Automatic parking performance quantification method and system, terminal equipment and storage medium

Abstract

The invention relates to the technical field of automatic parking, and discloses an automatic parking performance quantification method and system, terminal equipment and a storage medium, and the automatic parking performance quantification method comprises the steps: obtaining multi-dimensional actual measurement parameters when a target vehicle is automatically parked for multiple times in different test scenes; determining a target performance quantitative score when the target vehicle is automatically parked in each test scene based on the multi-dimensional actual measurement parameters; and according to the scene weight and the scene type weight of each test scene, performing weighted summation on the performance quantification score of each test scene to obtain a total performance quantification score. In various complex test scenes covering horizontal, vertical and inclined train positions, the multi-dimensional actual measurement parameters of the target vehicle in multiple parking processes are comprehensively obtained, the performance of the system under specific working conditions is effectively reflected, the overall importance of different scene types is further comprehensively considered, and the test efficiency is improved. And the comprehensiveness, objectivity and repeatability of automatic parking performance quantification are obviously improved.

Description

Technical Field

[0001] This application relates to the field of automatic parking technology, and in particular to an automatic parking performance quantification method, system, terminal device and storage medium. Background Technology

[0002] With the development of intelligent driving technology, automatic parking systems have been widely used in many vehicles, but their performance evaluation methods remain relatively outdated. Existing evaluations often rely on a binary "pass / fail" judgment or a single indicator, making it difficult to comprehensively reflect the system's true performance. Common problems include incomplete scenario coverage, a single evaluation dimension, and a lack of unified quantitative standards. Incomplete test scenario coverage and a single evaluation dimension often focus only on parking success rate or time, lacking a multi-dimensional quantitative assessment of the parking process. Furthermore, inconsistent evaluation standards among different manufacturers lead to incomparable results, hindering technological benchmarking and iterative optimization. In addition, the importance of different test scenarios and scenario types is not reflected through scientific weighting, making it difficult for evaluation results to reflect the system's true performance. Summary of the Invention

[0003] In view of this, embodiments of this application provide a method, system, terminal device, and storage medium for quantifying the performance of automatic parking systems, which can comprehensively, objectively, and repeatably achieve a comprehensive performance evaluation of automatic parking systems.

[0004] In a first aspect, embodiments of this application provide a method for quantifying the performance of automatic parking, including: The test scenarios include horizontal parking, perpendicular parking, and angled parking, and each type of test scenario includes multiple test scenarios. Based on the multi-dimensional measured parameters, the target performance quantitative score of the target vehicle when automatically parking in each test scenario is determined. The performance quantification scores of each test scenario are weighted and summed according to the scenario weight and scenario type weight of each test scenario to obtain the total performance quantification score. The higher the total performance quantification score, the better the automatic parking performance of the target vehicle.

[0005] In a first possible embodiment of the first aspect, determining the target performance quantification score of the target vehicle during automatic parking in each test scenario based on the multidimensional measured parameters includes: The initial performance quantification score after each automatic parking is determined based on the multi-dimensional measured parameters after each parking. The average performance quantization score for each test scenario is calculated based on the number of tests for each test scenario and the initial performance quantization score after each parking. The average performance quantization score is used as the target performance quantization score.

[0006] In a second possible embodiment of the first aspect, the multidimensional measured parameters include automatic parking results, parking space recognition results, parking control parameters, parking posture parameters, and safety performance parameters. The automatic parking results include parking success status and parking failure status. Determining the initial performance quantification score after each parking based on the multidimensional measured parameters after each automatic parking includes: Under the condition that the target vehicle is in the parking success state, the initial performance quantification score is determined based on the parking space recognition result, the parking control parameters, the parking posture parameters, and the safety performance parameters; If the target vehicle is in the parking failure state, the initial performance quantification score is determined to be zero.

[0007] In a third possible embodiment of the first aspect, determining the initial performance quantification score based on the parking space recognition result, the parking control parameters, the parking posture parameters, and the safety performance parameters includes: Based on the parking space recognition results, a first score is determined, which is the cumulative number of times the target vehicle successfully recognizes the target parking space each time it automatically parks in the test scenario. A second score is determined based on the parking control parameters, a third score is determined based on the parking posture parameters, and a fourth score is determined based on the safety performance parameters. The sum of the first score, the second score, the third score, and the fourth score is used as the initial performance quantification score.

