Test method, test device and test bench for intelligent driving system

Abstract

The invention provides a test method, a test device and a test bench for an intelligent driving system. The test method comprises the following steps: collecting original drive test data; acquiring transmission configuration data corresponding to the target test scene; target transmission data in the original drive test data is screened based on the transmission configuration data, and the target transmission data is recharged to the tested end through the Ethernet transmission gateway, so that an intelligent driving system located at the tested end can respond to the target transmission data; receiving target response data of the intelligent driving system returned by the tested end through the Ethernet transmission gateway, wherein the target response data is obtained by screening response data of the intelligent driving system based on the transmission configuration data; and testing the intelligent driving system according to the target response data to obtain a test result of the intelligent driving system. The method has low requirements on software and hardware environments of equipment, does not occupy the storage space of the domain controller, improves the test efficiency and the test accuracy, and is suitable for different projects and different intelligent driving software versions.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent driving technology, and in particular to a testing method, a testing device and a testing bench for an intelligent driving system. Background Art

[0002] Testing is a key step to ensure the performance and reliability of intelligent driving. The main testing methods include real-car road testing, simulation testing and bench testing. Real-car testing completes relevant scenario testing in environments such as open roads or parking lots, which can reflect the real situation but is inefficient and does not cover enough scenarios. Simulation testing has advantages in simulating complex environments and scenarios, but because its sensors are simulated data and lack authenticity, it is mainly used to discover potential problems and defects in the early stages of intelligent driving products. Bench testing uses real equipment and corresponding test instruments, and focuses more on evaluating the actual performance and performance of the equipment or system.

[0003] There are two main implementation forms of bench re-injection testing: one is external devices, such as test cabinets or CANoe (a data playback analysis tool) containing video injection boards, CAN (controller area network) bus boards, clock synchronization boards, etc., which send the original collected data to the domain controller through external devices to achieve effective interaction between the two, thereby completing the bench re-injection test; the other is to copy the original data to the domain controller in the form of a bag package, and directly replay the data in the domain controller to complete the bench test. However, the former will increase the test cost because of the connection to external devices, while the latter will limit the test efficiency due to the storage space and copying time of the domain controller.

[0004] There are two main methods for bench re-injection testing: automated testing and manual testing. However, manual testing is inefficient and wastes manpower. Although automated testing has greatly improved the test speed, it also has the problem of being unable to accurately monitor the processing results of the domain controller after receiving the re-injection data in real time due to IO read and write delays, which leads to errors in the test conclusions. Summary of the invention

[0005] The technical problem to be solved by the present disclosure is to overcome the defects in the prior art that external devices increase the testing cost, bag copying is time-consuming and occupies the storage space of the domain controller, and the accuracy of the test conclusions cannot be ensured, and to provide a testing method, testing device and testing bench for an intelligent driving system.

[0006] The present invention solves the above technical problems through the following technical solutions:

[0007] According to a first aspect of the present disclosure, a test method for an intelligent driving system is provided. The test method is applied to a test end, and the test method includes:

[0008] Collect original drive test data;

[0009] Obtain the transmission configuration data corresponding to the target test scenario;

[0010] Filtering target transmission data in the original drive test data based on the transmission configuration data, and feeding the target transmission data back to the tested end via the Ethernet transmission gateway, so that the intelligent driving system at the tested end can respond;

[0011] receiving target response data of the intelligent driving system returned by the tested end via the Ethernet transmission gateway, wherein the target response data is obtained by filtering the response data of the intelligent driving system based on the transmission configuration data;

[0012] The intelligent driving system is tested according to the target response data to obtain a test result of the intelligent driving system.

[0013] Preferably, after the step of collecting original drive test data, the test method further comprises:

[0014] Splitting the original drive test data into different drive test data packets according to different test scenarios;

[0015] The step of screening the target transmission data in the original drive test data based on the transmission configuration data, and feeding the target transmission data back to the tested end via the Ethernet transmission gateway for the intelligent driving system to respond includes:

[0016] Acquire a target drive test data packet according to the target test scenario;

[0017] Filtering the target transmission data in the target drive test data packet based on the transmission configuration data;

[0018] According to the configured transmission rate, the target transmission data is sequentially fed back to the tested end via the Ethernet transmission gateway for the intelligent driving system to respond.

[0019] Preferably, the step of screening the target transmission data in the target drive test data packet based on the transmission configuration data comprises:

[0020] Obtaining scenario configuration data corresponding to the target test scenario;

[0021] Filtering the target scenario data in the target drive test data packet according to the scenario configuration data, and recording and generating the target scenario data packet;

[0022] The target transmission data in the target scenario data packet is filtered based on the transmission configuration data.

[0023] Preferably, the scene configuration data includes at least one of a data type and a transmission rate.

[0024] Preferably, the step of testing the intelligent driving system according to the target response data to obtain the test result of the intelligent driving system includes:

[0025] Obtaining recording configuration data corresponding to the target test scenario;

[0026] Filtering target recording data in the target response data based on the recording configuration data, and generating a recording data packet;

[0027] The recorded data packet is tested offline using a test script to obtain the test result of the intelligent driving system.

