Autonomous vending vehicle collaborative control method, platform and autonomous vending vehicle

Abstract

This invention relates to a method, platform, and autonomous vending vehicle for collaborative control. The method includes monitoring real-time status data of vehicles within a target area, identifying collaborative events requiring multi-vehicle collaboration and / or receiving collaboration requests, and generating standardized collaborative event instructions. In response to the collaborative event instructions, multiple candidate collaborative strategies are generated. The multiple candidate collaborative strategies are then simulated and evaluated to determine and execute the optimal collaborative strategy. This method, by monitoring real-time status data of vehicles within a target area, identifying collaborative events requiring multi-vehicle collaboration, and / or receiving collaboration requests, generating standardized collaborative event instructions, and dynamically scheduling relevant autonomous vending vehicles based on these instructions, achieves remote control and scheduling of autonomous vending vehicles, improves the intelligent management level of autonomous vending vehicles, reduces the number of times personnel need to go to the site, and saves time and costs.

Description

Technical Field

[0001] This invention relates to the field of vending vehicle technology, and in particular to a collaborative control method, platform, and autonomous vending vehicle for autonomous driving. Background Technology

[0002] With the development of technologies such as 5G communication, vehicle-to-everything (V2X) communication, and autonomous driving, the integration of driverless vehicles with commercial retail has become a new application hotspot. In many public places, such as scenic spots, autonomous intelligent connected commercial vehicles have begun to serve users. For example, users only need to wave their hands in front of the driverless vending vehicle, and the vehicle will automatically stop. Users can then select the goods they need and complete their purchase independently. The driverless vending vehicle will continue to move within a designated area, meeting users' purchasing needs anytime, anywhere, greatly facilitating people's daily lives.

[0003] However, current autonomous vending vehicles in public places are simply a combination of driverless vehicles and vending machines. The main management method still relies on manual on-site inspections, which is inefficient and has high operating costs. Summary of the Invention

[0004] This invention provides a collaborative control method, platform, and autonomous vending vehicle for autonomous vending vehicles, in order to overcome at least one of the aforementioned technical problems existing in the prior art.

[0005] To achieve the above objectives, the embodiments of the present invention adopt the following technical solutions: In a first aspect, the present invention provides a collaborative control method for an autonomous vending vehicle, comprising: Monitor real-time status data of vehicles within the target area and construct a global status data view, wherein the vehicles include a cluster of autonomous vending vehicles within the target area; Analyze the global state data view to identify collaborative events that require multi-vehicle collaborative processing, and / or receive collaborative requests to generate standardized collaborative event instructions; In response to the collaborative event command, multiple candidate collaborative strategies are generated based on the global state data view and preset collaborative strategy generation rules; The candidate collaborative strategies are simulated and evaluated to determine the optimal collaborative strategy. Based on the optimal coordination strategy, a coordination task is assigned to the coordination vehicle executing the optimal coordination strategy, and a target driving path corresponding to the coordination task is planned for the coordination vehicle, so that the coordination vehicle completes the coordination task based on the target driving path.

[0006] In one possible implementation of the first aspect, the analysis of the global state data view, identification of collaborative events requiring multi-vehicle collaborative processing, and / or receipt of collaborative requests, and generation of standardized collaborative event instructions, includes: The real-time status data of the vehicle is matched with preset event triggering rules. If the match is successful, an initial collaborative event identifier is generated. Based on the initial collaborative event identifier, related features are extracted from the global status data view. The related features include related status data related to a specific operational event represented by the initial collaborative event identifier. Based on the associated features, the event category corresponding to the initial collaborative event identifier is determined, and the processing priority of the initial collaborative event identifier is divided according to the preset priority division rules; Based on the event category and the processing priority, a standardized collaborative event instruction containing the complete collaborative event is generated.

[0007] In one possible implementation of the first aspect, in response to the collaborative event instruction, multiple candidate collaborative strategies are generated based on the global state data view and preset collaborative strategy generation rules, including: The collaborative event command is analyzed to determine the core elements and target area of ​​the event corresponding to the collaborative event command. Based on the core elements of the event and the target area of ​​the event, potential collaborative vehicles that are in an effective state and can participate in collaboration are selected from the global status data view to form a candidate vehicle set; Based on the various cooperative combinations of potential cooperative vehicles in the candidate vehicle set, multiple logically feasible cooperative strategies are enumerated. Based on hard constraints, the cooperative strategy is filtered to obtain multiple candidate cooperative strategies.

[0008] In one possible implementation of the first aspect, the step of filtering potential collaborative vehicles that are in an effective state and capable of participating in collaboration from the global state data view based on the core elements of the event and the target area of ​​the event, forming a candidate vehicle set, includes: Based on the core elements of the event and the target area of ​​the event, set the filtering radius and status filtering conditions; From the global state data view, find vehicles that are within the filtering radius and meet the state filtering conditions, and identify them as potential cooperative vehicles; All the potential cooperative vehicles are aggregated to form the candidate vehicle set.

[0009] In one possible implementation of the first aspect, the hard constraints include at least one of vehicle state, task compatibility, and resource constraints. The step of filtering the cooperative strategy based on the hard constraints to obtain multiple candidate cooperative strategies includes: Obtain real-time status information that affects the execution of the collaboration strategy for each potential collaborative vehicle in the candidate vehicle set. The real-time status information includes at least one of vehicle location, current task status, cargo capacity, and energy status. Determine whether the planned action of each potential cooperating vehicle in the candidate vehicle set conflicts with its real-time status information in the cooperative strategy. By summarizing multiple collaborative strategies that do not conflict with the planned actions and the real-time status information, multiple candidate collaborative strategies are obtained.

[0010] In one possible implementation of the first aspect, the step of simulating and evaluating multiple candidate cooperative strategies to determine the optimal cooperative strategy includes: For each of the candidate collaborative strategies, the estimated spatiotemporal trajectory of each of the potential collaborative vehicles involved in the simulation strategy execution process is calculated, and the estimated resource consumption of each of the potential collaborative vehicles is calculated. The estimated resource consumption includes the estimated vehicle loss and the estimated total execution time of the candidate collaborative strategy. Based on the estimated spatiotemporal trajectory and the estimated resource consumption, evaluate the impact of at least two of the following indicators: total operational benefits, overall system efficiency, total scheduling cost, and average waiting time corresponding to the execution of each candidate collaborative strategy; Based on preset weights, at least two of the following indicators—total operating revenue, overall system efficiency impact, total scheduling cost, and average waiting time—are weighted and fused to obtain a comprehensive utility evaluation value for each candidate collaborative strategy. The candidate collaborative strategy with the highest comprehensive utility evaluation value is selected as the optimal collaborative strategy.