[0008] In a fourth possible embodiment of the first aspect, the parking control parameters include the number of times the target vehicle maneuvers into the parking space, the number of times it brakes suddenly, and the parking timeout during the automatic parking process. Determining the second score based on the parking control parameters includes: The second score is obtained by deducting a first preset score from the initial parking control score based on the number of times the vehicle tumbles into the parking space, the number of times the vehicle brakes suddenly, and the parking timeout period. The parking posture parameters include the steering wheel angle, parking posture, lateral posture, and longitudinal posture of the target vehicle after automatic parking. The parking posture is the degree of tilt of the target vehicle relative to the target parking space. The lateral posture is the lateral distance between the target vehicle and the parking space line. The longitudinal posture is the longitudinal distance between the target vehicle and the parking space line. Determining the third score based on the parking posture parameters includes: The third score is obtained by deducting a second preset score from the initial score of the parking posture based on the steering wheel angle, the parking posture, the lateral posture, and the longitudinal posture. The safety performance parameters include the number of times the target vehicle hits the wheel chocks, the number of times it hits the parking locks, and the number of times it touches the curb during the automatic parking process. The determination of the fourth score based on these safety performance parameters includes: The fourth score is obtained by multiplying the number of times the wheel stop was pressed, the number of times the ground lock was pressed, and the number of times the curb was touched by the third preset score, respectively. The fourth score is a negative value.

[0009] In a fifth possible embodiment of the first aspect, the weighted summation of the performance quantification scores of each test scenario based on the scenario weight and scenario type weight of each test scenario includes: The performance quantification scores of each test scenario of the same type are weighted and summed according to the scenario weight to obtain the performance quantification score of each type of test scenario. The performance quantification scores of each type of test scenario are weighted and summed according to the scenario type weight to obtain the total performance quantification score. In a sixth possible embodiment of the first aspect, obtaining the multi-dimensional measured parameters of the target vehicle during multiple automatic parking operations in different test scenarios includes: The multidimensional measured parameters are bound to timestamps and scene identifiers to generate structured multidimensional measured parameters.

[0010] Secondly, embodiments of this application provide an automatic parking performance quantification system, comprising: The data acquisition module is used to acquire multi-dimensional measured parameters of the target vehicle when it performs multiple automatic parking operations in different test scenarios. The types of test scenarios include horizontal parking, vertical parking, and angled parking, and each type of test scenario includes multiple test scenarios. The scenario testing module is used to determine the target performance quantification score of the target vehicle when automatically parking in each test scenario based on the multi-dimensional measured parameters. The performance quantization module is used to perform a weighted summation of the performance quantization scores of each test scenario based on the scenario weight and scenario type weight of each test scenario to obtain a total performance quantization score. The higher the total performance quantization score, the better the automatic parking performance of the target vehicle.

[0011] Thirdly, embodiments of this application provide a terminal device, including a memory and a processor. The memory stores a computer program, and the computer program executes the above-described automatic parking performance quantification method when it runs on the processor.

[0012] Fourthly, embodiments of this application provide a readable storage medium storing a computer program that executes the above-described automatic parking performance quantification method when run on a processor.

[0013] The embodiments of this application have the following beneficial effects: This embodiment of an automatic parking performance quantification method includes: acquiring multi-dimensional measured parameters of a target vehicle during multiple automatic parking maneuvers in different test scenarios. The test scenarios include horizontal parking, perpendicular parking, and angled parking, with each type encompassing multiple test scenarios; determining the target performance quantification score for the target vehicle's automatic parking in each test scenario based on the multi-dimensional measured parameters; and weighting and summing the performance quantification scores of each test scenario according to its scenario weight and scenario type weight to obtain a total performance quantification score, where a higher total performance quantification score indicates better automatic parking performance of the target vehicle. This application comprehensively acquires multi-dimensional measured parameters of the target vehicle during multiple parking maneuvers across various complex test scenarios covering horizontal, perpendicular, and angled parking spaces, generating an independent score for each test scenario, effectively reflecting the system's performance under specific operating conditions. Furthermore, it comprehensively considers the overall importance of different scenario types (such as horizontal, perpendicular, and angled) and the complexity and frequency of actual application of each specific test scenario, assigning corresponding scenario weights and type weights. By weighted summing of scores from each scenario, a comparable total performance quantification score is obtained. A higher score indicates better automatic parking performance. This method significantly improves the comprehensiveness, objectivity, and repeatability of the evaluation. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This paper illustrates a flowchart of an embodiment of the automatic parking performance quantification method of this application. Figure 2a This illustration shows a schematic diagram of a first-level test scenario according to an embodiment of this application; Figure 2b This illustration shows a schematic diagram of a second-level test scenario according to an embodiment of this application; Figure 2c This illustration shows a schematic diagram of a third-level test scenario according to an embodiment of this application; Figure 2dThis illustration shows a schematic diagram of a fourth-level test scenario according to an embodiment of this application; Figure 2e A schematic diagram of a fifth-level test scenario according to an embodiment of this application is shown; Figure 3a This illustration shows a schematic diagram of a first vertical test scenario according to an embodiment of this application; Figure 3b This illustration shows a schematic diagram of a second vertical test scenario according to an embodiment of this application; Figure 3c This illustration shows a schematic diagram of a third vertical test scenario according to an embodiment of this application; Figure 3d This illustration shows a schematic diagram of a fourth vertical test scenario according to an embodiment of this application; Figure 3e This illustration shows a schematic diagram of a fifth vertical test scenario according to an embodiment of this application; Figure 3f This illustration shows a schematic diagram of a sixth vertical test scenario according to an embodiment of this application; Figure 3g This illustration shows a schematic diagram of a seventh vertical test scenario according to an embodiment of this application; Figure 4a This illustration shows a schematic diagram of a first oblique test scenario according to an embodiment of this application; Figure 4b This illustration shows a schematic diagram of a second oblique test scenario according to an embodiment of this application; Figure 4c This illustration shows a schematic diagram of a third oblique test scenario according to an embodiment of this application; Figure 5a This illustration shows a first schematic diagram of a performance benchmarking report for a target vehicle automatic parking system according to an embodiment of this application; Figure 5b This paper illustrates a second schematic diagram of a performance benchmarking report for a target vehicle automatic parking system according to an embodiment of this application. Figure 5c This illustration shows a third type of schematic diagram of a performance benchmarking report for a target vehicle automatic parking system according to an embodiment of this application; Figure 6 A schematic diagram of an automatic parking performance quantification system according to an embodiment of this application is shown.

