A cloud service platform, collaborative scheduling method, device and system

By implementing a collaborative scheduling method on the cloud service platform, selecting suitable sentinel vehicles for operation task management, the problems of operation costs and edge server recycling difficulties in unmanned cluster operations are solved, and the optimal scheduling and cost control of the job are achieved.

CN114510052BActive Publication Date: 2024-12-03SHENZHEN HAIXING ZHIJIA TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202210145905.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-02-17
Publication Date
2024-12-03
Estimated Expiration
2042-02-17

AI Technical Summary

Technical Problem

In unmanned cluster operations, the cost of using the Vehicle Cloud Association has increased simultaneously, and the difficulty of recycling and mobility of edge servers at the same time by using the Vehicle Cloud Association has led to system cost and availability issues.

Method used

By implementing a collaborative scheduling method on the cloud service platform, obtain sub-interval information, select suitable sentinel vehicles for operation task scheduling management, avoiding each engineering vehicle from having a large number of sensors and high-performance computing platforms, and dividing the operation into multiple sub-intervals , authorize different sentinel vehicles for optimal dispatch.

Benefits of technology

It reduces operational costs, solves the difficulties in edge server recycling and mobility, and achieves optimal scheduling and comprehensive results of jobs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114510052B_ABST
    Figure CN114510052B_ABST
Patent Text Reader

Abstract

The present invention discloses a cloud service platform, a collaborative scheduling method, a device and a system, wherein the collaborative scheduling method includes: obtaining current sub-interval information; obtaining the operation content of the current sub-interval and the capability information of each vehicle operating in the current sub-interval according to the current sub-interval information; selecting the current sentinel vehicle corresponding to the current sub-interval according to the operation content and the capability information of each vehicle; determining the current operation constraint corresponding to the current sub-interval according to the operation content; and sending the current operation constraint to the current sentinel vehicle. Different sentinel vehicles can be selected to act as edge servers for different sub-operation intervals of the same operation, and it is not necessary for each engineering vehicle to have the capabilities of environmental perception fusion, behavior decision planning, and multi-machine collaborative scheduling. Since different sentinel vehicles are authorized to perform optimal scheduling for each sub-interval, the overall scheduling effect of the entire operation can be optimized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of cluster operation technology, and in particular to a cloud service platform, a collaborative scheduling method, a device and a system. Background Art

[0002] Unmanned swarm operation is to complete the joint operation of multiple types of work and multiple equipment under the coordinated scheduling of the system. Most of the current solutions for unmanned swarm operation are vehicle-cloud collaboration (such as Figure 1 ), i.e. engineering vehicle-cloud server, or vehicle-side cloud collaboration (e.g. Figure 2 ), namely engineering vehicle—edge server—cloud server.

[0003] When vehicle-cloud collaboration is adopted, if each engineering vehicle has the environmental perception fusion, behavior decision-making planning, and multi-machine collaborative scheduling capabilities required for unmanned operations, each engineering vehicle will need to be equipped with a large number of sensors and high-performance computing platforms, which will lead to increased operating costs.

[0004] When using vehicle-side cloud collaboration, the coordinated scheduling of unmanned cluster operations of engineering vehicles, including autonomous driving, requires a lot of computing power. If the computing power is placed in the cloud, a large number of devices will be directly connected to the cloud, and the large amount of cloud computing data will cause great pressure on the server. Once the cloud server crashes, all devices will become unavailable. If an edge server is set up between the vehicle and the cloud, the cost of edge server deployment and equipment will increase, and the crash of the edge server will also cause the connected devices to be unavailable. It is also a big difficulty for the recovery and movement of edge servers in a large operating area. Summary of the invention

[0005] In view of this, embodiments of the present invention provide a cloud service platform, a collaborative scheduling method, a device and a system to solve the problem of increased operating costs when vehicle-cloud collaboration is adopted, or the problem of difficulty in recovering and moving edge servers when vehicle-side-cloud collaboration is adopted.

[0006] According to the first aspect, an embodiment of the present invention provides a collaborative scheduling method, which is applied to a cloud service platform, and includes the following steps: obtaining current sub-interval information; obtaining the job content of the current sub-interval and the capability information of each vehicle operating in the current sub-interval based on the current sub-interval information; selecting the current sentinel vehicle corresponding to the current sub-interval based on the job content and the capability information of each vehicle; determining the current job constraint corresponding to the current sub-interval based on the job content; sending the current job constraint to the current sentinel vehicle, and authorizing the current sentinel vehicle to schedule and manage the job tasks of the current sub-interval.

