Safety performance quantitative index determination method for lane line detection module, safety performance quantitative evaluation method for automatic driving system and related products

Abstract

The invention discloses a safety performance quantitative index determination method of a lane line detection module, a safety performance quantitative evaluation method for an automatic driving system and a related product, and the method comprises the steps: obtaining the lane line detection uncertainty of a plurality of algorithm modules of the lane line detection module, the hazard event of the lane line detection module is decomposed to be caused by lane line detection uncertainty of different algorithm modules of the lane line detection module; performing scene modeling on the probability of the hazard event caused by the lane line detection uncertainty of the lane line detection module to obtain a driver model under different hazard events; and obtaining quantization targets corresponding to different algorithm modules of the lane line detection module at least based on the driver models under different hazard events.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of autonomous driving, and particularly to a method for quantitatively evaluating the safety performance of a lane line detection module, a method for quantitatively evaluating the safety performance of an autonomous driving system, and related products. Background Art

[0002] In related technologies, one of the important systems for ensuring a safe environment for drivers and passengers in autonomous vehicles is the Advanced Driver Assistance System (ADAS). Adaptive cruise control, automatic braking / steering away, lane keeping system, blind spot assistance, lane departure warning system, and lane line detection are representatives of ADAS. Lane line detection displays specific information on the geometric features of the lane line structure to the intelligent system of the vehicle to show the position marked by the lane line. Common lane line recognition algorithms use image processing techniques such as edge detection, color filtering, and Hough transform to extract the position and shape information of the lane line. Model-based lane line detection algorithms usually establish a geometric model of the lane line according to the geometric characteristics of the lane line shape, and then use methods such as the Random Sample Consensus (RANSAC) algorithm, the least squares method, and the Hough transform to find the geometric model parameters of the lane line, so as to fit the corresponding lane line curve.

[0003] Currently, for the safety design of autonomous driving systems, either a general safety quantification target is designed at the vehicle level, or some experience-based safety quantification targets are designed at the system level, or some safety requirements based on experience or theoretical analysis are set, without specific quantification indicators and with poor theoretical basis. Among them, the safety design of the lane line detection module of autonomous driving systems is mostly qualitative design without quantitative design reference. A small part of the quantitative safety design of autonomous driving systems is based on estimated values of engineering experience or expert experience without theoretical basis. Currently, for the performance development of autonomous driving systems, due to the lack of safety targets, only the usability of the performance can be guaranteed, and it is not clear to what extent the performance needs to be developed and improved. Summary of the Invention

[0004] The embodiments of the present application provide a method for quantitatively evaluating the safety performance of a lane line detection module, an electronic device, and a storage medium, which are used to solve at least one of the above technical problems.

[0005] In a first aspect, an embodiment of the present application provides a method for determining safety performance quantification indicators of a lane line detection module, including: obtaining the lane line detection uncertainty of multiple algorithm modules of the lane line detection module, where the hazard events of the lane line detection module are decomposed into those caused by the lane line detection uncertainty of different algorithm modules of the lane line detection module; performing scenario modeling on the probability of the lane line detection uncertainty of the lane line detection module causing hazard events to obtain a driver model under different hazard events; and obtaining the quantification targets corresponding to different algorithm modules of the lane line detection module at least based on the driver models under different hazard events.

[0006] In a second aspect, an embodiment of the present application provides a method for quantitatively evaluating the safety performance of an autonomous driving system, including: evaluating the safety performance of the autonomous driving system by using the quantification targets in the method described in the first aspect.

[0007] In a third aspect, an embodiment of the present application provides an electronic device, which includes: at least one processor, and a memory communicatively connected to the at least one processor, where the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute any one of the above methods for determining safety performance quantification indicators of a lane line detection module and the method for quantitatively evaluating the safety performance of an autonomous driving system.

[0008] In a fourth aspect, an embodiment of the present application provides a storage medium, in which one or more programs including execution instructions are stored, and the execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to be used for executing any one of the above methods for determining safety performance quantification indicators of a lane line detection module and the method for quantitatively evaluating the safety performance of an autonomous driving system.

[0009] In a fifth aspect, an embodiment of the present application further provides a computer program product, where the computer program product includes a computer program stored on a storage medium, and the computer program includes program instructions, and when the program instructions are executed by a computer, the computer is enabled to execute any one of the above methods for determining safety performance quantification indicators of a lane line detection module and the method for quantitatively evaluating the safety performance of an autonomous driving system.

[0010] In a sixth aspect, an embodiment of the present application further provides a movable platform, including the electronic device described in the third aspect.

