Controller verification method and device, storage medium and electronic equipment

Abstract

The present disclosure relates to a controller verification method and device, a storage medium and an electronic device, which solve the technical problems of high verification cost and long verification time of vehicle controllers in the related art. The method comprises: obtaining road data, wherein the road data comprises historical road information; preprocessing the road data to obtain a target data set, sending the target data set to a vehicle controller, and generating second driving warning information based on the target data set by the vehicle controller; and generating first driving warning information according to the target data set; and verifying the accuracy of the second driving warning information generated by the vehicle controller according to the first driving warning information. The present disclosure does not need to perform real vehicle road test again to obtain new road information when verifying different vehicle controllers, thereby reducing the verification cost and time.

Description

Technical Field

[0001] This disclosure relates to the field of hardware testing technology, and more specifically, to a controller verification method, apparatus, storage medium, and electronic device. Background Technology

[0002] During the development phase, intelligent driving vehicles require extensive real-vehicle road testing to obtain test data for the controller. After debugging the controller based on the test data, it is necessary to conduct real-vehicle road testing again to obtain new test data, which consumes a lot of time and costs. Summary of the Invention

[0003] The purpose of this disclosure is to provide a controller verification method, apparatus, storage medium, and electronic device to solve the technical problems of high verification cost and long verification time for vehicle controllers in related technologies.

[0004] To achieve the above objectives, according to a first aspect of the present disclosure, a controller verification method is provided, applied to a host computer, the method comprising:

[0005] Acquire road data, wherein the road data includes historically collected road information;

[0006] The road data is preprocessed to obtain a target dataset, which is then sent to the vehicle controller, which generates a second driving warning message based on the target dataset.

[0007] Generate first driving warning information based on the target dataset;

[0008] The accuracy of the second driving warning information generated by the vehicle controller is verified based on the first driving warning information.

[0009] Optionally, verifying the accuracy of the vehicle controller generating the second driving warning information based on the first driving warning information includes:

[0010] Based on the first driving warning information and the second driving warning information, the abnormal warning information of the vehicle controller is obtained, and the abnormal warning information includes the false alarm rate and / or the missed alarm rate.

[0011] Verification of the vehicle controller based on the abnormal warning information.

[0012] Optionally, the road data includes CAN data and video data, and the preprocessing of the road data to obtain the target dataset includes:

[0013] The format of the CAN data and the video data are verified separately.

[0014] If the CAN data and video data formats pass verification, the CAN data and video data are synchronized to obtain the target dataset.

[0015] Optionally, the timestamps of the CAN data and the video data are consistent, and the synchronization processing of the CAN data and the video data includes:

[0016] The video data is played back using a video darkroom based on the timestamp to obtain first target data from the video data. The first target data includes the speed and acceleration of the person or object carried in the video data relative to the vehicle.

[0017] The CAN data is replayed using the CAN card according to the timestamp to obtain the second target data in the CAN data. The second target data includes the speed and acceleration of the person or object carried in the CAN data relative to the vehicle.

[0018] The target dataset is obtained based on the first target data and the second target data.

[0019] Optionally, the timestamps of the CAN data and the video data are consistent, and the synchronization processing of the CAN data and the video data includes:

[0020] Based on the user's operation instructions, a target recognition algorithm is determined from multiple recognition algorithms. The target recognition algorithm processes the video data according to the timestamp to obtain third target data in the video data. The third target data includes the speed and acceleration of the people and objects carried in the video data relative to the vehicle.

[0021] The CAN data is replayed using the CAN card according to the timestamp to obtain the fourth target data in the CAN data. The fourth target data includes the speed and acceleration of the person or object carried in the CAN data relative to the vehicle.

[0022] The target dataset is obtained based on the third target data and the fourth target data.

[0023] Optionally, generating the first driving warning information based on the target dataset includes:

[0024] Based on the user's operation instructions, a target fusion algorithm is determined from multiple fusion algorithms, and the target dataset is processed by the target fusion algorithm to obtain the first driving warning information.

[0025] Optionally, the target recognition algorithm may be one or more. When there are multiple recognition algorithms, the step of processing the video data according to the timestamp using the target recognition algorithm to obtain the third target data in the video data includes:

[0026] For each recognition algorithm, the video data is processed according to the timestamp to obtain the third target data in the video data;

[0027] Accordingly, obtaining the target dataset based on the third target data and the fourth target data includes:

[0028] For each of the third target data, a target dataset is obtained based on the third target data and the fourth target data;

[0029] The step of generating the first driving warning information based on the target dataset includes:

[0030] A first driving warning message is generated based on each of the target datasets to obtain multiple first driving warning messages.

[0031] Optionally, the fusion algorithm may be one or more. When there are multiple fusion algorithms, the step of processing the target dataset using a target fusion algorithm to obtain the first driving warning information includes:

[0032] For each fusion algorithm, the target dataset is processed by the fusion algorithm to obtain first driving warning information, so as to obtain multiple first driving warning information.