[0007] By utilizing the collaborative scheduling method provided by the embodiment of the present invention, different sentinel vehicles can be selected to act as edge servers for different sub-operation intervals of the same operation, thereby solving the problem of difficulty in recovering and moving edge servers; and it is not necessary for each engineering vehicle to have environmental perception fusion, behavior decision planning, and multi-machine collaborative scheduling capabilities, so in addition to the sentinel vehicles, it is not necessary for each engineering vehicle to be equipped with numerous sensors and high-performance computing platforms, and the cost of the entire system is effectively controlled; and the entire operation can also be divided into multiple sub-intervals according to time and space, and different sentinel vehicles are authorized to optimally schedule the operations of each sub-interval, so that the operations of each sub-interval are optimal, and thus the overall scheduling effect of the entire operation is also optimal.

[0008] In combination with the first aspect, in the first implementation of the first aspect, before determining the current job constraint corresponding to the current sub-interval based on the job content, it also includes: dividing the entire job into multiple sub-intervals, and separately specifying the job constraint conditions for each sub-interval.

[0009] In combination with the first aspect and the first embodiment of the first aspect, in the second embodiment of the first aspect, the capability information of each vehicle includes an evaluation score of one or more individual capabilities of the vehicle, wherein the one or more individual capabilities include one or more of the following: driving environment perception capability, operation perception capability, driving decision-making and planning capability, operation decision-making and planning capability, communication capability with a cloud service platform, and communication capability with other vehicles.

[0010] In combination with the second embodiment of the first aspect, in the third embodiment of the first aspect, selecting the current sentinel vehicle corresponding to the current sub-interval according to the operation content and the capability information of each vehicle includes: determining the weights of different individual capabilities in the capability information according to the operation content of the current sub-interval; for the same individual capability of the same vehicle, multiplying the evaluation score of the individual capability by the weight of the individual capability to obtain the individual capability index of the individual capability; traversing all individual capabilities of the same vehicle to obtain all individual capability indicators of the same vehicle; traversing each vehicle operating in the current sub-interval to obtain each individual capability indicator of each vehicle; and selecting the current sentinel vehicle corresponding to the current sub-interval based on each individual capability indicator of each vehicle.

[0011] In combination with the third embodiment of the first aspect, in the fourth embodiment of the first aspect, the current sentinel vehicle corresponding to the current sub-interval is selected based on each individual capability indicator of each vehicle, including: for the same vehicle, adding all individual capability indicators of the vehicle to obtain a comprehensive capability indicator of the vehicle; traversing each vehicle operating in the current sub-interval to obtain the comprehensive capability indicator of each vehicle; taking the vehicle with the highest comprehensive capability indicator as the current sentinel vehicle corresponding to the current sub-interval; or, for the same vehicle, adding all individual capability indicators of the vehicle to obtain the comprehensive capability indicator of the vehicle; traversing each vehicle operating in the current sub-interval to obtain the comprehensive capability indicator of each vehicle; selecting from each vehicle operating in the current sub-interval a vehicle whose individual capability indicator is greater than a preset first threshold value to obtain a pre-screened vehicle; and selecting from the pre-screened vehicles the vehicle with the highest comprehensive capability indicator as the current sentinel vehicle corresponding to the current sub-interval.

[0012] In combination with the fourth embodiment of the first aspect, in the fifth embodiment of the first aspect, before taking the vehicle with the highest comprehensive capability index as the current sentinel vehicle corresponding to the current sub-interval, or before selecting vehicles whose individual capability index is greater than a preset first threshold from each vehicle operating in the current sub-interval to obtain pre-screened vehicles, it also includes: eliminating vehicles whose functional safety levels do not meet the preset conditions.

[0013] In combination with the first aspect, in the sixth embodiment of the first aspect, the current operating constraint corresponding to the current sub-interval is a constraint that all vehicles operating in the current sub-interval need to comply with in order to achieve the optimal operating effect of the current sub-interval. The optimal operating effect includes one or more of the following: shortest time, least energy consumption, and highest efficiency.

