Multi-intelligent-vehicle material collaborative distribution method and system

Abstract

The invention discloses a multi-intelligent-vehicle material collaborative distribution method and system, and the method comprises the steps: enabling task management equipment to respond to an emergency task distribution request, obtaining a distribution task set and task information based on the emergency task distribution request, and transmitting the task information to material management equipment and all intelligent vehicles, the method comprises the steps of constructing a task matching graph based on material configuration information, task information and a task matching degree, obtaining to-be-distributed task nodes and available vehicle nodes in the task matching graph, performing node splitting on the to-be-distributed task nodes to obtain a plurality of sub-task nodes, constructing a task matching matrix based on the sub-task nodes and the available vehicle nodes, and performing task matching on the sub-task nodes and the available vehicle nodes. And determining an emergency task distribution strategy based on the task matching matrix, and sending the emergency task distribution strategy to each intelligent vehicle, so that each intelligent vehicle carries out emergency material distribution based on the emergency task distribution strategy, thereby realizing accurate distribution of tasks, improving cooperative distribution capability of the intelligent vehicles, and ensuring timeliness of material distribution.

Description

Technical Field

[0001] The present invention relates to the field of smart vehicle technology, and in particular to a method and system for collaborative material distribution using multiple smart vehicles. Background Art

[0002] With the acceleration of globalization and urbanization, emergency logistics plays an increasingly important role in responding to emergencies such as natural disasters and public health incidents. Emergency logistics tasks typically require that supplies be delivered to designated destinations in the shortest possible time and via the optimal route. This places extremely high demands on logistics management and scheduling, requiring not only precise decision-making within the shortest possible timeframe but also consideration of potential traffic changes, emergencies, and various unpredictable factors. Therefore, how to quickly and efficiently complete emergency delivery tasks within limited time and resources has become a crucial topic in modern logistics research and application. Traditional emergency logistics systems typically rely on manual scheduling and single-vehicle delivery, which often proves inefficient and slow to respond to large-scale, multi-point emergency needs. The limitations of traditional systems are particularly pronounced when dealing with a wide variety of supplies and tight delivery deadlines.

[0003] In recent years, the development of intelligent vehicle technology has brought new solutions to emergency logistics systems. By integrating advanced sensors, navigation systems, and communication technologies, intelligent vehicles can achieve autonomous navigation, real-time obstacle avoidance, and multi-vehicle collaborative operations. The application of these technologies not only improves delivery efficiency but also enhances system flexibility and reliability. However, existing multi-intelligent vehicle collaborative delivery systems suffer from a lack of dynamic adaptability in task allocation, route planning, and fault handling, as well as unrefined task allocation, inefficient route planning, insufficient obstacle avoidance, delayed fault response, and inflexible task transfer. Summary of the Invention

[0004] The main purpose of the present invention is to provide a method and system for collaborative material distribution by multiple intelligent vehicles, aiming to solve the technical problems in the existing technology of collaborative material distribution by multiple intelligent vehicles, such as lack of dynamic adaptability, unrefined task allocation, low path planning efficiency, poor delivery timeliness and delayed response.

[0005] To achieve the above objectives, the present invention provides a method for collaborative material distribution using multiple intelligent vehicles. The method is applied to a task management device, wherein the task management device is communicatively connected to a material management device and multiple intelligent vehicles. The method comprises: In response to an emergency task delivery request, obtaining a delivery task set and task information based on the emergency task delivery request, and sending the task information to the material management device and each smart vehicle, wherein the delivery task set includes at least one emergency delivery task; A task matching graph is constructed based on the material configuration information, the task information, and the task matching degree. The material configuration information is generated by the material management device after performing material configuration based on the task information. The task matching degree is the degree of matching between each smart vehicle and each emergency delivery task. The task matching graph includes task nodes, vehicle nodes, material nodes, edge weights between the task nodes and the vehicle nodes, edge weights between the material nodes and the vehicle nodes, and node states of the task nodes and the vehicle nodes. Performing a breadth-first search on the task matching graph, obtaining the to-be-delivered task nodes and available vehicle nodes in the task matching graph based on the node status, and obtaining the task required load of each to-be-delivered task node and the remaining load information of each available vehicle node; Splitting the to-be-delivered task node based on the task required load and the remaining load information to obtain a plurality of subtask nodes; Building a task matching matrix based on the subtask nodes and the available vehicle nodes; An emergency task allocation strategy is determined based on the task matching matrix, and the emergency task allocation strategy is sent to each smart car, so that each smart car performs emergency material distribution based on the emergency task allocation strategy.

[0006] Optionally, constructing a task matching matrix based on the subtask nodes and the available vehicle nodes includes: Sending a matching degree update request to each available vehicle node based on the subtask node, and obtaining the updated task matching degree sent by each available vehicle node based on the subtask node; Construct an initial matching matrix based on the updated task matching degree: in, represents the initial matching matrix, Representative tasks With vehicle The degree of task matching between Reducing the initial matching matrix to obtain a target matrix; The target matrix is adjusted based on a dynamic updating zero element strategy to obtain a task matching matrix, wherein the dynamic updating zero element strategy includes: in, is the task matching matrix obtained after adjustment, is the target matrix, is the adjustment coefficient, Used to control the adjustment range, is the minimum non-zero matching value in the target matrix.

[0007] Optionally, reducing the initial matching matrix to obtain a target matrix includes: Calculate the adaptive weight based on the adaptive weight adjustment function: in, Representative vehicle With the task The matching degree between Represents the first i The maximum matching degree in the row, represents a constant, represents adaptive weight; The initial matching matrix is reduced according to the adaptive weight to obtain a candidate matrix, and the reduction refers to the following formula: in, represents the matching degree after reduction adjustment, represents the matching degree before adjustment in the initial matching matrix; Adjust the candidate matrix based on the time window constraint to obtain the target matrix: in, Represents the matching degree after time window constraint adjustment, Representative vehicle Execute the task Estimated completion time, For the task The latest completion time specified, is the time window penalty coefficient, Used to control the degree of timeout penalty.

[0008] Optionally, determining an emergency task allocation strategy based on the task matching matrix, and sending the emergency task allocation strategy to each smart vehicle so that each smart vehicle performs emergency material distribution based on the emergency task allocation strategy, includes: A task allocation model is constructed based on the task matching matrix, and the task allocation model includes: in, Representative vehicle With the task The distribution status between Representative vehicle With the task The matching degree between Represents the set of task nodes to be delivered. Represents a set of vehicle nodes, Represents the maximum load capacity of the vehicle. Represents the load required by the task; An emergency task allocation strategy is determined according to the task allocation model, and the emergency task allocation strategy is sent to each smart car, so that each smart car performs emergency material distribution based on the emergency task allocation strategy.

[0009] In addition, to achieve the above-mentioned objectives, the present invention further proposes a multi-intelligent vehicle coordinated material distribution method, which is applied to intelligent vehicles in an intelligent vehicle cluster, wherein the intelligent vehicle cluster includes multiple intelligent vehicles, and the multiple intelligent vehicles are communicatively connected to a task management device and a material management device. The method includes: In response to the task information sent by the task management device, determine the task matching degree between itself and each emergency delivery task based on the task information; Sending the task matching degree to the task management device and monitoring a distribution message, wherein the distribution message is sent by the task management device and includes an emergency task allocation strategy; When the delivery message is received, emergency supplies are delivered based on the emergency task allocation strategy in the delivery message.

[0010] Optionally, determining the task matching degree between itself and each emergency delivery task based on the task information includes: Determine the location of the material point, the location of the task point, and the required load capacity of the task based on the task information; Determine the task matching degree between the vehicle and each emergency delivery task based on the vehicle's maximum load capacity, the location of the material point, the location of the task point, and the required load capacity of the task: in, Indicates vehicle The distance to the supply point, Indicates the distance between the material point and the mission point, Represents the maximum load capacity of the vehicle. Represents the load required by the task, is the adjustment coefficient, They are used to balance priority, driving cost and load matching respectively. is the task priority, represents the vehicle position, Represents the location of the material point, Represents the location of the mission point.

