Intelligent driving backfill data verification method and device and storage medium

Abstract

The application provides a kind of intelligent driving backfill data verification method, device and storage medium.It includes: receiving first sensor configuration parameter and sensor acquisition data, generating first configuration file, receiving second configuration file, second configuration file is configured with test and the second sensor configuration parameter required by each algorithm in algorithm verification device is verified algorithm, first configuration file is checked by second configuration file, and the first sensor configuration parameter that passes verification is obtained, the sensor acquisition data corresponding to the first sensor configuration parameter that passes verification is obtained, and is issued to algorithm verification device and is tested and verified.Before data backfill, sensor configuration parameter is verified, and then the backfill data corresponding to the sensor required by algorithm in algorithm verification device is obtained, to achieve the effect of accurate matching, solve the problem that existing technology is difficult to match the data required by algorithm verification device due to numerous acquisition data when intelligent driving acquisition data is backfilled.

Description

Technical Field

[0001] This application relates to the technical field of intelligent driving data verification, and more specifically, to a method, apparatus, storage medium, and electronic device for intelligent driving data verification. Background Technology

[0002] Because intelligent driving vehicles have a wide variety of sensors and collect diverse data, the data collected varies greatly depending on the scenario. For example, the sensor configurations and arrangements differ for certain forward collision scenarios and automatic parking scenarios.

[0003] Existing technologies have a problem when collecting data for intelligent driving and then feeding it back in: the large amount of data collected makes it difficult to match the data that the algorithm verification equipment needs to verify. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, storage medium, and electronic device for verifying intelligent driving data re-feedback, so as to at least solve the problem in the prior art where the large amount of collected data makes it difficult to match with the data required for verification by the algorithm verification device during intelligent driving data re-feedback.

[0005] To achieve the above objectives, according to one aspect of this application, a method for verifying intelligent driving data recharge is provided. The method is applied to a cloud platform in a data recharge verification system. The data recharge verification system further includes a first data acquisition device and a vehicle-side sensor belonging to the acquisition scenario, and a second data acquisition device and an algorithm verification device belonging to the verification scenario. The first data acquisition device communicates with the vehicle-side sensor and the cloud platform, respectively, and the second data acquisition device communicates with the algorithm verification device and the cloud platform, respectively. The method includes: receiving first sensor configuration parameters and sensor acquisition data of the vehicle-side sensor uploaded by the first data acquisition device, and generating a first configuration file characterizing the first sensor configuration parameters. The first sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identifier. The system receives a second configuration file uploaded by the second data acquisition device. This configuration file contains second sensor configuration parameters required for testing and verifying each algorithm in the algorithm verification device. These parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification. The system then verifies the first configuration file using the second configuration file to obtain verified first sensor configuration parameters. It also acquires the sensor acquisition data corresponding to the verified first sensor configuration parameters, obtaining verified sensor acquisition data. Finally, the system sends the verified sensor acquisition data to the second data acquisition device, which then sends it to the algorithm verification device to test and verify the algorithms within the algorithm verification device.

[0006] Optionally, the first configuration file is verified using the second configuration file, including: verifying whether the sensor type and sensor identifier in the first configuration file include the sensor type and sensor identifier in the second configuration file; if the sensor type and sensor identifier in the first configuration file include the sensor type and sensor identifier in the second configuration file, verifying whether the sensor installation position in the first configuration file matches the sensor installation position in the second configuration file, and verifying whether the sensor accuracy in the first configuration file matches the sensor accuracy in the second configuration file, wherein the sensor installation position is determined by the sensor installation height, the sensor installation angle, and the sensor installation distance, and the sensor accuracy includes installation height accuracy, installation angle accuracy, and installation distance accuracy.

[0007] Optionally, the first configuration file further includes a first reserved field, which is an invalid field, and the second configuration file further includes a second reserved field. Verifying whether the sensor accuracy in the first configuration file matches the sensor accuracy in the second configuration file includes: determining whether to verify the installation height accuracy, the installation angle accuracy, and the installation distance accuracy based on the second reserved field of the second configuration file, wherein the second reserved field is a verification identifier indicating that the corresponding item needs to be verified, and the second reserved field is a non-verification identifier indicating that the corresponding item does not need to be verified; and performing sensor accuracy matching for one or more of the installation height accuracy, the installation angle accuracy, and the installation distance accuracy that need to be verified.

[0008] Optionally, verifying whether the sensor accuracy in the first configuration file matches the sensor accuracy in the second configuration file includes: verifying whether the installation height of the sensor in the second configuration file is within a first height range using a first accuracy criterion, wherein the upper limit of the first height range is the sum of the installation height of the sensor in the first configuration file and the sensor height accuracy, and the lower limit of the first height range is the difference between the installation height of the sensor in the first configuration file and the sensor height accuracy; if it is determined that the installation height of the sensor in the second configuration file is within the first height range, verifying whether the second height range intersects with the first height range using a second accuracy criterion, wherein the upper limit of the second height range is the sum of the installation height of the sensor in the second configuration file and the sensor height accuracy, and the lower limit of the second height range is the difference between the installation height of the sensor in the second configuration file and the sensor height accuracy; if it is determined that the second height range intersects with the first height range, determining that the installation height accuracy verification in the first configuration file is passed.

[0009] Optionally, the method further includes: after determining that the installation height accuracy in the first configuration file has passed verification, verifying other items that need to be verified, including installation angle accuracy and / or installation distance accuracy; and if the other items have also passed verification, obtaining the verified first sensor configuration parameters.

[0010] Optionally, the method further includes: real-time monitoring of the sensor installation position of the vehicle-side sensor; and generating alarm information when the sensor installation position of the vehicle-side sensor changes.

[0011] Optionally, there are multiple data collection scenarios, multiple first configuration files, and each data collection scenario corresponds one-to-one with the first configuration file. There are also multiple verification scenarios, multiple second configuration files, and each verification scenario corresponds one-to-one with the second configuration file.

