Simulation test method, system, device and equipment for intelligent driving and medium

Through the encoding and decoding technology of WebSocket connection and cloud simulation platform, the delay problem caused by massive data processing in intelligent driving simulation test is solved, real-time feedback and efficient scene presentation of simulation tests are realized.

CN118938705APending Publication Date: 2024-11-12CHONGQING CHANGAN AUTOMOBILE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410849164.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-27
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In intelligent driving simulation test, the processing of massive simulation data cannot be done in real time, which affects the accuracy and efficiency of the test.

Method used

Receive massive simulation data sent by the server in real time through WebSocket connection, and perform encoding and decoding operations on the cloud simulation platform, shortening transmission time and speeding up the establishment and presentation of simulation scenarios.

Benefits of technology

Real-time feedback of simulation results in simulation tests is realized, the establishment and presentation speed of simulation scenarios is improved, and the delay problem caused by massive data processing is solved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118938705A_ABST
    Figure CN118938705A_ABST
Patent Text Reader

Abstract

The invention relates to a simulation test method, system, device and equipment for intelligent driving and a medium, and the method comprises the steps: building a WebSocket connection with a server under the condition that a test control of a cloud simulation platform is detected to be triggered; when a test instruction selected by the target object is received, generating a test request carrying the test instruction, and sending the test request to the server; receiving first simulation data returned by the server through the WebSocket connection, and performing encoding and decoding operation on the first simulation data through the cloud simulation platform to construct and display an initial simulation scene; under the condition that an operation instruction triggered by the target object is detected, the cloud simulation platform is used for carrying out encoding and decoding operation on the operation instruction and the first simulation data, and second simulation data is obtained; and rendering the second simulation data to the initial simulation scene, and obtaining and displaying a simulation test result. The technical problem that a simulation result cannot be fed back in real time due to the fact that massive simulation data is processed for a long time during simulation testing is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to an intelligent driving simulation test method, system, device, equipment and medium. Background Art

[0002] With the continuous development of intelligent driving technology, more and more assisted driving functions and even autonomous driving functions have been introduced. The development and testing of intelligent driving related algorithms and functions have become an extremely important part of intelligent driving. The reliability of intelligent driving has also become the main obstacle for intelligent driving systems to move from the research and development stage to industrialization. Before conducting road tests on intelligent driving functions, simulation test scenarios are usually constructed and intelligent driving algorithms are simulated and tested in advance in the constructed simulation scenarios to verify the confidence and feasibility of the algorithms.

[0003] The main purpose of intelligent driving simulation testing is to simulate real-world driving scenarios in a virtual environment to evaluate the performance of the autonomous driving system. Due to the complexity and diversity of driving scenarios, in order to improve the accuracy and precision of simulation testing, the data required for simulation is often massive. If massive simulation data is simulated on the simulation platform, the large amount of data may affect the processing performance, resulting in the inability to feedback the simulation results in real time due to the long time spent processing massive simulation data during simulation testing. Summary of the invention

[0004] The present application provides a simulation test method, system, device, equipment and medium for intelligent driving to solve the technical problem that simulation results cannot be fed back in real time due to the long time spent processing massive simulation data during simulation testing.

[0005] In the first aspect, the present application provides a simulation test method for intelligent driving, which is applied to a client, including: when it is detected that a test control of a cloud simulation platform is triggered, establishing a WebSocket connection with a server; when a test instruction selected by a target object is received, generating a test request carrying the test instruction, and sending the test request to the server, so that the server parses the test request and generates a large amount of first simulation data; receiving the first simulation data returned by the server through the WebSocket connection, and encoding and decoding the first simulation data through the cloud simulation platform to construct and display an initial simulation scene; when an operation instruction triggered by the target object is detected, using the cloud simulation platform to encode and decode the operation instruction and the first simulation data to obtain second simulation data; rendering the second simulation data to the initial simulation scene to obtain and display the simulation test results.

[0006] Optionally, when a test instruction selected by the target object is received, a test request carrying the test instruction is generated and sent to the server, including: obtaining static environment information and dynamic environment information of the simulation scenario used to execute the test instruction; determining the test instruction, static environment information and dynamic environment information as a test request; and sending the test request to the server via a WebSocket connection.

[0007] Optionally, encoding and decoding operations are performed on the first simulation data through the cloud simulation platform to construct and display an initial simulation scene, including: using the back end of the cloud simulation platform to encode and compress the first simulation data to obtain first encoded data; sending the first encoded data to the front end of the cloud simulation platform, and decoding the first encoded data through the front end to obtain first decoded data; rendering the first decoded data to obtain an initial simulation scene.

[0008] Optionally, the first simulation data is encoded and compressed using the back end of the cloud simulation platform to obtain first encoded data, including: setting a coding interval and determining the probability distribution of each character in the first simulation data; dividing the coding interval into multiple sub-intervals according to the probability distribution, and mapping each character to the sub-interval according to the probability distribution; reading each character in the first simulation data in turn, and updating the coding interval according to the read characters and the sub-intervals to which the characters belong; after completing the reading of each character in the first simulation data, obtaining the latest target coding interval; extracting the shortest decimal from the target coding interval, and converting the decimal into a binary number to obtain the first encoded data.

