Intelligent driving traffic accident analysis method and device, domain controller and medium

Abstract

The application is suitable for the automatic driving technical field, and provides an intelligent driving traffic accident analysis method, device, domain controller and medium, wherein the method comprises: analyzing intelligent driving control data and actual driving data when a vehicle has an accident, and determining whether a vehicle system of the vehicle has a problem when the accident occurs; generating an accident analysis report according to the determination result; and the accident analysis report is used for prompting whether the vehicle system of the vehicle has a problem when the accident occurs. The application can provide the accident analysis report of the vehicle when the vehicle has the accident, provide a basis for defining the responsibility of the traffic accident, facilitate the traffic manager to define the responsibility of the accident, and also facilitate the automatic driving vehicle manager to know the driving process of the vehicle in the accident, and facilitate the automatic driving vehicle manager to master the vehicle condition of the automatic driving vehicle.

Description

Technical Field

[0001] This application belongs to the field of autonomous driving technology, and in particular relates to an intelligent driving traffic accident analysis method, device, domain controller and medium. Background Technology

[0002] Autonomous driving is a mainstream application in the field of artificial intelligence. It relies on sensors such as vision, millimeter-wave radar, lidar, ultrasonic radar, and integrated navigation to perceive the environment, enabling motor vehicles to drive autonomously without human intervention. Since autonomous driving technology eliminates the need for human drivers, it theoretically can effectively avoid human driver errors and reduce traffic accidents. However, when autonomous vehicles are operating on actual roads, traffic accidents are inevitable due to factors such as dynamic obstacles and road limitations. Currently, when an autonomous vehicle is involved in an accident, it is difficult to determine whether there was a problem with the vehicle's own system, making it impossible for traffic managers to assign responsibility for the accident. Summary of the Invention

[0003] This application provides an intelligent driving traffic accident analysis method, device, domain controller, and medium, which can solve the problem that traffic managers cannot determine liability for accidents.

[0004] In a first aspect, embodiments of this application provide an intelligent driving traffic accident analysis method, applied to an intelligent driving domain controller, the method comprising:

[0005] Analyze intelligent driving data and actual driving data at the time of a vehicle accident to determine whether the vehicle's system malfunctioned at the time of the accident;

[0006] An accident analysis report is generated based on the determined results; the accident analysis report is used to indicate whether there was a problem with the vehicle's system at the time of the accident.

[0007] Optionally, the vehicle system includes an execution system and an intelligent driving system, and the intelligent driving data includes intelligent driving control data, decision planning data, fusion processing data, and perception data;

[0008] Analyze intelligent driving data and actual driving data at the time of a vehicle accident to determine whether the vehicle's systems malfunctioned at the time of the accident, including:

[0009] Comparative analysis of intelligent driving control data and actual driving data at the time of a vehicle accident;

[0010] When the intelligent driving control data and the actual driving data do not match, it is determined that there was a problem with the vehicle's execution system at the time of the accident.

[0011] When the intelligent driving control data matches the actual driving data, the vehicle's intelligent driving system is analyzed step by step to determine whether there is a problem with the intelligent driving system.

[0012] Optionally, a step-by-step analysis of the vehicle's intelligent driving system can be performed to determine if any problems have occurred, including:

[0013] Calculate the decision-making and planning data of the vehicle's intelligent driving system at the time of the accident to obtain intelligent driving control data;

[0014] Determine whether the actual driving data matches the calculated intelligent driving control data;

[0015] When the actual driving data does not match the calculated intelligent driving control data, it is determined that the module in the intelligent driving system used to calculate the intelligent driving control data malfunctioned at the time of the accident.

[0016] Optionally, after determining whether the actual driving data matches the calculated intelligent driving control data, the method further includes:

[0017] When the actual driving data matches the calculated intelligent driving control data, the fusion processing data of the intelligent driving system at the time of the accident is calculated to obtain decision planning data.

[0018] Determine whether the actual decision-making and planning data matches the calculated decision-making and planning data;

[0019] When the actual decision-making and planning data do not match the calculated decision-making and planning data, it is determined that the module in the intelligent driving system used to calculate the decision-making and planning data malfunctioned when the accident occurred.

[0020] Optionally, after determining whether the actual decision-making and planning data at the time of the vehicle accident matches the calculated decision-making and planning data, the method further includes:

[0021] When the actual decision-making and planning data matches the calculated decision-making and planning data, the perception data of the intelligent driving system at the time of the accident is calculated to obtain fused processing data.

[0022] Determine whether the actual fusion-processed data matches the calculated fusion-processed data;

[0023] When the actual fused data does not match the calculated fused data, it is determined that the module in the intelligent driving system used to calculate the fused data malfunctioned at the time of the accident.

[0024] When the actual fusion data matches the calculated fusion data, it is determined that the intelligent driving system did not malfunction at the time of the accident.

[0025] Optionally, the method also includes:

[0026] Based on the accident analysis report of the vehicle when an accident occurs within a preset time period, the vehicle condition is scored to obtain the first score result.

[0027] Acquire actual driving data and intelligent driving control data of the vehicle within a target time interval; the target time interval includes all times within a preset time period except for the time when the vehicle accident occurs.

[0028] Based on the actual driving data and intelligent driving control data obtained, the vehicle's condition is scored to obtain a second score result;

[0029] The vehicle's condition score is determined based on the first and second score results.

[0030] Optionally, based on accident analysis reports of accidents occurring within a preset time period, the vehicle's condition is scored to obtain a first score result, including:

[0031] For each accident that occurs within a preset time period, the vehicle's condition is scored based on the accident analysis report at the time of the accident, and a first score is obtained.

[0032] The first score result is obtained based on the first score value corresponding to all accidents within the preset time period;

[0033] Based on the acquired actual driving data and intelligent driving control data, the vehicle's condition is scored to obtain a second score result, including:

[0034] The actual driving data and intelligent driving control data at the same moment within the target time interval are treated as a single data set for analysis.

[0035] For each set of analysis data, the difference between the actual driving data and the intelligent driving control data of the analysis data set is compared with multiple pre-stored difference intervals, and the vehicle condition is scored according to the difference interval in which the difference falls, to obtain a second score value.