[0012] According to another aspect of this application, an apparatus for verifying intelligent driving data recharge is provided. The apparatus is applied to a cloud platform in a data recharge verification system. The data recharge verification system further includes a first data acquisition device and a vehicle-side sensor belonging to the acquisition scenario, and a second data acquisition device and an algorithm verification device belonging to the verification scenario. The first data acquisition device communicates with both the vehicle-side sensor and the cloud platform, and the second data acquisition device communicates with both the algorithm verification device and the cloud platform. The apparatus includes: a first receiving unit, configured to receive first sensor configuration parameters and sensor acquisition data uploaded by the first data acquisition device from the vehicle-side sensor, and generate a first configuration file characterizing the first sensor configuration parameters, wherein the first sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identifier; and a second receiving unit, configured to receive... The second data acquisition device uploads a second configuration file, which contains second sensor configuration parameters required for testing and verifying each algorithm in the algorithm verification device. These second sensor configuration parameters include the number of sensors, sensor types, sensor installation locations, sensor accuracy, and sensor identification. A verification unit is used to verify the first configuration file using the second configuration file to obtain the verified first sensor configuration parameters, and to acquire the sensor acquisition data corresponding to the verified first sensor configuration parameters, thus obtaining the verified sensor acquisition data. A testing unit is used to send the verified sensor acquisition data to the second data acquisition device, so that the second data acquisition device can send the verified sensor acquisition data to the algorithm verification device for testing and verification of the algorithms in the algorithm verification device.

[0013] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform any of the intelligent driving data reinjection verification methods.

[0014] According to another aspect of this application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a method for performing any of the intelligent driving data backfeed verification methods.

[0015] Applying the technical solution of this application, the system receives first sensor configuration parameters and sensor acquisition data from vehicle-side sensors uploaded by a first data acquisition device, and generates a first configuration file characterizing the first sensor configuration parameters, wherein the first sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification; it then receives a second configuration file uploaded by a second data acquisition device, which contains second sensor configuration parameters required for testing and verifying each algorithm in the algorithm verification device, wherein the second sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification; the first configuration file is verified using the second configuration file to obtain verified first sensor configuration parameters, and sensor acquisition data corresponding to the verified first sensor configuration parameters is acquired to obtain verified sensor acquisition data; the verified sensor acquisition data is then sent to the second data acquisition device, which in turn sends the verified sensor acquisition data to the algorithm verification device for testing and verification of the algorithms in the algorithm verification device. Before data refeedback, the sensor configuration parameters are verified, thereby obtaining the refeedback data corresponding to the sensors required by the algorithm in the algorithm verification device, achieving a precise matching effect. This solves the problem in existing technologies where, during the refeedback of intelligent driving data, it is difficult to match the large amount of collected data with the data required for verification by the algorithm verification device. Attached Figure Description

[0016] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a mobile terminal for performing a method for verifying intelligent driving data reinjection according to an embodiment of this application is shown.

[0018] Figure 2 A flowchart illustrating a method for verifying intelligent driving data reinjection according to an embodiment of this application is shown.

[0019] Figure 3 A top view of a vehicle outline provided according to an embodiment of this application is shown;

[0020] Figure 4 A schematic diagram of the process for determining the accuracy verification of sensor mounting height according to an embodiment of this application is shown;

[0021] Figure 5 A schematic diagram illustrating a specific method for verifying intelligent driving data reinjection according to an embodiment of this application is shown;

[0022] Figure 6 A structural block diagram of an apparatus for verifying intelligent driving data reinjection according to an embodiment of this application is shown. Detailed Implementation

[0023] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0024] 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 with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application:

[0027] Re-injection: The data collected by the intelligent driving system (also known as re-injection data) is re-injected into the algorithm device for algorithm testing and verification.

[0028] Algorithm verification equipment: such as industrial control computers or domain controllers that execute intelligent driving algorithms.

[0029] As described in the background section, existing technologies have a problem with matching the large amount of collected data with the data required for verification by the algorithm verification device during the data re-feedback process of intelligent driving. To solve this problem, embodiments of this application provide a method, apparatus, storage medium, and electronic device for verifying intelligent driving data re-feedback.

[0030] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0031] The methods and embodiments provided in this application can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of verifying intelligent driving data refeedback according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0032] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the intelligent driving data verification method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0033] This embodiment provides a method for verifying intelligent driving data backflow that runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0034] Figure 2 This is a flowchart of a method for verifying intelligent driving data recharge according to an embodiment of this application. The method is applied to a cloud platform in a data recharge verification system. The data recharge verification system also includes a first data acquisition device and vehicle-side sensors belonging to the acquisition scenario, and a second data acquisition device and algorithm verification device belonging to the verification scenario. The first data acquisition device communicates with both the vehicle-side sensors and the cloud platform, and the second data acquisition device communicates with both the algorithm verification device and the cloud platform. Figure 2 As shown, the method includes the following steps:

[0035] Step S201: Receive the first sensor configuration parameters and sensor acquisition data of the vehicle-side sensor uploaded by the first data acquisition device, and generate a first configuration file characterizing the first sensor configuration parameters, wherein the first sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification.

[0036] The types of sensors include cameras and LiDAR, and the sensor installation locations include sensor height, sensor angle, and sensor distance, such as... Figure 3 As shown, the distance to sensor A is the line connecting sensor A to the origin of the vehicle center, denoted as d; the angle of sensor A is the angle between the sensor distance and the Y-axis, denoted as θ; the sensor height is the height of the sensor from the ground; and the sensor accuracy includes sensor height accuracy, sensor angle accuracy, and sensor distance accuracy.

[0037] For example, an 8M camera, where 8M indicates the sensor camera's identifier.

[0038] Step S202: Receive the second configuration file uploaded by the second data acquisition device. The second configuration file contains the second sensor configuration parameters required by each algorithm in the testing and verification algorithm verification device. The second sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification.

[0039] Specifically, the configuration parameters of the second sensor are set according to the algorithm in the algorithm verification device, which can be an industrial control computer, domain controller, or other device that executes intelligent driving algorithms.

[0040] Step S203: Verify the first configuration file through the second configuration file to obtain the first sensor configuration parameters that have passed the verification, and obtain the sensor acquisition data corresponding to the first sensor configuration parameters that have passed the verification to obtain the sensor acquisition data that has passed the verification.

[0041] Specifically, by using the sensor configuration parameters set in the second configuration file to verify the sensor configuration parameters in the first configuration file, the verified first sensor configuration parameters are obtained. Then, the sensor acquisition data corresponding to the verified first sensor configuration parameters is determined based on the verified first sensor configuration parameters, thereby achieving precise selection of sensor acquisition data.

[0042] Step S204: The sensor data that has passed the verification is sent to the second data acquisition device, so that the second data acquisition device can send the sensor data that has passed the verification to the algorithm verification device to test and verify the algorithm in the algorithm verification device.

[0043] Specifically, the sensor data collected by the first sensor, which has been verified, is input into the algorithm verification device to test and verify the algorithm based on this part of the data.