[0016] Explanation of key component symbols: 200 - Automatic parking performance quantification system; 210 - Data acquisition module; 220 - Scenario testing module; 230 - Performance quantification module. Detailed Implementation

[0017] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0018] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0019] In the following text, the terms "comprising," "having," and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more combinations thereof. Furthermore, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0020] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be construed as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

[0021] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0022] The following examples illustrate the method for quantifying the performance of automatic parking.

[0023] Figure 1 A flowchart of an automatic parking performance quantification method according to an embodiment of this application is shown. Exemplarily, the automatic parking performance quantification method includes the following steps: S110: Obtain multi-dimensional measured parameters of the target vehicle when it performs multiple automatic parking maneuvers in different test scenarios. The test scenarios include horizontal parking, perpendicular parking, and angled parking, with each type of test scenario including multiple test scenarios.

[0024] Exemplary, the multi-dimensional measured parameters include, but are not limited to, automatic parking results, parking space recognition results, parking control parameters, parking posture parameters, and safety performance parameters. Automatic parking results include successful parking and failed parking states. A successful parking state means the target vehicle successfully completes the automatic parking operation under the control of the automatic parking system. A failed parking state means the automatic parking process fails to achieve the predetermined goal, such as failing to park successfully in the target parking space or experiencing any form of collision, such as rubbing against water-filled barriers, other vehicles, or curbs. Water-filled barriers are introduced as obstacles in the automatic parking test to simulate common non-standard obstacles in real parking environments, such as temporarily placed warning cones, construction fences, and temporary parking posts.

[0025] The parking space recognition result is the cumulative number of times the automatic parking system successfully identifies the target parking space in the test scenario. Parking control parameters include, but are not limited to, the number of times the target vehicle maneuvers through the parking space, the number of times it brakes suddenly, and the parking timeout time during the automatic parking process. A maneuver through the parking space is the operation of shifting gears from R to D or D to R during the parking process, each counted as one maneuver. The number of maneuvers is the cumulative number of shifts from the start of parking to the system indicating completion. The number of sudden braking operations is the number of braking operations with an absolute value of braking acceleration ≥ 5 m / s² during the parking process. The parking timeout time is the duration from when the system completes parking space recognition and issues a parking command until the vehicle comes to a complete stop and the system indicates parking is complete.

[0026] Parking posture parameters include, but are not limited to, the steering wheel angle, parking posture, lateral posture, and longitudinal posture of the target vehicle after automatic parking. The steering wheel angle is the steering wheel rotation angle after parking; the parking posture is the angle difference between the vehicle's longitudinal axis and the design centerline of the target parking space, i.e., the parking angle deviation; the lateral posture is the lateral posture deviation of the target vehicle, i.e., the left-right offset; and the longitudinal posture is the longitudinal posture deviation of the vehicle, i.e., the front-rear offset. The number of times the target vehicle compresses the wheel chocks, the parking locks, and the curb during automatic parking is recorded in a binary state (yes / no) for each instance.