[0028] Preferably, after the step of collecting original drive test data, the test method further comprises:

[0029] Performing true value annotation and data extraction on the original drive test data to obtain true value drive test data;

[0030] Splitting the true value drive test data into different true value data packets according to different test scenarios;

[0031] The step of performing offline testing on the recorded data packet using a test script to obtain the test result of the intelligent driving system comprises:

[0032] Obtaining a target true value data packet corresponding to the target test scenario;

[0033] Performing scene alignment processing on the recorded data packet and the target true value data packet, and matching the first timestamp of each target recorded data in the recorded data packet with the second timestamp of each true value data in the target true value data packet, to obtain actual response data and expected true value data;

[0034] The actual response data and the expected true value data are tested using the test script to obtain the test result of the intelligent driving system.

[0035] Preferably, the transmission configuration data includes a data type and at least one of a data name under the data type, a data sending end, a data receiving end and a data transmission mode.

[0036] According to a second aspect of the present disclosure, a test method for an intelligent driving system is provided. The test method is applied to a tested end, and the test method includes:

[0037] Receiving target transmission data fed back via the Ethernet transmission gateway, wherein the target transmission data is obtained by filtering original drive test data based on transmission configuration data of a target test scenario;

[0038] Acquire response data output by the intelligent driving system based on the target transmission data;

[0039] The target response data in the response data is filtered according to the transmission configuration data, and the target response data is transmitted to the test end via the Ethernet transmission gateway so that the test end can test the intelligent driving system.

[0040] According to a third aspect of the present disclosure, a test device for an intelligent driving system is provided, the test device being applied to a test end, the test device comprising a collection module, a configuration acquisition module, a test data transmission module and a test module;

[0041] The acquisition module is used to acquire original drive test data;

[0042] The configuration acquisition module is used to obtain transmission configuration data corresponding to the target test scenario;

[0043] The test data transmission module is used to filter the target transmission data in the original drive test data based on the transmission configuration data, and feed the target transmission data back to the tested end via the Ethernet transmission gateway for the intelligent driving system to respond;

[0044] The test data transmission module is further used to receive target response data of the intelligent driving system returned by the tested end via the Ethernet transmission gateway, wherein the target response data is obtained by filtering the response data of the intelligent driving system based on the transmission configuration data;

[0045] The testing module is used to test the intelligent driving system according to the target response data to obtain a test result of the intelligent driving system.

[0046] According to a fourth aspect of the present disclosure, a test device for an intelligent driving system is provided, the test device being applied to a tested end, the test device comprising a response data transmission module and a data acquisition module;

[0047] The response data transmission module is used to receive target transmission data fed back via the Ethernet transmission gateway, wherein the target transmission data is obtained by filtering the original drive test data based on the transmission configuration data of the target test scenario;

[0048] The data acquisition module is used to acquire response data output by the intelligent driving system based on the target transmission data;

[0049] The response data transmission module is also used to filter target response data in the response data according to the transmission configuration data, and transmit the target response data to the test end via the Ethernet transmission gateway to test the intelligent driving system.

[0050] According to a fifth aspect of the present disclosure, a test bench for an intelligent driving system is provided, the test bench comprising a test end and a tested end;

[0051] The test end includes the test device of the intelligent driving system according to the third aspect of the present disclosure;

[0052] The tested end includes the testing device of the intelligent driving system described in the fourth aspect of the present disclosure.

[0053] According to the sixth aspect of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and used to run on the processor, wherein when the processor executes the computer program, the testing method of the intelligent driving system described in the first aspect of the present disclosure or the second aspect of the present disclosure is implemented.

[0054] According to the seventh aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the test method of the intelligent driving system described in the first aspect of the present disclosure or the second aspect of the present disclosure is implemented.

[0055] According to an eighth aspect of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the testing method of the intelligent driving system described in the first aspect of the present disclosure or the second aspect of the present disclosure.

[0056] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present disclosure.

[0057] The positive progressive effects of the present disclosure are: it does not rely on data transmission boards, has low requirements on the software and hardware environment of the equipment, greatly saves testing costs, does not occupy the storage space of the domain controller, ensures the integrity of the test data, saves the time of manually or automatically copying the output data of the domain controller during the bench re-injection test, avoids the inaccurate test conclusions caused by incomplete verification, and batch re-injection scripts improve test efficiency. It is suitable for different projects and different intelligent driving software versions, avoids repetitive work, and greatly saves time and labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a flow chart of a testing method for an intelligent driving system in Embodiment 1 of the present disclosure;

[0059] Figure 2This is a flowchart of step S15 in the test method of the intelligent driving system in Embodiment 1 of the present disclosure;

[0060] Figure 3 This is a flowchart of processing original road test data in the test method of the intelligent driving system in Embodiment 1 of the present disclosure;

[0061] Figure 4 This is a flow chart of a testing method for an intelligent driving system in Embodiment 2 of the present disclosure;

[0062] Figure 5 This is a schematic diagram of a test device module for an intelligent driving system in Embodiment 3 of the present disclosure;

[0063] Figure 6 This is a schematic diagram of a test device module for an intelligent driving system in Embodiment 4 of the present disclosure;

[0064] Figure 7 This is a data processing schematic diagram of a test bench for an intelligent driving system in Embodiment 5 of the present disclosure;

[0065] Figure 8 This is a schematic diagram of the structure of an electronic device in Embodiment 6 of the present disclosure. DETAILED DESCRIPTION

[0066] The present disclosure is further described below by way of examples, but the present disclosure is not limited to the scope of the examples.