[0011] In one possible implementation of the first aspect, after assigning a cooperative task to the cooperative vehicle executing the optimal cooperative strategy and planning a target driving path corresponding to the cooperative task for the cooperative vehicle, the method further includes: Continuously acquire dynamic motion status information of vehicles awaiting replenishment, including real-time location information and predicted trajectory information within a preset future time period; The dynamic motion status information of the vehicle to be replenished is synchronized to the cooperating vehicle that performs the replenishment task corresponding to the vehicle to be replenished, so that the cooperating vehicle can dynamically adjust its driving path according to the dynamic motion status information.

[0012] In one possible implementation of the first aspect, after assigning a cooperative task to the cooperative vehicle executing the optimal cooperative strategy and planning a target driving path corresponding to the cooperative task for the cooperative vehicle, the method further includes: The execution status of the collaborative task is acquired in real time, including the operating status of the collaborative vehicle; In the event of an execution anomaly in the execution state, the optimal coordination strategy is re-evaluated to obtain the re-evaluation result; Based on the reassessment results, the task allocation of the collaborative task or the driving path of the collaborative vehicle is dynamically adjusted.

[0013] Compared with the prior art, the present invention has at least the following beneficial effects: The present invention provides a collaborative control method for autonomous vending vehicles. By monitoring the real-time status data of vehicles in a target area, identifying collaborative events that require multi-vehicle collaborative processing, and / or receiving collaborative requests, generating standardized collaborative event instructions, and dynamically scheduling relevant autonomous vending vehicles based on the collaborative event instructions, the method realizes remote control and scheduling of autonomous vending vehicles, improves the intelligent management level of autonomous vending vehicles, reduces the number of times personnel need to go to the site, and saves time and costs.

[0014] Secondly, this invention provides a collaborative control platform for autonomous vending vehicles, including... The monitoring module is used to monitor the real-time status data of vehicles within the target area and build a global status data view, wherein the vehicles include a cluster of autonomous vending vehicles within the target area; The collaborative event triggering module is used to analyze the global status data view, identify collaborative events that require multi-vehicle collaborative processing, and / or receive collaborative requests and generate standardized collaborative event instructions. The collaboration strategy construction module is used to respond to the collaboration event command and generate multiple candidate collaboration strategies based on the global state data view and preset collaboration strategy generation rules. The collaborative strategy evaluation module is used to simulate and evaluate the multiple candidate collaborative strategies respectively, and determine the optimal collaborative strategy. The collaborative strategy execution module is used to assign collaborative tasks to collaborative vehicles that execute the optimal collaborative strategy based on the optimal collaborative strategy, and to plan the target driving path corresponding to the collaborative task for the collaborative vehicle, so that the collaborative vehicle completes the collaborative task based on the target driving path.

[0015] Thirdly, the present invention provides an electronic device comprising: at least one processor and at least one memory, wherein the memory stores computer-readable instructions; the computer-readable instructions are executed by one or more of the processors, causing the electronic device to implement the collaborative control method for an autonomous vending vehicle as described in any implementation of the first aspect.

[0016] Fourthly, the present invention provides a storage medium having a computer-executable program stored thereon, the computer-executable program being used to cause a computer to execute the collaborative control method for an autonomous vending vehicle as described in any implementation of the first aspect.

[0017] Understandably, the beneficial effects achieved by the system of the second aspect, the electronic device of the third aspect, and the storage medium of the fourth aspect provided above can be referred to in light of the beneficial effects of the first aspect and any of its possible design embodiments, which will not be repeated here.

[0018] Fifthly, the present invention provides an autonomous driving vending vehicle, comprising: A communication module is used to communicate with the autonomous driving vending vehicle collaborative control platform as described in claim 9; The data acquisition module is used to collect real-time status data of the autonomous vending vehicle; The control module is configured to receive a target driving path transmitted by the autonomous driving vending vehicle collaborative control platform and control the autonomous driving vending vehicle to perform autonomous driving according to the target driving path; and to receive a remote assisted driving command transmitted by the autonomous driving vending vehicle collaborative control platform and control the autonomous driving vending vehicle to perform remote assisted driving according to the remote assisted driving command. The communication module is a dual-link communication module. The first link is used to transmit the target driving path and the real-time status data of the autonomous vending vehicle during autonomous driving. The second link is used to transmit the remote assisted driving command and the real-time status data of the autonomous vending vehicle during remote assisted driving.

[0019] The autonomous vending vehicle provided by this invention adopts a dual-link communication architecture. One link is dedicated to the transmission of autonomous driving-related data, and the other link is used for the interaction of information required for remote driving. This ensures that autonomous driving and remote driving functions do not interfere with each other, improves the efficiency and accuracy of information transmission, and ensures that the vehicle can respond quickly to commands under various circumstances. Moreover, the dual-link communication architecture enhances the system's fault tolerance. When one link fails, the other link can still maintain some functions, preventing the autonomous vending vehicle from losing control due to communication interruption. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention; Figure 2 A flowchart illustrating a collaborative control method for an autonomous vending vehicle provided in an embodiment of the present invention; Figure 3 A structural block diagram of a collaborative control platform for an autonomous vending vehicle provided in an embodiment of the present invention; Figure 4 This is a structural schematic diagram of an autonomous vending vehicle provided in an embodiment of the present invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be described below with reference to the accompanying drawings. In the description of the present invention, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. The "or" in the present invention is merely a description of the relationship between the related objects, indicating that three relationships can exist. For example, A or B can represent: A alone, A and B simultaneously, and B alone. A and B can be singular or plural. Furthermore, in the description of the present invention, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items.