[0033] According to a second aspect of the present disclosure, a controller verification method is provided, applied to a vehicle controller, the method comprising:

[0034] Receive the target dataset sent by the host computer, which is obtained by the host computer through preprocessing historically collected road information;

[0035] The second driving warning information is obtained based on the target dataset, and the second driving warning information is fed back to the host computer so that the host computer can obtain the false alarm rate and false alarm rate of the vehicle controller based on the second driving warning information.

[0036] According to a third aspect of the embodiments of this disclosure, this disclosure provides a controller verification device applied to a host computer, the device comprising:

[0037] The reading module is configured to acquire road data, wherein the road data includes historically collected road information;

[0038] The first execution module is configured to preprocess the road data to obtain a target dataset, and send the target dataset to the vehicle controller so that the vehicle controller can generate a second driving warning information based on the target dataset.

[0039] The second execution module is configured to generate first driving warning information based on the target dataset;

[0040] The verification module is configured to verify the accuracy of the second driving warning information generated by the vehicle controller based on the first driving warning information.

[0041] According to a fourth aspect of the present disclosure, a controller verification apparatus is provided for use in a vehicle controller, the apparatus comprising:

[0042] The receiving module is configured to receive a target dataset sent by a host computer, the target dataset being obtained by the host computer through preprocessing historically collected road information;

[0043] The sending module is configured to obtain second driving warning information based on the target dataset, and feed the second driving warning information back to the host computer, so that the host computer can obtain the false alarm rate and false alarm rate of the vehicle controller based on the second driving warning information.

[0044] According to a fifth aspect of the present disclosure, a computer-readable storage medium is provided that stores a computer program thereon, which, when executed by a processor, implements the steps of the controller verification method described in the first aspect or the steps of the controller verification method described in the second aspect.

[0045] According to a sixth aspect of the present disclosure, an electronic device is provided, the electronic device comprising:

[0046] A memory on which computer programs are stored;

[0047] A processor for executing the computer program in the memory to implement the steps of the controller verification method described in the first aspect above.

[0048] According to a seventh aspect of the present disclosure, an electronic device is provided, the electronic device comprising:

[0049] A memory on which computer programs are stored;

[0050] A processor is configured to execute the computer program in the memory to implement the steps of the controller verification method described in the second aspect above.

[0051] Through the above technical solutions, the technical solutions provided by the embodiments of this disclosure can include the following beneficial effects: The host computer of this disclosure only needs to perform a real vehicle road test once to obtain road data, and send the target dataset obtained based on the road data to different vehicle controllers. The accuracy of the first driving warning information generated by the host computer based on the target dataset is verified against the accuracy of the second driving warning information generated by the vehicle controller based on the target dataset. The verification of different vehicle controllers can be realized based on the driving warning information. There is no need to perform a real vehicle road test again to obtain new road information when verifying different vehicle controllers, which reduces the verification cost and reduces the verification time.

[0052] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0053] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings:

[0054] Figure 1 This is a flowchart illustrating a controller verification method according to an exemplary embodiment.

[0055] Figure 2 This is a flowchart illustrating a method for obtaining a target dataset according to an exemplary embodiment.

[0056] Figure 3 This is a schematic diagram illustrating the structure of a method for obtaining a target dataset according to an exemplary embodiment.

[0057] Figure 4 This is a flowchart illustrating another method for obtaining a target dataset according to an exemplary embodiment.

[0058] Figure 5 This is a schematic diagram illustrating the structure of another method for obtaining a target dataset according to an exemplary embodiment.

[0059] Figure 6 This is a block diagram illustrating a controller verification device according to an exemplary embodiment.

[0060] Figure 7 This is a block diagram illustrating another controller verification device according to an exemplary embodiment.

[0061] Figure 8 This is a block diagram illustrating an electronic device according to an exemplary embodiment.

[0062] Figure 9 This is a block diagram illustrating another electronic device according to an exemplary embodiment. Detailed Implementation

[0063] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure.

[0064] It should be noted that in this disclosure, the terms "S101", "S102", etc., in the specification, claims and drawings are used to distinguish steps, and should not be construed as performing method steps in a specific order or sequence.

[0065] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0066] The host computer disclosed herein can be an industrial control computer, which includes: a real-time processing module, a time synchronization module, a video dark box, a CAN communication module, and a power supply module; the real-time processing module, the time synchronization module, and the video dark box are connected to each other via the CAN communication module; the real-time processing module is used to obtain CAN data based on historical road data; the video dark box is used to obtain video data based on historical road data; the time synchronization module is used to synchronize the CAN data and video data; and the power supply module provides power to the real-time processing module, the time synchronization module, and the video dark box.

