Vehicle control method and device, electronic equipment and medium

Abstract

A vehicle control method includes: obtaining a vehicle parameter of a target vehicle and a scene parameter of a scene where the target vehicle is located; if the vehicle parameter is within a preset vehicle parameter range and the scene parameter is within a preset scene parameter range, searching a strategy library for a target strategy corresponding to the vehicle parameter and the scene parameter; if the vehicle parameter is not within the preset vehicle parameter range or the scene parameter is not within the preset scene parameter range, inputting the vehicle parameter and the scene parameter into a pre-trained model to generate the target strategy; and controlling the target vehicle based on the target strategy. A vehicle control device, an electronic device, and a computer-readable storage medium are also disclosed.

Description

Technical Field

[0001] This application relates to the field of autonomous driving, and in particular to a vehicle control method, device, electronic device, and medium. Background Technology

[0002] As people's living standards gradually improve and the number of vehicles increases, the safety requirements for autonomous driving are becoming increasingly stringent.

[0003] In existing technologies, it is usually necessary to determine the vehicle's driving strategy based on the scenario in which the vehicle is located. Therefore, how to accurately determine the vehicle's driving strategy based on the scenario is an urgent problem to be solved. Summary of the Invention

[0004] According to embodiments of this disclosure, a vehicle control method, an electronic device, and a medium are provided. The technical solution is as follows:

[0005] According to a first aspect of the embodiments of this application, a vehicle control method is provided, comprising: acquiring vehicle parameters of a target vehicle and scene parameters of the scene in which the target vehicle is located; if the vehicle parameters are within a preset range of vehicle parameters and the scene parameters are within a preset range of scene parameters, then searching for a target policy corresponding to the vehicle parameters and the scene parameters in a policy library; if the vehicle parameters are not within the preset range of vehicle parameters or the scene parameters are not within the preset range of scene parameters, then inputting the vehicle parameters and the scene parameters into a pre-trained model to generate the target policy; and controlling the target vehicle based on the target policy.

[0006] According to a second aspect of the embodiments of this application, a vehicle control device is provided, comprising: an acquisition module configured to acquire vehicle parameters of a target vehicle and scene parameters of the scene in which the target vehicle is located; a search module configured to search for a target policy corresponding to the vehicle parameters and the scene parameters in a policy library if the vehicle parameters are within a preset range of vehicle parameters and the scene parameters are within a preset range of scene parameters; a generation module configured to input the vehicle parameters and the scene parameters into a pre-trained model to generate the target policy if the vehicle parameters are not within the preset range of vehicle parameters or the scene parameters are not within the preset range of scene parameters; and a control module configured to control the target vehicle based on the target policy.

[0007] According to a third aspect of the embodiments of this application, an electronic device is provided, comprising: a memory for storing computer-readable instructions; and a processor for reading the computer-readable instructions stored in the memory to execute the vehicle control method described above.

[0008] According to a fourth aspect of the present invention, a non-transitory computer-readable storage medium is provided, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by a processor of a computer, the computer performs the vehicle control method described above.

[0009] The technical solutions provided by the embodiments of this application may include the following beneficial effects:

[0010] In some embodiments of this application, the technical solutions are as follows: Vehicle parameters of the target vehicle and scene parameters of the scene in which the target vehicle is located are obtained; if the vehicle parameters are within a preset range and the scene parameters are within a preset range, a target strategy corresponding to the vehicle parameters and scene parameters is searched in the strategy library; if the vehicle parameters are not within the preset range or the scene parameters are not within the preset range, the vehicle parameters and scene parameters are input into a pre-trained model to generate a target strategy; the target vehicle is controlled based on the target strategy, thereby finding the target strategy of the target vehicle in multiple scenarios, better controlling the target vehicle, and increasing the stability of determining the driving strategy of the vehicle according to the scenario. Attached Figure Description

[0011] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the principles of this application.

[0012] Figure 1 A schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of this application can be applied is shown;

[0013] Figure 2 A flowchart illustrating a vehicle control method according to an embodiment of this application is shown schematically.

[0014] Figure 3 The diagram schematically illustrates the architecture of a vehicle control method according to an embodiment of this application;

[0015] Figure 4 A block diagram of a vehicle control device according to one embodiment of this application is shown schematically;

[0016] Figure 5 This is a hardware diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0017] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0018] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0019] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0020] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0021] Figure 1 A schematic diagram of an exemplary system architecture 100 to which the technical solutions of the embodiments of this application can be applied is shown.

