Vehicle control method and device, vehicle and storage medium

Abstract

The invention discloses a vehicle control method and device, a vehicle and a readable storage medium, and the method comprises the steps: determining the control data of the vehicle through an intelligent driving function of the vehicle based on the environment data collected by the vehicle; performing data detection on the to-be-detected data to obtain a data detection result; the to-be-detected data comprises at least one of environment data and control data; the data detection comprises at least one of physical effective range value detection, effective interval detection, information clamping stagnation detection and timestamp detection; if the data detection result indicates that the to-be-detected data is abnormal, the vehicle is controlled to exit the intelligent driving function, and a driver of the vehicle is reminded to take over the vehicle. According to the method, the safety of the driving process is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and more specifically, to a vehicle control method, device, vehicle, and computer-readable storage medium. Background Art

[0002] With the development of electronic information technology, vehicles are becoming increasingly versatile. Currently, vehicles can autonomously drive or assist the driver in their active driving process through their own intelligent driving functions. However, in related technologies, such autonomous driving or assisting the driver in their active driving process through intelligent driving functions often results in low driving safety. Summary of the Invention

[0003] The present application proposes a vehicle control method, device, vehicle and computer-readable storage medium to increase the safety of the vehicle during driving.

[0004] In a first aspect, an embodiment of the present application provides a vehicle control method, the method comprising: Determine the vehicle's control data based on the vehicle's collected environmental data through the vehicle's intelligent driving function; Performing data detection on the data to be detected to obtain a data detection result; the data to be detected includes at least one of environmental data and control data; the data detection includes at least one of physical valid range value detection, valid interval detection, information jam detection and timestamp detection; the physical valid range value detection is used to detect whether the data to be detected exceeds the planning rationality range corresponding to the data to be detected; the valid interval detection is used to detect whether the data to be detected exceeds the hardware rationality range corresponding to the data to be detected; the information jam detection is used to detect whether the data to be detected is jammed; the timestamp detection is used to detect whether the timestamp of the data to be detected is abnormal; If the data detection result indicates that there is an abnormality in the data to be detected, the vehicle will be controlled to exit the intelligent driving function and the driver of the vehicle will be reminded to take over the vehicle.

[0005] In a second aspect, an embodiment of the present application further provides a vehicle control device, the device comprising: A determination module, configured to determine vehicle control data based on environmental data collected by the vehicle through the vehicle's intelligent driving function; The detection module is used to perform data detection on the data to be detected and obtain a data detection result; the data to be detected includes at least one of environmental data and control data; the data detection includes at least one of physical valid range value detection, valid interval detection, information jam detection and timestamp detection; the physical valid range value detection is used to detect whether the data to be detected exceeds the planning rationality range corresponding to the data to be detected; the valid interval detection is used to detect whether the data to be detected exceeds the hardware rationality range corresponding to the data to be detected; the information jam detection is used to detect whether the data to be detected is jammed; the timestamp detection is used to detect whether the timestamp of the data to be detected is abnormal; The control module is used to control the vehicle to exit the intelligent driving function and remind the driver of the vehicle to take over the vehicle if the data detection result indicates that there is an abnormality in the data to be detected.

[0006] In a third aspect, an embodiment of the present application also provides a vehicle, comprising: one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the above method.

[0007] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a program code executable by a processor, and when the program code is executed by the processor, the processor executes the above method.

[0008] The present application provides a vehicle control method, device, vehicle and computer-readable storage medium. In the present application, first, environmental data collected by the vehicle and at least one of the control data determined by the intelligent driving function of the vehicle are obtained as data to be detected, and then the data to be detected are detected to obtain a data detection result. When the data detection result indicates that there is an abnormality in the data to be detected, the vehicle is controlled to exit the intelligent driving function and the driver of the vehicle is reminded to take over the vehicle. In this way, when the environmental data is abnormal and / or the determined control data is abnormal, the intelligent driving function is no longer used, thereby reducing the risk of inaccurate determined control data due to abnormal environmental data or inaccurate control data determined based on normal environmental data due to abnormal intelligent driving function, resulting in a situation where the vehicle is less safe when driving based on the control data, so that the driver can take over the vehicle when the control data is inaccurate, thereby effectively ensuring the safety of the vehicle driving process.

[0009] Other features and advantages of the embodiments of the present application will be described in the following description and, in part, will become apparent from the description or be understood by practicing the embodiments of the present application. The objectives and other advantages of the embodiments of the present application can be achieved and obtained through the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of a vehicle hardware environment suitable for an embodiment of the present application is shown.

[0012] Figure 2 A flow chart of a vehicle control method proposed according to an embodiment of the present application is shown.

[0013] Figure 3 Shown Figure 2 The steps after step S102 of the corresponding embodiment are in a flowchart of an embodiment.

[0014] Figure 4 Shown Figure 2 The steps subsequent to step S102 of the corresponding embodiment are in the flowchart of yet another embodiment.

[0015] Figure 5 A schematic diagram of a vehicle structure in an embodiment of the present application is shown.

[0016] Figure 6 Shown Figure 5 A schematic structural diagram of the intelligent driving domain controller module 52 in one embodiment.