[0011] The method of the present application provides a complete set of methods for determining the safety performance quantification index and evaluating the safety performance of an autonomous driving system with a theoretical basis. By using the method of the embodiments of the present application, the quantified safety design indexes of each algorithm module in the autonomous driving system and its lane line detection module can be obtained, providing a clear quantified reference for the safety design and development stage and the testing stage of the autonomous driving system. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0013] Figure 1 It is a flowchart of a method for determining the safety performance quantification index of a lane line detection module provided by an embodiment of the present application;

[0014] Figure 2 It is a vehicle failure decomposition scheme provided by an embodiment of the present application;

[0015] Figure 3 It is a lane line error deviation model established when the lane line detection value is outward relative to the true value provided by an embodiment of the present application;

[0016] Figure 4 It is a lane line error deviation model established when the lane line detection value is inward relative to the true value provided by an embodiment of the present application;

[0017] Figure 5 It is a simulation result provided by an embodiment of the present application;

[0018] Figures 6a - 6d It is a method for calculating the quantification index of the corresponding lane center line according to the lateral deviation threshold of the lane line provided by an embodiment of the present application;

[0019] Figure 7 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0021] The present invention designs a method for quantitatively evaluating the safety performance of the lane line detection algorithm module of an autonomous driving system. By using methods such as mathematical modeling, theoretical analysis, and natural driving data analysis, a quantitative scheme for the safety performance indicators of the lane line detection module is designed, and the safety quantification target of the lane line detection module is obtained, providing a reference for the safety design and evaluation of the lane line detection module of the autonomous driving system.

[0022] Among them, mathematical modeling mainly involves the analysis of some kinematic models and the modeling of dangerous scenarios. Theoretical analysis mainly conducts theoretical analysis on the hazards generated by each algorithm module and the rationality of mathematical modeling. Natural driving data analysis mainly obtains driver behavior by statistically analyzing natural driving data.

[0023] In the safety design of the autonomous driving system in the related art, reasonable theoretical derivations cannot be given, resulting in no quantitative safety target for the lane line detection module. Based on reasonable mathematical modeling, the present invention obtains a quantitative scheme for the safety performance target of the lane line detection module, which is used for the safety design and evaluation of the autonomous driving system.

[0024] Please refer to Figure 1 , which shows a flowchart of a method for determining the safety performance quantification index of a lane line detection module provided by an embodiment of the present application. This method is used for an autonomous driving system and can be applied to the field of safety design and evaluation of the lane line detection module of the autonomous driving system or the testing field of the lane line detection module of the autonomous driving system. As a part of autonomous driving safety, it can be applied to the safety design and evaluation of the lane line detection module of various levels of autonomous driving systems or the testing of the lane line detection module of the autonomous driving system. The execution subject of the embodiment of the present application can be an electronic device or a safety performance quantification index determination device provided in the electronic device. The safety performance quantification index determination device can be implemented by software or a combination of software and hardware. The safety performance quantification index determination device can be a processor in the electronic device. The electronic device can be a device installed with an autonomous driving system or other devices connected to the autonomous driving system.

[0025] As Figure 1 shown, in step 101, obtain the lane line detection uncertainty of multiple algorithm modules of the lane line detection module;

[0026] In step 102, perform scenario modeling on the probability of hazard events caused by the lane line detection uncertainty of the lane line detection module to obtain a driver model under different hazard events;

[0027] In step 103, obtain the quantification targets corresponding to different algorithm modules of the lane line detection module based at least on the driver models under different hazard events.

[0028] In this embodiment, for step 101, the hazard event of the lane line detection module is decomposed into the lane line detection uncertainty of different algorithm modules of the lane line detection module. Thus, the uncertainty of the lane line detection module can be decomposed into the uncertainties of its corresponding multiple algorithm modules, and the uncertainty of the lane line detection module can be obtained by acquiring the lane line detection uncertainties of the multiple algorithm modules. Among them, the multiple algorithm modules may include a lane line position detection module and a lane center line position detection module, and may also include other detection modules currently used or detection modules to be used in the future. This application has no limitation here. Further, the lane line detection uncertainties of the multiple algorithm modules may include lane line position detection errors and lane center line position detection errors.

[0029] After that, for step 102, scenario modeling is performed on the probability of the hazard event caused by the lane line detection uncertainty, and a driver model under different hazard events is obtained through scenario analysis and modeling. Specifically, due to the uncertainty of lane line detection, it may cause the vehicle to deviate from the current lane, and then it may collide with vehicles in adjacent lanes, nearby obstacles or pedestrians, resulting in a hazard event. For the above-mentioned hazard events, an analysis and modeling can be carried out to obtain a relationship model (driver model) between the probability of the hazard event occurring and the lane line detection uncertainty.