[0044] In this embodiment, the system receives first sensor configuration parameters and sensor acquisition data from vehicle-side sensors uploaded by a first data acquisition device, and generates a first configuration file representing the first sensor configuration parameters, which include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identifier. It then receives a second configuration file uploaded by a second data acquisition device. This second configuration file contains second sensor configuration parameters required for testing and verifying algorithms in the algorithm verification device, including the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identifier. The first configuration file is then verified using the second configuration file to obtain verified first sensor configuration parameters, and sensor acquisition data corresponding to these verified parameters is acquired, resulting in verified sensor acquisition data. This verified sensor acquisition data is then sent to the second data acquisition device, which in turn sends it to the algorithm verification device for testing and verification of the algorithms within the algorithm verification device. Before data refeedback, the sensor configuration parameters are verified, thereby obtaining the refeedback data corresponding to the sensors required by the algorithm in the algorithm verification device, achieving a precise matching effect. This solves the problem in existing technologies where, during the refeedback of intelligent driving data, it is difficult to match the large amount of collected data with the data required for verification by the algorithm verification device.

[0045] In the specific implementation process, step S203 above verifies the first configuration file through the second configuration file, including: verifying whether the sensor type and sensor identifier in the first configuration file include the sensor type and sensor identifier in the second configuration file; if the sensor type and sensor identifier in the first configuration file include the sensor type and sensor identifier in the second configuration file, verifying whether the sensor installation position in the first configuration file matches the sensor installation position in the second configuration file, and verifying whether the sensor accuracy in the first configuration file matches the sensor accuracy in the second configuration file. The sensor installation position is determined by the sensor installation height, sensor installation angle, and sensor installation distance, and the sensor accuracy includes installation height accuracy, installation angle accuracy, and installation distance accuracy.

[0046] For example: The vehicle is equipped with only a front-facing camera and a rear-facing camera. The LiDAR sensor has 3 sensors. The first camera is 1.5 meters high with an accuracy of ±0.1 meters, located directly in front with an accuracy of ±1°, at a distance of 2.5 meters with an accuracy of ±0.2 meters. The parameter is labeled 8M and is reserved. The second camera is 1.2 meters high with an accuracy of ±0.1 meters, located directly behind with an accuracy of ±1°, at a distance of 2.3 meters with an accuracy of ±0.1 meters. The parameter is labeled 2M and is reserved. The first LiDAR sensor is 1.7 meters high with an accuracy of ±0.2 meters, located directly in front with an accuracy of ±0.5°, at a distance of 1.1 meters with an accuracy of ±0.1 meters. The wiring harness parameter is labeled 150 and is reserved. The sensor arrangement parameters are as follows: 3, camera, 1.5, 0.1, 0, 1, 2.5, 0.2, 8M, 0, camera, 1, 2, 0.1, 180, 1, 2.3, 0.1, 2M, 0, lidar, 1.7, 0.2, 0, 0.5, 1.1, 0.1, 150, 0.

[0047] Specifically, the first configuration file also includes a first reserved field, which is an invalid field. The second configuration file also includes a second reserved field. Verifying whether the sensor accuracy in the first configuration file matches the sensor accuracy in the second configuration file includes: determining whether to verify the installation height accuracy, installation angle accuracy, and installation distance accuracy based on the second reserved field of the second configuration file. If the second reserved field is a verification identifier, it indicates that the corresponding item needs to be verified. If the second reserved field is a non-verification identifier, it indicates that the corresponding item does not need to be verified. For one or more of the installation height accuracy, installation angle accuracy, and installation distance accuracy that need to be verified, sensor accuracy matching is performed.

[0048] The parameters of the first configuration file and the second configuration file correspond. The reserved fields in the first configuration file are invalid fields. The determination of whether to verify the installation height accuracy, installation angle accuracy, and installation distance accuracy is based on the reserved fields in the second configuration file. When the reserved fields corresponding to the installation height accuracy, and / or installation angle accuracy, and / or installation distance accuracy in the second configuration file are "0", the corresponding installation height accuracy, and / or installation angle accuracy, and / or installation distance accuracy do not need to be verified by the sensor. When the reserved fields corresponding to the installation height accuracy, and / or installation angle accuracy, and / or installation distance accuracy in the second configuration file are "1", the corresponding installation height accuracy, and / or installation angle accuracy, and / or installation distance accuracy need to be verified by the sensor.

[0049] More specifically, the flowchart for verifying whether the sensor accuracy in the first configuration file matches the sensor accuracy in the second configuration file, and determining whether the sensor installation height accuracy verification has passed, is shown below. Figure 4 As shown, the specific steps include:

[0050] Step S401: Verify whether the installation height of the sensor in the second configuration file is within the first height range using the first accuracy criterion. The upper limit of the first height range is the sum of the installation height of the sensor in the first configuration file and the sensor height accuracy, and the lower limit of the first height range is the difference between the installation height of the sensor in the first configuration file and the sensor height accuracy.

[0051] Step S402: After determining that the installation height of the sensor in the second configuration file is within the first height range, the second accuracy criterion is used to verify whether there is an intersection between the second height range and the first height range. The upper limit of the second height range is the sum of the installation height of the sensor in the second configuration file and the sensor height accuracy, and the lower limit of the second height range is the difference between the installation height of the sensor in the second configuration file and the sensor height accuracy.

[0052] Step S403: If it is determined that the second height range and the first height range intersect, the installation height accuracy verification in the first configuration file is confirmed to be successful.

[0053] For example: The installation height of sensor A in the first configuration file is 1m, and the accuracy is ±0.1m, that is, the first height range is 0.9m to 1.1m. The installation height of sensor A in the second configuration file is 0.95m, and the accuracy is ±0.5m, that is, the second height range is 0.9m to 1m. After determining that the installation height of the sensor in the second configuration file is within the first height range, and determining that the second height range intersects with the first height range, it is considered that the installation height accuracy verification of sensor A in the first configuration file has passed.

[0054] Furthermore, the method also includes: after determining that the installation height accuracy in the first configuration file has passed verification, verifying other items that need to be verified, including installation angle accuracy and / or installation distance accuracy; and if the other items have also passed verification, obtaining the first sensor configuration parameters that have passed verification.

[0055] After verifying the sensor installation height accuracy, the method also includes verifying the sensor angle accuracy and the sensor installation distance accuracy. It determines whether the sensor installation height accuracy, and / or sensor angle accuracy, and / or sensor position accuracy need to be verified based on the second reserved field in the second configuration file. For example, if the second reserved field corresponding to the sensor A angle accuracy is "0", it means that the sensor A angle accuracy does not need to be verified. If the second reserved field corresponding to the sensor A position accuracy is "1", it means that the sensor A position accuracy needs to be verified using the first accuracy criterion verification and the second accuracy criterion verification.