[0036] The second score result is obtained based on the second score value corresponding to all the analyzed data groups.

[0037] Secondly, embodiments of this application provide an intelligent driving traffic accident analysis device, applied to an intelligent driving domain controller, the intelligent driving traffic accident analysis device comprising:

[0038] The analysis module is used to analyze intelligent driving data and actual driving data at the time of a vehicle accident;

[0039] The determination module is used to determine whether the vehicle's system malfunctioned at the time of the accident, based on the analysis results from the analysis module.

[0040] The generation module is used to generate an accident analysis report based on the determined results; the accident analysis report is used to indicate whether there was a problem with the vehicle system of the intelligent driving vehicle when the accident occurred.

[0041] Optionally, the vehicle system includes an execution system and an intelligent driving system, and the intelligent driving data includes intelligent driving control data, decision planning data, fusion processing data, and perception data.

[0042] Optionally, the analysis module is specifically used to compare and analyze the intelligent driving control data and actual driving data when a vehicle accident occurs;

[0043] Optionally, the determination module includes:

[0044] The first determination submodule is used to determine that the vehicle's execution system malfunctioned at the time of the accident when the analysis results of the analysis module show that the intelligent driving control data and the actual driving data do not match.

[0045] The second determination submodule is used to perform step-by-step analysis of the vehicle's intelligent driving system to determine whether there is a problem with the intelligent driving system when the analysis result of the analysis module is consistent with the intelligent driving control data and the actual driving data.

[0046] The third determining submodule is used to determine whether there is a problem with the vehicle system of the intelligent driving vehicle based on the conclusions of the first determining submodule and the second determining submodule.

[0047] Optionally, the intelligent driving traffic accident analysis device also includes:

[0048] The first calculation module is used to calculate the fusion processing data of the intelligent driving system at the time of the accident when the actual driving data matches the calculated intelligent driving control data, and to obtain decision planning data.

[0049] The first judgment module is used to determine whether the actual decision planning data at the time of the vehicle accident matches the calculated decision planning data, and to trigger the first processing module when the actual decision planning data at the time of the vehicle accident does not match the calculated decision planning data.

[0050] The first processing module is used to output the analysis conclusion based on the triggering of the first judgment module: when an accident occurs, the module used to calculate decision planning data in the intelligent driving system malfunctions.

[0051] Optionally, the intelligent driving traffic accident analysis device also includes:

[0052] The second calculation module is used to calculate the perception data of the intelligent driving system at the time of the accident and obtain fused processing data when the actual decision planning data at the time of the vehicle accident matches the calculated decision planning data.

[0053] The second judgment module is used to determine whether the actual fusion processing data at the time of the vehicle accident matches the calculated fusion processing data. When the actual fusion processing data at the time of the vehicle accident does not match the calculated fusion processing data, the second processing module is triggered. When the actual fusion processing data at the time of the vehicle accident matches the calculated fusion processing data, the third processing module is triggered.

[0054] The second processing module is used to output the analysis conclusion based on the triggering of the second judgment module: when an accident occurs, the module used to calculate and process the fusion data in the intelligent driving system has a problem;

[0055] The third processing module is used to output the analysis conclusion based on the triggering of the second judgment module: the intelligent driving system did not have any problems when the accident occurred.

[0056] Optionally, the intelligent driving traffic accident analysis device also includes:

[0057] The first scoring module is used to score the vehicle's condition based on the accident analysis report when the vehicle is involved in an accident within a preset time period, and obtain the first scoring result.

[0058] The acquisition module is used to acquire the vehicle's actual driving data and intelligent driving control data within a target time interval; the target time interval includes all times within a preset time period except for the time when the vehicle accident occurs.

[0059] The second scoring module is used to score the vehicle's condition based on the acquired actual driving data and intelligent driving control data, and obtain a second scoring result.

[0060] The third scoring module is used to determine the vehicle's condition score based on the first and second scoring results.

[0061] Optionally, the first scoring module is specifically used to score the vehicle's condition based on the accident analysis report at the time of the accident for each accident that occurs within a preset time period, to obtain a first score value, and to obtain a first score result based on the first score values ​​corresponding to all accidents within the preset time period.

[0062] The second scoring module includes:

[0063] The grouping submodule is used to group the actual driving data and intelligent driving control data at the same moment within the target time interval into a single data group for analysis.

[0064] The first scoring submodule is used to compare the difference between the actual driving data and the intelligent driving control data of each analysis data group with multiple pre-stored difference intervals, and score the vehicle condition according to the difference interval in which the difference lies, so as to obtain the second score value.

[0065] The second scoring submodule is used to obtain the second scoring result based on the second scoring value corresponding to all the analyzed data groups.

[0066] Thirdly, embodiments of this application provide an intelligent driving domain controller, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the computer program, it implements the aforementioned intelligent driving traffic accident analysis method.

[0067] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned intelligent driving traffic accident analysis method.

[0068] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the terminal device to execute the aforementioned intelligent driving traffic accident analysis method.

[0069] The beneficial effects of the embodiments of this application compared with the prior art are:

[0070] In the embodiments of this application, when a vehicle accident occurs, the intelligent driving data and actual driving data at the time of the accident are analyzed to determine whether the vehicle system malfunctioned at the time of the accident. Based on the determination results, an accident analysis report is generated to indicate whether the vehicle system malfunctioned at the time of the accident. This allows traffic managers to analyze the accident responsibility based on the accident analysis report, making it easier for traffic managers to determine responsibility for the accident. At the same time, it also helps autonomous vehicle managers to know the driving process of their vehicle during the accident, making it easier for them to grasp the vehicle's condition. Attached Figure Description

[0071] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0072] Figure 1 This is a general flowchart of an embodiment of the intelligent driving traffic accident analysis method provided in this application;

[0073] Figure 2This is a flowchart of a step-by-step analysis method for an intelligent driving system provided in an embodiment of this application;

[0074] Figure 3 This is a flowchart illustrating a specific implementation method for determining a vehicle's condition score according to an embodiment of this application;

[0075] Figure 4 This is a schematic diagram of the structure of an intelligent driving traffic accident analysis device provided in an embodiment of this application;

[0076] Figure 5 This is a schematic diagram of the structure of an intelligent driving domain controller provided in an embodiment of this application. Detailed Implementation

[0077] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0078] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, elements, components and / or collections thereof.