[0067] The host computer disclosed herein only needs to perform one real-vehicle road test to acquire road data. The target dataset obtained from the road data is then sent to different vehicle controllers. The host computer verifies the accuracy of the second driving warning information generated by the vehicle controllers based on the target dataset using the first driving warning information generated by the host computer based on the target dataset. Verification of different vehicle controllers can be achieved based on the driving warning information, eliminating the need for repeated real-vehicle road tests to obtain new road information when verifying different vehicle controllers, thus reducing verification costs and time. This disclosure does not require a specific camera assembly during the road data acquisition process; the accuracy of the warning information generated by the vehicle controllers can be verified regardless of whether the camera assembly can output target data. During the verification process, the host computer can schedule multiple recognition and fusion algorithms, and can verify the accuracy of the warning information generated by the vehicle controllers based on the first driving warning information obtained through multiple recognition and fusion algorithms, improving the reliability and accuracy of the verification results.

[0068] Example 1

[0069] Figure 1This is a flowchart illustrating a controller verification method according to an exemplary embodiment. Figure 1 As shown, taking the application of this method to a host computer as an example, the method includes the following steps.

[0070] In step S101, the host computer acquires road data, which includes historically collected road information.

[0071] In step S102, the host computer preprocesses the road data to obtain the target dataset, and sends the target dataset to the vehicle controller so that the vehicle controller can generate a second driving warning information based on the target dataset.

[0072] In step S103, the host computer generates the first driving warning information based on the target dataset.

[0073] In step S104, the host computer verifies the accuracy of the second driving warning information generated by the vehicle controller based on the first driving warning information.

[0074] Specifically, road data can include road information obtained from extensive real-vehicle road testing during the vehicle development phase. The host computer obtains road data by reading the road information stored in a specified storage path.

[0075] Among them, the first driver warning information is the alarm result generated by the host computer based on the target dataset.

[0076] Specifically, when the host computer acquires road data, it performs time matching with the timeline when reading each frame of data to ensure the time synchronization of the road data.

[0077] Optionally, if the road data includes CAN data and video data, in step S102, the host computer preprocesses the road data to obtain the target dataset, which may include the following steps:

[0078] In step S1021, the host computer performs format verification on the CAN data and video data respectively;

[0079] In step S1022, if the CAN data and video data formats pass the verification, the host computer performs synchronous processing on the CAN data and video data to obtain the target dataset.

[0080] Specifically, road data can include CAN data and video data. CAN data can include vehicle CAN data and millimeter-wave radar CAN data, while video data can include video data collected by cameras on the vehicle.

[0081] The CAN data contains the speed and acceleration of people and objects relative to the vehicle during the actual vehicle road test, while the video data also contains the speed and acceleration of people (pedestrians), objects (other vehicles, road signs, and other objects involved in the vehicle's driving process) relative to the vehicle during the actual vehicle road test.

[0082] For example, when road data includes CAN data and video data, the host computer verifies the CAN data and video data in the road data according to the format of the CAN data and the format of the video data; then, it performs synchronous processing on the CAN data and video data to obtain the target dataset.

[0083] Because existing camera assemblies can output target data and those cannot, different methods are required to synchronize CAN data and video data based on different types of camera assemblies.

[0084] When the camera assembly is able to output target data, the video data is processed through a video darkroom to obtain the target data.

[0085] Because the processing time for video data is longer than that for CAN data, the video data and CAN data cannot be synchronized in time. Therefore, it is necessary to synchronize the CAN data and video data.

[0086] Optionally, if the timestamps of the CAN data and the video data are consistent, step S1022, which involves synchronizing the CAN data and the video data, may include:

[0087] By using a video darkroom to replay video data based on timestamps, the first target data in the video data is obtained. The first target data includes the speed and acceleration of the person or object carried in the video data relative to the vehicle.

[0088] The CAN data is replayed using the CAN card according to the timestamp to obtain the second target data in the CAN data. The second target data includes the speed and acceleration of the person or object carried in the CAN data relative to the vehicle.

[0089] The target dataset is obtained based on the first target data and the second target data.

[0090] The timestamp can be adjusted according to the user's verification needs, and this disclosure does not impose specific limitations on it.

[0091] Specifically, CAN data and video data are played back using the same timestamp. During the playback process, the CAN data is played back with a necessary delay to ensure the time synchronization of CAN data and video data.

[0092] For example, such as Figure 2 As shown, the host computer's data reading software reads the vehicle CAN data, millimeter-wave radar CAN data, and video data, and performs format verification on the obtained vehicle CAN data, millimeter-wave radar CAN data, and video data respectively; if the format verification of the vehicle CAN data, millimeter-wave radar CAN data, and video data passes, the host computer realizes the synchronization of the vehicle CAN data, millimeter-wave radar CAN data, and video data through data playback.

