image to obtain a binarized real-time image; inputting the binarized real-time image into a preset target detection model to obtain an obstacle outline; and marking the area of ​​the obstacle outline based on a preset icon to obtain obstacle area identification information.

[0092] Specifically, the auxiliary transport vehicle performs transportation according to the corresponding working mode. During the transportation process, the built-in warning equipment of the auxiliary transport vehicle is used to obtain real-time images of the transportation process, and the real-time images are transmitted to the cloud platform; the cloud platform analyzes the real-time images based on the image detection algorithm, binarizes the real-time images, sets an initial threshold, and divides each pixel data of the real-time image into object pixel data and background pixel data according to the initial threshold, calculates the average value of the object pixel data and the background pixel data, and uses the average value as the new threshold to continue to divide other pixel data, repeats the above process until all pixel data of the real-time image are processed, and obtains a binarized real-time image; the binarized real-time image is input into the preset target detection model, and each layer structure in the preset target detection model performs binarization on the input. The image is subjected to feature discrimination extraction processing, and the extraction result is outputted finally, that is, the obstacle outline is obtained; after obtaining the obstacle outline, since the obstacle outline may be irregular in shape, the obstacle outline is regionally marked according to the preset icon, and a rectangular icon or a circular icon can be used to mark the obstacle outline and obtain the obstacle area identification information; the transportation route is adjusted in time according to the obstacle area identification information to avoid the obstacle; if after the obstacle avoidance operation is performed, the obstacle is still detected to be approaching the auxiliary transport vehicle, an alarm prompt is issued through the alarm system of the auxiliary transport vehicle; during the transportation process, the user can also manually control it through the screen on the auxiliary transport vehicle. When the auxiliary transport vehicle reaches the destination, the load balance platform extends forward to allow the wheelchair or package to leave the auxiliary transport vehicle smoothly.

[0093] In an embodiment of the present invention, work task information is obtained and a global map is established through a cloud platform, which can unify management tasks and better control auxiliary transport vehicles. Work task allocation is performed through a particle swarm algorithm, which can complete the allocation of work tasks in a faster time, and path planning is performed through a fuzzy logic algorithm, which can quickly and accurately plan the transportation route. According to the work task allocation plan and the optimized transportation route, the corresponding auxiliary transport vehicle is selected for the working mode to meet the transportation requirements of different scenarios and different types of transported items. During the transportation process of the auxiliary transport vehicle, images can be collected and analyzed in real time, and the transportation route can be adjusted according to the analysis results to effectively avoid obstacles and achieve better obstacle avoidance effects. The present invention can not only effectively improve the management and control efficiency of transportation, greatly reduce the investment in labor costs, and improve the reliability of the transportation process, meeting the high requirements of users for the transportation process.

[0094] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0095] In addition, the above provides a detailed introduction to the embodiments of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method based on intelligent assisted transportation control, characterized in that: The method comprises: Acquire work task information based on the cloud platform, and establish a global map based on the work task information; Based on the work task information, a particle swarm algorithm is used to allocate work tasks to obtain a work task allocation plan; Based on the work task information and the global map, a fuzzy logic algorithm is used to perform path planning to obtain an optimized transportation path; Allocate corresponding auxiliary transport vehicles based on the work task allocation plan and the optimized transport route, and select a working mode for the corresponding auxiliary transport vehicles; Based on the working mode, transportation is performed using the built-in warning device of the auxiliary transport vehicle, the warning device is used to collect real-time images of the transportation process, the real-time images transmitted by the warning device are analyzed based on the cloud platform, and the transportation route is adjusted based on the analysis results; The obtaining of work task information based on a cloud platform and establishing a global map based on the work task information include: obtaining work task information based on a cloud platform, wherein the work task information includes: working status of auxiliary transport vehicles, corresponding supporting facility information, and positioning information of auxiliary transport vehicles in working status; establishing a global map based on the working status of the auxiliary transport vehicles, corresponding supporting facility information, and positioning information of auxiliary transport vehicles in working status; The method comprises: performing path planning based on the work task information and the global map using a fuzzy logic algorithm to obtain an optimized transportation path, comprising: establishing a global coordinate system based on the work task information using the global map; setting a starting point and an end point of the transportation path in the global coordinate system, and generating an initial transportation path based on the starting point and the end point of the transportation path using an A-star algorithm; and performing fuzzy inference processing on the initial transportation path based on a preset fuzzy controller to obtain an optimized transportation path. The deploying of corresponding auxiliary transport vehicles based on the work task deployment plan and the optimized transport path, and selecting a working mode for the corresponding auxiliary transport vehicles, includes: marking the corresponding auxiliary transport vehicles based on the work task deployment plan and the optimized transport path, and deploying the marked auxiliary transport vehicles based on the cloud platform; obtaining the type of transported items, and selecting a working mode for the corresponding auxiliary transport vehicle based on the type of transported items.