[0079] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0080] In the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0081] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0082] To facilitate understanding of the technical solutions involved in the embodiments of this application, the relevant technologies will be described below.

[0083] In intelligent driving, according to the classic domain controller classification, vehicle domain controllers can be divided into power domain controllers, chassis domain controllers, cockpit / intelligent information domain controllers, intelligent driving domain controllers, and body domain controllers.

[0084] The aforementioned intelligent driving domain controller possesses the capabilities of multi-sensor information acquisition, multi-sensor information fusion, processing, path planning, and decision-making control. Specifically, the intelligent driving domain controller needs to acquire perception sensor data (including but not limited to data from external cameras, millimeter-wave radar, lidar, integrated navigation systems, and other sensors), fuse and process the perception sensor data, and then formulate corresponding strategies based on an appropriate working model to make decisions and plans. After planning the path, it controls the vehicle to travel along the desired trajectory.

[0085] Currently, when autonomous vehicles are involved in traffic accidents, traffic managers are unable to determine liability because it is impossible to ascertain whether the vehicle's own system has a problem. For example, when vehicle A collides with vehicle B, traffic managers cannot determine liability because it is impossible to ascertain whether vehicle A (or vehicle B) has a problem with its own system. This makes it impossible to identify the party responsible for compensation from among the parties involved in the accident (including but not limited to the operator and manager of vehicle A, the designer and manufacturer of vehicle A's intelligent driving system, the operator and manager of vehicle B, the designer and manufacturer of vehicle B's intelligent driving system).

[0086] Furthermore, when an autonomous vehicle is involved in a traffic accident, the vehicle manager cannot know the vehicle's driving process during the accident because it is impossible to determine whether there is a problem with the vehicle's own system, and at the same time, the autonomous vehicle's condition cannot be monitored.

[0087] To address the aforementioned issues, this application provides an intelligent driving traffic accident analysis method. This method analyzes intelligent driving data and actual driving data at the time of an accident to determine whether the vehicle's system malfunctioned at the time of the accident. Based on the determination results, it generates an accident analysis report to indicate whether the vehicle's system malfunctioned at the time of the accident. This allows traffic managers to analyze accident liability based on the accident analysis report, facilitating the determination of responsibility for accidents. It also allows autonomous vehicle managers to understand the vehicle's driving process during the accident, enabling them to monitor the vehicle's condition.

[0088] The intelligent driving traffic accident analysis method provided in this application will be described by way of example below with reference to specific embodiments.

[0089] like Figure 1 As shown, an embodiment of this application provides a method for analyzing traffic accidents while driving intelligently. This method is applied to an intelligent driving domain controller and specifically includes the following steps:

[0090] Step 11: Analyze the intelligent driving data and actual driving data at the time of the vehicle accident.

[0091] The aforementioned intelligent driving data includes intelligent driving control data, decision-making and planning data, fusion processing data, and perception data. The calculation process for the intelligent driving control data is as follows: The intelligent driving domain controller first fuses the sensor data (i.e., perception data) collected by perception sensors installed on the vehicle (including but not limited to external cameras, millimeter-wave radar, lidar, global navigation satellite systems, inertial navigation systems, etc.) to obtain fusion processing data; then, based on the fusion processing data and a pre-defined working model, it formulates corresponding strategies, performs decision-making and planning, and obtains decision-making and planning data; finally, based on the decision-making and planning data and a pre-defined control model, it calculates the intelligent driving control data. This intelligent driving control data includes, but is not limited to, heading angle, vehicle speed, mileage, accelerator pedal travel, brake pedal travel, and position.

[0092] In some embodiments of this application, the aforementioned intelligent driving control data can be specifically obtained by calculating the sensor data collected by the perception sensors through the intelligent driving computing platform of the intelligent driving domain controller. It should be noted that the specific implementation process of the intelligent driving computing platform calculating the intelligent driving control data can refer to the existing functional implementation of the intelligent driving computing platform, and will not be elaborated here.

[0093] The aforementioned actual driving data refers to the driving data of the vehicle during actual driving (including but not limited to heading angle, vehicle speed, mileage, accelerator pedal travel, brake pedal travel, and position), which can be collected using actual driving data sensors installed on the vehicle (including but not limited to accelerator sensor, brake sensor, heading angle sensor, global navigation satellite system, vehicle speed sensor, mileage sensor, etc.).

[0094] Step 12: Based on the analysis results, determine whether the vehicle's system malfunctioned at the time of the accident.

[0095] The aforementioned vehicle system includes an intelligent driving system and an execution system, which includes a vehicle controller, communication lines, actuators, etc.

[0096] In some embodiments of this application, the analysis of intelligent driving data and actual driving data mainly includes comparative analysis and step-by-step analysis. Specifically, the analysis can be based on the results of the comparative analysis and step-by-step analysis to determine whether the vehicle system malfunctioned at the time of the accident. That is, the specific implementation of analyzing the intelligent driving data and actual driving data at the time of the accident and determining whether the vehicle system malfunctioned at the time of the accident can be as follows: Comparative analysis is performed on the intelligent driving control data and actual driving data at the time of the accident. When the intelligent driving control data and actual driving data do not match, it is determined that the vehicle's execution system malfunctioned at the time of the accident. When the intelligent driving control data and actual driving data match, step-by-step analysis is performed on the vehicle's intelligent driving system to determine whether the intelligent driving system malfunctioned. The step-by-step analysis process will be described in detail later.

