Forward collision test analysis method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a forward collision test analysis method and device, electronic equipment and a storage medium, and the method comprises the steps: executing an active emergency braking simulation task of a vehicle active emergency braking system according to a preset test scene case and a preset test speed, and collecting test feedback data; determining a test index attribute value corresponding to the at least one test index dimension based on a preset test scene case, a preset test speed, the test feedback data and a pre-trained collision result analysis model; and determining a target test attribute corresponding to the active emergency braking simulation task based on the test index attribute value corresponding to each test index dimension, so that the transformation of the vehicle active emergency braking system test from traditional manual evaluation to intelligent and efficient analysis is realized on the whole. The test efficiency of the vehicle active emergency braking system and the accuracy of the test result are improved.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a forward collision test analysis method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the rapid development of intelligent driving technology, the Autonomous Emergency Braking System (AEBS), as one of the core functions of vehicle active safety, plays an important role in reducing traffic accidents and improving driving safety.

[0003] Currently, AEBS field testing primarily relies on regulatory-stipulated test items and scoring standards. This includes simulating collision risks at different speeds with stationary, moving, or pedestrian targets, and recording parameters such as warning time, braking timing, and collision speed. Test results are calculated manually or semi-automatically, item by item against regulatory clauses, and finally summarized into a system performance evaluation.

[0004] However, the above testing methods have the following problems: First, test data analysis relies on manual processing, which is time-consuming and prone to errors; second, the fragmentation of regulatory provisions makes the scoring process cumbersome and makes it difficult to quickly locate system performance shortcomings. These problems restrict the efficiency and relevance of AEBS testing, and there is an urgent need for an intelligent analysis model to achieve rapid scoring, multi-dimensional evaluation, and data-driven performance optimization. Summary of the Invention

[0005] This invention provides a forward collision test analysis method, apparatus, electronic device, and storage medium to realize the transformation of vehicle active emergency braking system testing from traditional manual evaluation to intelligent and efficient analysis, thereby improving the testing efficiency and accuracy of test results for vehicle active emergency braking systems.

[0006] In a first aspect, embodiments of the present invention provide a forward collision test analysis method, the method comprising:

[0007] Based on preset test scenario cases and preset test speeds, execute an active emergency braking simulation task of the vehicle's active emergency braking system and collect test feedback data; wherein, the test feedback data includes at least one of pre-collision warning time, emergency braking time, and test vehicle collision speed;

[0008] Based on the preset test scenario cases, the preset test speed, the test feedback data, and the pre-trained collision result analysis model, determine the test indicator attribute value corresponding to at least one test indicator dimension;

[0009] Based on the test indicator attribute values ​​corresponding to the at least one test indicator dimension, the target test attribute corresponding to the active emergency braking simulation task is determined.

[0010] Secondly, embodiments of the present invention also provide a forward collision test analysis apparatus, the apparatus comprising:

[0011] The test data acquisition module is used to execute the active emergency braking simulation task of the vehicle active emergency braking system according to the preset test scenario test cases and preset test speed, and to collect test feedback data; wherein, the test feedback data includes at least one of the pre-collision warning time, emergency braking time and test vehicle collision speed;

[0012] The indicator attribute value determination module is used to determine the test indicator attribute value corresponding to at least one test indicator dimension based on preset test scenario test cases, preset test speed, test feedback data, and pre-trained collision result analysis model.

[0013] The target attribute determination module is used to determine the target test attributes corresponding to the active emergency braking simulation task based on the test indicator attribute values ​​corresponding to at least one test indicator dimension.

[0014] Thirdly, embodiments of the present invention also provide an electronic device, the electronic device comprising:

[0015] One or more processors;

[0016] Storage device for storing one or more programs.

[0017] When one or more programs are executed by one or more processors, the one or more processors implement a forward collision test analysis method as described in any of the embodiments of the present invention.

[0018] Fourthly, embodiments of the present invention also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform any of the forward collision test analysis methods described in the embodiments of the present invention.