[0011] Optionally, after sending the task matching degree to the task management device, the method further includes: Monitor matching update requests; Upon receiving a matching degree update request, the task matching degree is updated based on the subtask node in the matching degree update request to obtain an updated task matching degree: in, Indicates vehicle With subtasks The matching degree between For subtasks The mission requirements load; The updated task matching degree is sent to the task management device.

[0012] Optionally, after the emergency supplies are distributed based on the emergency task allocation strategy in the distribution message, the method further includes: Based on the point cloud data collected by sensors during the distribution of emergency supplies, raster mapping is performed to construct a raster map; Determine the occupancy probability of each grid in the grid map: in, Represents a grid Likelihood of being occupied, Represents a grid Prior probability of being occupied, represents the normalization factor, Represents a grid The probability of occupation, Indicates the current sensor measurement result, Represents historical sensor measurement results; Performing a traffic analysis on the grid map based on the occupancy probability to determine a current passable area in the grid map; A topological node, a topological edge between adjacent topological nodes, and an edge weight of the topological edge are determined based on the current traversable area. The edge weight is calculated based on the following formula: in, represents the edge weight, Indicates adjacent nodes and The Euclidean distance between is the speed of the smart car, is the traffic correction factor, is the obstacle impact factor, Representation node and The accident rate of the road sections between them in the same time period, Indicates the number of accidents. Indicates the number of vehicles passing through. and represents the adjustment factor; Constructing a topological map based on the topological nodes, the topological edges, and the edge weights; Path planning is performed according to the topological map and the emergency task allocation strategy, and emergency supplies distribution is continued based on the path planning result.

[0013] Optionally, performing path planning according to the topology map and the emergency task allocation strategy includes: Determine the dynamic weight adjustment factor of the current node based on the topology map and the emergency task allocation strategy: in, represents the dynamic weight adjustment factor, and is the preset fixed parameter value, Indicates the starting point and the current node The distance between Indicates the current node The distance to the target node; Perform cost evaluation based on the dynamic weight adjustment factor to determine the total delivery cost of the current node: in, Indicates the current node n The total delivery cost, Indicates the actual cost from the starting point to the current node, Indicates the current node n The heuristic cost to the goal point; Perform global path planning based on the total delivery cost to generate an initial delivery path; The initial delivery path is smoothed to obtain a target delivery path, and path planning is performed based on the target delivery path.

[0014] In addition, to achieve the above-mentioned purpose, the present invention also proposes a multi-intelligent vehicle material collaborative distribution system, the multi-intelligent vehicle material collaborative distribution system includes a task management device, a material management device and multiple intelligent vehicles, the task management device is communicatively connected with the material management device and the multiple intelligent vehicles; The task management device is configured to respond to an emergency task delivery request, obtain a delivery task set and task information based on the emergency task delivery request, and send the task information to the material management device and each smart vehicle, wherein the delivery task set includes at least one emergency delivery task; The material management device is used to configure materials based on the task information, generate material configuration information, and send the material configuration information to the task management device; The smart car is configured to respond to the task information sent by the task management device and determine the task matching degree between itself and each emergency delivery task based on the task information; The smart car is further configured to send the task matching degree to the task management device and monitor a delivery message, wherein the delivery message is sent by the task management device and includes an emergency task allocation strategy; The task management device is further configured to construct a task matching graph based on material configuration information, task information, and task matching degree, wherein the material configuration information is generated by the material management device after performing material configuration based on the task information, and the task matching degree is the degree of matching between each smart vehicle and each emergency delivery task. The task matching graph includes task nodes, vehicle nodes, material nodes, edge weights between the task nodes and the vehicle nodes, edge weights between the material nodes and the vehicle nodes, and node states of the task nodes and the vehicle nodes. The task management device is further configured to perform a breadth-first search on the task matching graph, obtain the to-be-delivered task nodes and available vehicle nodes in the task matching graph based on the node status, and obtain the task required load capacity of each to-be-delivered task node and the remaining load capacity information of each available vehicle node; The task management device is further configured to split the to-be-delivered task node based on the task required load and the remaining load information to obtain a plurality of subtask nodes; The task management device is further configured to construct a task matching matrix based on the subtask nodes and the available vehicle nodes; The task management device is further configured to determine an emergency task allocation strategy based on the task matching matrix, and send the emergency task allocation strategy to each smart vehicle, so that each smart vehicle performs emergency material distribution based on the emergency task allocation strategy; The smart car is further configured to deliver emergency supplies based on the emergency task allocation strategy in the delivery message when the delivery message is received.

[0015] In addition, to achieve the above-mentioned purpose, the present application also proposes a task management device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the multi-intelligent vehicle material collaborative distribution method as described above.

[0016] In addition, to achieve the above-mentioned purpose, the present application also proposes an intelligent vehicle, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the multi-intelligent vehicle collaborative material distribution method as described above.

[0017] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the multi-intelligent vehicle material collaborative distribution method as described above are implemented.

[0018] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the multi-intelligent vehicle material collaborative distribution method as described above.

[0019] The present invention responds to the emergency task distribution request through the task management device, obtains the distribution task set and task information based on the emergency task distribution request, and sends the task information to the material management device and each smart car, the distribution task set includes at least one emergency distribution task; the material management device performs material configuration based on the task information, generates material configuration information, and sends the material configuration information to the task management device; the smart car responds to the task information sent by the task management device, determines the task matching degree between itself and each emergency distribution task based on the task information, sends the task matching degree to the task management device, and monitors the distribution message, the distribution message is sent by the task management device, and the distribution message includes the emergency task allocation strategy; the task management device constructs a task matching graph based on the material configuration information, the task information and the task matching degree, the material configuration information is generated by the material management device after performing material configuration based on the task information, the task matching degree is the matching degree between each smart car and each emergency distribution task, and the task matching graph includes task nodes, vehicle nodes, material nodes, edge weights between the task nodes and the vehicle nodes, and the edge weights between the material nodes and the vehicle nodes. The edge weights between nodes and the node states of the task nodes and the vehicle nodes are used to perform a breadth-first search on the task matching graph. Based on the node states, the to-be-delivered task nodes and available vehicle nodes in the task matching graph are obtained, and the task required load of each to-be-delivered task node and the remaining load information of each available vehicle node are obtained. The to-be-delivered task node is split based on the task required load and the remaining load information to obtain multiple subtask nodes. A task matching matrix is constructed based on the subtask nodes and the available vehicle nodes. An emergency task allocation strategy is determined based on the task matching matrix, and the emergency task allocation strategy is sent to each smart car so that each smart car distributes emergency materials based on the emergency task allocation strategy. When the smart car receives the distribution message, it distributes emergency materials based on the emergency task allocation strategy in the distribution message. Since the present invention splits the distribution task into multiple subtasks, constructs a matching matrix based on the subtasks, and distributes tasks based on the matching matrix, it realizes the refined distribution of distribution tasks, ensures the rationality of task distribution, and performs path planning based on the emergency task allocation strategy, thereby improving the collaborative distribution capability of the smart car and ensuring the timeliness of emergency material distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0021] Figure 1 This is a schematic diagram of the structure of a multi-intelligent vehicle material collaborative distribution device in the hardware operating environment involved in an embodiment of the present invention; Figure 2 This is a flow chart of an embodiment of a method for collaborative material distribution using multiple intelligent vehicles according to the present invention; Figure 3 This is a flow chart of an embodiment of a method for collaborative material distribution using multiple intelligent vehicles according to the present invention; Figure 4 This is a flow chart of intelligent vehicle path planning in an embodiment of the method for coordinated material distribution by multiple intelligent vehicles of the present invention; Figure 5 This is a structural block diagram of an embodiment of the multi-intelligent vehicle material collaborative distribution system of the present invention.

[0022] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0023] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0024] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a multi-intelligent vehicle collaborative material distribution device in the hardware operating environment involved in the embodiment of the present invention.

[0025] like Figure 1 As shown, the multi-intelligent vehicle coordinated material distribution device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display and an input unit such as a keyboard. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a wireless fidelity (WI-FI) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also be a storage system independent of the processor 1001.

