Simulation model construction method and device, equipment and computer storage medium

Abstract

The application discloses a simulation model construction method and device, equipment and a computer storage medium. Vehicle state data and vehicle control data having a corresponding relationship can be synchronized according to a preset synchronization time interval to obtain control synchronization data and state synchronization data corresponding to each synchronization node. The control synchronization data and the state synchronization data corresponding to any synchronization node are input into a simulation model, parameters of the simulation model are adjusted based on obtained model prediction data and control synchronization data of a first synchronization node after the synchronization node through a target algorithm. According to the embodiment of the application, a simulation model can be constructed. The simulation model is determined based on vehicle control data and vehicle state data through a target algorithm. It can be seen that the simulation model can more accurately simulate the vehicle state of a vehicle after receiving a control instruction in actual driving, improve the accuracy of the simulation result of the vehicle, and has low construction difficulty.

Description

Technical Field

[0001] This application belongs to the field of data processing, and in particular relates to a method, apparatus, device and computer storage medium for constructing simulation models. Background Technology

[0002] Typically, during the development of autonomous driving equipment, to save costs, simulation tests are conducted in a virtual environment on the models or algorithms integrated into the autonomous driving equipment, thereby identifying and resolving any problems. Among these tests, the ability of the vehicle dynamics model to accurately reflect changes in parameters such as speed and acceleration after receiving control commands plays a crucial role in the successful implementation of the autonomous driving simulation.

[0003] In existing technologies, vehicle dynamics models are often constructed using multi-degree-of-freedom (DOF) dynamics models. To more accurately simulate the vehicle's operating state, the degrees of freedom in these models are gradually increased. However, due to the increase in degrees of freedom, the number of model parameters that need to be defined also gradually increases, making the construction more difficult.

[0004] It is evident that in the process of constructing vehicle dynamics models, it is often difficult to balance the accuracy of the vehicle dynamics model with the difficulty of its construction. Summary of the Invention

[0005] This application provides a simulation model construction method, apparatus, device, and computer storage medium, which can more accurately simulate the vehicle state after receiving control commands during actual driving, improve the accuracy of vehicle simulation results, and has low construction difficulty, thus improving the efficiency of simulation model construction.

[0006] On the one hand, embodiments of this application provide a simulation model construction method, the method including:

[0007] Acquire vehicle status data and vehicle control data, wherein there is a corresponding relationship between the vehicle status data and the vehicle control data;

[0008] Based on the preset synchronization time interval, several synchronization nodes are determined in chronological order;

[0009] The vehicle status data and the vehicle control data are synchronized according to the synchronization time interval to obtain control synchronization data and status synchronization data corresponding to each synchronization node.

[0010] Input the control synchronization data and state synchronization data corresponding to any synchronization node into the simulation model to obtain the model prediction data output by the simulation model.

[0011] Based on the control synchronization data of the first synchronization node after the synchronization node and the model prediction data, the parameters of the simulation model are adjusted by the target algorithm.

[0012] Optionally, after adjusting the parameters of the simulation model using the target algorithm based on the control synchronization data of the first synchronization node after the synchronization node and the model prediction data, the method further includes:

[0013] The first driving trajectory of the unmanned driving device is determined according to the control synchronization data of the first synchronization node after the synchronization node, and the second driving trajectory of the unmanned driving device is determined according to the model prediction data.

[0014] When it is determined that the difference between the first driving trajectory and the second driving trajectory is greater than the preset error threshold, the process of inputting the control synchronization data and state synchronization data corresponding to any synchronization node into the simulation model is resumed, and the model prediction data output by the simulation model is obtained, until the difference between the first driving trajectory and the second driving trajectory is less than or equal to the error threshold.

[0015] When it is determined that the difference between the first driving trajectory and the second driving trajectory is less than or equal to the error threshold, the construction of the simulation model is completed.

[0016] Optionally, before synchronizing the vehicle status data and the vehicle control data according to the synchronization time interval to obtain the control synchronization data and status synchronization data corresponding to each synchronization node, the method further includes:

[0017] The control synchronization data and status synchronization data corresponding to the synchronization node are subjected to smoothing filtering.

