An intelligent scheduling system and method for the passage of driverless logistics vehicles in a park

Abstract

The present invention discloses an intelligent scheduling system and method for the passage of unmanned logistics vehicles in a park, specifically relating to the technical field of intelligent scheduling. All scheduling data is stored through a decentralized blockchain network, and each unmanned logistics vehicle is connected to the blockchain. Whether there is a need for information transfer is judged according to its usage scenario. If necessary, the information interaction mechanism is activated, and the vehicles that need to interact with the target unmanned logistics vehicle are screened out through interaction analysis, and the corresponding database combination is obtained from the blockchain; based on the database combination, a pre-trained neural network model is used to extract restrictive features to generate a set of restrictive conditions; subsequently, a genetic algorithm is used to optimize the scheduling path of the target vehicle based on the restrictive conditions and update it to the blockchain network; the present invention can accurately judge whether there is a need for information transfer between the target vehicle and surrounding vehicles, and start the information interaction mechanism when necessary to ensure that vehicles can effectively coordinate their work.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent scheduling, and more specifically, to an intelligent scheduling system and method for the passage of driverless logistics vehicles in a park. Background Art

[0002] With the development of driverless technology and intelligent scheduling systems, driverless logistics vehicles in parks have played an increasingly important role in logistics transportation, distribution, and other tasks. Current driverless logistics vehicle scheduling systems mainly rely on a centralized server for scheduling and management. Although this mode can meet basic scheduling requirements, when dealing with complex scenarios, such as the collaborative work between vehicles, the avoidance of path conflicts, and resource scheduling, the efficiency is often not high, and single-point failures are prone to occur. In addition, during the vehicle scheduling process, there are also certain challenges in the real-time and security of information sharing and data transfer. Without an effective vehicle-to-vehicle information interaction mechanism and collaborative work means, path conflicts, resource waste, and low task execution efficiency may occur.

[0003] To address these problems, the decentralized blockchain technology has been introduced into the scheduling system of driverless logistics vehicles. Blockchain technology has the characteristics of data immutability, transparent information sharing, and decentralization, but it also brings unnecessary information transmission. How to reduce communication overhead and efficiently perform path planning in complex and changeable scheduling scenarios is an urgent problem to be solved currently. Summary of the Invention

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] An intelligent scheduling method for the passage of driverless logistics vehicles in a park, comprising the following steps:

[0006] Store all scheduling data in a decentralized blockchain network, connect each driverless logistics vehicle to the blockchain network, judge the usage scenarios of each driverless logistics vehicle, and determine whether there is a need for information transfer for the target driverless logistics vehicle;

[0007] When there is a need for information transfer for the target driverless logistics vehicle, activate the information interaction mechanism, and through interaction analysis, screen out the driverless logistics vehicles that need to interact with the target driverless logistics vehicle, and then obtain the database combination corresponding to the information interaction from the blockchain network;

[0008] Based on the database combination, use a pre-trained neural network model to extract restricted features to obtain a set of restricted conditions;

[0009] Use a genetic algorithm to optimize and plan the scheduling path of the target driverless logistics vehicle based on the set of restricted conditions and update the optimized scheduling path in the blockchain network.

[0010] In a preferred embodiment, the decentralized blockchain network contains the respective data sets of all unmanned logistics vehicles, as well as a common data set.

[0011] In a preferred embodiment, the usage scenarios of each unmanned logistics vehicle are judged to generate a conflict coefficient for the target unmanned logistics vehicle. The conflict coefficient is compared with a preset conflict threshold. If the conflict coefficient is greater than the preset conflict threshold, it is judged that the target unmanned logistics vehicle has a need for information transfer. If the conflict coefficient is less than or equal to the preset conflict threshold, it is judged that the target unmanned logistics vehicle has no need for information transfer.

[0012] In a preferred embodiment, the acquisition logic of the conflict coefficient is as follows:

[0013] Obtain the preset path vector and time vector of the target vehicle, mark the path vector as Ptarget, mark the time vector as Ttarget, mark the preset path vector corresponding to each other vehicle around as Pi, and the time vector as Ti, where i represents the number of the vehicle around the target vehicle;

[0014] For each surrounding vehicle i, calculate the conflict value Ci between it and the target vehicle:

[0015] Ci represents the conflict value between the surrounding vehicle i and the target vehicle, and then the maximum value of the conflict value Ci is used as the conflict coefficient.

[0016] The database combination consists of a restricted database jointly composed of the own databases of all unmanned logistics vehicles that the target unmanned logistics vehicle interacts with, and a common database.