[0017] Figure 7 Shown Figure 5 A schematic structural diagram of the intelligent driving domain controller module 52 in another embodiment.

[0018] Figure 8 A structural block diagram of a vehicle control device proposed in one embodiment of the present application is shown. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for which protection is claimed, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0020] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0021] Reference Figure 1 , Figure 1 A schematic diagram of a vehicle hardware environment suitable for an embodiment of the present application is shown, where the vehicle 100 includes a driving system 110. The driving system 110 may have multiple built-in autonomous driving functions. The driving system 110 may store an electronic map. The driving system 110 may plan a driving route based on the electronic map stored in itself, and may also control the vehicle's autonomous driving based on the planned driving route.

[0022] The driving system 110 may include a data acquisition device 111 , one or more (only one is shown in the figure) processors 112 , and a memory 113 .

[0023] The data acquisition device 111 is used to detect the vehicle's environmental information, which may include in-vehicle environmental information and out-vehicle environmental information. The data acquisition device 111 may include a camera, an ultrasonic radar, a millimeter-wave radar, a lidar, a high-precision combined navigation and positioning system, and a high-precision map, etc., so as to collect the sum of the in-vehicle environmental information and the out-vehicle environmental information through the data acquisition device 111 as environmental information.

[0024] The processor 112 may be a microcontroller unit (MCU) having a built-in memory 113 . The memory 113 stores a program that can execute the contents of the following embodiments, and the processor 112 can execute the program stored in the memory 113 .

[0025] The processor 112 may include one or more processors. The processor 112 utilizes various interfaces and circuits to connect various components within the vehicle 100 and execute various functions and process data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 113 and accessing data stored in the memory 113.

[0026] The memory 113 may include random access memory (RAM) or read-only memory (ROM). The memory 15 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 15 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), and instructions for implementing the following method embodiments.

[0027] See also Figure 2 , Figure 2 A flow chart of a vehicle control method according to one embodiment of the present application is shown, which is used for a vehicle. The method includes: S101. Determine vehicle control data based on environmental data collected by the vehicle through the vehicle's intelligent driving function.

[0028] The vehicle in this embodiment can be an electric vehicle or a fuel vehicle, or a car, an SUV, a bus, a truck, etc.

[0029] Intelligent driving functions refer to functions used to achieve autonomous driving or assist drivers with assisted driving. Intelligent driving functions include model software components based on machine learning. This model software component can include a segmented end-to-end large model architecture (such as a perception large model + a prediction and decision large model) or a holistic large model architecture (a full link of perception, prediction and decision). This model software component can perform planning, decision-making, and control operations based on environmental data collected by the vehicle to obtain control data for the vehicle. Generally, control data can refer to data that achieves lateral and longitudinal control of the vehicle. Control data can include, for example, speed, acceleration, steering angle, and trajectory.

[0030] As mentioned above, the vehicle's environmental data may include in-vehicle environmental data and out-vehicle environmental data. The in-vehicle environmental data may include the driver's status and the passenger's status, etc., and the out-vehicle environmental data may include obstacle information, lane information, and traffic sign information around the vehicle.

[0031] Sensors used to collect environmental data include but are not limited to cameras, ultrasonic radars, millimeter-wave radars, lidars, and high-precision integrated navigation and positioning systems. Of course, vehicles can also have built-in high-precision maps to achieve high-precision area maps near the vehicle's location based on high-precision maps. The high-precision area maps can be used as part of the environmental data to determine control data.

[0032] In some embodiments, S101 may include: performing data preprocessing on environmental data through the intelligent driving function to obtain preprocessed environmental data; and determining vehicle control data based on the preprocessed environmental data through the intelligent driving function.

[0033] The intelligent driving function may include a preprocessing module for preprocessing environmental data. The preprocessing module is used to preprocess the environmental data. The data preprocessing includes coordinate system conversion, data cleaning, data unit conversion, and data format conversion, etc. The data after preprocessing the environmental data is used as preprocessed environmental data.

[0034] Generally speaking, directly collected environmental data is difficult to be directly used by the model in the intelligent driving function. Therefore, a preprocessing module is also needed to preprocess the environmental data through the preprocessing module to obtain preprocessed environmental data that can be directly used by the model in the intelligent driving function. Then, the model in the intelligent driving function performs planning, decision-making and control operations based on the preprocessed environmental data to obtain control data for the vehicle.

[0035] In some further embodiments, the aforementioned determination of the vehicle's control data based on the pre-processed environmental data by the intelligent driving function may also include: performing control prediction based on the pre-processed environmental data by the intelligent driving function to determine the vehicle's initial control data; and performing data post-processing based on the initial control data by the intelligent driving function to obtain the vehicle's control data.

[0036] The intelligent driving function uses pre-processed environmental data to perform planning, decision-making, and control operations to obtain data used to implement vehicle control, which serves as initial control data. Initial control data may be difficult for the vehicle to use directly, so it is necessary to perform data post-processing on the initial control data to obtain post-processed data as control data. Data post-processing can include coordinate system conversion, data unit conversion, and data format conversion.

[0037] S102: Perform data detection on the data to be detected to obtain a data detection result.