[0009] Optionally, the first encoded data is decoded by the front end to obtain the first decoded data, including: converting the first encoded data into a decimal number by the front end; obtaining a probability dictionary, and decoding the decimal number by the probability dictionary to obtain a character sequence, wherein the probability dictionary is obtained when each character is mapped to a sub-interval according to a probability distribution; and determining the character sequence as the first decoded data.

[0010] Optionally, a cloud simulation platform is used to perform encoding and decoding operations on the operation instructions and the first simulation data to obtain second simulation data, including: adjusting the first simulation data according to the operation instructions to obtain third simulation data; using the back end of the cloud simulation platform to encode and compress the third simulation data to obtain second encoded data; sending the second encoded data to the front end of the cloud simulation platform, and decoding the second encoded data through the front end to obtain second decoded data; and determining the second decoded data as the second simulation data.

[0011] On the second aspect, the present application provides a simulation test system for intelligent driving, and the system includes: a client, which is used to establish a WebSocket connection with a server when it detects that a test control of a cloud simulation platform is triggered; when receiving a test instruction selected by a target object, generate a test request carrying the test instruction, and send the test request to the server; receive a large amount of first simulation data returned by the server, and encode and decode the first simulation data through the cloud simulation platform to construct an initial simulation scene; when an operation instruction triggered by the target object is detected, use the cloud simulation platform to encode and decode the operation instruction and the first simulation data to obtain second simulation data; render the second simulation data to the initial simulation scene to obtain and display the simulation test results; a server, which communicates with the client through a WebSocket connection, and is used to parse the test request and generate first simulation data when it receives a test request sent by the client.

[0012] In the third aspect, the present application provides a simulation test device for intelligent driving, which is applied to a client and includes: a connection module, which is used to establish a WebSocket connection with a server when it is detected that a test control of a cloud simulation platform is triggered; a generation module, which is used to generate a test request carrying a test instruction when a test instruction selected by a target object is received, and send the test request to the server, so that the server parses the test request and generates a large amount of first simulation data; a construction module, which is used to receive the first simulation data returned by the server through a WebSocket connection, and encode and decode the first simulation data through a cloud simulation platform to construct and display an initial simulation scene; an encoding and decoding module, which is used to use the cloud simulation platform to encode and decode the operation instruction and the first simulation data to obtain second simulation data when an operation instruction triggered by a target object is detected; and a display module, which is used to render the second simulation data to the initial simulation scene to obtain and display the simulation test results.

[0013] In a fourth aspect, the present application provides an electronic device comprising a memory, a processor, a communication interface and a communication bus, wherein the memory stores a computer program that can be run on the processor, the memory and the processor communicate through the communication bus and the communication interface, and when the processor executes the computer program, the steps of the above-mentioned intelligent driving simulation test method are implemented.

[0014] In a fifth aspect, the present application provides a computer-readable medium having a non-volatile program code executable by a processor, and the program code enables the processor to execute the above-mentioned intelligent driving simulation test method.

[0015] Beneficial effects of this application:

[0016] The present application provides a simulation test method for intelligent driving, including: establishing a WebSocket connection with a server when a test control of a cloud simulation platform is detected to be triggered; generating a test request carrying the test instruction when a test instruction selected by a target object is received, and sending the test request to the server so that the server parses the test request and generates a large amount of first simulation data; receiving the first simulation data returned by the server through a WebSocket connection, and encoding and decoding the first simulation data through a cloud simulation platform to build and display an initial simulation scene; when an operation instruction triggered by a target object is detected, encoding and decoding the operation instruction and the first simulation data using a cloud simulation platform to obtain second simulation data; rendering the second simulation data to the initial simulation scene to obtain and display simulation test results. The massive simulation data sent by the server is received in real time through a WebSocket connection, and the simulation data is encoded and decoded through a cloud simulation platform when processing the simulation data, which shortens the transmission time in the cloud simulation platform and can speed up the establishment and presentation of simulation scenes. The technical problem that the simulation results cannot be fed back in real time during simulation testing due to the long time spent processing massive simulation data is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 A flowchart of an optional intelligent driving simulation test method applied to a client according to an embodiment of the present application;

[0020] Figure 2 An optional interaction diagram of a simulation test according to an embodiment of the present application;

[0021] Figure 3 A schematic diagram of encoding and decoding on an optional cloud simulation platform provided according to an embodiment of the present application;

[0022] Figure 4 A schematic diagram of an optional intelligent driving simulation test system provided according to an embodiment of the present application;

[0023] Figure 5An optional client-server interaction architecture diagram provided according to an embodiment of the present application;

[0024] Figure 6 A block diagram of an optional intelligent driving simulation test device applied to a client according to an embodiment of the present application;

[0025] Figure 7 A schematic diagram of an optional electronic device structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0027] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0028] For ease of description, spatial relative terms may be used in the text to describe the relative position or movement of an element or feature as shown in the figure relative to another element or feature, such as "inside", "outside", "inner side", "outer side", "below", "below", "above", "above", "front", "back", etc. Such spatial relative terms are intended to include different orientations of the device in use or operation in addition to the orientation depicted in the figure. For example, if the device in the figure undergoes a position flip or a change in posture or a change in motion state, then these directional indications will also change accordingly, for example: an element described as "below other elements or features" or "below other elements or features" will subsequently be oriented as "above other elements or features" or "above other elements or features". Therefore, the example term "below..." can include both upper and lower orientations. The device can be oriented otherwise (rotated 90 degrees or in other directions) and the spatial relative descriptors used in the text are interpreted accordingly.

