Unmanned vehicle cluster risk control method, device, equipment and medium

Abstract

The embodiment of the invention discloses an unmanned vehicle cluster risk control method and device, equipment and a medium. The method comprises the following steps: dividing an unmanned vehicle cluster into at least two sub-clusters; determining a service task arrival rate of the sub-cluster, and determining a preset arrival rate threshold value corresponding to the service task; wherein the service task arrival rate is used for representing the arrival number of the sub-cluster service tasks in a preset time interval; when the service task arrival rate is greater than or equal to a preset arrival rate threshold value, determining that the current sub-cluster has a fault and performing fault diagnosis; and determining a fault association sub-cluster according to the fault diagnosis result, and performing fault isolation processing on the fault association sub-cluster to perform risk control on the unmanned vehicle cluster. According to the scheme, after it is determined that the unmanned vehicle cluster breaks down, degradation and fault isolation are carried out on the fault associated sub-cluster, and the influence of the fault on the overall service function of the unmanned vehicle cluster is effectively reduced.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of unmanned driving technology, and in particular to a method, device, equipment and medium for risk control of unmanned vehicle clusters. Background Art

[0002] With the development of artificial intelligence technology, autonomous driving technology has become more mature. Although the development goal of unmanned vehicles is to achieve fully autonomous driving, in actual applications, in order to ensure safety and reliability, remote safety officers are still essential system capabilities to intervene and control unmanned vehicles.

[0003] From the perspective of risk control of driverless vehicle clusters, the supply of remote safety officers must be greater than or equal to the demand at any time, that is, there should not be a situation where there is no remote safety officer to respond when there is a need to interfere with the vehicle. Improving safety through system redundancy design is a commonly used method, but if the redundancy configuration is too high, it will lead to low human resource utilization of remote safety officers, increase costs and difficulty in management and maintenance.

[0004] Therefore, how to control the risks of unmanned vehicle clusters is a technical problem that needs to be solved urgently by technical personnel in this field. Summary of the invention

[0005] Embodiments of the present invention provide a method, device, electronic device and storage medium for risk control of an unmanned vehicle cluster, so as to achieve downgrading and fault isolation of fault-associated subclusters after determining that an unmanned vehicle cluster has a fault, thereby effectively reducing the impact of the fault on the overall service function of the unmanned vehicle cluster.

[0006] In a first aspect, an embodiment of the present invention provides a method for controlling risk of a cluster of unmanned vehicles, comprising:

[0007] Dividing the autonomous vehicle cluster into at least two subclusters;

[0008] Determine the service task arrival rate of the sub-cluster, and determine the preset arrival rate threshold corresponding to the service task; wherein the service task arrival rate is used to characterize the arrival number of the sub-cluster service tasks within a preset time interval;

[0009] When the service task arrival rate is greater than or equal to a preset arrival rate threshold, determining that the current sub-cluster has a fault and performing fault diagnosis;

[0010] The fault-associated subclusters are determined based on the fault diagnosis results, and the fault-associated subclusters are isolated to perform risk control on the unmanned vehicle cluster.

[0011] In a second aspect, an embodiment of the present invention further provides a risk control device for a cluster of unmanned vehicles, comprising:

[0012] A cluster division module, used for dividing the unmanned vehicle cluster into at least two sub-clusters;

[0013] A task service determination module is used to determine the arrival rate of the service tasks of the sub-cluster and determine the preset arrival rate threshold corresponding to the service tasks; wherein the service task arrival rate is used to characterize the arrival number of the sub-cluster service tasks within a preset time interval;

[0014] A fault diagnosis module, used to determine that a fault occurs in the current sub-cluster and perform fault diagnosis when the arrival rate of the service task is greater than or equal to a preset arrival rate threshold;

[0015] The risk control module is used to determine the fault-related sub-clusters according to the fault diagnosis results, and to perform fault isolation processing on the fault-related sub-clusters to perform risk control on the unmanned vehicle cluster.