[0014] According to the second aspect, an embodiment of the present invention also provides a collaborative scheduling device, which is applied to a cloud service platform, and includes an acquisition module, a parsing module, a screening module, a processing module and a sending module; the acquisition module is used to acquire current sub-interval information; the parsing module is used to obtain the job content of the current sub-interval and the capability information of each vehicle operating in the current sub-interval based on the current sub-interval information; the screening module is used to select the current sentinel vehicle corresponding to the current sub-interval based on the job content and the capability information of each vehicle; the processing module is used to determine the current job constraint conditions corresponding to the current sub-interval based on the job content; and the sending module is used to send the current job constraint conditions to the current sentinel vehicle.

[0015] According to the third aspect, an embodiment of the present invention further provides a cloud service platform, comprising a memory and a processor, wherein the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the collaborative scheduling method described in the first aspect or any embodiment of the first aspect by executing the computer instructions.

[0016] According to a fourth aspect, an embodiment of the present invention further provides a collaborative scheduling system, comprising a sentinel vehicle, a non-sentinel vehicle and the cloud service platform described in the third aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The features and advantages of the present invention will be more clearly understood by referring to the accompanying drawings, which are schematic and should not be construed as limiting the present invention in any way. In the accompanying drawings:

[0018] Figure 1 This is a schematic diagram of vehicle-cloud collaboration;

[0019] Figure 2 This is a schematic diagram of vehicle-side cloud collaboration;

[0020] Figure 3 This is a flow chart of a collaborative scheduling method for a cloud service platform in Embodiment 1 of the present invention;

[0021] Figure 4 This is a structural diagram of a collaborative scheduling device applied to a cloud service platform in Example 2 of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0023] Example 1

[0024] Embodiment 1 of the present invention provides a collaborative scheduling method applied to a cloud service platform. Figure 3 FIG. 1 is a flow chart of a collaborative scheduling method for a cloud service platform in Embodiment 1 of the present invention. Figure 3 As shown, the collaborative scheduling method applied to the cloud service platform in embodiment 1 of the present invention includes the following steps:

[0025] S101: Obtain current sub-interval information.

[0026] Specifically, when the current sub-interval is the first sub-interval, the current sub-interval information can be obtained based on the initial operation information reported by the vehicle in communication with the cloud service platform; when the current sub-interval is not the first sub-interval, the current sub-interval information is sent by the previous sentinel vehicle corresponding to the previous sub-interval. After the sentinel vehicle completes the collaborative scheduling task in this interval, it will send the next sub-interval information to the cloud service platform. The sub-interval information can only be information related to the sub-interval name. At this time, the cloud service platform pre-stores the sub-interval's operation task information, operation constraints, operation participating vehicle information, etc.

[0027] S102: Obtaining the operation content of the current sub-interval and the capability information of each vehicle operating in the current sub-interval according to the current sub-interval information.

[0028] As a specific implementation, the capability information of each vehicle includes an evaluation score of one or more individual capabilities of the vehicle, wherein the one or more individual capabilities are one or more of the following: driving environment perception capability, operation perception capability, driving decision-making and planning capability, operation decision-making and planning capability, communication capability with a cloud service platform, and communication capability with other vehicles.

[0029] Specifically, since different operating scenarios (such as industrial parks, ports, mines, etc.) place different emphasis on the capabilities of engineering vehicles, the election strategy for sentinel vehicles can be customized based on different operating scenarios. The capabilities of all vehicles can be scored using the set standards combined with historical data, and then experienced experts can set weights for different capabilities based on different operating scenarios to calculate the evaluation scores of each vehicle. The sentinel vehicles are selected based on the ranking of scores. For example:

[0030]

[0031]

[0032] Furthermore, in the same operation scenario, different sub-intervals have different emphases on the capabilities of engineering vehicles, so the election strategies of sentinel vehicles in different sub-intervals can be customized in combination with different sub-intervals. For example, for the operation loading sub-interval, the requirements for loading efficiency are high, so a higher weight can be set for the operation decision-making and planning capabilities; for the transportation driving sub-interval, the requirements for energy consumption are high, so a higher weight can be set for the driving decision-making and planning capabilities.

[0033] S103: Selecting a current sentinel vehicle corresponding to the current sub-interval according to the operation content and the capability information of each vehicle.

