Method, device, equipment and readable storage medium for extracting false trigger scene information

Abstract

The present application relates to a method, apparatus, device and readable storage medium for extracting false trigger scene information, and relates to the field of vehicle testing technology. The method obtains scene data corresponding to historical abnormal braking scenes, including vehicle CAN data, radar CAN data and camera data; when it is determined that AEB is in a working state, scene extraction and analysis is performed based on the radar CAN data to extract each scene target and its corresponding first target type that triggered the historical abnormal braking scene; the type of each scene target is identified based on the azimuth angle of the scene target and the camera data to obtain the second target type corresponding to each scene target; if the first target type and the second target type are inconsistent, the scene information corresponding to the scene target is extracted from the scene data as false trigger scene information to form a false trigger scene library, thereby providing data support for subsequent bench verification and vehicle testing, shortening the verification cycle and improving R&D efficiency.

Description

Technical Field

[0001] The present application relates to the field of vehicle testing technology, and in particular to a method, device, equipment and readable storage medium for extracting false triggering scene information. Background Art

[0002] With the development and popularization of automatic emergency braking (AEB) technology, false triggering of AEB systems has become increasingly prominent in vehicles, especially in single-radar solutions. This false triggering can lead to a poor user experience and, in severe cases, can cause financial or personal damage. Therefore, preventing or reducing the occurrence of false AEB triggering has become a critical issue for engineers. Fully verifying the reliability of AEB systems in actual vehicles is an effective way to prevent or reduce false AEB triggering.

[0003] However, current public road tests for real vehicles all rely on random verification of the AEB system, requiring extensive road testing. This not only requires significant time and cost, but also suffers from long cycles and poor targeting. Furthermore, the system can only verify false trigger scenarios under expected ideal operating conditions, resulting in poor integrity and an inability to effectively guarantee the reliability of the AEB system. Therefore, effectively extracting AEB false trigger scenario data to provide data support for rapid and limited verification of the AEB system's reliability is an urgent issue that needs to be addressed. Summary of the Invention

[0004] The present application provides a method, device, equipment and readable storage medium for extracting false trigger scene information, so as to effectively realize the extraction of AEB false trigger scene data, provide data support for the rapid limited verification of AEB reliability, thereby shortening the verification cycle and improving the integrity of false trigger scene verification.

[0005] In a first aspect, a method for extracting false triggering scene information is provided, comprising the following steps:

[0006] Acquire scene data corresponding to historical abnormal braking scenes, wherein the scene data includes vehicle CAN data, radar CAN data, and camera data;

[0007] When the vehicle CAN data confirms that the automatic emergency braking system AEB is in an active state, a scene extraction analysis is performed based on the radar CAN data to extract each scene target that triggered the historical abnormal braking scene and its corresponding first target type;

[0008] Performing type identification on each scene target according to the azimuth angle of the scene target and the camera data to obtain a second target type corresponding to each scene target;

[0009] For each scene target, if the first target type and the second target type are inconsistent, scene information corresponding to the scene target is extracted from the scene data as false trigger scene information to form a false trigger scene library.

[0010] In some embodiments, performing scene extraction and analysis based on radar CAN data to extract each scene target that triggers the historical abnormal braking scene and its corresponding first target type includes:

[0011] Extracting all candidate targets that may trigger historical abnormal braking scenarios and their corresponding target information from the radar CAN data, the target information including target type information, collision time information, azimuth information, distance information, and speed information;

[0012] For each candidate target, determining whether the candidate target will collide with the vehicle in the longitudinal direction according to the collision time information;

[0013] If the candidate target is likely to collide with the vehicle in the longitudinal direction, the safe area where the candidate target is located is determined based on the azimuth information and the distance information;

[0014] Determining whether the candidate target is the target that triggered the historical abnormal braking scenario based on the preset speed limit, speed information, collision time information corresponding to the safety zone where the candidate target is located, and the safety zone where the vehicle is located;

[0015] If so, the candidate target is used as the scene target.

[0016] In some embodiments, the safety zone includes a left area, a middle area, and a right area, and the vehicle is located in the middle area. Determining the safety zone where the candidate target is located based on the azimuth information and the distance information includes:

[0017] When it is determined based on the azimuth information that the candidate target is located on the left side of the vehicle, if the lateral distance between the candidate target and the vehicle is greater than the first distance between the right sideline of the left area and the left side of the vehicle, then the safe area where the candidate target is located is determined to be the left area;

[0018] When it is determined based on the azimuth information that the candidate target is located on the right side of the vehicle, if the lateral distance between the candidate target and the vehicle is greater than the second distance between the left sideline of the right area and the right side of the vehicle, then the safe area where the candidate target is located is determined to be the right area;

[0019] When it is determined according to the azimuth information that the candidate target is located in front of or behind the vehicle, the safe area where the candidate target is located is determined to be the middle area.