[0016] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0017] one or more processors;

[0018] A storage device for storing one or more programs;

[0019] When the one or more programs are executed by the one or more processors, the one or more processors implement the unmanned vehicle cluster risk control method described in any embodiment of the present invention.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the unmanned vehicle cluster risk control method described in any embodiment of the present invention is implemented.

[0021] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the unmanned vehicle cluster risk control method as described in any embodiment of the present invention.

[0022] The embodiment of the present invention provides a method, device, electronic device and storage medium for risk control of an unmanned vehicle cluster, which divides an unmanned vehicle cluster into at least two subclusters; determines the service task arrival rate of the subclusters, and determines the preset arrival rate threshold corresponding to the service tasks; when the service task arrival rate is greater than or equal to the preset arrival rate threshold, determines that the current subcluster has a fault and performs fault diagnosis; determines the fault-associated subcluster based on the fault diagnosis result, and performs fault isolation processing on the fault-associated subcluster to perform risk control on the unmanned vehicle cluster. By adopting the technical solution of the embodiment of the present invention, after determining that the unmanned vehicle cluster has a fault, the fault-associated subcluster is downgraded and fault-isolated, while the normal unmanned vehicle subcluster is not affected, effectively reducing the impact of the fault on the overall service function of the unmanned vehicle cluster. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. Also, the same reference symbols are used throughout the drawings to represent the same parts. In the drawings:

[0024] Figure 1 is a flow chart of a method for controlling risk of a cluster of unmanned vehicles provided in an embodiment of the present invention;

[0025] Figure 2 is a flow chart of another unmanned vehicle cluster risk control method provided in an embodiment of the present invention;

[0026] Figure 3 is a flow chart of another unmanned vehicle cluster risk control method provided in an embodiment of the present invention;

[0027] Figure 4 is a schematic structural diagram of an unmanned vehicle cluster risk control device provided in an embodiment of the present invention;

[0028] Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0030] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations (or steps) as sequential processes, many of the operations (or steps) therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0031] Among them, the acquisition, storage, use and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. It should be noted that in the embodiments of this application, some existing solutions in the industry such as certain software, components or models may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0033] Embodiment 1

[0034] Figure 1 This is a flow chart of a method for risk control of unmanned vehicle clusters provided in an embodiment of the present invention. This embodiment is applicable to the situation of risk control of unmanned vehicle clusters. The method of this embodiment can be executed by an unmanned vehicle cluster risk control device, which can be implemented in hardware and / or software. The device can be configured in a server for risk control of unmanned vehicle clusters. The method specifically includes the following steps:

[0035] S110: Divide the unmanned vehicle cluster into at least two subclusters.

[0036] Among them, an unmanned vehicle cluster risk control system is provided in an embodiment of the present invention, and the system includes a control system and a random service system. The monitoring module of the control system is used to monitor the status of the random service system, including the number of remote safety officers Z currently available, the service tasks Q in the random service system, and the status data of the unmanned vehicles associated with the service tasks. Among them, the number of remote safety officers is a global resource shared by the vehicle cluster; the status data includes but is not limited to the vehicle's system data, positioning data, operating condition status data, environmental status data, and network communication status data. The data collected by the monitoring module is the input of the fault detection and isolation (FDI) module, and the fault identification and isolation module performs real-time fault diagnosis and isolation on the unmanned vehicle cluster based on the input data.

[0037] First, the unmanned vehicle cluster is divided into a plurality of subclusters as an initial division, and the subclusters are divided in a manner including but not limited to division based on the operating area to which the unmanned vehicle belongs, division based on the administrative division to which the unmanned vehicle belongs, division based on the unmanned vehicle in a specific subnetwork in the traffic network, or division based on the communication network to which the unmanned vehicle is connected. Through the initial division, the unmanned vehicle cluster is divided into at least two subclusters Group i .

[0038] S120: Determine the arrival rate of the service tasks of the sub-cluster, and determine a preset arrival rate threshold corresponding to the service tasks.