[0034] As a specific implementation, the following scheme can be adopted to select the current sentinel vehicle corresponding to the current sub-interval according to the operation content of the current sub-interval and the capability information of each vehicle: determine the weights of different individual capabilities in the capability information according to the operation content of the current sub-interval; for the same individual capability of the same vehicle, multiply the evaluation score of the individual capability by the weight of the individual capability to obtain the individual capability index of the individual capability; traverse all individual capabilities of the same vehicle to obtain all individual capability indicators of the same vehicle; traverse each vehicle operating in the current sub-interval to obtain each individual capability indicator of each vehicle; select the current sentinel vehicle corresponding to the current sub-interval based on each individual capability indicator of each vehicle.

[0035] More specifically, the current sentinel vehicle corresponding to the current sub-interval may be selected based on each individual capability indicator of each vehicle by the following scheme.

[0036] The first solution is: for the same vehicle, all individual capability indicators of the vehicle are added together to obtain the comprehensive capability indicator of the vehicle; each vehicle operating in the current sub-interval is traversed to obtain the comprehensive capability indicator of each vehicle; the vehicle with the highest comprehensive capability indicator is used as the current sentinel vehicle corresponding to the current sub-interval.

[0037] The second solution is: for the same vehicle, all individual capability indicators of the vehicle are added together to obtain the comprehensive capability indicator of the vehicle; each vehicle operating in the current sub-interval is traversed to obtain the comprehensive capability indicator of each vehicle; from each vehicle operating in the current sub-interval, vehicles whose individual capability indicators are greater than a preset first threshold are selected to obtain pre-screened vehicles; and the vehicle with the highest comprehensive capability indicator is selected from the pre-screened vehicles as the current sentinel vehicle corresponding to the current sub-interval.

[0038] For example, the comprehensive capability index of each vehicle is calculated using the formula F=i+j+k+l+m+n…, where F is the comprehensive capability index, i is the driving environment perception capability index, which is obtained by multiplying the driving environment perception capability score and the weight of the individual capability; j is the operation perception capability index, which is obtained by multiplying the operation perception capability score and the weight of the individual capability; k is the driving decision planning capability index, which is obtained by multiplying the driving decision planning capability score and the weight of the individual capability; l is the operation decision planning capability index, which is obtained by multiplying the operation decision planning capability score and the weight of the individual capability; m is the communication capability index with the cloud service platform, which is obtained by multiplying the communication capability score with the cloud service platform and the weight of the individual capability; n is the communication capability index with other vehicles, which is obtained by multiplying the communication capability score with other vehicles and the weight of the individual capability. In the first scheme, the election strategy of the sentinel vehicle is to elect the one with the highest total score F. In the second scheme, the election strategy of the sentinel vehicle is to meet both conditions 1 and 2, where condition 1 is that the total score F is the highest; condition 2 is that if one of the scores among i, j, k, l, m, and n is less than 7 points, it cannot be elected as a sentinel vehicle.

[0039] As a further solution of the first solution, before the vehicle with the highest comprehensive capability index is used as the current sentinel vehicle corresponding to the current sub-interval, it also includes: eliminating vehicles whose functional safety levels do not meet preset conditions.

[0040] As a further solution of the second solution, before selecting vehicles whose individual capability indicators are greater than a preset first threshold from each vehicle operating in the current sub-interval to obtain the pre-screened vehicles, it also includes: eliminating vehicles whose functional safety levels do not meet the preset conditions.

[0041] S104: Determine a current task constraint corresponding to the current sub-interval according to the task content.

[0042] Furthermore, before determining the job constraint condition corresponding to the current sub-interval, the method further includes: dividing the entire job into a plurality of sub-intervals, and respectively defining the job constraint condition for each sub-interval.

[0043] S105: Sending the current operation constraint condition to the current sentinel vehicle, authorizing the current sentinel vehicle to perform scheduling management on the operation task of the current sub-interval.

[0044] By using the collaborative scheduling method provided by the embodiment of the present invention, different sentinel vehicles can be selected to act as edge servers for different sub-operation intervals of the same overall operation task, solving the problem of difficulty in recovering and moving edge servers. For example, in some locations, the operation is one-time, such as transporting goods on a highway. If an edge server is set up in this interval to achieve collaborative scheduling of driving and transportation, the edge server needs to be recovered when the driving and transportation task is completed and another route is taken next time. The role of the sentinel vehicle is to command and schedule the operation instead of the server. When the operation is completed, the identity of the sentinel vehicle will also disappear. In most cases, the sentinel vehicle itself will also participate in the actual operation "labor". In addition, the entire operation can be divided into multiple sub-intervals according to time and space, and different sentinel vehicles are authorized to optimally schedule the operation of each sub-interval, so that the operation of each sub-interval is optimal, and thus the comprehensive scheduling effect of the entire operation is also optimal.