[0026] Those skilled in the art will understand that Figure 1The structure shown in the figure does not constitute a limitation on the multi-intelligent vehicle material collaborative distribution equipment, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0027] like Figure 1 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and a multi-intelligent vehicle material collaborative distribution program.

[0028] exist Figure 1 In the multi-intelligent vehicle material collaborative distribution device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the multi-intelligent vehicle material collaborative distribution device of the present invention can be set in the multi-intelligent vehicle material collaborative distribution device, and the multi-intelligent vehicle material collaborative distribution device calls the multi-intelligent vehicle material collaborative distribution program stored in the memory 1005 through the processor 1001, and executes the multi-intelligent vehicle material collaborative distribution method provided by the embodiment of the present invention.

[0029] The embodiment of the present invention provides a method for collaborative material distribution by multiple intelligent vehicles. Figure 2 , Figure 2 This is a flow chart of an embodiment of a method for collaborative material distribution using multiple intelligent vehicles according to the present invention.

[0030] In this embodiment, the multi-intelligent vehicle material collaborative distribution method is applied to a task management device, the task management device is communicatively connected with a material management device and multiple intelligent vehicles, and the multi-intelligent vehicle material collaborative distribution method includes the following steps: Step S10: In response to the emergency task delivery request, a delivery task set and task information are obtained based on the emergency task delivery request, and the task information is sent to the material management device and each smart vehicle.

[0031] In some embodiments, the material management device is responsible for assembling materials for the smart car, calculating the remaining amount of materials for delivery, and finally feeding back the results to the task management device. After receiving a new task, the smart car calculates the matching degree between the task and the vehicle based on its own status, and feeds back the result to the task management device. The task management device constructs a task-vehicle-material point matching graph and uses the improved Hungarian algorithm to perform efficient task allocation, and finally broadcasts the task allocation results. During the delivery process, the smart car combines hybrid map construction and improved The algorithm performs path planning, while also incorporating virtual potential fields and virtual impedance models to ensure local obstacle avoidance and dynamic path adjustment. If a smart vehicle malfunctions, the system triggers an early warning mechanism on the emergency management side. Based on the priority scores of task transfer and support vehicles, the optimal task transfer and support vehicles are automatically selected, ensuring that the faulty vehicle receives prompt support and can continue its delivery mission.

[0032] It should be understood that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a computer, or a terminal electronic device capable of implementing the above functions. The following describes this embodiment and the following embodiments using a task management device as an example.

[0033] It should be noted that the delivery task set includes at least one emergency delivery task, which can be a material delivery task for emergency logistics. The task information may include the delivery destination, required material type, material quantity, delivery time limit, and other specific requirements (such as storage temperature requirements and special loading and unloading requirements).

[0034] In some embodiments, after receiving a task request (a task request is a request sent by the task management device to the material management device based on the task information), the material management device begins to prepare and dispatch materials. The material management device will check whether there are sufficient materials in the existing inventory to complete the delivery based on the task requirements. If the inventory is sufficient, the material management device will further confirm the type, specifications and quantity of the materials to ensure that they meet the delivery requirements. If the inventory is insufficient, the material management device will issue a replenishment request to the supplier or other warehouse to ensure that the execution of the task is not affected by material shortages. When the materials are confirmed to be sufficient, the material management device will pre-sort and package them. Once all materials are assembled, the material management device will send a material preparation completion message to the task management device and provide a detailed material list and assembly information, including material type, quantity, weight, etc., to prepare for the next task allocation.

[0035] Step S20: Constructing a task matching graph based on the material configuration information, task information, and task matching degree.

[0036] It should be noted that the material configuration information is generated by the material management device after configuring materials based on the task information. The task matching degree is the degree of matching between each smart vehicle and each emergency delivery task. The task matching graph includes task nodes, vehicle nodes, material nodes, edge weights between the task nodes and the vehicle nodes, edge weights between the material nodes and the vehicle nodes, and the node states of the task nodes and the vehicle nodes. Among them, the above-mentioned task nodes represent emergency delivery tasks, the above-mentioned vehicle nodes represent smart vehicles, and the above-mentioned material nodes represent material points.

[0037] It should be noted that the above-mentioned node status includes the node status of the task node and the node status of the vehicle node. For example, two node statuses can be set. For the task node, 1 indicates that the task has been assigned and is being distributed, and 0 indicates that the task is to be assigned; for the vehicle node, 1 indicates that the vehicle has reached the maximum load, and 0 indicates that the vehicle has not reached the maximum load.

[0038] It is understandable that after the task management device sends the task information to the material management device, it monitors the material preparation completion message, and when receiving the material preparation completion message, obtains the material configuration information based on the material preparation completion message.

[0039] It should be understood that after the task management device sends task information to each smart car, it monitors the task matching degree sent by the smart car and constructs a task matching graph based on the task matching degree, material configuration information and task information sent by each smart car.

[0040] In some embodiments, the task management device performs task allocation. First, a task-vehicle-material point matching graph is constructed to define the task nodes. , vehicle node , material point node Each task corresponds to a material point, and the edge weight between the task node and the material point node represents the quantity of materials required for the task; each vehicle may have multiple delivery tasks, that is, each vehicle may correspond to multiple material nodes and task nodes. Need to go to the supply point To collect supplies, build a vehicle and supply points The edge weight represents the vehicle The transportation cost from the current location to the material point; if the vehicle Delivery tasks required , then create a vehicle With the task The edge weight represents the matching degree between the vehicle and the task. Two node states are set: for the task node, 1 indicates that the task has been assigned and is being delivered, and 0 indicates that the task is waiting to be assigned; for the vehicle node, 1 indicates that the vehicle has reached the maximum load, and 0 indicates that the vehicle has not reached the maximum load.

[0041] Step S30: Perform a breadth-first search on the task matching graph, obtain the task nodes to be delivered and the available vehicle nodes in the task matching graph based on the node status, and obtain the task required load of each task node to be delivered and the remaining load information of each available vehicle node.

[0042] It should be noted that the task node to be delivered can be a task node with a node status of 0 (i.e., a task that requires the allocation of a vehicle for delivery); the available vehicle node can be a vehicle node with a node status of 0 (i.e., a vehicle that has not reached the maximum load).

[0043] It is understandable that the task management device uses breadth-first search to search for all task nodes and vehicle nodes with status 0 in the task-vehicle-material point matching graph. Assume there are m task nodes and n vehicle nodes. If a task A single smart car in the vehicle node can complete the delivery, and the car will be assigned to the task first. If the task The amount of materials required for delivery Exceeds the current remaining load of any vehicle in set V , the task is split and completed by multiple vehicles.

[0044] Step S40: Split the task node to be delivered based on the task required load and the remaining load information to obtain multiple subtask nodes.

[0045] It should be noted that the task management device can classify each task node to be delivered and determine the first task node and the second task node, where the first task node is a task node that does not require splitting the task (that is, the task node that can be delivered by a single smart car), and the second task node is a task node that needs to be split (that is, the task node that requires collaborative delivery by multiple smart cars).

[0046] In some embodiments, the task management device may directly match the first task node with an available vehicle node that meets the task load requirements (or may directly match based on the matching degree feedback from the smart car), split the second task node into multiple subtask nodes, obtain the updated matching degree of the smart car for the subtask node, and assign tasks to the subtask nodes based on the updated matching degree.

[0047] It is understandable that the task management device can determine the task nodes to be delivered based on the task required load and the remaining load information of each available vehicle node. The minimum number of vehicles required is as follows: Split into Subtasks: The task Split into Subtasks, the materials for each subtask are: The task-vehicle allocation will form a matching matrix, and the matching degree will be adjusted according to the new sub-task distribution material requirements. Therefore, in some embodiments, the task management device sends the sub-task node to each available vehicle node so that the smart car can update the matching degree and determine the matching degree between each available vehicle node and the sub-task node.

[0048] Step S50: constructing a task matching matrix based on the subtask nodes and the available vehicle nodes.