[0022] like Figure 1 As shown, system architecture 100 may include client 101, network 102, and server 103. Network 102 is used as a medium to provide a communication link between client 101 and server 103. Network 102 may include various connection types, such as wired communication links, wireless communication links, etc., which are not limited herein.

[0023] It should be understood that Figure 1The number of clients 101, networks 102, and servers 103 shown is merely illustrative. Depending on implementation needs, there can be any number of clients 101, networks 102, and servers 103. For example, server 103 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms. Client 101 can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these.

[0024] In one embodiment of this application, server 103 obtains vehicle parameters of the target vehicle and scene parameters of the scene in which the target vehicle is located; if the vehicle parameters are within a preset range and the scene parameters are within a preset range, the server searches for the target policy corresponding to the vehicle parameters and scene parameters in the policy library; if the vehicle parameters are not within the preset range or the scene parameters are not within the preset range, the server inputs the vehicle parameters and scene parameters into a pre-trained model to generate a target policy; the server controls the target vehicle based on the target policy, thereby finding the target policy of the target vehicle in multiple scenarios, better controlling the target vehicle, and increasing the stability of determining the driving policy of the vehicle according to the scenario.

[0025] It should be noted that the vehicle control method provided in this application embodiment is generally executed by server 103, and correspondingly, the vehicle control device is generally located in server 103. However, in other embodiments of this application, client 101 may also have similar functions to server 103, thereby executing the vehicle control method provided in this application embodiment.

[0026] The implementation details of the technical solutions in the embodiments of this application are described in detail below:

[0027] Figure 2 The schematic diagram illustrates a flowchart of a vehicle control method according to an embodiment of this application. The vehicle control method can be executed by a server, for example, a... Figure 1 Server 103 is shown in the image.

[0028] Reference Figure 2 As shown, the vehicle control method includes at least steps S210 to S240, which are described in detail below:

[0029] In step S210, the vehicle parameters of the target vehicle and the scene parameters of the scene in which the target vehicle is located are obtained.

[0030] In one embodiment of this application, vehicle parameters may include the target vehicle's position, speed, size, presence or absence of traffic signal control, and whether the vehicle is lying on its side. Scene parameters may include surrounding vehicle parameters, road parameters, and surrounding non-motorized vehicle parameters. Surrounding vehicle parameters may include vehicle position, speed, size, presence or absence of traffic signal control, and whether the vehicle is lying on its side. Road parameters may include radius of curvature, number of lanes, presence or absence of traffic lights, and whether any vehicles are lying on their side. Surrounding non-motorized vehicle parameters may include non-motorized vehicle position, speed, size, and presence or absence of traffic signal control. Non-motorized vehicle types may include pedestrians, motorcycles, bicycles, and electric vehicles. Scene parameters should be selected based on scene characteristics, ensuring both a certain degree of scene independence and considering scene coverage.

[0031] In one embodiment of this application, the scene in which the target vehicle is located can be obtained; the scene parameters of the scene in which the target vehicle is located can be obtained by parsing the scene.

[0032] In step S220, if the vehicle parameters are within the preset vehicle parameter range and the scene parameters are within the preset scene parameter range, then the target strategy corresponding to the vehicle parameters and scene parameters is searched in the strategy library.

[0033] In one embodiment of this application, the preset vehicle parameter range can be pre-set, and the vehicle parameter range and the scene parameter range can correspond to each other. It can be that a specified scene parameter corresponds to a specified vehicle parameter range. When the scene parameter changes, the vehicle parameter range corresponding to the scene parameter also changes.

[0034] In one embodiment of this application, a specified vehicle parameter range can be determined based on the parameters of the vehicle under extreme conditions under specified scenario parameters.

[0035] In one embodiment of this application, the range of scene parameters can be determined based on scene parameters in extreme scenarios, and the range of vehicle parameters can be determined based on the range of scene parameters. The extreme scenarios can be set based on date, time, location, weather, road conditions, terrain, etc.

[0036] In one embodiment of this application, before searching for the target policy corresponding to the vehicle parameters and scene parameters in the policy library, an optimized online model, such as a partially objective Markov autonomous driving policy model, can be developed. Simulation data, including vehicle simulation data and scene simulation data, can be obtained. The simulation data is then input into a partially observable Markov Decision Processes (POMDP) ​​to obtain the predicted policy corresponding to the simulation data output by the partially observable Markov autonomous driving policy model. The simulation data and the predicted policy are stored accordingly to form a policy library.