[0045] Furthermore, after the sentinel vehicle is selected, other non-sentinel vehicles register with the sentinel vehicle, establish communication, and are managed by the sentinel vehicle. The cloud (i.e., the cloud server includes the central cloud server and the edge server) issues operation information to the sentinel vehicle and receives task completion feedback from the sentinel vehicle. The sentinel vehicle decomposes the operation task. The sentinel vehicle uses the onboard sensors to obtain environmental information, uses the onboard computing platform to further plan the decomposed tasks, and assigns the decomposed tasks to the corresponding vehicles in accordance with certain scheduling principles. Furthermore, the sentinel vehicle uses the onboard computing platform to plan the behavior of each vehicle performing the task. The sentinel vehicle issues the above operation information to the non-sentinel vehicles and receives task completion feedback from the non-sentinel vehicles. The sentinel vehicle can also perform operation tasks at the same time.

[0046] Sentinel vehicles can sense the relative positions of other non-sentinel vehicles through sensors. Sentinel vehicles combine the relative positions and absolute positions of vehicles to calculate the absolute positions of non-sentinel vehicles. At the same time, the positioning information of all vehicles is sent to the cloud for accurate presentation to users.

[0047] Non-sentinel vehicles send positioning information to sentinel vehicles on time, and sentinel vehicles send positioning information to the cloud on time, which also serves as a heartbeat connection detection. If no connection information is sent for five consecutive times, the vehicle is determined to have lost connection, and it can be reported as a communication abnormality of the vehicle to help users respond in time. If it is determined that the sentinel vehicle has lost connection, the cloud will promptly convert the backup sentinel vehicle to the sentinel vehicle to ensure overall high availability without affecting the operation of other vehicles. When the original sentinel vehicle that lost connection reconnects, it can be registered as a normal vehicle with the current sentinel vehicle.

[0048] If the sentinel vehicle self-checks and finds that the battery is low or it goes offline due to other abnormal conditions, the cloud will promptly transfer the spare sentinel vehicle to the sentinel vehicle. Similarly, when the sentinel vehicle that has lost connection is reconnected, it can be registered as a normal vehicle with the current sentinel vehicle.

[0049] In addition, when the workload increases and additional operating vehicles are needed during the operation, the newly added vehicles only need to be registered with the sentinels. At the same time, when it is determined that the remaining workload is not much and the operating vehicles can be reduced, some non-sentinel vehicles can be disconnected and sent back to the parking area. In other words, it is convenient to dynamically expand the operating vehicles and make the operation more flexible.

[0050] Furthermore, some vehicles can always be used as ordinary non-sentinel vehicles, requiring only basic operating capabilities and v2x communication capabilities. In this case, some sensor equipment can be reduced accordingly, or the computing power on the vehicle side can be appropriately reduced to control costs.

[0051] Specifically, the vehicle-mounted equipment can be divided into two types: vehicle-mounted equipment required for operations and edge server-mounted equipment. Installing both devices at the same time can serve as a sentinel vehicle and can perform operations. If only the operation equipment is installed, it can be used as a non-sentinel vehicle for operations. If only the edge server-mounted equipment is installed, it can be used as a mobile edge server.

[0052] In order to explain the collaborative scheduling method of embodiment 1 of the present invention in more detail, a specific embodiment is used below to illustrate how the collaborative scheduling system works.

[0053] (1) In large and complex intelligent operation systems, multiple types of equipment are involved in joint operations, and the operation areas are relatively scattered. A well-designed collaborative scheduling system can make the entire operation process more efficient and stable, and the comprehensive scheduling effect is optimal. In the intelligent operation transportation system, the entire operation and transportation integration process can be divided into three sections in time and space: the AB section operation loading area (such as a mine), the BC section transportation driving area (such as a highway), and the CD section unloading operation area (such as a port). In the AB section operation loading area, there are excavators and loaders, in the BC end transportation driving operation mainly includes loaders, and in the CD section unloading operation area mainly includes loaders and forklifts.