[0020] In some embodiments, the candidate target is in a left area and the preset speed limit in the left area is a lateral speed less than 0. Determining whether the candidate target is a target that triggers a historical abnormal braking scenario based on the preset speed limit corresponding to the safety area where the candidate target is located, speed information, collision time information, and the safety area where the host vehicle is located includes:

[0021] Determine whether the lateral speed of the candidate target is less than 0;

[0022] If so, determine whether the candidate target will enter the middle area after the collision time is reached;

[0023] If the candidate target will enter the middle area, the candidate target is determined to be the target that triggers the historical abnormal braking scenario.

[0024] In some embodiments, the candidate target is in a middle zone and the preset speed limit in the middle zone is a lateral speed equal to 0. Determining whether the candidate target is a target that triggers a historical abnormal braking scenario based on the preset speed limit corresponding to the safety zone where the candidate target is located, speed information, collision time information, and the safety zone where the host vehicle is located includes:

[0025] Determine whether the lateral velocity of the candidate target is equal to 0;

[0026] If so, the candidate target is determined to be the target that triggered the historical abnormal braking scenario;

[0027] If not, determine whether the candidate target is still in the middle area after the collision time is reached;

[0028] If the candidate target is still in the middle area, it is determined that the candidate target is the target that triggered the historical abnormal braking scenario.

[0029] In some embodiments, if the candidate target is in a right area and the preset speed limit in the right area is a lateral speed greater than 0, determining whether the candidate target is a target that triggers a historical abnormal braking scenario based on the preset speed limit corresponding to the safety area where the candidate target is located, speed information, collision time information, and the safety area where the host vehicle is located includes:

[0030] Determine whether the lateral speed of the candidate target is greater than 0;

[0031] If so, determine whether the candidate target will enter the middle area after the collision time is reached;

[0032] If the candidate target will enter the middle area, the candidate target is determined to be the target that triggers the historical abnormal braking scenario.

[0033] In some embodiments, before the step of acquiring scene data corresponding to historical abnormal braking scenes, the method further includes:

[0034] When a historical abnormal braking scenario occurs, the scenario data corresponding to the trigger signal generated by manual control is collected.

[0035] In a second aspect, a device for extracting false triggering scene information is provided, comprising:

[0036] An acquisition unit, configured to acquire scene data corresponding to historical abnormal braking scenes, wherein the scene data includes vehicle CAN data, radar CAN data, and camera data;

[0037] an analysis unit configured to, when determining through vehicle CAN data that the automatic emergency braking system (AEB) is in an engaged state, perform scene extraction and analysis based on the radar CAN data to extract each scene target that triggered the historical abnormal braking scenario and its corresponding first target type;

[0038] an identification unit, configured to perform type identification on each scene target according to the azimuth angle of the scene target and the camera data, so as to obtain a second target type corresponding to each scene target;

[0039] The extraction unit is configured to extract, for each scene target, scene information corresponding to the scene target from the scene data as false trigger scene information if the first target type and the second target type are inconsistent, so as to form a false trigger scene library.

[0040] In a third aspect, a false trigger scene information extraction device is provided, comprising: a memory and a processor, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the aforementioned false trigger scene information extraction method.

[0041] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the aforementioned false triggering scene information extraction method is implemented.

[0042] The present application provides a method, device, equipment and readable storage medium for extracting false trigger scene information, including obtaining scene data corresponding to historical abnormal braking scenes, wherein the scene data includes vehicle CAN data, radar CAN data and camera data; when the automatic emergency braking system AEB is determined to be in working state through the vehicle CAN data, scene extraction and analysis are performed based on the radar CAN data to extract the various scene targets and their corresponding first target types that trigger the historical abnormal braking scene; each scene target is type-identified based on the azimuth angle of the scene target and the camera data to obtain the second target type corresponding to each scene target; for each scene target, if the first target type and the second target type are inconsistent, the scene information corresponding to the scene target is extracted from the scene data as false trigger scene information to form a false trigger scene library. Through the present application, a large amount of historical data in the past can be quickly analyzed to extract various specific false trigger scenes and form a false trigger scene library, providing data support for later bench verification and vehicle testing, thereby achieving targeted algorithm verification, thereby shortening the verification cycle and improving R&D efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0044] Figure 1 A flowchart of a method for extracting false triggering scene information provided in an embodiment of the present application;

[0045] Figure 2 A schematic diagram of a specific process for extracting false trigger scenario information provided in an embodiment of the present application;

[0046] Figure 3 A schematic diagram of the data acquisition structure provided in an embodiment of the present application;

[0047] Figure 4 A schematic diagram of the specific process of scene extraction and analysis provided in an embodiment of the present application;

[0048] Figure 5 A schematic diagram of the partitions provided in the embodiment of this application;

[0049] Figure 6 A structural diagram of a false triggering scene information extraction device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0051] The embodiments of the present application provide a method, device, equipment and readable storage medium for extracting false trigger scene information, so as to effectively realize the extraction of AEB false trigger scene data, provide data support for the rapid limited verification of AEB reliability, thereby shortening the verification cycle and improving the integrity of false trigger scene verification.