[0029] With the continuous development of intelligent driving technology, more and more assisted driving functions and even autonomous driving functions have been introduced. The development and testing of intelligent driving related algorithms and functions have become an extremely important part of intelligent driving. The reliability of intelligent driving has also become the main obstacle for intelligent driving systems to move from the research and development stage to industrialization. Before conducting road tests on intelligent driving functions, simulation test scenarios are usually constructed and intelligent driving algorithms are simulated and tested in advance in the constructed simulation scenarios to verify the confidence and feasibility of the algorithms.

[0030] The main purpose of intelligent driving simulation testing is to simulate real-world driving scenarios in a virtual environment to evaluate the performance of the autonomous driving system. Due to the complexity and diversity of driving scenarios, in order to improve the accuracy and precision of simulation testing, the data required for simulation is often massive. If massive simulation data is simulated on the simulation platform, the large amount of data may affect the processing performance, resulting in the inability to feedback the simulation results in real time due to the long time spent processing massive simulation data during simulation testing.

[0031] In order to solve the technical problem in the prior art that the simulation results cannot be fed back in real time due to the long time spent processing massive simulation data during simulation testing, the present application provides a simulation test method for intelligent driving, which is applied to the client, such as Figure 1 As shown, including:

[0032] Step 101, when it is detected that the test control of the cloud simulation platform is triggered, establish a WebSocket connection with the server;

[0033] Step 103, upon receiving the test instruction selected by the target object, generating a test request carrying the test instruction, and sending the test request to the server, so that the server parses the test request and generates a massive amount of first simulation data;

[0034] Step 105, receiving the first simulation data returned by the server through the WebSocket connection, and encoding and decoding the first simulation data through the cloud simulation platform to construct and display the initial simulation scene;

[0035] Step 107, when an operation instruction triggered by the target object is detected, encoding and decoding the operation instruction and the first simulation data using the cloud simulation platform to obtain second simulation data;

[0036] Step 109, rendering the second simulation data to the initial simulation scene, obtaining and displaying the simulation test results.

[0037] During simulation testing, in order to accurately present the simulation scene, it involves the data transmission and data processing of massive simulation data. At the same time, in order to give users a better simulation experience, the simulation results need to be displayed in real time, which places high requirements on the transmission time of the simulation data. This application receives massive simulation data sent by the server in real time through a WebSocket connection, and encodes and decodes the simulation data through the cloud simulation platform when processing the simulation data, which shortens the transmission time within the cloud simulation platform, speeds up the establishment of simulation scenes, and achieves the purpose of presenting simulation results in real time.

[0038] The client is equipped with a cloud simulation platform for simulation testing. The target object (i.e., user) can start the cloud simulation platform through the client's browser, including: opening the browser and entering the URL of the cloud simulation platform; the cloud simulation platform displays the login interface, and the user enters the user name and password (or uses other authentication methods such as OAuth, OpenID, etc.) to log in; after successful login, the user enters the main interface of the cloud simulation platform and clicks the "Test" button to start the test process.

[0039] For example, after the user starts the test process, the client initiates a request to the server to establish a WebSocket connection. After the WebSocket connection is established, two-way real-time data transmission between the client and the server can be achieved through the WebSocket connection.

[0040] For example, the steps of establishing a WebSocket connection between a client and a server include: the client sends an HTTP request to the server, and in the request header, two special fields are included, namely, Connection:Upgrade and Upgrade:websocket, which indicate that the current HTTP connection is expected to be upgraded to a WebSocket connection; after receiving the HTTP request from the client, the server checks the Upgrade field in the request header, and if the server supports the WebSocket protocol and agrees to upgrade the connection, the server returns an HTTP 101 status code to the client, indicating the protocol switch. At the same time, in the response header, the server also adds the Upgrade:websocket and Connection:upgrade fields to inform the client that the communication connection has been successfully upgraded to the WebSocket protocol, and thus a WebSocket connection is established between the client and the server.

[0041] For example, on the main interface of the cloud simulation platform, the user can select a predefined initial simulation scenario or customize the initial simulation scenario. The user can configure simulation parameters such as vehicle type, road environment, weather conditions, etc. as needed.

[0042] For example, a user may select a test instruction for a simulation test on an HMI interface (Human Machine Interface). The test instruction may be an instruction for parking or other driving behaviors in a vehicle. This application does not limit the test instruction.

[0043] For example, after a WebSocket connection is established between the client and the server, the client generates a test request based on the test instruction selected by the received user, and sends the test request to the server through the WebSocket connection. After receiving the test request, the server parses the test request and generates a large amount of first simulation data, and then returns the large amount of first simulation data to the client through the WebSocket connection.