[0049] It should be noted that the matching degree between the intelligent vehicle calculation of each available vehicle node and the subtask node , to complete the update of the matching degree, and feed back the matching degree update result to each task management device, and the task management device constructs a matching matrix based on the updated matching degree.

[0050] Furthermore, in order to accurately construct the task matching matrix, in some embodiments, step S50 may include: Step S501: sending a matching degree update request to each available vehicle node based on the subtask node, and obtaining the updated task matching degree sent by each available vehicle node based on the subtask node; Step S502: constructing an initial matching matrix based on the updated task matching degree; Step S503: reducing the initial matching matrix to obtain a target matrix; Step S504: adjusting the target matrix based on the dynamic update zero element strategy to obtain a task matching matrix.

[0051] It should be noted that the matching degree between the intelligent vehicle calculation of each available vehicle node and the subtask node , to complete the update of the matching degree, and feed back the matching degree update result to each task management device. The task management device constructs the following matching matrix based on the updated matching degree: in, represents the initial matching matrix, Representative tasks With vehicle The matching degree between tasks.

[0052] It should be noted that after completing row reduction and column reduction, it is checked whether there are enough zero elements to match the task. If the matching is complete, the process ends directly. If not, the dynamic update of zero elements strategy is executed to gradually reduce non-zero elements. The dynamic update of zero elements strategy includes: in, is the task matching matrix obtained after adjustment, is the target matrix, is the adjustment coefficient, Used to control the adjustment range, such as The value can be 0.5, is the minimum non-zero matching value in the target matrix.

[0053] In some embodiments, the task management device adjusts the target matrix based on the dynamic update zero element strategy to obtain a task matching matrix, which can be a binary matrix X ,in, Represents a subtask Assigned to vehicle , Represents a subtask Not assigned to a vehicle , and calculate the actual amount of materials each smart car bears: If a vehicle's load exceeds its maximum load , the vehicle only retains the maximum load it can bear , overload Assign to other vehicles. Traverse all currently available vehicles. If a vehicle There is still enough remaining load , then directly assign to Otherwise, it will be split twice. After the task allocation is completed, the split subtask nodes are added to the task-vehicle-material point matching graph, and the status of the task node and vehicle node are updated.

[0054] Furthermore, in order to effectively avoid matching imbalance and improve matching accuracy, in some embodiments, step S503 may include: Step S5031: Calculating adaptive weights based on an adaptive weight adjustment function; Step S5032: reducing the initial matching matrix according to the adaptive weight to obtain a candidate matrix; Step S5033: Adjust the candidate matrix based on the time window constraint to obtain a target matrix.

[0055] In some embodiments, the task management device may use a modified Hungarian algorithm on the initial matching matrix, with the following modifications: Introducing adaptive weight adjustment function during row reduction ,The tasks with larger matching degree will have less impact on the adjustment, while the tasks with smaller matching degree will be adjusted more significantly, reducing the possible mismatching, adaptive weight adjustment function Refer to the following formula: in, Representative vehicle With the task The matching degree between Represents the first i The maximum matching degree in the row, represents a constant, Represents adaptive weight.

[0056] To ensure that during reduction, task allocation still tends to select tasks with higher matching degrees while taking into account tasks with lower matching degrees to avoid matching imbalance, the improved formula for row reduction is as follows: in, represents the matching degree after reduction adjustment, Represents the matching degree before adjustment in the initial matching matrix.

[0057] In some embodiments, the matching degree is adjusted using a time window constraint. Vehicles that can complete tasks within the specified time window are given priority. For tasks that are completed overtime, their matching degree is lowered to reduce the probability of being selected. The matching degree is adjusted using the time window constraint condition according to the following formula: in, Represents the matching degree after time window constraint adjustment, Representative vehicle Execute the task Estimated completion time, For the task The latest completion time specified, is the time window penalty coefficient, Used to control the degree of timeout penalty.

[0058] Step S60: determining an emergency task allocation strategy based on the task matching matrix, and sending the emergency task allocation strategy to each smart car, so that each smart car performs emergency material distribution based on the emergency task allocation strategy.

[0059] In some embodiments, when a single new task appears When there are vehicles with remaining load, calculate the vehicles with remaining load and the new task The matching degree between Sort vehicles in descending order: in, W The amount of materials required to be delivered to each vehicle, To update the remaining amount of materials required for distribution. If all vehicles with the current remaining load have not been allocated, , or when a new task appears and there is no remaining load vehicle, compare the priority of the new task with the task set in the vehicle, assuming that the vehicle The current task set is , the priority of the vehicle is: .

[0060] If the new task priority is less than the priority of the task set in the vehicle, wait for an idle vehicle; if the new task priority is less than the priority of the task set in the vehicle, wait for an idle vehicle; Larger than some vehicles Calculate the matching degree between these free vehicles and new tasks , sort the vehicles by the matching degree, and allocate the maximum load of materials required for the new task to each vehicle until all the materials required for the new task are allocated.

[0061] vehicle The assigned vehicles immediately return to the nearest supply point, unload all supplies, and carry out new tasks.

[0062] When another or more emergency events occur, multiple tasks are added. Add it to the set of tasks to be assigned T and update the task-vehicle-material point matching graph. Use breadth-first search to search for all vehicle nodes with status 0 in the task-vehicle-material point matching graph. Based on the amount of materials required for each task and the vehicle status, decide whether to use a single vehicle or multiple vehicles. If multiple vehicles are used, calculate the new task according to the task matching degree calculation formula in step 12. The matching degree between these vehicles is calculated, a matching matrix is constructed, and the improved Hungarian algorithm is used to calculate the optimal task-vehicle matching.

[0063] After the task is successfully completed, the task management device deletes the task node in the task-vehicle-material point matching graph, cancels all vehicles related to the completed task, and updates the vehicle status.

[0064] In some embodiments, in order to improve the efficiency of task allocation and enhance the rationality of collaborative delivery, the above step S60 may include: Step S601: constructing a task allocation model based on the task matching matrix; Step S602: determining an emergency task allocation strategy according to the task allocation model, and sending the emergency task allocation strategy to each smart car, so that each smart car performs emergency material distribution based on the emergency task allocation strategy.

[0065] It should be noted that in emergency logistics scenarios, an emergency typically requires a variety of different supplies, meaning there will be multiple assignments at the same time. Assuming T is the set of tasks to be assigned and V is the set of vehicles that have not yet reached their maximum load, the task assignment problem can be defined as a task assignment model, which includes: in, Representative vehicle With the task The distribution status between Representative vehicle With the task The matching degree between Represents the set of task nodes to be delivered. Represents a set of vehicle nodes, Represents the maximum load capacity of the vehicle. Represents the load required by the task.

[0066] This embodiment responds to an emergency task delivery request, obtains a delivery task set and task information based on the emergency task delivery request, and sends the task information to a material management device and each smart car, wherein the delivery task set includes at least one emergency delivery task; constructs a task matching graph based on material configuration information, task information and task matching degree, wherein the material configuration information is generated by the material management device after performing material configuration based on the task information, and the task matching degree is the degree of matching between each smart car and each emergency delivery task; the task matching graph includes task nodes, vehicle nodes, material nodes, edge weights between the task nodes and the vehicle nodes, edge weights between the material nodes and the vehicle nodes, and node states of the task nodes and the vehicle nodes; performs a breadth-first search on the task matching graph, Based on the node status, the to-be-delivered task nodes and available vehicle nodes in the task matching graph are obtained, and the task requirement load of each to-be-delivered task node and the remaining load information of each available vehicle node are obtained; based on the task requirement load and the remaining load information, the to-be-delivered task nodes are split to obtain multiple subtask nodes; a task matching matrix is constructed based on the subtask nodes and the available vehicle nodes; an emergency task allocation strategy is determined based on the task matching matrix, and the emergency task allocation strategy is sent to each smart car, so that each smart car performs emergency material distribution based on the emergency task allocation strategy, thereby realizing refined distribution of distribution tasks, ensuring the rationality of task allocation, and performing path planning based on the emergency task allocation strategy, thereby improving the collaborative distribution capability of smart cars and ensuring the timeliness of emergency material distribution.