[0056] Furthermore, the method also includes: real-time monitoring of the sensor installation location of the vehicle-side sensors; and generating alarm information when the sensor installation location of the vehicle-side sensors changes.

[0057] In the event of a vehicle collision, the position of the vehicle's sensors changes, triggering an alarm message. The data collected by the sensors whose positions have changed is then labeled and processed.

[0058] Specifically, there are multiple data collection scenarios and multiple first configuration files. Each data collection scenario corresponds to a first configuration file. There are also multiple verification scenarios and multiple second configuration files. Each verification scenario corresponds to a second configuration file.

[0059] The data collection scenarios include: urban road data collection scenarios, highway data collection scenarios, field and suburban road data collection scenarios, compact area data collection scenarios, and nighttime driving data collection scenarios; the verification scenarios include: urban road verification scenarios, highway verification scenarios, field and suburban road verification scenarios, compact area verification scenarios, and nighttime driving verification scenarios.

[0060] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the intelligent driving data reinjection verification method of this application will be described in detail below with reference to specific embodiments.

[0061] Because intelligent driving vehicles have a wide variety of sensors and collect diverse data, the collected scenario data is numerous. For example, the sensor configurations and arrangements for collecting data in certain forward collision scenarios and automatic parking scenarios are different. In order to solve the problem that the large amount of data makes it difficult to match with the algorithm verification equipment when intelligent driving data is fed back, this embodiment proposes a method for intelligent driving data backfeeding test. Before data backfeeding, the data validity is verified to select backfeeding data that is consistent with the algorithm deployed in the algorithm verification equipment.

[0062] In existing solutions, when feeding back intelligent driving data, only manual judgment is required to determine whether the fed-back data is consistent with the data required by the algorithm verification device, or whether the fed-back data contains the data required for algorithm verification. Manual operation is prone to judgment errors, which may result in the fed-back data not meeting the needs of the algorithm verification device.

[0063] This embodiment relates to a specific method for verifying intelligent driving data recharge, applied to a cloud platform in a data recharge verification system. The system consists of four parts: a cloud platform, data acquisition devices, vehicle-side sensor devices, and algorithm verification devices. After powering on, the data acquisition devices are all remotely connected to the cloud platform. The cloud platform supports the management and data interaction of multiple data acquisition devices. The data acquisition devices can be used for data acquisition (acquisition scenario) and recharge testing (test scenario), such as... Figure 5 As shown, it specifically includes the following:

[0064] 1) In intelligent driving data acquisition scenarios, while the data acquisition device collects vehicle-side sensor data and uploads the data to the cloud platform, it also uploads the vehicle-side sensor deployment information to the cloud platform and writes the sensor deployment parameters into the first configuration file. The sensor deployment parameters include:

[0065] a. Number of sensors;

[0066] b. The type of each sensor (camera or other sensors such as LiDAR);

[0067] c. Height of sensor 1;

[0068] d. The accuracy of the height of sensor 1, for example, 0.1 represents ±0.1;

[0069] e. Sensor 1 position (0° to 360°, with the frontal angle in the vehicle's top view being 0°, rotating clockwise);

[0070] f. The accuracy of the sensor 1 position, for example, 1 represents ±1°;

[0071] g. Sensor 1 distance (distance from the center point of the vehicle's top view to the sensor);

[0072] h represents the accuracy of the distance to sensor 1, for example, 0.2 represents ±0.1;

[0073] i. Sensor 1 parameter identification;

[0074] j. Reserved fields are filled with 0;

[0075] k, sensor 2 parameters such as bj, and so on, sensor 3, ..., sensor n.

[0076] For example: The vehicle is equipped with only a front-facing camera and a rear-facing camera. The LiDAR sensor has 3 sensors. The first camera is 1.5 meters high with an accuracy of ±0.1 meters, located directly in front with an accuracy of ±1°, at a distance of 2.5 meters with an accuracy of ±0.2 meters. The parameter is labeled 8M and is reserved. The second camera is 1.2 meters high with an accuracy of ±0.1 meters, located directly behind with an accuracy of ±1°, at a distance of 2.3 meters with an accuracy of ±0.1 meters. The parameter is labeled 2M and is reserved. The first LiDAR sensor is 1.7 meters high with an accuracy of ±0.2 meters, located directly in front with an accuracy of ±0.5°, at a distance of 1.1 meters with an accuracy of ±0.1 meters. The wiring harness parameter is labeled 150 and is reserved. The sensor arrangement parameters are as follows: 3, camera, 1.5, 0.1, 0, 1, 2.5, 0.2, 8M, 0, camera, 1, 2, 0.1, 180, 1, 2.3, 0.1, 2M, 0, lidar, 1.7, 0.2, 0, 0.5, 1.1, 0.1, 150, 0.

[0077] 2) When the algorithm is deployed to the algorithm verification device, the sensor layout parameters corresponding to the algorithm are written into the second configuration file. The sensor layout parameters are the same as those mentioned above. The reserved fields in the second configuration file store the verification accuracy criteria. When the reserved field in the second configuration file is 0, it means that accuracy verification is not required. When the reserved field in the second configuration file is 1, it means that accuracy verification is required.

[0078] 3) In the test scenario, the second configuration file in the algorithm verification device is uploaded to the cloud platform through the data acquisition device.

[0079] 4) Before the cloud platform sends data back to the data acquisition equipment, it verifies the validity of the sensor deployment in the acquisition scenario and the configuration data in the test scenario. The verification process includes:

[0080] a. Sensor type and identification verification: Does the sensor layout parameters of the data collected in the cloud platform include the sensor configuration required by the algorithm verification device? For example, if the algorithm verification requires a camera with a parameter identification of 8M, then the layout parameters of the cloud platform must at least include the layout parameters of a camera with a parameter identification of 8M.

[0081] b. Sensor height, position, and distance verification: Verify by comparing the sensor height, position, distance, and various accuracies in the configuration file of the device with the sensor layout parameters of the data collected in the cloud platform.

[0082] c. The sensor verification accuracy criterion is 1 (the default accuracy is 0). Verification method: The sensor height in the configuration file of the algorithm verification device is 1 meter. If it is within the height ± accuracy of the sensor layout parameters on the cloud platform, the verification is passed; otherwise, the verification fails. The sensor position and distance verification methods are the same as those for sensor height.