[0039] The service task arrival rate is used to characterize the number of sub-cluster service tasks arriving within a preset time interval. i The time distribution of service task arrival is X i , the service task arrival rate is calculated based on the historical data of X, and the service task arrival rate can be represented as:

[0040]

[0041] Among them, λ i is the arrival rate of service tasks. Define λ i The corresponding preset arrival rate threshold α i In the embodiment of the present invention, i There is no specific restriction on the calculation method of i The calculation is based on historical data or business models.

[0042] S130: When the service task arrival rate is greater than or equal to a preset arrival rate threshold, determine that a fault occurs in the current sub-cluster and perform fault diagnosis.

[0043] The service task may refer to a service task in a random service system that needs to be processed by a remote safety officer. When the arrival rate of the service task is greater than or equal to a preset arrival rate threshold, a large number of remote safety officers are required to process the service task, and it is determined that the current subcluster has a fault at this time; after determining that the current subcluster has a fault, fault diagnosis is required.

[0044] S140. Determine fault-associated subclusters based on the fault diagnosis result, and perform fault isolation processing on the fault-associated subclusters to perform risk control on the unmanned vehicle cluster.

[0045] Among them, fault isolation processing can refer to downgrading the task level of the fault-associated sub-cluster to free up the remote management resources of the low-priority unmanned vehicles in the fault-associated sub-cluster to process the service tasks of the high-priority unmanned vehicles in the fault-associated sub-cluster.

[0046] Wherein, the fault-associated sub-cluster is determined according to the fault diagnosis result, and the fault-associated sub-cluster may refer to the current sub-cluster or to the associated sub-cluster of the current sub-cluster. After the fault-associated sub-cluster is determined, the fault-associated sub-cluster is subjected to fault isolation processing to perform risk control on the unmanned vehicle cluster.

[0047] The embodiment of the present invention provides a method for risk control of an unmanned vehicle cluster, by dividing an unmanned vehicle cluster into at least two subclusters; determining the service task arrival rate of the subclusters, and determining a preset arrival rate threshold corresponding to the service task; wherein the service task arrival rate is used to characterize the number of arrivals of the subcluster service tasks within a preset time interval; when the service task arrival rate is greater than or equal to the preset arrival rate threshold, determining that the current subcluster has a fault and performing a fault diagnosis; determining a fault-associated subcluster based on the fault diagnosis result, and performing fault isolation processing on the fault-associated subcluster, so as to perform risk control on the unmanned vehicle cluster. By adopting the technical solution of the embodiment of the present invention, after determining that the unmanned vehicle cluster has a fault, the fault-associated subcluster is downgraded and fault-isolated, while the normal unmanned vehicle subcluster is not affected, effectively reducing the impact of the fault on the overall service function of the unmanned vehicle cluster.

[0048] Embodiment 2

[0049] Figure 2 The flowchart of a method for controlling the risk of a cluster of unmanned vehicles provided in an embodiment of the present invention is shown in FIG. The embodiment of the present invention further optimizes the above embodiment on the basis of the above embodiment, and the embodiment of the present invention can be combined with various optional solutions in one or more of the above embodiments. Figure 2As shown, the unmanned vehicle cluster risk control method provided in the embodiment of the present invention may include the following steps:

[0050] S210: Divide the unmanned vehicle cluster into at least two subclusters.

[0051] S220: Determine the arrival rate of the service tasks of the sub-cluster, and determine a preset arrival rate threshold corresponding to the service tasks.

[0052] S230: When the service task arrival rate is greater than or equal to a preset arrival rate threshold, determine that a fault occurs in the current sub-cluster, and determine external causes that affect the autonomous driving capability of the unmanned vehicle.

[0053] Among them, when λ i ≥α i When , it is regarded as the current subcluster g i When a fault occurs, the cause of the current sub-cluster fault is diagnosed. Fault diagnosis includes fault characterization and fault attribution. Among them, fault characterization can refer to judging and identifying the cause and location of the fault by observing and analyzing the various manifestations and characteristics of the current sub-cluster when the fault occurs; in practical applications, fault characterization can help technicians quickly locate the problem, take corresponding maintenance measures, and reduce equipment downtime and maintenance costs. Fault attribution can refer to determining the root cause of the current sub-cluster fault in a systematic way.