[0030] Finally, for step 103, after establishing the driver model under different hazard events, at least the quantization targets corresponding to the multiple algorithm modules of the lane line detection module can be obtained based on this driver model. Specifically, based on the safety of the autonomous driving system not being lower than the safety reference benchmark, such as the safety of a human driver or the safety of other better-performing autonomous driving systems, the following values can be obtained through scenario simulation: when a lane line detection error is found, the critical value for preventing the vehicle from deviating from the current lane. If this critical value is exceeded, the vehicle cannot be prevented from deviating from the current lane, and in this case, a hazard event is likely to occur. Then this critical value can be used as the quantization target, so that the quantization targets corresponding to the multiple algorithm modules can be obtained. Of course, the quantization target can also be set smaller than this critical value. This application has no limitation here. For example, the maximum value of the lane line position detection error and the maximum value of the lane center line position detection error.

[0031] In the embodiment of this application, by decomposing the hazard event of the lane line detection module into the lane line detection uncertainty of different algorithm modules of the lane line detection module, then performing scenario modeling on different algorithm modules to obtain the corresponding driver model, and then based on this driver model, the quantization targets of different algorithm modules can be obtained.

[0032] Please refer to Figure 2 , which shows the decomposition scheme of the embodiment of this application.

[0033] As Figure 2 shown, the embodiments of the present application adopt a method of layer-by-layer decomposition to decompose the problem of vehicle failure layer by layer into each algorithm module. The core idea is that the safety of the autonomous driving system should not be lower than that of humans. First, analyze the reasons for vehicle failure. Vehicle failure is jointly caused by hazardous behaviors and relevant scenarios. For relevant scenarios, scenario modeling can be carried out to obtain the regions of interest for different scenarios; then analyze the hazardous behaviors and list specific hazardous behaviors; afterwards, analyze the reasons for the hazardous behaviors to identify the performance limitations that lead to the generation of hazardous behaviors, including:

[0034] Performance limitations related to perception: Lane line state uncertainty. It mainly includes performance limitations such as the position error of lane line detection and the position error of lane center line detection.

[0035] All performance limitations are caused by different algorithm modules. By analyzing and modeling the performance limitations and performing calculations through natural driving data sets, driver model modeling, etc., quantitative indicators of the performance limitations corresponding to different algorithm modules can be obtained as the quantitative safety performance objectives of the corresponding algorithm modules.

[0036] Regarding the performance limitations related to perception: state uncertainty, state uncertainty mainly includes lane line position detection error, lane center line position detection error, etc.

[0037] In some alternative embodiments, the lane line detection uncertainty of multiple algorithm modules of the lane line detection module includes: when lane line detection uncertainty occurs in different algorithm modules of the lane line detection module, obtaining the lane line detection uncertainty that leads to the exposure of hazardous behaviors, where the hazardous behaviors are uncontrollable. Here, the exposure of hazardous behaviors means that a hazardous behavior has occurred. The uncontrollability of hazardous behaviors means that the hazardous behaviors cannot be controlled (for example, it is impossible to predict the specific operations of the driver to respond to hazardous behaviors).

[0038] In some alternative embodiments, the lane line detection uncertainty is the lane line position detection error. Scenario modeling of the probability of a hazard event caused by the lane line detection uncertainty of the lane line detection module to obtain a driver model under different hazard events includes: when there is a vehicle in the adjacent lane of the vehicle's own lane, scenario modeling of the scenario of deviating from the vehicle's own lane caused by the lane line position detection error to obtain a driver model corresponding to the lane line position detection error; wherein, the scenario of deviating from the vehicle's own lane is: the vehicle has a lane line position detection error, and the lane line position detection error makes it impossible to correct the vehicle back to its own lane using a lateral acceleration in the direction opposite to the deviation direction of the lane line detection error; The quantization objectives corresponding to different algorithm modules of the lane line detection module obtained at least based on the driver models under different hazard events include: obtaining, at least based on the driver model corresponding to the lane line position detection error, the maximum offset amount that can prevent the vehicle from deviating from its own lane using a lateral acceleration in the opposite direction, and obtaining the quantization objective corresponding to the lane line position detection error of the autonomous driving system.

[0039] Further refer to Figure 3 and Figure 4 , which shows two lane line error deviation models of the embodiments of the present application.

[0040] In the embodiments of the present application, for the lateral detection error of the lane line, the considered dangerous scenario is that there is a vehicle in the adjacent lane, and the core constraint is that when there is a lateral detection error in the lane line, the vehicle has a lateral offset, and the maximum allowable lateral offset of the vehicle is not more than its own lane. Therefore, a lane line lateral deviation model is established.