[0017] In a preferred embodiment, the unmanned logistics vehicles that need to interact with the target unmanned logistics vehicle are screened out through interaction analysis, which means:

[0018] Obtain the frequency of the target unmanned logistics vehicle and the surrounding vehicle i in the past collaborative tasks and mark it as Hi, and mark the absolute value of the difference in task priority levels between the target vehicle and vehicle i as Yi, and then substitute them into the formula:

[0019]

[0020] α, β satisfy:

[0021] Poverlap i represents the path overlap length between the target unmanned logistics vehicle and the surrounding vehicle i, and Toverlap iIt represents the time overlap interval between the target unmanned logistics vehicle and the surrounding vehicle i. Ptotal represents the path length of the target unmanned logistics vehicle, Ttotal represents the time length of the target unmanned logistics vehicle, CNR represents the cooperation necessity index, and w1 and w2 are both preset proportionality coefficients and are not zero;

[0022] When the cooperation necessity index CNR is greater than the preset information transfer threshold, there is a need for information transfer between the target unmanned logistics vehicle and the surrounding vehicle i.

[0023] In a preferred embodiment, the neural network model is a convolutional neural network model.

[0024] In a preferred embodiment, using the genetic algorithm to optimize and plan the scheduling path of the target unmanned logistics vehicle based on the set of constraint conditions and update the optimized scheduling path in the blockchain network means:

[0025] Initializing the population: Taking the set of constraint conditions extracted from the own database and the public database of all unmanned logistics vehicles that the target unmanned logistics vehicle interacts with as the initial scheduling conditions, and randomly generating an initial scheduling path plan as the initial population for path planning;

[0026] Fitness evaluation: Using the set of constraint conditions as the constraint conditions in the fitness evaluation, and at the same time establishing a fitness evaluation formula: ZYj represents the utilization efficiency of the resource type j of the target unmanned logistics vehicle, m represents the total amount of the resource types of the target unmanned logistics vehicle, fj represents the preset influence coefficient corresponding to the resource type j of the target unmanned logistics vehicle, and F is the fitness value;

[0027] Selection operation: Using the roulette wheel selection method to screen the offspring as the new parents;

[0028] Crossover operation: Randomly exchanging the data in different parent chromosomes;

[0029] Mutation operation: Randomly adjusting the data of different offspring chromosomes;

[0030] Iteration and termination conditions: When the preset termination conditions are reached, select the chromosome with the highest fitness from the final population for decoding to obtain the optimal scheduling path plan.

[0031] In a preferred embodiment, an intelligent scheduling system for the passage of unmanned logistics vehicles in a park includes:

[0032] A storage module that stores all scheduling data in a decentralized blockchain network;

[0033] A scenario judgment module connects each driverless logistics vehicle to the blockchain network, judges the usage scenarios of each driverless logistics vehicle, and determines whether there is a need for information transfer for the target driverless logistics vehicle;

[0034] An interaction screening module activates the information interaction mechanism when there is a need for information transfer for the target driverless logistics vehicle, and screens out the driverless logistics vehicles that need to interact with the target driverless logistics vehicle through interaction analysis;

[0035] A feature extraction module obtains the database combination corresponding to the information interaction from the blockchain network, and based on the database combination, uses a pre-trained neural network model to perform restricted feature extraction to obtain a set of restricted conditions;

[0036] A scheduling module uses a genetic algorithm to optimize and plan the scheduling path of the target driverless logistics vehicle based on the set of restricted conditions and updates the optimized scheduling path in the blockchain network.

[0037] The technical effects and advantages of the present invention:

[0038] By introducing a decentralized blockchain network and storing all scheduling data in the blockchain, the present invention realizes transparent sharing and immutability of data, and avoids the single-point failure problem in traditional centralized systems. Through the application of blockchain technology, the scheduling system can process and share information in real time in multi-vehicle collaborative work and path planning, improving the security of the system and the accuracy of scheduling.

[0039] The present invention combines neural networks and genetic algorithms, and can efficiently schedule and optimize the path of driverless logistics vehicles in a complex and changing park environment. The neural network is used to extract restricted conditions from multi-dimensional data, and the genetic algorithm is used to intelligently plan the path based on the restricted conditions, so that the scheduling process can quickly adapt to different task requirements and effectively avoid potential path conflicts and resource waste.

[0040] Through the intelligent scheduling system of the present invention, accurate scheduling can be performed according to the resource status of the vehicle, reducing excessive energy consumption and improving resource utilization. This is particularly important in multi-vehicle collaborative tasks, which can ensure that the tasks of each vehicle can be completed efficiently, while maximizing the use of available infrastructure resources.

[0041] Through the collaborative necessity index calculation method of the present invention, the system can accurately judge whether there is a need for information transfer between the target vehicle and surrounding vehicles, and activate the information interaction mechanism when necessary to ensure effective coordination between vehicles, avoid task conflicts or resource contention, which greatly improves the efficiency of multi-vehicle collaborative work.

[0042] The scheduling system of the present invention can flexibly handle scheduling problems under the circumstances of task complexity and ever-changing park environment, provide personalized path planning and optimization solutions, and meet the scheduling requirements of driverless logistics vehicles in various complex scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings;

[0044] Figure 1 It is a schematic diagram of an intelligent scheduling method for the passage of driverless logistics vehicles in a park in the present invention.