[0019] The technical solution of this invention executes an active emergency braking simulation task of a vehicle's active emergency braking system according to preset test scenario cases and preset test speeds, and collects test feedback data. The test feedback data includes at least one of pre-collision warning time, emergency braking time, and test vehicle collision speed. Then, based on the preset test scenario cases, preset test speeds, test feedback data, and a pre-trained collision result analysis model, it determines test indicator attribute values ​​corresponding to at least one test indicator dimension. Based on the test indicator attribute values ​​corresponding to each test indicator dimension, it determines the target test attribute corresponding to the active emergency braking simulation task. This embodiment's technical solution significantly improves testing efficiency through preset test scenarios and automated data collection, avoiding errors and delays caused by manual data processing. It also utilizes a pre-trained collision result analysis model to achieve multi-dimensional intelligent scoring, enabling rapid and accurate location of system performance defects. This solves the problems of cumbersome scoring and difficult problem location in traditional methods, thus realizing a transformation from traditional manual evaluation to intelligent and efficient analysis in vehicle active emergency braking system testing, improving the testing efficiency and accuracy of test results. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of exemplary embodiments of the present invention, the accompanying drawings used in describing the embodiments are briefly introduced below. Obviously, the accompanying drawings described are only a portion of the drawings of the embodiments to be described in this invention, and not all of the drawings. For those skilled in the art, other drawings can be obtained from these drawings without any creative effort.

[0021] Figure 1 This is a flowchart illustrating a forward collision test analysis method provided in an embodiment of the present invention.

[0022] Figure 2 This is a schematic diagram of the structure of a forward collision test analysis device provided in an embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0024] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0025] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance. The acquisition, storage, use, and processing of data in the technical solutions of this application all comply with the relevant provisions of national laws and regulations.

[0026] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0027] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0028] The present application will now be further described in conjunction with the accompanying drawings and specific embodiments. It should be noted that, without conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0029] Figure 1 This is a flowchart illustrating a forward collision test analysis method provided in an embodiment of the present invention. This embodiment is applicable to scenarios where it is necessary to test the active emergency braking system of an autonomous vehicle. The method can be executed by a forward collision test analysis device, which can be implemented in the form of software and / or hardware. The hardware can be an electronic device, such as a mobile terminal, a PC, or a server.

[0030] like Figure 1 As shown, the forward collision test analysis method includes:

[0031] S110. Based on the preset test scenario cases and preset test speed, execute the active emergency braking simulation task of the vehicle active emergency braking system and collect test feedback data.

[0032] The preset test scenario use cases refer to predefined standardized test scenarios used to simulate typical collision risk conditions that vehicles may encounter during actual driving. Optionally, the preset test scenario use cases include collision scenarios between the test vehicle and vulnerable road users, and collision scenarios between the test vehicle and interfering vehicles. The collision scenarios between the vehicle and vulnerable road users include at least one of pedestrian crossing and lateral collision with a bicycle; the collision scenarios between the test vehicle and interfering vehicles include at least one of the following: the vehicle in front is stationary and the vehicle in front is decelerating.

[0033] In this embodiment, the preset test scenario use cases include three main categories of typical collision test scenarios: one category is collision scenarios between the test vehicle and vulnerable road users, mainly simulating the interaction between the vehicle and vulnerable road users such as pedestrians or bicycles, specifically including typical dangerous situations such as pedestrians crossing the road and bicycles colliding from the side; another category is collision scenarios between the test vehicle and interfering vehicles, mainly assessing the collision risk between the vehicle and the vehicle in front, including common situations such as the vehicle in front being completely stationary and / or the vehicle in front decelerating; and the third category is collision scenarios that combine the first and second categories of collision test scenarios. These scenarios are designed to comprehensively cover the types of collisions that may occur on real roads, in order to verify the response capability of the active emergency braking system under different dangerous situations.

[0034] The preset test speed refers to the initial vehicle speed set during the test. Different speed gradients, such as 30 km / h and 50 km / h, are typically selected based on regulatory requirements or engineering needs to evaluate the performance of the active emergency braking system under different speed conditions. The preset test scenario cases and preset test speed together constitute the basic parameters of the test, ensuring the coverage and comparability of the evaluation.

