An autonomous driving event testing method, system, device, and medium

Abstract

The application provides an automatic driving event testing method, system, device and medium, the method comprising: acquiring a current scene parameter, triggering an automatic driving event and collecting an event message of the automatic driving event when the current scene parameter meets a preset automatic driving triggering scene; uploading the event message to the cloud to make the cloud compare the event message with a corresponding standard message stored in advance to obtain a comparison result; and determining an execution state of automatic driving according to the comparison result. The application can quickly and efficiently complete automatic driving testing.

Description

Technical Field

[0001] This application relates to the field of autonomous driving applications, and in particular to an autonomous driving event testing method, system, device, and medium. Background Technology

[0002] With the rise of autonomous driving technology, more and more users are willing to accept the convenience it brings. However, we know that autonomous driving cannot completely replace human driving behavior at this stage. For example, when encountering situations that the autonomous driving system cannot handle, the system may have already alerted the user to take over, but an accident may still occur. To clarify the situation at that time, the collection and uploading of autonomous driving event data to the cloud becomes particularly important, as it can be used to support the analysis of the vehicle's condition when a potential hazard occurs. Testing with real vehicles is too risky and detrimental to personal safety. Using simulated triggering automated testing can help mitigate risks and improve testing efficiency.

[0003] Comparing this to patent number CN202111453982.6, which discloses a method for testing big data cloud migration based on an in-vehicle Ethernet architecture, the present invention provides a method for testing big data cloud migration based on an in-vehicle Ethernet architecture including APA, GW, ADS, FC, and THU. The big data cloud migration test includes four test dimensions, which are performed sequentially as follows: data integrity rate test; data accuracy rate test; data success rate test; and data migration time test. This invention performs cloud migration testing from the above four dimensions, effectively and fully verifying the quality of big data cloud migration using the Ethernet architecture.

[0004] The patent descriptions above describe the dimensions from which data is tested in the cloud, but they do not establish automated testing in the testing system, thus failing to effectively improve testing efficiency. Summary of the Invention

[0005] In view of the problems existing in the prior art, this application proposes an autonomous driving event testing method, system, device and medium, which mainly solves the problems that existing autonomous driving testing methods are difficult to automate and have low testing efficiency.

[0006] To achieve the above and other objectives, the technical solution adopted in this application is as follows.

[0007] This application provides a method for testing autonomous driving events, including:

[0008] Obtain the current scene parameters, and when the current scene parameters meet the preset autonomous driving trigger scenario, trigger an autonomous driving event and collect the event message of the autonomous driving event;

[0009] The event message is uploaded to the cloud so that the cloud can compare the event message with the pre-stored corresponding standard message to obtain the comparison result;

[0010] The execution status of autonomous driving is determined based on the comparison results.

[0011] In one embodiment of this application, before obtaining the current scene parameters, the method further includes:

[0012] Obtain historical scene parameters when historical autonomous driving events were triggered;

[0013] The historical scene parameters are associated with the historical autonomous driving events and stored in a preset scene library as preset autonomous driving trigger scenarios, so as to determine whether the current scene parameters meet the preset autonomous driving trigger scenarios based on the historical scene parameters in the preset scene library.

[0014] In one embodiment of this application, the historical scene parameters are associated with the historical autonomous driving events and stored in a preset scene library, including:

[0015] The historical scene parameters are reported to the cloud by calling the cloud interface. The cloud then associates and stores the historical scene parameters with the corresponding historical autonomous driving events. The historical scene parameters include: road signals, driving targets, obstacles, and traffic signs.

[0016] In one embodiment of this application, after associating and storing the historical scene parameters with the corresponding historical autonomous driving events in the cloud, the method further includes:

[0017] Historical messages during the execution of each historical autonomous driving event are obtained through the cloud.

[0018] Historical messages corresponding to historical autonomous driving events without anomaly indicators are stored as standard messages, wherein the anomaly indicators are generated based on the anomaly signals fed back by the vehicle during autonomous driving.