[0045] Figure 2 It is a schematic diagram of an intelligent scheduling system for the passage of driverless logistics vehicles in a park in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0047] Refer to Figure 1 - Figure 2 The following embodiments are obtained:

[0048] Embodiment 1: An intelligent scheduling method for the passage of driverless logistics vehicles in a park, including the following steps:

[0049] All scheduling data are stored in a decentralized blockchain network, each driverless logistics vehicle is connected to the blockchain network, and the usage scenarios of each driverless logistics vehicle are judged to determine whether there is a need for information transfer for the target driverless logistics vehicle; the decentralized blockchain network ensures the security, transparency, and immutability of scheduling data. All vehicles and the scheduling system can access the same data source in real time, ensuring information consistency and preventing single-point failures, and improving the reliability and efficiency of the scheduling system.

[0050] When there is a need for information transfer in the target unmanned logistics vehicle, the information interaction mechanism is activated, and the unmanned logistics vehicles that need to interact with the target unmanned logistics vehicle are screened through interaction analysis, and then the database combination corresponding to the information interaction is obtained from the blockchain network; in each scheduling scenario, determining whether the target vehicle needs to interact with other vehicles can avoid unnecessary information transmission and reduce communication overhead. If the conflict risk is high, information transfer is necessary, thus ensuring more efficient collaborative scheduling between vehicles. Through analysis and screening, information interaction is carried out with the vehicles that may have path or time conflicts with the target vehicle. This information interaction mechanism helps to improve the collaborative ability of vehicles, avoid route conflicts, resource conflicts, etc., and improve the accuracy and efficiency of vehicle scheduling. Extract the data sets of the target vehicle and its interacting vehicles from the blockchain network to ensure that the scheduling algorithm can calculate based on the latest, true, and reliable data, avoiding information lag or errors.

[0051] Based on the database combination, use the pre-trained neural network model to extract restricted features and obtain a set of restricted conditions; the convolutional neural network (CNN) can more effectively extract multi-dimensional features affecting vehicle scheduling by extracting a set of restricted conditions from the complex database combination, ensuring that the scheduling algorithm takes into account various possible restricted conditions, such as traffic conditions, equipment status, etc., making the scheduling plan more accurate.

[0052] Use the genetic algorithm to optimize and plan the scheduling path of the target unmanned logistics vehicle based on the set of restricted conditions and update the optimized scheduling path in the blockchain network. The genetic algorithm can select the optimal scheduling path from a large number of possible path plans by simulating the natural selection process. The fitness evaluation is comprehensively optimized based on conditions such as the resource utilization efficiency of the target vehicle to ensure that the selected path can maximize resource utilization and reduce conflicts. As an important indicator of fitness evaluation, resource utilization efficiency can measure how reasonably a vehicle uses its resources such as energy and equipment during driving.

[0053] The decentralized blockchain network contains the respective data sets of all unmanned logistics vehicles and the public data set. The decentralized blockchain network ensures data security through distributed storage. The data of all unmanned logistics vehicles (such as status information, task progress, etc.) are stored in the blockchain to prevent data tampering or forgery, enhancing the security and transparency of the system. Because the blockchain has the characteristic of being immutable, all scheduling-related data sets (whether individual vehicle data or public data) can be shared safely and reliably.

[0054] Through the blockchain, all vehicles and the dispatching center can access the public data set at any time, ensuring that each node can obtain global information (such as traffic conditions, road closures, environmental data, etc.), so as to use the most accurate and up-to-date information in dispatching decisions. The sharing of the public data set ensures that each node in the vehicle dispatching system makes decisions using consistent information, avoiding information asymmetry.

[0055] Although the individual vehicle data sets of driverless logistics vehicles are stored on the blockchain, the decentralized nature allows the privacy of each vehicle to be protected through permission management. Each vehicle can choose to share its own data with other vehicles under specific circumstances, such as when there is a necessary dispatching interaction, without having to share all information in irrelevant situations. This protects privacy while enabling data sharing when necessary. Since the blockchain network is decentralized, the data of all vehicles are backed up on multiple nodes, and the system will not suffer data loss or inaccessibility due to a single point of failure. Even if some nodes or vehicles fail to connect to the network due to faults, other nodes can still work normally, ensuring the stability and fault tolerance of the dispatching system.

[0056] The data in the decentralized network is updated and synchronized in real time, which means that the status of each vehicle and the public data can be quickly updated to all nodes in the network, ensuring that dispatching decisions are based on the latest data. During the dispatching process, vehicles can adjust their route planning at any time according to the latest status and environmental data, improving the real-time performance and response speed of dispatching. In some scenarios, multiple driverless logistics vehicles need to cooperate. The decentralized blockchain network can efficiently achieve data exchange. By sharing individual vehicle data and public data, cooperative vehicles can quickly obtain each other's status and constraints, and make intelligent decisions based on global information, avoiding route conflicts or resource contention.

[0057] Moreover, the data of all vehicle and dispatching operations are stored in the blockchain and can be traced and verified. During the dispatching process, if a problem or conflict occurs, the transparency of the blockchain record allows the dispatching center or manager to view the historical record of the data, so as to trace the root cause of the problem. This enhances the responsibility management of the system and reduces the risk of dispatching errors or failures.