[0067] Prefixes such as "first" and "second" are used in the embodiments of the present disclosure only to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present disclosure does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and no unnecessary limitation should be constituted due to the use of such prefixes. In addition, in the description of the present embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

[0068] In the embodiments of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0069] Example 1

[0070] In a specific embodiment of the present disclosure, a test method for an intelligent driving system is provided. The test method is applied to a test end, such as Figure 1 As shown, the test methods include:

[0071] S11, collecting original drive test data;

[0072] S12, obtaining transmission configuration data corresponding to the target test scenario;

[0073] S13, filtering target transmission data in the original drive test data based on the transmission configuration data, and feeding the target transmission data back to the tested end via the Ethernet transmission gateway, so that the intelligent driving system at the tested end can respond;

[0074] S14, receiving target response data of the intelligent driving system returned by the tested end via the Ethernet transmission gateway, where the target response data is obtained by filtering the response data of the intelligent driving system based on the transmission configuration data;

[0075] S15. Test the intelligent driving system according to the target response data to obtain a test result of the intelligent driving system.

[0076] Specifically, step S11 can record the original road test data related to the vehicle's surrounding environment, vehicle status, driving behavior, etc. under different demand scenarios through a collection vehicle. In order to improve the reusability of the original road test data, the collection vehicle needs to be equipped with various sensors that can collect the original road test data, such as lidar, camera, ultrasonic detector, etc., and then use the data recording function (for example, using the recording node (data_recorder node)) to record the collected original road test data (including images, videos, lidar scanning point clouds, inertial measurement unit (IMU) data, GPS (global positioning system) location information, dr (track calculation)), etc. into a bag package as the input of the intelligent driving system for perception, decision-making and control.

[0077] In order to solve the problem that the existing test cabinet needs to use a data transmission board to realize data re-injection, this specific implementation method is based on the ROS (Robot Operating System) framework to develop a data transmission node (transport_gatewaynode) for data interaction between the test end (for example, PC end) and the tested end (domain controller end). In order to ensure error-free, loss-free, and non-repetitive data transmission at both ends, the TCP (Transmission Control Protocol) communication method is adopted. Among them, the data transmission node includes two transmission configuration files, and the transmission configuration file 1 is used to set the data that needs to be transmitted from the test end to the intelligent driving system of the tested end for response, and the intelligent driving system response data that needs to be transmitted back from the tested end to the test end; the transmission configuration file 2 is used to set the IP (Internet Protocol) addresses of the test end and the tested end, so that the test end and the tested end are in the same local area network segment to realize data transmission. Since the data transmission node has no dependency on the domain controller and the test model, the tester can configure the data transmission node according to different target test scenarios to realize batch setting of test data, so as to meet the needs of different projects and different versions for different test data.

[0078] In a specific example, the transmission configuration file 1 contains data types of service service, interface node_interface and topic topic. Each data type includes the data name name, sender export_hosts, receiver import_hosts, transmission mode deliver_mode and other main fields. Among them, deliver_mode is empty by default. If data needs to be sent all the time, fill in "always". If data transmission is only performed when there is a request or data output, leave this field blank. The main fields of configuration file 1 are as follows:

[0079]

[0080]

[0081]

[0082] For example, if you need to send data of a topic type a.topic from the test end dev to the tested end soc for the intelligent driving software to respond to, and you need to send it all the time, you can configure the topics data type as follows:

[0083]

[0084] It should be noted that when some data needs to be sent from the test end to the tested end and also transmitted back from the tested end to the test end, the data type field can be repeatedly filled in the transmission configuration file 1 and the names of the receiving end and the sending end can be exchanged.

[0085] After obtaining the configuration file of the data transmission node flexibly configured by the tester for the target test scenario through step S12, the original road test data can be filtered according to the transmission configuration data in the configuration file through step S13 to obtain the target transmission data, and then the filtered target transmission data is fed back to the tested end via the Ethernet transmission gateway (ETH) for the intelligent driving system at the tested end to respond.

[0086] Continuing with the previous example, the configuration file of the data transmission node is configured to send topic type data a.topic from the test end to the tested end. The target transmission data of a.topic can be filtered out from the original road test data, and then fed back to the tested end in the order of timestamps via the Ethernet transmission gateway in a continuous sending transmission mode for the intelligent driving software to respond.

[0087] Since both the test end and the tested end are deployed with data transmission nodes, before the tested end transmits the response data output by the intelligent driving system in response to the target transmission data back to the test end, the response data will also be filtered according to the transmission configuration data, and only the target response data that needs to be transmitted to the test end will be transmitted back to the test end in sequence through the Ethernet transmission gateway according to the timestamp, so that the test end can receive it through step S14.

[0088] After obtaining the target response data output by the intelligent driving system, the test end can test the intelligent driving system using the test nodes set in the test end through step S15 to obtain the test result of the intelligent driving system.

[0089] This specific implementation method replaces the data transmission board in the test cabinet by setting up data transmission nodes at the test end and the tested end respectively. The data transmission node has a two-way transmission capability and can transmit the response data of the intelligent driving system to the test end in timestamp order for storage and testing, which not only ensures the integrity of the data and saves the test cost, but also avoids the data loss phenomenon caused by insufficient storage space of the domain controller, ensures the integrity of the test data, and saves the time of manually or automatically copying the output data of the domain controller during the bench re-injection test, thereby improving the test efficiency. At the same time, the tester can flexibly adjust the transmission data transmitted from the test end to the tested end and the response data transmitted back from the tested end to the test end by modifying the configuration file of the data transmission node, which not only saves the extra time consumed by the re-injection of all original road test data and the preservation of response data, but also saves storage space.