[0018] Optionally, the control synchronization data and state synchronization data corresponding to any synchronization node are input into the simulation model to obtain the model prediction data output by the simulation model, specifically including:

[0019] The state synchronization data corresponding to any synchronization node is used as the hidden layer input and input into the hidden layer of the simulation model.

[0020] The control synchronization data corresponding to the synchronization node is used as model input and input into the simulation model;

[0021] The model prediction data output by the simulation model is obtained.

[0022] Optionally, the control synchronization data corresponding to the synchronization node is used as model input and input into the simulation model, specifically including:

[0023] According to the time sequence, based on the timestamps corresponding to the synchronization nodes, a number of synchronization nodes whose time interval with the synchronization nodes is less than a preset interval threshold are determined.

[0024] The state synchronization data corresponding to each of the plurality of synchronization nodes is used as model input and input into the simulation model.

[0025] Optionally, after adjusting the parameters of the simulation model using the target algorithm based on the control synchronization data of the first synchronization node after the synchronization node and the model prediction data, the method further includes:

[0026] Real-time driving data, real-time status data, and actual driving trajectory of the vehicle within a target time period are acquired at the first moment, wherein the target time period is after the first moment.

[0027] The real-time driving data and the real-time status data are input into the simulation model to obtain the model prediction data output by the simulation model.

[0028] Based on the simulated prediction data, the simulated driving trajectory is determined;

[0029] When it is determined that the error between the actual driving trajectory and the simulated driving trajectory is greater than a preset error threshold, the process of acquiring vehicle status data and vehicle control data is returned. The vehicle status data and the vehicle control data have a corresponding relationship, wherein the vehicle status data and the vehicle control data are data of the vehicle during driving.

[0030] On the other hand, embodiments of this application provide a simulation model construction apparatus, the apparatus comprising:

[0031] The acquisition unit is used to acquire vehicle status data and vehicle control data, wherein there is a corresponding relationship between the vehicle status data and the vehicle control data.

[0032] The determining unit is used to determine several synchronization nodes in chronological order according to a preset synchronization time interval.

[0033] The synchronization unit is used to synchronize the vehicle status data and the vehicle control data according to the synchronization time interval to obtain control synchronization data and status synchronization data corresponding to each synchronization node.

[0034] The input unit is used to input the control synchronization data and state synchronization data corresponding to any synchronization node into the simulation model to obtain the model prediction data output by the simulation model.

[0035] The construction unit is used to adjust the parameters of the simulation model using a target algorithm based on the control synchronization data of the first synchronization node after the synchronization node and the model prediction data.

[0036] Furthermore, embodiments of this application provide a simulation model construction device, the device comprising:

[0037] Processor and memory storing computer program instructions;

[0038] When the processor executes the computer program instructions, it implements the simulation model construction method as described above.

[0039] In another aspect, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the simulation model construction method as described in any of the preceding aspects.

[0040] In another aspect, embodiments of this application provide a computer program product, wherein the instructions in the computer program product, when executed by the processor of an electronic device, cause the electronic device to implement the simulation model construction method as described in any of the preceding aspects.

[0041] The simulation model construction method, apparatus, device, and computer storage medium of this application embodiment can construct simulation models. The simulation model takes vehicle control data and vehicle state data at a certain moment as input to obtain model prediction data output by the simulation model. Then, the vehicle's driving trajectory after that moment is compared with the model prediction data, and the simulation model is determined through a target algorithm. It can be seen that this simulation model can more accurately simulate the vehicle state after receiving control commands during actual driving, improving the accuracy of vehicle simulation results. Furthermore, this simulation model only requires data during vehicle driving and does not require analysis of the motion state of each vehicle component, making construction less difficult and more efficient. Attached Figure Description

[0042] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart illustrating a simulation model construction method provided in one embodiment of this application;

[0044] Figure 2 This is a schematic diagram of the structure of a simulation model building device provided in one embodiment of this application;

[0045] Figure 3 This is a schematic diagram of the structure of a simulation model building device provided in one embodiment of this application. Detailed Implementation

[0046] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0047] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0048] To address the problems of the prior art, embodiments of this application provide a simulation model construction method, apparatus, device, and computer storage medium. The simulation model construction method provided in this application embodiment will be described first below.