[0067] refer to Figure 3 , Figure 3 This is a flow chart of an embodiment of a method for collaborative material distribution using multiple intelligent vehicles according to the present invention.

[0068] In this embodiment, the multi-intelligent vehicle material collaborative distribution method is applied to intelligent vehicles in an intelligent vehicle cluster, wherein the intelligent vehicle cluster includes multiple intelligent vehicles, and the multiple intelligent vehicles are communicatively connected to a task management device and a material management device. The method includes: Step S1: In response to the task information sent by the task management device, determine the task matching degree between itself and each emergency delivery task based on the task information.

[0069] It is understandable that the smart car calculates the degree of matching between itself and the new task based on its current situation and feeds the matching result back to the task management device.

[0070] In some embodiments, the smart car calculates the matching degree between the vehicle and the task based on the task priority (which changes over time), the vehicle driving cost, and the maximum load (or remaining load) of the vehicle.

[0071] Furthermore, in order to accurately calculate the task matching degree, in some embodiments, the above step S1 may include: Step S11: Determine the material point location, the task point location, and the task required load based on the task information; Step S12: Determine the task matching degree between the vehicle itself and each emergency delivery task based on the maximum load capacity of the vehicle, the location of the material point, the location of the task point and the required load capacity of the task.

[0072] It should be noted that the smart car can be based on the location of material points, the location of task points, and the priority of tasks. (varies over time) and vehicle travel costs Calculate the matching degree between vehicle and task , the calculation formula is as follows: in, Indicates vehicle The distance to the supply point, Indicates the distance between the material point and the mission point, Represents the maximum load capacity of the vehicle. Represents the load required by the task, is the adjustment coefficient, They are used to balance priority, driving cost and load matching respectively. is the task priority, Represents the vehicle position, Represents the location of the material point, Represents the location of the mission point.

[0073] Step S2: Send the task matching degree to the task management device and monitor the delivery message.

[0074] It should be noted that the delivery message is sent by the task management device and includes an emergency task allocation policy. Upon receiving the delivery message, the smart vehicle determines that the task management device has completed task allocation, determines the target task based on the emergency task allocation policy, and proceeds to the material management device to load materials based on the target task before delivering the materials.

[0075] Furthermore, in order to accurately calculate the matching degree between the task and the subtask, thereby updating the task matching degree, in some embodiments, after sending the task matching degree to the task management device, the method further includes: Step S21: monitoring matching degree update request; Step S22: upon receiving a matching degree update request, updating the task matching degree based on the subtask node in the matching degree update request to obtain an updated task matching degree; Step S23: Sending the updated task matching degree to the task management device.

[0076] In some embodiments, the task management device Split into subtasks, and the materials for each subtask are , the task-vehicle allocation will form a matching matrix, and the matching degree will be adjusted according to the new subtask distribution material requirements. The calculation formula is: in, Indicates vehicle With subtasks The matching degree between For subtasks The task requires load.

[0077] Step S3: upon receiving the delivery message, emergency supplies are delivered based on the emergency task allocation strategy in the delivery message.

[0078] It should be noted that the matching degree update request is sent by the task management device. After the task management device splits the second task node (that is, the task that requires collaborative delivery of multiple smart cars) into multiple subtasks, the smart car needs to recalculate the task matching degree between the subtasks, so as to reasonably formulate a collaborative delivery plan for the subtasks.

[0079] In some embodiments, a smart vehicle assigned to a mission first assembles supplies at a supply point and then delivers them to the mission point. The smart vehicle collects environmental data using LiDAR, GPS+IMU, and cameras. Using occupancy grid mapping, the point cloud data is converted into a grid map for detecting obstacles and traversable areas. Simultaneously, based on road connectivity analysis, a topological map is constructed, and weights for road segments are defined for global path search. Global planning utilizes an improved heuristic search algorithm, combined with a dynamic weight adjustment factor and curvature-constrained B-spline curves, to optimize and smooth the path. Local planning uses a virtual potential field model to guide the smart vehicle along the global path. A virtual attraction field guides the vehicle toward the target, a virtual repulsion field avoids obstacles, and a virtual navigation field adjusts the path based on traffic information. Furthermore, a virtual impedance model further stabilizes the smart vehicle's motion and performs dynamic obstacle avoidance adjustments. The entire process combines global path planning with local dynamic obstacle avoidance strategies to ensure the smart vehicle can efficiently and smoothly complete its mission in complex environments.

[0080] Furthermore, in order to improve the transportation efficiency of smart vehicles, improve the accuracy of transportation routes and obstacle avoidance capabilities, refer to Figure 4 , Figure 4FIG. 5 is a flow chart of path planning for an intelligent vehicle in one embodiment. In some embodiments, after step S3, the following steps are further included: Step S4: Perform raster mapping based on the point cloud data collected by sensors during the emergency supplies distribution process to construct a raster map.

[0081] In some embodiments, the smart car uses LiDAR to obtain point cloud data and obtains obstacle information based on this point cloud data. GPS and IMU are used to obtain vehicle location information. Cameras are used to assist in detecting traversable areas. Occupancy grid mapping is used to convert the point cloud data into a grid map for precise local obstacle avoidance.

[0082] Step S5: Determine the occupancy probability of each grid in the grid map.

[0083] It should be noted that in order to accurately analyze the traversable area in the grid map, the smart car can calculate the occupancy probability of each grid in the grid map, referring to the following formula: in, Represents a grid Likelihood of being occupied, Represents a grid Prior probability of being occupied, represents the normalization factor, Represents a grid The probability of occupation, Indicates the current sensor measurement result, Represents historical sensor measurements.

[0084] In some embodiments, if a grid If the occupancy probability is greater than 0.7, it is set as an obstacle M(x,y)=1; otherwise, it is set as a passable area M(x,y)=0.

[0085] Step S6: performing a traffic analysis on the grid map based on the occupancy probability to determine a current passable area in the grid map.

[0086] In some embodiments, the smart car may perform neighborhood traversal on the grid map based on the occupancy probability, analyze the passable direction of the current node, detect key intersections (T-shaped, cross intersections, etc.), and determine the current passable area in the grid map based on the key intersections, material points, and mission points.

[0087] Step S7: determining topological nodes, topological edges between adjacent topological nodes, and edge weights of the topological edges according to the current traversable area.

[0088] It should be noted that the edge weight is calculated based on the following formula: in, represents the edge weight, Indicates adjacent nodes and The Euclidean distance between is the speed of the smart car, is the traffic correction factor, is the obstacle impact factor, Representation node and The accident rate of the road sections between them in the same time period, Indicates the number of accidents. Indicates the number of vehicles passing through. and Indicates the adjustment factor.

[0089] In some embodiments, the traffic correction factor is determined based on the road congestion state, with a value of 1.0 for no congestion, 0.7 for light congestion, and 0.5 for heavy congestion. The obstacle factor is 0 for no obstruction, 1 for light obstruction, and 5 for complete obstruction.

[0090] Step S8: constructing a topological map based on the topological nodes, the topological edges, and the edge weights.

[0091] It should be noted that the smart car uses key intersections, material points and task points as nodes V of the topological map. Based on road connectivity analysis, topological edges E between adjacent nodes are established. The edge weight represents the cost of moving from adjacent node i to node j. The topological map thus constructed is Used for global planning and efficient search of global paths.

[0092] Step S9: performing path planning according to the topological map and the emergency task allocation strategy, and continuing emergency material distribution based on the path planning result.

[0093] In some embodiments, the smart car can use improved The algorithm calculates the globally optimal path from the starting point to the end point.

[0094] Furthermore, in order to accurately perform path planning, in some embodiments, the above step S9 may include: Step S91: determining a dynamic weight adjustment factor of a current node based on the topology map and the emergency task allocation strategy; Step S92: performing cost evaluation based on the dynamic weight adjustment factor to determine the total delivery cost of the current node; Step S93: performing global path planning based on the total delivery cost to generate an initial delivery path; Step S94: Smoothing the initial delivery path to obtain a target delivery path, and performing path planning based on the target delivery path.