[0052] See also Figure 1 and Figure 2 As shown, the embodiment of the present application provides a method for extracting false triggering scene information, comprising the following steps:

[0053] Step S10: Acquire scene data corresponding to historical abnormal braking scenes, wherein the scene data includes vehicle CAN (Controller Area Network) data, radar CAN data, and camera data;

[0054] For example, in this embodiment, data acquisition equipment is used to collect scene data corresponding to historical abnormal braking scenarios. Specifically, when an abnormal braking scenario occurs, camera data, vehicle CAN data, and radar-specific CAN data within that time period are collected. Therefore, when a false trigger scenario library is needed, the collected scene data can be directly accessed for extracting false trigger scenario information.

[0055] Among them, the camera data includes data on the surrounding scenes in the front, left, right and rear directions during the vehicle's driving process, which is used for later analysis and confirmation of specific false triggering of things; the whole vehicle CAN data includes parameters such as vehicle operating parameters (such as vehicle speed, etc.) and the working status of the automatic emergency braking system (such as information used to identify whether it is in a working state) during the operation of the whole vehicle. Some of its parameters are output as scene requirements (such as some operating parameters of the vehicle), and some parameters are used for analysis of abnormal scenes as the basis for analyzing scenes; the radar's private CAN data includes the target detected by the radar in real time and its related information parameters.

[0056] Furthermore, before the step of acquiring scene data corresponding to historical abnormal braking scenes, the method further includes:

[0057] When a historical abnormal braking scenario occurs, the scenario data corresponding to the trigger signal generated by manual control is collected.

[0058] For example, in this embodiment, the collection of scene data corresponding to historical abnormal braking scenarios can be achieved by setting a trigger. Specifically, a trigger is integrated into the vehicle. When abnormal braking occurs during an actual road test, the driver can manually control the trigger to trigger a signal, causing the data acquisition equipment to record scene data before and after the trigger point, such as collecting data within 2 minutes before and 3 minutes after the trigger point. In addition, the collected scene data in this embodiment supports offline data playback, allowing data to be played back on a computer.

[0059] For details, see Figure 3 As shown in the figure, when the trigger is triggered, the data acquisition device will collect camera data (such as data from 4 cameras such as the front, left, right and rear cameras), vehicle CAN data, radar private CAN data, camera private CAN data, etc., and make the collected data available for offline playback on the data acquisition side, that is, through clock-synchronized playback, to synchronously observe various parameters at the time of false triggering.

[0060] Step S20: When it is determined through the vehicle CAN data that the automatic emergency braking system AEB is in an active state, scene extraction and analysis are performed based on the radar CAN data to extract each scene target that triggered the historical abnormal braking scene and its corresponding first target type;

[0061] For example, in this embodiment, vehicle CAN data is used to determine whether abnormal braking is caused by the emergency brake system. For example, if the AEB operating status in the vehicle CAN data is 0, indicating that the AEB is not in operation, it can be determined that the abnormal braking is not caused by the emergency brake system, and the corresponding scene data can be discarded. If the AEB operating status in the vehicle CAN data is 1, indicating that the AEB is in operation, it can be determined that the abnormal braking is caused by the emergency brake system.

[0062] After determining that AEB is in working state, scene extraction and analysis will be performed based on the targets identified by the radar in the radar CAN data and their corresponding target information to extract the various scene targets and their corresponding first target types that triggered the historical abnormal braking scene. For example, if the targets identified by the radar include target 1, target 2 and target 3, it is necessary to determine whether target 1 is the target that triggered the historical abnormal braking scene based on target 1 and the relevant information of target 1. If not, target 1 is directly eliminated and the analysis and processing of the next target continues; if so, target 1 is used as the scene target and the type of target 1 (i.e., the first target type) is directly extracted from the radar CAN data; similarly, similar analysis and processing is performed on targets 2 and 3 until all scene targets and their corresponding types are determined, thereby extracting all scene targets, relevant information of scene targets, and relevant information of the scene in which the scene targets are located (such as the speed of the vehicle, etc.).