[0090] In a specific embodiment, after step S11, the testing method further includes:

[0091] Split the original drive test data into different drive test data packets according to different test scenarios;

[0092] Step S13 includes:

[0093] S131, obtaining a target drive test data packet according to a target test scenario;

[0094] S132, filtering target transmission data in the target drive test data packet based on the transmission configuration data;

[0095] S133. According to the configured transmission rate, the target transmission data is sequentially fed back to the tested end via the Ethernet transmission gateway for the intelligent driving system to respond.

[0096] Specifically, after the original drive test data is collected, it can be unpacked according to the requirements of the test scenario. For example, the original drive test data can be split into multiple bags corresponding to each target test scenario, and some test required data can be extracted and compressed into new drive test data bags with smaller capacity.

[0097] When filtering the target transmission data in the original road test data according to the transmission configuration data, the corresponding target road test data packet can be obtained according to the target test scenario, and then the target transmission data packet is directly filtered from the target road test data packet, and the target transmission data is sequentially fed back to the tested end in the order of timestamps via the Ethernet transmission gateway at the configured transmission rate for the intelligent driving system to respond, thereby improving the processing efficiency of the test data.

[0098] In a specific implementation, step S132 includes:

[0099] S1321. Obtaining scenario configuration data corresponding to the target test scenario;

[0100] S1322, filtering target scenario data in the target drive test data packet according to the scenario configuration data, and recording and generating the target scenario data packet;

[0101] S1323. Filter the target transmission data in the target scene data packet based on the transmission configuration data.

[0102] Specifically, this specific implementation also develops and designs a data playback node (zplayernode) in the test end. The data playback node is provided with a scenario configuration file. The tester can select scenario data and configure the transmission rate according to the actual test requirements, unpack and parse the data according to the fields in the scenario configuration file, and transmit the data to the data transmission node in chronological order for transmission. For example, the configuration file includes three fields by default: , and , Indicates that all data in the target drive test data packet will be read and transmitted by default. If only part of the data needs to be transmitted, you can select which field the data belongs to and delete it. , and add the relevant data name at the end; in addition, the scenario configuration file also includes a --zplayer speed 1.0 field, which defaults to a one-to-one transmission rate based on the frame rate of the original drive test data. Of course, it also supports modifying the transmission rate to be backward compatible with different projects and versions.

[0103] Among them, when the zplayer speed 1.0 field is modified, that is, the transmission is not performed at a rate of 1:1, the data needs to be decoded and re-encoded, and then the re-encoded data is transmitted. For example, the data in the target drive test data packet is 20 frames per second. After setting the zplayer speed to 0.5, the data playback node will decode the data and extract frames to encode it into a rate of 10 frames per second to form a target scenario data packet. When the target transmission data in the original drive test data is filtered according to the transmission configuration data, the target transmission data can be directly filtered from the target scenario data packet, and the target transmission data can be transmitted to the tested end at a rate of 10 frames per second, thereby extracting the original packet of 20 frames per second into 10 frames per second and transmitting it to the domain controller.

[0104] This specific implementation method configures the batch re-injection script, and can select different types of re-injection data sets for different projects and versions to perform intelligent driving software testing by modifying the scenario configuration file or modifying the interface parameters, thereby greatly improving the testing efficiency.

[0105] In a specific embodiment, Figure 2 As shown, step S15 includes:

[0106] S151, obtaining recording configuration data corresponding to the target test scenario;

[0107] S152, filtering target recording data in the target response data based on the recording configuration data, and generating a recording data packet;

[0108] S153. Use the test script to perform offline testing on the recorded data packets to obtain test results of the intelligent driving system.

[0109] Specifically, this specific implementation also develops and designs a data recording node (zrecordernode) in the test end, which is provided with a recording configuration file. The tester can selectively save the useful data concerned in this test according to the actual test requirements, and save storage space and test time by discarding the irrelevant data, while also reducing the trouble caused by redundant data to problem analysis. Among them, the fields in the recording configuration file are consistent with the fields in the scenario configuration file.

[0110] The target response data returned from the domain controller is filtered and recorded according to the recording configuration data in the recording configuration file, and a recording data packet is generated and saved in the specified directory, so that the recording data packet can be tested offline using the test script to complete the test of intelligent driving.

[0111] In a specific embodiment, after step S11, the testing method further includes:

[0112] Perform true value annotation and data extraction on the original drive test data to obtain true value drive test data;

[0113] Split the true value drive test data into different true value data packets according to different test scenarios;

[0114] Step S153 includes:

[0115] S1531, obtaining a target true value data packet corresponding to the target test scenario;

[0116] S1532, performing scene alignment processing on the recorded data packet and the target true value data packet, and matching the first timestamp of each target recorded data in the recorded data packet with the second timestamp of each true value data in the target true value data packet to obtain actual response data and expected true value data;

[0117] S1533. Use the test script to test the actual response data and the expected true value data to obtain the test results of the intelligent driving system.

[0118] Specifically, Figure 3 As shown, if the test needs to use true values ​​for result comparison, after the original road test data is collected by configuring a multi-sensor collection vehicle, data extraction can be performed, true value tools can be used for automatic labeling or manual labeling to generate true values, and scripts can be used to read relevant data in the bag package and save it as a true value file to obtain true value road test data. Then, the true value road test data can be split and processed according to different test scenarios to obtain true value data packets under each test scenario.