[0097] The above comparative analysis primarily assesses whether the intelligent driving control data and actual driving data at the time of an accident are consistent, specifically whether the difference between the intelligent driving control data and actual driving data is within the allowable deviation range. It should be noted that when comparing and analyzing the intelligent driving control data and actual driving data at the time of an accident, the data being compared and analyzed are of the same type. For example, if the intelligent driving control data is the distance traveled on the accelerator pedal, then the actual driving data is also the distance traveled on the accelerator pedal; if the intelligent driving control data is the vehicle speed, then the actual driving data is also the vehicle speed.

[0098] Step 13: Generate an accident analysis report based on the determined results. This accident analysis report is used to indicate whether there was a problem with the vehicle's system at the time of the accident.

[0099] In some embodiments of this application, the aforementioned accident analysis report is an accident analysis report for the vehicle itself, used to indicate whether there is a problem with the vehicle's own system when an accident occurs, so as to provide traffic managers with a basis for determining accident liability and facilitate traffic managers in determining liability for accidents.

[0100] Specifically, when the intelligent driving control data at the time of an accident does not match the actual driving data, the aforementioned accident analysis report indicates a problem with the vehicle's execution system at the time of the accident. This allows traffic managers to determine liability based on the accident analysis report. It also allows vehicle managers to understand the vehicle's driving process during the accident, facilitating vehicle maintenance.

[0101] When the intelligent driving control data at the time of an accident matches the actual driving data, the intelligent driving domain controller generates an accident analysis report based on the hierarchical analysis results. This report indicates whether the vehicle's intelligent driving system has malfunctioned, enabling traffic managers to determine liability based on the report. It also informs vehicle managers of the vehicle's driving process during the accident.

[0102] For example, after receiving an accident analysis report, the intelligent driving domain controller can make the traffic manager / vehicle manager aware of the accident analysis report by displaying it, or by sending it to the traffic manager / vehicle manager. It should be noted that the specific display and sending methods of the accident analysis report are not limited in the embodiments of this application.

[0103] As can be seen, in some embodiments of this application, when a vehicle accident occurs, the intelligent driving data and actual driving data at the time of the accident are analyzed to determine whether the vehicle system malfunctioned at the time of the accident. Based on the determination results, an accident analysis report is generated to indicate whether the vehicle system malfunctioned at the time of the accident. This allows traffic managers to analyze accident liability based on the accident analysis report, facilitating the determination of liability by traffic managers. It also allows autonomous vehicle managers to know the driving process of their vehicle during the accident.

[0104] The step-by-step analysis process is illustrated below with specific examples.

[0105] like Figure 2 As shown, the specific steps for analyzing a vehicle's intelligent driving system step by step to determine whether a problem has occurred include the following:

[0106] Step 201: Calculate the decision-making and planning data of the vehicle's intelligent driving system at the time of the accident to obtain intelligent driving control data.

[0107] The aforementioned decision-making and planning data refers to the data used to calculate intelligent driving control data.

[0108] Step 202: Determine whether the actual driving data matches the calculated intelligent driving control data. If the actual driving data does not match the calculated intelligent driving control data, proceed to step 203. If the actual driving data matches the calculated intelligent driving control data, proceed to step 204.

[0109] The aforementioned actual driving data refers to the actual driving data at the time of the accident, i.e., the actual driving data in step 11. If the actual driving data does not match the intelligent driving control data calculated in step 201 (i.e., the difference between the actual driving data and the intelligent driving control data calculated in step 201 exceeds the allowable deviation range), it is determined that the module in the intelligent driving system used to calculate the intelligent driving control data malfunctioned at the time of the accident, and step 203 is executed. If the actual driving data matches the intelligent driving control data calculated in step 201 (i.e., the difference between the actual driving data and the intelligent driving control data calculated in step 201 is within the allowable deviation range), then step 204 is executed.

[0110] Step 203, Output analysis conclusion: The module in the intelligent driving system used to calculate intelligent driving control data malfunctioned when the accident occurred.

[0111] In some embodiments of this application, when it is determined that the module used to calculate intelligent driving control data has malfunctioned, an accident analysis report is generated to indicate the problem when an accident occurs. This allows traffic managers to determine liability for the accident based on the accident analysis report. Simultaneously, it also informs vehicle managers of the vehicle's driving process during the accident, facilitating maintenance of the module used to calculate intelligent driving control data.

[0112] For example, the problem with the module used to calculate intelligent driving control data may be a failure of the module's calculation or program, and the problem may be caused by other interruptions.

[0113] Step 204: Calculate the fusion processing data of the intelligent driving system at the time of the accident to obtain decision planning data.

[0114] The aforementioned decision-making and planning data refers to the data used to calculate decision-making and planning data.

[0115] Step 205: Determine whether the actual decision planning data at the time of the vehicle accident matches the calculated decision planning data. If the actual decision planning data at the time of the vehicle accident does not match the calculated decision planning data, proceed to step 206. If the actual decision planning data at the time of the vehicle accident matches the calculated decision planning data, proceed to step 207.

[0116] In some embodiments of this application, the aforementioned intelligent driving domain controller has a large-capacity storage device for storing intelligent driving data (including sensor data collected by perception sensors, data calculated by the intelligent driving computing platform on the sensor data (such as fusion processing data, decision planning data, and intelligent driving control data) and actual driving data).

[0117] In some embodiments of this application, the aforementioned actual decision-making and planning data refers to the decision-making and planning data at the time of a vehicle accident. Specifically, the intelligent driving domain controller can retrieve the actual decision-making and planning data at the time of a vehicle accident from the aforementioned storage device.

[0118] If the actual decision planning data does not match the decision planning data calculated in step 204 (i.e., the difference between the actual decision planning data and the decision planning data calculated in step 204 exceeds the allowable deviation range), it is determined that the module used to calculate the decision planning data in the intelligent driving system had a problem when the accident occurred, and step 206 is executed. If the actual decision planning data matches the decision planning data calculated in step 204 (i.e., the difference between the actual decision planning data and the decision planning data calculated in step 204 is within the allowable deviation range), then step 207 is executed.

[0119] Step 206, Output analysis conclusion: The module in the intelligent driving system used to calculate decision-making and planning data malfunctioned when the accident occurred.