[0049] Figure 1 A flowchart illustrating a simulation model construction method provided in one embodiment of this application is shown. Figure 1 As shown, the simulation model construction method provided in this application embodiment includes the following steps: S101 to S105.

[0050] S101: Obtain vehicle status data and vehicle control data, wherein the vehicle status data and the vehicle control data have a corresponding relationship.

[0051] As described in the background section, during the development of autonomous driving equipment, the models or algorithms carried by the autonomous driving equipment are usually simulated and tested in a virtual environment to identify problems with the autonomous driving equipment.

[0052] However, when testing autonomous driving equipment in a virtual space, it is often necessary to make the simulated vehicle model in the virtual space simulate the response of a real vehicle. That is, after the control module in the simulated vehicle model sends control commands, the simulated vehicle model needs to change its speed, acceleration, and other motion states based on the control commands.

[0053] Typically, vehicle dynamics models are used to predict the motion state of an autonomous vehicle in the next moment or within a certain period of time, based on control commands and the motion state data of the autonomous vehicle at the current moment.

[0054] Existing vehicle dynamics models are often constructed using multi-degree-of-freedom dynamics models, such as 28-DOF lateral and longitudinal models, two-DOF bicycle models, and multibody dynamics models that are detailed down to the component or subsystem level. However, these models often involve a large amount of computation based on mathematical formulas, resulting in high computational complexity and long processing time. It is difficult to balance the accuracy of the vehicle dynamics model with the difficulty of its construction, and the prediction accuracy of the vehicle dynamics model is relatively low.

[0055] Therefore, in one or more embodiments of this application, a vehicle dynamics model, i.e. a simulation model, with high accuracy can be constructed quickly and efficiently.

[0056] In one or more embodiments of this application, the simulation model construction method can be determined by an electronic device. Of course, this electronic device can be a vehicle control center, mobile phone, tablet computer, server, or other similar devices. This application does not limit the specific type of electronic device and it can be configured as needed.

[0057] In one or more embodiments of this application, the electronic device may acquire vehicle driving data in order to construct the simulation model.

[0058] Specifically, the electronic device can acquire vehicle status data and vehicle control data. The vehicle status data includes data such as speed, acceleration, and vehicle steering angle. The vehicle control data includes vehicle control commands such as acceleration, deceleration, and steering. This application does not limit the specific data included in the vehicle control data and vehicle status data; they can be set as needed.

[0059] It should be noted that there is a correspondence between the vehicle status data and the vehicle control data; that is, both the vehicle control data and the vehicle status data are data collected by the same autonomous driving recognition system within the same time period.

[0060] In one or more embodiments of this application, when the autonomous driving device collects vehicle status data and vehicle control data, the vehicle status data and vehicle control data may be stored in various data formats such as binary data and Extensible Markup Language (XML). Therefore, in one or more embodiments of this application, after acquiring the vehicle status data and vehicle control data, the electronic device can convert both the vehicle status data and vehicle control data into text format. Furthermore, since the technology for converting data from various data formats such as XML and binary data into text format is relatively mature, for the sake of brevity, the specific conversion process will not be described in detail in this application.

[0061] Using the above method, the electronic device can acquire vehicle status data and vehicle control data in order to construct the simulation model.

[0062] S102: Determine several synchronization nodes in chronological order according to the preset synchronization time interval.

[0063] Since the vehicle status data and vehicle control data are usually continuous, while the input to the simulation model is discrete, the electronic device can determine several synchronization nodes in one or more embodiments of this application.

[0064] Specifically, in one or more embodiments of this application, the electronic device first obtains a preset time interval. This time interval can be 10ms, 20ms, 30ms, etc. The specific value of this time interval is not limited in this application and can be set as needed.