[0119] The result data in the recorded data packet and the true value data in the preprocessed true value data packet are automatically tested offline to complete the verification of the results. In the specific test process, the actual result data of each data frame in the recorded data packet can be compared with the target true value data packet. The scene coordinates of the actual result data can be converted into the true value data using the coordinate system conversion matrix for timestamp matching. If the difference between the timestamps of the two is less than a certain value, it is considered to be the same time. The allowable difference size is determined according to the output frequency of different functional modules. In the case of timestamp alignment, the scene alignment is also required to be processed into a coordinate system consistent with the expected result data in the target true value data packet, and then the fields that are the same as the actual result and the expected result are compared in turn, and different return results are obtained according to different test indicators, such as whether there is or is no similar intelligent driving system output result and true value data after comparison to return True or False (right or wrong) Boolean value type conclusion, there is a specific value of the intelligent driving system output result and true value data after comparison to return the error value of the two, etc., so as to obtain the test result of the intelligent driving system.

[0120] Among them, this specific implementation method also visualizes and documents the test results. Among them, in order to ensure the traceability of the test results, Python (a programming language) script is used to summarize and save the final conclusions and detailed comparison results of each test in a csv (a data format) file; and in order to see the test data and test results more clearly and intuitively, the relevant key data can also be visualized, for example, using a bar chart to show the distribution and distribution trend of various results, using a line chart to show the test results of the difference in intelligent driving performance between different versions, and using an html page to show whether the actual output results and the true value data are the same, as well as the entire test report.

[0121] Since the test end has low requirements for the software and hardware environment of the device, for example, the Ubuntu system, Python dependency environment, and a relatively large hard disk (if the machine itself has small storage space, an external mechanical hard disk or mobile hard disk can be used for capacity expansion), common laptops or desktops on the market can be selected to replace relatively expensive bench test cabinets, thereby greatly saving test costs.

[0122] It should be noted that, in this embodiment, all data can be transmitted, stored, etc. in the form of bags.

[0123] This specific implementation method uses an automated test script to perform timestamp matching on the PC side, and then completes the offline comparison of the real-time output results in the domain controller with the expected results in a time sequence to obtain the test results of the intelligent driving software, which effectively solves the time delay caused by the time complexity of the automated script and the time-consuming IO (input and output) reading and writing, thereby avoiding the phenomenon of inaccurate test results caused by incomplete verification. In addition, offline testing can complete the performance evaluation of different modules (for example, visual perception, fusion perception, positioning, etc.) by modifying parameters, avoiding repetitive work and greatly saving time and labor costs.

[0124] In a specific example, according to the different test items and test modules, the re-injection data classified according to the scenarios are screened through a python script to combine all the data sets for this re-injection test; then the relevant fields in the transmission configuration file of the data transmission node, the scenario configuration file of the data playback node and the recording configuration file of the data recording node are modified to set the data that needs to be re-injected, the data that needs to be recorded, and the data that needs to be transmitted between the PC and the domain controller for this re-injection test; then all the data sets are re-injected in turn using the script and the corresponding output results are stored in turn.

[0125] Taking the visual perception module test as an example, since the overall link of the visual perception module is that the visual perception node receives the image data and then identifies the obstacles around itself and outputs the type of obstacles, it will also use the coordinate conversion matrix in the dr data to give the location information of the obstacles in the baselink coordinate system (the coordinate system based on itself as the origin of the coordinates). Therefore, the recharge evaluation method for the visual perception module is to filter out the data set according to the visual perception keywords, and use the script to automatically complete the modification of the configuration file fields of the recharge-related nodes, that is, the data playback node configuration needs to replay the upstream data related to the visual perception node: image data (camera topic), track calculation (dr topic) and some vehicle body data (live_msg), etc.; the data transmission node configuration configures the upstream data required by the above perception nodes to be sent from the PC end to the domain controller, and configures the output data of the visual perception node (visual_perception topic) to be sent by the domain controller and received by the PC end; the data recording node configuration needs to record the output data of the visual perception node. After completing the above configuration, the output result of the visual perception module can be obtained by recharging and stored on the PC in the form of a bag.

[0126] Taking the positioning module test as an example, the working mode of the positioning module is that after the positioning node receives various semantic information around the vehicle, such as the camera topic of the camera, the USS topic (ultrasonic data) of the ultrasonic sensor, and the lidar topic (laser radar data) of the laser, the positioning node gives a fusion positioning result based on various semantic information and GPS data to inform the downstream of the current location. According to the above principle, the data playback node can be used to configure the data of all sensors required for positioning and some vehicle body data; the data transmission node configures the above upstream data to be sent from the PC to the domain controller, and the output data of the positioning node is configured to be sent from the domain controller to the PC; the data recording node configures the output data of the positioning node. After completing the above configuration, the output result of the positioning module can be obtained by re-injection and stored on the PC in the form of a bag.

[0127] It should be noted that this embodiment takes the intelligent driving system as an example, but is not limited to this.

[0128] This embodiment does not rely on the data transmission board, has low requirements on the software and hardware environment of the equipment, greatly saves testing costs, does not occupy the storage space of the domain controller, ensures the integrity of the test data, saves the time of manually or automatically copying the output data of the domain controller during the bench re-injection test, avoids the inaccurate test conclusions caused by incomplete verification, and improves the test efficiency. The batch re-injection script is suitable for different projects and different intelligent driving software versions, avoids repetitive work, and greatly saves time and labor costs.