[0054] (2) Initial state: All mechanical equipment (here mainly excavators and loaders) in the AB section working loading area that are connected to the cloud service platform report their own status and environmental characteristics to the cloud service platform. The cloud service platform determines that the current scene is working loading based on the reports of the excavators and loaders. The cloud service platform evaluates and scores many excavators and loaders according to the conditions that the sentinel vehicles should have in the pre-designed working loading scene, and selects the sentinel vehicles.

[0055] The sentinel vehicle election strategy in the operation loading scenario includes: (1) the total score F is the highest, F = i + j + k + l + m + n..., i is the driving environment perception capability index, j is the operation perception capability index, k is the driving decision planning capability index, l is the operation decision planning capability index, m is the communication capability index with the cloud service platform, and n is the communication capability index with other vehicles; (2) if one of the scores among i, j, k, l, m, and n is less than 7 points, it cannot be elected as a sentinel vehicle.

[0056] After the excavator A is elected as the sentinel vehicle for the AB section, other non-sentinel vehicles such as excavators and loaders can be offline from the cloud service platform and directly registered on the excavator A. The excavator A still maintains a communication connection with the cloud service platform. The excavator A becomes the nerve center of all equipment in this area, responsible for directing all equipment to complete the loading task. The excavator A requests the cloud service platform to query the constraints for the coordinated scheduling of other equipment operations in the loading scenario. The cloud service platform sends the pre-designed constraint efficiency H to the excavator A. The excavator A schedules other equipment based on the principle of the highest efficiency H, so as to maximize the efficiency when completing the task in this interval.

[0057] (3) After the loading task of the AB interval operation is completed, the excavator reports to the cloud service platform that the current interval task has ended and is about to switch to a new interval operation scene. The excavator sends the B point environmental information or other information that will help the cloud service platform determine the type of operation scene next to the cloud service platform. The cloud service platform determines that the operation scene of the BC section is transportation driving. The excavator sends the status of all vehicles and equipment involved in the BC section transportation driving task to the cloud service platform, and the cloud service platform selects the sentinel vehicle for the BC section according to the pre-set sentinel election strategy under the transportation driving scene.

[0058] The election strategies in the transportation driving scenario include: (1) the total score F is the highest, F = i + j + k + l + m + n..., i is the driving environment perception capability index, j is the operation perception capability index, k is the driving decision-making and planning capability index, l is the operation decision-making and planning capability index, m is the communication capability index with the cloud service platform, and n is the communication capability index with other vehicles; (2) if one of the scores among i, j, k, and l is less than 7 points, the vehicle cannot be elected as a sentinel vehicle; (3) vehicles with a functional safety level lower than ASID B cannot be elected as sentinel vehicles.

[0059] After selecting the loading vehicle heavy truck B as the sentinel vehicle, heavy truck B sends a communication connection request to the cloud service platform. The vehicles and equipment that will participate in the BC section transportation driving task will register with heavy truck B, and the original communication connection with the excavator A will be disconnected. Heavy truck B requests the cloud service platform to query the constraints for coordinating the operation of other equipment in the pre-designed transportation driving scenario. The cloud service platform finds the constraint condition for the transportation driving scenario with the minimum energy consumption N in the database and sends it to heavy truck B. Heavy truck B organizes all other vehicles to drive in formation based on the principle of minimum energy consumption.

[0060] (3) When the convoy reaches point C, heavy truck B reports to the cloud service platform that the transport mission is complete. The operation scene will be switched, and the cloud service platform will upload the information needed to determine the type of new operation scene, such as surrounding environment information, surrounding vehicle equipment information, or manual instructions. The cloud service platform determines that section CD is the unloading operation area. The cloud service platform collects the equipment status information of all heavy trucks and forklifts involved in the unloading operation in section CD. The cloud service platform queries the pre-designed unloading operation sentinel vehicle election strategy.

[0061] The sentinel vehicle election strategy in the unloading operation scenario is as follows: (1) The total score F is the highest, F = i + j + k + l + m + n..., i is the driving environment perception ability score, j is the operation perception ability score, k is the driving decision planning ability score, l is the operation decision planning ability score, m is the communication ability score with the cloud service platform, and n is the communication ability score with other vehicles. 2) If one of the scores among i, j, k, l, m, and n is less than 7 points, it cannot be elected as a sentinel vehicle.