[0093] The playback process consists of two parts: video data and CAN data playback based on the same timestamp. The first part is video data playback: the display in the video darkroom plays and displays the video data according to the timestamp, and the camera in the video darkroom captures and identifies the video played on the display. The speed and acceleration of people and objects relative to the vehicle in the identified video data are used as the first target data. The second part is CAN data playback: the CAN card plays back the vehicle CAN data and millimeter-wave radar CAN data according to the timestamp, and the speed and acceleration of people and objects relative to the vehicle carried in the vehicle CAN data and millimeter-wave radar CAN data are used as the second target data.

[0094] The target dataset is obtained based on the first target data and the second target data. After obtaining the target dataset, the host computer sends the target dataset to the ECU (Electronic Control Unit) controller to be verified and receives the processing result of the ECU controller based on the target dataset.

[0095] When the camera assembly is capable of outputting target data, the video data is played back using a video darkroom, such as... Figure 3 As shown, the host computer sends the video data to be played back to the video dark box via HDMI (High Definition Multimedia Interface). The video dark box obtains the first target data (the speed and acceleration of people and objects relative to the vehicle carried in the video data) based on the video data, and sends the first target data to the host computer and the ECU controller respectively via the CAN cable. The host computer sends the CAN data to the CAN card via USB. The CAN card obtains the second target data (the speed and acceleration of people and objects relative to the vehicle carried in the millimeter radar wave and vehicle signal) based on the CAN data, and sends the second target data to the ECU controller via the CAN cable. The host computer also receives the second driving warning information generated by the ECU controller based on the first and second target data via the CAN cable.

[0096] If the camera assembly cannot output target data, the host computer calls the recognition algorithm to process the video data and obtain the target data.

[0097] Optionally, if the timestamps of the CAN data and the video data are consistent, step S1022, which involves synchronizing the CAN data and the video data, may include:

[0098] Based on the user's operation instructions, a target recognition algorithm is determined from multiple recognition algorithms. The target recognition algorithm processes the video data according to the timestamp to obtain third target data in the video data. The third target data includes the speed and acceleration of the people and objects carried in the video data relative to the vehicle.

[0099] The CAN data is replayed using the CAN card according to the timestamp to obtain the fourth target data in the CAN data. The fourth target data includes the speed and acceleration of the person or object carried in the CAN data relative to the vehicle.

[0100] The target dataset is obtained based on the third target data and the fourth target data.

[0101] The timestamp can be adjusted according to the user's verification needs, and the multiple recognition algorithms are existing recognition algorithms, which are not specifically limited in this disclosure.

[0102] For example, such as Figure 4 As shown, the host computer's data reading software reads the vehicle CAN data, millimeter-wave radar CAN data, and video data, and performs format verification on the obtained vehicle CAN data, millimeter-wave radar CAN data, and video data respectively; if the format verification of the vehicle CAN data, millimeter-wave radar CAN data, and video data passes, the host computer realizes the synchronization of the vehicle CAN data, millimeter-wave radar CAN data, and video data through data playback.

[0103] The playback process consists of two parts: video data and CAN data playback based on the same timestamp. The first part is video data playback: the host computer determines the target recognition algorithm from multiple recognition algorithms according to the user's operation instructions, calls the target recognition algorithm to recognize the video data according to the timestamp, and uses the speed and acceleration of people and objects relative to the vehicle in the video data identified by the target recognition algorithm as the third target data. The second part is CAN data playback: the CAN card plays back the vehicle CAN data and millimeter-wave radar CAN data according to the timestamp, and obtains the speed and acceleration of people and objects relative to the vehicle carried in the vehicle CAN data and millimeter-wave radar CAN data as the fourth target data.

[0104] The target dataset is obtained based on the third and fourth target data. After obtaining the target dataset, the host computer sends the target dataset to the ECU controller to be verified and receives the processing result of the ECU controller based on the target dataset.

[0105] When the camera assembly fails to output target data, the host computer processes the video data by calling a recognition algorithm. Figure 5 .like Figure 5 As shown, the host computer calls the recognition algorithm to obtain third target data (the speed and acceleration of people and objects carried in the video data relative to the vehicle) based on the video data, and sends the third target data to the ECU controller via the CAN line. The host computer sends the CAN data to the CAN card via USB. The CAN card obtains fourth target data (the speed and acceleration of people and objects carried in the millimeter radar waves and vehicle signals relative to the vehicle) based on the CAN data, and sends the fourth target data to the ECU controller via the CAN line. The host computer also receives the second driving warning information generated by the ECU controller based on the third and fourth target data via the CAN line.

[0106] The host computer can schedule multiple recognition algorithms. For each recognition algorithm, corresponding driving warning information can be obtained. The accuracy of the driving warning information generated by the vehicle controller can be verified based on multiple driving warning information, thereby improving the accuracy and reliability of the verification results.