[0054] As an optional but non-limiting implementation method, the external factors affecting the autonomous driving capability of the unmanned vehicle include weather conditions, traffic environment, road conditions and infrastructure conditions.

[0055] Among them, after determining that the current sub-cluster has a fault, based on prior knowledge and historical data, the external reasons that affect the autonomous driving capability of the unmanned vehicle are determined, and the external reasons include but are not limited to weather conditions, traffic environment, road conditions and infrastructure conditions.

[0056] S240, characterize the external cause with geographic information, and attribute the fault based on the geographic information.

[0057] Among them, the external causes that affect the autonomous driving capability of the unmanned vehicle are represented by geographic information and fault attribution is performed to determine the cause of the failure of the current sub-cluster.

[0058] As an optional but non-limiting implementation, the geographic information representation method includes any one of a raster / grid model, a vector topology model, an object model, a kernel function model or a hybrid model.

[0059] Among them, in the embodiment of the present invention, there is no specific limitation on the way of representing geographic information of external causes, and the geographic information representation method includes but is not limited to any one of a raster / grid model, a vector topology model, an object model, a kernel function model or a hybrid model.

[0060] Among them, raster / grid model representation can refer to the use of unified grid units to represent spatial areas, and record attribute information such as weather, traffic status, and the location of unmanned vehicles corresponding to the grid. Vector topology model representation can refer to the use of geometric elements such as points, lines, and surfaces to describe the spatial distribution of infrastructure such as road networks and traffic signs, and the use of topological relationships to express information such as road connectivity, traffic status, and the location of unmanned vehicles. Object model representation can refer to abstracting unmanned vehicles and other traffic participants into independent objects, including information such as position and motion status, and using object-oriented methods to organize and manage complex traffic scenes. Kernel function model representation can refer to the use of kernel functions to describe the relationship and influence between unmanned vehicles and between unmanned vehicles and other traffic participants, and provide a mathematical model for modeling complex interactions for decision-making systems. Hybrid model representation can refer to combining the above multiple representation methods to comprehensively express the geometric characteristics, attribute information, and dynamic changes of unmanned vehicles and the environment.

[0061] Among them, the FDI module attributes faults based on geographic information representation. The embodiment of the present invention does not limit the fault attribution method, and the fault attribution method includes but is not limited to any one of a rule-based method, a data-driven method, a model-based method, a probability analysis method, a causal analysis method, or a fusion method.

[0062] Among them, the rule-based approach can refer to manually establishing mapping rules between fault modes and environmental conditions based on prior knowledge in the field of traffic and unmanned driving, and determining the cause of the fault through rule reasoning. The data-driven approach can refer to using historical fault data to train machine learning models and predict possible fault types based on current environmental characteristics. The model-based approach can refer to establishing unmanned vehicle models and environmental models, analyzing the fault propagation mechanism, and inferring the cause and propagation path of the fault based on the model. The probability analysis approach can refer to using probabilistic graph models such as Bayesian networks to describe the dependency relationship between faults and the environment, and using probability inference to determine the possible cause of the fault. The causal analysis approach can refer to using causal graphs to model the causal relationship of fault propagation and finding the root cause of the fault through reverse tracing. The fusion approach can refer to combining the above multiple fault attribution methods and comprehensively utilizing knowledge, data, and models to improve the accuracy and explainability of fault diagnosis.

[0063] S250: Perform fault diagnosis on the unmanned vehicles included in the current sub-cluster according to the fault attribution result.

[0064] Among them, the key parameters of fault diagnosis are defined according to the fault attribution results to perform fault diagnosis on the unmanned vehicles included in the current sub-cluster.