[0041] Please refer to Figure 3 , which shows the lane line error deviation model established when the lane line detection value is outward relative to the true value. Among them, the black dotted chain is the true value of the lane line, the black curve is the lane line detection result output by the lane line detection module, the black concentric circles are the vehicle (the diameter is the vehicle width), and the black dotted concentric circles are the position of the vehicle in the next frame.

[0042] Assume that the lane line detection generates a large error (this error is an assumed error, and after this error occurs, the vehicle will have unsafe actions), resulting in the vehicle driving along the wrong lane line and deviating from the true lane. At this time, if the maximum lateral acceleration is applied in the opposite direction to correct the vehicle's deviation from the lane, it can ensure that the vehicle can always drive within the lane. When the error output by the lane line detection is large enough, the vehicle cannot be corrected back to the lane using the opposite lateral acceleration. At this time, the detection error is the critical value. Therefore, Figure 3Along the vertical (tangent) direction of the true lane line points, the intersection of the avoidance trajectory (black dashed line) and the deceleration direction (dashed arrow) in the vertical direction gives the possible offset according to dynamics. This offset is the allowed outward offset of the lane line. The process of calculating this offset is as follows: First, calculate the slope of the two points of the true lane line to obtain the slope in the vertical direction. Then, calculate the perpendicular line equation based on the slope and one of the above two points (the solid arrow indicates). After that, calculate the offset trajectory according to the acceleration components. The intersection coordinates (i.e., the black crosses) are obtained from the offset trajectory and the perpendicular line equation. Finally, the allowed offset (considering the vehicle size) is obtained from the intersection and the discrete points on the corresponding GT (Ground Truth, true value).

[0043] The specific calculation process is as follows: Assume two points a(x1, y1) and b(x2, y2) of the true lane line of the point lane. Then the tangent slope c = (y2 - y1) / (x2 - x1), and the slope of the deceleration direction is d = 1 / -c. The deceleration a is decomposed into ax in the x direction and ay in the y direction. Then ay / ax = d, and ax*ax + ay*ay = a*a. Ax and ay can be solved, and then the values of ax and ay are obtained. Using y = ay*t + 1 / 2*ay*t*t and x = ax*t + 1 / 2*ax*t*t, the coordinates of the point are obtained, and thus the maximum offset of this point from the true value point is obtained.

[0044] Please refer to Figure 4 , which shows the lane line error deviation model established when the lane line detection value is inward relative to the true value. Among them, the black dotted chain is the true lane line, the black curve is the lane line detection result output by the lane line detection module, the black concentric circles are the vehicle (the diameter is the vehicle width), and the black dashed concentric circles are the position of the vehicle in the next frame.

[0045] Assume that the lane line detection generates a large error, resulting in the vehicle driving along the wrong lane line and deviating from the true lane. When the vehicle drives to press on the true lane line, the relative distance between the true lane line and the detected lane line is the largest. This maximum relative distance is the maximum allowed offset of the lane line. The calculation model established is

[0046] lane_error_in = lane_w - car_w

[0047] In the formula, lane_error_in is the maximum allowed offset, lane_w is the lane line width, and car_w is the vehicle width.

[0048] In some alternative embodiments, the quantization target corresponding to the lane line position detection error of the autonomous driving system includes: simulating based on a driver model corresponding to the lane line position detection error and actual scenario parameters to obtain the maximum allowable detection error at different detection distances of the lane line detection model; and using the maximum allowable detection error at different detection distances as the quantization target corresponding to the lane line position detection error of the autonomous driving system.

[0049] Specifically, it can be assumed that the vehicle is in the middle of a lane with a width of 3.5 m, the width of the vehicle is 2 m (the radius of the vehicle size is 1 m), and the vehicle speed is 130 km / h. The lane line index model is established using the method of the above embodiment and simulated to obtain the simulation results as Figure 5 shown.

[0050] As Figure 5 in the simulation results, the dotted line is the avoidance trajectory of the vehicle to avoid deviating from the lane due to excessive lane line detection error; the area 1 surrounded by dots indicates that the point chain with allowable lane line detection error falls within this area, and the vehicle can avoid deviating from the lane under the avoidance trajectory in this scenario; the black solid line below is the right lane line of the lane, the black dotted line above is the left lane line of the lane, and the following table is the boundary value of the simulation results, that is, in this case, the maximum allowable detection error of the lane line detection module at different detection distances.