[0107] Optionally, there can be one or more recognition algorithms. When there are multiple recognition algorithms, processing the video data based on timestamps using the target recognition algorithm to obtain third target data from the video data may include:

[0108] For each recognition algorithm, the video data is processed based on the timestamp to obtain the third target data in the video data;

[0109] Accordingly, the target dataset obtained based on the third and fourth target data may include:

[0110] For each third target data point, the target dataset is obtained based on the third target data and the fourth target data.

[0111] The first driving warning information generated based on the target dataset may also include:

[0112] A first driving warning message is generated for each target dataset to obtain multiple first driving warning messages.

[0113] For example, the host computer calls recognition algorithm A to obtain the third target data corresponding to recognition algorithm A, calls recognition algorithm B to obtain the third target data corresponding to recognition algorithm B, calls recognition algorithm C to obtain the third target data corresponding to recognition algorithm C, and calls recognition algorithm D to obtain the third target data corresponding to recognition algorithm D. Then, based on the four third target data, four first driving warning messages are obtained. Based on these four first driving warning messages, the accuracy of the vehicle controller in generating second driving warning messages is verified, thereby improving the accuracy and reliability of the verification results.

[0114] The host computer calls the fusion algorithm to process the target dataset to obtain driving warning information, thereby verifying the accuracy of the driving warning information generated by the vehicle controller.

[0115] Optionally, in step S103, generating the first driving warning information based on the target dataset may include:

[0116] Based on the user's operation instructions, a target fusion algorithm is determined from multiple fusion algorithms, and the target dataset is processed by the target fusion algorithm to obtain the first driving warning information.

[0117] Many of the fusion algorithms are existing fusion algorithms, and this disclosure does not impose any specific limitations on them.

[0118] Users can determine the fusion algorithm according to the verification needs and operate the host computer. The host computer determines the target fusion algorithm from multiple fusion algorithms according to the operation instructions used.

[0119] For example, when a user clicks on the A fusion algorithm on the touch screen of the host computer, the host computer determines the A fusion algorithm as the target fusion algorithm based on the user's click. At this time, the host computer calls the A fusion algorithm to process the target dataset to obtain the first driving warning information.

[0120] The host computer can schedule multiple fusion algorithms. For each fusion algorithm, corresponding driving warning information can be obtained. The accuracy of the driving warning information generated by the vehicle controller can be verified based on multiple driving warning information, thereby improving the accuracy and reliability of the verification results.

[0121] Optionally, one or more fusion algorithms may be used. When multiple fusion algorithms are used, the target dataset is processed by the target fusion algorithm to obtain the first driving warning information, including:

[0122] For each fusion algorithm, the target dataset is processed by the fusion algorithm to obtain first driving warning information, so as to obtain multiple first driving warning information.

[0123] For example, the host computer calls the A fusion algorithm to process the target data set to obtain a first driving warning message, calls the B fusion algorithm to process the target data set to obtain a first driving warning message, calls the C fusion algorithm to process the target data set to obtain a first driving warning message, calls the D fusion algorithm to process the target data set to obtain a first driving warning message, and then verifies the accuracy rate of the vehicle controller to generate the second driving warning message based on these four first driving warning messages, which improves the accuracy and reliability of the verification result.

[0124] Optionally, in step S104, verifying the accuracy rate of the vehicle controller to generate the second driving warning message based on the first driving warning message may include:

[0125] Based on the first driving warning message and the second driving warning message, obtain the abnormal warning message of the vehicle controller, and the abnormal warning message includes the false alarm rate and / or the missed alarm rate;

[0126] Verify the vehicle controller according to the abnormal warning message.

[0127] Among them, for the controller of functions such as AEB (Autonomous Emergency Braking), the output result is compared and analyzed with the first driving warning output by the host computer calling the fusion algorithm. For the controller of functions such as LDW (Lane Departure Warning) and FCW (Forward Collision Warning), the output result is compared and analyzed with the output target data of the host computer calling the recognition algorithm.

[0128] For example, the host computer obtains the false alarm rate and / or the missed alarm rate of the vehicle controller according to the first driving warning message and the second driving warning message sent by the vehicle controller, generates a test report according to the false alarm rate and / or the missed alarm rate, and analyzes the false alarm rate and / or the missed alarm rate of the vehicle controller according to the test. The lower the false alarm rate and / or the missed alarm rate, the better the performance of the vehicle controller. On the contrary, the performance of the vehicle controller is worse.

[0129] Or compare the false alarm rate of the vehicle controller with the false alarm rate threshold, and compare the missed alarm rate of the vehicle controller with the missed alarm rate threshold. When the false alarm rate is less than the false alarm rate threshold and the missed alarm rate is less than the missed alarm rate threshold, or the false alarm rate is less than the false alarm rate threshold, or the missed alarm rate is less than the missed alarm rate threshold, the vehicle controller is qualified. Among them, the false alarm rate threshold and the missed alarm rate threshold are preset according to the user's requirements for the vehicle controller, and the present disclosure does not make specific limitations on this.