[0083] d. Sensor verification accuracy criterion is 2 (accuracy participates in verification). Verification method: The sensor height in the configuration file of the algorithm verification device is 1 meter and the accuracy is 0.1 meters. The height of the cloud platform sensor layout parameters is 1.1 meters and the accuracy is 0.2 meters. Then, whether there is an intersection between [1-0.1, 1+0.1] and [1.1-0.2, 1.1+0.2]. If there is an intersection, the verification is passed. If there is no intersection, the verification fails. The verification method for sensor position and distance is the same as that for sensor height.

[0084] e. If the sensors to be verified in the algorithm verification device are a front-facing camera, a rear-facing camera, or a LiDAR, for example: 3 sensors, Sensor 1 name, verification result (0 for verification passed, 1 for verification failed), Sensor 2 name, verification result, Sensor 3 name, verification result. Verification result: 3, Camera: 0, Camera: 0, LiDAR: 0, indicates that all three sensors have passed verification; otherwise, verification fails.

[0085] 5) After verification, the recharge data will be distributed and the recharge test will be conducted.

[0086] Existing solutions rely solely on manual verification during intelligent driving data reinjection to determine whether the reinjected data matches the data required by the algorithm verification device, or whether the reinjected data contains the necessary data for algorithm verification. This manual operation is prone to errors, leading to reinjected data that fails to meet the requirements of the algorithm verification device. This embodiment addresses this by adding steps such as uploading vehicle-side sensor deployment data, uploading algorithm verification device configuration data, and verifying data validity before data reinjection. This automatically matches the reinjected data with the algorithm deployed in the algorithm verification device, achieving a precise matching effect.

[0087] This embodiment has the following key points:

[0088] 1) In intelligent driving data collection scenarios, the data collection equipment uploads the vehicle-side sensor deployment information to the cloud platform.

[0089] 2) In the test scenario, the algorithm verification device generates a configuration file based on the data required by the algorithm (in the real vehicle verification scenario, that is, the sensor access data situation) and transmits the configuration data to the data acquisition device.

[0090] 3) The cloud platform verifies the validity of data by comparing the sensor deployment information uploaded during data collection with the configuration data uploaded by the algorithm verification device during testing, thus achieving a precise matching effect.

[0091] This application also provides an apparatus for verifying intelligent driving data backflow. It should be noted that the apparatus for verifying intelligent driving data backflow in this application can be used to execute the method for verifying intelligent driving data backflow provided in this application. This apparatus is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0092] The following describes the apparatus for verifying intelligent driving data reinjection provided in the embodiments of this application.

[0093] Figure 6 This is a schematic diagram of an apparatus for verifying intelligent driving data recharge according to an embodiment of this application. The apparatus is applied to a cloud platform in a data recharge verification system. The data recharge verification system also includes a first data acquisition device and a vehicle-side sensor belonging to the acquisition scenario, and a second data acquisition device and an algorithm verification device belonging to the verification scenario. The first data acquisition device communicates with both the vehicle-side sensor and the cloud platform, and the second data acquisition device communicates with both the algorithm verification device and the cloud platform. Figure 6 As shown, the device includes: a first receiving unit 61, a second receiving unit 62, a verification unit 63, and a testing unit 64;

[0094] The first receiving unit 61 is used to receive the first sensor configuration parameters and sensor acquisition data of the vehicle-end sensor uploaded by the first data acquisition device, and to generate a first configuration file characterizing the first sensor configuration parameters, wherein the first sensor configuration parameters include the number of sensors, sensor type, sensor installation position, sensor accuracy, and sensor identification.

[0095] The types of sensors include cameras and lidar, and the sensor installation locations include sensor height, sensor angle, and sensor distance.

[0096] For example, an 8M camera, where 8M indicates the sensor camera's identifier.

[0097] The second receiving unit 62 is used to receive the second configuration file uploaded by the second data acquisition device. The second configuration file contains the second sensor configuration parameters required by each algorithm in the testing and verification algorithm verification device. The second sensor configuration parameters include the number of sensors, sensor type, sensor installation position, sensor accuracy, and sensor identification.

[0098] Specifically, the configuration parameters of the second sensor are set according to the algorithm in the algorithm verification device, which can be an industrial control computer, domain controller, or other device that executes intelligent driving algorithms.

[0099] The verification unit 63 is used to verify the first configuration file through the second configuration file, obtain the first sensor configuration parameters that have passed the verification, and acquire the sensor acquisition data corresponding to the first sensor configuration parameters that have passed the verification, thereby obtaining the sensor acquisition data that has passed the verification.

[0100] Specifically, by using the sensor configuration parameters set in the second configuration file to verify the sensor configuration parameters in the first configuration file, the verified first sensor configuration parameters are obtained. Then, the sensor acquisition data corresponding to the verified first sensor configuration parameters is determined based on the verified first sensor configuration parameters, thereby achieving precise selection of sensor acquisition data.

[0101] Test unit 64 is used to send the sensor data that has passed the verification to the second data acquisition device, so that the second data acquisition device can send the sensor data that has passed the verification to the algorithm verification device to test and verify the algorithm in the algorithm verification device.

[0102] Specifically, the sensor data collected by the first sensor, which has been verified, is input into the algorithm verification device to test and verify the algorithm based on this part of the data.

[0103] In this embodiment, the first receiving unit is used to receive the first sensor configuration parameters and sensor acquisition data of the vehicle-side sensors uploaded by the first data acquisition device, and to generate a first configuration file characterizing the first sensor configuration parameters, wherein the first sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identifier; the second receiving unit is used to receive the second configuration file uploaded by the second data acquisition device, wherein the second configuration file is configured with the second sensor configuration parameters required by each algorithm in the algorithm verification device for testing and verification, wherein the second sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identifier; the verification unit is used to verify the first configuration file through the second configuration file to obtain the verified first sensor configuration parameters, and to acquire the sensor acquisition data corresponding to the verified first sensor configuration parameters to obtain the verified sensor acquisition data; the testing unit is used to send the verified sensor acquisition data to the second data acquisition device, so that the verified sensor acquisition data can be sent to the algorithm verification device to test and verify the algorithms in the algorithm verification device.

[0104] As an optional solution, the verification unit includes a first verification module and a second verification module; the first verification module is used to verify whether the sensor types and sensor identifiers in the first configuration file include the sensor types and sensor identifiers in the second configuration file; the second verification module is used to verify whether the sensor installation position in the first configuration file matches the sensor installation position in the second configuration file, and whether the sensor accuracy in the first configuration file matches the sensor accuracy in the second configuration file, provided that the sensor types and sensor identifiers in the first configuration file include the sensor types and sensor identifiers in the second configuration file. The sensor installation position is determined by the sensor installation height, the sensor installation angle, and the sensor installation distance, and the sensor accuracy includes installation height accuracy, installation angle accuracy, and installation distance accuracy.