[0062] The cloud service platform selects forklift C as the sentinel vehicle for the CD section unloading operation area. Forklift C maintains a communication connection with the cloud service platform, and other engineering vehicles involved in the unloading operation task are offline from the cloud service platform and registered on forklift C. Forklift C queries the cloud service platform for the constraints of coordinating the operations of other equipment in the pre-designed unloading operation scenario. The cloud service platform finds the constraint condition time T in the unloading operation scenario in the database and sends it to forklift C. Forklift C organizes the unloading operations of all other vehicles based on the principle of shortest time. After the unloading operation is completed, other forklifts and heavy trucks involved in the unloading operation are offline from forklift C. Forklift C reports the completion of the unloading task to the cloud service platform, and the cloud service platform confirms the completion of the integrated scheduling task of the entire operation and transportation, and forklift C is offline from the cloud service platform.

[0063] Example 2

[0064] Embodiment 2 of the present invention provides a collaborative scheduling device applied to a cloud service platform. Figure 4 Schematic diagram of the structure of the collaborative scheduling device applied to the cloud service platform in Example 2 of the present invention. Figure 4As shown, the collaborative scheduling device applied to the cloud service platform in embodiment 2 of the present invention includes an acquisition module 20, a parsing module 21, a screening module 22, a processing module 23 and a sending module 24.

[0065] Specifically, the acquisition module 20 is used to obtain the current sub-interval information;

[0066] The parsing module 21 is used to obtain the operation content of the current sub-interval and the capability information of each vehicle operating in the current sub-interval according to the current sub-interval information;

[0067] A screening module 22, configured to select a current sentinel vehicle corresponding to the current sub-interval according to the operation content of the current sub-interval and the capability information of each vehicle;

[0068] A processing module 23, configured to determine a current job constraint condition corresponding to the current sub-interval according to the job content of the current sub-interval;

[0069] The sending module 24 is used to send the current operation constraint condition to the current sentinel vehicle.

[0070] For details of the above-mentioned collaborative scheduling device applied to the cloud service platform, please refer to Figures 1 to 3 The corresponding related descriptions and effects in the illustrated embodiments can be understood and will not be repeated here.

[0071] Example 3

[0072] Embodiment 3 of the present invention further provides a cloud service platform, which may include a processor and a memory, wherein the processor and the memory may be connected via a bus or other means.

[0073] Furthermore, Embodiment 3 of the present invention also provides a collaborative scheduling system, including a sentinel vehicle, a non-sentinel vehicle and the above-mentioned cloud service platform.

[0074] The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0075] The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the collaborative scheduling method applied to the cloud service platform in the embodiment of the present invention (for example, Figure 4 The processor executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory, that is, the collaborative scheduling method applied to the cloud service platform in the above method embodiment is realized.

[0076] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0077] The one or more modules are stored in the memory and when executed by the processor, perform the following steps: Figures 1 to 3 The collaborative scheduling method applied to the cloud service platform in the illustrated embodiment.

[0078] For details of the above cloud service platforms, please refer to Figures 1 to 4 The corresponding related descriptions and effects in the illustrated embodiments can be understood and will not be repeated here.

[0079] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0080] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A collaborative scheduling method, applied to a cloud service platform, It is characterized in that include: Get the current sub-interval information; Obtaining the operation content of the current sub-interval and the capability information of each vehicle operating in the current sub-interval according to the current sub-interval information; Selecting a current sentinel vehicle corresponding to the current sub-interval according to the operation content and the capability information of each vehicle; Determine a current job constraint condition corresponding to the current sub-interval according to the job content; Sending the current operation constraint condition to the current sentinel vehicle, authorizing the current sentinel vehicle to perform scheduling management on the operation task of the current sub-interval; The capability information of each vehicle includes evaluation scores of one or more individual capabilities of the vehicle, wherein the one or more individual capabilities include one or more of the following: driving environment perception capability, operation perception capability, driving decision planning capability, operation decision planning capability, communication capability with a cloud service platform, and communication capability with other vehicles; The current sentinel vehicle corresponding to the current sub-interval is selected according to the operation content and the capability information of each vehicle, including: Determining the weights of the evaluation scores of different individual abilities in the ability information according to the job content; For the same individual capability of the same vehicle, the evaluation score of the individual capability and the weight of the individual capability are multiplied to obtain the individual capability index of the individual capability; all individual capabilities of the same vehicle are traversed to obtain all individual capability indexes of the same vehicle; Traversing each vehicle operating in the current sub-interval to obtain each individual capability indicator of each vehicle; A current sentinel vehicle corresponding to the current sub-interval is selected based on each individual capability indicator of each vehicle.