[0037] In one embodiment of this application, the strategy library can be retrieved using methods such as Structured Query Language (SQL), and the strategy library can be an offline database.

[0038] In step S230, if the vehicle parameters are not within the preset vehicle parameter range, or the scene parameters are not within the preset scene parameter range, the vehicle parameters and scene parameters are input into the pre-trained model to generate the target strategy.

[0039] In one embodiment of this application, the scene simulation data includes dynamic simulation data and static simulation data. Before inputting vehicle parameters and scene parameters into the pre-trained model, the vehicle simulation data, dynamic simulation data, and static simulation data can be clustered separately. The k-Nearest Neighbors (KNN) algorithm can be used for clustering to obtain vehicle clustering results, dynamic clustering results, and static clustering results. Training data is generated based on the vehicle clustering results, dynamic clustering results, and static clustering results. The training data includes vehicle training data, dynamic training data, and static training data. The neural network model is trained using the training data to obtain the pre-trained model.

[0040] In one embodiment of this application, the neural network model can be a partially observable Markov model, a classification model such as a random forest, or a deep learning model.

[0041] In one embodiment of this application, the correspondence between vehicle simulation data, dynamic simulation data and static simulation data can be determined based on the scenario and the vehicle parameters suitable for the scenario. The corresponding vehicle simulation data, dynamic simulation data and static simulation data are treated as a group of parameters, and the vehicle simulation data, dynamic simulation data and static simulation data are clustered simultaneously in groups.

[0042] In this embodiment, the vehicle simulation data, dynamic simulation data, and static simulation data are distributed independently. For example, they can be distinguished and controlled by the mean and variance of the distribution. The vehicle simulation data, dynamic simulation data, and static simulation data can also be generated through simulation.

[0043] In one embodiment of this application, vehicle training data can be selected from vehicle clusters in the vehicle clustering results, where the difference between the vehicle training data and the vehicle cluster is greater than a set minimum vehicle difference; dynamic training data can be selected from dynamic clusters in the dynamic clustering results, where the difference between the dynamic training data and the vehicle cluster is greater than a set minimum dynamic difference; and static training data can be selected from static clusters in the static clustering results, where the difference between the static training data and the static cluster is greater than a set minimum static difference. This allows the vehicle training data, dynamic training data, and static training data to comprehensively cover multiple scenarios as much as possible. At the same time, compared to directly training the neural network model using vehicle simulation data, dynamic simulation data, and static simulation data, training the neural network model using vehicle training data, dynamic training data, and static training data can save training time.

[0044] In one embodiment of this application, the preset vehicle parameter range and the preset scenario parameter range can be determined based on simulation data.

[0045] In one embodiment of this application, the relationship between vehicle parameters, scene parameters, and target policy can be constructed using a decision tree, or using a reinforcement learning algorithm (Q-learning) or a deep learning network.

[0046] In one embodiment of this application, if the vehicle parameters are not within the preset vehicle parameter range, or the scene parameters are not within the preset scene parameter range, the vehicle parameters, scene parameters and target strategies can be stored in the strategy library.

[0047] In one embodiment of this application, a suggested vehicle parameter range can be determined based on scenario parameters; if the suggested vehicle parameter range does not intersect with the target vehicle's capability vehicle parameter range, it can be determined that the target vehicle cannot operate in the scenario in which the target vehicle is located. The suggested vehicle parameter range is used to represent the parameters that allow the target vehicle to drive without damage in the scenario corresponding to the scenario parameters; the capability vehicle parameter range can be obtained based on the target vehicle's driving situation in a standard scenario, which is the scenario in which the vehicle is most suitable to drive.

[0048] In this embodiment, the limitations of the target vehicle's mobility are taken into account, enabling better control of the target vehicle.

[0049] Continue to refer to Figure 2 In step S240, the target vehicle is controlled based on the target strategy.

[0050] exist Figure 2In this embodiment, the vehicle parameters of the target vehicle and the scene parameters of the scene in which the target vehicle is located are obtained; if the vehicle parameters are within a preset range and the scene parameters are within a preset range, the target policy corresponding to the vehicle parameters and scene parameters is searched in the policy library; if the vehicle parameters are not within the preset range or the scene parameters are not within the preset range, the vehicle parameters and scene parameters are input into a pre-trained model to generate a target policy; the target vehicle is controlled based on the target policy, thereby finding the target policy of the target vehicle in multiple scenarios, better controlling the target vehicle, and increasing the stability of determining the driving policy of the vehicle according to the scenario.