[0035] The active emergency braking (AEBS) simulation task involves triggering and recording the response process of the vehicle's AEBS system through computer simulation or real-vehicle testing under preset collision scenarios (such as pedestrians crossing or a stationary vehicle ahead) and set speeds. Test feedback data consists of key system performance parameters collected during the simulation task. This data includes at least one of the following: pre-collision warning time, emergency braking time, and test vehicle collision speed. Pre-collision warning time is the time interval from the vehicle's first collision warning signal (e.g., audible or visual alarm) to the actual moment a collision may occur, used to assess the timeliness of the system's warning. Emergency braking time is the time interval from when the vehicle automatically triggers emergency braking to the moment a collision may occur, reflecting the braking system's response speed. Test vehicle collision speed refers to the actual speed at the moment of collision between the vehicle and a target (e.g., pedestrian, bicycle, or other vehicle) at the end of the test scenario if the system fails to completely avoid a collision; this parameter directly reflects the collision avoidance effect of the AEBS. This test feedback data is used to quantitatively evaluate the AEBS's warning timeliness, braking effectiveness, and collision avoidance capability.

[0036] In this embodiment, the vehicle's active emergency braking system is first triggered in a simulated environment or actual test site based on preset test scenario cases (including vulnerable road user scenarios such as pedestrians crossing, bicycle side collisions, and interfering vehicle scenarios such as a stationary or decelerating vehicle in front) and preset test speeds. Key performance data is collected in real time during system operation; this data constitutes the test feedback data. The test feedback data includes the trigger time of the collision warning system (pre-collision warning time), the intervention time of the automatic braking system (emergency braking time), and the final collision speed of the vehicle at the end of the test (if a collision occurs). This data is fully captured by sensors and recording equipment, providing a quantitative basis for subsequent performance evaluation.

[0037] S120. Based on preset test scenario cases, preset test speed, test feedback data, and pre-trained collision result analysis model, determine the test indicator attribute value corresponding to at least one test indicator dimension.

[0038] The collision result analysis model refers to an evaluation model established through machine learning or statistical analysis, used to predict and evaluate the performance of the active emergency braking system based on test data. Test indicator dimensions refer to the dimensions used to classify and evaluate system performance from different perspectives. These dimensions may include at least one of the following: automatic emergency braking for vulnerable road users (evaluating the ability to protect pedestrians / cyclists), automatic emergency braking for vehicles (evaluating the ability to prevent vehicle collisions), and automatic emergency braking malfunction (evaluating the situation of false triggering of the system). Test indicator attribute values ​​are specific quantitative scores calculated by the model for each dimension, used to objectively reflect the system's performance level in each dimension.

[0039] Next, we can elaborate on the construction method of the collision result analysis model. The construction method of the collision result analysis model is as follows: train a machine learning model through historical test data, establish a mapping relationship between test parameters and test indicator attribute values ​​corresponding to at least one test indicator dimension, and obtain the collision result analysis model.

[0040] Historical test data refers to the accumulated test dataset of active emergency braking systems. This data includes historical preset test scenario test cases, historical preset test speeds, historical test feedback data, and historical test indicator attribute values ​​for at least one test indicator dimension. In other words, historical test data contains historical preset test scenario test cases, historical preset test speeds (e.g., 30km / h, 50km / h), historical test feedback data (e.g., warning time, braking time, collision speed), and corresponding historical test indicator attribute values—that is, performance scores for each dimension. Test parameters refer to the variable parameters input to the model in the current test task, including the current preset test scenario test cases, preset test speeds, and real-time collected test feedback data. These parameters will serve as input to the collision result analysis model to predict the performance indicator attribute values ​​for each dimension of the current test.