[0129] Example 2

[0130] In a specific embodiment of the present disclosure, a test method for an intelligent driving system is provided. The test method is applied to a tested end, such as Figure 4 As shown, the test method includes:

[0131] S21, receiving target transmission data fed back via the Ethernet transmission gateway, where the target transmission data is obtained by filtering the original drive test data based on the transmission configuration data of the target test scenario;

[0132] S22, obtaining response data output by the intelligent driving system based on the target transmission data;

[0133] S23. Filter target response data in the response data according to the transmission configuration data, and transmit the target response data to the test end via the Ethernet transmission gateway, so that the test end can test the intelligent driving system.

[0134] Specifically, the tested end may be a domain controller, and a data transmission node (transport_gateway node) for data interaction between the test end (for example, the PC end) and the tested end (domain controller end) is provided in the domain controller. In step S21, the test end receives the target transmission data obtained by screening the transmission configuration data of the transmission configuration file through the data transmission node, and the target transmission data is fed back through the Ethernet transmission gateway. After receiving the target transmission data, the video stream is decoded, for example, it is decoded into YUYV (an image format) or NV12 (an image format) format according to the requirements of the module and the project, and is sent to the intelligent driving system in sequence according to the timing. The intelligent driving system obtains the original data of the relevant sensors, performs corresponding data processing and calculation, and makes corresponding feedback responses. Then, the response data of the intelligent driving system for the target transmission data is obtained through step S22. In step S23, the response data is screened by using the transmission configuration data of the transmission configuration file in the data transmission node to obtain the target response data that needs to be transmitted back to the test end, and then transmitted to the test end through the Ethernet transmission gateway for the test end to perform the test. This not only avoids the occupation of the storage space of the domain controller, but also ensures the integrity of the test data to ensure the accuracy of the test results.

[0135] It should be noted that this embodiment takes the intelligent driving system as an example, but is not limited to this.

[0136] This embodiment does not rely on the data transmission board, has low requirements on the software and hardware environment of the equipment, greatly saves testing costs, does not occupy the storage space of the domain controller, ensures the integrity of the test data, saves the time of manually or automatically copying the output data of the domain controller during the bench re-injection test, avoids the inaccurate test conclusions caused by incomplete verification, and improves the test efficiency. The batch re-injection script is suitable for different projects and different intelligent driving software versions, avoids repetitive work, and greatly saves time and labor costs.

[0137] Example 3

[0138] In a specific embodiment of the present disclosure, a test device for an intelligent driving system is provided. The test device is applied to a test end, such as Figure 5 As shown, the test device includes a collection module 101, a configuration acquisition module 102, a test data transmission module 103 and a test module 104;

[0139] The acquisition module 101 is used to acquire original drive test data;

[0140] The configuration acquisition module 102 is used to obtain transmission configuration data corresponding to the target test scenario;

[0141] The test data transmission module 103 is used to filter the target transmission data in the original drive test data based on the transmission configuration data, and feed the target transmission data back to the tested end via the Ethernet transmission gateway for the intelligent driving system to respond;

[0142] The test data transmission module 103 is also used to receive target response data of the intelligent driving system returned by the tested end via the Ethernet transmission gateway, where the target response data is obtained by filtering the response data of the intelligent driving system based on the transmission configuration data;

[0143] The testing module 104 is used to test the intelligent driving system according to the target response data to obtain the test result of the intelligent driving system.

[0144] In a specific implementation, the acquisition module 101 is further used to split the original drive test data into different drive test data packets according to different test scenarios;

[0145] The test data transmission module 103 is also used to obtain a target road test data packet according to a target test scenario; filter the target transmission data in the target road test data packet based on the transmission configuration data; and sequentially feed the target transmission data back to the tested end via the Ethernet transmission gateway according to the configured transmission rate for the intelligent driving system to respond.

[0146] In a specific implementation, the test data transmission module 103 is also used to obtain scenario configuration data corresponding to the target test scenario; filter the target scenario data in the target road test data packet according to the scenario configuration data, and record and generate the target scenario data packet; and filter the target transmission data in the target scenario data packet based on the transmission configuration data.

[0147] In a specific implementation, the scene configuration data includes at least one of a data type and a transmission rate.

[0148] In a specific implementation, the test module 104 is also used to obtain recording configuration data corresponding to the target test scenario; filter the target recording data in the target response data based on the recording configuration data, and generate a recording data packet; use the test script to perform offline testing on the recording data packet to obtain the test results of the intelligent driving system.

[0149] In a specific implementation, the acquisition module 101 is further used to perform true value annotation and data extraction on the original drive test data to obtain true value drive test data; split the true value drive test data into different true value data packets according to different test scenarios;

[0150] The test module 104 is also used to obtain a target true value data packet corresponding to a target test scenario; perform scene alignment processing on the recorded data packet and the target true value data packet, and match the first timestamp of each target recorded data in the recorded data packet with the second timestamp of each true value data in the target true value data packet to obtain actual response data and expected true value data; use a test script to test the actual response data and the expected true value data to obtain a test result of the intelligent driving system.

[0151] In a specific implementation, the transmission configuration data includes a data type and at least one of a data name under the data type, a data sending end, a data receiving end, and a data transmission mode.

[0152] As for the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The system embodiment described above is only illustrative, wherein the units described as separate components may or may not be physically separated, and the components as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution.