[0051] In one embodiment of this application, the vehicle control method utilizes an offline database strategy and an online model generation strategy. The offline strategy leverages existing data to address autonomous driving strategies under complex conditions, considering both static driving scenarios and dynamic traffic participants during the decision-making process, while also taking into account the limitations of vehicle mobility. The offline strategy categorizes scenarios based on static scene and dynamic traffic participant characteristics, calculates the optimal strategy using optimization algorithms, and generates an optimal strategy library based on the optimal strategies under different static scene and dynamic traffic participant characteristics. The optimal strategy can be directly queried based on scenario matching. To overcome the shortcomings of the offline strategy, which customizes the optimal strategy library for specific static scene and dynamic traffic participant characteristics and cannot cover all possible scenarios and pre-calculated strategies for vehicle configuration, this application also proposes an online strategy. The online strategy generates autonomous driving strategies based on uncovered scenarios, solving the decision-making problem for unknown scenarios, and stores the calculated optimal strategy in the offline strategy library, improving the capability and coverage of the offline strategy.

[0052] In one embodiment of this application, the vehicle control system architecture for implementing the vehicle control method of this application is as follows: Figure 3 As shown. Figure 3 A schematic diagram of the architecture of a vehicle control system according to an embodiment of this application is shown. Figure 3As shown, the vehicle control system may include: a scene identifier, a pre-consideration, a policy library, and an online solver. The scene identifier is used to obtain the vehicle parameters of the target vehicle and the scene parameters of the scene in which the target vehicle is located. The pre-consideration is used to determine whether the vehicle parameters are within a preset range of vehicle parameters, and also to determine whether the scene parameters are within a preset range of scene parameters. The policy library is used to store vehicle control policies when both the vehicle parameters and scene parameters are within a preset range of scene parameters. The policies stored in the policy library may come from an offline server. The optimal policy can be found in the policy library. The online server is used to generate the optimal policy when either the vehicle parameters or scene parameters are not within a preset range of vehicle parameters or scene parameters. Using the vehicle control method of this invention, autonomous vehicles can adapt to unknown scenarios and achieve autonomous driving strategies using limited data. The driving strategy continuously improves its performance in real-world scenarios to achieve adaptive capabilities.

[0053] The following describes an embodiment of the apparatus described in this application, which can be used to execute the vehicle control method described in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the vehicle control method described above.

[0054] Figure 4 A block diagram of a vehicle control device according to one embodiment of this application is shown schematically.

[0055] Reference Figure 4 As shown, a vehicle control device 400 according to an embodiment of this application includes an acquisition module 401, a search module 402, a generation module 403, and a control module 404.

[0056] According to one aspect of the embodiments of this application, based on the foregoing scheme, the acquisition module 401 is configured to acquire vehicle parameters of the target vehicle and scene parameters of the scene in which the target vehicle is located; the search module 402 is configured to search for the target policy corresponding to the vehicle parameters and scene parameters in the policy library if the vehicle parameters are within a preset range of vehicle parameters and the scene parameters are within a preset range of scene parameters; the generation module 403 is configured to input the vehicle parameters and scene parameters into a pre-trained model to generate a target policy if the vehicle parameters are not within a preset range of vehicle parameters or the scene parameters are not within a preset range of scene parameters; and the control module 404 is configured to control the target vehicle based on the target policy.

[0057] In one embodiment of this application, based on the aforementioned scheme, before searching for the target strategy corresponding to the vehicle parameters and scene parameters in the strategy library, the search module 402 is configured to: acquire simulation data, including vehicle simulation data and scene simulation data; input the simulation data into a partially observable Markov autonomous driving strategy model to obtain the prediction strategy corresponding to the simulation data output by the partially observable Markov autonomous driving strategy model; and store the simulation data and prediction strategy accordingly to form a strategy library.