[0027] In one embodiment, the automatic parking system can directly collect data via its onboard data interface, including parking success status, parking failure status, number of times the vehicle swerved into a parking space, number of times it braked suddenly, parking timeout time, steering wheel angle, lateral distances between each tire and the parking space line (perpendicular distances between the left front wheel, right front wheel, left rear wheel, and right rear wheel and their respective side parking space lines), distance between the front of the vehicle and the upper boundary of the parking space (longitudinal straight-line distance between the foremost point of the vehicle and the upper boundary baseline of the parking space), number of times the vehicle hits the wheel chock, number of times it hits the parking lock, and number of times it touches the curb. The lateral attitude deviation can be calculated based on the acquired lateral distances between each tire and the parking space line, the longitudinal attitude deviation can be directly determined based on the distance between the front of the vehicle and the upper boundary of the parking space, and the parking angle deviation can be calculated by combining the lateral attitude deviation and the vehicle wheelbase.

[0028] For example, in one implementation, it is assumed that the distance between the two left wheels of the vehicle and the left parking line is... , The distance between the two right-side wheels and the right-side parking line is , The vehicle wheelbase is L (a constant value). The formula for calculating lateral attitude deviation is:

[0029] in, This indicates the lateral attitude deviation. When the lateral attitude deviation is equal to zero, it means that there is no deviation at all.

[0030] The formula for calculating the parking angle deviation is:

[0031] This indicates the parking angle deviation value. When the parking angle deviation value is zero, it means there is no deviation at all.

[0032] In one embodiment, timestamps and scene identifiers are bound to multidimensional measured parameters to generate structured multidimensional measured parameters. In this embodiment, each multidimensional measured parameter is bound to the timestamp corresponding to its acquisition time to achieve data time serialization; simultaneously, the test scene identifier corresponding to the current timestamp is determined and associated with the multidimensional measured parameters. Finally, the multidimensional measured parameters with timestamps and scene identifiers are integrated into structured data records and stored in a local cache or remote database for subsequent data analysis and evaluation of automatic parking performance.

[0033] In one embodiment, the test scenarios are divided into three categories according to type: horizontal parking space entry, vertical parking space entry, and angled parking space entry. Each type of test scenario includes multiple specific test scenarios, covering complex conditions such as side-wall, vehicles in front and behind, curb, square pillar obstacles, narrow passages, and ground lock limiters, thereby improving the reliability of automatic parking performance testing.

[0034] For example, in one embodiment, the horizontal parking space entry types include, but are not limited to, the first horizontal test scenario Scene_01, the second horizontal test scenario Scene_02, the third horizontal test scenario Scene_03, the fourth horizontal test scenario Scene_04, and the fifth horizontal test scenario Scene_05. For example, as... Figure 2a As shown, the first horizontal test scenario, Scene_01, is a standard horizontal parking space. The horizontal parking space area is against a wall on the side and has limit blocks. The lateral distance of this parking space is 100±10cm, which is the minimum distance a vehicle can move laterally within the parking space. The longitudinal distance is 150cm±10cm, which is the minimum distance a vehicle can move longitudinally within the parking space, ensuring that vehicles can smoothly enter and exit the target parking space. The dimensions of the parking space are... The distance behind the parking space with the limit switch is 80 cm. For example... Figure 2b As shown, the second level test scenario, Scene_02, is a standard parking space. There are cars in front and behind the target parking space, and one side of the space is close to the curb. The lateral distance of the parking space is 100±10cm, and the longitudinal distance is 150cm±10cm. The dimensions of the parking space are... The distance between the parking space and the curb should be 10-20cm. For example... Figure 2c As shown, the third level test scenario, Scene_03, is a horizontal parking space with a square pillar located on one side. It does not have a curb. The lateral distance of the parking space is 100±10cm, and the longitudinal distance is 150cm±10cm. The dimensions of the parking space are... .like Figure 2d As shown, the fourth level test scenario, Scene_04, is a parallel parking space with a narrow aisle on one side. The lateral distance between the parking spaces is 100±10cm, the longitudinal distance is 150cm±10cm, the aisle width is 380~400cm, and the angle of the car in front of the parking space is... The angle is 6° to 10°. For example... Figure 2e As shown, the fifth level test scenario, Scene_05, is a parallel parking space with the rear of the car in front occupying the line. The lateral distance is 100±10cm, and the longitudinal distance is 150cm±10cm. The dimensions of the parking space are... Angle of the car in front of the parking space The angle is 6°~10°, the lateral offset of the car in front of the parking space is 10~20cm, and it is on the line.