[0044] For example, encoding and decoding the first simulation data through the cloud simulation platform to construct and display the initial simulation scene mainly includes encoding and compressing the first simulation data through the back end of the cloud simulation platform, and then transmitting it to the front end of the cloud simulation platform. The front end decodes the encoded first simulation data and then performs rendering and other operations to construct the initial simulation scene and then display it on the display interface.

[0045] This application aims to achieve high-precision scene simulation, so the simulation data involved are massive data.

[0046] For example, after the initial simulation scene is displayed on the display interface, the cloud simulation platform can receive operation instructions triggered by the user, such as controlling the acceleration, deceleration and steering of the vehicle, and then update the simulation scene in real time according to the operation instructions, and push it to the client's display interface in real time to promptly reflect the changes in the vehicle state and the new simulation results. How to encode and decode the simulation data according to the operation instructions to achieve real-time update of the simulation scene will be explained below.

[0047] For example, after the simulation test is completed, the user clicks the "Stop" button on the cloud simulation platform. At this time, the client initiates a request to close the WebSocket connection to the server. After receiving the closing request sent by the client, the server organizes and releases the resources held by the user and closes the WebSocket connection.

[0048] Figure 2 The interaction diagram during the simulation test provided for this application includes the interaction between the user, the client and the server, and the specific interaction implementation example is the above example.

[0049] As an optional embodiment, when a test instruction selected by a target object is received, a test request carrying the test instruction is generated and sent to a server, including: obtaining static environment information and dynamic environment information of a simulation scenario for executing the test instruction; determining the test instruction, the static environment information and the dynamic environment information as a test request; and sending the test request to the server via a WebSocket connection.

[0050] Specifically, static environment information includes, but is not limited to, a directed graph of roads and their lanes, the locations of road lane lines, stop lines, stop signs, traffic lights, the physical locations of crosswalks and other traffic control elements, speed limits, and parking areas.

[0051] Specifically, dynamic environmental information includes but is not limited to information such as the position, speed, direction of the vehicle, information such as the position, speed, acceleration of the target object, traffic light status (updated in real time, such as "red", "green", "yellow"), lanes that control traffic (for example, left turns, through lanes, and right turns, etc.), and upcoming traffic conditions (such as traffic jams, accidents, etc.).

[0052] In addition to static and dynamic environmental information, the test request may also include other driving-related data, such as weather conditions, road construction conditions, and vehicle health conditions.

[0053] The client can send the test request to the server in real time through the WebSocket connection. After receiving the test request, the server will parse the data in the test request and generate a large amount of first simulation data.

[0054] As an optional embodiment, the first simulation data is encoded and decoded through a cloud simulation platform to construct and display an initial simulation scene, including: using the back end of the cloud simulation platform to encode and compress the first simulation data to obtain first encoded data; sending the first encoded data to the front end of the cloud simulation platform, and decoding the first encoded data through the front end to obtain first decoded data; rendering the first decoded data to obtain an initial simulation scene.

[0055] The first simulation data is encoded and compressed by the back end of the cloud simulation platform to obtain the first encoded data. At this time, the first encoded data is a relatively small data that can be transmitted quickly. The first encoded data can be sent to the front end of the cloud simulation platform very quickly and with less resources. The front end of the cloud simulation platform decodes the first encoded data to obtain the first decoded data, and then renders the first decoded data to generate visual effects such as vehicle driving animation and instrument panel display, thereby obtaining the initial simulation scene.

[0056] After receiving a massive amount of first simulation data, some data preprocessing may also be performed, such as data cleaning, data sorting, etc. Currently, there are relatively mature data preprocessing technologies, which will not be elaborated here.

[0057] Figure 3 Schematic diagram of encoding and decoding of the cloud simulation platform provided by this application. As shown in the figure, the cloud simulation platform includes a front-end and a back-end, the back-end includes a converter, a verifier, an encoding and a cache part, and the front-end includes decoding, data buffering, data synchronization, 3D rendering and UI (User Interface) interaction parts.

[0058] Next, based on Figure 3 The interaction process between the front-end and the back-end when encoding and decoding through the cloud simulation platform is described in detail. After the back-end receives the raw data, it performs data cleaning, data conversion, data organization, data verification and quality inspection, data encoding, and data caching in sequence. The raw data can be simulation data or the raw data of the autonomous driving vehicle (such as position, speed, image, and point cloud, etc.). The encoded data is transmitted to the front-end. After the front-end receives the encoded data, it performs decoding, data buffering, data synchronization, 3D rendering, and UI interaction in sequence. Next, the various execution steps of the front-end and the back-end are described:

[0059] The steps for data cleaning at the back end include: processing missing values, detecting and processing missing values ​​in the data, which can be processed by deletion, interpolation filling or using other methods; then processing outliers, which can use statistical methods, visualization tools or specialized anomaly detection algorithms; finally, processing duplicate values, detecting and removing duplicate records in the data.