[0019] In one embodiment of this application, triggering the autonomous driving event further includes:

[0020] Obtain the transition state of the CAN signal when an autonomous driving event is triggered within a preset historical time period;

[0021] The transition states of the CAN signal are associated with and stored with autonomous driving events, so as to trigger the corresponding autonomous driving events by simulating the transition states of the CAN signal.

[0022] This application also provides an autonomous driving event testing system, including:

[0023] The event triggering module is used to obtain the current scene parameters, and when the current scene parameters meet the preset autonomous driving triggering scenario, to trigger an autonomous driving event and collect the event message of the autonomous driving event;

[0024] The test comparison module is used to upload the event message to the cloud, so that the cloud can compare the event message with the pre-stored corresponding standard message to obtain the comparison result;

[0025] The result output module is used to determine the execution status of autonomous driving based on the comparison results.

[0026] In one embodiment of this application, the system further includes: a scene parameter recognition module, used to classify and recognize scene parameters based on scene images collected by the vehicle, wherein the scene parameters include: road signals, physical objects, obstacles, and traffic signs.

[0027] In one embodiment of this application, the system further includes: an in-vehicle communication module, used to upload messages, images or videos collected by the vehicle to the cloud.

[0028] This application also provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the autonomous driving event testing method.

[0029] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the autonomous driving event testing method described above.

[0030] As described above, the autonomous driving event testing method of this application has the following beneficial effects.

[0031] This application triggers autonomous driving through scene parameters and collects event messages, which are then uploaded to the cloud. The cloud-stored messages are compared with standard messages of normal autonomous driving events to determine whether the currently triggered autonomous driving time is running normally, thus completing autonomous driving testing quickly and efficiently. Attached Figure Description

[0032] Figure 1 This is a schematic diagram of the overall architecture of autonomous driving event testing in one embodiment of this application.

[0033] Figure 2 This is a flowchart illustrating an autonomous driving event testing method in one embodiment of this application.

[0034] Figure 3 This is a block diagram of an autonomous driving event testing system according to one embodiment of this application.

[0035] Figure 4This is a schematic diagram of the device in one embodiment of this application. Detailed Implementation

[0036] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0037] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0038] Terminology Explanation:

[0039] APA - Automatic Parking System Controller; ADAS - Autonomous Driving System Controller; FC - Front Camera Controller; THU - In-vehicle Entertainment Terminal with Communication Function.

[0040] Please see Figure 1 , Figure 1 This is a schematic diagram of the overall architecture for autonomous driving event testing in one embodiment of this application. The testing architecture of this embodiment includes: a scenario simulation system, an autonomous driving system, a vehicle-mounted THU system, a test management software system, a cloud data interface system, and an automated test management software system. The scenario simulation system is used to simulate the scenarios required to trigger autonomous driving events. One scenario is a scenario created using scenario simulation software that enables the autonomous driving controller system to ideally identify road information, driving targets, obstacles, traffic signs, etc., and transmit the collected data to the autonomous driving system to support the triggering of autonomous driving events. For example, when recognizing traffic lights, the simulation software can use instructions to simulate triggering the FC controller of the autonomous driving system to recognize traffic light information. Another scenario is simulating CAN messages to trigger some easily triggered autonomous driving events, such as emergency collision events, by setting the CAN message of the collision event to a collision state and then restoring it to a non-collision state.

[0041] The autonomous driving system is used for real-time data acquisition and to determine whether an autonomous driving event has been triggered. When an event is detected, the ADAS, APA, and FC controllers can collect and cache the CAN message data, images, and videos of the event according to the acquisition rules. After the acquisition is completed, the event message of the corresponding event is sent to the vehicle's THU system to be uploaded to the cloud. After receiving the pull command from the cloud, the data of the event is provided for uploading.