[0041] When constructing the collision result analysis model, the historical test dataset is first collected and organized. This dataset contains various test scenario cases, test feedback data under different test speed conditions (warning time, braking time, collision speed, etc.), and corresponding performance scores for each dimension. Then, a suitable machine learning algorithm, such as random forest or neural network, is selected. The historical test parameters (scenario type, speed value, test feedback data) are used as input features, and the indicator attribute values ​​of each test dimension are used as output labels for supervised learning training. Through feature engineering and model optimization, a mapping model that can accurately predict the performance scores of each dimension in new test tasks is finally established, forming a usable collision result analysis model.

[0042] In practical applications, preset test scenario cases, preset test speeds, and test feedback data can be input into the trained collision result analysis model to output test indicator attribute values ​​corresponding to at least one test indicator dimension.

[0043] Specifically, the preset test scenario cases, preset test speed, and real-time collected test feedback data in the current test task are used as input features and input into a pre-trained collision result analysis model. The machine learning model automatically calculates and outputs a quantitative score of at least one core test indicator dimension through the internally established mapping relationship, namely, the automatic emergency braking dimension score of vulnerable road users, the automatic emergency braking dimension score of the vehicle, and / or the automatic emergency braking malfunction dimension score, thereby realizing a multi-dimensional quantitative evaluation of system performance.

[0044] For example, when the test vehicle was tested in a "pedestrian crossing" scenario at a speed of 50 km / h, the following data were collected: a warning was triggered 2.5 seconds before the collision (warning time), automatic braking was initiated 1.8 seconds before the collision (braking time), and the collision occurred at a speed of 20 km / h (collision speed). These parameters, along with the test scenario type and test speed, were input into a trained collision result analysis model. The model output scores in three dimensions: a score of 65 for the vulnerable road user automatic emergency braking dimension (indicating moderate pedestrian protection performance), a score of 70 for the vehicle automatic emergency braking dimension (indicating general collision prevention capability), and a score of 90 for the automatic emergency braking false triggering dimension (reflecting a low false triggering rate of the system). These scores comprehensively reflect the overall performance of the vehicle's active emergency braking system under the test conditions.

[0045] S130. Based on the test index attribute values ​​corresponding to at least one test index dimension, determine the target test attribute corresponding to the active emergency braking simulation task.

[0046] The target test attribute refers to the comprehensive performance evaluation conclusion of the active emergency braking system under a specific test scenario, determined by analyzing the scoring results of various test indicator dimensions. This conclusion may include at least one of the following: a rating of the overall system effectiveness, such as excellent / good / qualified; specific improvement suggestions, such as optimizing the pedestrian detection algorithm; and a determination of whether it meets safety standards, such as passing / failing certification tests.

[0047] In this embodiment, by analyzing the specific scoring results of three dimensions—vulnerable road user protection, vehicle collision prevention, and / or system false triggering—a comprehensive evaluation is conducted to arrive at the final performance conclusion of the test, which may include key judgment results such as the overall system rating, specific improvement directions, and / or whether it meets industry standards.

[0048] For example, after the test vehicle completes the "front vehicle deceleration" scenario test at a speed of 40 km / h, the collision result analysis model outputs scores in three dimensions: 85 points for automatic emergency braking (excellent braking timeliness), 60 points for vulnerable road users (this scenario is not applicable, so the baseline score is used), and 95 points for erroneous action (no erroneous triggering). Based on this scoring matrix, the target test attribute is automatically generated as "overall score 82 points, excellent performance in urban following scenarios, but requires supplementary pedestrian scenario-specific testing," and it is marked that the AEBS meets the preset standard requirements, but the pedestrian protection aspect needs significant improvement.

[0049] Optionally, the method for determining the target test attribute corresponding to the active emergency braking simulation task based on the test indicator attribute value corresponding to at least one test indicator dimension may include: performing a weighted calculation on the test indicator attribute value corresponding to at least one test indicator dimension to obtain the target test attribute corresponding to the active emergency braking simulation task.