[0130] Embodiment 2

[0131] Figure 1 This is a flowchart illustrating a controller verification method according to an exemplary embodiment. Figure 1 As shown, taking the application of this method to a vehicle controller as an example, the method includes the following steps.

[0132] In step S201, the vehicle controller receives the target dataset sent by the host computer. The target dataset is obtained by the host computer preprocessing historically collected road information.

[0133] In step S202, the vehicle controller obtains the second driving warning information based on the target dataset and sends the second driving warning information to the host computer so that the host computer can obtain the false alarm rate and false alarm rate of the vehicle controller based on the second driving warning information.

[0134] The second driving warning information is an alarm result generated by the controller based on the target dataset. The vehicle controller can be a controller that needs to be verified, such as the AEB controller, LDW controller, FCW controller, etc. on the vehicle.

[0135] Specifically, the method by which the vehicle controller receives the target dataset sent by the host computer, and the specific process by which the vehicle controller sends the second driving warning information to the host computer so that the host computer can obtain the false alarm rate and false alarm rate of the vehicle controller based on the second driving warning information, have been described in detail in the embodiments of the controller verification method applied to the host computer, and will not be elaborated here.

[0136] Example 3

[0137] Figure 6 This is a block diagram illustrating a controller verification device according to an exemplary embodiment. Figure 6 As shown, the controller verification device 300 is applied to a host computer and includes: a reading module 301, a first execution module 302, a second execution module 303, and a verification module 304.

[0138] The reading module 301 is configured to acquire road data, which includes historically collected road information.

[0139] The first execution module 302 is configured to preprocess road data to obtain a target dataset, and send the target dataset to the vehicle controller so that the vehicle controller can generate a second driving warning information based on the target dataset.

[0140] The second execution module 303 is configured to generate first driving warning information based on the target dataset.

[0141] The verification module 304 is configured to verify the accuracy of the second driving warning information generated by the vehicle controller based on the first driving warning information.

[0142] Optionally, when the road data includes CAN data and video data, the first execution module 302 is configured to perform format verification on the CAN data and video data respectively;

[0143] If the CAN data and video data formats pass verification, the CAN data and video data are synchronized to obtain the target dataset.

[0144] Optionally, the first execution module 302 is configured to perform playback processing on video data according to timestamps through a video dark box to obtain first target data in the video data. The first target data includes the speed and acceleration of the person or object carried in the video data relative to the vehicle.

[0145] The CAN data is replayed using the CAN card according to the timestamp to obtain the second target data in the CAN data. The second target data includes the speed and acceleration of the person or object carried in the CAN data relative to the vehicle.

[0146] The target dataset is obtained based on the first target data and the second target data.

[0147] Optionally, the first execution module 302 is configured to determine a target recognition algorithm from multiple recognition algorithms according to the user's operation instructions when the timestamps of the CAN data and the video data are consistent, and to process the video data according to the timestamps using the target recognition algorithm to obtain third target data in the video data. The third target data includes the speed and acceleration of the person or object carried in the video data relative to the vehicle.

[0148] The CAN data is replayed using the CAN card according to the timestamp to obtain the fourth target data in the CAN data. The fourth target data includes the speed and acceleration of the person or object carried in the CAN data relative to the vehicle.

[0149] The target dataset is obtained based on the third target data and the fourth target data.

[0150] Optionally, when there are multiple recognition algorithms, the first execution module 302 is configured to process the video data according to the timestamp for each recognition algorithm to obtain the third target data in the video data;

[0151] For each third target data point, the target dataset is obtained based on the third target data and the fourth target data.

[0152] At this time, the second execution module 303 is configured to generate a first driving warning message based on each target dataset, so as to obtain multiple first driving warning messages.

[0153] Optionally, the second execution module 303 is configured to determine a target fusion algorithm from multiple fusion algorithms based on the user's operation instructions, and process the target dataset through the target fusion algorithm to obtain the first driving warning information.

[0154] Optionally, when there are multiple fusion algorithms, the second execution module 303 is configured to process the target dataset through the fusion algorithm to obtain first driving warning information for each fusion algorithm, so as to obtain multiple first driving warning information.

[0155] Optionally, the verification module 304 is configured to obtain abnormal warning information of the vehicle controller based on the first driving warning information and the second driving warning information, the abnormal warning information including false alarm rate and / or false alarm rate;

[0156] Verification of the vehicle controller based on abnormal warning information.

[0157] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in Embodiment 1 of the method, and will not be elaborated upon here.

[0158] Example 4

[0159] Figure 7 This is a block diagram illustrating another controller verification device according to an exemplary embodiment. Figure 7 As shown, the controller verification device 400 is applied to a vehicle controller and includes a receiving module 401 and a transmitting module 402.