[0042] The vehicle-mounted THU system is used to receive autonomous driving event messages forwarded from the gateway by the autonomous driving system, and to provide the mobile network to upload the event messages to the cloud. Then, it receives pull instructions from the cloud to actively upload or passively pull the data of the autonomous driving event.

[0043] The test management software system monitors and analyzes the status of CAN messages of the autonomous driving system and the vehicle's THU system. It can be called by the automated test management software system, allowing the automated test software system to monitor the changes in CAN messages of the vehicle's THU system and the autonomous driving system in real time, thereby confirming whether the autonomous driving event has been successfully triggered as expected.

[0044] The cloud-based data interface system, acting as the main entity for file retrieval and management, will be responsible for judging autonomous driving event messages based on file retrieval rules. When it is determined that a file needs to be retrieved, a retrieval task will be issued to retrieve the corresponding autonomous driving event and store it in the cloud. It will also provide a data interface for the automated testing software system to query information such as the name, upload time, upload format, and retrieval logs of autonomous driving events, thereby determining whether corresponding data has been uploaded to the cloud after the autonomous driving system triggers an autonomous driving event.

[0045] The automated test management software system is the core step in achieving automation in the entire test system. By calling the scenario simulation software system and the test management software system, it establishes automated test case tasks and monitors the test execution process. It also calls the cloud data interface to compare the information with the preset autonomous driving events to determine whether the current autonomous driving event is running as expected, thus forming a closed-loop verification of the entire chain.

[0046] Based on the above testing architecture, this application also provides an autonomous driving event testing method. The autonomous driving event testing method will be described in detail below with reference to specific embodiments.

[0047] Please see Figure 2 This application provides a method for testing autonomous driving events, which includes the following steps:

[0048] Step S200: Obtain the current scene parameters. When the current scene parameters meet the preset autonomous driving triggering scenario, trigger an autonomous driving event and collect the event message of the autonomous driving event.

[0049] In one embodiment, before obtaining the current scene parameters, the method further includes:

[0050] Obtain historical scene parameters when historical autonomous driving events were triggered;

[0051] The historical scene parameters are associated with the historical autonomous driving events and stored in a preset scene library as preset autonomous driving trigger scenarios, so as to determine whether the current scene parameters meet the preset autonomous driving trigger scenarios based on the historical scene parameters in the preset scene library.

[0052] Specifically, it is possible to obtain autonomous driving event records for a period of time prior to the current point in time, and extract historical scene parameters from these records when the corresponding historical autonomous driving events were triggered. These scene parameters may include road information, driving targets, obstacles, traffic signs, etc. Furthermore, the historical scene parameters can be associated and stored with the corresponding autonomous driving events.

[0053] In one embodiment, the historical scene parameters are associated with the historical autonomous driving events and stored in a preset scene library, including:

[0054] The historical scene parameters are reported to the cloud by calling the cloud interface. The cloud then associates and stores the historical scene parameters with the corresponding historical autonomous driving events. The historical scene parameters include: road signals, driving targets, obstacles, and traffic signs.

[0055] In one embodiment, after the vehicle obtains historical scene parameters through camera equipment, image recognition engine, etc., it can upload historical autonomous driving events and corresponding historical scene parameters to the cloud for associated storage. Alternatively, the cloud can create a periodic task to retrieve the corresponding historical autonomous driving events and historical scene parameters from the vehicle for associated storage. The historical scene parameters are then used as trigger scenarios for subsequent autonomous driving.

[0056] In one embodiment, after associating and storing the historical scene parameters with the corresponding historical autonomous driving events in the cloud, the method further includes:

[0057] Historical messages during the execution of each historical autonomous driving event are obtained through the cloud.

[0058] Historical messages corresponding to historical autonomous driving events without anomaly indicators are stored as standard messages, wherein the anomaly indicators are generated based on the anomaly signals fed back by the vehicle during autonomous driving.