[0065] S260: Determine fault-associated subclusters based on the fault diagnosis result, and perform fault isolation processing on the fault-associated subclusters to perform risk control on the unmanned vehicle cluster.

[0066] Among them, the fault-associated subcluster may refer to the current subcluster or the associated subcluster of the current subcluster, and there is no specific limitation in the embodiments of the present invention. The fault-associated subcluster is determined based on the fault diagnosis result, and the fault-associated subcluster is isolated to control the risk of the unmanned vehicle cluster. The embodiments of the present invention realize real-time identification, attribution and isolation of faults through fault identification and isolation based on active fault tolerance, thereby reducing the risk of the unmanned vehicle cluster and reducing the impact of the fault on the overall business service function of the unmanned vehicle cluster.

[0067] As an optional but non-limiting implementation, the method of determining the fault-associated sub-clusters based on the fault diagnosis results and performing fault isolation processing on the fault-associated sub-clusters to perform risk control on the unmanned vehicle cluster includes but is not limited to steps A1-A3:

[0068] Step A1: Determine a fault-associated subcluster according to the fault diagnosis result, and determine a vehicle set and a business task set corresponding to the fault-associated subcluster.

[0069] Step A2: Sort the vehicle collection according to the priority of the business tasks, and perform fault isolation processing on the first unmanned vehicle corresponding to the low-priority first business task; the fault isolation processing includes downgrading the first business task corresponding to the first unmanned vehicle to change the driving state of the first unmanned vehicle to a stationary state under safe conditions.

[0070] Step A3: releasing the remote safety resources corresponding to the first unmanned vehicle, and using the remote safety resources to perform risk control on the unmanned vehicle corresponding to the high-priority business task.

[0071] Among them, the fault-associated sub-cluster h is determined according to the fault diagnosis result. j , for h j To isolate the fault, the isolation method is to j Degrade the service. The fault is associated with the sub-cluster h j The associated vehicle set is {A} j , the business task set is {P} j For the vehicle set {A} j , the unmanned vehicle performs the business tasks according to {PA} j The priorities are sorted, and low-priority business tasks P are suspended first, and the suspended business tasks P and the corresponding priority information are saved. Among them, if the business task P has no associated service task Q, the business task P is still suspended, and the present invention does not limit the priority definition method of the business task P. The way to suspend business task P is: the remote safety officer immediately changes the driving state of the unmanned vehicle in the fault-associated subcluster from the driving state to the stationary state in a safe manner. If the business task P has an associated service task Q, the service task Q in the random service system is terminated after the unmanned vehicle is in a stationary state, and the remote safety officer resources are released; if the business task P has no associated service task Q, the probability of generating the corresponding service task Q after the business task P is suspended is 0. Therefore, in the isolation mode, the fault-associated subcluster g j The occupied remote security officer resources are quickly released.

[0072] As an optional but non-limiting implementation, after the fault-associated sub-clusters are isolated, the method further includes but is not limited to steps B1-B2:

[0073] Step B1: Continuously monitor the fault status of the fault-associated sub-cluster and determine whether the fault is resolved.

[0074] Step B2: Determine the target vehicle set and target business task set for fault resolution, and recover the second vehicle corresponding to the second business task and restart the corresponding second business task according to the business task priority; wherein the second business task is a high-priority business task for priority sorting.

[0075] Among them, after completing the fault isolation of the fault-associated sub-cluster, the fault status detection of the fault-associated sub-cluster is continuously performed to determine whether the fault is resolved. The present invention does not limit the method of determining whether the fault is resolved, which may be monitoring key parameters of fault diagnosis or performing diagnostic tests or manual intervention confirmation or fusion methods, etc. Monitoring key parameters of fault diagnosis may refer to continuously monitoring key parameters of fault diagnosis. If these parameters meet the normal working state standards, it means that the fault has been resolved. Performing diagnostic tests may refer to performing a series of self-tests or diagnostic tests on the diagnostic isolation vehicle. If the test results show that the unmanned vehicle system is working normally, it can be considered that the fault has been resolved. Manual intervention confirmation may refer to maintenance personnel confirming that the fault has been resolved through inspection and debugging. The fusion method may refer to combining the above multiple methods to confirm that the fault has been resolved.