[0120] In some embodiments of this application, when it is determined that the module used to calculate decision-planning data is malfunctioning, an accident analysis report is generated to indicate the problem when a vehicle accident occurs. This allows traffic managers to determine liability for the accident based on the accident analysis report. Simultaneously, it also informs vehicle managers of the vehicle's driving process during the accident, facilitating maintenance of the module used to calculate decision-planning data.

[0121] For example, the problem with the module used to calculate decision planning data may be the module's calculation or program failure, and the problem may be caused by other interruptions.

[0122] Step 207: Calculate the perception data of the intelligent driving system at the time of the accident to obtain fused processing data.

[0123] The aforementioned perception data refers to the data used for calculating and fusion processing data, that is, the sensor data collected by the perception sensors installed on the vehicle.

[0124] Step 208: Determine whether the actual fusion processing data at the time of the vehicle accident matches the calculated fusion processing data. If the actual fusion processing data at the time of the vehicle accident does not match the calculated fusion processing data, proceed to step 209. If the actual fusion processing data at the time of the vehicle accident matches the calculated fusion processing data, proceed to step 210.

[0125] The aforementioned actual fusion processing data refers to the actual fusion processing data at the time of the vehicle accident. If the actual fusion processing data does not match the fusion processing data calculated in step 207 (i.e., the difference between the actual fusion processing data and the fusion processing data calculated in step 207 exceeds the allowable deviation range), it is determined that the module in the intelligent driving system used to calculate the fusion processing data had a problem at the time of the accident, and step 209 is executed. If the actual fusion processing data matches the fusion processing data calculated in step 207 (i.e., the difference between the actual fusion processing data and the fusion processing data calculated in step 207 is within the allowable deviation range), it is determined that the intelligent driving system did not have a problem at the time of the accident, and step 210 is executed.

[0126] Step 209, Output analysis conclusion: The module in the intelligent driving system used to calculate and process data fusion malfunctioned when the accident occurred.

[0127] In some embodiments of this application, when it is determined that the module used to calculate the fusion processing data has malfunctioned, an accident analysis report is generated to indicate the problem when a vehicle accident occurs. This allows traffic managers to determine liability for the accident based on the accident analysis report. Simultaneously, it also informs vehicle managers of the vehicle's driving process during the accident, facilitating maintenance of the module used to calculate the fusion processing data.

[0128] For example, the problem with the module used to calculate and process the fusion data could be a failure of the module's calculation or program, and the problem could be caused by other interruptions.

[0129] Step 210, output analysis conclusion: The intelligent driving system did not have any problems when the accident occurred.

[0130] In some embodiments of this application, when it is determined that the intelligent driving system has not malfunctioned, an accident analysis report is generated to indicate that the intelligent driving system did not malfunction when the vehicle was involved in an accident. This allows traffic managers to determine liability for the accident based on the accident analysis report, and also enables vehicle managers to know the vehicle's driving process during the accident.

[0131] As can be seen, in some embodiments of this application, intelligent driving traffic accidents can be analyzed using comparative analysis and hierarchical analysis methods to determine whether the vehicle's system has malfunctioned. Specifically, when the comparative analysis process determines that the vehicle's execution system has malfunctioned, a result indicating a problem with the vehicle's execution system is output. When the comparative analysis process indicates that the vehicle's intelligent driving system may have a problem, the intelligent driving traffic accident is analyzed using a hierarchical analysis method, and based on the analysis results, a result indicating either a problem with the vehicle's intelligent driving system or a result indicating that the vehicle's intelligent driving system has not malfunctioned is output.

[0132] The vehicle condition scoring process is illustrated below with reference to specific embodiments.

[0133] like Figure 3 As shown, the intelligent driving traffic accident analysis method provided in the embodiments of this application further includes the following steps for determining the vehicle's condition score:

[0134] Step 31: Based on the accident analysis report of the vehicle when an accident occurs within a preset time period, score the vehicle's condition to obtain the first score result.

[0135] In some embodiments of this application, for each accident that occurs within a preset time period, the vehicle condition can be scored based on the accident analysis report at the time of the accident to obtain a first score value; then, based on the first score values ​​corresponding to all accidents within the preset time period, a first score result can be obtained.

[0136] In some embodiments of this application, a first score value corresponding to the accident can be determined from a scoring rule table based on the accident analysis report at the time of the accident. This scoring rule table records vehicle condition scores corresponding to when the vehicle experiences problems (including but not limited to problems with the execution system, problems with modules in the intelligent driving system used to calculate intelligent driving control data, problems with modules in the intelligent driving system used to calculate decision-making and planning data, and problems with modules in the intelligent driving system used to calculate fusion processing data) and when no problems occur. For example, if the accident analysis report at the time of the accident indicates a problem with the vehicle's execution system, the vehicle condition score value (i.e., the aforementioned first score value) corresponding to the accident can be determined by querying the scoring rule table.

[0137] Specifically, in some embodiments of this application, the average value of the first score corresponding to all accidents within a preset time period can be calculated, and the product of the average value and the first preset weight coefficient can be used as the first score result.

[0138] It should be noted that the above preset time period can be set according to the actual situation, such as the past 3 months, the past 6 months, etc.

[0139] Step 32: Obtain the vehicle's actual driving data and intelligent driving control data within the target time interval.

[0140] The aforementioned target time interval includes all times within the preset time period except for the time when the vehicle accident occurs. In some embodiments of this application, the intelligent driving domain controller can retrieve the actual driving data and intelligent driving control data from step 32 from the aforementioned storage device.

[0141] Step 33: Based on the obtained actual driving data and intelligent driving control data, score the vehicle's condition to obtain a second score result.

[0142] In some embodiments of this application, the actual driving data and intelligent driving control data at the same moment within the target time interval can be used as an analysis data group; then, for each analysis data group, the difference between the actual driving data and the intelligent driving control data of the analysis data group is compared with multiple pre-stored difference intervals, and the vehicle condition is scored according to the difference interval in which the difference lies, to obtain a second score value; finally, a second score result is obtained based on the second score values ​​corresponding to all analysis data groups.