[0105] For example: The vehicle is equipped with only a front-facing camera and a rear-facing camera. The LiDAR sensor has 3 sensors. The first camera is 1.5 meters high with an accuracy of ±0.1 meters, located directly in front with an accuracy of ±1°, at a distance of 2.5 meters with an accuracy of ±0.2 meters. The parameter is labeled 8M and is reserved. The second camera is 1.2 meters high with an accuracy of ±0.1 meters, located directly behind with an accuracy of ±1°, at a distance of 2.3 meters with an accuracy of ±0.1 meters. The parameter is labeled 2M and is reserved. The first LiDAR sensor is 1.7 meters high with an accuracy of ±0.2 meters, located directly in front with an accuracy of ±0.5°, at a distance of 1.1 meters with an accuracy of ±0.1 meters. The wiring harness parameter is labeled 150 and is reserved. The sensor arrangement parameters are as follows: 3, camera, 1.5, 0.1, 0, 1, 2.5, 0.2, 8M, 0, camera, 1, 2, 0.1, 180, 1, 2.3, 0.1, 2M, 0, lidar, 1.7, 0.2, 0, 0.5, 1.1, 0.1, 150, 0.

[0106] In one optional scheme, the second verification module includes a first determination submodule and a precision matching submodule. The first determination submodule is used to verify whether the sensor types and sensor identifiers in the first configuration file include the sensor types and sensor identifiers in the second configuration file. The precision matching submodule is used to verify whether the sensor installation position in the first configuration file matches the sensor installation position in the second configuration file, and whether the sensor precision in the first configuration file matches the sensor precision in the second configuration file, provided that the sensor types and sensor identifiers in the first configuration file include the sensor types and sensor identifiers in the second configuration file. The sensor installation position is determined by the sensor installation height, the sensor installation angle, and the sensor installation distance, and the sensor precision includes installation height precision, installation angle precision, and installation distance precision.

[0107] The parameters of the first configuration file and the second configuration file correspond. The reserved fields in the first configuration file are invalid fields. The determination of whether to verify the installation height accuracy, installation angle accuracy, and installation distance accuracy is based on the reserved fields in the second configuration file. When the reserved fields corresponding to the installation height accuracy, and / or installation angle accuracy, and / or installation distance accuracy in the second configuration file are "0", the corresponding installation height accuracy, and / or installation angle accuracy, and / or installation distance accuracy do not need to be verified by the sensor. When the reserved fields corresponding to the installation height accuracy, and / or installation angle accuracy, and / or installation distance accuracy in the second configuration file are "1", the corresponding installation height accuracy, and / or installation angle accuracy, and / or installation distance accuracy need to be verified by the sensor.

[0108] In one optional embodiment, the second verification module further includes a first verification submodule, a second verification submodule, and a second determination submodule. The first verification submodule is used to verify whether the installation height of the sensor in the second configuration file is within a first height range using a first accuracy criterion, wherein the upper limit of the first height range is the sum of the installation height of the sensor in the first configuration file and the sensor height accuracy, and the lower limit of the first height range is the difference between the installation height of the sensor in the first configuration file and the sensor height accuracy. The second verification submodule, if it is determined that the installation height of the sensor in the second configuration file is within the first height range, uses a second accuracy criterion to verify whether there is an intersection between the second height range and the first height range, wherein the upper limit of the second height range is the sum of the installation height of the sensor in the second configuration file and the sensor height accuracy, and the lower limit of the second height range is the difference between the installation height of the sensor in the second configuration file and the sensor height accuracy. The second determination submodule, if it is determined that there is an intersection between the second height range and the first height range, determines that the installation height accuracy verification in the first configuration file has passed.

[0109] For example: The installation height of sensor A in the first configuration file is 1m, and the accuracy is ±0.1m, that is, the first height range is 0.9m to 1.1m. The installation height of sensor A in the second configuration file is 0.95m, and the accuracy is ±0.5m, that is, the second height range is 0.9m to 1m. After determining that the installation height of the sensor in the second configuration file is within the first height range, and determining that the second height range intersects with the first height range, it is considered that the installation height accuracy verification of sensor A in the first configuration file has passed.

[0110] In one optional scheme, the second verification module further includes a third verification submodule and an acquisition submodule. The third verification submodule is used to verify other items that need to be verified after determining that the installation height accuracy in the first configuration file has passed verification. The other items include installation angle accuracy and / or installation distance accuracy. The acquisition submodule is used to acquire the first sensor configuration parameters that have passed verification if the other items have also passed verification.

[0111] Specifically, after verifying the sensor installation height accuracy, the verification also includes verifying the sensor angle accuracy and the sensor installation distance accuracy. The verification of sensor installation height accuracy, and / or sensor angle accuracy, and / or sensor position accuracy is determined according to the second reserved field in the second configuration file. For example, if the second reserved field corresponding to the angle accuracy of sensor A is "0", it means that the angle accuracy of sensor A does not need to be verified. If the second reserved field corresponding to the position accuracy of sensor A is "1", it means that the position accuracy of sensor A needs to be verified by the first accuracy criterion verification and the second accuracy criterion verification.

[0112] In one alternative embodiment, the device further includes a real-time monitoring unit and a generation unit. The real-time monitoring unit is used to monitor the sensor installation position of the vehicle-side sensor in real time. The generation unit is used to generate alarm information when the sensor installation position of the vehicle-side sensor changes.

[0113] In the event of a vehicle collision, the position of the vehicle's sensors changes, generating an alarm message, and the data collected by the sensors whose positions have changed is labeled and processed.

[0114] One possible approach is to have multiple data collection scenarios, multiple first configuration files, and a one-to-one correspondence between the data collection scenarios and the first configuration files. There are also multiple verification scenarios and multiple second configuration files, with each verification scenario corresponding to a second configuration file.

[0115] The data collection scenarios include: urban road data collection scenarios, highway data collection scenarios, field and suburban road data collection scenarios, compact area data collection scenarios, and nighttime driving data collection scenarios; the verification scenarios include: urban road verification scenarios, highway verification scenarios, field and suburban road verification scenarios, compact area verification scenarios, and nighttime driving verification scenarios.