[0058] Judge the usage scenarios of each driverless logistics vehicle to generate the conflict coefficient of the target driverless logistics vehicle. Compare the conflict coefficient with the preset conflict threshold. If the conflict coefficient is greater than the preset conflict threshold, it is judged that the target driverless logistics vehicle has the necessity of information transfer. If the conflict coefficient is less than or equal to the preset conflict threshold, it is judged that the target driverless logistics vehicle has no necessity of information transfer. This mechanism can be understood as a smart contract. A smart contract is an automated protocol running on the blockchain that can automatically execute operations according to preset conditions.

[0059] Preset condition: The comparison between the conflict coefficient and the threshold is used as the criterion for judging whether information transfer is required. This comparison logic can be used as a triggering condition in a smart contract.

[0060] Automatic execution: When the conflict coefficient is greater than the threshold, the system automatically judges and activates the necessity of information transfer; when it is less than or equal to the threshold, no information transfer is performed. This is a typical automated execution logic in a smart contract.

[0061] No manual intervention required: The smart contract automatically executes corresponding tasks when certain conditions are met. In this scenario, the system can automatically determine whether the target unmanned logistics vehicle needs to exchange data with other vehicles through the calculation of the conflict coefficient, without manual intervention.

[0062] Decentralized execution: Since the data is stored in a decentralized blockchain network, this judgment mechanism can also be automatically executed on the blockchain through a smart contract, without relying on the intervention of a central server or dispatching center.

[0063] Contract content: The triggering condition of the smart contract can be designed as follows: Compare the conflict coefficient with the preset conflict threshold. If the conflict coefficient is greater than the preset conflict threshold, it is judged that there is a need for information transfer for the target unmanned logistics vehicle; if the conflict coefficient is less than or equal to the preset conflict threshold, it is judged that there is no need for information transfer for the target unmanned logistics vehicle.

[0064] The acquisition logic of the conflict coefficient is as follows:

[0065] Obtain the preset path vector and time vector of the target vehicle, mark the path vector as Ptarget and the time vector as Ttarget, and mark the preset path vector and time vector of each surrounding vehicle as Pi and Ti respectively, where i represents the number of the surrounding vehicle of the target vehicle;

[0066] For each surrounding vehicle i, calculate the conflict value Ci between it and the target vehicle:

[0067] Ci represents the conflict value between the surrounding vehicle i and the target vehicle, and then take the maximum value of the conflict value Ci as the conflict coefficient.

[0068] The conflict coefficient C is an indicator that measures the possible spatial and temporal conflicts between a target vehicle and the vehicles around it. It is comprehensively calculated through the path vector (i.e., the driving path of the vehicle) and the time vector (i.e., the expected time of the vehicle). The calculation of the conflict coefficient reflects the spatio-temporal overlap between the target vehicle and the surrounding vehicles. The larger the value, the higher the possibility of conflict. Through the vectors in two dimensions of path and time, the system can evaluate the conflicts of vehicles in space (path) and time (time window). If two vehicles have a large degree of time coincidence on the same path, the risk of conflict will increase accordingly. The formula C i represents the calculation of the conflict value between the target vehicle and the surrounding vehicle i, which combines the overlap degree of the path and time between the vehicles. The dot product of the path vector and the time vector is calculated in the formula to judge how much overlap there is between the two vehicles in terms of path and time. At the same time, through the normalization of the denominator part, the excessive numerical difference is avoided. The maximum value among all the calculated conflict values Ci is used as the conflict coefficient of the target vehicle. The maximum conflict value reflects the most serious conflict situation between the target vehicle and all the surrounding vehicles. If the conflict value of a certain vehicle is very high, it means that the overlap degree of the path and time between this vehicle and the target vehicle is very large, and special attention needs to be paid and avoidance measures may be taken. By calculating the conflict coefficient, the system can automatically judge whether there is a need for data interaction or cooperation between the target vehicle and other vehicles. If the conflict coefficient is higher than the preset threshold, the system will trigger an information flow mechanism to optimize the path and time planning by exchanging data with other vehicles.

[0069] It should be noted that the definition of the surrounding vehicle i is usually comprehensively judged based on multiple dimensions such as the spatial position, time, task relevance, and communication range of the target vehicle. The specific definition methods can be as follows:

[0070] Based on distance: The surrounding vehicle i can be defined according to the physical distance from the target vehicle. Usually, a perception range radius (such as 50 meters or 100 meters) is set, and all vehicles within this range are considered surrounding vehicles.

[0071] Based on area division: The park can be divided into several areas, and all vehicles in the same area as the target vehicle are regarded as surrounding vehicles. This can avoid too many vehicles being included in the calculation.