[0051]

[0052]

[0053]

[0054] In a further alternative embodiment, the simulation based on the driver model corresponding to the lane line position detection error and actual scenario parameters includes: temporarily storing the lane line at the far end detected by the lane line detection module as the detected lane line; when the vehicle travels to the lane line at the far end, using the detected lane line as the true value lane line; and comparing the detected lane line with the true value lane line to obtain the lane line position detection error.

[0055] Further optionally, after obtaining the lane line position detection error, the method further includes: determining whether the current detection error exceeds the maximum detection error of the current detection distance; and if the current detection error exceeds the maximum detection error of the current detection distance, recording the scenario reason for the excessive error.

[0056] In a specific example, the index requirements in the above table can be used to determine in real time whether the detection error of the lane line meets the safety requirements, and record the scenarios where the lane line error does not meet the safety index requirements. The specific operation is as follows: temporarily store the lane line at the far end detected by the lane line detection module (such as the lane line result at 120 m). When the vehicle travels to 120 m, take the lane line detected here as the true value and compare it with the temporarily stored lane line at the same position (the lane line result at the previous 120 m) to obtain the detection error of the lane line at the far end, and record the scenarios where the error exceeds the safety index requirements. Further, the recorded scenario data can be used to optimize the algorithm of the lane line detection module of the autonomous driving system in the future.

[0057] In some other alternative embodiments, the lane line detection uncertainty is the detection error of the lane center line position. Scenario modeling of the probability of a hazard event caused by the lane line detection uncertainty of the lane line detection module to obtain driver models under different hazard events includes: when there is a vehicle in the adjacent lane of the vehicle's own lane, scenario modeling of the deviation from the vehicle's own lane caused by the detection error of the lane center line position to obtain a driver model corresponding to the detection error of the lane center line position; wherein, the above scenario of deviating from the vehicle's own lane is: the vehicle has a detection error of the lane center line position, and the detection error of the lane center line position makes it impossible to correct the vehicle back to its own lane even with a lateral acceleration in the direction opposite to the deviation direction of the lane center line detection error; the quantization targets corresponding to different algorithm modules of the lane line detection module obtained at least based on the driver models under different hazard events include: at least based on the driver model corresponding to the detection error of the lane center line position, obtain the maximum offset that can keep the vehicle from deviating from its own lane using a lateral acceleration in the opposite direction, and obtain the quantization target corresponding to the detection error of the lane center line position of the autonomous driving system, wherein the detection error of the lane center line position is obtained by back-calculating through the detection error of the lane line position.

[0058] Specifically, through a method similar to the above-mentioned lane line detection error modeling and analysis, change the lane line detection error parameter to the detection error of the lane center line position, and conduct scenario modeling and analysis of the deviation from the vehicle's own lane caused by the detection error of the lane center line position, then the quantization target corresponding to the detection error of the lane center line position of the autonomous driving system can be obtained.

[0059] Further optionally, different types of lane centerline deviations include: the lane centerline deviation distance a caused by the two lane lines deviating by the same distance a in the same direction; the lane centerline having no deviation caused by the two lane lines deviating by the same distance a in different directions respectively; the lane centerline deviation (a + b) / 2 caused by the two lane lines deviating by distances a and b in the same direction respectively; and the lane centerline deviation |b - a| / 2 caused by one lane line deviating by distance b in the first direction and the other lane deviating by distance a in the second direction. Therefore, after determining the deviation direction and distance of the lane lines in the current scenario, the lane centerline position detection error can be deduced based on the lane line position detection error.

[0060] In a specific example, for the lateral position error of the lane centerline, the lateral threshold of the lane centerline can be deduced through the threshold of the lane line lateral deviation. Among them, due to the deviation of the lane lines, there are four ways in which the lane centerline deviates. Given the lateral deviation threshold of the lane lines, the method for calculating the corresponding quantization index of the lane centerline can be referred to Figures 6a - 6d .

[0061] Among them, in Figures 6a - 6d , the black solid line represents the true value of the lane line, the black dashed line represents the true value of the lane centerline, the gray solid line represents the detection result of the lane line, and the gray dashed line represents the detection result of the lane centerline.

[0062] As Figure 6a shown, when the lane lines deviate to the left simultaneously and by the same distance a, the deviation of the lane centerline is the same as that of the lane lines, and the deviation is a. As Figure 6b shown, when one lane line deviates to the left and the other deviates to the right, and the deviation distances are the same at a, there is no deviation in the lane centerline. As Figure 6c shown, when the lane lines deviate to the left simultaneously and by different distances a and b, the deviation of the lane centerline is (a + b) / 2. As Figure 6d shown, when one lane line deviates to the left and the other deviates to the right, and the deviation distances are b and a respectively, the deviation of the lane centerline is |b - a| / 2.