[0060] The steps for data conversion at the back end include: first standardizing / normalizing the data to ensure that the data is consistent at different scales; then performing a logarithmic transformation on the data to eliminate or mitigate the skewed distribution of the data and converting categorical variables into binary vectors; and finally converting continuous data into discrete data.

[0061] The steps of data sorting in the backend include: feature selection, selecting the features most relevant to analysis and modeling. First, create new features by combining, transforming or extracting original features; then process time series data and unbalanced data: for unbalanced data sets in classification problems, undersampling, oversampling or synthesizing minority category data can be used; finally, process text tagging data, including word segmentation, semantic parsing, etc.

[0062] The steps of data verification and quality check at the back end include: Checking whether the data is complete and contains all required fields. Checking whether the data conforms to the preset rules or standards, for example, checking whether the date format is correct, whether the value is within a reasonable range, etc. Checking whether there are duplicate records or fields in the data. Checking whether errors occurred during data transmission by calculating the CRC value (Cyclic Redundancy Check) of the data and comparing it with the original CRC value.

[0063] The step of performing data encoding at the back end includes: encoding the verified data to obtain encoded data.

[0064] The steps of data caching in the backend include: first, data reading and loading, the system reads data from the main memory or disk. During the data loading process, the system will determine the amount of data to be loaded and the order of loading according to the pre-set cache strategy (such as FIFO (First in Firstout), LRU (Recently Used), etc.). Then the data is written. When the data is loaded, the system will write the data to the cache. The data written to the cache needs to be stored in a location determined by the cache replacement algorithm (such as LRU, LFU (Least Frequently Used), etc.). The data written to the cache will overwrite the previous data, so it is necessary to ensure that the data stored in the cache is the latest. Finally, when the data is written to the cache, the system will return the data to the user. The next time the user requests the same data, it can be read directly from the cache without loading the data again, thereby improving the response speed and performance of the system.

[0065] After the data is cached, the data stream is sent to the front end through the websocket network. The data stream refers to a sequence of data with the same data structure and timestamp.

[0066] The step of decoding data at the front end includes: decoding the encoded data to obtain decoded data.

[0067] The steps of front-end data caching include: temporarily storing the decoded data in memory for subsequent processing and use.

[0068] The steps of front-end data synchronization include: updating the locally stored data according to the latest data obtained by the front-end.

[0069] The steps of performing 3D rendering at the front end include: constructing a 3D scene according to the decoded simulation data, and rendering the simulation data into the 3D scene to obtain a simulation visual effect.

[0070] The steps of UI interaction at the front end include: displaying the simulation visual effects on an interactive UI interface, the UI interface can monitor user input events and process corresponding data, and update the status and display content of the 3D simulation scene according to user input and data processing results.

[0071] Implement interactive operations of UI components under the React framework. In intelligent driving simulation, real-time updating and display of data are crucial. UI components support data binding and calculated properties, which can easily realize dynamic updating of simulation data. UI components are highly customizable, and developers can personalize the style and behavior of components according to the specific needs of intelligent driving simulation. This helps to build a user interface that meets the characteristics of intelligent driving simulation and improve the user experience. Specifically, UI provides a variety of form components, such as input boxes, selection boxes, switches, etc., through which users can enter data or make selections. The system can listen to the change events of these components. When the user enters or selects data, the simulation parameters are automatically updated and the corresponding simulation process is triggered. At the same time, the simulation results can be displayed in the form of a table, and the user can view the simulation data of each frame; or the simulation data can be displayed in the form of a chart, and the user can understand the trend and change of the data more intuitively. Intelligent driving simulation systems usually provide a variety of operation control options, such as starting simulation, pausing simulation, resetting simulation, etc. The system can bind the corresponding event processing function to each button, and when the user clicks the button, the corresponding operation logic is executed. When necessary, a prompt box or a notification bar is displayed to show relevant information to the user. Finally, the HTML (HyperText Markup Language) framework is used to divide the structure, and CSS (Cascading Style Sheets) is used to achieve the mapping effect and display it to the end user.

[0072] The cloud simulation platform provided in this application can implement encoding at the back end, improve data compression rate, transmit to the front end through a custom protocol format, implement decoding at the front end, and organize business logic to achieve real-time interaction of large amounts of data.

[0073] As an optional embodiment, the first simulation data is encoded and compressed using the back end of the cloud simulation platform to obtain the first encoded data, including: setting a coding interval and determining the probability distribution of each character in the first simulation data; dividing the coding interval into multiple sub-intervals according to the probability distribution, and mapping each character to the sub-interval according to the probability distribution; reading each character in the first simulation data in turn, and updating the coding interval according to the read characters and the sub-intervals to which the characters belong; after completing the reading of each character in the first simulation data, obtaining the latest target coding interval; extracting the shortest decimal from the target coding interval, and converting the decimal into a binary number to obtain the first encoded data.

[0074] For example, a coding interval is set and the probability distribution of each character in the first simulation data is determined, including: setting the coding interval to [0, 1). If the probability is known, the probability distribution of each character in the first simulation data can be directly obtained. If the probability is unknown, the probability dictionary can be dynamically updated during the encoding process.