[0095] It should be noted that the smart car can use the improved The algorithm calculates the global optimal path from the starting point to the end point, The algorithm is a heuristic search algorithm commonly used in path planning. To enhance the adaptability of the algorithm, this embodiment introduces a dynamic weight adjustment factor , according to the current stage of the path, the search should be accelerated near the starting point; near the target point, the overestimation of the path cost should be reduced. The core of the algorithm is the evaluation function , which consists of two parts: actual cost and heuristic cost.

[0096] The dynamic weight adjustment factor calculation formula is as follows: in, represents the dynamic weight adjustment factor, and It is a preset fixed parameter value, which depends on factors such as the complexity of the environment, the dynamic characteristics of the smart car, and the smoothness of the path. It needs to be determined through actual application results. Indicates the starting point and the current node The distance between Indicates the current node The distance to the target node.

[0097] Evaluation Function The calculation formula is as follows: in, Indicates the current node n The total delivery cost, Indicates the actual cost from the starting point to the current node, Indicates the current node n The heuristic cost to reach the goal point.

[0098] In some embodiments, the smart car may introduce a curvature-constrained B-spline curve to smooth the path. The B-spline path is defined as follows: The curvature is calculated according to the following formula: in, Represents the path control point, represents the B-spline basis function, represents the curvature, if Exceeding the threshold , the path control points are automatically adjusted to limit the steering angle of the smart car and improve driving stability.

[0099] In some embodiments, the smart car can perform a local planning algorithm design. The virtual potential field is a guidance method based on attraction and repulsion, including a virtual attraction field and a virtual repulsion field, and further combined with a virtual navigation field. The virtual attraction field is used to guide the smart car along the global path. This embodiment introduces dynamic attraction and adjusts it according to the accuracy of path tracking. Assuming the target position is , the attractive potential energy calculation formula is and the gravitational force calculation formula are respectively: in, is the base attraction constant, To adjust the parameters, is the maximum target distance, is the distance from the current point to the target.

[0100] The virtual repulsion field is used to avoid obstacles. The repulsion force constant is adjusted to be dynamic and is adjusted based on the occupancy status of each grid in the grid map and the distance between the smart car and the obstacle. As the smart car approaches the obstacle, the repulsion force of the obstacle increases. The formula for calculating the repulsion force of the obstacle is: in, refers to obstacles, is the distance from the current point to the obstacle, is the base repulsive force constant, To affect the distance threshold, is the regulating factor, is the parameter that controls the rate of deceleration of the repulsive force, is the grid map influence factor, local grid is the rectangular area within the perception range of the smart car, is the weight of each grid point, Indicates the degree of influence of the grid map influence factor on the repulsive potential energy, Indicates the degree of influence of the grid map influence factor on the repulsive force.

[0101] The virtual navigation field provides navigation guidance based on traffic regulations and road data. This field can influence route selection based on external inputs, such as traffic flow data. Furthermore, if a smart car detects traffic congestion on a particular road section, it transmits this information to other smart cars via V2X communication. Upon receiving this notification, other vehicles can recalculate their routes to avoid the congested area.

[0102] in, For location Road i The guiding force on Indicates the vehicle position, Indicates location The navigation force at the place, which is the sum of all road navigation forces, Indicates the number of roads.

[0103] The final total virtual force is the sum of the attractive force, the repulsive force, and the navigation force: in, For location The total virtual force at is the sum of attraction, repulsion and navigation force. Indicates location The attraction of represents the number of repulsive force sources, Indicates location Place The repulsive force of a repulsive force source.

[0104] By simulating a virtual spring-damper-inertia system, the present invention proposes a virtual impedance model, which enables the smart car to smoothly follow the global path in a complex environment and perform dynamic obstacle avoidance adjustments.

[0105] In virtual impedance control, the motion of the smart car is constrained by the following dynamic equation constraint formula: in, is the current actual position of the smart car, and is the current speed and acceleration of the smart car, is the desired trajectory, usually provided by the global planning path, and are the velocity and acceleration of the desired trajectory, is the calculated virtual total force, virtual inertia matrix , virtual damping matrix , virtual elastic matrix They are all diagonal matrices, with the upper left corner representing the value in the x-axis direction and the lower right corner representing the value in the y-axis direction.

[0106] By transforming the constraint formula of the dynamic equation, the actual acceleration calculation formula of the smart car is: Update the speed and final trajectory of the smart car through integration: In some embodiments, each smart car is equipped with a variety of sensors (such as temperature sensor, oil pressure sensor, battery level sensor, speed sensor, etc.) to collect various operating status data of the car in real time, including the real-time speed of the car. , battery level , oil pressure , engine temperature The data are analyzed in real time and the threshold method is used to detect anomalies. , assuming its normal range is .

[0107] Perform the above detection on each sensor data and define a fault detection signal , the calculation formula is: Where n is the number of sensors, Indicates whether each sensor detects an abnormality. When a threshold k is reached, the vehicle is considered faulty, triggering a fault response mechanism. Once the fault response mechanism is triggered, the original vehicle stops operating due to the fault, and the original load task needs to be transferred to another vehicle, a process known as task transfer. Furthermore, an idle vehicle is selected to assist the faulty vehicle. This is assumed to involve a hook between smart vehicles, helping to tow the vehicle back to base or a repair station.

[0108] For task transfer, if there are currently remaining load vehicles, assuming that the maximum load of the remaining load vehicles is , the original load of the faulty vehicle is L, if , then all vehicles with a remaining load exceeding L are regarded as candidate task transfer vehicles, and the priority scores are calculated according to the priority scoring formula, and finally the vehicle with the highest score is selected as the task transfer vehicle. Calculate the priority score according to the priority scoring formula, sort them in descending order, and allocate the materials with the largest remaining load to each vehicle until all the materials on the original load vehicle of the faulty vehicle are transferred. The priority scoring formula is as follows: in, It's a vehicle With a broken-down car The distance between It's a vehicle The remaining load capacity, It's a vehicle The current load, It's a vehicle Available time, are all weight coefficients.

[0109] If there are no remaining loaded vehicles, compare the priorities of the faulty vehicle and the load task sets of other vehicles. If the priority of the faulty vehicle is lower than that of other vehicles, wait; if the priority of the faulty vehicle exceeds that of some vehicles, seize the vehicle with the lowest priority among the exceeded vehicles, and that vehicle immediately returns to the nearest material point to unload the materials and go to the faulty vehicle to transfer the task with the faulty vehicle.

[0110] For assisted towing, calculate the priority scores between other vehicles and the disabled vehicle, and select the vehicle with the highest score as the assisted towing vehicle, referring to the following formula: in, It's a vehicle energy status, are all weight coefficients.

[0111] This embodiment responds to the task information sent by the task management device, determines the task matching degree between itself and each emergency distribution task based on the task information, sends the task matching degree to the task management device, and monitors the distribution message. The distribution message is sent by the task management device, and the distribution message includes an emergency task allocation strategy. When the distribution message is received, emergency materials are distributed based on the emergency task allocation strategy in the distribution message, thereby ensuring that the smart car reasonably distributes the material transportation tasks that match itself, improving the collaborative distribution efficiency of the smart car, ensuring that the emergency materials can be quickly transported to the target location, and effectively improving the responsiveness of the emergency material transportation.

[0112] In addition, to achieve the above-mentioned purpose, the present application also proposes a task management device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the multi-intelligent vehicle material collaborative distribution method as described above.

[0113] In addition, to achieve the above-mentioned purpose, the present application also proposes an intelligent vehicle, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the multi-intelligent vehicle collaborative material distribution method as described above.

[0114] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, which stores a multi-intelligent vehicle material collaborative distribution program. When the multi-intelligent vehicle material collaborative distribution program is executed by a processor, the steps of the multi-intelligent vehicle material collaborative distribution method described above are implemented.

[0115] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0116] The computer-readable storage medium may be included in the multi-intelligent vehicle coordinated material distribution device; or it may exist independently without being assembled into the multi-intelligent vehicle coordinated material distribution device.