[0050] In this embodiment, different weight values ​​can be set for different test index dimensions, and the original scores of each dimension can be weighted and summed. For example, the weights of the vulnerable road user automatic emergency braking dimension, the vehicle automatic emergency braking dimension, and the automatic emergency braking malfunction dimension are 40%, 40%, and 20%, respectively. Then the quantified comprehensive score is: pedestrian protection 70 points × 0.4 + vehicle collision avoidance 80 points × 0.4 + malfunction triggering 90 points × 0.2 = 78 points. Finally, this quantified comprehensive performance score is generated as the target test attribute. At the same time, the weight allocation strategy can be combined to highlight key safety dimensions, such as pedestrian protection with a higher weight, so that the evaluation results are more in line with actual safety needs.

[0051] The technical solution of this invention executes an active emergency braking simulation task of a vehicle's active emergency braking system according to preset test scenario cases and preset test speeds, and collects test feedback data. The test feedback data includes at least one of pre-collision warning time, emergency braking time, and test vehicle collision speed. Then, based on the preset test scenario cases, preset test speeds, test feedback data, and a pre-trained collision result analysis model, it determines test indicator attribute values ​​corresponding to at least one test indicator dimension. Based on the test indicator attribute values ​​corresponding to each test indicator dimension, it determines the target test attribute corresponding to the active emergency braking simulation task. This embodiment's technical solution significantly improves testing efficiency through preset test scenarios and automated data collection, avoiding errors and delays caused by manual data processing. It also utilizes a pre-trained collision result analysis model to achieve multi-dimensional intelligent scoring, enabling rapid and accurate location of system performance defects. This solves the problems of cumbersome scoring and difficult problem location in traditional methods, thus realizing a transformation from traditional manual evaluation to intelligent and efficient analysis in vehicle active emergency braking system testing, improving the testing efficiency and accuracy of test results.

[0052] Based on the above technical solution, optionally, the method also includes: performing multi-dimensional correlation analysis on preset test scenario test cases, preset test speeds, test feedback data, and test process log data corresponding to the vehicle under test through an automatic emergency braking misdiagnosis analysis model, generating information on points lost and improvement suggestions for the vehicle's active emergency braking system.

[0053] The Automatic Emergency Braking (AEBS) misdiagnosis analysis model refers to an analysis model established through machine learning to identify the causes of AEBS misjudgments. Optionally, the AEBS misdiagnosis analysis model can be an intelligent analysis model based on big data. Test process log data refers to detailed operational data recorded in real time by the vehicle control system and sensors during the active emergency braking test of the vehicle under test. This includes, but is not limited to: the timing records of the working status of each system module, such as sensor wake-up time and algorithm processing delay; raw environmental perception data, such as radar point clouds and camera image frames; the decision logic execution process, such as the collision risk assessment calculation process; control command issuance records, such as brake pressure change curves; and system error codes, etc., providing a complete digital information throughout the entire process. This data provides a complete traceability basis for the test process for misdiagnosis analysis. The key factors leading to a decrease in performance score are those identified in the model output, such as "pedestrian detection delay of 0.3 seconds."

[0054] The improvement suggestions refer to a set of targeted optimization solutions generated from in-depth analysis of test data and system logs based on a misdiagnosis analysis model. These suggestions include braking timing adjustment strategies and sensor sensitivity optimization schemes. Braking timing adjustment strategies refer to optimization schemes for triggering emergency braking, such as "advancing the braking trigger time by 200 milliseconds." Sensor sensitivity optimization schemes are recommendations for adjusting the parameters of sensing devices such as radar / cameras, such as "lowering the millimeter-wave radar detection threshold by 15%." These suggestions guide engineers to precisely optimize key modules of the AEB system, such as perception algorithms, decision logic, or execution control, through quantitative parameter adjustments, thereby systematically improving the vehicle's active safety performance.

[0055] Specifically, a well-trained automatic emergency braking misdiagnosis analysis model can be used to perform multi-dimensional cross-analysis of test scenario parameters (such as pedestrian crossing scenario / 50km / h), real-time collected test data (such as warning delay of 300ms), and vehicle system logs (including raw sensor data, control command timing, etc.). By using pattern recognition to locate the root cause of performance defects, the model can ultimately output specific reasons for score loss and targeted improvement solutions and other engineering and technical measures.