[0038] The data detection result is used to indicate whether the data to be detected is abnormal. The data to be detected includes at least one of environmental data and control data. Therefore, the data detection result includes whether the environmental data is abnormal and / or whether the control data is abnormal.

[0039] In this embodiment, data detection includes at least one of physical valid range value detection, valid interval detection, information stuck detection, and timestamp detection; the physical valid range value detection is used to detect whether the data to be detected exceeds the planning rationality range corresponding to the data to be detected; the valid interval detection is used to detect whether the data to be detected exceeds the hardware rationality range corresponding to the data to be detected; the information stuck detection is used to detect whether the data to be detected is stuck; and the timestamp detection is used to detect whether the timestamp of the data to be detected is abnormal. The planning rationality range refers to the data range in which the data to be detected is reasonable in the scenario to which it belongs. For example, the data to be detected is the speed data of other vehicles in the environmental data, and the scenario to which the data to be detected belongs is the urban road scenario. At this time, the planning rationality range of the speed data is generally 10km / h-60km / h. For another example, the data to be detected is the speed data in the control data, and the scenario to which the data to be detected belongs is the highway scenario. At this time, the planning rationality range of the speed data is generally 80km / h-130km / h.

[0040] If the data to be tested does not exceed the planned rationality range, it means that the data to be tested is normal. If the data to be tested exceeds the planned rationality range, it means that the data to be tested is abnormal.

[0041] The hardware rationality range refers to the data range covered by the hardware on which the data to be detected depends. For example, if the data to be detected is the speed data of other vehicles in the environmental data, and the other vehicles are ordinary cars, then the hardware rationality range of the speed data is generally the speed range covered by cars, 0-160km / h. For another example, if the data to be detected is the acceleration data in the control data, and the vehicle is a car, then the hardware rationality range of the acceleration data is generally 0-50m / h. .

[0042] If the data to be tested does not exceed the hardware rationality range, it means that the data to be tested is normal. If the data to be tested exceeds the hardware rationality range, it means that the data to be tested is abnormal.

[0043] Generally speaking, environmental data is usually collected through sensors. At this time, when the hardware rationality range of the environmental data is detected, it can be directly determined whether the collected environmental data exceeds the range of the corresponding sensor. If it exceeds the corresponding range, it means that the environmental data does not meet the hardware rationality range and the environmental data is abnormal.

[0044] Information stagnation detection refers to detecting whether the data to be tested is continuously not updated. If it occurs, it means that the data to be tested is stuck and the data to be tested is abnormal.

[0045] For example, if the camera image data remains unchanged and is not updated while the vehicle is in motion, it means that the data collected by the camera is stuck and the data collected by the camera is abnormal.

[0046] Timestamp testing is the process of checking whether the timestamps of the data being tested have rolled back, become stuck, or become discontinuous. If this happens, it indicates an anomaly in the timestamps of the data being tested, and the data is considered abnormal. This is because, under normal circumstances, the timestamps of the data being tested should continue to accumulate. If the timestamps between two frames of data roll back, become stuck, or become discontinuous, it indicates an anomaly in the data being tested.

[0047] For example, if the timestamp information of the previous and next frames of the control torque signal output by the vehicle regresses, it can be determined that the control torque signal is abnormal.

[0048] Generally speaking, when the data to be detected is environmental data, the environmental data not only involves specific data values, but also includes information such as timestamps. Therefore, the data detection involved in the environmental data can include physical valid range value detection, valid interval detection, information jam detection and timestamp detection. However, when the data to be detected is control data, the timestamp of the control data is generally not prone to problems, and the control data may remain unchanged for a continuous period of time. Therefore, the data detection involved in the control data can include physical valid range value detection and valid interval detection.

[0049] Of course, in order to ensure the accuracy and integrity of data verification, the data detection involved in controlling data may also include information jam detection and time stamp detection.

[0050] In some embodiments, as described in S101 above, the intelligent driving function can also obtain pre-processed environmental data. Thus, the pre-processed environmental data can also be obtained as data to be detected. Similarly to the above, the data detection involved in the pre-processed environmental data can include physical valid range value detection, valid interval detection, information jam detection and timestamp detection.

[0051] In some other embodiments, as described in S101 above, the intelligent driving function can also obtain initial control data, thereby obtaining the initial control data as data to be detected. Similarly to the above, the data detection involved in the initial control data can include physical valid range value detection and valid interval detection.

[0052] It is easy to understand that, referring to the above content, the data to be detected includes environmental data, pre-processed environmental data, initial control data, and control data. Therefore, when the data to be detected is tested, the data to be detected can be at least one of the environmental data, pre-processed environmental data, initial control data, and control data, and the data to be detected is not limited to including any one of the environmental data, pre-processed environmental data, initial control data, and control data. Of course, for the accuracy and completeness of the test, the data to be detected can include the aforementioned environmental data, pre-processed environmental data, initial control data, and control data.

[0053] S103. If the data detection result indicates that there is an abnormality in the data to be detected, control the vehicle to exit the intelligent driving function and remind the driver of the vehicle to take over the vehicle.