[0076] Among them, after the fault state detection, the target vehicle set in the fault-related sub-cluster that meets the fault removal criteria is defined as {B} j, the corresponding target business task set is {P B} j . The FDI module unlinks the subcluster {B} j Isolate the fault and switch back to normal working mode, restart the suspended business tasks {P B} j .

[0077] Optionally, in an embodiment of the present invention, when contacting fault isolation, the second vehicle corresponding to the second business task with a high priority is fault-recovered and the corresponding second business task is restarted. If the second business task generates an associated service task, a corresponding remote safety officer resource is allocated to the second vehicle.

[0078] Optionally, in an alternative solution of the embodiment of the present invention, see Figure 3 , the unmanned vehicle risk control method provided by the embodiment of the present invention can also be expressed as:

[0079] S10: Divide the unmanned vehicle cluster into multiple sub-clusters through initial division i

[0080] S20, monitoring module real-time computing sub-cluster g i The service task arrival rate λ i ;

[0081] S30, setting threshold α i , when λ i ≥α i , regarded as subcluster g i A malfunction occurs;

[0082] S40,FDI module diagnoses faults through fault characterization and fault attribution;

[0083] S50, dynamically determine the fault-related unmanned vehicle sub-cluster h based on the FDI diagnosis result i ;

[0084] S60, FDI for fault-associated sub-cluster h j Perform fault isolation by downgrading business services;

[0085] S70, for the fault-associated sub-cluster h j Perform fault status detection and determine whether the fault is resolved;

[0086] S80, for the fault-associated sub-cluster h j For vehicles that meet the fault elimination criteria, the fault isolation is lifted and the vehicle is switched back to normal working mode.

[0087] The embodiment of the present invention provides a method for risk control of unmanned vehicles, by dividing an unmanned vehicle cluster into at least two subclusters; determining the service task arrival rate of the subclusters, and determining the preset arrival rate threshold corresponding to the service tasks; when the service task arrival rate is greater than or equal to the preset arrival rate threshold, determining that the current subcluster has a fault, and determining the external cause that affects the automatic driving capability of the unmanned vehicle; characterizing the external cause with geographic information, and attributing the fault based on the geographic information mark; diagnosing the unmanned vehicles included in the current subcluster based on the fault attribution result; determining the fault-related subcluster based on the fault diagnosis result, and isolating the fault-related subcluster to control the risk of the unmanned vehicle cluster. The technical solution of the embodiment of the present invention is adopted to monitor the occurrence of faults in real time, and proposes a fault diagnosis method based on characterization and attribution, which can integrate multiple algorithm implementation methods and can more accurately and dynamically determine the fault-related subcluster. In the fault-tolerant mode with limited degradation after a fault occurs, the fault-related sub-cluster is downgraded and the fault is isolated, while the normal unmanned vehicle sub-cluster is not affected, so that vehicles that meet the fault elimination standards can be dynamically and efficiently restored to normal working mode, effectively reducing the impact of the fault on the overall business service function of the unmanned vehicle cluster.

[0088] Embodiment 3

[0089] Figure 4 This is a schematic diagram of the structure of an unmanned vehicle cluster risk control device provided in an embodiment of the present invention. The technical solution of this embodiment can be applied to the situation of unmanned vehicle cluster risk control. The device can be implemented by software and / or hardware and is generally integrated on any electronic device with network communication function, including but not limited to: servers, computers, personal digital assistants and other devices. Figure 4 As shown, the unmanned vehicle cluster risk control device provided in this embodiment may include: a cluster division module 410, a task service determination module 420, a fault diagnosis module 430 and a risk control module 440; wherein,

[0090] A cluster division module 410, configured to divide the unmanned vehicle cluster into at least two sub-clusters;