[0056] Based on the above technical solution, optionally, the method also includes: visually outputting at least one of the target test score, key points of failure, and improvement suggestions to the test report interface, and supporting the function of comparing and analyzing historical test data.

[0057] The test report interface refers to an interactive visualization platform used to centrally display the analysis results of forward collision tests.

[0058] In this embodiment, the test analysis results, including the target test score, key points of failure, and / or improvement suggestions, are displayed on an interactive interface using visualizations such as charts and heatmaps. For example, radar charts are used to present the test indicator attribute values ​​of each dimension, key points of failure are marked with colors, and flowcharts are used to explain improvement suggestions. Simultaneously, a comparison function with historical test data is provided, such as displaying performance changes during version iterations through timeline curves and comparing test results of different vehicle models through parallel bar charts. This allows engineers to intuitively identify system shortcomings, track optimization effects, and formulate improvement strategies.

[0059] Example 2

[0060] Figure 2 This is a schematic diagram of a forward collision test analysis device provided in an embodiment of the present invention. The device includes: a scene file acquisition module 210, a scene content extraction module 220, a scene list construction module 230, and a scene retrieval module 240.

[0061] The test data acquisition module 210 is used to execute the active emergency braking simulation task of the vehicle active emergency braking system according to the preset test scenario test cases and preset test speed, and to collect test feedback data; wherein, the test feedback data includes at least one of the pre-collision warning time, emergency braking time and test vehicle collision speed.

[0062] The indicator attribute value determination module 220 is used to determine the test indicator attribute value corresponding to at least one test indicator dimension based on preset test scenario test cases, preset test speed, test feedback data and pre-trained collision result analysis model.

[0063] The target attribute determination module 230 is used to determine the target test attributes corresponding to the active emergency braking simulation task based on the test indicator attribute values ​​corresponding to at least one test indicator dimension.

[0064] The technical solution of this invention executes an active emergency braking simulation task of a vehicle's active emergency braking system according to preset test scenario cases and preset test speeds, and collects test feedback data. The test feedback data includes at least one of pre-collision warning time, emergency braking time, and test vehicle collision speed. Then, based on the preset test scenario cases, preset test speeds, test feedback data, and a pre-trained collision result analysis model, it determines test indicator attribute values ​​corresponding to at least one test indicator dimension. Based on the test indicator attribute values ​​corresponding to each test indicator dimension, it determines the target test attribute corresponding to the active emergency braking simulation task. This embodiment's technical solution significantly improves testing efficiency through preset test scenarios and automated data collection, avoiding errors and delays caused by manual data processing. It also utilizes a pre-trained collision result analysis model to achieve multi-dimensional intelligent scoring, enabling rapid and accurate location of system performance defects. This solves the problems of cumbersome scoring and difficult problem location in traditional methods, thus realizing a transformation from traditional manual evaluation to intelligent and efficient analysis in vehicle active emergency braking system testing, improving the testing efficiency and accuracy of test results.

[0065] Based on the above-mentioned device, optionally, the preset test scenario use cases include a collision scenario between the test vehicle and a vulnerable road user, and a collision scenario between the test vehicle and a disruptive vehicle. The collision scenario between the vehicle and the vulnerable road user includes at least one of pedestrian crossing and lateral collision with a bicycle. The collision scenario between the test vehicle and the disruptive vehicle includes at least one of the vehicle in front being stationary and the vehicle in front decelerating.

[0066] Based on the above-mentioned device, the collision result analysis model can be constructed as follows:

[0067] A machine learning model is trained using historical test data to establish a mapping relationship between test parameters and test indicator attribute values ​​corresponding to at least one test indicator dimension, thereby obtaining a collision result analysis model. The historical test data includes historical preset test scenario cases, historical preset test speeds, historical test feedback data, and historical test indicator attribute values ​​corresponding to at least one test indicator dimension.

[0068] Based on the above-mentioned device, optionally, the indicator attribute value determination module 220 is used to input the preset test scenario test cases, preset test speed and test feedback data into the trained collision result analysis model, and output the test indicator attribute value corresponding to at least one test indicator dimension; wherein, at least one test indicator includes the vulnerable road user automatic emergency braking dimension, the vehicle automatic emergency braking dimension and the automatic emergency braking malfunction dimension.