[0035] The types of perpendicular parking spaces include, but are not limited to, the first perpendicular test scenario (Scene_06), the second perpendicular test scenario (Scene_07), the third perpendicular test scenario (Scene_08), the fourth perpendicular test scenario (Scene_09), the fifth perpendicular test scenario (Scene_010), the sixth perpendicular test scenario (Scene_011), and the seventh perpendicular test scenario (Scene_012). For example... Figure 3aAs shown, the first vertical test scenario, Scene_06, is of standard size, with limiters, and cars on both sides. The lateral distance is 100±10cm, and the longitudinal distance is 150cm±10cm. The parking space dimensions are... The parking limiter is located 80cm behind the parking space. For example... Figure 3b As shown, the second vertical test scenario, Scene_07, is a narrow parking space with cars on both sides. The lateral distance is 100±10cm, and the longitudinal distance is 150cm±10cm. The dimensions of the parking space are... .like Figure 3c As shown, the third vertical test scenario, Scene_08, is a linear parking space with a parking lock and limiter inside the car. The parking lock is closed. The lateral distance is 100±10cm, and the longitudinal distance is 150cm±10cm. The dimensions of the parking space are... The distance between the limit switch and the rear of the parking space line is 80cm. For example... Figure 3d As shown, the fourth vertical test scenario, Scene_09, is a narrow aisle with a lateral distance of 100±10cm and a longitudinal distance of 150cm±10cm. The parking space dimensions are... The aisle width is 480 cm. (Example) Figure 3e As shown, the fifth vertical test scenario, Scene_010, features a square column wall on one side, with a fire hydrant suspended above the wall. The horizontal distance is 100±10cm, and the vertical distance is 150cm±10cm. The parking space dimensions are... .like Figure 3f As shown, in the sixth vertical test scenario, Scene_011, there is a pillar obstacle on one side, and the passageway is restricted by water-filled barriers. The lateral distance is 100±10cm, the longitudinal distance is 150cm±10cm, and the parking space dimensions are... The square column has a side length of 65cm, and the aisle width is 480cm. (Example:) Figure 3g As shown, the seventh vertical test scenario, Scene_012, is a dead-end road with a lateral distance of 100±10cm and a longitudinal distance of 150cm±10cm. The parking space dimensions are... The wall is adjacent to the parking space, and the aisle width is 550cm.

[0036] The types of inclined train parking include, but are not limited to, the first inclined train test scenario Scene_013, the second inclined train test scenario Scene_014, and the third inclined train test scenario Scene_015. For example, such as... Figure 4a As shown, the first diagonal test scenario, Scene_013, is a standard diagonal parking space. The parking spaces have parking lock limiters in the closed state. The lateral distance is 100±10cm, and the longitudinal distance is 150cm±10cm. The dimensions of the parking spaces are... The parking space is tilted at a 45° angle, and the rear line of the wheel chock is 60cm. For example... Figure 4bAs shown, the second oblique test scenario, Scene_014, has cars on both sides with the front of the car protruding. The lateral distance is 100±10cm, and the longitudinal distance is 150cm±10cm. The parking space dimensions are... The car in front protruded about 30cm. Figure 4c As shown, the third oblique test scenario, Scene_015, is a double-boundary, unmarked parking space with a lateral distance of 100±10cm and a longitudinal distance of 150cm±10cm. The dimensions of the parking space are... The parking space is tilted at a 45° angle.

[0037] S120 determines the target performance quantification score of the target vehicle when automatically parking in each test scenario based on multi-dimensional measured parameters.

[0038] In one embodiment, the initial performance quantification score after each automatic parking is determined based on the multi-dimensional measured parameters after each parking; the average performance quantification score for each test scenario is calculated based on the number of tests for each test scenario and the initial performance quantification score after each parking; and the average performance quantification score is used as the target performance quantification score.

[0039] In this embodiment, during the testing process, the target vehicle maintains a constant speed of 5km / h ± 2km / h throughout the parking space search and parking operation to ensure consistency of testing conditions. Each test scenario (Scene_01~Scene_15) is independently repeated multiple times, with the vehicle's initial position reset before each test (distance error from the parking space baseline ≤ 5cm). The average score from multiple tests in the same scenario is then used as the target performance quantification score for that scenario, reducing the randomness of individual tests and improving data reliability.

[0040] In one embodiment, assuming the target vehicle is in a successfully parked state, an initial performance quantification score is determined based on the parking space recognition result, parking control parameters, parking posture parameters, and safety performance parameters. Specifically, a first score is determined based on the parking space recognition result, whereby the first score is the cumulative number of times the target vehicle successfully recognizes the target parking space each time it automatically parks in the test scenario. A second score is determined based on the parking control parameters, a third score is determined based on the parking posture parameters, and a fourth score is determined based on the safety performance parameters. The sum of the first, second, third, and fourth scores is used as the initial performance quantification score.

[0041] In one implementation, the formula for calculating the first score is:

[0042] Indicates the first score. This represents the count value for each successful identification of a target parking space. This indicates the number of times the target parking space is successfully identified. For example, the initial score for the parking space identification result can be set to 0 points, and the total score for the parking space identification result can be 10 points. In each test scenario, the target parking space is identified 10 times, and 1 point is counted for each successful identification.