[0054] As mentioned above, the data to be detected may include one or more of environmental data and control data (of course, the data to be detected may also be one or more of environmental data, pre-processed environmental data, initial control data and control data).

[0055] Therefore, when the data to be detected includes one item, if the data detection result of the data to be detected indicates that the data to be detected is abnormal, then it is determined that the data detection result indicates that the data to be detected is abnormal; if the data detection result of the data to be detected indicates that the data to be detected is normal, then it is determined that the data detection result indicates that the data to be detected is normal.

[0056] Correspondingly, when the data to be detected includes multiple items, if the data detection result of at least one item in the data to be detected is data abnormality, it is determined that the data detection result indicates that there is an abnormality in the data to be detected; if the data detection results of all items in the data to be detected are data normal, it is determined that the data detection result indicates that the data to be detected is normal.

[0057] When the data detection results indicate that there are abnormalities in the data to be detected, the intelligent driving function is determined to be unreliable and the control data output by the intelligent driving function is inaccurate (this may be due to abnormal environmental data causing the determined control data to be inaccurate, or the intelligent driving function itself is abnormal causing the control data determined based on normal environmental data to be inaccurate). The intelligent driving function is exited and the driver takes over the vehicle, thereby reducing the possibility of inaccurate control data determined by the intelligent driving function, resulting in lower safety of the vehicle driving process controlled based on the control data determined by the intelligent driving function, and improving driving safety.

[0058] Of course, after exiting the intelligent driving function, the driver can be prompted to take over the vehicle through lights, voice or text prompts.

[0059] It is worth mentioning that when the data to be processed includes environmental data and the environmental data is abnormal, the abnormal environmental data can also be determined, and the abnormal environmental data and its corresponding sensor can be output to facilitate repair processing of the sensor corresponding to the abnormal environmental data and eliminate the problem of sensor abnormality.

[0060] In this embodiment, at least one of the environmental data collected by the vehicle and the control data determined by the intelligent driving function of the vehicle is first obtained as the data to be detected, and then the data to be detected is detected to obtain a data detection result. When the data detection result indicates that there is an abnormality in the data to be detected, the vehicle is controlled to exit the intelligent driving function, and the driver of the vehicle is reminded to take over the vehicle. In this way, when the environmental data is abnormal and / or the determined control data is abnormal, the intelligent driving function is no longer used, thereby reducing the possibility that the determined control data is inaccurate due to abnormal environmental data or the control data determined based on normal environmental data is inaccurate due to abnormal intelligent driving function, resulting in a situation where the vehicle is less safe when driving based on the control data, so that the driver can take over the vehicle when the control data is inaccurate, thereby effectively ensuring the safety of the vehicle driving process.

[0061] In some embodiments, as Figure 3 As shown, after S102, if the data detection result indicates that the data to be detected is abnormal, the method may further include: S310: Determine a first auxiliary detection result based on a difference between a detection result corresponding to the environmental data in the data detection result and a detection result corresponding to the pre-processed environmental data.

[0062] The detection result corresponding to the environmental data is used to indicate whether the environmental data is abnormal, and the detection result corresponding to the preprocessed environmental data is used to indicate whether the preprocessed environmental data is abnormal. By comparing the difference between the detection result corresponding to the environmental data and the detection result corresponding to the preprocessed environmental data, the first auxiliary detection result is determined. The first auxiliary detection result indicates whether the process of data preprocessing of the environmental data is abnormal (that is, when data preprocessing is implemented through the preprocessing module, it is determined that the preprocessing module is abnormal).

[0063] If the detection result corresponding to the environmental data indicates that the environmental data is normal, and the detection result corresponding to the preprocessed environmental data indicates that the preprocessed environmental data is abnormal, it means that a data error occurred when the environmental data was preprocessed, resulting in abnormal preprocessed environmental data. At this time, it is determined that an abnormality occurred in the data preprocessing process.

[0064] If the detection result corresponding to the environmental data indicates that the environmental data is normal, and the detection result corresponding to the preprocessed environmental data indicates that the preprocessed environmental data is normal, it means that no data error occurs when the environmental data is preprocessed. At this time, it is determined that there is no abnormality in the data preprocessing process.

[0065] If the test results for the environmental data indicate an anomaly, and the test results for the preprocessed environmental data also indicate an anomaly, it's difficult to directly determine whether an anomaly occurred during data preprocessing. In this case, if the environmental data includes multiple sub-data, further analysis of each sub-data item is necessary. A sub-data item is a category of environmental data, such as velocity, acceleration, image, torque, radar, or heading angle.

[0066] Specifically, for any sub-data in the environmental data, if the sub-data is abnormal before and after data preprocessing, it is difficult to determine whether the data preprocessing process of the sub-data is abnormal. The data preprocessing process of the sub-data is taken as the first candidate preprocessing process.

[0067] For any sub-data in the environmental data, if the sub-data is normal before data preprocessing (there are abnormal sub-data of other items, and thus the overall performance of the environmental data is abnormal), and is abnormal after data preprocessing, it is determined that the data preprocessing process of the sub-data is abnormal.