[0072] Time coincidence: If there is a large coincidence in the driving time periods between the target vehicle and other vehicles, then these vehicles can be regarded as surrounding vehicles. Even if the physical distance is far, but if the two vehicles will meet in the same area at a certain time point, these vehicles also need to be included in the category of surrounding vehicles. Set a time window, such as vehicles that may meet within 10 minutes. Vehicles outside this time window are not regarded as surrounding vehicles.

[0073] Task Association: If the target vehicle and other vehicles are performing the same task (such as collaborative cargo transportation or jointly completing a certain task), these vehicles will be regarded as surrounding vehicles even if there are slight differences in space or time.

[0074] Task Priority: Some key task vehicles may require special attention during scheduling. Even if they are not within the physical space perception range, they can be regarded as surrounding vehicles for early conflict detection and collaborative planning.

[0075] Based on Communication Network: If direct communication is possible between the target vehicle and other vehicles (such as through in-vehicle communication systems or dedicated wireless networks within the park), then vehicles within the communication range can be defined as surrounding vehicles.

[0076] Based on Dynamic Sensing: Through in-vehicle sensors and environmental perception systems, the target vehicle can detect in real time whether there are other vehicles around. Based on these sensor data, it can determine in real time which vehicles are in its vicinity. For example, using lidar, cameras, etc. to detect nearby vehicles in real time, so as to dynamically update the list of surrounding vehicles.

[0077] Based on Road Topology: In some complex park scenarios, the definition of surrounding vehicles can be based on the structure of the road network. If the target vehicle and other vehicles will meet at the same intersection or junction, or are on the same road segment, they are regarded as surrounding vehicles.

[0078] Based on Preset Rules: There may be specific rules in the park that stipulate that certain types of vehicles or vehicles for certain tasks are always regarded as surrounding vehicles of each other. For example, loading and unloading vehicles and freight vehicles near the logistics center will be predefined as surrounding vehicles by the system even if they are not within the physical range.

[0079] The database combination consists of a restricted database jointly composed of the own databases of all the unmanned logistics vehicles that the target unmanned logistics vehicle interacts with information, and a public database. The database combination consists of two parts: Restricted Database: The own databases of all the unmanned logistics vehicles that the target unmanned logistics vehicle interacts with information. Each vehicle has its own status information, task information, resource usage, etc., including various dynamic data of each vehicle when performing scheduling tasks. Public Database: Contains global information that all vehicles can access, such as the road conditions of the park, real-time traffic information, environmental changes, available resources (such as the usage of charging stations or parking spaces), etc. These information can provide real-time reference for all vehicles.

[0080] Restrict database content (from the target vehicle and other vehicles that interact with it for information): Vehicle status: such as location, speed, remaining battery power, current task progress. Task information: including the target location, priority, task time window, etc. of the transportation task. Resource usage information: such as the current resource consumption status, remaining battery capacity, whether charging or maintenance is required. Historical data: the previous scheduling path of the vehicle, the success rate of task execution, the collaboration records with other vehicles, etc.

[0081] Public database content: Road conditions: such as current traffic flow, congestion, road section closures, etc. Environmental information: environmental factors such as weather conditions, temperature, humidity, etc. that affect vehicle performance. Resource availability: such as the location and availability of charging piles in the park, the number and distribution of parking spaces, etc. Infrastructure data: including road networks, restricted areas and passable areas in the park.

[0082] Step 1: Construction of the database combination. When the target unmanned logistics vehicle needs to perform path planning or adjustment, the system first identifies other unmanned logistics vehicles related to it through the information transfer mechanism. The system combines the restricted databases (vehicle status, tasks, resource information, etc.) of these vehicles and the relevant information in the public database into a comprehensive database, which contains all the information related to the scheduling of the target vehicle. The database combination can ensure that the target vehicle fully considers its own, surrounding collaborative vehicles, and environmental constraints when planning paths or tasks, forming a complete global view.

[0083] Step 2: The neural network model is a convolutional neural network model. Use a pre-trained convolutional neural network model. The convolutional neural network (CNN) model has been trained with historical data and has the ability to extract complex constraints. After the database combination is constructed, the data is input into the CNN model. Through layer-by-layer convolution and pooling operations, CNN can extract key constraints from the data, mainly including: risk assessment of vehicle task and path conflicts; impact assessment of environmental impacts (such as weather changes) on scheduling; dependency analysis of multi-vehicle collaborative tasks. The CNN model can extract key constraints from complex multi-dimensional data, helping the scheduling system quickly determine which factors need to be considered first when the target vehicle plans its path, improving the scheduling efficiency and decision-making accuracy.