[0043] A second score is obtained by deducting a first preset score from the initial parking control score based on the number of times the vehicle maneuvers to maneuver, the number of times it brakes suddenly, and the parking timeout period. For example, if the initial parking control score is set to 50 points, with 20 points for the number of maneuvers, 10 points for the number of sudden brakes, and 20 points for the parking timeout period, the formula for calculating the first preset score can be set as follows:

[0044] Indicates the first preset score. This indicates the points deducted for each time the ball is rubbed. Indicates the number of times the rubbed sac is used. This indicates the points deducted for each instance of emergency braking. Indicates the number of emergency braking operations. This indicates the points deducted for each second exceeding the time limit. This indicates the parking time limit. For example, 2 points are deducted for each instance of maneuvering into a parking space, 2 points are deducted for each instance of sudden braking, and 0.4 points are deducted for each second exceeding the 30-second parking time limit.

[0045] The formula for calculating the second score is:

[0046] Indicates the second score. This indicates the initial score for parking control.

[0047] A third score is obtained by deducting a second preset score from the initial parking posture score based on factors such as steering wheel angle, parking posture, lateral posture, and longitudinal posture. For example, the initial parking posture score can be set to 40 points, with the initial scores for steering wheel angle, parking posture, lateral posture, and longitudinal posture all set to 10 points. The formula for calculating the second preset score is:

[0048] This represents the second preset score. This indicates the points deducted for every 1° deviation of the steering wheel angle. For steering wheel angle, This represents the fraction deducted for each preset angle deviation in the parking angle deviation value. This represents the integer part of the parking angle deviation value divided by the preset angle deviation. This represents the score deducted for each preset lateral attitude deviation. This represents the integer part of the lateral attitude deviation divided by the preset lateral deviation. This indicates the score deducted for each preset longitudinal deviation of the vehicle body's longitudinal attitude. This means that when the longitudinal attitude deviation of the vehicle body is less than the maximum longitudinal attitude deviation, the difference between the longitudinal attitude deviation of the vehicle body and the maximum longitudinal attitude deviation is divided by the integer part of the preset longitudinal deviation.

[0049] For example, 0.1 points are deducted for every 1° deviation of the steering wheel angle; 1 point is deducted for every 0.3° deviation of the parking angle; no points are deducted for deviations less than 0.3°. 1 point is deducted for every 7cm deviation of the lateral posture; no points are deducted for deviations less than 7cm. A full score is given for a longitudinal posture deviation of more than 10cm; 1 point is deducted for deviations less than 1cm; no points are deducted for deviations less than 1cm.

[0050] The formula for calculating the third score is:

[0051] Indicates the third score. This indicates the initial score for the parking posture.

[0052] A fourth score is calculated by multiplying the number of times the wheel stop was pressed, the number of times the parking lock was pressed, and the number of times the curb was touched, by the third preset score. The fourth score is negative. The formula for calculating the fourth score is as follows:

[0053] Fourth place in the scoring. The third preset score, The number of times the wheel stop is pressed, This is based on the number of times the vehicle touches the curb. For example, 5 points are deducted for each time the vehicle hits a wheel chock, 5 points are deducted for each time the vehicle hits a ground lock, and 5 points are deducted for each time the vehicle touches the curb.

[0054] In summary, the formula for calculating the initial performance quantification score is as follows:

[0055] This represents the initial performance quantification score.

[0056] In another implementation, if the target vehicle is in a parking failure state, the initial performance quantification score is set to zero. In this embodiment, when the target vehicle is involved in a collision (the vehicle body scrapes against water barriers, other vehicles, etc.) or fails to park successfully in the target parking space during the automatic parking process, it is determined to be in a parking failure state. At this time, in order to objectively reflect the actual performance of the parking task, the corresponding initial performance quantification score is directly set to zero.

[0057] S130: The performance quantification scores of each test scenario are weighted and summed according to the scenario weight and scenario type weight of each test scenario to obtain the total performance quantification score. The higher the total performance quantification score, the better the automatic parking performance of the target vehicle.

[0058] In one embodiment, the performance quantification scores of various test scenarios of the same type are weighted and summed according to the scenario weight to obtain the performance quantification score of each type of test scenario. The performance quantification scores of all types of test scenarios are then weighted and summed according to the scenario type weight to obtain the total performance quantification score.

[0059]

[0060] This represents the total performance quantification score. This indicates the scene type weight for horizontal parking space entry. This indicates the scene type weight for vertical parking space entry. This indicates the scene type weight for the type of oblique train parking. Indicates the target vehicle is in the The target performance quantification score for automatic parking in test scenarios of horizontal parking space type. Indicates the first The scene weights for test scenarios of horizontal parking space entry type. Indicates the target vehicle is in the The target performance quantification score for automatic parking in a test scenario of vertical parking space entry. Indicates the first The scenario weights for each test scenario involving vertical parking space entry. Indicates the target vehicle is in the The target performance quantification score for automatic parking in a test scenario involving angled train parking. Indicates the first The scenario weights for each test scenario involving inclined train parking. , , .