[0065] Secondly, the electronic device can determine several time nodes in chronological order. For example, when the time interval is 10ms, the electronic device can determine the time nodes as 10ms, 20ms, 30ms, 40ms, etc.

[0066] Since the vehicle status data and the vehicle control data may contain noise, in one or more embodiments of this application, the electronic device may perform smoothing filtering on the vehicle status data and the vehicle control data.

[0067] Using the above method, the electronic device can determine several time points for data synchronization.

[0068] S103: Synchronize the vehicle status data and the vehicle control data according to the synchronization time interval to obtain control synchronization data and status synchronization data corresponding to each synchronization node.

[0069] Specifically, in one or more embodiments of this application, the electronic device can synchronize the vehicle status data and the vehicle control data according to the synchronization time interval, that is, the vehicle control data in the first time interval after each synchronization node is determined as the corresponding control synchronization data for that time node. The vehicle status data in the first time interval after each synchronization node is determined as the corresponding status synchronization data for that time node.

[0070] For example, the time interval is 10ms, and the time nodes are 10ms, 20ms, 30ms, etc. This electronic device can determine the left turn command at 1ms, the deceleration command at 3ms, and the acceleration command at 9ms as the control synchronization data corresponding to 10ms.

[0071] Using the above method, the electronic device can synchronize the vehicle control data and the vehicle status data to each time node according to time intervals, so as to build the simulation model.

[0072] S104: Input the control synchronization data and state synchronization data corresponding to any synchronization node into the simulation model to obtain the model prediction data output by the simulation model.

[0073] In one or more embodiments of this application, after determining the control synchronization data and state synchronization data corresponding to each time node, the electronic device can input the control synchronization data and state synchronization data into the simulation model.

[0074] Specifically, the electronic device can randomly determine any time point from a range of time points, and then input the control synchronization data corresponding to that time point into the simulation model as the model input. The state synchronization data corresponding to that time point is also input into the simulation model as the hidden layer input. Finally, the model prediction data output by the simulation model is obtained.

[0075] However, since the vehicle needs a certain amount of time to adjust its state data after receiving the control synchronization data, in one or more embodiments of this application, the electronic device can determine a number of synchronization nodes from a number of time nodes whose time interval with the synchronization node is less than a preset interval threshold, based on the timestamp carried by the synchronization node. The timestamp represents the acquisition time of the control synchronization data and state synchronization data corresponding to that time node. Then, the state synchronization data corresponding to each of these synchronization nodes is used as model input and input into the simulation model. The model prediction data output by the simulation model is then obtained.

[0076] In one or more embodiments of this application, in order to construct the simulation model more accurately and efficiently, the electronic device may obtain timestamps of several time nodes, and then determine the time nodes used to train the simulation model according to the order corresponding to the timestamps.

[0077] Using the above method, the electronic device can input data corresponding to certain time points into the simulation model to obtain the model prediction data output by the simulation model.

[0078] S105: Based on the control synchronization data of the first synchronization node after the synchronization node and the model prediction data, adjust the parameters of the simulation model through the target algorithm.

[0079] In one or more embodiments of this application, the electronic device may train the simulation model based on the control synchronization data of the first synchronization node after the synchronization node and the model prediction data.

[0080] Specifically, in one or more embodiments of this application, the electronic device can adjust the parameters of the simulation model based on the control synchronization data of the first synchronization node after the synchronization node and the model test data, using a target algorithm. The target algorithm can be an algorithm used for training neural network models, such as backpropagation (BP). This application does not limit the specific algorithm used and it can be set as needed.

[0081] In one or more embodiments of this application, in order to more accurately determine the simulation model, the electronic device can determine a first driving trajectory of the autonomous vehicle when driving according to the state synchronization data, and a second driving trajectory of the autonomous vehicle when driving according to the model prediction data.

[0082] The electronic device can determine the error between the first driving trajectory and the second driving trajectory. When the electronic device determines that the error is greater than a preset error threshold, it returns to step S104 until the error is less than or equal to the error threshold. Since the technology for determining the error between two driving trajectories is relatively mature, it will not be elaborated upon here for the sake of brevity.