[0143] It should be noted that the intelligent driving control data and actual driving data in the analysis data set are of the same type. For example, if the intelligent driving control data in the analysis data set is vehicle speed, then the actual driving data in the analysis data set is also vehicle speed. Furthermore, the aforementioned multiple difference intervals can be pre-set and stored based on the experience of staff in vehicle condition scoring. In specific settings, the difference intervals corresponding to different types of data can be different. For example, when the intelligent driving control data and actual driving data in the analysis data set are vehicle speed, the corresponding multiple difference intervals are speed difference intervals; when the intelligent driving control data and actual driving data in the analysis data set are the vehicle's accelerator pedal travel, the corresponding multiple difference intervals are accelerator pedal travel difference intervals.

[0144] In some embodiments of this application, for each set of analyzed data, a second score value corresponding to that set of analyzed data can be determined from a scoring rule table based on the difference range between the actual driving data and the intelligent driving control data of the analyzed data set. This scoring rule table records the vehicle condition score value corresponding to each of the aforementioned multiple difference ranges. For example, if both the intelligent driving control data and the actual driving data in the analyzed data set are vehicle speeds, and the difference between the intelligent driving control data and the actual driving data is 2 km / h, then the difference range containing this difference can be determined by querying the scoring rule table, and the vehicle condition score value (i.e., the aforementioned second score value) corresponding to that set of analyzed data can be determined based on the determined difference range.

[0145] Specifically, in some embodiments of this application, the average value of the second score corresponding to all analysis data groups can be calculated, and the product of the average value and the second preset weight coefficient can be used as the second score result.

[0146] Step 34: Determine the vehicle condition score based on the first and second score results.

[0147] In some embodiments of this application, the sum of the values ​​corresponding to the first rating result and the second rating result can be used as the vehicle condition rating.

[0148] In some embodiments of this application, the second preset weight coefficient is less than the first preset weight coefficient, so that the weight of the first scoring result is higher than that of the second scoring result, thereby improving the accuracy and authenticity of the vehicle condition scoring.

[0149] For example, after obtaining the vehicle's condition score, the intelligent driving domain controller can display the score to inform the vehicle manager, thereby enabling the vehicle manager to monitor the autonomous vehicle's condition. Alternatively, the vehicle manager can be informed of the condition score by sending it to the controller. It should be noted that the specific display and sending methods of the condition score are not limited in the embodiments of this application.

[0150] The intelligent driving traffic accident analysis device, intelligent driving domain controller and related media and products provided in the embodiments of this application are described below with reference to the accompanying drawings.

[0151] Corresponding to the intelligent driving traffic accident analysis method described in the above embodiments, such as Figure 4 As shown, an embodiment of this application provides an intelligent driving traffic accident analysis device, applied to an intelligent driving domain controller. The intelligent driving traffic accident analysis device 400 includes:

[0152] Analysis module 401 is used to analyze intelligent driving data and actual driving data when a vehicle accident occurs;

[0153] The determination module 402 is used to determine whether the vehicle system has malfunctioned at the time of the accident, based on the analysis results of the analysis module 401.

[0154] The generation module 403 is used to generate an accident analysis report based on the determined results; the accident analysis report is used to indicate whether there is a problem with the vehicle system of the intelligent driving vehicle when an accident occurs.

[0155] Optionally, the vehicle system includes an execution system and an intelligent driving system, and the intelligent driving data includes intelligent driving control data, decision planning data, fusion processing data, and perception data.

[0156] Optionally, the analysis module 401 is specifically used to compare and analyze the intelligent driving control data and actual driving data when a vehicle accident occurs;

[0157] Optionally, the determining module 402 includes:

[0158] The first determination submodule is used to determine that the vehicle's execution system malfunctioned at the time of the accident when the analysis results of the analysis module show that the intelligent driving control data and the actual driving data do not match.

[0159] The second determination submodule is used to perform step-by-step analysis of the vehicle's intelligent driving system to determine whether there is a problem with the intelligent driving system when the analysis result of the analysis module is consistent with the intelligent driving control data and the actual driving data.

[0160] The third determining submodule is used to determine whether there is a problem with the vehicle system of the intelligent driving vehicle based on the conclusions of the first determining submodule and the second determining submodule.

[0161] It should be noted that the prerequisite for the module to perform the above steps is that all the perception sensors of the intelligent driving vehicle are operating normally.

[0162] Optionally, the intelligent driving traffic accident analysis device 400 also includes:

[0163] The first calculation module is used to calculate the fusion processing data of the intelligent driving system at the time of the accident when the actual driving data matches the calculated intelligent driving control data, and to obtain decision planning data.

[0164] The first judgment module is used to determine whether the actual decision planning data at the time of the vehicle accident matches the calculated decision planning data, and to trigger the first processing module when the actual decision planning data at the time of the vehicle accident does not match the calculated decision planning data.

[0165] The first processing module is used to output the analysis conclusion based on the triggering of the first judgment module: when an accident occurs, the module used to calculate decision planning data in the intelligent driving system malfunctions.

[0166] Optionally, the intelligent driving traffic accident analysis device 400 also includes:

[0167] The second calculation module is used to calculate the perception data of the intelligent driving system at the time of the accident and obtain fused processing data when the actual decision planning data at the time of the vehicle accident matches the calculated decision planning data.

[0168] The second judgment module is used to determine whether the actual fusion processing data at the time of the vehicle accident matches the calculated fusion processing data. When the actual fusion processing data at the time of the vehicle accident does not match the calculated fusion processing data, the second processing module is triggered. When the actual fusion processing data at the time of the vehicle accident matches the calculated fusion processing data, the third processing module is triggered.

[0169] The second processing module is used to output the analysis conclusion based on the triggering of the second judgment module: when an accident occurs, the module used to calculate and process the fusion data in the intelligent driving system has a problem;

[0170] The third processing module is used to output the analysis conclusion based on the triggering of the second judgment module: the intelligent driving system did not have any problems when the accident occurred.

[0171] Optionally, the intelligent driving traffic accident analysis device 400 also includes:

[0172] The first scoring module is used to score the vehicle's condition based on the accident analysis report when the vehicle is involved in an accident within a preset time period, and obtain the first scoring result.