[0063] Furthermore, the scene extraction and analysis based on the radar CAN data to extract each scene target that triggers the historical abnormal braking scene and its corresponding first target type includes:

[0064] Extracting all candidate targets that may trigger historical abnormal braking scenarios and their corresponding target information from the radar CAN data, the target information including target type information, collision time information, azimuth information, distance information, and speed information;

[0065] For each candidate target, determining whether the candidate target will collide with the vehicle in the longitudinal direction according to the collision time information;

[0066] If the candidate target is likely to collide with the vehicle in the longitudinal direction, the safe area where the candidate target is located is determined based on the azimuth information and the distance information;

[0067] Determining whether the candidate target is the target that triggered the historical abnormal braking scenario based on the preset speed limit, speed information, collision time information corresponding to the safety zone where the candidate target is located, and the safety zone where the vehicle is located;

[0068] If so, the candidate target is used as the scene target.

[0069] For example, in this embodiment, see Figure 4As shown, during the scene extraction analysis, all candidate targets identified by the radar as potentially triggering a historical abnormal braking scenario and their corresponding target information are extracted from the radar CAN data. It is understood that target information includes, but is not limited to, target type, collision time, azimuth, distance, and speed. For example, if the candidate targets include targets 1 through 5, then the target type, collision time (TTC), azimuth, distance, and relative speed (the lateral speed of the target can be determined from the relative speed) of targets 1 through 5 need to be extracted separately.

[0070] For each candidate target, a longitudinal collision judgment must first be performed based on the longitudinal TTC parameter. That is, whether the candidate target will collide with the vehicle in the longitudinal direction is determined based on whether the candidate target's collision time TTC is less than or equal to the specified collision time threshold t. Specifically, if TTC>t, it means that the candidate target will not collide with the vehicle in the longitudinal direction. In this case, the candidate target is directly eliminated and the longitudinal collision judgment continues for the next candidate target. If TTC≤t, it means that the candidate target will collide with the vehicle in the longitudinal direction. In this case, the candidate target is filtered and partitioned according to its lateral position relative to the vehicle. In other words, the safe area where the candidate target is located is determined based on the azimuth information and distance information.

[0071] After the partitioning of candidate targets is completed, the preset speed limit, speed information, collision time information corresponding to the safety area where the candidate target is located and the safety area where the vehicle is located will be used to determine whether the candidate target is the target that triggered the historical abnormal braking scenario; if the candidate target is the target that triggered the historical abnormal braking scenario, the candidate target will be used as the scene target, otherwise the candidate target will be directly eliminated.

[0072] Furthermore, the safe area includes a left area, a middle area, and a right area, and the vehicle is located in the middle area. The determining of the safe area where the candidate target is located based on the azimuth information and the distance information includes:

[0073] When it is determined based on the azimuth information that the candidate target is located on the left side of the vehicle, if the lateral distance between the candidate target and the vehicle is greater than the first distance between the right sideline of the left area and the left side of the vehicle, then the safe area where the candidate target is located is determined to be the left area;

[0074] When it is determined based on the azimuth information that the candidate target is located on the right side of the vehicle, if the lateral distance between the candidate target and the vehicle is greater than the second distance between the left sideline of the right area and the right side of the vehicle, then the safe area where the candidate target is located is determined to be the right area;

[0075] When it is determined according to the azimuth information that the candidate target is located in front of or behind the vehicle, the safe area where the candidate target is located is determined to be the middle area.

[0076] For example, see Figure 5 As shown, this embodiment divides the target into regions according to the lateral position relationship between the target and the vehicle, specifically including the left region (i.e. Figure 5 A area in the middle area (i.e. Figure 5 B in the middle) and the right side (i.e. Figure 5 Zone A is located in the safety zone on the left side of the vehicle, and the distance between the right sideline of Zone A and the left side of the vehicle is 1 / 4L (L represents the vehicle width); Zone B is located in the area directly in front of the vehicle; Zone C is located in the safety zone on the right side of the vehicle, and the distance between the left sideline of Zone C and the right side of the vehicle is 1 / 4L.

[0077] Therefore, when it is determined based on the azimuth information that the candidate target is located on the left side of the vehicle, if the lateral distance between the candidate target and the vehicle is greater than the first distance between the right side line of the left area and the left side of the vehicle (i.e., 1 / 4L), the safe area where the candidate target is located is determined to be area A; when it is determined based on the azimuth information that the candidate target is located on the right side of the vehicle, if the lateral distance between the candidate target and the vehicle is greater than the second distance between the left side line of the right area and the right side of the vehicle (i.e., 1 / 4L), the safe area where the candidate target is located is determined to be area C; when it is determined based on the azimuth information that the candidate target is located in front of or behind the vehicle, the safe area where the candidate target is located is determined to be area B.