[0083] When the electronic device determines that the error is less than or equal to the error threshold, the training of the simulation model is completed.

[0084] In one or more embodiments of this application, in order to more accurately construct the simulation model, the electronic device can acquire real-time driving data, real-time status data, and the vehicle's actual driving trajectory during a target time period at a first moment. The first moment is adjacent to the target time period and precedes it.

[0085] The electronic device can input the real-time driving data and the real-time status data into the simulation model and obtain the model prediction data output by the simulation model.

[0086] Based on the model's predicted data, the electronic device can determine the simulated driving trajectory of the vehicle when it travels according to the model's predicted data. The electronic device can then determine the error between the simulated and actual driving trajectories, and further determine whether the error exceeds a preset error threshold. If so, the electronic device can return the acquired vehicle status data and vehicle control data. This vehicle status data and vehicle control data are data collected during the vehicle's operation. If not, the simulation model construction is complete.

[0087] The above describes the specific implementation of the simulation model construction method provided in the embodiments of this application. It can be seen that in the above embodiments,

[0088] This system can construct a simulation model. The simulation model takes vehicle control data and vehicle state data at a specific moment as input, and outputs model prediction data. Then, the vehicle's trajectory after that moment is compared with the model prediction data, and the simulation model is determined through a target algorithm. It is evident that this simulation model can more accurately simulate the vehicle's state after receiving control commands during actual driving, improving the accuracy of vehicle simulation results. Furthermore, the simulation model only requires data from the vehicle's driving process during construction, without needing to analyze the motion state of each vehicle component, making the construction process relatively simple and efficient.

[0089] Furthermore, the acquisition, storage, use, and processing of data in this application's technical solution all comply with relevant national laws and regulations.

[0090] Based on the simulation model construction method provided in the above embodiments, this application also provides specific implementation methods of the simulation model construction device. Please refer to the following embodiments.

[0091] First see Figure 2 The simulation model construction apparatus provided in this application embodiment includes the following units:

[0092] The acquisition unit 801 is used to acquire vehicle status data and vehicle control data, wherein there is a corresponding relationship between the vehicle status data and the vehicle control data.

[0093] The determining unit 802 is used to determine a number of synchronization nodes in chronological order according to a preset synchronization time interval;

[0094] Synchronization unit 803 is used to synchronize the vehicle status data and the vehicle control data according to the synchronization time interval to obtain control synchronization data and status synchronization data corresponding to each synchronization node.

[0095] The input unit 804 is used to input the control synchronization data and state synchronization data corresponding to any synchronization node into the simulation model to obtain the model prediction data output by the simulation model.

[0096] The construction unit 805 is used to adjust the parameters of the simulation model according to the control synchronization data of the first synchronization node after the synchronization node and the model prediction data through the target algorithm.

[0097] According to the above embodiment, the construction unit 805 can construct a simulation model. This simulation model is obtained by the input unit 804 taking vehicle control data and vehicle state data at a certain moment as input, and then outputting model prediction data. The construction unit 805 then compares the vehicle's trajectory after that moment with the model prediction data, and determines the simulation model through a target algorithm. Therefore, this simulation model can more accurately simulate the vehicle's state after receiving control commands during actual driving, improving the accuracy of vehicle simulation results. Furthermore, the simulation model only requires data from the vehicle's driving process during construction, without needing to analyze the motion state of each vehicle component, making construction less difficult and more efficient.

[0098] As another implementation of this application, in order to build a more accurate simulation model and improve the accuracy of the simulation model in simulating the vehicle state after receiving control commands during actual driving, the above-mentioned device may further include: a construction subunit 8051.

[0099] The construction subunit 8051 is used to determine the first driving trajectory of the unmanned driving device according to the control synchronization data of the first synchronization node after the synchronization node, and the second driving trajectory of the unmanned driving device according to the model prediction data. When it is determined that the difference between the first driving trajectory and the second driving trajectory is greater than a preset error threshold, the process returns to inputting the control synchronization data and state synchronization data corresponding to any synchronization node into the simulation model to obtain the model prediction data output by the simulation model, until the difference between the first driving trajectory and the second driving trajectory is less than or equal to the error threshold. When it is determined that the difference between the first driving trajectory and the second driving trajectory is less than or equal to the error threshold, the construction of the simulation model is completed.