[0153] This embodiment does not rely on the data transmission board, has low requirements on the software and hardware environment of the equipment, greatly saves testing costs, does not occupy the storage space of the domain controller, ensures the integrity of the test data, saves the time of manually or automatically copying the output data of the domain controller during the bench re-injection test, avoids the inaccurate test conclusions caused by incomplete verification, and improves the test efficiency. The batch re-injection script is suitable for different projects and different intelligent driving software versions, avoids repetitive work, and greatly saves time and labor costs.

[0154] Example 4

[0155] In a specific embodiment of the present disclosure, a test device for an intelligent driving system is provided. The test device is applied to a tested end, such as Figure 6 As shown, the test device includes a response data transmission module 201 and a data acquisition module 202;

[0156] The response data transmission module 201 is used to receive target transmission data fed back via the Ethernet transmission gateway, where the target transmission data is obtained by filtering the original drive test data based on the transmission configuration data of the target test scenario;

[0157] The data acquisition module 202 is used to acquire response data output by the intelligent driving system based on the target transmission data;

[0158] The response data transmission module 201 is also used to filter the target response data in the response data according to the transmission configuration data, and transmit the target response data to the test end via the Ethernet transmission gateway to test the intelligent driving system.

[0159] As for the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The system embodiment described above is only illustrative, wherein the units described as separate components may or may not be physically separated, and the components as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution.

[0160] This embodiment does not rely on the data transmission board, has low requirements on the software and hardware environment of the equipment, greatly saves testing costs, does not occupy the storage space of the domain controller, ensures the integrity of the test data, saves the time of manually or automatically copying the output data of the domain controller during the bench re-injection test, avoids the inaccurate test conclusions caused by incomplete verification, and improves the test efficiency. The batch re-injection script is suitable for different projects and different intelligent driving software versions, avoids repetitive work, and greatly saves time and labor costs.

[0161] Example 5

[0162] In a specific embodiment of the present disclosure, a test bench for an intelligent driving system is provided, the test bench comprising a testing end and a tested end;

[0163] The test end includes the test device of the intelligent driving system of Example 3;

[0164] The tested end includes the testing device of the intelligent driving system of Example 4.

[0165] Specifically, the test bench of the intelligent driving system can be used to implement the test method of the intelligent driving system in Example 1 alone, can be used to implement the test method of the intelligent driving system in Example 2 alone, and can also be used to jointly implement the test methods of the intelligent driving systems in Example 1 and Example 2.

[0166] like Figure 7As shown, the test end can be a PC end, in which a data playback node, a data transmission node, a data recording node and a test node are set; the tested end can be a domain controller end, in which a data transmission node and an intelligent driving system integrated in the domain controller end are set, and the test end and the tested end realize data (msgs) transmission through the data transmission node via the Ethernet transmission gateway to complete the test of the intelligent driving system. Among them, different nodes transmit different data. The specific functions of each node in the PC end and the domain controller end and the transmitted data can be referred to the relevant descriptions in Example 1 and Example 2, which will not be repeated here.

[0167] It should be noted that this embodiment takes the intelligent driving system as an example, but is not limited to this.

[0168] This embodiment does not rely on the data transmission board, has low requirements on the software and hardware environment of the equipment, greatly saves testing costs, does not occupy the storage space of the domain controller, ensures the integrity of the test data, saves the time of manually or automatically copying the output data of the domain controller during the bench re-injection test, avoids the inaccurate test conclusions caused by incomplete verification, and improves the test efficiency. The batch re-injection script is suitable for different projects and different intelligent driving software versions, avoids repetitive work, and greatly saves time and labor costs.

[0169] Example 6

[0170] Figure 8 This is a structural schematic diagram of an electronic device shown in an example embodiment of the present disclosure, the electronic device includes a memory, a processor, and a computer program stored in the memory and used to run on the processor, and when the processor executes the computer program, the test method of the intelligent driving system described in any of the above embodiments is implemented. Figure 8 The electronic device 30 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0171] like Figure 8 As shown, the electronic device 30 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 30 may include, but are not limited to: at least one processor 31, at least one memory 32, and a bus 33 connecting different system components (including the memory 32 and the processor 31).

[0172] The bus 33 includes a data bus, an address bus, and a control bus.

[0173] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 322 , and may further include a read only memory (ROM) 323 .

[0174] The memory 32 may also include a program tool 325 (or utility) having a set (at least one) of program modules 324, such program modules 324 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0175] The processor 31 executes various functional applications and data processing by running the computer program stored in the memory 32, such as the test method of the intelligent driving system provided in any of the above embodiments.

[0176] The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 35. Furthermore, the electronic device 30 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 36. As shown, the network adapter 36 communicates with other modules of the electronic device 30 via a bus 33. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0177] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0178] Example 7

[0179] An embodiment of the present disclosure also provides a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the test method of the intelligent driving system provided in any of the above embodiments is implemented.

[0180] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0181] Example 8

[0182] An embodiment of the present disclosure also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for testing an intelligent driving system.

[0183] Among them, the program code for executing the computer program product of the present disclosure can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device, partially on the remote device, or completely on the remote device. Although the specific implementation of the present disclosure is described above, it should be understood by those skilled in the art that this is only an example, and the scope of protection of the present disclosure is defined by the attached claims. Those skilled in the art can make various changes or modifications to these implementations without departing from the principles and essence of the present disclosure, but these changes and modifications all fall within the scope of protection of the present disclosure.