[0058] In one embodiment of this application, based on the aforementioned scheme, the scene simulation data includes dynamic simulation data and static simulation data. Before inputting vehicle parameters and scene parameters into the pre-trained model, the generation module 403 is further configured to: cluster the vehicle simulation data, dynamic simulation data, and static simulation data respectively to obtain vehicle clustering results, dynamic clustering results, and static clustering results; generate training data based on the vehicle clustering results, dynamic clustering results, and static clustering results, wherein the training data includes vehicle training data, dynamic training data, and static training data; and use the training data to train the neural network model to obtain the pre-trained model.

[0059] In one embodiment of this application, based on the aforementioned scheme, the generation module 403 is configured to: select vehicle training data from vehicle clusters in the vehicle clustering results, wherein the difference between the vehicle training data and the same vehicle cluster is greater than a set minimum vehicle difference; select dynamic training data from dynamic clusters in the dynamic clustering results, wherein the difference between the dynamic training data and the same dynamic cluster is greater than a set minimum dynamic difference; and select static training data from static clusters in the static clustering results, wherein the difference between the static training data and the same static cluster is greater than a set minimum static difference. Difference refers to the distance between cluster data within the same cluster.

[0060] In one embodiment of this application, based on the foregoing scheme, before obtaining the vehicle parameters of the target vehicle and the scene parameters of the scene in which the target vehicle is located, the acquisition module 401 is further configured to: acquire the scene in which the target vehicle is located; and parse the scene to obtain the scene parameters of the scene in which the target vehicle is located.

[0061] In one embodiment of this application, based on the aforementioned scheme, if the vehicle parameters are not within the preset vehicle parameter range, after generating the target strategy, the generation module 403 is further configured to: store the vehicle parameters, scene parameters and target strategy in the strategy library.

[0062] In one embodiment of this application, based on the foregoing scheme, after obtaining the vehicle parameters of the target vehicle and the scene parameters of the scene in which the target vehicle is located, the control module 404 is further configured to: determine the suggested vehicle parameter range of the vehicle based on the scene parameters; if the suggested vehicle parameter range does not intersect with the capability vehicle parameter range of the target vehicle, then it is determined that the target vehicle cannot operate in the scene in which the target vehicle is located.

[0063] Those skilled in the art will understand that various aspects of this application can be implemented as a system, method, or program product. Therefore, various aspects of this application can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, collectively referred to herein as a "circuit," "module," or "system."

[0064] The following reference Figure 5 To describe an electronic device 50 according to this embodiment of the present application. Figure 5 The electronic device 50 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0065] like Figure 5 As shown, the electronic device 50 is presented in the form of a general-purpose computing device. The components of the electronic device 50 may include, but are not limited to: at least one processing unit 51, at least one storage unit 52, a bus 53 connecting different system components (including storage unit 52 and processing unit 51), and a display unit 54.

[0066] The storage unit stores program code that can be executed by the processing unit 51, causing the processing unit 51 to perform the steps described in the "Embodiment Method" section above according to various exemplary embodiments of this application.

[0067] Storage unit 52 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 521 and / or a cache memory unit 522, and may further include a read-only memory unit (ROM) 523.

[0068] Storage unit 52 may also include a program / utility 524 having a set (at least one) program module 525, such program module 525 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0069] Bus 53 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0070] Electronic device 50 can also communicate with one or more external devices (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 50, and / or any device that enables electronic device 50 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 55. Furthermore, electronic device 50 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 56. As shown, network adapter 56 communicates with other modules of electronic device 50 via bus 53. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with electronic device 50, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0071] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this application.

[0072] According to one embodiment of this application, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above in this specification is stored. In some possible implementations, various aspects of this application may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of this application described in the "Exemplary Methods" section of this specification.

[0073] According to one embodiment of this application, a non-transitory computer-readable storage medium is also provided, on which computer-readable instructions are stored, which, when executed by a computer's processor, cause the computer to perform the above-described vehicle control method.