[0100] As another implementation of this application, in order to construct a more accurate simulation model and improve the accuracy of the simulation model in simulating the vehicle state after receiving control commands during actual driving, the above-mentioned device may further include: an acquisition subunit 8011.

[0101] The acquisition subunit 8011 is used to perform smoothing filtering on the control synchronization data and status synchronization data corresponding to the synchronization node.

[0102] As another implementation of this application, in order to construct a more accurate simulation model and improve the accuracy of the simulation model in simulating the vehicle state after receiving control commands during actual driving, the above-mentioned device may further include: an input subunit 8041.

[0103] The input subunit 8041 is used to input the state synchronization data corresponding to any synchronization node as the hidden layer input into the hidden layer of the simulation model, and to input the control synchronization data corresponding to the synchronization node as the model input into the simulation model, so as to obtain the model prediction data output by the simulation model.

[0104] As another implementation of this application, in order to construct a more accurate simulation model and improve the accuracy of the simulation model in simulating the vehicle state after receiving control commands during actual driving, the above-mentioned device may further include: an input subunit 8042.

[0105] The input subunit 8042 is used to determine, according to the time sequence and the timestamp corresponding to the synchronization node, a number of synchronization nodes whose time interval with the synchronization node is less than a preset interval threshold, and input the state synchronization data corresponding to each of the number of synchronization nodes into the simulation model as model input.

[0106] As another implementation of this application, in order to build a more accurate simulation model and improve the accuracy of the simulation model in simulating the vehicle state after receiving control commands during actual driving, the above-mentioned device may further include: a construction subunit 8052.

[0107] The construction subunit 8052 is used to acquire real-time driving data, real-time status data, and the actual driving trajectory within a target time period at a first moment. The target time period is after the first moment. The real-time driving data and the real-time status data are input into the simulation model to acquire the model prediction data output by the simulation model. Based on the simulation prediction data, the simulated driving trajectory is determined. When the error between the actual driving trajectory and the simulated driving trajectory is determined to be greater than a preset error threshold, the acquisition of vehicle status data and vehicle control data is returned. The vehicle status data and the vehicle control data have a corresponding relationship, wherein the vehicle status data and the vehicle control data are data of the vehicle during driving.

[0108] Figure 3 A schematic diagram of the hardware structure for constructing the simulation model provided in this application embodiment is shown.

[0109] The simulation model building device may include a processor 901 and a memory 902 storing computer program instructions.

[0110] Specifically, the processor 901 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0111] Memory 902 may include mass storage for data or instructions. For example, and not limitingly, memory 902 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 902 may include removable or non-removable (or fixed) media. Where appropriate, memory 902 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 902 is non-volatile solid-state memory.

[0112] In a particular embodiment, memory 902 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, generally, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this disclosure.

[0113] The processor 901 reads and executes computer program instructions stored in the memory 902 to implement any of the simulation model construction methods in the above embodiments.

[0114] In one example, the simulation model building device may also include a communication interface 903 and a bus 910. For example, Figure 3 As shown, the processor 901, memory 902, and communication interface 903 are connected through bus 910 and complete communication with each other.

[0115] The communication interface 903 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0116] Bus 910 includes hardware, software, or both, that couples components of a simulation model building device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 910 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0117] This simulation model building device can execute the simulation model building method in this application embodiment based on currently blocked spam SMS messages and SMS messages reported by users, thereby achieving a combination of... Figure 1 and Figure 2 The simulation model construction method and apparatus are described.

[0118] Furthermore, in conjunction with the simulation model construction methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the simulation model construction methods in the above embodiments.

[0119] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method of this application is...

[0120] The procedure is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications and additions, or change the order of steps after understanding the spirit of this application.