Claims

1. A testing method for an intelligent driving system, characterized in that: The test method is applied to the test end, and the test method includes: Collect original drive test data; Obtain the transmission configuration data corresponding to the target test scenario; Filtering target transmission data in the original drive test data based on the transmission configuration data, and feeding the target transmission data back to the tested end via the Ethernet transmission gateway, so that the intelligent driving system at the tested end can respond; receiving target response data of the intelligent driving system returned by the tested end via the Ethernet transmission gateway, wherein the target response data is obtained by filtering the response data of the intelligent driving system based on the transmission configuration data; The intelligent driving system is tested according to the target response data to obtain a test result of the intelligent driving system.

2. The testing method according to claim 1, characterized in that: After the step of collecting original drive test data, the test method further includes: Splitting the original drive test data into different drive test data packets according to different test scenarios; The step of filtering the target transmission data in the original drive test data based on the transmission configuration data, and feeding the target transmission data back to the tested end via the Ethernet transmission gateway for the intelligent driving system to respond includes: Acquire a target drive test data packet according to the target test scenario; Filtering the target transmission data in the target drive test data packet based on the transmission configuration data; According to the configured transmission rate, the target transmission data is sequentially fed back to the tested end via the Ethernet transmission gateway for the intelligent driving system to respond.

3. The testing method according to claim 2, characterized in that: The step of screening the target transmission data in the target drive test data packet based on the transmission configuration data comprises: Obtaining scenario configuration data corresponding to the target test scenario; Filtering the target scenario data in the target drive test data packet according to the scenario configuration data, and recording and generating the target scenario data packet; The target transmission data in the target scenario data packet is filtered based on the transmission configuration data.

4. The testing method according to claim 3, characterized in that: The scene configuration data includes at least one of a data type and the transmission rate.

5. The testing method according to claim 1, characterized in that: The step of testing the intelligent driving system according to the target response data to obtain the test result of the intelligent driving system comprises: Obtaining recording configuration data corresponding to the target test scenario; Filtering target recording data in the target response data based on the recording configuration data, and generating a recording data packet; The recorded data packet is tested offline using a test script to obtain the test result of the intelligent driving system.

6. The testing method according to claim 5, characterized in that: After the step of collecting original drive test data, the test method further includes: Performing true value annotation and data extraction on the original drive test data to obtain true value drive test data; Splitting the true value drive test data into different true value data packets according to different test scenarios; The step of performing offline testing on the recorded data packet using a test script to obtain the test result of the intelligent driving system comprises: Obtaining a target true value data packet corresponding to the target test scenario; Performing scene alignment processing on the recorded data packet and the target true value data packet, and matching the first timestamp of each target recorded data in the recorded data packet with the second timestamp of each true value data in the target true value data packet, to obtain actual response data and expected true value data; The actual response data and the expected true value data are tested using the test script to obtain the test result of the intelligent driving system.

7. The testing method according to any one of claims 1 to 6, characterized in that: The transmission configuration data includes a data type and at least one of a data name under the data type, a data sending end, a data receiving end, and a data transmission mode.

8. A method for testing an intelligent driving system, characterized in that: The test method is applied to the tested end, and the test method includes: Receiving target transmission data fed back via the Ethernet transmission gateway, wherein the target transmission data is obtained by filtering original drive test data based on transmission configuration data of a target test scenario; Acquire response data output by the intelligent driving system based on the target transmission data; The target response data in the response data is filtered according to the transmission configuration data, and the target response data is transmitted to the test end via the Ethernet transmission gateway so that the test end can test the intelligent driving system.

9. A testing device for an intelligent driving system, characterized in that: The test device is applied to the test end, and the test device includes a collection module, a configuration acquisition module, a test data transmission module and a test module; The acquisition module is used to acquire original drive test data; The configuration acquisition module is used to obtain transmission configuration data corresponding to the target test scenario; The test data transmission module is used to filter the target transmission data in the original drive test data based on the transmission configuration data, and feed the target transmission data back to the tested end via the Ethernet transmission gateway for the intelligent driving system to respond; The test data transmission module is further used to receive target response data of the intelligent driving system returned by the tested end via the Ethernet transmission gateway, wherein the target response data is obtained by screening the response data of the intelligent driving system based on the transmission configuration data; The testing module is used to test the intelligent driving system according to the target response data to obtain a test result of the intelligent driving system.

10. A testing device for an intelligent driving system, characterized in that: The test device is applied to the tested end, and the test device includes a response data transmission module and a data acquisition module; The response data transmission module is used to receive target transmission data fed back via the Ethernet transmission gateway, wherein the target transmission data is obtained by filtering the original drive test data based on the transmission configuration data of the target test scenario; The data acquisition module is used to acquire response data output by the intelligent driving system based on the target transmission data; The response data transmission module is also used to filter target response data in the response data according to the transmission configuration data, and transmit the target response data to the test end via the Ethernet transmission gateway to test the intelligent driving system.

11. A test bench for an intelligent driving system, characterized in that: The test bench comprises a testing end and a tested end; The test end includes the test device of the intelligent driving system according to claim 9; The tested end includes the testing device of the intelligent driving system as claimed in claim 10.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and used to run on the processor, characterized in that: When the processor executes the computer program, the test method of the intelligent driving system according to any one of claims 1 to 8 is implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the test method of the intelligent driving system according to any one of claims 1 to 8 is implemented.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the test method of the intelligent driving system according to any one of claims 1 to 8 is implemented.

Images