[0116] The intelligent driving data reinjection verification device includes a processor and a memory. The first receiving unit, the second receiving unit, the verification unit, the testing unit, etc., are all stored as program units in the memory. The processor executes the program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0117] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can address the problem in existing technologies where, during the data feedback process for intelligent driving data, the large volume of collected data makes it difficult to match the data required for verification by the algorithm verification device.

[0118] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0119] This invention provides a computer-readable storage medium including a stored program, wherein the program controls the device containing the computer-readable storage medium to perform the intelligent driving data reinjection verification method during runtime.

[0120] Specifically, the methods for verifying intelligent driving data reinjection include:

[0121] Step S201: Receive the first sensor configuration parameters and sensor acquisition data of the vehicle-side sensor uploaded by the first data acquisition device, and generate a first configuration file characterizing the first sensor configuration parameters, wherein the first sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification.

[0122] Step S202: Receive the second configuration file uploaded by the second data acquisition device. The second configuration file contains the second sensor configuration parameters required by each algorithm in the testing and verification algorithm verification device. The second sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification.

[0123] Step S203: Verify the first configuration file through the second configuration file to obtain the first sensor configuration parameters that have passed the verification, and obtain the sensor acquisition data corresponding to the first sensor configuration parameters that have passed the verification to obtain the sensor acquisition data that has passed the verification.

[0124] Step S204: The sensor data that has passed the verification is sent to the second data acquisition device, so that the second data acquisition device can send the sensor data that has passed the verification to the algorithm verification device to test and verify the algorithm in the algorithm verification device.

[0125] This invention provides a processor for running a program, wherein the program executes the method for verifying intelligent driving data recharge during runtime.

[0126] Specifically, the methods for verifying intelligent driving data reinjection include:

[0127] Step S201: Receive the first sensor configuration parameters and sensor acquisition data of the vehicle-side sensor uploaded by the first data acquisition device, and generate a first configuration file characterizing the first sensor configuration parameters, wherein the first sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification.

[0128] Step S202: Receive the second configuration file uploaded by the second data acquisition device. The second configuration file contains the second sensor configuration parameters required by each algorithm in the testing and verification algorithm verification device. The second sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification.

[0129] Step S203: Verify the first configuration file through the second configuration file to obtain the first sensor configuration parameters that have passed the verification, and obtain the sensor acquisition data corresponding to the first sensor configuration parameters that have passed the verification to obtain the sensor acquisition data that has passed the verification.

[0130] Step S204: The sensor data that has passed the verification is sent to the second data acquisition device, so that the second data acquisition device can send the sensor data that has passed the verification to the algorithm verification device to test and verify the algorithm in the algorithm verification device.

[0131] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0132] Step S201: Receive the first sensor configuration parameters and sensor acquisition data of the vehicle-side sensor uploaded by the first data acquisition device, and generate a first configuration file characterizing the first sensor configuration parameters, wherein the first sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification.

[0133] Step S202: Receive the second configuration file uploaded by the second data acquisition device. The second configuration file contains the second sensor configuration parameters required by each algorithm in the testing and verification algorithm verification device. The second sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification.

[0134] Step S203: Verify the first configuration file through the second configuration file to obtain the first sensor configuration parameters that have passed the verification, and obtain the sensor acquisition data corresponding to the first sensor configuration parameters that have passed the verification to obtain the sensor acquisition data that has passed the verification.

[0135] Step S204: The sensor data that has passed the verification is sent to the second data acquisition device, so that the second data acquisition device can send the sensor data that has passed the verification to the algorithm verification device to test and verify the algorithm in the algorithm verification device.

[0136] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0137] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0138] Step S201: Receive the first sensor configuration parameters and sensor acquisition data of the vehicle-side sensor uploaded by the first data acquisition device, and generate a first configuration file characterizing the first sensor configuration parameters, wherein the first sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification.

[0139] Step S202: Receive the second configuration file uploaded by the second data acquisition device. The second configuration file contains the second sensor configuration parameters required by each algorithm in the testing and verification algorithm verification device. The second sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification.

[0140] Step S203: Verify the first configuration file through the second configuration file to obtain the first sensor configuration parameters that have passed the verification, and obtain the sensor acquisition data corresponding to the first sensor configuration parameters that have passed the verification to obtain the sensor acquisition data that has passed the verification.

[0141] Step S204: The sensor data that has passed the verification is sent to the second data acquisition device, so that the second data acquisition device can send the sensor data that has passed the verification to the algorithm verification device to test and verify the algorithm in the algorithm verification device.

[0142] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0143] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0145] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0146] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0147] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0148] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0149] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0150] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0151] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0152] 1) A method for verifying intelligent driving data recharge, as disclosed in this application, is applied to a cloud platform in a data recharge verification system. The data recharge verification system further includes a first data acquisition device and vehicle-side sensors belonging to the acquisition scenario, and a second data acquisition device and algorithm verification device belonging to the verification scenario. The first data acquisition device communicates with both the vehicle-side sensors and the cloud platform, and the second data acquisition device communicates with both the algorithm verification device and the cloud platform. The method includes: receiving first sensor configuration parameters and sensor acquisition data uploaded by the first data acquisition device from the vehicle-side sensors, and generating a first configuration file representing the first sensor configuration parameters, wherein the first sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identifier; receiving the second data recharge data... The data acquisition device uploads a second configuration file, which contains second sensor configuration parameters required for testing and verifying each algorithm in the algorithm verification device. These second sensor configuration parameters include the number of sensors, sensor types, sensor installation locations, sensor accuracy, and sensor identification. The first configuration file is then validated using the second configuration file to obtain validated first sensor configuration parameters. The sensor acquisition data corresponding to the validated first sensor configuration parameters is then acquired, resulting in validated sensor acquisition data. This validated sensor acquisition data is then sent to the second data acquisition device, which in turn sends the validated sensor acquisition data to the algorithm verification device for testing and verification of the algorithms within the algorithm verification device.

[0153] 2) A device for verifying intelligent driving data recharge, as disclosed in this application, is applied to a cloud platform in a data recharge verification system. The data recharge verification system further includes a first data acquisition device and vehicle-side sensors belonging to the acquisition scenario, and a second data acquisition device and algorithm verification device belonging to the verification scenario. The first data acquisition device communicates with both the vehicle-side sensors and the cloud platform, and the second data acquisition device communicates with both the algorithm verification device and the cloud platform. The device includes: a first receiving unit, used to receive first sensor configuration parameters and sensor acquisition data uploaded by the first data acquisition device from the vehicle-side sensors, and to generate a first configuration file representing the first sensor configuration parameters, wherein the first sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification; and a second receiving unit, used to receive... The second configuration file uploaded by the second data acquisition device contains the second sensor configuration parameters required for each algorithm in the algorithm verification device for testing and verification. These parameters include the number of sensors, sensor types, sensor installation locations, sensor accuracy, and sensor identification. A verification unit verifies the first configuration file using the second configuration file to obtain the verified first sensor configuration parameters and acquires the sensor acquisition data corresponding to these parameters, thus obtaining the verified sensor acquisition data. A testing unit sends the verified sensor acquisition data to the second data acquisition device, which then sends the verified sensor acquisition data to the algorithm verification device for testing and verification of the algorithms within the algorithm verification device.