[0023] Furthermore, to facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0024] In this embodiment of the invention, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this embodiment of the invention should not be construed as superior or more advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0025] With the development of technologies such as 5G communication, vehicle-to-everything (V2X) communication, and autonomous driving, the integration of driverless vehicles with commercial retail has become a new application hotspot. In many public places, such as scenic spots, autonomous intelligent connected commercial vehicles have begun to serve users. For example, users only need to wave their hand in front of the driverless vending vehicle, and the vehicle will automatically stop, allowing users to select the goods they need and complete their purchase independently. The driverless vending vehicle will then continue to move within a designated area, meeting users' purchasing needs anytime, anywhere, greatly facilitating people's daily lives. However, current public place autonomous vending vehicles are simply a combination of driverless vehicles and vending machines, and the main management method still relies on manual on-site inspections, which is inefficient and has high operating costs.

[0026] In view of this, on the one hand, embodiments of the present invention provide a method for collaborative control of autonomous vending vehicles, comprising: monitoring real-time status data of vehicles within a target area, constructing a global status data view, wherein the vehicles include a cluster of autonomous vending vehicles within the target area; analyzing the global status data view, identifying collaborative events requiring multi-vehicle collaborative processing, and / or receiving collaborative requests, and generating standardized collaborative event instructions; responding to the collaborative event instructions, generating multiple candidate collaborative strategies according to the global status data view and preset collaborative strategy generation rules; simulating and evaluating the multiple candidate collaborative strategies respectively, and determining the optimal collaborative strategy; based on the optimal collaborative strategy, assigning collaborative tasks to the collaborative vehicles executing the optimal collaborative strategy, and planning a target driving path corresponding to the collaborative task for the collaborative vehicles, so that the collaborative vehicles complete the collaborative task based on the target driving path.

[0027] The present invention provides a method for the collaborative control of autonomous vending vehicles. By monitoring the real-time status data of vehicles within a target area, identifying collaborative events requiring multi-vehicle collaborative processing, and / or receiving collaborative requests, generating standardized collaborative event instructions, and dynamically scheduling relevant autonomous vending vehicles based on the collaborative event instructions, the method realizes remote control and scheduling of autonomous vending vehicles, improves the intelligent management level of autonomous vending vehicles, reduces the number of times personnel need to go to the site, and saves time and costs.

[0028] In some embodiments, the collaborative control method for an autonomous vending vehicle provided by the present invention can be executed by any electronic device 20 with data processing capabilities, such as a general-purpose computer, personal computer, laptop computer, switch, or tablet computer, etc. The specific implementation of the electronic device 20 is not limited here.

[0029] Figure 1A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention is shown. The electronic device 20 includes a processor 210, a memory 220, and a communication interface 230.

[0030] Processor 210 may include one or more processing cores. Processor 210 connects to various parts within electronic device 200 using various interfaces and lines, and performs various functions and processes data of electronic device 200 by running or executing instructions, programs, code sets, or instruction sets stored in memory 220, and by calling data stored in memory 220. Optionally, processor 210 may be implemented using at least one of the following hardware forms: Central Processing Unit (CPU), Graphics Processing Unit (GPU), Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA).

[0031] The memory 220 may include random access memory (RAM) or read-only memory (ROM). Optionally, the memory 220 may include a non-transitory computer-readable storage medium. The memory 220 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 220 may include a program storage area. This program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the various method embodiments described above, etc.

[0032] Communication interface 230 is used to communicate with other devices, equipment or communication networks, such as data storage devices, image processing devices or Ethernet, wireless access network (RAN), wireless local area network (WLAN), etc.

[0033] In terms of physical implementation, the aforementioned devices (such as processor 210, memory 220, and communication interface 230) can each be devices within the same device (such as a laptop computer). Alternatively, at least two of these devices can be located within the same device, i.e., as different devices within the same device, similar to the deployment of devices or components in a distributed system.

[0034] It is understood that the structure illustrated in this embodiment does not constitute a specific limitation on the electronic device 20. In other embodiments of the present invention, the electronic device 20 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0035] The following description, in conjunction with the accompanying drawings, illustrates a collaborative control method for an autonomous vending vehicle provided by an embodiment of the present invention.

[0036] like Figure 2 As shown, this embodiment of the invention provides a collaborative control method for autonomous vending vehicles, which may include, but is not limited to: S1: Monitor the real-time status data of vehicles within the target area and construct a global status data view, wherein the vehicles include a cluster of autonomous vending vehicles within the target area.

[0037] In specific implementation, each autonomous vending vehicle is equipped with a data acquisition unit and a data transmission unit. The data acquisition unit collects real-time status data during its operation. The real-time status data may include, but is not limited to, vehicle ID, GPS location, speed, inventory status of each product, current task, battery level, etc., which are not limited here.

[0038] In specific implementation, the global state data view in this embodiment of the invention may be, but is not limited to, a global state data table, which is dynamically updated autonomously according to the changes in the real-time state data.

[0039] S2: Analyze the global state data view, identify collaborative events that require multi-vehicle collaborative processing, and / or receive collaborative requests, and generate standardized collaborative event instructions.

[0040] In one feasible implementation, the analysis of the global state data view, identification of collaborative events requiring multi-vehicle collaborative processing, and / or receipt of collaborative requests, and generation of standardized collaborative event instructions in this embodiment of the invention may include, but is not limited to: The real-time status data of the vehicle is matched with preset event triggering rules. If the match is successful, an initial collaborative event identifier is generated. Based on the initial collaborative event identifier, related features are extracted from the global status data view. The related features include related status data related to a specific operational event represented by the initial collaborative event identifier. Based on the associated features, the event category corresponding to the initial collaborative event identifier is determined, and the processing priority of the initial collaborative event identifier is divided according to the preset priority division rules; Based on the event category and the processing priority, a standardized collaborative event instruction containing the complete collaborative event is generated.

[0041] In specific implementation, the preset event triggering rules in this embodiment define what constitutes an "event" that needs attention. These preset event triggering rules may include, but are not limited to: State threshold rules: Content: Monitor whether specific indicators of a single vehicle's status exceed a threshold, such as: "The inventory of product X for vehicle A has been 0 for more than 30 seconds."

[0042] Triggering result: An initial "Out of Stock Collaboration Event" identifier is generated.