[0121] The functional blocks shown in the above structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software,

[0122] The elements of this application are programs or code segments used to perform desired tasks. The program or code segment 0 may be stored on a machine-readable medium or transmitted via a data signal carried on a carrier wave through a transmission medium.

[0123] Alternatively, it can be transmitted over a communication link. "Machine-readable media" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and so on. Code segments can be downloaded via computer networks such as the Internet or intranets.

[0124] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0125] The above refers to the flow of methods, apparatus, and computer program products according to embodiments of the present disclosure.

[0126] The diagrams and / or block diagrams illustrate various aspects of this disclosure. It should be understood that each block in the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, or other programmable computer.

[0127] A processor of a data processing device to produce a machine such that these instructions, which are executed via a processor of a computer or other programmable data processing device, enable one or more flowcharts and / or block diagrams.

[0128] The implementation of the function / action specified in each block. This processor may be, but is not limited to, a general-purpose processor, a special-purpose processor, an application-specific processor, or a field-programmable logic circuit. It is also understood that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by dedicated hardware that performs the specified function or action, or by a combination of dedicated hardware and computer instructions.

[0129] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for constructing a simulation model, characterized in that, include: Acquire vehicle status data and vehicle control data, wherein there is a corresponding relationship between the vehicle status data and the vehicle control data; Based on the preset synchronization time interval, several synchronization nodes are determined in chronological order; The vehicle status data and the vehicle control data are synchronized according to the synchronization time interval to obtain control synchronization data and status synchronization data corresponding to each synchronization node. The vehicle control data in the first time interval after each synchronization node is determined as the control synchronization data corresponding to that time node, and the vehicle status data in the first time interval after each synchronization node is determined as the status synchronization data corresponding to that time node. Input the control synchronization data and state synchronization data corresponding to any synchronization node into the simulation model to obtain the model prediction data output by the simulation model. Based on the control synchronization data of the first synchronization node after the synchronization node and the model prediction data, the parameters of the simulation model are adjusted by the target algorithm; Specifically, the control synchronization data and state synchronization data corresponding to any synchronization node are input into the simulation model to obtain the model prediction data output by the simulation model, including: The state synchronization data corresponding to any synchronization node is used as the hidden layer input and input into the hidden layer of the simulation model. The control synchronization data corresponding to the synchronization node is used as model input and input into the simulation model; Obtain the model prediction data output by the simulation model; The method further includes, after adjusting the parameters of the simulation model using a target algorithm based on the control synchronization data of the first synchronization node following the synchronization node and the model prediction data: The first driving trajectory of the unmanned driving device is determined according to the control synchronization data of the first synchronization node after the synchronization node, and the second driving trajectory of the unmanned driving device is determined according to the model prediction data. When it is determined that the difference between the first driving trajectory and the second driving trajectory is greater than the preset error threshold, the process of inputting the control synchronization data and state synchronization data corresponding to any synchronization node into the simulation model is resumed, and the model prediction data output by the simulation model is obtained, until the difference between the first driving trajectory and the second driving trajectory is less than or equal to the error threshold. When it is determined that the difference between the first driving trajectory and the second driving trajectory is less than or equal to the error threshold, the construction of the simulation model is completed; or, Real-time driving data, real-time status data, and actual driving trajectory of the vehicle within a target time period are acquired at the first moment, wherein the target time period is after the first moment. The real-time driving data and the real-time status data are input into the simulation model to obtain the model prediction data output by the simulation model. Based on the model's prediction data, the simulated driving trajectory is determined; When it is determined that the error between the actual driving trajectory and the simulated driving trajectory is greater than a preset error threshold, the process of acquiring vehicle status data and vehicle control data is returned. The vehicle status data and the vehicle control data have a corresponding relationship, wherein the vehicle status data and the vehicle control data are data of the vehicle during driving.

2. The method according to claim 1, characterized in that, Before synchronizing the vehicle status data and the vehicle control data according to the synchronization time interval to obtain the control synchronization data and status synchronization data corresponding to each synchronization node, the method further includes: The control synchronization data and status synchronization data corresponding to the synchronization node are subjected to smoothing filtering.