2. The collaborative scheduling method according to claim 1, It is characterized in that Before determining the current job constraint condition corresponding to the current sub-interval according to the job content, the method further includes: The entire job is divided into multiple sub-intervals, and the job constraints of each sub-interval are specified separately.

3. The collaborative scheduling method according to claim 1, It is characterized in that The selecting the current sentinel vehicle corresponding to the current sub-interval based on each individual capability indicator of each vehicle comprises: For the same vehicle, all individual capability indicators of the vehicle are added together to obtain a comprehensive capability indicator of the vehicle; each vehicle operating in the current sub-interval is traversed to obtain the comprehensive capability indicator of each vehicle; The vehicle with the highest comprehensive capability index is used as the current sentinel vehicle corresponding to the current sub-interval; Alternatively, for the same vehicle, all individual capability indicators of the vehicle are added together to obtain a comprehensive capability indicator of the vehicle; each vehicle operating in the current sub-interval is traversed to obtain the comprehensive capability indicator of each vehicle; Selecting, from each vehicle operating in the current sub-interval, a vehicle whose individual capability index is greater than a preset first threshold value to obtain a pre-screened vehicle; A vehicle with the highest comprehensive capability index is selected from the pre-screened vehicles as a current sentinel vehicle corresponding to the current sub-interval.

4. The collaborative scheduling method according to claim 3, It is characterized in that Before taking the vehicle with the highest comprehensive capability index as the current sentinel vehicle corresponding to the current sub-interval, or selecting vehicles whose individual capability index is greater than a preset first threshold from each vehicle operating in the current sub-interval to obtain pre-screened vehicles, the method further includes: Vehicles whose functional safety levels do not meet the preset conditions are eliminated.

5. The collaborative scheduling method according to claim 1, It is characterized in that The current operation constraint corresponding to the current sub-interval is a constraint that all vehicles operating in the current sub-interval need to comply with in order to achieve the optimal operation effect of the current sub-interval. The optimal operation effect includes one or more of the following: shortest time, least energy consumption, and highest efficiency.

6. A collaborative scheduling device, applied to a cloud service platform, It is characterized in that include: The acquisition module is used to obtain the current sub-interval information; A parsing module, used for obtaining the operation content of the current sub-interval and the capability information of each vehicle operating in the current sub-interval according to the current sub-interval information; A screening module, used for selecting a current sentinel vehicle corresponding to the current sub-interval according to the operation content and the capability information of each vehicle; A processing module, configured to determine a current job constraint corresponding to the current sub-interval according to the job content; A sending module, used for sending the current operation constraint condition to the current sentinel vehicle; The capability information of each vehicle includes evaluation scores of one or more individual capabilities of the vehicle, wherein the one or more individual capabilities include one or more of the following: driving environment perception capability, operation perception capability, driving decision planning capability, operation decision planning capability, communication capability with a cloud service platform, and communication capability with other vehicles; The screening module is specifically used to: determine the weights of the evaluation scores of different individual capabilities in the capability information according to the job content; for the same individual capability of the same vehicle, multiply the evaluation score of the individual capability by the weight of the individual capability to obtain the individual capability index of the individual capability; traverse all individual capabilities of the same vehicle to obtain all individual capability indicators of the same vehicle; traverse each vehicle operating in the current sub-interval to obtain each individual capability index of each vehicle; and select the current sentinel vehicle corresponding to the current sub-interval based on each individual capability index of each vehicle.

7. A cloud service platform, It is characterized in that include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the collaborative scheduling method according to any one of claims 1 to 5 by executing the computer instructions.

8. A collaborative scheduling system, It is characterized in that It includes a sentinel vehicle, a non-sentinel vehicle and the cloud service platform described in claim 7.

Citation Information

Patent Citations

  • Computing resource sharing method and system based on automatic driving and readable storage medium

    CN109714422A