[0043] Timing pattern rules: Content: Identify a specific sequence of states over time. For example: "Within region Z, the inventory of goods Y for three consecutive vehicles is below 20%."

[0044] Triggering result: Generates an initial "Regional Stockout Warning Event" flag, indicating that proactive restocking may be necessary.

[0045] External event association rules: Content: Associate vehicle status with external information. For example: "Vehicle B has been in 'remote assistance' mode for more than 2 minutes, and its location has remained unchanged."

[0046] Triggering result: Generate an initial "Single vehicle struggling to get out of trouble, requiring coordinated rescue event" flag.

[0047] It should be noted that the "remote assistance" mode in this embodiment of the invention refers to remote assistance performed when an autonomous vending vehicle is found to be stuck, and may specifically include, but is not limited to: Obtain vehicle pose data and environmental data of the trapped autonomous vending vehicle; Extract key obstacle features from the environmental data; Based on the key obstacle features and the vehicle body pose data, an escape path is generated; Remote assisted driving commands are generated based on the escape path and transmitted to the stranded autonomous vending vehicle.

[0048] This invention acquires the vehicle posture data and environmental data of a stuck autonomous vending vehicle, then generates an escape path based on the vehicle posture data and environmental data, and generates remote assisted driving commands based on the escape path to help the stuck autonomous vending vehicle get out of trouble. This enables the stuck autonomous vending vehicle to quickly get rid of obstacles and resume operation, reducing human intervention and lowering operating costs.

[0049] In the specific implementation process, the remote assistance can be initiated when a remote assistance request is received from the stranded autonomous vending vehicle, or it can be initiated proactively by analyzing the real-time status data of the autonomous vending vehicle. No limitation is made here.

[0050] In the specific implementation process, after obtaining the key obstacle features and the vehicle body posture data, the embodiments of the present invention can autonomously generate multiple escape paths. Then, the remote monitoring operator, based on their own experience, makes a judgment and selects a suitable path to generate remote assisted driving commands, thereby improving the probability of escaping difficulties.

[0051] In specific implementation, the associated features in this embodiment of the invention include associated status data related to the specific operational event represented by the initial collaborative event identifier. For example, for a "vehicle A out of stock" event, the system will immediately perform an associated query: (1) The location, inventory and mission status of all other vehicles within 500 meters of vehicle A.

[0052] (2) Heat map of the inventory distribution of out-of-stock goods in vehicle A throughout the park.

[0053] (3) Is the current time a peak sales period?

[0054] The purpose of extracting related features is to enable subsequent decision-makers (collaborative decision engine) to make judgments based on complete information.

[0055] In specific implementation, the factors determining the priority division rules in this embodiment of the invention may include, but are not limited to, event type, scope of impact, and time sensitivity. For example, events involving safety (such as vehicles trapped on main roads) have the highest priority, events affecting sales of multiple vehicles or areas have a high priority, and events during peak hours will have an increased priority, etc., without limitation. Ultimately, events will be marked with priority labels such as "urgent," "high," "medium," and "low," and the processing priority of the event will be determined based on the priority labels.

[0056] In specific implementation, the collaborative event instruction in this embodiment of the invention is a standardized instruction package containing all necessary information, which may include, but is not limited to: unique event ID and type, trigger source (which vehicle, what rule), priority, event details (out-of-stock items, trapped location, etc.) and associated features (list of surrounding vehicles, inventory heat map, etc.), etc., without limitation.

[0057] In specific implementation, the autonomous vending vehicle in this embodiment of the invention also monitors its own real-time status data during autonomous driving. When special changes occur in the real-time status data, it can proactively send a collaboration request. After receiving the collaboration request proactively transmitted by the autonomous vending vehicle, this embodiment of the invention generates standardized collaboration event instructions based on the collaboration request. This avoids the problem of untimely collaboration caused by unexpected situations such as data delays or interruptions, thereby improving collaboration efficiency.

[0058] S3: In response to the collaborative event command, generate multiple candidate collaborative strategies based on the global state data view and preset collaborative strategy generation rules.

[0059] In one feasible implementation, in this embodiment of the invention, in response to the collaborative event instruction, multiple candidate collaborative strategies are generated based on the global state data view and preset collaborative strategy generation rules. These strategies may include, but are not limited to, the following: The collaborative event command is analyzed to determine the core elements and target area of ​​the event corresponding to the collaborative event command. Based on the core elements of the event and the target area of ​​the event, potential collaborative vehicles that are in an effective state and can participate in collaboration are selected from the global status data view to form a candidate vehicle set; Based on the various cooperative combinations of potential cooperative vehicles in the candidate vehicle set, multiple logically feasible cooperative strategies are enumerated. Based on hard constraints, the cooperative strategy is filtered to obtain multiple candidate cooperative strategies.

[0060] Parse the collaborative event instructions to obtain the event core and target location; Potential collaborative autonomous vending vehicles are identified based on the core of the event and the target location.

[0061] In specific implementation, the core elements of the event in this embodiment of the invention may be "replenishing vehicle A with goods X", "assisting vehicle B in getting out of trouble", or "delivering goods W to area C", etc., and are not limited here. The target area of ​​the event may be the vehicle location or a designated point in the area, etc., and are not limited here.

[0062] In one feasible implementation, the step of filtering potential collaborative vehicles that are in an effective state and capable of participating in collaboration from the global state data view based on the core elements of the event and the target area of ​​the event, to form a candidate vehicle set, may include, but is not limited to: Based on the core elements of the event and the target area of ​​the event, set the filtering radius and status filtering conditions; From the global state data view, find vehicles that are within the filtering radius and meet the state filtering conditions, and identify them as potential cooperative vehicles; All the potential cooperative vehicles are aggregated to form the candidate vehicle set.

[0063] In the specific implementation process, in this embodiment of the invention, a filtering radius and status filtering conditions are set based on the core elements of the event and the target area of ​​the event. This can be understood as follows: when the core element of the event is vehicle A replenishing goods X, and the target area of ​​the event is located at point D, a filtering radius is set with point D as the center, such as a range of 500m or 1000m, etc. The status filtering condition is that the vehicle is operating normally and is loaded with goods X, etc., without limitation. Then, from the global status data view, vehicles located within the filtering radius and meeting the status filtering conditions are searched, and these are summarized to form the candidate vehicle set.