[0078] Furthermore, if the candidate target is in a left area and the preset speed limit for the left area is a lateral speed less than 0, determining whether the candidate target is a target that triggers a historical abnormal braking scenario based on the preset speed limit corresponding to the safety area where the candidate target is located, the speed information, the collision time information, and the safety area where the host vehicle is located includes:

[0079] Determine whether the lateral speed of the candidate target is less than 0;

[0080] If so, determine whether the candidate target will enter the middle area after the collision time is reached;

[0081] If the candidate target will enter the middle area, the candidate target is determined to be the target that triggers the historical abnormal braking scenario.

[0082] For example, in this embodiment, see Figure 4As shown in the figure, after determining the area where the candidate targets are located, it will be judged whether the candidate targets in each area are the targets that triggered the historical abnormal braking scenario. Specifically, assuming that according to the partition analysis, it is determined that target 1 is located in area A and the preset speed limit corresponding to area A is a lateral speed less than 0, at this time, it will be judged whether the lateral speed V1 of target 1 is less than 0. If V1 ≥ 0, target 1 will be directly eliminated and the candidate targets in the next area will be judged. If V1 < 0, it will be further judged whether target 1 will enter area B after the TTC time. If so, target 1 will be determined to be the target that triggered the historical abnormal braking scenario. If not, target 1 will be directly eliminated and the candidate targets in the next area will be judged.

[0083] Furthermore, if the candidate target is in the middle area and the preset speed limit in the middle area is that the lateral speed is equal to 0, determining whether the candidate target is a target that triggers the historical abnormal braking scenario based on the preset speed limit corresponding to the safety area where the candidate target is located, the speed information, the collision time information, and the safety area where the host vehicle is located includes:

[0084] Determine whether the lateral velocity of the candidate target is equal to 0;

[0085] If so, the candidate target is determined to be the target that triggered the historical abnormal braking scenario;

[0086] If not, determine whether the candidate target is still in the middle area after the collision time is reached;

[0087] If the candidate target is still in the middle area, it is determined that the candidate target is the target that triggered the historical abnormal braking scenario.

[0088] For example, in this embodiment, see Figure 4 As shown, assuming that after the partition analysis, it is determined that target 3 and target 5 are located in area B and the preset speed limit corresponding to area B is that the lateral speed is equal to 0, at this time, it is judged in turn whether the lateral speed V of target 3 and target 5 is less than 0; among them, since the lateral speed V3 of target 3 = 0, it can be directly determined that target 3 is the target that triggered the historical abnormal braking scenario; and since the lateral speed V5 of target 5 ≠ 0, it is necessary to further determine whether target 5 is still in area B after the TTC time. If so, it will be determined that target 5 is the target that triggered the historical abnormal braking scenario. If not, target 5 will be directly eliminated, and the candidate targets in the next area will continue to be judged.

[0089] Furthermore, if the candidate target is in the right area and the preset speed limit for the right area is that the lateral speed is greater than 0, determining whether the candidate target is a target that triggers the historical abnormal braking scenario based on the preset speed limit corresponding to the safety area where the candidate target is located, the speed information, the collision time information, and the safety area where the host vehicle is located includes:

[0090] Determine whether the lateral speed of the candidate target is greater than 0;

[0091] If so, determine whether the candidate target will enter the middle area after the collision time is reached;

[0092] If the candidate target will enter the middle area, the candidate target is determined to be the target that triggers the historical abnormal braking scenario.

[0093] For example, in this embodiment, it is assumed that after zoning analysis, it is determined that target 4 is located in zone C and the preset speed limit corresponding to zone C is a lateral speed greater than 0. At this time, it is determined whether the lateral speed V4 of target 4 is greater than 0. If V4≤0, target 4 is directly eliminated and the next candidate target is judged; if V4>0, it is further determined whether target 4 will enter zone B after the TTC time. If so, target 4 is determined to be the target that triggered the historical abnormal braking scenario. If not, target 4 is directly eliminated and the next candidate target is judged.

[0094] Step S30: performing type identification on each scene target according to the azimuth angle of the scene target and the camera data to obtain a second target type corresponding to each scene target;

[0095] For example, in this embodiment, after scene extraction and analysis, each scene target and its type can be preliminarily determined. Further image analysis of the scene target type is then performed using the video data. Specifically, based on the azimuth of the extracted scene target, the type of the target corresponding to that azimuth is identified in the camera data. This means that the azimuth information of the scene target is used to further analyze the target information in the video data to form a target type based on the video data (i.e., a second target type).

[0096] Step S40: For each scene target, if the first target type and the second target type are inconsistent, scene information corresponding to the scene target is extracted from the scene data as false trigger scene information to form a false trigger scene library.