[0069] Based on the above-mentioned device, the forward collision test analysis device may optionally include: an improvement suggestion determination module;

[0070] The improvement suggestion determination module is used to perform multi-dimensional correlation analysis on the preset test scenario test cases, the preset test speed, the test feedback data, and the test process log data corresponding to the vehicle under test through the automatic emergency braking misdiagnosis analysis model, and generate information on the points of failure and improvement suggestions for the vehicle's active emergency braking system; wherein, the improvement suggestion information includes braking timing adjustment strategies and sensor sensitivity optimization schemes.

[0071] Based on the above-mentioned device, optionally, the indicator attribute value determination module 220 is used to input the preset test scenario test cases, preset test speed and test feedback data into the trained collision result analysis model, and output the test indicator attribute value corresponding to at least one test indicator dimension; wherein, at least one test indicator includes the vulnerable road user automatic emergency braking dimension, the vehicle automatic emergency braking dimension and the automatic emergency braking malfunction dimension.

[0072] Based on the above-mentioned device, optionally, the target attribute determination module 230 is used to perform weighted calculation on the test index attribute values ​​corresponding to at least one test index dimension to obtain the target test attribute corresponding to the active emergency braking simulation task.

[0073] Based on the above-mentioned device, the forward collision test analysis device may optionally include: an information display module;

[0074] The information display module is specifically used to visualize at least one of the target test score, key points of failure, and improvement suggestions to the test report interface, and supports the function of comparing and analyzing historical test data.

[0075] The forward collision test analysis device provided in the embodiments of the present invention can execute the forward collision test analysis method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0076] It is worth noting that the various units and modules included in the above system are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of the present invention.

[0077] Example 3

[0078] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 3 A block diagram is shown of an exemplary electronic device 30 suitable for implementing embodiments of the present invention. Figure 3The electronic device 30 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0079] like Figure 3 As shown, the electronic device 30 is presented in the form of a general-purpose computing device. The components of the electronic device 30 may include, but are not limited to: one or more processors or processing units 301, system memory 302, and bus 303 connecting different system components (including system memory 302 and processing unit 301).

[0080] Bus 303 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0081] Electronic device 30 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 30, including volatile and non-volatile media, removable and non-removable media.

[0082] System memory 302 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 304 and / or cache memory 305. Electronic device 30 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 306 may be used to read and write non-removable, non-volatile magnetic media (… Figure 3 Not shown; usually referred to as a "hard drive"). Although Figure 3 As not shown, disk drives for reading and writing to removable non-volatile disks (e.g., "floppy disks") and optical disc drives for reading and writing to removable non-volatile optical discs (e.g., CD-ROMs, DVD-ROMs, or other optical media) may be provided. In these cases, each drive may be connected to bus 303 via one or more data media interfaces. Memory 302 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0083] A program / utility 308 having a set (at least one) of program modules 307 may be stored, for example, in memory 302. Such program modules 307 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 307 typically perform the functions and / or methods described in the embodiments of the present invention.

[0084] Electronic device 30 can also communicate with one or more external devices 309 (e.g., keyboard, pointing device, display 810, etc.), and with one or more devices that enable a user to interact with electronic device 30, and / or with any device that enables electronic device 30 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 311. Furthermore, electronic device 30 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 312. As shown, network adapter 312 communicates with other modules of electronic device 30 via bus 303. It should be understood that, although... Figure 3 As not shown, other hardware and / or software modules may be used in conjunction with electronic device 30, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0085] The processing unit 301 executes various functional applications and page processing by running programs stored in the system memory 302, such as implementing the forward collision test analysis method provided in the embodiments of the present invention.