3. The method according to claim 1, characterized in that, The control synchronization data corresponding to the synchronization node is used as model input and input into the simulation model, specifically including: According to the time sequence, based on the timestamps corresponding to the synchronization nodes, a number of synchronization nodes whose time interval with the synchronization nodes is less than a preset interval threshold are determined. The state synchronization data corresponding to each of the plurality of synchronization nodes is used as model input and input into the simulation model.

4. A simulation model construction device, characterized in that, The device includes: The acquisition unit is used to acquire vehicle status data and vehicle control data, wherein there is a corresponding relationship between the vehicle status data and the vehicle control data. The determining unit is used to determine a number of synchronization nodes in chronological order according to a preset synchronization time interval, wherein the number of time nodes is determined in chronological order and the number of synchronization nodes is determined based on the number of time nodes. The synchronization unit is used to synchronize the vehicle status data and the vehicle control data according to the synchronization time interval to obtain control synchronization data and status synchronization data corresponding to each synchronization node. The vehicle control data in the first time interval after each synchronization node is determined as the control synchronization data corresponding to that time node, and the vehicle status data in the first time interval after each synchronization node is determined as the status synchronization data corresponding to that time node. The input unit is used to input the control synchronization data and state synchronization data corresponding to any synchronization node into the simulation model to obtain the model prediction data output by the simulation model. A construction unit is used to adjust the parameters of the simulation model using a target algorithm based on the control synchronization data of the first synchronization node after the synchronization node and the model prediction data. The input unit is further configured to input the state synchronization data corresponding to any synchronization node as a hidden layer input into the hidden layer of the simulation model; input the control synchronization data corresponding to the synchronization node as a model input into the simulation model; and obtain the model prediction data output by the simulation model. The construction unit is further configured to, based on the control synchronization data of the first synchronization node after the synchronization node and the model prediction data, adjust the parameters of the simulation model using a target algorithm, and then determine a first driving trajectory of the autonomous vehicle according to the control synchronization data of the first synchronization node after the synchronization node, and a second driving trajectory of the autonomous vehicle according to the model prediction data; when it is determined that the difference between the first driving trajectory and the second driving trajectory is greater than a preset error threshold, return to inputting the control synchronization data and state synchronization data corresponding to any synchronization node into the simulation model to obtain the model prediction data output by the simulation model, until the difference between the first driving trajectory and the second driving trajectory is less than or equal to the error threshold; when it is determined that the difference between the first driving trajectory and the second driving trajectory is greater than a preset error threshold, return to inputting the control synchronization data and state synchronization data corresponding to any synchronization node into the simulation model to obtain the model prediction data output by the simulation model, until the difference between the first driving trajectory and the second driving trajectory is less than or equal to the error threshold; when it is determined that the difference between the first driving trajectory and the second driving trajectory is greater than or equal to the control synchronization data of the first synchronization node after the synchronization node, adjust the parameters of the simulation model using a target algorithm, and then determine a first driving trajectory of the autonomous vehicle according to the control synchronization data of the first synchronization node after the synchronization node, and a second driving trajectory of the autonomous vehicle according to the model prediction data ... second driving trajectory of the autonomous vehicle according to the control synchronization data of the first synchronization node after the synchronization node, and a second driving trajectory When the difference between the two driving trajectories is less than or equal to the error threshold, the simulation model is completed; or, real-time driving data, real-time status data, and the actual driving trajectory within a target time period are acquired at a first moment, the target time period being after the first moment; the real-time driving data and the real-time status data are input into the simulation model to obtain the model prediction data output by the simulation model; based on the model prediction data, the simulated driving trajectory is determined; when it is determined that the error between the actual driving trajectory and the simulated driving trajectory is greater than a preset error threshold, the process of acquiring vehicle status data and vehicle control data is returned, the vehicle status data and the vehicle control data having a corresponding relationship, wherein the vehicle status data and the vehicle control data are data of the vehicle during driving.

5. A simulation model building device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the simulation model construction method as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the simulation model construction method as described in any one of claims 1-3.

7. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the simulation model construction method as described in any one of claims 1-3.

Images