[0064] In specific implementation, the multiple logically feasible collaborative strategies in the embodiments of the present invention may include, but are not limited to: Direct assistance: dispatched by the single nearest vehicle with matching inventory; Multiple vehicles converge: The demanders and supplyers travel in opposite directions and meet midway. Inventory consolidation and redistribution: dispatching one vehicle to replenish multiple out-of-stock vehicles in a centralized manner; Task handover: Another vehicle temporarily takes over the regional sales task of the stranded vehicle.

[0065] In one feasible implementation, the hard constraints in this embodiment of the invention include at least one of vehicle state, task compatibility, and resource constraints. The filtering of the cooperative strategy based on the hard constraints to obtain multiple candidate cooperative strategies may include, but is not limited to: Obtain real-time status information that affects the execution of the collaboration strategy for each potential collaborative vehicle in the candidate vehicle set. The real-time status information includes at least one of vehicle location, current task status, cargo capacity, and energy status. Determine whether the planned action of each potential cooperating vehicle in the candidate vehicle set conflicts with its real-time status information in the cooperative strategy. By summarizing multiple collaborative strategies that do not conflict with the planned actions and the real-time status information, multiple candidate collaborative strategies are obtained.

[0066] In the specific implementation process, in this embodiment of the invention, determining whether the planned action of each potential collaborative vehicle in the candidate vehicle set conflicts with its real-time state information in the collaborative strategy can be understood as follows: For example, vehicle B is performing a delivery task to point C, and in the collaborative strategy, all other hard constraints are met, but vehicle B's planned action is to replenish goods to point D, and points C and D are in opposite directions. In this case, it indicates that the planned action conflicts with its real-time state information, and it is not suitable to execute the collaborative strategy; however, if points C and D are in the same direction, it indicates that the planned action does not conflict with its real-time state information, and the collaborative strategy can be executed.

[0067] S4: Simulate and evaluate the multiple candidate cooperative strategies to determine the optimal cooperative strategy. In one feasible implementation, the step of simulating and evaluating multiple candidate cooperative strategies to determine the optimal cooperative strategy in this embodiment of the invention may include, but is not limited to: For each of the candidate collaborative strategies, the estimated spatiotemporal trajectory of each of the potential collaborative vehicles involved in the simulation strategy execution process is calculated, and the estimated resource consumption of each of the potential collaborative vehicles is calculated. The estimated resource consumption includes the estimated vehicle loss and the estimated total execution time of the candidate collaborative strategy. Based on the estimated spatiotemporal trajectory and the estimated resource consumption, evaluate the impact of at least two of the following indicators: total operational benefits, overall system efficiency, total scheduling cost, and average waiting time corresponding to the execution of each candidate collaborative strategy; Based on preset weights, at least two of the following indicators—total operating revenue, overall system efficiency impact, total scheduling cost, and average waiting time—are weighted and fused to obtain a comprehensive utility evaluation value for each candidate collaborative strategy. The candidate collaborative strategy with the highest comprehensive utility evaluation value is selected as the optimal collaborative strategy.

[0068] In the specific implementation process, the estimated vehicle loss in the embodiments of the present invention includes the additional mileage, time, and energy consumption of each potential collaborative vehicle, as well as the delay time of the original task plan of each potential collaborative vehicle, etc., which are not limited here.

[0069] In specific implementation, this invention quantifies total operating revenue, overall system efficiency impact, total scheduling cost, and average waiting time into calculable indicators. For example: total operating revenue is quantified as "expected recovered sales revenue" (which can be estimated based on the unit price of the goods, the historical sales rate of the out-of-stock area, and the remaining operating time); overall system efficiency is quantified as "the reciprocal of the total system task throughput or the negative correlation value of the total task completion time," or more directly, as the negative value of "the total task delay time of all affected vehicles caused by this coordination" (the less the delay, the higher the efficiency); total scheduling cost is quantified as a monetized estimate of "the additional mileage cost, energy consumption cost, and possible communication and computing resource cost of all participating vehicles"; average waiting time is quantified as "the expected waiting time for the source vehicle (or the demander) from the event trigger to the demand being met," and "the increase in waiting time for other tasks affected by this scheduling."

[0070] In its specific implementation, this invention calculates the comprehensive utility evaluation value of the candidate collaborative strategy by weighted fusion after obtaining at least two of the following indicators: total operating revenue, overall system efficiency impact, total scheduling cost, and average waiting time. The weight coefficient for each indicator can be a fixed weight coefficient or a dynamic weight coefficient; for example, different weight coefficients can be assigned based on different event types, which is not limited here.

[0071] S5: Based on the optimal coordination strategy, assign coordination tasks to the coordination vehicles that execute the optimal coordination strategy, and plan the target driving path corresponding to the coordination task for the coordination vehicles, so that the coordination vehicles complete the coordination task based on the target driving path.

[0072] In one feasible implementation, after assigning a cooperative task to the cooperative vehicle executing the optimal cooperative strategy and planning the target driving path corresponding to the cooperative task for the cooperative vehicle, the embodiments of the present invention may further include, but are not limited to: Continuously acquire dynamic motion status information of vehicles awaiting replenishment, including real-time location information and predicted trajectory information within a preset future time period; The dynamic motion status information of the vehicle to be replenished is synchronized to the cooperating vehicle that performs the replenishment task corresponding to the vehicle to be replenished, so that the cooperating vehicle can dynamically adjust its driving path according to the dynamic motion status information.

[0073] In the specific implementation process, the goods carried by the vehicles to be replenished are of many kinds. When one kind of goods is sold out and needs to be replenished, other goods are also being sold normally. At this time, the vehicles to be replenished may be in a continuous state of movement. This embodiment of the invention continuously acquires the dynamic motion status information of the vehicles to be replenished and transmits it to each cooperating vehicle that performs the replenishment task corresponding to the vehicle to be replenished, so that the cooperating vehicles and the vehicles to be replenished can achieve dynamic convergence and improve replenishment efficiency.