[0097] For example, in this embodiment, after determining the first and second target types of each scene target through scene extraction analysis and image analysis, the first and second target types are then compared to determine whether the historical abnormal braking scene is a true false triggering scene. Specifically, taking scene target 1 as an example, where the first and second target types of Target 1 are a puppy and a puppy, respectively, since the first and second target types of Target 1 are identical, the abnormal braking scene in which Target 1 is extracted is a normal scene, i.e., a braking scene resulting from a normal braking action after AEB accurately identified Target 1's type, rather than a false triggering action caused by AEB misidentification. In this case, Target 1 and its corresponding braking scene can be directly eliminated without being retained.

[0098] Assume again that the first object type of Target 1 is a puppy, and the second object type of Target 1 is a cardboard box. Since the first and second object types of Target 1 are different, this indicates that the AEB has misidentified. That is, the abnormal braking scenario extracted for Target 1 is indeed an abnormal scenario and a false triggering scenario caused by AEB operation. Therefore, Target 1 and its corresponding braking scenario are retained. In this case, all information related to Target 1 can be extracted from the radar CAN data, and vehicle information related to Target 1 (such as vehicle speed) can be extracted from the vehicle CAN data as false triggering scenario information to form a false triggering scenario library. This false triggering scenario library is highly AEB-specific, allowing various false triggering scenarios suitable for bench testing to be constructed. This library enables targeted algorithm verification of the AEB system without the need for extensive road testing. This effectively reduces the time and cost investment, improves the efficiency and completeness of false triggering scenario verification, and thus effectively ensures the reliability of the AEB system.

[0099] In summary, the current SIL test (software-in-the-loop test), HIL test (hardware-in-the-loop test) and actual vehicle test are all verification methods, but they often lack corresponding false triggering scenario data. The present embodiment can collect perception and vehicle data when AEB is falsely triggered in real time, and can quickly analyze a large amount of historical data in the past to extract various specific false triggering scenarios and form a false triggering scenario library, providing data support for subsequent bench verification and vehicle testing, and then realizing targeted algorithm verification, thereby shortening the verification cycle and improving R&D efficiency.

[0100] The present application also provides a device for extracting false triggering scene information, including:

[0101] An acquisition unit, configured to acquire scene data corresponding to historical abnormal braking scenes, wherein the scene data includes vehicle CAN data, radar CAN data, and camera data;

[0102] an analysis unit configured to, when determining through vehicle CAN data that the automatic emergency braking system (AEB) is in an engaged state, perform scene extraction and analysis based on the radar CAN data to extract each scene target that triggered the historical abnormal braking scenario and its corresponding first target type;

[0103] an identification unit, configured to perform type identification on each scene target according to the azimuth angle of the scene target and the camera data, so as to obtain a second target type corresponding to each scene target;

[0104] The extraction unit is configured to extract, for each scene target, scene information corresponding to the scene target from the scene data as false trigger scene information if the first target type and the second target type are inconsistent, so as to form a false trigger scene library.

[0105] Furthermore, the analysis unit is specifically used for:

[0106] Extracting all candidate targets that may trigger historical abnormal braking scenarios and their corresponding target information from the radar CAN data, the target information including target type information, collision time information, azimuth information, distance information, and speed information;

[0107] For each candidate target, determining whether the candidate target will collide with the vehicle in the longitudinal direction according to the collision time information;

[0108] If the candidate target is likely to collide with the vehicle in the longitudinal direction, the safe area where the candidate target is located is determined based on the azimuth information and the distance information;

[0109] Determining whether the candidate target is the target that triggered the historical abnormal braking scenario based on the preset speed limit, speed information, collision time information corresponding to the safety zone where the candidate target is located, and the safety zone where the vehicle is located;

[0110] If so, the candidate target is used as the scene target.

[0111] Furthermore, the safety area includes a left area, a middle area, and a right area, and the vehicle is located in the middle area. The analysis unit is further configured to:

[0112] When it is determined based on the azimuth information that the candidate target is located on the left side of the vehicle, if the lateral distance between the candidate target and the vehicle is greater than the first distance between the right sideline of the left area and the left side of the vehicle, then the safe area where the candidate target is located is determined to be the left area;

[0113] When it is determined based on the azimuth information that the candidate target is located on the right side of the vehicle, if the lateral distance between the candidate target and the vehicle is greater than the second distance between the left sideline of the right area and the right side of the vehicle, then the safe area where the candidate target is located is determined to be the right area;

[0114] When it is determined according to the azimuth information that the candidate target is located in front of or behind the vehicle, the safe area where the candidate target is located is determined to be the middle area.

[0115] Furthermore, the candidate target is in the left area and the preset speed limit of the left area is that the lateral speed is less than 0, and the analysis unit is further configured to:

[0116] Determine whether the lateral speed of the candidate target is less than 0;

[0117] If so, determine whether the candidate target will enter the middle area after the collision time is reached;

[0118] If the candidate target will enter the middle area, the candidate target is determined to be the target that triggers the historical abnormal braking scenario.