[0173] The acquisition module is used to acquire the vehicle's actual driving data and intelligent driving control data within a target time interval; the target time interval includes all times within a preset time period except for the time when the vehicle accident occurs.

[0174] The second scoring module is used to score the vehicle's condition based on the acquired actual driving data and intelligent driving control data, and obtain a second scoring result.

[0175] The third scoring module is used to determine the vehicle's condition score based on the first and second scoring results.

[0176] Optionally, the first scoring module is specifically used to score the vehicle's condition based on the accident analysis report at the time of the accident for each accident that occurs within a preset time period, to obtain a first score value, and to obtain a first score result based on the first score values ​​corresponding to all accidents within the preset time period.

[0177] The second scoring module includes:

[0178] The grouping submodule is used to group the actual driving data and intelligent driving control data at the same moment within the target time interval into a single data group for analysis.

[0179] The first scoring submodule is used to compare the difference between the actual driving data and the intelligent driving control data of each analysis data group with multiple pre-stored difference intervals, and score the vehicle condition according to the difference interval in which the difference lies, so as to obtain the second score value.

[0180] The second scoring submodule is used to obtain the second scoring result based on the second scoring value corresponding to all the analyzed data groups.

[0181] It is understood that the various implementation methods and combinations of implementation methods and their beneficial effects in the above-described intelligent driving traffic accident analysis method embodiments are also applicable to intelligent driving traffic accident analysis devices, and will not be elaborated here.

[0182] like Figure 5 As shown, embodiments of this application provide an intelligent driving domain controller, such as... Figure 5 As shown, the intelligent driving domain controller D10 of this embodiment includes: at least one processor D100 ( Figure 5 The diagram shows only one processor, a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100. When the processor D100 executes the computer program D102, it implements the steps in any of the above method embodiments. Alternatively, when the processor D100 executes the computer program D102, it implements the functions of each module / unit in the above device embodiments.

[0183] In some embodiments, when the processor D100 executes the computer program D102, it performs the following steps: analyzing the intelligent driving data and actual driving data at the time of the vehicle accident to determine whether the vehicle system malfunctioned at the time of the accident; generating an accident analysis report based on the determination result; the accident analysis report is used to indicate whether the vehicle system malfunctioned at the time of the accident.

[0184] Optionally, the vehicle system includes an execution system and an intelligent driving system. Intelligent driving data includes intelligent driving control data, decision-making and planning data, fusion processing data, and perception data. When processor D100 executes computer program D102, it can also perform the following steps: compare and analyze the intelligent driving control data and actual driving data at the time of the accident; when the intelligent driving control data and actual driving data do not match, determine that the vehicle's execution system malfunctioned at the time of the accident; when the intelligent driving control data and actual driving data match, perform a step-by-step analysis of the vehicle's intelligent driving system to determine whether the intelligent driving system has malfunctioned.

[0185] Optionally, when the processor D100 executes the computer program D102, it may also perform the following steps: calculate the decision planning data of the vehicle's intelligent driving system at the time of the accident to obtain intelligent driving control data; determine whether the actual driving data matches the calculated intelligent driving control data; when the actual driving data does not match the calculated intelligent driving control data, conclude that the module used to calculate the intelligent driving control data in the intelligent driving system at the time of the accident has a problem.

[0186] Optionally, when the processor D100 executes the computer program D102, it may also perform the following steps: when the actual driving data matches the calculated intelligent driving control data, calculate the fusion processing data of the intelligent driving system at the time of the accident to obtain decision planning data; determine whether the actual decision planning data at the time of the vehicle accident matches the calculated decision planning data; when the actual decision planning data at the time of the vehicle accident does not match the calculated decision planning data, conclude that the module used to calculate the decision planning data in the intelligent driving system at the time of the accident has a problem.

[0187] Optionally, when processor D100 executes computer program D102, it may also perform the following steps: when the actual decision-making and planning data at the time of the vehicle accident matches the calculated decision-making and planning data, calculate the perception data of the intelligent driving system at the time of the accident to obtain fused processing data; determine whether the actual fused processing data at the time of the vehicle accident matches the calculated fused processing data; when the actual fused processing data at the time of the vehicle accident does not match the calculated fused processing data, conclude that the module in the intelligent driving system used to calculate the fused processing data at the time of the accident has a problem; when the actual fused processing data at the time of the vehicle accident matches the calculated fused processing data, conclude that the intelligent driving system has no problem at the time of the accident.

[0188] Optionally, when processor D100 executes computer program D102, it may also perform the following steps: scoring the vehicle's condition based on the accident analysis report when the vehicle has an accident within a preset time period, and obtaining a first score result; acquiring the vehicle's actual driving data and intelligent driving control data within a target time interval; the target time interval includes other times within the preset time period besides the time when the vehicle has an accident; scoring the vehicle's condition based on the acquired actual driving data and intelligent driving control data, and obtaining a second score result; and determining the vehicle's condition score based on the first score result and the second score result.

[0189] Optionally, when the processor D100 executes the computer program D102, it may also perform the following steps: for each accident that occurs to the vehicle within a preset time period, score the vehicle condition based on the accident analysis report at the time of the accident to obtain a first score value; and obtain a first score result based on the first score values ​​corresponding to all accidents within the preset time period.

[0190] Optionally, when the processor D100 executes the computer program D102, it can also perform the following steps: taking the actual driving data and intelligent driving control data at the same moment within the target time interval as an analysis data group; for each analysis data group, comparing the difference between the actual driving data and the intelligent driving control data of the analysis data group with multiple pre-stored difference intervals, and scoring the vehicle condition according to the difference interval in which the difference lies, to obtain a second score value; and obtaining a second score result based on the second score values ​​corresponding to all analysis data groups.