[0061] For example, in one embodiment, the scene weight of the first level test scene Scene_01 is 20%, the scene weight of the second level test scene Scene_02 is 20%, the scene weight of the third level test scene Scene_03 is 20%, the scene weight of the fourth level test scene Scene_04 is 20%, and the scene weight of the fifth level test scene Scene_05 is 20%. The scene weight of the first vertical test scene Scene_06 is 20%, the scene weight of the second vertical test scene Scene_07 is 20%, the scene weight of the third vertical test scene Scene_08 is 10%, the scene weight of the fourth vertical test scene Scene_09 is 10%, the scene weight of the fifth vertical test scene Scene_010 is 15%, the scene weight of the sixth vertical test scene Scene_011 is 10%, and the scene weight of the seventh vertical test scene Scene_012 is 15%. The first oblique test scenario Scene_013 has a scene weight of 30%, the second oblique test scenario Scene_014 has a scene weight of 40%, and the third oblique test scenario Scene_015 has a scene weight of 30%.

[0062] The scenario type weight for horizontal parking space entry is 40%, used to evaluate the parking performance of the automatic parking system for horizontally laid-out parking spaces; the scenario type weight for vertical parking space entry is 40%, used to evaluate the parking performance of the automatic parking system for vertically laid-out parking spaces; and the scenario type weight for angled parking space entry is 20%, used to evaluate the parking performance of the automatic parking system for angledly laid-out parking spaces.

[0063] In this embodiment, this application achieves a comprehensive and objective evaluation of the performance of the automatic parking system by introducing multi-dimensional quantitative indicators and a scientific weighting system. The specific effects are as follows: Improved evaluation comprehensiveness: Covering most real-world parking environments through multiple typical scenarios, including complex obstacle scenarios, ensures system robustness. Enhanced result comparability: A unified scoring system and weighting allocation make different systems and versions comparable, facilitating technical benchmarking and iteration. Optimized system design guidance: Indicators such as the number of parking maneuvers and the frequency of emergency braking guide the system to optimize path planning and control algorithms, improving user experience and safety.

[0064] In one implementation, the system can output the target performance quantification score for each test scenario, the score for each type of test scenario, and the total performance quantification score, generating a performance benchmarking report for system optimization and competitor analysis. Figure 5a , 5b Figure 5c shows a performance benchmarking report for an automatic parking system for a target vehicle.

[0065] Figure 6A schematic diagram of an automatic parking performance quantification system 200 according to an embodiment of this application is shown. Exemplarily, the automatic parking performance quantification system 200 includes: The data acquisition module 210 is used to acquire multi-dimensional measured parameters of the target vehicle when it performs multiple automatic parking operations in different test scenarios. The test scenarios include horizontal parking, vertical parking, and angled parking, with each type of test scenario including multiple test scenarios.

[0066] The scenario testing module 220 is used to determine the target performance quantification score of the target vehicle when automatically parking in each test scenario based on multi-dimensional measured parameters.

[0067] The performance quantization module 230 is used to perform a weighted sum of the performance quantization scores of each test scenario based on the scenario weight and scenario type weight of each test scenario to obtain the total performance quantization score. The higher the total performance quantization score, the better the automatic parking performance of the target vehicle.

[0068] It is understood that the system in this embodiment corresponds to the automatic parking performance quantification method in the above embodiments, and the options in the above embodiments are also applicable to this embodiment, so they will not be described again here.

[0069] This application also provides a terminal device, exemplary of which includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to enable the terminal device to perform the functions of the various modules in the above-described automatic parking performance quantification method or the above-described automatic parking performance quantification system.

[0070] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0071] Memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), and Electrically Erasable Programmable Read-Only Memory (EEPROM). Memory is used to store computer programs, and the processor can execute these programs upon receiving execution instructions.

[0072] This application also provides a computer-readable storage medium for storing computer programs used in the aforementioned terminal devices. For example, the computer-readable storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0073] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that, as an alternative implementation, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0074] In addition, the functional modules or units in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0075] If a function is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application.

[0076] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for quantifying the performance of automatic parking, characterized in that, include: The test scenarios include horizontal parking, perpendicular parking, and angled parking, and each type of test scenario includes multiple test scenarios. Based on the multi-dimensional measured parameters, the target performance quantitative score of the target vehicle when automatically parking in each test scenario is determined. The performance quantification scores of each test scenario are weighted and summed according to the scenario weight and scenario type weight of each test scenario to obtain the total performance quantification score. The higher the total performance quantification score, the better the automatic parking performance of the target vehicle.