[0091] The task service determination module 420 is used to determine the arrival rate of the service tasks of the sub-cluster and determine the preset arrival rate threshold corresponding to the service tasks; wherein the service task arrival rate is used to characterize the arrival number of the sub-cluster service tasks within a preset time interval;

[0092] A fault diagnosis module 430, configured to determine that a fault occurs in the current sub-cluster and perform fault diagnosis when the service task arrival rate is greater than or equal to a preset arrival rate threshold;

[0093] The risk control module 440 is used to determine the fault-related sub-clusters according to the fault diagnosis results, and perform fault isolation processing on the fault-related sub-clusters to perform risk control on the unmanned vehicle cluster.

[0094] Based on the above embodiment, optionally, the fault diagnosis module is specifically used to:

[0095] When the arrival rate of the service tasks is greater than or equal to a preset arrival rate threshold, determining that the current subcluster has a fault, and determining an external cause that affects the autonomous driving capability of the unmanned vehicle;

[0096] Characterize the external cause with geographic information, and attribute the fault according to the geographic information;

[0097] Perform fault diagnosis on the unmanned vehicles included in the current sub-cluster based on the fault attribution results.

[0098] Based on the above embodiments, optionally, the external factors affecting the autonomous driving capability of the unmanned vehicle include weather conditions, traffic environment, road conditions and infrastructure conditions; the geographic information representation method includes any one of a raster / grid model, a vector topology model, an object model, a kernel function model or a hybrid model.

[0099] Based on the above embodiment, optionally, the fault attribution method includes any one of a rule-based method, a data-driven method, a model-based method, a probability analysis method, a causal analysis method or a fusion method.

[0100] Based on the above embodiment, optionally, the risk control module is specifically used to:

[0101] Determine the fault-associated sub-cluster according to the fault diagnosis result, and determine the vehicle set and business task set corresponding to the fault-associated sub-cluster;

[0102] The vehicle set is sorted according to the priority of the business tasks, and a first unmanned vehicle corresponding to a first business task with a low priority is subjected to fault isolation processing; the fault isolation processing includes downgrading the first business task corresponding to the first unmanned vehicle, so as to convert the driving state of the first unmanned vehicle to a stationary state under safe conditions;

[0103] The remote safety resources corresponding to the first unmanned vehicle are released, and the remote safety resources are used to perform risk control on the unmanned vehicle corresponding to the high-priority business task.

[0104] Based on the above embodiment, optionally, the risk control module is further specifically used for:

[0105] Continuously monitor the fault status of the fault-associated sub-clusters and determine whether the fault has been resolved;

[0106] Determine a target vehicle set and a target business task set for troubleshooting, and perform fault recovery on a second vehicle corresponding to a second business task and restart the corresponding second business task according to the business task priority; wherein the second business task is a high-priority business task for priority sorting.

[0107] Based on the above embodiment, optionally, if the second business task generates an associated service task, corresponding remote safety officer resources are allocated to the second vehicle.

[0108] The unmanned vehicle cluster risk control device provided in the embodiments of the present invention can execute the unmanned vehicle cluster risk control method provided in any of the above embodiments of the present invention, and has the corresponding functions and beneficial effects of executing the unmanned vehicle cluster risk control method. For detailed processes, please refer to the relevant operations of the unmanned vehicle cluster risk control method in the above embodiments.

[0109] Embodiment 4

[0110] Figure 5 1 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0111] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0112] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0113] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the unmanned vehicle cluster risk control method.

[0114] In some embodiments, the unmanned vehicle cluster risk control method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the unmanned vehicle cluster risk control method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the unmanned vehicle cluster risk control method in any other appropriate manner (e.g., by means of firmware).

[0115] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0116] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0117] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0118] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0119] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0120] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0121] Embodiment 5

[0122] An embodiment of the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the unmanned vehicle cluster risk control method provided in any embodiment of the present application.