[0160] The receiving module 401 is configured to receive a target dataset sent by a host computer. The target dataset is obtained by the host computer through preprocessing historically collected road information.

[0161] The sending module 402 is configured to obtain second driving warning information based on the target dataset and feed the second driving warning information back to the host computer, so that the host computer can obtain the false alarm rate and false alarm rate of the vehicle controller based on the second driving warning information.

[0162] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in Embodiment 2 of the method, and will not be elaborated upon here.

[0163] Example 5

[0164] This disclosure also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of the controller verification method for a host computer provided in this disclosure.

[0165] Specifically, the computer-readable storage medium can be flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, server, etc.

[0166] Regarding the computer-readable storage medium in the above embodiments, the steps of the controller verification method applied to the host computer, implemented when the computer program stored thereon is executed, have been described in detail in Embodiment 1 of the method, and will not be elaborated here.

[0167] Example 6

[0168] This disclosure also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of the controller verification method for a vehicle controller provided in this disclosure.

[0169] Specifically, the computer-readable storage medium can be flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, server, etc.

[0170] Regarding the computer-readable storage medium in the above embodiments, the steps of the controller verification method applied to the vehicle controller, implemented when the computer program stored thereon is executed, have been described in detail in Embodiment 2 of the method, and will not be elaborated here.

[0171] Example 7

[0172] This disclosure also provides an electronic device, the electronic device comprising:

[0173] A memory on which computer programs are stored;

[0174] A processor is used to execute a computer program in memory to implement the steps of the controller verification method applied to the host computer described above.

[0175] Figure 8This is a block diagram illustrating an electronic device 500 according to an exemplary embodiment. For example... Figure 8 As shown, the electronic device 500 may include a processor 501 and a memory 502. The electronic device 500 may also include one or more of a multimedia component 503, an input / output (I / O) interface 504, and a communication component 505.

[0176] The processor 501 is used to control the overall operation of the electronic device 500 to complete all or part of the steps in the controller verification method applied to the host computer described above.

[0177] Memory 502 is used to store various types of data to support the operation of the electronic device 500. This data may include, for example, instructions for any application or method operating on the electronic device 500, and application-related data such as CAN data, video data, first-drive warning information, target datasets, etc. Memory 502 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0178] Multimedia component 503 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 502 or transmitted via communication component 505. The audio component also includes at least one speaker for outputting audio signals.

[0179] I / O interface 504 provides an interface between processor 501 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical buttons.

[0180] Communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. Wireless communication includes, for example, Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, or 5G, NB-IoT (Narrow Band Internet of Things), or one or more combinations thereof. Therefore, the corresponding communication component 505 may include: a Wi-Fi module, a Bluetooth module, and an NFC module. Wired communication includes, for example, CAN, USB, HDMI, etc.

[0181] In an exemplary embodiment, the electronic device 500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the controller verification method applied to the host computer described above.

[0182] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the above-described controller verification method applied to a host computer when executed by the programmable device.

[0183] Example 8

[0184] This disclosure also provides an electronic device, the electronic device comprising:

[0185] A memory on which computer programs are stored;

[0186] A processor is used to execute a computer program in memory to implement the steps of the controller verification method applied to a vehicle controller described above.

[0187] Figure 9 This is a block diagram illustrating an electronic device 700 according to an exemplary embodiment. Figure 9As shown, the electronic device 700 may include a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0188] The processor 701 controls the overall operation of the electronic device 700 to complete all or part of the steps in the controller verification method applied to the vehicle controller described above. The memory 702 stores various types of data to support the operation of the electronic device 700. This data may include, for example, instructions for any application or method operating on the electronic device 700, and application-related data, such as target datasets, second driving warning information, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0189] Multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 702 or transmitted via communication component 705. The audio component also includes at least one speaker for outputting audio signals.

[0190] I / O interface 704 provides an interface between processor 701 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, or 5G, NB-IoT (Narrow Band Internet of Things), or one or more combinations thereof. Therefore, the corresponding communication component 705 may include: a Wi-Fi module, a Bluetooth module, and an NFC module. Wired communication includes CAN, USB, HDMI, etc.

[0191] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the controller verification method applied to the vehicle controller described above.

[0192] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the controller verification method applied to a vehicle controller described above. For example, the computer-readable storage medium may be the memory 702 including the program instructions described above, which may be executed by the processor 701 of the electronic device 700 to complete the controller verification method applied to a vehicle controller described above.

[0193] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the controller verification method applied to a vehicle controller as described above when executed by the programmable device.