[0068] Of course, when the data preprocessing processes of each sub-data in the environmental data are all first candidate preprocessing processes, it means that the data preprocessing processes of each sub-data are all first candidate preprocessing processes that are difficult to identify. At this time, technical personnel are required to manually analyze to determine whether each first candidate preprocessing process is abnormal, and then determine that the entire data preprocessing process is abnormal if at least one first candidate preprocessing process is abnormal. If none of the first candidate preprocessing processes are abnormal, determine that the entire data preprocessing process is normal.

[0069] S320: Determine a second auxiliary detection result based on a difference between a detection result corresponding to the pre-processing environment data and a detection result corresponding to the initial control data in the data detection result.

[0070] The detection result corresponding to the pre-processed environment data is used to indicate whether the pre-processed environment data is abnormal, and the detection result corresponding to the initial control data is used to indicate whether the initial control data is abnormal. By comparing the difference between the detection result corresponding to the pre-processed environment data and the detection result corresponding to the initial control data, the second auxiliary detection result is determined. The second auxiliary detection result indicates whether there is an abnormality in the planning process of the data for controlling the vehicle based on the pre-processed data (the planning process refers to the process of planning, decision-making and control operations based on the pre-processed environment data to obtain the initial control data).

[0071] If the detection result corresponding to the preprocessing environment data indicates that the preprocessing environment data is normal, and the detection result corresponding to the initial control data indicates that the initial control data is abnormal, it means that a data error occurred in the planning process, resulting in abnormal initial control data. At this time, it is determined that the planning process is abnormal.

[0072] If the detection result corresponding to the preprocessing environment data indicates that the preprocessing environment data is normal, and the detection result corresponding to the initial control data indicates that the initial control data is normal, it means that there is no data error in the planning process. At this time, it is determined that there is no abnormality in the planning process.

[0073] If the detection results corresponding to the preprocessing environment data indicate that the preprocessing environment data is abnormal, and the detection results corresponding to the initial control data also indicate that the initial control data is abnormal, it is difficult to directly determine whether there is an abnormality in the data preprocessing process. At this time, it can be determined whether the abnormality indicated by the detection results corresponding to the preprocessing environment data is consistent or similar to that indicated by the detection results of the initial control data. If they are consistent or similar, it means that the planning process obtains wrong data based on wrong data, and there is a high probability that there is no abnormality in the planning process, and it is determined that there is no abnormality in the planning process; if they are inconsistent and dissimilar, it means that the planning process has generated new wrong data, and there is a high probability that there is an abnormality in the planning process, and there is an abnormality in the planning process.

[0074] S330: Determine a third auxiliary detection result based on a difference between a detection result corresponding to the initial control data and a detection result corresponding to the control data in the data detection result.

[0075] The detection result corresponding to the initial control data is used to indicate whether the initial control data is abnormal, and the detection result corresponding to the control data is used to indicate whether the control data is abnormal. By comparing the difference between the detection result corresponding to the initial control data and the detection result corresponding to the control data, the third auxiliary detection result is determined. The third auxiliary detection result indicates whether the process of post-processing the initial control data is abnormal (that is, when data post-processing is implemented through the post-processing module, it is determined that the post-processing module is abnormal).

[0076] If the detection result corresponding to the initial control data indicates that the initial control data is normal, and the detection result corresponding to the control data indicates that the control data is abnormal, it means that a data error occurred when the initial control data was post-processed, resulting in abnormal control data. At this time, it is determined that the data post-processing process is abnormal.

[0077] If the detection result corresponding to the initial control data indicates that the initial control data is normal, and the detection result corresponding to the control data indicates that the control data is normal, it means that no data error occurs when the initial control data is post-processed. At this time, it is determined that there is no abnormality in the data post-processing process.

[0078] If the test results corresponding to the initial control data indicate an anomaly, and the test results corresponding to the control data also indicate an anomaly, it is difficult to directly determine whether an anomaly has occurred during data post-processing. In this case, if the initial control data includes multiple sub-data, further analysis of each sub-data item is necessary. A sub-data item is a category of data in the initial control data, such as velocity, acceleration, or heading angle.

[0079] Specifically, for any sub-data in the initial control data, if the sub-data is abnormal before and after data post-processing, it is difficult to determine whether the data post-processing process of the sub-data is abnormal, and the data post-processing process of the sub-data is used as the second candidate post-processing process.

[0080] For any sub-data in the initial control data, if the sub-data is normal before data post-processing (there are abnormal sub-data of other items, and thus the initial control data as a whole is abnormal), and is abnormal after data post-processing, it is determined that the data post-processing process of the sub-data is abnormal.

[0081] Of course, when the data post-processing processes of each sub-data in the initial control data are all second candidate post-processing processes, it means that the data post-processing processes of each sub-data are all second candidate post-processing processes that are difficult to identify. At this time, technical personnel are required to manually analyze to determine whether each second candidate post-processing process is abnormal, and then determine that the entire data post-processing process is abnormal if at least one second candidate post-processing process is abnormal. If none of the second candidate post-processing processes are abnormal, determine that the entire data post-processing process is normal.

[0082] S340. Determine a functional detection result of the intelligent driving function based on at least one of the first auxiliary detection result, the second auxiliary detection result, and the third auxiliary detection result.