[0074] In the specific implementation process, the optimal coordination strategy may include a coordination vehicle or may not include a coordination vehicle, and may only target vehicles waiting to be replenished. For example, if the cost of coordinating replenishment with other autonomous vending vehicles is too high, the optimal coordination strategy may be to allow the autonomous vending vehicle waiting to be replenished to return to the replenishment point for autonomous replenishment, etc., without limitation.

[0075] In one feasible implementation, after assigning a cooperative task to the cooperative vehicle executing the optimal cooperative strategy and planning the target driving path corresponding to the cooperative task for the cooperative vehicle, this embodiment of the invention may, but is not limited to, further include: The execution status of the collaborative task is acquired in real time, including the operating status of the collaborative vehicle; In the event of an execution anomaly in the execution state, the optimal coordination strategy is re-evaluated to obtain the re-evaluation result; Based on the reassessment results, the task allocation of the collaborative task or the driving path of the collaborative vehicle is dynamically adjusted.

[0076] This invention, by acquiring the real-time operating status of the collaborative vehicle, can effectively save collaborative control time and improve collaborative control efficiency if the collaborative vehicle encounters an unexpected event, such as being trapped, while executing the optimal collaborative strategy. This allows for timely re-evaluation of the optimal collaborative strategy and dynamic adjustment of the task allocation of the collaborative task or the driving path of the collaborative vehicle.

[0077] In the specific implementation process, while executing the optimal coordination strategy, the embodiments of the present invention retain the candidate coordination strategy with the second comprehensive utility evaluation value as a backup plan, so as to quickly switch in case of emergencies, save coordination control time, and improve coordination control efficiency.

[0078] The above-mentioned autonomous driving vending vehicle collaborative control method provided in this embodiment of the invention monitors the real-time status data of vehicles in the target area, identifies collaborative events that require multi-vehicle collaborative processing, and / or receives collaborative requests, generates standardized collaborative event instructions, and dynamically schedules relevant autonomous driving vending vehicles based on the collaborative event instructions. This realizes remote control and scheduling of autonomous driving vending vehicles, improves the intelligent management level of autonomous driving vending vehicles, reduces the number of times personnel need to go to the site, and saves time and costs.

[0079] Based on the aforementioned collaborative control method for autonomous vending vehicles provided in the first aspect, embodiments of the present invention provide a collaborative control platform for autonomous vending vehicles, such as... Figure 3 As shown, the autonomous driving vending vehicle collaborative control platform includes: The monitoring module 110 is used to monitor the real-time status data of vehicles within the target area and construct a global status data view, wherein the vehicles include a cluster of autonomous vending vehicles within the target area. The collaborative event triggering module 120 is used to analyze the global status data view, identify collaborative events that require multi-vehicle collaborative processing, and / or receive collaborative requests and generate standardized collaborative event instructions. The collaborative strategy construction module 130 is used to respond to the collaborative event instruction and generate multiple candidate collaborative strategies according to the global state data view and preset collaborative strategy generation rules. The collaborative strategy evaluation module 140 is used to simulate and evaluate the multiple candidate collaborative strategies respectively to determine the optimal collaborative strategy. The collaborative strategy execution module 150 is used to assign collaborative tasks to collaborative vehicles that execute the optimal collaborative strategy based on the optimal collaborative strategy, and to plan a target driving path corresponding to the collaborative task for the collaborative vehicle, so that the collaborative vehicle completes the collaborative task based on the target driving path.

[0080] In one feasible implementation, the collaborative event triggering module 120 in this embodiment of the invention may include, but is not limited to: The matching submodule is used to match the real-time status data of the vehicle with preset event triggering rules. If the match is successful, an initial collaborative event identifier is generated. The associated feature extraction submodule is used to extract associated features from the global status data view based on the initial collaborative event identifier. The associated features include associated status data related to a specific operational event represented by the initial collaborative event identifier. The classification and priority submodule is used to determine the event category corresponding to the initial collaborative event identifier based on the association features, and to classify the processing priority of the initial collaborative event identifier based on the preset priority classification rules. The instruction generation submodule is used to generate standardized collaborative event instructions containing complete collaborative events based on the event category and the processing priority.

[0081] In one feasible implementation, the collaborative strategy construction module 130 in this embodiment of the invention may include, but is not limited to: The instruction parsing submodule is used to parse the collaborative event instruction and determine the core elements and target area of ​​the event corresponding to the collaborative event instruction. The vehicle filtering submodule is used to filter potential collaborative vehicles that are in an effective state and can participate in collaboration from the global status data view based on the core elements of the event and the target area of ​​the event, forming a candidate vehicle set. The strategy enumeration submodule is used to enumerate multiple logically feasible collaboration strategies based on various collaboration combinations of vehicles in the candidate vehicle set. The strategy filtering submodule is used to filter the collaborative strategies based on hard constraints to obtain multiple candidate collaborative strategies.

[0082] In one feasible implementation, the vehicle screening submodule in this embodiment of the invention may be used, but is not limited to: Based on the core elements of the event and the target area of ​​the event, set the filtering radius and status filtering conditions; From the global state data view, find vehicles that are within the filtering radius and meet the state filtering conditions, and identify them as potential cooperative vehicles; All the potential cooperative vehicles are aggregated to form the candidate vehicle set.

[0083] In one feasible implementation, the strategy filtering submodule in this embodiment of the invention may be used, but is not limited to: Obtain real-time status information that affects the execution of the collaboration strategy for each potential collaborative vehicle in the candidate vehicle set. The real-time status information includes at least one of vehicle location, current task status, cargo capacity, and energy status. Determine whether the planned action of each potential cooperating vehicle in the candidate vehicle set conflicts with its real-time status information in the cooperative strategy. By summarizing multiple collaborative strategies that do not conflict with the planned actions and the real-time status information, multiple candidate collaborative strategies are obtained.