[0063] The embodiments of the present application also provide a method for quantitatively evaluating the safety performance of an autonomous driving system, including: evaluating the safety performance of the autonomous driving system by using the quantization target in any one of the above methods. Thus, the safety performance of the autonomous driving system can be evaluated through the quantization target. The execution subject of the embodiments of the present application can be an electronic device or a safety performance quantization evaluation device provided in the electronic device. The safety performance quantization evaluation device can be implemented by software or by a combination of software and hardware. The safety performance quantization evaluation device can be a processor in the electronic device. The electronic device can be a device installed with an autonomous driving system or other devices connected to the autonomous driving system.

[0064] In some alternative embodiments, the above-mentioned evaluation of the safety performance of the autonomous driving system includes: determining a lane line detection error based on the detected lane line position; comparing the lane line detection error with a quantization target corresponding to the lane line position detection error; and evaluating the safety performance of the autonomous driving system according to the comparison result. Thus, the lane line detection error can be determined by the above method and the safety performance of the autonomous driving system can be evaluated using this error.

[0065] In some alternative embodiments, the above-mentioned evaluation of the safety performance of the autonomous driving system includes: determining a lane center line detection error based on the detected lane center line position; comparing the lane center line detection error with a quantization target corresponding to the lane line center position detection error; and evaluating the safety performance of the autonomous driving system according to the comparison result. Thus, the lane center line detection error can be determined by the above method, and then the safety performance of the autonomous driving system can be evaluated using this lane center line error.

[0066] Further optionally, the above method further includes: if the evaluated safety performance does not meet the preset requirements, optimizing the corresponding algorithm and then performing the test evaluation again. Furthermore, when the evaluated safety performance of the lane line detection or the lane center line detection does not meet the preset requirements, the algorithm module related to the lane line detection or the lane center line detection can be optimized, and then the test evaluation is performed again until the evaluated performance meets the preset requirements. Herein, the preset requirements are that the system can meet the safety requirements according to the evaluation result of the above-mentioned evaluation of the safety performance of the autonomous driving system. In a specific example, when the maximum allowable detection error of the lane line detection module at a certain detection distance is a lateral error of 1.01 m outwards and a lateral error of 1.5 m inwards, if the lane line detection error at this detection distance exceeds the lateral error of 1.01 m outwards and the lateral error of 1.5 m inwards, for example, it is offset 1.6 m outwards on average, then according to the comparison result, this error exceeds the safety range and the evaluation is that the system does not meet the safety requirements, that is, the evaluated safety performance of this module does not meet the preset requirements, and the lane line detection algorithm needs to be optimized to meet the preset requirements.

[0067] Further optionally, the above method further includes: if the evaluated safety performance meets the preset requirements, deploying the corresponding algorithm to the autonomous driving system. Thus, when the evaluated performance meets the preset requirements, the corresponding algorithm or module can be deployed to the autonomous driving system. In a specific example, when the maximum detection error allowed by the lane line detection module at a certain detection distance is a lateral error of 0.99 m outwards and a lateral error of 1.5 m inwards, if the lane line detection error at this detection distance does not exceed a lateral error of 0.99 m outwards and a lateral error of 1.5 m inwards, for example, a lateral error of 0.8 m outwards and a lateral error of 1.2 m inwards, then according to the comparison result, this error is within the safety range, and it is evaluated that the system meets the safety requirements, that is, the evaluated safety performance of this module meets the preset requirements, and the lane line detection algorithm or module can be deployed to the autonomous driving system.

[0068] The solution for evaluating the safety performance of the autonomous driving system based on the lane center line detection error is similar to the above example and will not be elaborated here.

[0069] In some other embodiments, the embodiments of the present application further provide a non-volatile computer storage medium. The computer storage medium stores computer-executable instructions, and the computer-executable instructions can execute the method for determining the safety performance quantization index of the lane line detection module in any of the above method embodiments;

[0070] As an implementation manner, the non-volatile computer storage medium of the present application stores computer-executable instructions, and the computer-executable instructions are set as:

[0071] Obtain the lane line detection uncertainty of multiple algorithm modules of the lane line detection module, where the hazard events of the lane line detection module are decomposed into being caused by the lane line detection uncertainty of different algorithm modules of the lane line detection module;

[0072] Perform scenario modeling on the probability of the lane line detection uncertainty of the lane line detection module causing hazard events to obtain driver models under different hazard events;

[0073] Obtain the quantization targets corresponding to different algorithm modules of the lane line detection module based at least on the driver models under different hazard events.