[0154] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for verifying intelligent driving data refeedback, characterized in that, The method is applied to a cloud platform in a data reinjection verification system. The data reinjection verification system further includes a first data acquisition device and a vehicle-mounted sensor belonging to the acquisition scenario, and a second data acquisition device and an algorithm verification device belonging to the verification scenario. The first data acquisition device communicates with both the vehicle-mounted sensor and the cloud platform, and the second data acquisition device communicates with both the algorithm verification device and the cloud platform. The system receives the first sensor configuration parameters and sensor acquisition data of the vehicle-side sensor uploaded by the first data acquisition device, and generates a first configuration file characterizing the first sensor configuration parameters, wherein the first sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification. The system receives a second configuration file uploaded by the second data acquisition device. The second configuration file contains second sensor configuration parameters required for testing and verifying each algorithm in the algorithm verification device. The second sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification. The first configuration file is verified by the second configuration file to obtain the first sensor configuration parameters that have passed the verification, and the sensor acquisition data corresponding to the first sensor configuration parameters that have passed the verification is obtained to obtain the sensor acquisition data that has passed the verification. The sensor data that has passed verification is sent to the second data acquisition device, which then sends the verified sensor data to the algorithm verification device to test and verify the algorithm in the algorithm verification device.

2. The method according to claim 1, characterized in that, The first configuration file is validated using the second configuration file, including: Verify whether the sensor types and sensor identifiers in the first configuration file include the sensor types and sensor identifiers in the second configuration file; If the sensor type and sensor identifier in the first configuration file include the sensor type and sensor identifier in the second configuration file, verify whether the sensor installation position in the first configuration file matches the sensor installation position in the second configuration file, and verify whether the sensor accuracy in the first configuration file matches the sensor accuracy in the second configuration file. The sensor installation position is determined by the sensor installation height, the sensor installation angle, and the sensor installation distance, and the sensor accuracy includes installation height accuracy, installation angle accuracy, and installation distance accuracy.

3. The method according to claim 2, characterized in that, The first configuration file also includes a first reserved field, which is an invalid field. The second configuration file also includes a second reserved field. Verifying whether the sensor accuracy in the first configuration file matches the sensor accuracy in the second configuration file includes: Whether to verify the installation height accuracy, the installation angle accuracy, and the installation distance accuracy is determined based on the second reserved field of the second configuration file. If the second reserved field is a verification identifier, it indicates that the corresponding item needs to be verified. If the second reserved field is a non-verification identifier, it indicates that the corresponding item does not need to be verified. Sensor accuracy matching is performed for one or more of the installation height accuracy, installation angle accuracy, and installation distance accuracy that need to be verified.

4. The method according to claim 2, characterized in that, Verifying whether the sensor accuracy in the first configuration file matches the sensor accuracy in the second configuration file includes: The installation height of the sensor in the second configuration file is verified using a first accuracy criterion. The upper limit of the first height range is the sum of the installation height of the sensor in the first configuration file and the sensor height accuracy, and the lower limit of the first height range is the difference between the installation height of the sensor in the first configuration file and the sensor height accuracy. If the installation height of the sensor in the second configuration file is determined to be within the first height range, a second accuracy criterion is used to verify whether there is an intersection between the second height range and the first height range. The upper limit of the second height range is the sum of the installation height of the sensor in the second configuration file and the sensor height accuracy, and the lower limit of the second height range is the difference between the installation height of the sensor in the second configuration file and the sensor height accuracy. If it is determined that the second height range intersects with the first height range, then the installation height accuracy verification in the first configuration file is deemed successful.

5. The method according to claim 4, characterized in that, The method further includes: After verifying that the installation height accuracy in the first configuration file has passed the verification, other items that need to be verified are verified, including installation angle accuracy and / or installation distance accuracy. If the other items are also verified, the verified configuration parameters of the first sensor are obtained.

6. The method according to claim 1, characterized in that, The method further includes: The sensor installation position of the vehicle-side sensor is monitored in real time; An alarm message is generated if the installation position of the vehicle-side sensor changes.

7. The method according to claim 1, characterized in that, There are multiple data collection scenarios, and multiple first configuration files. Each data collection scenario corresponds to one of the first configuration files. There are multiple verification scenarios, and multiple second configuration files. Each verification scenario corresponds to one of the second configuration files.

8. A device for verifying intelligent driving data reinjection, characterized in that, The device is applied to a cloud platform in a data reinjection verification system. The data reinjection verification system further includes a first data acquisition device and a vehicle-mounted sensor belonging to the acquisition scenario, and a second data acquisition device and an algorithm verification device belonging to the verification scenario. The first data acquisition device communicates with both the vehicle-mounted sensor and the cloud platform, and the second data acquisition device communicates with both the algorithm verification device and the cloud platform. The first receiving unit is configured to receive the first sensor configuration parameters and sensor acquisition data of the vehicle-end sensor uploaded by the first data acquisition device, and generate a first configuration file characterizing the first sensor configuration parameters, wherein the first sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification. The second receiving unit is used to receive the second configuration file uploaded by the second data acquisition device. The second configuration file contains the second sensor configuration parameters required for testing and verifying each algorithm in the algorithm verification device. The second sensor configuration parameters include the number of sensors, sensor type, sensor installation location, sensor accuracy, and sensor identification. The verification unit is used to verify the first configuration file through the second configuration file to obtain the first sensor configuration parameters that have passed the verification, and to obtain the sensor acquisition data corresponding to the first sensor configuration parameters that have passed the verification to obtain the sensor acquisition data that has passed the verification. The testing unit is used to send the sensor data that has passed verification to the second data acquisition device, so that the second data acquisition device can send the sensor data that has passed verification to the algorithm verification device to test and verify the algorithm in the algorithm verification device.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the intelligent driving data reinjection verification method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a method for performing the intelligent driving data reinjection verification according to any one of claims 1 to 7.

Images