[0084] In one feasible implementation, the collaborative strategy evaluation module 140 in this embodiment of the invention may include, but is not limited to: The strategy simulation execution submodule is used to simulate the estimated spatiotemporal trajectory of each potential collaborative vehicle involved in the execution of each candidate collaborative strategy, and to calculate the estimated resource consumption of each potential collaborative vehicle, wherein the estimated resource consumption includes the estimated vehicle loss and the estimated total execution time of the candidate collaborative strategy. The utility evaluation submodule is used to evaluate the impact of at least two of the following indicators: total operational benefits, overall system efficiency, total scheduling cost, and average waiting time, based on the estimated spatiotemporal trajectory and the estimated resource consumption: The comprehensive utility calculation submodule is used to perform weighted fusion of at least two indicators among the total operating revenue, the overall system efficiency impact, the total scheduling cost and the average waiting time according to preset weights, so as to obtain the comprehensive utility evaluation value of each candidate collaborative strategy. The collaborative strategy decision-making submodule is used to select the candidate collaborative strategy with the highest comprehensive utility evaluation value as the optimal collaborative strategy.

[0085] In one feasible implementation, the collaborative strategy execution module 150 in this embodiment of the invention may include, but is not limited to: The dynamic motion state acquisition submodule is used to continuously acquire the dynamic motion state information of the vehicle to be replenished. The dynamic motion state information includes real-time location information and predicted trajectory information within a preset time period in the future. The dynamic motion status sharing submodule is used to synchronize the dynamic motion status information of the vehicle to be replenished to the cooperating vehicle that performs the replenishment task corresponding to the vehicle to be replenished, so that the cooperating vehicle can dynamically adjust its driving path according to the dynamic motion status information.

[0086] In one feasible implementation, the collaborative strategy execution module 150 in this embodiment of the invention may include, but is not limited to: The collaborative strategy monitoring submodule is used to obtain the execution status of the collaborative task in real time, including the running status of the collaborative vehicle; The collaborative strategy re-evaluation submodule is used to re-evaluate the optimal collaborative strategy when an execution anomaly occurs in the execution state, and obtain the re-evaluation result; The collaborative strategy adjustment submodule is used to dynamically adjust the task allocation of the collaborative task or the driving path of the collaborative vehicle based on the re-evaluation results.

[0087] Based on the aforementioned method for coordinated control of an autonomous vending vehicle provided in the first aspect, this embodiment of the invention also provides a storage medium storing a computer-executable program. The computer-executable program is used to cause a computer to execute the method for coordinated control of an autonomous vending vehicle as described in any implementation of the first aspect. Explanations of the relevant content and descriptions of the beneficial effects of any of the computer-readable storage media provided above can be found in the corresponding embodiments described above, and will not be repeated here.

[0088] Based on the aforementioned collaborative control method for an autonomous vending vehicle provided in the first aspect, embodiments of the present invention also provide an autonomous vending vehicle, such as... Figure 4 As shown, the autonomous vending vehicle includes: Communication module 310 is used to communicate with the autonomous driving vending vehicle collaborative control platform provided in the second aspect; The data acquisition module 320 is used to collect real-time status data of the autonomous vending vehicle; Control module 330 is configured to receive a target driving path transmitted by the autonomous driving vending vehicle collaborative control platform and control the autonomous driving vending vehicle to perform autonomous driving according to the target driving path; and to receive a remote assisted driving command transmitted by the autonomous driving vending vehicle collaborative control platform and control the autonomous driving vending vehicle to perform remote assisted driving according to the remote assisted driving command. The communication module is a dual-link communication module. The first link is used to transmit the target driving path and the real-time status data of the autonomous vending vehicle during autonomous driving. The second link is used to transmit the remote assisted driving command and the real-time status data of the autonomous vending vehicle during remote assisted driving. The autonomous vending vehicle provided in this embodiment of the invention adopts a dual-link communication architecture. One link is dedicated to the transmission of autonomous driving-related data, and the other link is used for the interaction of information required for remote driving. This ensures that autonomous driving and remote driving functions do not interfere with each other, improves the efficiency and accuracy of information transmission, and ensures that the vehicle can respond quickly to commands under various circumstances. Moreover, the dual-link communication architecture enhances the fault tolerance of the system. When one link fails, the other link can still maintain some functions, preventing the autonomous vending vehicle from losing control due to communication interruption.

[0089] Those skilled in the art will understand that the program for implementing all or part of the steps of the above embodiments, which can be executed by a program instructing related hardware, can be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, a random access memory, etc. The processing unit or processor mentioned above can be a central processing unit, a general-purpose processor, an application-specific integrated circuit (ASIC), a microprocessor (DSP), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof.

[0090] This invention also provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform any of the methods described in the above embodiments. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., SSD), etc.

[0091] It should be noted that the devices for storing computer instructions or computer programs provided in the embodiments of the present invention, such as, but not limited to, the aforementioned memory, computer-readable storage medium, and communication chip, are all non-transitory. Those skilled in the art should recognize that the functions described in the embodiments of the present invention in one or more of the above examples can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable storage medium or transmitted as one or more instructions or code on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium accessible to general-purpose or special-purpose computers.

[0092] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A collaborative control method for an autonomous vending vehicle, characterized in that, include: Monitor real-time status data of vehicles within the target area and construct a global status data view, wherein the vehicles include a cluster of autonomous vending vehicles within the target area; Analyze the global state data view to identify collaborative events that require multi-vehicle collaborative processing, and / or receive collaborative requests to generate standardized collaborative event instructions; In response to the collaborative event command, multiple candidate collaborative strategies are generated based on the global state data view and preset collaborative strategy generation rules; The candidate collaborative strategies are simulated and evaluated to determine the optimal collaborative strategy. Based on the optimal coordination strategy, a coordination task is assigned to the coordination vehicle executing the optimal coordination strategy, and a target driving path corresponding to the coordination task is planned for the coordination vehicle, so that the coordination vehicle completes the coordination task based on the target driving path.

2. The method for coordinated control of an autonomous vending vehicle according to claim 1, characterized in that, The analysis of the global state data view identifies collaborative events requiring multi-vehicle collaborative processing, and / or receives collaborative requests, generating standardized collaborative event instructions, including: The real-time status data of the vehicle is matched with preset event triggering rules. If the match is successful, an initial collaborative event identifier is generated. Based on the initial collaborative event identifier, related features are extracted from the global status data view. The related features include related status data related to a specific operational event represented by the initial collaborative event identifier. Based on the associated features, the event category corresponding to the initial collaborative event identifier is determined, and the processing priority of the initial collaborative event identifier is divided according to the preset priority division rules; Based on the event category and the processing priority, a standardized collaborative event instruction containing the complete collaborative event is generated.