[0075] For example, the coding interval is divided into multiple sub-intervals according to the probability distribution, and each character is mapped to the sub-interval according to the probability distribution, including: according to the probability of each character, non-overlapping sub-intervals are allocated from left to right in the interval [0, 1), and then each character is mapped to the sub-interval according to the probability distribution, and a unique number is assigned to each sub-interval and the character therein.

[0076] For example, each character in the first simulation data is read in sequence, and the encoding interval is updated according to the read characters and the sub-interval to which the characters belong, including: reading one character from the first simulation data each time; updating the encoding interval to the sub-interval corresponding to the current character according to the read characters and the corresponding sub-interval; repeating the reading and updating process until the entire first simulation data is encoded.

[0077] For example, extracting the shortest decimal from the target coding interval and converting the decimal into a binary number to obtain the first coded data includes: selecting a number in the target coding interval finally obtained as the final coded decimal, converting the selected coded decimal into a binary number, and obtaining the first coded data. Usually, the lower bound or midpoint of the interval is selected as the final coded decimal, because arithmetic coding is prefix coding, so any number in the interval is valid.

[0078] The encoding method provided by the present application is a lossless encoding method that can effectively compress information source redundancy.

[0079] As an optional embodiment, the first encoded data is decoded by the front end to obtain the first decoded data, including: converting the first encoded data into a decimal number by the front end; obtaining a probability dictionary, and decoding the decimal number by the probability dictionary to obtain a character sequence, wherein the probability dictionary is obtained when each character is mapped to a sub-interval according to a probability distribution; and determining the character sequence as the first decoded data.

[0080] The first coded data is a binary number, which represents the position of the coded message in the interval [0, 1). The binary number needs to be converted into a decimal number during decoding.

[0081] During encoding, each character is mapped to a subinterval in the interval [0, 1). During decoding, we need to determine the corresponding character based on the position of the decimal in this interval. First, we need to obtain the same probability dictionary as during encoding, that is, we know the subinterval corresponding to each character; then, starting from the entire [0, 1) interval, we gradually narrow the range based on the position of the decimal and the subinterval in the probability dictionary until we find the corresponding character.

[0082] The decoding process is an iterative process. After locating a character, we update the current range according to the subrange of the character (that is, update the value of the decimal fraction), and then continue to locate the next character in the new range until the entire simulation data is decoded.

[0083] As an optional embodiment, a cloud simulation platform is used to encode and decode operation instructions and first simulation data to obtain second simulation data, including: adjusting the first simulation data according to the operation instructions to obtain third simulation data; using the back end of the cloud simulation platform to encode and compress the third simulation data to obtain second encoded data; sending the second encoded data to the front end of the cloud simulation platform, and decoding the second encoded data through the front end to obtain second decoded data; determining the second decoded data as the second simulation data.

[0084] For example, users can send operating instructions through the browser interface of the client, such as controlling the acceleration, deceleration, and steering of the vehicle. The browser encodes the operating instructions into a standard format and sends them to the cloud simulation platform through WebSocket or other real-time communication technologies. The cloud simulation platform can then update the vehicle status in the simulation scene according to the operating instructions and continue to simulate driving. The back end of the cloud simulation platform collects the third simulation data updated based on the operating instructions, encodes the third simulation data, and the front end decodes and renders it, and can push the rendered simulation scene to the user's browser display interface in real time.

[0085] The steps of encoding and compressing the third simulation data using the back end of the cloud simulation platform and decoding the encoded third simulation data using the front end are similar to the above-mentioned steps of encoding and decoding the first simulation data, and will not be repeated here.

[0086] This application provides a cloud-based intelligent driving simulator with real-time dynamic interactive response, which can utilize the powerful computing resources of the cloud, process user input in real time, and provide instant feedback on simulation results. Whether it is vehicle status updates, environmental changes, or sensor data processing, it can be completed in a short time, ensuring that users get a smooth, delay-free interactive experience.

[0087] The present application provides a simulation test method for intelligent driving, which is applied to the client, including: when the test control of the cloud simulation platform is detected to be triggered, a WebSocket connection is established with the server; when the test instruction selected by the target object is received, a test request carrying the test instruction is generated, and the test request is sent to the server, so that the server parses the test request and generates a large amount of first simulation data; the first simulation data returned by the server through the WebSocket connection is received, and the first simulation data is encoded and decoded through the cloud simulation platform to build and display the initial simulation scene; when the operation instruction triggered by the target object is detected, the operation instruction and the first simulation data are encoded and decoded using the cloud simulation platform to obtain the second simulation data; the second simulation data is rendered to the initial simulation scene to obtain and display the simulation test results. The massive simulation data sent by the server is received in real time through the WebSocket connection, and the simulation data is encoded and decoded through the cloud simulation platform when the simulation data is processed, which shortens the transmission time in the cloud simulation platform and can speed up the establishment and presentation of the simulation scene. The technical problem that the simulation results cannot be fed back in real time due to the long time spent processing massive simulation data during the simulation test is solved.