[0083] As previously mentioned, the first auxiliary detection result, the second auxiliary detection result, and the third auxiliary detection result respectively indicate whether the three different processes involved in the entire intelligent driving function (preprocessing process, planning process, and post-processing process) are abnormal. Therefore, based on at least one of the first auxiliary detection result, the second auxiliary detection result, and the third auxiliary detection result, it is determined whether the three processes involved in the entire intelligent driving function are abnormal. In other words, the functional test result of the intelligent driving function is used to indicate whether at least one of the three different processes involved in the entire intelligent driving function is abnormal.

[0084] Of course, after obtaining the functional test results of the intelligent driving function, the functional test results of the intelligent driving function can be output, and the functional test results of the intelligent driving function can be output so that the driver can check the functional test results of the intelligent driving function in time, determine the specific abnormal content of the intelligent driving function, and facilitate abnormal repair of the intelligent driving function.

[0085] In this embodiment, when the data detection results indicate that there are abnormalities in the data to be detected, the intelligent driving function is also analyzed to determine whether the various processes of the intelligent driving function are abnormal, so that the user can promptly discover whether the intelligent driving function is abnormal and promptly repair the abnormal intelligent driving function, thereby improving the repair efficiency of the intelligent driving function.

[0086] In some embodiments, as Figure 4 As shown, after S102, the method further includes: S410: If the data detection result indicates that there is no abnormality in the data to be detected, obtain auxiliary control data of the vehicle.

[0087] The auxiliary control data is determined based on environmental data using a preset rule algorithm for the vehicle. The preset rule algorithm is different from the method used by the intelligent driving function in the aforementioned embodiment. The preset rule algorithm may include a Pid algorithm, model predictive control (MPC), an adaptive control algorithm, and a vector control algorithm. The intelligent driving function in step S101 of the aforementioned embodiment may include data preprocessing, model software components, and data post-processing. In this embodiment, for ease of distinction and understanding, the intelligent driving function in step S101 of the aforementioned embodiment is referred to as a model predictive algorithm.

[0088] The environmental data collected by the preset rule algorithm is directly analyzed to determine the data used to control the vehicle as auxiliary control data.

[0089] S420: Control the vehicle based on the auxiliary control data and the control data.

[0090] After obtaining the auxiliary control data and the control data, the auxiliary control data and the control data may be combined to control the vehicle.

[0091] In some implementations, a weighted summation of the auxiliary control data and the control data (e.g., where the weight of the control data is greater than the weight of the auxiliary control data) may be performed to obtain target control data, which is then used to control the vehicle. The weighted summation process may involve weighted summation of specific values for each category of data under the auxiliary control data and the control data. The categories here may include speed, acceleration, and heading angle, for example.

[0092] In some further embodiments, the vehicle may be controlled based on the difference between the auxiliary control data and the control data.

[0093] For example, the difference between the auxiliary control data and the control data can be determined, and the difference can be multiplied by a specified coefficient to obtain a product. The product is then calculated (summed, subtracted, multiplied, etc.) with the control data to obtain target control data, and the vehicle is controlled using the target control data. The specified coefficient can be, for example, 0.5 or 0.6.

[0094] Alternatively, if the difference between the auxiliary control data and the control data is greater than a preset difference, the vehicle is controlled based on the preset safety control data; if the difference between the auxiliary control data and the control data is not greater than the preset difference, the vehicle is controlled based on the control data. The preset difference can be a difference based on demand calibration, which is not limited in this application.

[0095] The preset security control data may refer to control data corresponding to a security boundary or control data when executing an action corresponding to a minimum risk maneuver (MRM).

[0096] When the difference between the auxiliary control data and the control data is greater than the preset difference, it is determined that even if the data detection result indicates that there is no abnormality in the data to be detected, there may be an abnormality in the model prediction algorithm in the aforementioned intelligent driving function, and a given safety strategy (preset safety control data) is adopted to control the vehicle. When the difference between the auxiliary control data and the control data is not greater than the preset difference, it is determined that there is no abnormality in the model prediction algorithm in the aforementioned intelligent driving function, and control is performed by directly adopting the control data determined by the model prediction algorithm in the aforementioned intelligent driving function.

[0097] It is worth mentioning that the preset rule algorithm in this embodiment is also part of the intelligent driving function. When the "data detection result indicates that there is an abnormality in the data to be detected" in S103 is met, exiting the intelligent driving function means no longer using the preset rule algorithm to determine the auxiliary control data.

[0098] In this embodiment, the vehicle is controlled by combining the model prediction algorithm in the intelligent driving function and a given preset rule algorithm, avoiding driving solely relying on the model prediction algorithm in the intelligent driving function, thereby reducing the occurrence of low driving safety caused by inaccurate intelligent driving function, and making the vehicle driving safer.

[0099] For example, the structural block diagram of the vehicle is as follows: Figure 5 As shown, the vehicle includes a vehicle environment detection module 51, an intelligent driving domain controller module 52 and a vehicle control execution module 53, wherein the vehicle environment detection module 51 is used to collect environmental data, the intelligent driving domain controller module 52 is used to obtain control data, and the vehicle control execution module 53 is used to control the vehicle driving based on the vehicle control data.