[0123] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0124] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0125] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for controlling the risk of unmanned vehicle clusters, characterized in that: The method comprises: Dividing the autonomous vehicle cluster into at least two subclusters; Determine the service task arrival rate of the sub-cluster, and determine the preset arrival rate threshold corresponding to the service task; wherein the service task arrival rate is used to characterize the arrival number of the sub-cluster service tasks within a preset time interval; When the service task arrival rate is greater than or equal to a preset arrival rate threshold, determining that the current sub-cluster has a fault and performing fault diagnosis; The fault-associated subclusters are determined based on the fault diagnosis results, and the fault-associated subclusters are isolated to perform risk control on the unmanned vehicle cluster.

2. The method according to claim 1, characterized in that When the arrival rate of the service tasks is greater than or equal to a preset arrival rate threshold, determining that a fault occurs in the current sub-cluster and performing fault diagnosis includes: When the arrival rate of the service tasks is greater than or equal to a preset arrival rate threshold, determining that the current subcluster has a fault, and determining an external cause that affects the autonomous driving capability of the unmanned vehicle; Characterize the external cause with geographic information, and attribute the fault according to the geographic information; Perform fault diagnosis on the unmanned vehicles included in the current sub-cluster based on the fault attribution results.

3. The method according to claim 2, characterized in that The external factors that affect the autonomous driving capability of the unmanned vehicle include weather conditions, traffic environment, road conditions and infrastructure conditions; the geographic information representation method includes any one of a raster / grid model, a vector topology model, an object model, a kernel function model or a hybrid model.

4. The method according to claim 2, characterized in that: The fault attribution method includes any one of a rule-based method, a data-driven method, a model-based method, a probability analysis method, a causal analysis method or a fusion method.

5. The method according to claim 1, characterized in that The method of determining the fault-associated sub-clusters according to the fault diagnosis results and isolating the fault-associated sub-clusters to perform risk control on the unmanned vehicle cluster includes: Determine the fault-associated sub-cluster according to the fault diagnosis result, and determine the vehicle set and business task set corresponding to the fault-associated sub-cluster; The vehicle set is sorted according to the priority of the business tasks, and a first unmanned vehicle corresponding to a first business task with a low priority is subjected to fault isolation processing; the fault isolation processing includes downgrading the first business task corresponding to the first unmanned vehicle, so as to convert the driving state of the first unmanned vehicle to a stationary state under safe conditions; The remote safety resources corresponding to the first unmanned vehicle are released, and the remote safety resources are used to perform risk control on the unmanned vehicle corresponding to the high-priority business task.

6. The method according to claim 5, characterized in that After performing fault isolation processing on the fault-associated sub-clusters, the method further includes: Continuously monitor the fault status of the fault-associated sub-clusters and determine whether the fault has been resolved; Determine a target vehicle set and a target business task set for troubleshooting, and perform fault recovery on a second vehicle corresponding to a second business task and restart the corresponding second business task according to the business task priority; wherein the second business task is a high-priority business task for priority sorting.

7. The method according to claim 6, characterized in that If the second business task generates an associated service task, a corresponding remote safety officer resource is allocated to the second vehicle.

8. An unmanned vehicle cluster risk control device, characterized in that: The device comprises: A cluster division module, used for dividing the unmanned vehicle cluster into at least two sub-clusters; A task service determination module is used to determine the arrival rate of the service tasks of the sub-cluster and determine the preset arrival rate threshold corresponding to the service tasks; wherein the service task arrival rate is used to characterize the arrival number of the sub-cluster service tasks within a preset time interval; A fault diagnosis module, used to determine that a fault occurs in the current sub-cluster and perform fault diagnosis when the arrival rate of the service task is greater than or equal to a preset arrival rate threshold; The risk control module is used to determine the fault-related sub-clusters according to the fault diagnosis results, and to perform fault isolation processing on the fault-related sub-clusters to perform risk control on the unmanned vehicle cluster.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the unmanned vehicle cluster risk control method described in any one of claims 1-7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the unmanned vehicle cluster risk control method as described in any one of claims 1-7.

Images