2. The method based on intelligent assisted transportation control according to claim 1, characterized in that: The process of allocating work tasks using a particle swarm algorithm based on the work task information to obtain a work task allocation plan includes: Generate an initial particle population using an encoding method based on the work task information, and calculate a first fitness value for each particle in the initial particle population and a first population extreme value of the initial particle population; performing an optimization and updating process on the initial particle population to obtain an optimized particle population; Calculating a second population extreme value of the optimized particle population and a second fitness value of each particle in the optimized particle population; Comparing the second population extreme value of the optimized particle population with the first population extreme value of the initial particle population, wherein, if the second population extreme value of the optimized particle population is greater than the first population extreme value of the initial particle population, then using the optimized particle population as the new initial particle population to continue iterative optimization and update processing to a preset number of iterations to obtain a global optimized particle population; If the second population extreme value of the optimized particle population is less than or equal to the first population extreme value of the initial particle population, the particles in the initial particle population are compared with the particles in the optimized particle population, and all particles in the optimized particle population whose second fitness value is greater than the first fitness value are replaced with the corresponding particles in the initial particle population to obtain a new initial particle population. The new initial particle population is further iterated and optimized and updated to a preset number of iterations to obtain a global optimized particle population, and the global optimized particle population is used as the initial work task deployment plan; Based on the coordination strategy, it is determined whether the initial work task allocation plan needs to be adjusted, and the work task allocation plan is generated based on the determination result.

3. The method based on intelligent assisted transportation control according to claim 2, characterized in that: The determining whether the initial work task allocation plan needs to be adjusted based on the coordination strategy, and generating the work task allocation plan based on the determination result, includes: Determine whether the number of tasks assigned to the auxiliary transport vehicle in the initial work task allocation plan is greater than the task load upper limit of the auxiliary transport vehicle, wherein, if the number of tasks assigned to the auxiliary transport vehicle in the initial work task allocation plan is greater than the task load upper limit of the auxiliary transport vehicle, then calculate the number of tasks greater than the task load upper limit of the auxiliary transport vehicle, and readjust and allocate the tasks greater than the task load upper limit of the auxiliary transport vehicle to obtain a work task allocation plan; if the number of tasks assigned to the auxiliary transport vehicle in the initial work task allocation plan is less than or equal to the task load upper limit of the auxiliary transport vehicle, then the initial work task allocation plan does not need to be adjusted.

4. The method based on intelligent assisted transportation control according to claim 1, characterized in that: The initial transportation path is generated by using the A-star algorithm based on the starting point and the end point of the transportation path, including: Randomly generate several transport path points based on the starting and ending points of the transport path; A heuristic function based on the A-star algorithm searches for several transport path points to obtain several optimized path points, and generates an initial transport path based on the several optimized path points, the start point and the end point of the transport path.

5. The method based on intelligent assisted transportation control according to claim 1, characterized in that: The method of transporting the goods using the built-in warning device of the auxiliary transport vehicle based on the working mode, wherein the warning device is used to collect real-time images of the transportation process, analyzing the real-time images transmitted by the warning device based on the cloud platform, and adjusting the transportation route based on the analysis results, includes: The auxiliary transport vehicle performs transportation based on the corresponding working mode, wherein, during the transportation process of the auxiliary transport vehicle, a built-in warning device of the auxiliary transport vehicle is used to obtain real-time images of the transportation process, and the real-time images are transmitted to the cloud platform; The cloud platform analyzes the real-time image based on an image detection algorithm and adjusts the transportation route based on the analysis results.

6. The method based on intelligent assisted transportation control according to claim 5, characterized in that: The cloud platform analyzes the real-time image based on an image detection algorithm, including: Performing binarization processing on the real-time image to obtain a binarized real-time image; Inputting the binarized real-time image into a preset target detection model to obtain the obstacle outline; The obstacle outline is marked with an area based on a preset icon to obtain obstacle area marking information.

7. A system based on intelligent assisted transport control, characterized in that: The system comprises: A task acquisition and global map module is used to acquire work task information based on the cloud platform and establish a global map based on the work task information; A work task allocation module, configured to allocate work tasks using a particle swarm algorithm based on the work task information to obtain a work task allocation plan; A path planning module, configured to perform path planning based on the work task information and a global map using a fuzzy logic algorithm to obtain an optimized transportation path; A dispatching module, configured to dispatch corresponding auxiliary transport vehicles based on the work task dispatching plan and the optimized transport route, and select a working mode for the corresponding auxiliary transport vehicles; a transportation and real-time analysis module, configured to utilize the early warning device built into the auxiliary transport vehicle for transportation based on the working mode, the early warning device being configured to collect real-time images of the transportation process, analyze the real-time images transmitted by the early warning device based on the cloud platform, and adjust the transportation route based on the analysis results; The obtaining of work task information based on a cloud platform and establishing a global map based on the work task information include: obtaining work task information based on a cloud platform, wherein the work task information includes: working status of auxiliary transport vehicles, corresponding supporting facility information, and positioning information of auxiliary transport vehicles in working status; establishing a global map based on the working status of the auxiliary transport vehicles, corresponding supporting facility information, and positioning information of auxiliary transport vehicles in working status; The method comprises: performing path planning based on the work task information and the global map using a fuzzy logic algorithm to obtain an optimized transportation path, comprising: establishing a global coordinate system based on the work task information using the global map; setting a starting point and an end point of the transportation path in the global coordinate system, and generating an initial transportation path based on the starting point and the end point of the transportation path using an A-star algorithm; and performing fuzzy inference processing on the initial transportation path based on a preset fuzzy controller to obtain an optimized transportation path. The deploying of corresponding auxiliary transport vehicles based on the work task deployment plan and the optimized transport path, and selecting a working mode for the corresponding auxiliary transport vehicles, includes: marking the corresponding auxiliary transport vehicles based on the work task deployment plan and the optimized transport path, and deploying the marked auxiliary transport vehicles based on the cloud platform; obtaining the type of transported items, and selecting a working mode for the corresponding auxiliary transport vehicle based on the type of transported items.

Images