[0117] In addition, an embodiment of the present invention further provides a computer program product, including a multi-intelligent vehicle material collaborative distribution program, which, when executed by a processor, implements the steps of the multi-intelligent vehicle material collaborative distribution method described above.

[0118] The specific implementation of the computer program product of the present invention is basically the same as the various embodiments of the above-mentioned multi-intelligent vehicle material collaborative distribution method, and will not be repeated here.

[0119] Reference Figure 5 , Figure 5 This is a structural block diagram of an embodiment of the multi-intelligent vehicle material collaborative distribution system of the present invention.

[0120] like Figure 5 As shown, the multi-intelligent vehicle material collaborative distribution system proposed in an embodiment of the present invention includes a task management device 10, a material management device 20 and multiple intelligent vehicles 30, and the task management device 10 is communicatively connected with the material management device 20 and the multiple intelligent vehicles 30; The task management device 10 is configured to respond to an emergency task delivery request, obtain a delivery task set and task information based on the emergency task delivery request, and send the task information to the material management device and each smart vehicle, wherein the delivery task set includes at least one emergency delivery task; The material management device 20 is used to configure materials based on the task information, generate material configuration information, and send the material configuration information to the task management device; The smart car 30 is configured to respond to the task information sent by the task management device and determine the task matching degree between itself and each emergency delivery task based on the task information; The smart car 30 is further configured to send the task matching degree to the task management device and monitor the delivery message, wherein the delivery message is sent by the task management device and includes an emergency task allocation strategy; The task management device 10 is further configured to construct a task matching graph based on material configuration information, task information, and task matching degree, wherein the material configuration information is generated by the material management device after performing material configuration based on the task information, and the task matching degree is the degree of matching between each smart vehicle and each emergency delivery task. The task matching graph includes task nodes, vehicle nodes, material nodes, edge weights between the task nodes and the vehicle nodes, edge weights between the material nodes and the vehicle nodes, and node states of the task nodes and the vehicle nodes. The task management device 10 is further configured to perform a breadth-first search on the task matching graph, obtain the to-be-delivered task nodes and available vehicle nodes in the task matching graph based on the node status, and obtain the task required load of each to-be-delivered task node and the remaining load information of each available vehicle node; The task management device 10 is further configured to split the to-be-delivered task node based on the task required load and the remaining load information to obtain a plurality of subtask nodes; The task management device 10 is further configured to construct a task matching matrix based on the subtask nodes and the available vehicle nodes; The task management device 10 is further configured to determine an emergency task allocation strategy based on the task matching matrix, and send the emergency task allocation strategy to each smart vehicle, so that each smart vehicle performs emergency material distribution based on the emergency task allocation strategy; The smart car 30 is further configured to deliver emergency supplies based on the emergency task allocation strategy in the delivery message when the delivery message is received.

[0121] In this embodiment, a task management device responds to an emergency task distribution request, obtains a distribution task set and task information based on the emergency task distribution request, and sends the task information to a material management device and each smart car, wherein the distribution task set includes at least one emergency distribution task; the material management device performs material configuration based on the task information, generates material configuration information, and sends the material configuration information to the task management device; the smart car responds to the task information sent by the task management device, determines the task matching degree between itself and each emergency distribution task based on the task information, sends the task matching degree to the task management device, and monitors the distribution message, which is sent by the task management device and includes an emergency task allocation strategy; the task management device constructs a task matching graph based on the material configuration information, the task information and the task matching degree, wherein the material configuration information is generated by the material management device after performing material configuration based on the task information, and the task matching degree is the matching degree between each smart car and each emergency distribution task, and the task matching graph includes task nodes, vehicle nodes, material nodes, edge weights between the task nodes and the vehicle nodes, and the edge weights between the material nodes and the vehicle nodes. The edge weights between nodes and the node states of the task nodes and the vehicle nodes are used to perform a breadth-first search on the task matching graph. Based on the node states, the to-be-delivered task nodes and available vehicle nodes in the task matching graph are obtained, and the task required load of each to-be-delivered task node and the remaining load information of each available vehicle node are obtained. The to-be-delivered task node is split based on the task required load and the remaining load information to obtain multiple subtask nodes. A task matching matrix is constructed based on the subtask nodes and the available vehicle nodes. An emergency task allocation strategy is determined based on the task matching matrix, and the emergency task allocation strategy is sent to each smart car so that each smart car distributes emergency supplies based on the emergency task allocation strategy. When the smart car receives the distribution message, it distributes emergency supplies based on the emergency task allocation strategy in the distribution message. Since this embodiment splits the distribution task into multiple subtasks, constructs a matching matrix based on the subtasks, and distributes tasks based on the matching matrix, it realizes refined distribution of distribution tasks, ensures the rationality of task distribution, and performs path planning based on the emergency task allocation strategy, thereby improving the collaborative distribution capability of the smart car and ensuring the timeliness of emergency supply distribution.

[0122] The multi-intelligent vehicle coordinated material distribution system provided in this application utilizes the multi-intelligent vehicle coordinated material distribution method described in the aforementioned embodiment, and can resolve the technical issues associated with multi-intelligent vehicle coordinated material distribution. Compared to the prior art, the multi-intelligent vehicle coordinated material distribution system provided in this application has the same beneficial effects as the multi-intelligent vehicle coordinated material distribution method described in the aforementioned embodiment, and the other technical features of the multi-intelligent vehicle coordinated material distribution system are the same as those disclosed in the aforementioned embodiment, and are not further elaborated here.

[0123] It should be understood that the above is only an example and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any limitation on this.

[0124] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0125] In addition, for technical details not fully described in this embodiment, please refer to the multi-intelligent vehicle material collaborative distribution method provided in any embodiment of the present invention, and will not be repeated here.

[0126] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0127] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0128] Through the above description of the embodiments, those skilled in the art will clearly understand that the above-mentioned embodiments and methods can be implemented by means of software plus the necessary general-purpose hardware platform. Of course, hardware can also be used, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, a magnetic disk, or an optical disk) and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0129] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A multi-intelligent vehicle material collaborative distribution method, characterized in that: The multi-intelligent vehicle material collaborative distribution method is applied to a task management device, wherein the task management device is in communication with a material management device and multiple intelligent vehicles. The multi-intelligent vehicle material collaborative distribution method includes: In response to an emergency task delivery request, obtaining a delivery task set and task information based on the emergency task delivery request, and sending the task information to the material management device and each smart vehicle, wherein the delivery task set includes at least one emergency delivery task; A task matching graph is constructed based on the material configuration information, the task information, and the task matching degree. The material configuration information is generated by the material management device after performing material configuration based on the task information. The task matching degree is the degree of matching between each smart vehicle and each emergency delivery task. The task matching graph includes task nodes, vehicle nodes, material nodes, edge weights between the task nodes and the vehicle nodes, edge weights between the material nodes and the vehicle nodes, and node states of the task nodes and the vehicle nodes. Performing a breadth-first search on the task matching graph, obtaining the to-be-delivered task nodes and available vehicle nodes in the task matching graph based on the node status, and obtaining the task required load of each to-be-delivered task node and the remaining load information of each available vehicle node; Splitting the to-be-delivered task node based on the task required load and the remaining load information to obtain a plurality of subtask nodes; Building a task matching matrix based on the subtask nodes and the available vehicle nodes; An emergency task allocation strategy is determined based on the task matching matrix, and the emergency task allocation strategy is sent to each smart car, so that each smart car performs emergency material distribution based on the emergency task allocation strategy.

2. The multi-intelligent vehicle coordinated material distribution method according to claim 1, characterized in that: The constructing a task matching matrix based on the subtask nodes and the available vehicle nodes includes: Sending a matching degree update request to each available vehicle node based on the subtask node, and obtaining the updated task matching degree sent by each available vehicle node based on the subtask node; Construct an initial matching matrix based on the updated task matching degree: in, represents the initial matching matrix, Representative tasks With vehicle The degree of task matching between Reducing the initial matching matrix to obtain a target matrix; The target matrix is adjusted based on a dynamic updating zero element strategy to obtain a task matching matrix, wherein the dynamic updating zero element strategy includes: in, is the task matching matrix obtained after adjustment, is the target matrix, is the adjustment coefficient, Used to control the adjustment range, is the minimum non-zero matching value in the target matrix.