[0088] According to another aspect of the embodiment of the present application, the present application provides a simulation test system for intelligent driving, such as Figure 4 As shown, including:

[0089] The client 402 is used to establish a WebSocket connection with the server when it is detected that the test control of the cloud simulation platform is triggered; when receiving the test instruction selected by the target object, generate a test request carrying the test instruction, and send the test request to the server; receive a large amount of first simulation data returned by the server, and encode and decode the first simulation data through the cloud simulation platform to build an initial simulation scene; when detecting the operation instruction triggered by the target object, use the cloud simulation platform to encode and decode the operation instruction and the first simulation data to obtain second simulation data; render the second simulation data to the initial simulation scene, and obtain and display the simulation test results;

[0090] The server 404 communicates with the client through a WebSocket connection, and is used to parse the test request and generate first simulation data when receiving the test request sent by the client.

[0091] Figure 5This application provides an interactive architecture diagram of a client and a server, in which a WebSocket connection is established between the client and the server for real-time interaction. Based on the React and Three.js frameworks, the functional interaction event logic is implemented through React-Axios network requests, data visualization is achieved through WebSocket real-time communication, and JSX (JavaScriptXML) (which can be understood as JavaScript scripts) is used to implement the functional interaction logic. React contains elements for building a user interface (UI), and the UI includes two components: HTML and CSS. HTML is responsible for defining the structure and content of the web page, and CSS is responsible for describing the style and layout of these contents; the Three.js framework is used to implement Animation and Scence; and the transmission of video data streams (Stream) is achieved through WebRTC (Web Real-Time Communication, web page real-time communication), thereby realizing real-time interaction of intelligent driving simulators.

[0092] According to another aspect of the embodiment of the present application, the present application provides a simulation test device for intelligent driving, which is applied to a client, such as Figure 6 As shown, including:

[0093] The connection module 602 is used to establish a WebSocket connection with the server when it is detected that the test control of the cloud simulation platform is triggered;

[0094] A generating module 604 is used to generate a test request carrying the test instruction when receiving the test instruction selected by the target object, and send the test request to the server, so that the server parses the test request and generates a large amount of first simulation data;

[0095] A construction module 606 is used to receive the first simulation data returned by the server through the WebSocket connection, and to encode and decode the first simulation data through the cloud simulation platform to construct and display the initial simulation scene;

[0096] The encoding and decoding module 608 is used to, when an operation instruction triggered by the target object is detected, use the cloud simulation platform to perform encoding and decoding operations on the operation instruction and the first simulation data to obtain second simulation data;

[0097] The display module 610 is used to render the second simulation data to the initial simulation scene, and obtain and display the simulation test results.

[0098] Optionally, the generation module 604 is further used to obtain static environment information and dynamic environment information of a simulation scenario for executing a test instruction; determine the test instruction, the static environment information and the dynamic environment information as a test request; and send the test request to the server via a WebSocket connection.

[0099] Optionally, building module 606 includes:

[0100] An encoding unit, used to encode and compress the first simulation data using the back end of the cloud simulation platform to obtain first encoded data;

[0101] A decoding unit, used to send the first coded data to the front end of the cloud simulation platform, and decode the first coded data through the front end to obtain first decoded data;

[0102] The rendering unit is used to render the first decoded data to obtain an initial simulation scene.

[0103] Optionally, the encoding unit is also used to set a coding interval and determine the probability distribution of each character in the first simulation data; divide the coding interval into multiple sub-intervals according to the probability distribution, and map each character to a sub-interval according to the probability distribution; read each character in the first simulation data in turn, and update the coding interval according to the read characters and the sub-intervals to which the characters belong; after completing the reading of each character in the first simulation data, obtain the latest target coding interval; extract the shortest decimal from the target coding interval, and convert the decimal into a binary number to obtain the first coded data.

[0104] Optionally, the decoding unit is also used to convert the first encoded data into a decimal number through the front end; obtain a probability dictionary, and decode the decimal number through the probability dictionary to obtain a character sequence, wherein the probability dictionary is obtained when each character is mapped to a sub-interval according to a probability distribution; and determine the character sequence as the first decoded data.

[0105] Optionally, the encoding and decoding module 608 is also used to adjust the first simulation data according to the operating instructions to obtain third simulation data; use the back end of the cloud simulation platform to encode and compress the third simulation data to obtain second encoded data; send the second encoded data to the front end of the cloud simulation platform, and decode the second encoded data through the front end to obtain second decoded data; determine the second decoded data as the second simulation data.

[0106] It should be noted here that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments.

[0107] According to another aspect of the embodiments of the present application, the present application provides an electronic device, such as Figure 7As shown, it includes a memory 701, a processor 703, a communication interface 705 and a communication bus 707. The memory 701 stores a computer program that can be run on the processor 703. The memory 701 and the processor 703 communicate through the communication interface 705 and the communication bus 707. When the processor 703 executes the computer program, the steps of the above method are implemented.

[0108] The memory and processor in the above electronic device communicate via a communication bus and a communication interface. The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus may be divided into an address bus, a data bus, a control bus, etc.

[0109] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0110] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0111] According to another aspect of the embodiments of the present application, a computer-readable medium having a non-volatile program code executable by a processor is provided.