[0074] As another implementation manner, for an autonomous driving system, the non-volatile computer storage medium of the present application stores computer-executable instructions, and the computer-executable instructions can execute the safety performance quantization evaluation method for the autonomous driving system in any of the above method embodiments. The computer-executable instructions are set as:

[0075] Evaluate the safety performance of the autonomous driving system by using the quantization targets in the method described in the above implementation method.

[0076] The non-volatile computer-readable storage medium may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the safety performance quantification index determination device of the lane line detection module or for the use of the safety performance quantification evaluation device of the autonomous driving system, etc. In addition, the non-volatile computer-readable storage medium may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the non-volatile computer-readable storage medium may optionally include a memory remotely provided relative to the processor, and these remote memories may be connected to the safety performance quantification index determination device of the lane line detection module or the safety performance quantification evaluation device for the autonomous driving system through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0077] The embodiment of the present application also provides a computer program product. The computer program product includes a computer program stored on a non-volatile computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer is enabled to execute any one of the above-mentioned safety performance quantification index determination methods of the lane line detection module and the safety performance quantification evaluation method for the autonomous driving system.

[0078] Figure 7 is a schematic structural diagram of the electronic device provided by the embodiment of the present application, as Figure 7 shown, the device includes: one or more processors 710 and a memory 720, Figure 7 Taking one processor 710 as an example. The device for the safety performance quantification index determination method of the lane line detection module or the safety performance quantification evaluation method for the autonomous driving system may further include: an input device 730 and an output device 740. The processor 710, the memory 720, the input device 730, and the output device 740 may be connected through a bus or other means, Figure 7 Taking connection through a bus as an example. The memory 720 is the above-mentioned non-volatile computer-readable storage medium. The processor 710 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions, and modules stored in the memory 720, that is, implements the safety performance quantification index determination method of the lane line detection module or the safety performance quantification evaluation method for the autonomous driving system in the above method embodiments. The input device 730 may receive input digital or character information, and generate key signal inputs related to user settings and function controls of the safety performance quantification evaluation device for the autonomous driving system. The output device 740 may include a display device such as a display screen.

[0079] An embodiment of the present application further provides a movable platform, which includes: a vehicle body, a power system, and an electronic device as described in the above embodiment. Among them, the power system is installed on the vehicle body to provide power; the principle and implementation manner of the electronic device are the same as those described in the above embodiment, and will not be elaborated here. The electronic device may be a controller installed on the movable platform, or other computing devices connected to the controller. Optionally, the movable platform includes at least one of the following: a vehicle, a movable robot, and a driverless vehicle.

[0080] The above products can execute the methods provided in the embodiments of the present application, and have corresponding functional modules and beneficial effects for executing the methods. For technical details not described in detail in this embodiment, reference can be made to the methods provided in the embodiments of the present application.

[0081] As an implementation manner, the above electronic device is applied to a device for determining the safety performance quantification index of a lane line detection module, and includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0082] Obtain the lane line detection uncertainties of multiple algorithm modules of the lane line detection module, wherein the hazard events of the lane line detection module are decomposed into being caused by the lane line detection uncertainties of different algorithm modules of the lane line detection module;

[0083] Perform scenario modeling on the probability of the hazard events caused by the lane line detection uncertainties of the lane line detection module to obtain a driver model under different hazard events;

[0084] At least obtain the quantification targets corresponding to different algorithm modules of the lane line detection module based on the driver models under different hazard events.

[0085] As an implementation manner, the above electronic device is applied to a device for quantitatively evaluating the safety performance of an autonomous driving system, and includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0086] Evaluate the safety performance of the autonomous driving system by using the quantification targets in the method described in the above implementation method.

[0087] The electronic devices in the embodiments of the present application exist in various forms, including but not limited to:

[0088] (1) Mobile communication devices: These devices are characterized by having mobile communication functions and mainly aim to provide voice and data communication. Such terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones, etc.

[0089] (2) Ultra-mobile personal computer devices: These devices belong to the category of personal computers, have computing and processing functions, and generally also have the characteristic of mobile Internet access. Such terminals include: PDA, MID, and UMPC devices, etc., such as iPad.

[0090] (3) Portable entertainment devices: These devices can display and play multimedia content. Such devices include: audio and video players (such as iPod), handheld game consoles, e-books, and intelligent toys and portable vehicle navigation devices.

[0091] (4) Servers: Devices that provide computing services. The composition of a server includes a processor, hard disk, memory, system bus, etc. Servers are similar to general computer architectures, but due to the need to provide highly reliable services, they have higher requirements in terms of processing power, stability, reliability, security, scalability, and manageability, etc.