[0119] Furthermore, the candidate target is in the middle area and the preset speed limit in the middle area is that the lateral speed is equal to 0, and the analysis unit is further configured to:

[0120] Determine whether the lateral velocity of the candidate target is equal to 0;

[0121] If so, the candidate target is determined to be the target that triggered the historical abnormal braking scenario;

[0122] If not, determine whether the candidate target is still in the middle area after the collision time is reached;

[0123] If the candidate target is still in the middle area, it is determined that the candidate target is the target that triggered the historical abnormal braking scenario.

[0124] Furthermore, the candidate target is in the right area and the preset speed limit of the right area is that the lateral speed is greater than 0, and the analysis unit is further configured to:

[0125] Determine whether the lateral speed of the candidate target is greater than 0;

[0126] If so, determine whether the candidate target will enter the middle area after the collision time is reached;

[0127] If the candidate target will enter the middle area, the candidate target is determined to be the target that triggers the historical abnormal braking scenario.

[0128] Furthermore, the device also includes a data acquisition device, which is used to:

[0129] When a historical abnormal braking scenario occurs, the scenario data corresponding to the trigger signal generated by manual control is collected.

[0130] It should be noted that those skilled in the art can clearly understand that, for the convenience and conciseness of description, the specific working process of the above-described device and each unit can refer to the corresponding process in the aforementioned embodiment of the false triggering scene information extraction method, and will not be repeated here.

[0131] The apparatus provided in the above embodiment can be implemented in the form of a computer program. The computer program can be used in Figure 6 The false trigger scenario information shown is running on the extraction device.

[0132] An embodiment of the present application also provides a false trigger scene information extraction device, comprising: a memory, a processor, and a network interface connected via a system bus, wherein at least one instruction is stored in the memory, and at least one instruction is loaded and executed by the processor to implement all or part of the steps of the aforementioned false trigger scene information extraction method.

[0133] Among them, the network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0134] The processor may be a CPU, other general-purpose processors, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or any conventional processor. The processor is the control center of the computer device, connecting the various parts of the entire computer device using various interfaces and lines.

[0135] The memory can be used to store computer programs and / or modules. The processor implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area. The program storage area can store an operating system, at least one application required for a function (such as a video playback function, an image playback function, etc.), etc.; the data storage area can store data created based on the use of the mobile phone (such as video data, image data, etc.). In addition, the memory can include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, an SMC (SmartMediaCard, smart memory card), an SD (SecureDigital) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0136] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, all or part of the steps of the aforementioned false trigger scene information extraction method are implemented.

[0137] The embodiments of the present application implement all or part of the aforementioned processes, and may also be completed by instructing the relevant hardware through a computer program. The computer program may be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above methods may be implemented. Among them, the computer program includes computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, ROM (Read-Only memory), RAM (Random Access memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0138] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, servers, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0139] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0140] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0141] The foregoing is merely a list of specific embodiments of the present application, intended to enable those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the broadest scope consistent with the principles and novel features of the present application.

Claims

1. A method for extracting false triggering scene information, characterized in that: The following steps are involved: Acquire scene data corresponding to historical abnormal braking scenes, wherein the scene data includes vehicle CAN data, radar CAN data, and camera data; When the vehicle CAN data confirms that the automatic emergency braking system AEB is in an active state, a scene extraction analysis is performed based on the radar CAN data to extract each scene target that triggered the historical abnormal braking scene and its corresponding first target type; Performing type identification on each scene target according to the azimuth angle of the scene target and the camera data to obtain a second target type corresponding to each scene target; For each scene target, if the first target type and the second target type are inconsistent, extracting scene information corresponding to the scene target from the scene data as false trigger scene information to form a false trigger scene library; The scene extraction and analysis based on the radar CAN data to extract each scene target that triggers the historical abnormal braking scene and its corresponding first target type includes: Extracting all candidate targets that may trigger historical abnormal braking scenarios and their corresponding target information from the radar CAN data, the target information including target type information, collision time information, azimuth information, distance information, and speed information; For each candidate target, determining whether the candidate target will collide with the vehicle in the longitudinal direction according to the collision time information; If the candidate target is likely to collide with the vehicle in the longitudinal direction, the safe area where the candidate target is located is determined based on the azimuth information and the distance information; Determining whether the candidate target is the target that triggered the historical abnormal braking scenario based on the preset speed limit, speed information, collision time information corresponding to the safety zone where the candidate target is located, and the safety zone where the vehicle is located; If so, the candidate target is used as the scene target.