[0084] Step 3: Generate a set of restrictive conditions. Through the analysis of the convolutional neural network, the system will finally synthesize the key information extracted into a "set of restrictive conditions", which covers all the restrictive factors affecting the scheduling of the target vehicle. Specifically, it includes: the passability of the current road and path risks, task urgency and priority, the availability of vehicle energy resources, and the scheduling requirements of other collaborative vehicles. The set of restrictive conditions is the core basis for optimizing the scheduling path. The system ensures that potential risks can be avoided, urgent tasks can be prioritized, and resources can be effectively utilized during vehicle scheduling according to this set, ensuring the smooth progress of collaborative work. The training process of the convolutional neural network will not be elaborated here. The convolutional neural network CNN can extract deep features from multi-dimensional data from different sources. The convolutional neural network can fuse data from different sources (such as vehicle status, task requirements, environmental changes, etc.) through a hierarchical structure to form unified restrictive conditions. This ability makes CNN highly adaptable in complex scenarios. Since there may be a large number of vehicles scheduled simultaneously in the park, the convolutional neural network can efficiently process a large amount of data, quickly extract key scheduling factors from it, reduce manual intervention and calculation latency. Therefore, a pre-trained neural network model is selected to extract restrictive features to obtain the set of restrictive conditions.

[0085] The unmanned logistics vehicles that need to interact with the target unmanned logistics vehicle are selected through interactive analysis, which refers to:

[0086] Obtain the frequency of the target unmanned logistics vehicle and the surrounding vehicle i in the past collaborative tasks and mark it as Hi, and mark the absolute value of the difference in the task priority levels of the target vehicle and vehicle i as Yi, and then substitute them into the formula:

[0087]

[0088] α and β satisfy:

[0089] Poverlap i represents the path overlap length of the target unmanned logistics vehicle and the surrounding vehicle i, that is, the part where the two vehicles drive on the same path. Toverlap i represents the time overlap interval of the target unmanned logistics vehicle and the surrounding vehicle i, that is, the time when the two vehicles overlap on the same road section. Ptotal represents the path length of the target unmanned logistics vehicle, Ttotal represents the time length of the target unmanned logistics vehicle, CNR represents the collaborative necessity index, and w1 and w2 are both preset proportional coefficients and are both non-zero, used to balance the influence of the conflict coefficient and the task historical collaboration frequency on the collaborative necessity; Ci is the conflict value measuring the potential conflict situation between the target vehicle and the surrounding vehicle;

[0090] When the cooperation necessity index CNR is greater than the preset information flow threshold, there is a need for information flow between the target unmanned logistics vehicle and the surrounding vehicle i.

[0091] Two adaptive adjustment coefficients α and β are introduced into the formula, and their influence on the cooperation necessity is dynamically adjusted according to the coincidence degree of time and path. If the time coincidence degree of two vehicles is high, it means that they may use the same path at the same time. At this time, α will be larger, increasing the influence weight of the time coincidence degree; if the path coincidence degree is higher, then β will be larger, increasing the influence of the path coincidence. Through dynamic adjustment, the influence weights of time and path on the cooperation necessity can be reasonably allocated, avoiding a single factor dominating the decision-making. Adding the conflict value can ensure that the cooperation mechanism is triggered when there is a high risk of conflict, avoiding potential conflict problems in path planning. Hi represents the cooperation history between vehicles. The higher the frequency, the richer the successful cooperation experience, and the more necessary it is to continue information flow. Yi represents the difference in task priorities. The larger the difference, the lower the urgency of cooperation. The historical cooperation frequency and priority difference directly affect the cooperation necessity, avoiding high-priority tasks being interfered by low-priority tasks and being able to process vehicles that require close cooperation more efficiently. The cooperation necessity index (CNR) is used to judge whether information flow is necessary. By calculating CNR, the system can dynamically evaluate whether it is necessary for the target vehicle to perform data interaction with certain surrounding vehicles. If CNR exceeds the set threshold, the system triggers the information flow mechanism to ensure smooth collaborative work among vehicles. Dynamically balance the time and path coincidence degree: Through the adaptive adjustment of α and β, the system can dynamically balance the influence of the time and path coincidence degree according to the actual situation, avoiding a single factor overly influencing the decision-making and improving the accuracy of the cooperation necessity judgment. The formula combines multiple factors such as conflict risk, historical cooperation experience, and task priority difference, and can intelligently judge which vehicles need to cooperate in complex vehicle scheduling scenarios, thereby improving the scheduling efficiency, avoiding unnecessary information flow, and reducing the system burden. This formula can provide accurate cooperation judgment in complex multi-vehicle cooperation scenarios, especially in high-density unmanned logistics vehicle environments such as industrial parks, with high practical value.

[0092] Using the genetic algorithm to optimize and plan the scheduling path of the target unmanned logistics vehicle based on the set of constraints and update the optimized scheduling path in the blockchain network means:

[0093] Initializing the population: The set of constraints extracted from the own databases and the public databases of all unmanned logistics vehicles that interact with the target unmanned logistics vehicle is used as the initial scheduling condition, and an initial scheduling path plan is randomly generated as the initial population for path planning. For example, assume that there are multiple unmanned logistics vehicles transporting goods in the park simultaneously. The process of initializing the population is that the system generates multiple possible initial path plans based on current traffic conditions, vehicle battery levels, road usage restrictions, etc. For example, a certain unmanned logistics vehicle may have five different feasible paths, and these paths will become candidate solutions in the initial population.