3. The method for coordinated control of an autonomous vending vehicle according to claim 1, characterized in that, In response to the collaborative event command, multiple candidate collaborative strategies are generated based on the global state data view and preset collaborative strategy generation rules, including: The collaborative event command is analyzed to determine the core elements and target area of ​​the event corresponding to the collaborative event command. Based on the core elements of the event and the target area of ​​the event, potential collaborative vehicles that are in an effective state and can participate in collaboration are selected from the global status data view to form a candidate vehicle set; Based on the various cooperative combinations of potential cooperative vehicles in the candidate vehicle set, multiple logically feasible cooperative strategies are enumerated. Based on hard constraints, the cooperative strategy is filtered to obtain multiple candidate cooperative strategies.

4. The method for coordinated control of an autonomous vending vehicle according to claim 3, characterized in that, Based on the core elements of the event and the target area of ​​the event, potential collaborative vehicles that are in an effective state and can participate in the collaboration are selected from the global state data view to form a candidate vehicle set, including: Based on the core elements of the event and the target area of ​​the event, set the filtering radius and status filtering conditions; From the global state data view, find vehicles that are within the filtering radius and meet the state filtering conditions, and identify them as potential cooperative vehicles; All the potential cooperative vehicles are aggregated to form the candidate vehicle set.

5. The method for coordinated control of an autonomous vending vehicle according to claim 3, characterized in that, The hard constraints include at least one of vehicle state, task compatibility, and resource constraints. Based on these hard constraints, the cooperative strategy is filtered to obtain multiple candidate cooperative strategies, including: Obtain real-time status information that affects the execution of the collaboration strategy for each potential collaborative vehicle in the candidate vehicle set. The real-time status information includes at least one of vehicle location, current task status, cargo capacity, and energy status. Determine whether the planned action of each potential cooperating vehicle in the candidate vehicle set conflicts with its real-time status information in the cooperative strategy. By aggregating multiple collaborative strategies that do not conflict with the planned actions and the real-time status information, multiple candidate collaborative strategies are obtained.

6. The method for coordinated control of an autonomous vending vehicle according to claim 3, characterized in that, The step of simulating and evaluating multiple candidate cooperative strategies to determine the optimal cooperative strategy includes: For each of the candidate collaborative strategies, the estimated spatiotemporal trajectory of each of the potential collaborative vehicles involved in the simulation strategy execution process is calculated, and the estimated resource consumption of each of the potential collaborative vehicles is calculated. The estimated resource consumption includes the estimated vehicle loss and the estimated total execution time of the candidate collaborative strategy. Based on the estimated spatiotemporal trajectory and the estimated resource consumption, evaluate the impact of at least two of the following indicators: total operational benefits, overall system efficiency, total scheduling cost, and average waiting time corresponding to the execution of each candidate collaborative strategy; Based on preset weights, at least two of the following indicators—total operating revenue, overall system efficiency impact, total scheduling cost, and average waiting time—are weighted and fused to obtain a comprehensive utility evaluation value for each candidate collaborative strategy. The candidate collaborative strategy with the highest comprehensive utility evaluation value is selected as the optimal collaborative strategy.

7. The method for coordinated control of an autonomous vending vehicle according to claim 1, characterized in that, After assigning collaborative tasks to the collaborative vehicles executing the optimal collaborative strategy and planning the target driving path corresponding to the collaborative tasks for the collaborative vehicles, the method further includes: Continuously acquire dynamic motion status information of vehicles awaiting replenishment, including real-time location information and predicted trajectory information within a preset future time period; The dynamic motion status information of the vehicle to be replenished is synchronized to the cooperating vehicle that performs the replenishment task corresponding to the vehicle to be replenished, so that the cooperating vehicle can dynamically adjust its driving path according to the dynamic motion status information.

8. The method for coordinated control of an autonomous vending vehicle according to claim 7, characterized in that, After assigning collaborative tasks to the collaborative vehicles executing the optimal collaborative strategy and planning the target driving path corresponding to the collaborative tasks for the collaborative vehicles, the method further includes: The execution status of the collaborative task is acquired in real time, including the operating status of the collaborative vehicle; In the event of an execution anomaly in the execution state, the optimal coordination strategy is re-evaluated to obtain the re-evaluation result; The task allocation for the collaborative task or the travel path of the collaborative vehicle is dynamically adjusted based on the reassessment results.

9. A collaborative control platform for autonomous vending vehicles, characterized in that, include The monitoring module is used to monitor the real-time status data of vehicles within the target area and build a global status data view, wherein the vehicles include a cluster of autonomous vending vehicles within the target area; The collaborative event triggering module is used to analyze the global status data view, identify collaborative events that require multi-vehicle collaborative processing, and / or receive collaborative requests and generate standardized collaborative event instructions. The collaboration strategy construction module is used to respond to the collaboration event command and generate multiple candidate collaboration strategies based on the global state data view and preset collaboration strategy generation rules. The collaborative strategy evaluation module is used to simulate and evaluate the multiple candidate collaborative strategies respectively, and determine the optimal collaborative strategy. The collaborative strategy execution module is used to assign collaborative tasks to collaborative vehicles that execute the optimal collaborative strategy based on the optimal collaborative strategy, and to plan the target driving path corresponding to the collaborative task for the collaborative vehicle, so that the collaborative vehicle completes the collaborative task based on the target driving path.

10. An autonomous driving vending vehicle, characterized in that, include: A communication module is used to communicate with the autonomous driving vending vehicle collaborative control platform as described in claim 9; The data acquisition module is used to collect real-time status data of the autonomous vending vehicle; The control module is used to receive the target driving path transmitted by the autonomous driving vending vehicle collaborative control platform, and control the autonomous driving vending vehicle to drive autonomously according to the target driving path; And for receiving remote assisted driving instructions transmitted by the autonomous vending vehicle collaborative control platform, and controlling the autonomous vending vehicle to perform remote assisted driving according to the remote assisted driving instructions; The communication module is a dual-link communication module. The first link is used to transmit the target driving path and the real-time status data of the autonomous vending vehicle during autonomous driving. The second link is used to transmit the remote assisted driving command and the real-time status data of the autonomous vending vehicle during remote assisted driving.

Images