[0191] The processor D100 can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0192] In some embodiments, the memory D101 may be an internal storage unit of the intelligent driving domain controller D10, such as a hard disk or memory of the intelligent driving domain controller D10. In other embodiments, the memory D101 may be an external storage device of the intelligent driving domain controller D10, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the intelligent driving domain controller D10. Furthermore, the memory D101 may include both internal storage units and external storage devices of the intelligent driving domain controller D10. The memory D101 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory D101 can also be used to temporarily store data that has been output or will be output.

[0193] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0194] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0195] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps in the above-described intelligent driving traffic accident analysis method embodiments.

[0196] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the intelligent driving traffic accident analysis method embodiment.

[0197] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to the intelligent driving traffic accident analysis device / intelligent driving domain controller, recording media, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0198] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0199] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0200] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0201] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0202] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for analyzing traffic accidents while driving intelligently, characterized in that, Applied to intelligent driving domain controllers, the method includes: Analyze intelligent driving data and actual driving data at the time of a vehicle accident to determine whether the vehicle's system malfunctioned at the time of the accident; An accident analysis report is generated based on the determined results; the accident analysis report is used to indicate whether there was a problem with the vehicle system when the accident occurred; The vehicle system includes an execution system and an intelligent driving system, and the intelligent driving data includes intelligent driving control data, decision planning data, fusion processing data, and perception data. The analysis of intelligent driving data and actual driving data at the time of a vehicle accident to determine whether the vehicle's system malfunctioned at the time of the accident includes: Comparative analysis of intelligent driving control data and actual driving data at the time of a vehicle accident; When the intelligent driving control data at the time of the accident does not match the actual driving data, it is determined that the vehicle's execution system malfunctioned at the time of the accident. When the intelligent driving control data at the time of the vehicle accident matches the actual driving data, the intelligent driving system of the vehicle is analyzed step by step in the order of decision planning data, fusion processing data, and perception data to determine whether there is a problem with the intelligent driving system.

2. The method according to claim 1, characterized in that, The step-by-step analysis of the vehicle's intelligent driving system to determine whether a problem has occurred includes: The decision-making and planning data of the vehicle's intelligent driving system at the time of the accident are calculated to obtain intelligent driving control data; Determine whether the actual driving data matches the calculated intelligent driving control data; When the actual driving data does not match the calculated intelligent driving control data, it is determined that the module in the intelligent driving system used to calculate the intelligent driving control data malfunctioned when the accident occurred.

3. The method according to claim 2, characterized in that, After determining whether the actual driving data matches the calculated intelligent driving control data, the method further includes: When the actual driving data matches the calculated intelligent driving control data, the fusion processing data of the intelligent driving system at the time of the accident is calculated to obtain decision planning data. Determine whether the actual decision planning data matches the calculated decision planning data; When the actual decision-making and planning data do not match the calculated decision-making and planning data, it is determined that the module in the intelligent driving system used to calculate the decision-making and planning data malfunctioned when the accident occurred.

4. The method according to claim 3, characterized in that, After determining whether the actual decision-making planning data at the time of the accident matches the calculated decision-making planning data, the method further includes: When the actual decision planning data matches the calculated decision planning data, the perception data of the intelligent driving system at the time of the accident is calculated to obtain fused processing data. Determine whether the actual fusion processing data matches the calculated fusion processing data; When the actual fusion processing data does not match the calculated fusion processing data, it is determined that the module in the intelligent driving system used to calculate the fusion processing data malfunctioned when the accident occurred. When the actual fusion processing data matches the calculated fusion processing data, it is determined that the intelligent driving system did not malfunction when the accident occurred.

5. The method according to claim 1, characterized in that, The method further includes: Based on the accident analysis report of the vehicle when an accident occurs within a preset time period, the vehicle condition is scored to obtain a first score result; Acquire the actual driving data and intelligent driving control data of the vehicle within a target time interval; the target time interval includes all times within the preset time period except for the time when the vehicle is involved in an accident. Based on the acquired actual driving data and intelligent driving control data, the vehicle's condition is scored to obtain a second score result; The vehicle condition score is determined based on the first score and the second score.

6. The method according to claim 5, characterized in that, The step of scoring the vehicle's condition based on accident analysis reports from accidents occurring within a preset time period to obtain a first score result includes: For each accident that occurs to the vehicle within a preset time period, the vehicle condition is scored based on the accident analysis report at the time of the accident, and a first score value is obtained. The first score result is obtained based on the first score value corresponding to all accidents within the preset time period; The process of scoring the vehicle's condition based on the acquired actual driving data and intelligent driving control data to obtain a second scoring result includes: The actual driving data and intelligent driving control data at the same moment within the target time interval are used as a set of analysis data. For each set of analyzed data, the actual driving data of the analyzed data set is compared with that of intelligent driving. The difference in control data is compared with multiple pre-stored difference intervals, and the vehicle condition is scored according to the difference interval in which the difference falls, to obtain a second score value; The second score result is obtained based on the second score value corresponding to all the analyzed data groups.

7. An intelligent driving traffic accident analysis device, characterized in that, The intelligent driving traffic accident analysis device, applied to an intelligent driving domain controller, includes: The analysis module is used to analyze intelligent driving data and actual driving data at the time of a vehicle accident; The determination module is used to determine, based on the analysis results of the analysis module, whether the vehicle system malfunctioned at the time of the accident. A generation module is used to generate an accident analysis report based on the determined results; the accident analysis report is used to indicate whether the vehicle system of the vehicle malfunctioned when the accident occurred; The determining module includes: The first determination submodule is used to determine that the vehicle's execution system malfunctioned at the time of the accident when the analysis results of the analysis module show that the intelligent driving control data and the actual driving data do not match. The second determining submodule is used to perform step-by-step analysis of the vehicle's intelligent driving system in the order of decision planning data, fusion processing data, and perception data when the analysis result of the analysis module is consistent with the intelligent driving control data and the actual driving data. The third determining submodule is used to determine whether there is a problem with the vehicle system of the intelligent driving vehicle based on the conclusions of the first determining submodule and the second determining submodule.

8. An intelligent driving domain controller, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, When the processor executes the computer program, it implements the intelligent driving traffic accident analysis method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the intelligent driving traffic accident analysis method as described in any one of claims 1 to 6.

Images