[0112] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0113] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0115] It should be understood that the terms used in the text are only for the purpose of describing specific example embodiments, and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used in the text may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0116] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A simulation test method for intelligent driving, characterized in that: Applied to a client, the method comprises: When it is detected that the test control of the cloud simulation platform is triggered, a WebSocket connection is established with the server; Upon receiving the test instruction selected by the target object, generating a test request carrying the test instruction, and sending the test request to the server, so that the server parses the test request and generates a large amount of first simulation data; Receiving the first simulation data returned by the server through the WebSocket connection, and encoding and decoding the first simulation data through the cloud simulation platform to construct and display an initial simulation scene; In the case of detecting an operation instruction triggered by the target object, using the cloud simulation platform to perform the encoding and decoding operation on the operation instruction and the first simulation data to obtain second simulation data; The second simulation data is rendered to the initial simulation scene to obtain and display simulation test results.

2. The method according to claim 1, characterized in that When receiving the test instruction selected by the target object, generating a test request carrying the test instruction, and sending the test request to the server, comprises: Acquire static environment information and dynamic environment information of a simulation scenario for executing the test instruction; Determine the test instruction, the static environment information, and the dynamic environment information as the test request; The test request is sent to the server through the WebSocket connection.

3. The method according to claim 1, characterized in that The encoding and decoding operation of the first simulation data by the cloud simulation platform to construct and display an initial simulation scene includes: Using the back end of the cloud simulation platform to encode and compress the first simulation data to obtain first encoded data; Sending the first coded data to the front end of the cloud simulation platform, and decoding the first coded data through the front end to obtain first decoded data; The first decoded data is rendered to obtain the initial simulation scene.

4. The method according to claim 3, characterized in that: The using the back end of the cloud simulation platform to encode and compress the first simulation data to obtain first encoded data includes: Setting a coding interval and determining a probability distribution of each character in the first simulation data; Dividing the encoding interval into a plurality of sub-intervals according to the probability distribution, and mapping each of the characters to the sub-intervals according to the probability distribution; Reading each of the characters in the first simulation data in sequence, and updating the encoding interval according to the read characters and the sub-interval to which the characters belong; After completing reading of each character in the first simulation data, obtaining the latest target encoding interval; The shortest decimal is extracted from the target coding interval, and the decimal is converted into a binary number to obtain the first coding data.

5. The method according to claim 4, characterized in that The decoding of the first encoded data by the front end to obtain first decoded data includes: Converting the first coded data into a decimal number by the front end; Obtain a probability dictionary, and decode the decimal number using the probability dictionary to obtain a character sequence, wherein the probability dictionary is obtained when mapping each character to the subinterval according to the probability distribution; The character sequence is determined as the first decoded data.

6. The method according to claim 1, characterized in that The using the cloud simulation platform to perform the encoding and decoding operation on the operation instruction and the first simulation data to obtain second simulation data includes: Adjust the first simulation data according to the operation instruction to obtain third simulation data; Using the back end of the cloud simulation platform to encode and compress the third simulation data to obtain second encoded data; Sending the second encoded data to the front end of the cloud simulation platform, and decoding the second encoded data through the front end to obtain second decoded data; The second decoded data is determined as the second simulation data.

7. A simulation test system for intelligent driving, characterized in that: The system comprises: The client is used to establish a WebSocket connection with the server when it detects that the test control of the cloud simulation platform is triggered; when receiving the test instruction selected by the target object, generate a test request carrying the test instruction, and send the test request to the server; receive a large amount of first simulation data returned by the server, and encode and decode the first simulation data through the cloud simulation platform to build an initial simulation scene; when detecting the operation instruction triggered by the target object, use the cloud simulation platform to encode and decode the operation instruction and the first simulation data to obtain second simulation data; render the second simulation data to the initial simulation scene to obtain and display the simulation test results; the server communicates with the client through the WebSocket connection, and is used to parse the test request and generate the first simulation data when receiving the test request sent by the client.

8. A simulation test device for intelligent driving, characterized in that: Applied to the client, including: The connection module is used to establish a WebSocket connection with the server when it is detected that the test control of the cloud simulation platform is triggered; A generating module, configured to generate a test request carrying the test instruction upon receiving the test instruction selected by the target object, and send the test request to the server, so that the server parses the test request and generates a large amount of first simulation data; A construction module, configured to receive the first simulation data returned by the server through the WebSocket connection, and perform encoding and decoding operations on the first simulation data through the cloud simulation platform to construct and display an initial simulation scenario; A coding and decoding module, configured to, when an operation instruction triggered by the target object is detected, use the cloud simulation platform to perform the coding and decoding operation on the operation instruction and the first simulation data to obtain second simulation data; A display module is used to render the second simulation data to the initial simulation scene to obtain and display the simulation test results.

9. An electronic device, comprising a memory, a processor, a communication interface and a communication bus, wherein the memory stores a computer program that can be run on the processor, and the memory and the processor communicate through the communication bus and the communication interface, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer readable medium having a non-volatile program code executable by a processor, characterized in that: The program code enables the processor to execute the method according to any one of claims 1 to 6.