[0074] According to one embodiment of this application, the program product for implementing the above method can be a portable compact disc read-only memory (CD-ROM) and include program code, and can run on a terminal device, such as a personal computer. However, the program product of this application is not limited thereto. In this document, the readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0075] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0076] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0077] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0078] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0079] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this application, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0080] It should be understood that this application is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A vehicle control method, characterized in that, include: Acquire simulation data, which includes vehicle simulation data and scene simulation data, wherein the scene simulation data includes dynamic simulation data and static simulation data; The simulated data is input into a partially observable Markov autonomous driving policy model to obtain the prediction policy corresponding to the simulated data output by the partially observable Markov autonomous driving policy model. The simulation data and the prediction strategy are stored accordingly to form a strategy library, which is offline; The vehicle simulation data, the dynamic simulation data, and the static simulation data are clustered respectively to obtain vehicle clustering results, dynamic clustering results, and static clustering results; Training data is generated based on the vehicle clustering results, the dynamic clustering results, and the static clustering results. The training data includes vehicle training data, dynamic training data, and static training data. The neural network model is trained using the training data to obtain a pre-trained model, which is online; Obtain the vehicle parameters of the target vehicle and the scene parameters of the scene in which the target vehicle is located; If the vehicle parameters are within a preset range and the scene parameters are within a preset range, then the target strategy corresponding to the vehicle parameters and the scene parameters is searched in the strategy library. If the vehicle parameters are not within the preset vehicle parameter range, or the scene parameters are not within the preset scene parameter range, then the vehicle parameters and the scene parameters are input into the pre-trained model to generate the target strategy; The target vehicle is controlled based on the target strategy.

2. The vehicle control method according to claim 1, characterized in that, The generation of training data based on the vehicle clustering results, the dynamic clustering results, and the static clustering results includes: The vehicle training data is selected from the vehicle clusters in the vehicle clustering results, and the difference between the vehicle training data in the same vehicle cluster is greater than the set minimum vehicle difference. The dynamic training data is selected from the dynamic clusters of the dynamic clustering results, and the difference between the dynamic training data and the dynamic clusters is greater than the set minimum dynamic difference. The static training data is selected from the static clusters of the static clustering results, wherein the difference between the static training data and the static clusters is greater than the set minimum static difference.

3. The vehicle control method according to claim 1, characterized in that, Before obtaining the vehicle parameters of the target vehicle and the scene parameters of the scene in which the target vehicle is located, the method further includes: Obtain the scene where the target vehicle is located; The scene parameters of the scene in which the target vehicle is located are obtained by parsing the scene.

4. The vehicle control method according to claim 1, characterized in that, If the vehicle parameters are not within the preset vehicle parameter range, then after generating the target strategy, the method further includes: The vehicle parameters, the scene parameters, and the target strategy are stored in the strategy library.

5. The vehicle control method according to claim 1, characterized in that, After obtaining the vehicle parameters of the target vehicle and the scene parameters of the scene in which the target vehicle is located, the method further includes: Based on the scenario parameters, determine the recommended range of vehicle parameters for the vehicle; If the suggested vehicle parameter range does not intersect with the target vehicle's capability vehicle parameter range, then it is determined that the target vehicle cannot operate in the scenario in which the target vehicle is located.

6. A vehicle control device, characterized in that, include: The acquisition module is configured to acquire vehicle parameters of the target vehicle and scene parameters of the scene in which the target vehicle is located; The search module is configured to acquire simulation data, which includes vehicle simulation data and scene simulation data. The scene simulation data includes dynamic simulation data and static simulation data. The simulation data is input into a partially observable Markov autonomous driving strategy model to obtain the prediction strategy output by the partially observable Markov autonomous driving strategy model corresponding to the simulation data. The simulation data and the prediction strategy are stored accordingly to form a strategy library, which is offline. The search module is further configured to search for the target strategy corresponding to the vehicle parameters and the scene parameters in the strategy library if the vehicle parameters are within a preset vehicle parameter range and the scene parameters are within a preset scene parameter range. The generation module is configured to cluster the vehicle simulation data, the dynamic simulation data, and the static simulation data respectively to obtain vehicle clustering results, dynamic clustering results, and static clustering results; generate training data based on the vehicle clustering results, the dynamic clustering results, and the static clustering results; the training data includes vehicle training data, dynamic training data, and static training data; and use the training data to train a neural network model to obtain a pre-trained model, wherein the pre-trained model is online. The generation module is further configured to input the vehicle parameters and the scene parameters into a pre-trained model to generate the target strategy if the vehicle parameters are not within the preset vehicle parameter range or the scene parameters are not within the preset scene parameter range. The control module is configured to control the target vehicle based on the target strategy.

7. An electronic device, characterized in that, include: Memory, used to store computer-readable instructions; and A processor for reading computer-readable instructions stored in the memory to execute any one of the vehicle control methods of claims 1-5.

8. A non-transitory computer-readable storage medium having stored computer-readable instructions thereon, which, when executed by a processor of a computer, cause the computer to perform any one of the vehicle control methods of claims 1-5.

Images