[0059] Specifically, after obtaining historical autonomous driving events and corresponding historical scene parameters, the cloud can trigger a retrieval task to retrieve historical event messages when the vehicle triggers an autonomous driving event. The cloud parses the historical messages, and if the historical messages do not contain information such as anomaly identification codes, it considers the corresponding historical messages to be messages from when autonomous driving is executed normally. The cloud then stores the messages from when autonomous driving is executed normally in the cloud as standard messages for the corresponding autonomous driving events.

[0060] In another embodiment, triggering the autonomous driving event further includes:

[0061] Obtain the transition state of the CAN signal when an autonomous driving event is triggered within a preset historical time period;

[0062] The transition states of the CAN signal are associated with and stored with autonomous driving events, so as to trigger the corresponding autonomous driving events by simulating the transition states of the CAN signal.

[0063] Specifically, testers can collect the CAN signal transition status at the moment each autonomous driving event is triggered through the vehicle-side system, and then simulate the CAN signal transitions at the moment different autonomous driving events are triggered. Simply inputting the simulated CAN signal into the vehicle's infotainment system will trigger the corresponding autonomous driving event. Whether the test is triggered by scenario parameters or by simulated CAN signals can be chosen according to actual application requirements; there are no restrictions here.

[0064] Step S210: Upload the event message to the cloud so that the cloud can compare the event message with the pre-stored corresponding standard message to obtain the comparison result.

[0065] In one embodiment, after an autonomous driving event is triggered, the vehicle executes autonomous driving-related actions and reports the execution process data to the cloud in the form of an event message. Upon receiving the event message for the current autonomous driving event, the cloud can compare the event message with the standard message obtained in the aforementioned steps to determine whether the current autonomous driving event has been executed normally.

[0066] Step S220: Determine the execution state of autonomous driving based on the comparison results.

[0067] In one embodiment, if the autonomous driving event is determined to be executed normally based on the current event message, the test passes; otherwise, the test fails.

[0068] Based on the above technical solutions, scenario parameters can be constructed or invoked as needed to trigger corresponding autonomous driving events. Testing and testing process monitoring can be automatically completed based on cloud-stored data, thereby improving testing efficiency.

[0069] Please see Figure 3This embodiment provides an autonomous driving event testing system for executing the autonomous driving event testing method described in the foregoing method embodiments. Since the technical principles of the system embodiment are similar to those of the foregoing method embodiments, the same technical details will not be repeated.

[0070] In one embodiment, an autonomous driving event testing system includes: an event triggering module 10, configured to acquire current scene parameters, and when the current scene parameters satisfy a preset autonomous driving triggering scenario, trigger an autonomous driving event and collect event messages of the autonomous driving event; a test comparison module 11, configured to upload the event messages to the cloud, so that the cloud compares the event messages with pre-stored corresponding standard messages to obtain comparison results; and a result output module 12, configured to determine the execution state of autonomous driving based on the comparison results.

[0071] In one embodiment, the system further includes a scene parameter recognition module, used to classify and recognize scene parameters based on scene images collected by the vehicle, wherein the scene parameters include: road signals, physical objects, obstacles, and traffic signs.

[0072] In one embodiment, the system further includes: an in-vehicle communication module for uploading messages, images, or videos collected by the vehicle to the cloud.

[0073] This application also provides an autonomous driving event testing device, which may include: one or more processors; and one or more machine-readable media storing instructions thereon, which, when executed by the one or more processors, cause the device to perform... Figure 1 The method described herein. In practical applications, the device can function as a terminal device or a server. Examples of terminal devices include: smartphones, tablets, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptops, in-vehicle computers, desktop computers, set-top boxes, smart TVs, wearable devices, etc. This application does not limit the specific devices described.