[0100] Specifically, such as Figure 6 As shown, the intelligent driving domain controller module 52 can also include a control component 203, an arbitration module 210, a rationality monitoring module 208 and a redundancy rule module 209, wherein the control component 203 includes a preprocessing module 204, a machine learning module 205 and a post-processing module 206.

[0101] Environmental data is collected through the vehicle environment detection module 51, and the environmental data is preprocessed by the preprocessing module 204 to obtain preprocessed environmental data. The machine learning module 205 performs row planning, decision-making and control operations based on the preprocessed environmental data to obtain initial control data, and then the initial control data is post-processed by the post-processing module 206 to obtain control data.

[0102] The rationality monitoring module 208 is used to perform data detection on the environmental data, pre-processed environmental data and initial control data, and the arbitration module 210 is used to perform data detection on the control data. Specifically, the arbitration module 210 can output the detection results of each item of data to be detected.

[0103] At the same time, when the environmental data, pre-processed environmental data, initial control data and control data are all normal, the arbitration module 210 is also used to obtain the auxiliary control data determined by the redundant rule module 209, and combine the control data output by the post-processing module 206 and the auxiliary control data output by the redundant rule module 209 to determine the final output control data (preset safety control data or control data output by the post-processing module 206), and the intelligent driving domain controller module 53 performs output control based on the output control data.

[0104] For example, the structural block diagram of the aforementioned intelligent driving domain controller module 52 can also be as follows Figure 7 As shown, the intelligent driving domain controller processor 521 can be composed of multiple chips or a single-chip multi-core heterogeneous composition, and is used to execute computer instructions to implement the vehicle control method in this application. The storage device 522 includes ROM and RAM. The RAM in the storage device 522 is used as a medium for storing computer instructions that implement the vehicle control method in this application, and the ROM in the storage device 522 is used as a medium for running computer instructions that implement the vehicle control method in this application; the communication device 523 includes: supporting bus communication between the intelligent driving controller and other controllers, such as CAN bus and Ethernet bus.

[0105] The intelligent driving domain controller module 52 communicates with various sensor components in the vehicle through various interfaces or buses in the communication device 523, such as the UART serial port and the VSDL bus; the intelligent driving domain controller module 52 supports communication between various components in the intelligent driving domain controller module 52 (the intelligent driving domain controller processor 521 and the storage device 522) through the protocols supported by the communication device 523, such as SomeIP, PCIe, etc.

[0106] See attached Figure 8 , Figure 8 The following is a block diagram of a vehicle control device according to one embodiment of the present application. The device 700 is used in a vehicle and includes: A determination module 710 is configured to determine vehicle control data based on environmental data collected by the vehicle using the vehicle's intelligent driving function; The detection module 720 is used to perform data detection on the data to be detected and obtain a data detection result; the data to be detected includes at least one of environmental data and control data; the data detection includes at least one of physical valid range value detection, valid interval detection, information jam detection and timestamp detection; the physical valid range value detection is used to detect whether the data to be detected exceeds the planning rationality range corresponding to the data to be detected; the valid interval detection is used to detect whether the data to be detected exceeds the hardware rationality range corresponding to the data to be detected; the information jam detection is used to detect whether the data to be detected is jammed; and the timestamp detection is used to detect whether the timestamp of the data to be detected is abnormal. The control module 730 is used to control the vehicle to exit the intelligent driving function and remind the driver of the vehicle to take over the vehicle if the data detection result indicates that there is an abnormality in the data to be detected.

[0107] Optionally, the determination module 710 is also used to preprocess the environmental data through the intelligent driving function to obtain preprocessed environmental data; determine the control data of the vehicle based on the preprocessed environmental data through the intelligent driving function; and obtain the preprocessed environmental data as data to be detected.

[0108] Optionally, the determination module 710 is also used to perform control prediction based on pre-processed environmental data through the intelligent driving function to determine the initial control data of the vehicle; perform data post-processing based on the initial control data through the intelligent driving function to obtain the control data of the vehicle; and obtain the initial control data as the data to be detected.

[0109] Optionally, the data to be detected includes environmental data, pre-processed environmental data, initial control data and control data; the device also includes a function detection module for determining a first auxiliary detection result based on the difference between the detection result corresponding to the environmental data in the data detection result and the detection result corresponding to the pre-processed environmental data; determining a second auxiliary detection result based on the difference between the detection result corresponding to the pre-processed environmental data in the data detection result and the detection result corresponding to the initial control data; determining a third auxiliary detection result based on the difference between the detection result corresponding to the initial control data and the detection result corresponding to the control data in the data detection result; and determining the function detection result of the intelligent driving function based on at least one of the first auxiliary detection result, the second auxiliary detection result and the third auxiliary detection result.

[0110] Optionally, the control module 730 is also used to obtain auxiliary control data of the vehicle if the data detection result indicates that there is no abnormality in the data to be detected; wherein the auxiliary control data is determined based on environmental data through a preset rule algorithm for the vehicle; and the vehicle is controlled based on the auxiliary control data and the control data.

[0111] Optionally, the control module 730 is further configured to control the vehicle based on the auxiliary control data and the difference between the control data.