3. The multi-intelligent vehicle coordinated material distribution method according to claim 2, characterized in that: The reducing the initial matching matrix to obtain a target matrix includes: Calculate the adaptive weight based on the adaptive weight adjustment function: in, Representative vehicle With the task The matching degree between Represents the first i The maximum matching degree in the row, represents a constant, represents adaptive weight; The initial matching matrix is reduced according to the adaptive weight to obtain a candidate matrix, and the reduction refers to the following formula: in, represents the matching degree after reduction adjustment, represents the matching degree before adjustment in the initial matching matrix; Adjust the candidate matrix based on the time window constraint to obtain the target matrix: in, Represents the matching degree after time window constraint adjustment, Representative vehicle Execute the task Estimated completion time, For the task The latest completion time specified, is the time window penalty coefficient, Used to control the degree of timeout penalty.

4. The multi-intelligent vehicle coordinated material distribution method according to any one of claims 1 to 3, characterized in that: The step of determining an emergency task allocation strategy based on the task matching matrix and sending the emergency task allocation strategy to each smart vehicle so that each smart vehicle performs emergency material distribution based on the emergency task allocation strategy includes: A task allocation model is constructed based on the task matching matrix, and the task allocation model includes: in, Representative vehicle With the task The distribution status between Representative vehicle With the task The matching degree between Represents the set of task nodes to be delivered. Represents a set of vehicle nodes, Represents the maximum load capacity of the vehicle. Represents the load required by the task; An emergency task allocation strategy is determined according to the task allocation model, and the emergency task allocation strategy is sent to each smart car, so that each smart car performs emergency material distribution based on the emergency task allocation strategy.

5. A collaborative material distribution method using multiple intelligent vehicles, characterized in that: The multi-intelligent vehicle material collaborative distribution method is applied to intelligent vehicles in an intelligent vehicle cluster, wherein the intelligent vehicle cluster includes multiple intelligent vehicles, and the multiple intelligent vehicles are communicatively connected with a task management device and a material management device. The method includes: In response to the task information sent by the task management device, determine the task matching degree between itself and each emergency delivery task based on the task information; Sending the task matching degree to the task management device and monitoring a distribution message, wherein the distribution message is sent by the task management device and includes an emergency task allocation strategy; When the delivery message is received, emergency supplies are delivered based on the emergency task allocation strategy in the delivery message.

6. The multi-intelligent vehicle coordinated material distribution method according to claim 5, characterized in that: The determining of the task matching degree between the task itself and each emergency delivery task based on the task information includes: Determine the location of the material point, the location of the task point, and the required load capacity of the task based on the task information; Determine the task matching degree between the vehicle and each emergency delivery task based on the vehicle's maximum load capacity, the location of the material point, the location of the task point, and the required load capacity of the task: in, Indicates vehicle The distance to the supply point, Indicates the distance between the material point and the mission point, Represents the maximum load capacity of the vehicle. Represents the load required by the task, is the adjustment coefficient, They are used to balance priority, driving cost and load matching respectively. is the task priority, represents the vehicle position, Represents the location of the material point, Represents the location of the mission point.

7. The multi-intelligent vehicle coordinated material distribution method according to claim 6, characterized in that: After sending the task matching degree to the task management device, the method further includes: Monitor matching update requests; Upon receiving a matching degree update request, the task matching degree is updated based on the subtask node in the matching degree update request to obtain an updated task matching degree: in, Indicates vehicle With subtasks The matching degree between For subtasks The mission requirements load; The updated task matching degree is sent to the task management device.

8. The multi-intelligent vehicle coordinated material distribution method according to any one of claims 5 to 7, characterized in that: After the emergency supplies are distributed based on the emergency task allocation strategy in the distribution message, the method further includes: Based on the point cloud data collected by sensors during the distribution of emergency supplies, raster mapping is performed to construct a raster map; Determine the occupancy probability of each grid in the grid map: in, Represents a grid Likelihood of being occupied, Represents a grid Prior probability of being occupied, represents the normalization factor, Represents a grid The probability of occupation, Indicates the current sensor measurement result, Represents historical sensor measurement results; Performing a traffic analysis on the grid map based on the occupancy probability to determine a current passable area in the grid map; A topological node, a topological edge between adjacent topological nodes, and an edge weight of the topological edge are determined based on the current traversable area. The edge weight is calculated based on the following formula: in, represents the edge weight, Indicates adjacent nodes and The Euclidean distance between is the speed of the smart car, is the traffic correction factor, is the obstacle impact factor, Representation node and The accident rate of the road sections between them in the same time period, Indicates the number of accidents. Indicates the number of vehicles passing through. and represents the adjustment factor; Constructing a topological map based on the topological nodes, the topological edges, and the edge weights; Path planning is performed according to the topological map and the emergency task allocation strategy, and emergency supplies distribution is continued based on the path planning result.

9. The multi-intelligent vehicle coordinated material distribution method according to claim 8, characterized in that: The performing path planning according to the topological map and the emergency task allocation strategy includes: Determine the dynamic weight adjustment factor of the current node based on the topology map and the emergency task allocation strategy: in, represents the dynamic weight adjustment factor, and is the preset fixed parameter value, Indicates the starting point and the current node The distance between Indicates the current node The distance to the target node; Perform cost evaluation based on the dynamic weight adjustment factor to determine the total delivery cost of the current node: in, Indicates the current node n The total delivery cost, Indicates the actual cost from the starting point to the current node, Indicates the current node n The heuristic cost to the goal point; Perform global path planning based on the total delivery cost to generate an initial delivery path; The initial delivery path is smoothed to obtain a target delivery path, and path planning is performed based on the target delivery path.

10. A multi-intelligent vehicle material collaborative distribution system, characterized in that: The multi-intelligent vehicle material collaborative distribution system includes a task management device, a material management device, and multiple intelligent vehicles, wherein the task management device is in communication with the material management device and the multiple intelligent vehicles; The task management device is configured to respond to an emergency task delivery request, obtain a delivery task set and task information based on the emergency task delivery request, and send the task information to the material management device and each smart vehicle, wherein the delivery task set includes at least one emergency delivery task; The material management device is used to configure materials based on the task information, generate material configuration information, and send the material configuration information to the task management device; The smart car is configured to respond to the task information sent by the task management device and determine the task matching degree between itself and each emergency delivery task based on the task information; The smart car is further configured to send the task matching degree to the task management device and monitor a delivery message, wherein the delivery message is sent by the task management device and includes an emergency task allocation strategy; The task management device is further configured to construct a task matching graph based on material configuration information, task information, and task matching degree, wherein the material configuration information is generated by the material management device after performing material configuration based on the task information, and the task matching degree is the degree of matching between each smart vehicle and each emergency delivery task. The task matching graph includes task nodes, vehicle nodes, material nodes, edge weights between the task nodes and the vehicle nodes, edge weights between the material nodes and the vehicle nodes, and node states of the task nodes and the vehicle nodes. The task management device is further configured to perform a breadth-first search on the task matching graph, obtain the to-be-delivered task nodes and available vehicle nodes in the task matching graph based on the node status, and obtain the task required load capacity of each to-be-delivered task node and the remaining load capacity information of each available vehicle node; The task management device is further configured to split the to-be-delivered task node based on the task required load and the remaining load information to obtain a plurality of subtask nodes; The task management device is further configured to construct a task matching matrix based on the subtask nodes and the available vehicle nodes; The task management device is further configured to determine an emergency task allocation strategy based on the task matching matrix, and send the emergency task allocation strategy to each smart vehicle, so that each smart vehicle performs emergency material distribution based on the emergency task allocation strategy; The smart car is further configured to deliver emergency supplies based on the emergency task allocation strategy in the delivery message when the delivery message is received.

Images