[0094] Fitness evaluation: Using the set of constraints as the constraints in fitness evaluation, and at the same time establishing a fitness evaluation formula: ZYj represents the utilization efficiency of resource type j of the target unmanned logistics vehicle, m represents the total amount of resource types of the target unmanned logistics vehicle, fj represents the preset influence coefficient corresponding to resource type j of the target unmanned logistics vehicle, and F is the fitness value. For example, assume that an unmanned logistics vehicle needs to consume electricity and use road resources when driving in the park. Fitness evaluation calculates the quality of the path based on the utilization efficiency of these resources. For example, a path that consumes less electricity and avoids peak traffic periods will have a higher fitness value. Assume that a vehicle has low power consumption and avoids congestion, its fitness value F will be higher.

[0095] Selection operation: Using the roulette wheel selection method to screen the offspring as the new parents; for example, in the process of optimizing the scheduling path, a path plan with a high fitness value (such as less power consumption and smooth traffic) is more likely to be selected as the parent of the next generation for further crossover and mutation. This is similar to the biological evolution process where individuals with high fitness have a higher probability of passing on their genes.

[0096] Crossover operation: Randomly exchange the data in different parent chromosomes; for example, assume there are two path plans. One plan performs well in the first half of the path (such as low energy consumption), and the other plan is better in the second half of the path (such as avoiding traffic peaks). Through the crossover operation, the system may generate a new path whose first half comes from the first path and the second half comes from the second path.

[0097] Mutation operation: Randomly select and adjust the data of different offspring chromosomes; for example, in the path plan, the system may randomly select a section of the path for adjustment, such as selecting an alternative route or changing the usage strategy of certain resources. If the original path passes through a congested area, the mutation operation may randomly try to bypass this area, thus possibly discovering a better path.

[0098] Iteration and termination conditions: When the pre-set termination conditions are met, the chromosome with the highest fitness is selected from the final population for decoding to obtain the optimal scheduling path plan. For example, assume that the system is preset to stop iterating when the fitness value reaches a certain threshold. If in a certain iteration, the fitness of a certain path plan has met the goal (such as minimizing energy consumption and optimizing time), then the system will terminate the optimization and select this path as the final scheduling plan.

[0099] In all optimization iterations, the chromosome with the highest fitness is decoded into the final scheduling path plan and updated to the blockchain network. By uploading the optimized scheduling path to the blockchain, data transparency and security are ensured, and it can be shared with relevant vehicles in real time when necessary. In the finally selected scheduling plan, assuming that this path plan is not only optimal in resource use, but also avoids peak traffic and has the lowest power consumption, the system will update this path to the blockchain. The genetic algorithm is used to optimize the scheduling path. Through continuous selection, crossover, and mutation operations, the system can find the optimal solution from a large number of possible path plans. This method can quickly adapt to complex scheduling environments, optimize the paths of unmanned logistics vehicles, and achieve optimality in terms of resource utilization, time cost, etc. For example, in a park scenario, assume that an unmanned logistics vehicle needs to transport goods during peak hours. The genetic algorithm can generate multiple scheduling plans based on vehicle traffic congestion and other limiting factors, and find the optimal path through multiple iterations to ensure that the task can be completed smoothly and efficiently.

[0100] Embodiment 2: An intelligent scheduling system for the passage of unmanned logistics vehicles in a park, including:

[0101] A storage module that stores all scheduling data in a decentralized blockchain network;

[0102] A scenario judgment module that connects each unmanned logistics vehicle to the blockchain network, judges the usage scenarios of each unmanned logistics vehicle, and determines whether there is a need for information transfer for the target unmanned logistics vehicle;

[0103] An interaction screening module that activates the information interaction mechanism when there is a need for information transfer for the target unmanned logistics vehicle, and screens out the unmanned logistics vehicles that need to interact with the target unmanned logistics vehicle through interaction analysis;

[0104] A feature extraction module that obtains the database combination corresponding to the information interaction from the blockchain network, and uses a pre-trained neural network model to extract restricted features based on the database combination to obtain a set of restricted conditions;

[0105] A scheduling module that uses the genetic algorithm to optimize and plan the scheduling path of the target unmanned logistics vehicle based on the set of restricted conditions and updates the optimized scheduling path in the blockchain network.