[0112] Optionally, the control module 730 is also used to control the vehicle based on the preset safety control data if the difference between the auxiliary control data and the control data is greater than the preset difference; and to control the vehicle based on the control data if the difference between the auxiliary control data and the control data is not greater than the preset difference.

[0113] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0114] In addition, the functions in the various embodiments of the present application may be integrated into a single processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or software functional modules.

[0115] On the other hand, the present application also provides a computer-readable storage medium, which stores program code. The program code can be called by a processor to execute the method described in the above method embodiment.

[0116] The computer-readable storage medium may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, a hard disk, or a cluster of ROMs. Alternatively, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program code for executing any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code may be compressed, for example, in a suitable format.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements 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 the present application.

Claims

1. A vehicle control method, characterized in that: The method comprises: Determining control data of the vehicle based on environmental data collected by the vehicle through the intelligent driving function of the vehicle; Performing data detection on the data to be detected to obtain a data detection result; the data to be detected includes at least one of the environmental data and the control data; the data detection includes at least one of a physical valid range value detection, a valid interval detection, an information jam detection, and a timestamp detection; the physical valid range value detection is used to detect whether the data to be detected exceeds the planning rationality range corresponding to the data to be detected; the valid interval detection is used to detect whether the data to be detected exceeds the hardware rationality range corresponding to the data to be detected; the information jam detection is used to detect whether the data to be detected has a jamming phenomenon; the timestamp detection is used to detect whether the timestamp of the data to be detected is abnormal; If the data detection result indicates that there is an abnormality in the data to be detected, the vehicle is controlled to exit the intelligent driving function and the driver of the vehicle is reminded to take over the vehicle.

2. The method according to claim 1, characterized in that The determining, by the intelligent driving function of the vehicle based on environmental data collected by the vehicle, control data of the vehicle includes: Preprocessing the environmental data using the intelligent driving function to obtain preprocessed environmental data; Determining control data of the vehicle based on the pre-processed environmental data through the intelligent driving function; The method further comprises: The pre-processed environment data is obtained as data to be detected.

3. The method according to claim 2, characterized in that The determining, by the intelligent driving function based on the pre-processed environmental data, the control data of the vehicle includes: performing control prediction based on the pre-processed environmental data by the intelligent driving function to determine initial control data of the vehicle; Performing data post-processing based on the initial control data by the intelligent driving function to obtain control data of the vehicle; The method further comprises: The initial control data is obtained as data to be detected.

4. The method according to claim 3, characterized in that The data to be detected includes the environmental data, the pre-processed environmental data, the initial control data and the control data; If the data detection result indicates that the data to be detected is abnormal, the method further includes: determining a first auxiliary detection result based on a difference between a detection result corresponding to the environmental data in the data detection result and a detection result corresponding to the preprocessed environmental data; determining a second auxiliary detection result based on a difference between a detection result corresponding to the preprocessing environment data and a detection result corresponding to the initial control data in the data detection result; determining a third auxiliary detection result based on a difference between a detection result corresponding to the initial control data and a detection result corresponding to the control data in the data detection result; Based on at least one of the first auxiliary detection result, the second auxiliary detection result, and the third auxiliary detection result, a functional detection result of the intelligent driving function is determined.

5. The method according to claim 1, wherein The method further comprises: If the data detection result indicates that the data to be detected does not have an abnormality, obtaining auxiliary control data of the vehicle; wherein the auxiliary control data is determined based on the environmental data by a preset rule algorithm for the vehicle; The vehicle is controlled based on the auxiliary control data and the control data.

6. The method according to claim 5, characterized in that The controlling the vehicle based on the auxiliary control data and the control data includes: The vehicle is controlled based on the auxiliary control data and a difference between the control data.

7. The method according to claim 6, characterized in that The controlling the vehicle based on the difference between the auxiliary control data and the control data includes: If the difference between the auxiliary control data and the control data is greater than a preset difference, controlling the vehicle based on preset safety control data; If the difference between the auxiliary control data and the control data is not greater than the preset difference, the vehicle is controlled based on the control data.

8. A vehicle control device, characterized in that: The device comprises: a determination module, configured to determine control data of the vehicle based on environmental data collected by the vehicle through the intelligent driving function of the vehicle; A detection module is used to perform data detection on the data to be detected and obtain a data detection result; the data to be detected includes at least one of the environmental data and the control data; the data detection includes at least one of a physical valid range value detection, a valid interval detection, an information jam detection and a timestamp detection; the physical valid range value detection is used to detect whether the data to be detected exceeds the planning rationality range corresponding to the data to be detected; the valid interval detection is used to detect whether the data to be detected exceeds the hardware rationality range corresponding to the data to be detected; the information jam detection is used to detect whether the data to be detected has a jamming phenomenon; the timestamp detection is used to detect whether the timestamp of the data to be detected is abnormal; A control module is used to control the vehicle to exit the intelligent driving function and remind the driver of the vehicle to take over the vehicle if the data detection result indicates that there is an abnormality in the data to be detected.

9. A vehicle, characterized in that: include: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores program codes executable by a processor, and when the program codes are executed by the processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images