[0074] This application also provides a machine-readable medium storing one or more modules (programs) that, when applied to a device, enable the device to execute embodiments of this application. Figure 1The instructions for the steps included in the autonomous driving event testing method. Machine-readable media can be any usable medium that a computer can store, or a data storage device such as a server or data center that integrates one or more usable media. The usable medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

[0075] See Figure 4 This embodiment provides a device 80, which can be a desktop computer, a portable computer, a smartphone, or other devices. Specifically, the device 80 includes at least a memory 82 and a processor 83 connected via a bus 81. The memory 82 stores a computer program, and the processor 83 executes the computer program stored in the memory 82 to perform all or part of the steps in the aforementioned method embodiments.

[0076] The system bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus. The communication interface is used to enable communication between the database access device and other devices (e.g., clients, read-write libraries, and read-only libraries). Memory may include Random Access Memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0077] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0078] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. An automated driving event testing method, characterized by, The method comprises the following steps: obtaining current scene parameters, and triggering an automatic driving event and collecting an event message of the automatic driving event when the current scene parameters meet a preset automatic driving triggering scene; triggering the automatic driving event further comprises: obtaining a jump state of a CAN signal when the automatic driving event is triggered in a preset historical time period; and storing the jump state of the CAN signal in association with the automatic driving event, so as to trigger a corresponding automatic driving event by simulating the jump state of the CAN signal; uploading the event message to a cloud end, so that the cloud end compares the event message with a corresponding standard message stored in advance to obtain a comparison result; determining an execution state of the automatic driving according to the comparison result.

2. The method of claim 1, wherein, Before obtaining the current scene parameters, the method further comprises the following steps: obtaining historical scene parameters when a historical automatic driving event is triggered; associating the historical scene parameters with the historical automatic driving event and storing them in a preset scene library as the preset automatic driving triggering scene, so as to determine whether the current scene parameters meet the preset automatic driving triggering scene based on the historical scene parameters in the preset scene library.

3. The method of claim 2, wherein, associating the historical scene parameters with the historical automatic driving event and storing them in the preset scene library comprises: calling the cloud end interface to report the historical scene parameters to the cloud end, and storing the historical scene parameters in association with the corresponding historical automatic driving event through the cloud end, wherein the historical scene parameters comprise road signals, driving targets, obstacles and traffic signs.

4. The method of claim 3, wherein, After storing the historical scene parameters in association with the corresponding historical automatic driving event through the cloud end, the method further comprises the following steps: obtaining historical messages in the execution process of each historical automatic driving event through the cloud end; storing historical messages corresponding to historical automatic driving events without an abnormal identifier as standard messages, wherein the abnormal identifier is generated based on an abnormal signal fed back by a vehicle end during the automatic driving process.

5. An automated driving event testing system characterized by, The method comprises the following steps: an event triggering module is configured to obtain current scene parameters, and trigger an automatic driving event and collect an event message of the automatic driving event when the current scene parameters meet a preset automatic driving triggering scene; triggering the automatic driving event further comprises: obtaining a jump state of a CAN signal when the automatic driving event is triggered in a preset historical time period; and storing the jump state of the CAN signal in association with the automatic driving event, so as to trigger a corresponding automatic driving event by simulating the jump state of the CAN signal; a test comparison module is configured to upload the event message to a cloud end, so that the cloud end compares the event message with a corresponding standard message stored in advance to obtain a comparison result; a result output module is configured to determine an execution state of the automatic driving according to the comparison result.

6. The automated driving event testing system of claim 5, wherein, The system further comprises a scene parameter identification module configured to perform scene parameter classification and identification based on a scene image collected by a vehicle end, wherein the scene parameters comprise road signals, driving targets, obstacles and traffic signs.

7. The automated driving event testing system of claim 5, wherein, The system further comprises a vehicle-mounted communication module configured to upload a message, a picture or a video collected by the vehicle end to the cloud end.

8. A computer device comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of the automatic driving event test method of any one of claims 1 to 4.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the automatic driving event test method of any one of claims 1 to 4.

Images