[0086] Example 4

[0087] This invention also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform a forward collision test analysis method, the method comprising:

[0088] Based on the preset test scenario cases and preset test speed, execute the active emergency braking simulation task of the vehicle active emergency braking system and collect test feedback data; among which, the test feedback data includes at least one of the pre-collision warning time, emergency braking time and test vehicle collision speed;

[0089] Based on preset test scenario cases, preset test speed, test feedback data, and pre-trained collision result analysis model, determine the test indicator attribute value corresponding to at least one test indicator dimension.

[0090] Based on the test index attribute values ​​corresponding to at least one test index dimension, determine the target test attributes corresponding to the active emergency braking simulation task.

[0091] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0092] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0093] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0094] Computer program code for performing the operations of embodiments of the present invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0095] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method of analyzing a frontal crash test, the method comprising: The method comprises the following steps: According to the preset test scene case and the preset test speed, the active emergency braking simulation task of the vehicle active emergency braking system is executed, and test feedback data is collected; wherein the test feedback data includes at least one of the pre-crash warning time, the emergency braking time and the test vehicle collision speed; Based on the preset test scene case, the preset test speed, the test feedback data and the pre-trained collision result analysis model, the test index attribute value corresponding to at least one test index dimension is determined; Based on the test index attribute value corresponding to at least one test index dimension, the target test attribute corresponding to the active emergency braking simulation task is determined.

2. The method of claim 1, wherein, The preset test scene case includes a collision scene between a test vehicle and a vulnerable road user, and a collision scene between a test vehicle and an interference vehicle, and the collision scene between the vehicle and the vulnerable road user includes at least one of a pedestrian crossing and a bicycle lateral collision; the collision scene between the test vehicle and the interference vehicle includes at least one of a stationary front vehicle and a decelerating front vehicle.

3. The method of claim 1, wherein, Further comprising: The collision result analysis model is constructed in the following way: A machine learning model is trained through historical test data to establish a mapping relationship between test parameters and test index attribute values corresponding to at least one test index dimension, and a collision result analysis model is obtained; wherein the historical test data includes historical preset test scene cases, historical preset test speeds, historical test feedback data and historical test index attribute values corresponding to at least one test index dimension.

4. The method of claim 1, wherein, The method further comprises: The preset test scene case, the preset test speed and the test feedback data are input into the trained collision result analysis model, and at least one test index attribute value corresponding to at least one test index dimension is output; wherein the at least one test index includes a vulnerable road user automatic emergency braking dimension, a vehicle automatic emergency braking dimension and an automatic emergency braking misoperation dimension.

5. The method of claim 1, wherein, The method further comprises: The preset test scene case, the preset test speed, the test feedback data and the test process log data corresponding to the vehicle to be tested are analyzed by the automatic emergency braking misdiagnosis analysis model, and the loss point information and the improvement suggestion information corresponding to the vehicle active emergency braking system are generated; wherein the improvement suggestion information includes a braking timing adjustment strategy and a sensor sensitivity optimization scheme.

6. The method of claim 1, wherein, The method further comprises: The test index attribute values corresponding to at least one test index dimension are weighted to obtain the target test attribute corresponding to the active emergency braking simulation task.

7. The method according to any one of claims 1 to 6, characterized in that, Further comprising: At least one of the target test score, the loss point information and the improvement suggestion information is visually output to the test report interface, and a historical test data comparison and analysis function is supported.

8. A frontal crash test analysis apparatus characterized by comprising: Comprising: The test data collection module is configured to execute an active emergency braking simulation task of a vehicle active emergency braking system according to a preset test scenario use case and a preset test speed, and collect test feedback data; wherein the test feedback data comprises at least one of a pre-crash warning time, an emergency braking time, and a test vehicle collision speed; The index attribute value determination module is configured to determine a test index attribute value corresponding to at least one test index dimension based on the preset test scenario use case, the preset test speed, the test feedback data, and a pre-trained collision result analysis model; The target attribute determination module is configured to determine a target test attribute corresponding to the active emergency braking simulation task based on the test index attribute value corresponding to the at least one test index dimension.

9. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected to the at least one processor in communication; wherein The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the forward collision test analysis method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the forward collision test analysis method of any one of claims 1-7 when executed.

Images