2. The method for extracting false triggering scene information according to claim 1, wherein: The safe area includes a left area, a middle area, and a right area. The vehicle is located in the middle area. Determining the safe area where the candidate target is located based on the azimuth information and the distance information includes: When it is determined based on the azimuth information that the candidate target is located on the left side of the vehicle, if the lateral distance between the candidate target and the vehicle is greater than the first distance between the right sideline of the left area and the left side of the vehicle, then the safe area where the candidate target is located is determined to be the left area; When it is determined based on the azimuth information that the candidate target is located on the right side of the vehicle, if the lateral distance between the candidate target and the vehicle is greater than the second distance between the left sideline of the right area and the right side of the vehicle, then the safe area where the candidate target is located is determined to be the right area; When it is determined according to the azimuth information that the candidate target is located in front of or behind the vehicle, the safe area where the candidate target is located is determined to be the middle area.

3. The method for extracting false triggering scene information according to claim 2, wherein: The candidate target is in a left area and the preset speed limit for the left area is a lateral speed less than 0. The determining, based on the preset speed limit corresponding to the safety area where the candidate target is located, speed information, collision time information, and the safety area where the host vehicle is located, whether the candidate target is a target that triggers a historical abnormal braking scenario includes: Determine whether the lateral speed of the candidate target is less than 0; If so, determine whether the candidate target will enter the middle area after the collision time is reached; If the candidate target will enter the middle area, the candidate target is determined to be the target that triggers the historical abnormal braking scenario.

4. The method for extracting false triggering scene information according to claim 2, wherein: The candidate target is in a middle area and the preset speed limit in the middle area is that the lateral speed is equal to 0. The determining whether the candidate target is a target that triggers the historical abnormal braking scenario based on the preset speed limit corresponding to the safety area where the candidate target is located, the speed information, the collision time information, and the safety area where the host vehicle is located includes: Determine whether the lateral velocity of the candidate target is equal to 0; If so, the candidate target is determined to be the target that triggered the historical abnormal braking scenario; If not, determine whether the candidate target is still in the middle area after the collision time is reached; If the candidate target is still in the middle area, it is determined that the candidate target is the target that triggered the historical abnormal braking scenario.

5. The method for extracting false triggering scene information according to claim 2, wherein: The candidate target is in the right area and the preset speed limit of the right area is that the lateral speed is greater than 0. The determining whether the candidate target is a target that triggers the historical abnormal braking scenario based on the preset speed limit corresponding to the safety area where the candidate target is located, the speed information, the collision time information, and the safety area where the host vehicle is located includes: Determine whether the lateral speed of the candidate target is greater than 0; If so, determine whether the candidate target will enter the middle area after the collision time is reached; If the candidate target will enter the middle area, the candidate target is determined to be the target that triggers the historical abnormal braking scenario.

6. The method for extracting false triggering scene information according to claim 1, wherein: Before the step of acquiring scene data corresponding to historical abnormal braking scenes, the method further includes: When a historical abnormal braking scenario occurs, the scenario data corresponding to the trigger signal generated by manual control is collected.

7. A device for extracting false triggering scene information, characterized in that: include: An acquisition unit, configured to acquire scene data corresponding to historical abnormal braking scenes, wherein the scene data includes vehicle CAN data, radar CAN data, and camera data; an analysis unit configured to, when determining through vehicle CAN data that the automatic emergency braking system (AEB) is in an engaged state, perform scene extraction and analysis based on the radar CAN data to extract each scene target that triggered the historical abnormal braking scenario and its corresponding first target type; an identification unit, configured to perform type identification on each scene target according to the azimuth angle of the scene target and the camera data, so as to obtain a second target type corresponding to each scene target; an extraction unit configured to extract, for each scene target, scene information corresponding to the scene target from the scene data as false trigger scene information if the first target type and the second target type are inconsistent, so as to form a false trigger scene library; The scene extraction and analysis based on the radar CAN data to extract each scene target that triggers the historical abnormal braking scene and its corresponding first target type includes: Extracting all candidate targets that may trigger historical abnormal braking scenarios and their corresponding target information from the radar CAN data, the target information including target type information, collision time information, azimuth information, distance information, and speed information; For each candidate target, determining whether the candidate target will collide with the vehicle in the longitudinal direction according to the collision time information; If the candidate target is likely to collide with the vehicle in the longitudinal direction, the safe area where the candidate target is located is determined based on the azimuth information and the distance information; Determining whether the candidate target is the target that triggered the historical abnormal braking scenario based on the preset speed limit, speed information, collision time information corresponding to the safety zone where the candidate target is located, and the safety zone where the vehicle is located; If so, the candidate target is used as the scene target.

8. A device for extracting false trigger scene information, characterized in that: include: A memory and a processor, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the false triggering scene information extraction method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the false triggering scene information extraction method according to any one of claims 1 to 6 is implemented.

Images