[0194] The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0195] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0196] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A controller verification method characterized by, The method is applied to an upper computer, and comprises: obtaining road data, wherein the road data comprises historical collected road information; preprocessing the road data to obtain a target data set, sending the target data set to a vehicle controller, and generating second driving warning information based on the target data set by the vehicle controller; and generating first driving warning information according to the target data set; verifying the accuracy of the second driving warning information generated by the vehicle controller according to the first driving warning information; the road data comprises CAN data and video data, and the preprocessing of the road data to obtain a target data set comprises: respectively checking the formats of the CAN data and the video data; in the case that the format checking of the CAN data and the video data is passed, synchronously processing the CAN data and the video data to obtain a target data set; the timestamps of the CAN data and the video data are consistent, and the synchronous processing of the CAN data and the video data comprises: playing back the video data according to the timestamps by a video dark box to obtain first target data in the video data, wherein the first target data comprises the speed and acceleration of a person or object carried by the video data relative to a vehicle; playing back the CAN data according to the timestamps by a CAN card to obtain second target data in the CAN data, wherein the second target data comprises the speed and acceleration of a person or object carried by the CAN data relative to the vehicle; obtaining a target data set according to the first target data and the second target data.

2. The method of claim 1, wherein, the verification of the accuracy of the second driving warning information generated by the vehicle controller according to the first driving warning information comprises: obtaining abnormal warning information of the vehicle controller according to the first driving warning information and the second driving warning information, wherein the abnormal warning information comprises a false positive rate and / or a false negative rate; verifying the vehicle controller according to the abnormal warning information.

3. The method of claim 1, wherein, the timestamps of the CAN data and the video data are consistent, and the synchronous processing of the CAN data and the video data further comprises: determining a target recognition algorithm from a plurality of recognition algorithms according to an operation instruction of a user, processing the video data according to the timestamps by the target recognition algorithm to obtain third target data in the video data, wherein the third target data comprises the speed and acceleration of a person or object carried by the video data relative to the vehicle; playing back the CAN data according to the timestamps by a CAN card to obtain fourth target data in the CAN data, wherein the fourth target data comprises the speed and acceleration of a person or object carried by the CAN data relative to the vehicle; obtaining a target data set according to the third target data and the fourth target data.

4. The method of claim 1, wherein, the generation of the first driving warning information according to the target data set comprises: A target fusion algorithm is determined from a plurality of fusion algorithms according to an operation instruction of a user, and a first driving early warning information is obtained by processing the target data set through the target fusion algorithm.

5. A controller verification method characterized by, The method is applied to a vehicle controller, and the method comprises: receiving a target data set sent by a host computer, the target data set being obtained by preprocessing historical collected road information by the host computer; obtaining a second driving early warning information according to the target data set, and feeding back the second driving early warning information to the host computer, so that the host computer obtains a false alarm rate and a missed alarm rate of the vehicle controller according to the second driving early warning information.

6. A controller verification apparatus characterized by comprising: The device is applied to a host computer, and the device comprises: a reading module configured to acquire road data, wherein the road data comprises historical collected road information; a first execution module configured to preprocess the road data to obtain a target data set, and send the target data set to a vehicle controller, so that the vehicle controller generates a second driving early warning information based on the target data set; a second execution module configured to generate a first driving early warning information according to the target data set; a verification module configured to verify an accuracy of the second driving early warning information generated by the vehicle controller according to the first driving early warning information; the road data comprises CAN data and video data, the first execution module is further configured to respectively perform format checking on the CAN data and the video data, perform synchronous processing on the CAN data and the video data to obtain a target data set in a case where the format checking on the CAN data and the video data is passed, the time stamp of the CAN data is consistent with the time stamp of the video data, the video data is played back according to the time stamp by a video dark box to acquire first target data in the video data, the first target data comprises speed and acceleration of a person or object carried in the video data relative to a vehicle, the CAN data is played back according to the time stamp by a CAN card to acquire second target data in the CAN data, the second target data comprises speed and acceleration of a person or object carried in the CAN data relative to the vehicle, and the target data set is obtained according to the first target data and the second target data.

7. A controller verification apparatus characterized by comprising: The device is applied to a vehicle controller, and the device comprises: a receiving module configured to receive a target data set sent by a host computer, the target data set being obtained by preprocessing historical collected road information by the host computer; a sending module configured to obtain a second driving early warning information according to the target data set, and feed back the second driving early warning information to the host computer, so that the host computer obtains a false alarm rate and a missed alarm rate of the vehicle controller according to the second driving early warning information.

8. A computer-readable storage medium, characterized in that, A computer program is stored on the computer, and when the computer program is executed by a processor, the steps of the controller verification method in any one of claims 1-4 or the steps of the controller verification method in claim 5 are implemented.

9. An electronic device, comprising: The electronic device comprises: a memory having stored thereon a computer program; a processor configured to execute the computer program in the memory to implement the steps of the controller verification method of any one of claims 1-4 or the steps of the controller verification method of claim 5.

Images