2. The method for quantifying the performance of automatic parking according to claim 1, characterized in that, The determination of the target performance quantification score of the target vehicle during automatic parking in each test scenario based on the multi-dimensional measured parameters includes: The initial performance quantification score after each automatic parking is determined based on the multi-dimensional measured parameters after each parking. The average performance quantization score for each test scenario is calculated based on the number of tests for each test scenario and the initial performance quantization score after each parking. The average performance quantization score is used as the target performance quantization score.

3. The method for quantifying the performance of automatic parking according to claim 2, characterized in that, The multi-dimensional measured parameters include automatic parking results, parking space recognition results, parking control parameters, parking posture parameters, and safety performance parameters. The automatic parking results include successful parking status and failed parking status. The determination of the initial performance quantification score after each automatic parking based on the multi-dimensional measured parameters includes: Under the condition that the target vehicle is in the parking success state, the initial performance quantification score is determined based on the parking space recognition result, the parking control parameters, the parking posture parameters, and the safety performance parameters; If the target vehicle is in the parking failure state, the initial performance quantification score is determined to be zero.

4. The method for quantifying the performance of automatic parking according to claim 3, characterized in that, The determination of the initial performance quantification score based on the parking space recognition result, the parking control parameters, the parking posture parameters, and the safety performance parameters includes: Based on the parking space recognition results, a first score is determined, which is the cumulative number of times the target vehicle successfully recognizes the target parking space each time it automatically parks in the test scenario. A second score is determined based on the parking control parameters, a third score is determined based on the parking posture parameters, and a fourth score is determined based on the safety performance parameters. The sum of the first score, the second score, the third score, and the fourth score is used as the initial performance quantification score.

5. The method for quantifying the performance of automatic parking according to claim 4, characterized in that, The parking control parameters include the number of times the target vehicle maneuvers into the parking space, the number of times it brakes suddenly, and the parking timeout during the automatic parking process. Determining the second score based on the parking control parameters includes: The second score is obtained by deducting a first preset score from the initial parking control score based on the number of times the vehicle tumbles into the parking space, the number of times the vehicle brakes suddenly, and the parking timeout period. The parking posture parameters include the steering wheel angle, parking posture, lateral posture, and longitudinal posture of the target vehicle after automatic parking. The parking posture is the degree of tilt of the target vehicle relative to the target parking space. The lateral posture is the lateral distance between the target vehicle and the parking space line. The longitudinal posture is the longitudinal distance between the target vehicle and the parking space line. Determining the third score based on the parking posture parameters includes: The third score is obtained by deducting a second preset score from the initial score of the parking posture based on the steering wheel angle, the parking posture, the lateral posture, and the longitudinal posture. The safety performance parameters include the number of times the target vehicle hits the wheel chocks, the number of times it hits the parking locks, and the number of times it touches the curb during the automatic parking process. The determination of the fourth score based on these safety performance parameters includes: The fourth score is obtained by multiplying the number of times the wheel stop was pressed, the number of times the ground lock was pressed, and the number of times the curb was touched by the third preset score, respectively. The fourth score is a negative value.

6. The method for quantifying the performance of automatic parking according to claim 1, characterized in that, The step of weighted summation of the performance quantification scores of each test scenario based on the scenario weight and scenario type weight of each test scenario includes: The performance quantification scores of each test scenario of the same type are weighted and summed according to the scenario weight to obtain the performance quantification score of each type of test scenario. The performance quantification scores of each type of test scenario are weighted and summed according to the scenario type weight to obtain the total performance quantification score.

7. The method for quantifying the performance of automatic parking according to claim 1, characterized in that, The acquisition of multi-dimensional measured parameters of the target vehicle during multiple automatic parking operations in different test scenarios includes: The multidimensional measured parameters are bound to timestamps and scene identifiers to generate structured multidimensional measured parameters.

8. An automatic parking performance quantification system, characterized in that, include: The data acquisition module is used to acquire multi-dimensional measured parameters of the target vehicle when it performs multiple automatic parking operations in different test scenarios. The types of test scenarios include horizontal parking, vertical parking, and angled parking, and each type of test scenario includes multiple test scenarios. The scenario testing module is used to determine the target performance quantification score of the target vehicle when automatically parking in each test scenario based on the multi-dimensional measured parameters. The performance quantization module is used to perform a weighted summation of the performance quantization scores of each test scenario based on the scenario weight and scenario type weight of each test scenario to obtain a total performance quantization score. The higher the total performance quantization score, the better the automatic parking performance of the target vehicle.

9. A terminal device, characterized in that, It includes a memory and a processor, the memory storing a computer program that, when run on the processor, executes the automatic parking performance quantification method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that, It stores a computer program that, when run on a processor, executes the automatic parking performance quantification method according to any one of claims 1 to 7.

Images