[0106] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0107] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0108] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0109] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0110] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An intelligent scheduling method for unmanned logistics vehicles to pass through a park, characterized in that, It includes the following steps: All scheduling data are stored in a decentralized blockchain network. Each unmanned logistics vehicle is connected to the blockchain network, and the usage scenarios of each unmanned logistics vehicle are judged to determine whether there is a need for information transfer for the target unmanned logistics vehicle; When there is a need for information transfer for the target unmanned logistics vehicle, the information interaction mechanism is activated, and the unmanned logistics vehicles that need to interact with the target unmanned logistics vehicle are screened out through interaction analysis. Then, the database combination corresponding to the information interaction is obtained from the blockchain network; Based on the database combination, a pre-trained neural network model is used to extract restricted features to obtain a set of restricted conditions; The genetic algorithm is used to optimize and plan the scheduling path of the target unmanned logistics vehicle based on the set of restricted conditions, and the optimized scheduling path is updated in the blockchain network; The acquisition logic of the conflict coefficient is as follows: Obtain the preset path vector and time vector of the target vehicle, and mark the path vector as , and mark the time vector as , the preset path vector corresponding to each other vehicle around is marked as , and the time vector is marked as , where i represents the number of the vehicle around the target vehicle; For each surrounding vehicle i, calculate the conflict value Ci between it and the target vehicle; ; represents the conflict value between the surrounding vehicle i and the target vehicle, and then takes the maximum value of the conflict value Ci as the conflict coefficient; The unmanned logistics vehicles that need to interact with the target unmanned logistics vehicle screened out through interaction analysis refer to: Obtain the frequency of the target unmanned logistics vehicle and surrounding vehicle i in past collaborative tasks and mark it as , the absolute value of the difference in task priority levels between the target vehicle and vehicle i and mark it as , and then substitute it into the formula: ； , Satisfy: ; ; Indicates the overlapping length of the path between the target driverless logistics vehicle and the surrounding vehicle i, Indicates the time overlapping interval between the target driverless logistics vehicle and the surrounding vehicle i, Indicates the path length of the target driverless logistics vehicle, Indicates the time length of the target driverless logistics vehicle, Indicates the cooperation necessity index, 、 are both preset proportionality coefficients and are both non-zero; When the collaboration necessity index is greater than a preset information flow threshold, there is a need for information flow between the target driverless vehicle and the surrounding vehicle i; Using the genetic algorithm to optimize and plan the scheduling path of the target unmanned logistics vehicle based on the set of restricted conditions and updating the optimized scheduling path in the blockchain network refers to: Initializing the population: The set of restricted conditions extracted from the own databases and the public database of all unmanned logistics vehicles that interact with the target unmanned logistics vehicle is used as the initial scheduling conditions, and an initial scheduling path plan is randomly generated as the initial population for path planning; Fitness evaluation: Use the set of constraints as the constraints in the fitness evaluation, and at the same time establish the fitness evaluation formula: ; represents the utilization efficiency of the resource types of the target unmanned logistics vehicle, m represents the total amount of the resource types of the target unmanned logistics vehicle, and represents the resource types of the target unmanned logistics vehicle corresponding to the preset influence coefficient, and is the fitness value; ​ Selection operation: The roulette wheel selection method is used to screen the offspring as the new parents; Crossover operation: Randomly exchange the data in different parent chromosomes; Mutation operation: Randomly select and adjust the data in different offspring chromosomes; Iteration and termination conditions: When the preset termination conditions are reached, the chromosome with the highest fitness is selected from the final population for decoding to obtain the optimal scheduling path plan.

2. The intelligent scheduling method for unmanned logistics vehicle passing in a park according to claim 1, characterized in that The decentralized blockchain network contains the respective data sets of all unmanned logistics vehicles and the public data set.

3. The intelligent scheduling method for the passage of unmanned logistics vehicles in a park according to claim 2, wherein, The usage scenarios of each unmanned logistics vehicle are judged to generate the conflict coefficient of the target unmanned logistics vehicle. The conflict coefficient is compared with the preset conflict threshold. If the conflict coefficient is greater than the preset conflict threshold, it is judged that there is a need for information transfer for the target unmanned logistics vehicle. If the conflict coefficient is less than or equal to the preset conflict threshold, it is judged that there is no need for information transfer for the target unmanned logistics vehicle.

4. The intelligent scheduling method for unmanned logistics vehicle passing in a park according to claim 3, wherein, The database combination consists of a restricted database jointly composed of the own databases of all unmanned logistics vehicles that interact with the target unmanned logistics vehicle and the public database.

5. The intelligent scheduling method for unmanned logistics vehicle passing in a park according to claim 4, wherein The neural network model is a convolutional neural network model.

6. An intelligent scheduling system for the passage of unmanned logistics vehicles in a park, which is implemented based on the intelligent scheduling method for the passage of unmanned logistics vehicles in a park according to any one of claims 1-5, characterized in that, It includes: A storage module that stores all scheduling data in a decentralized blockchain network; A scenario judgment module that connects each unmanned logistics vehicle to the blockchain network, judges the usage scenarios of each unmanned logistics vehicle, and determines whether there is a need for information transfer for the target unmanned logistics vehicle; Interactive screening module. When there is a need for information transfer in the target unmanned logistics vehicle, the information interaction mechanism is activated, and the unmanned logistics vehicles that need to interact with the target unmanned logistics vehicle are screened out through interactive analysis; Feature extraction module. Obtain the database combination corresponding to information interaction from the blockchain network. Based on the database combination, use a pre-trained neural network model to perform restricted feature extraction to obtain a set of restricted conditions; Scheduling module. Use the genetic algorithm to optimize and plan the scheduling path of the target unmanned logistics vehicle based on the set of restricted conditions and update the optimized scheduling path in the blockchain network.

Images