[0092] (5) Other electronic devices with data interaction functions.

[0093] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0094] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solutions, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiments.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A method for determining a safety performance quantitative index of a lane detection module, for use in an autonomous driving system, comprising: Acquire lane line detection uncertainties of multiple algorithm modules of a lane line detection module, wherein the hazard event of the lane line detection module is decomposed into events caused by lane line detection uncertainties of different algorithm modules of the lane line detection module; Performing scenario modeling on the probability of hazardous events caused by lane detection uncertainty of the lane detection module to obtain driver models under different hazardous events; At least based on the driver model under different hazardous events, quantitative targets corresponding to different algorithm modules of the lane line detection module are obtained.

2. The method according to claim 1, characterized in that The lane line detection uncertainty of the multiple algorithm modules of the lane line detection module is obtained including: In the case where lane line detection uncertainty occurs in different algorithm modules of the lane line detection module, the lane line detection uncertainty that causes exposure of a hazardous behavior is obtained, wherein the hazardous behavior is uncontrollable.

3. The method according to claim 1, characterized in that The lane line detection uncertainty of different algorithm modules of the lane line detection module includes a lane line position detection error and a lane center line position detection error.

4. The method according to claim 3, characterized in that The lane line detection uncertainty is a lane line position detection error. The probability of a hazardous event caused by the lane line detection uncertainty of the lane line detection module is modeled in a scenario to obtain a driver model under different hazardous events, including: When there is a vehicle in the lane adjacent to the vehicle's road, scenario modeling is performed for the scenario of deviation from the vehicle's road caused by the lane line position detection error, and a driver model corresponding to the lane line position detection error is obtained; The quantitative targets corresponding to different algorithm modules of the lane detection module obtained based at least on the driver model under different hazardous events include: At least based on the driver model corresponding to the lane line position detection error, the maximum offset that can prevent the vehicle from deviating from the road using the lateral acceleration in the opposite direction is obtained, and the quantitative target corresponding to the lane line position detection error of the automatic driving system is obtained.

5. The method according to claim 4, characterized in that The quantitative target corresponding to the lane position detection error of the automatic driving system is obtained by: Simulating based on the driver model corresponding to the lane line position detection error and actual scene parameters to obtain the maximum detection error allowed by the lane line detection model at different detection distances; The maximum detection error allowed at the different detection distances is used as a quantitative target corresponding to the lane line position detection error of the automatic driving system.

6. The method according to claim 5, characterized in that The simulation based on the driver model corresponding to the lane line position detection error and the actual scene parameters includes: Temporarily storing the far lane line detected by the lane line detection module as the detected lane line; When the vehicle drives to the lane line at the far end, the detected lane line is used as the true lane line; The detected lane line is compared with the true value lane line to obtain a lane line position detection error.

7. The method according to claim 6, characterized in that After obtaining the lane line position detection error, the method further includes: Determine whether the current detection error exceeds the maximum detection error of the current detection distance; If the current detection error exceeds the maximum detection error of the current detection distance, the scene reason causing the excessive error is recorded.

8. The method according to claim 4, characterized in that The lane line detection uncertainty is the lane center line position detection error. The probability of a hazardous event caused by the lane line detection uncertainty of the lane line detection module is modeled by scenarios to obtain driver models under different hazardous events, including: When there is a vehicle in the lane adjacent to the vehicle's road, a scene modeling is performed for the deviation from the vehicle's road caused by the lane centerline position detection error to obtain a driver model corresponding to the lane centerline position detection error; The quantitative targets corresponding to different algorithm modules of the lane detection module obtained based at least on the driver model under different hazardous events include: At least based on the driver model corresponding to the lane centerline position detection error, a maximum offset that can prevent the vehicle from deviating from the road of the vehicle by using lateral acceleration in the opposite direction is obtained, and a quantitative target corresponding to the lane centerline position detection error of the automatic driving system is obtained, wherein the lane centerline position detection error is obtained by reverse deducing the lane line position detection error.

9. The method according to claim 8, characterized in that Different types of lane centerline deviation include: The two lane lines deviate in the same direction by a distance, resulting in a deviation of the lane centerline by a distance; The two lane lines deviate by the same distance a in different directions, resulting in no deviation in the center line of the lane; The two lane lines deviate in the same direction by distances a and b respectively, resulting in a lane centerline deviation of (a+b) / 2; and One lane deviates by a distance b in a first direction, and the other lane deviates by a distance a in a second direction, resulting in a lane centerline deviation of |ba| / 2.

10. A method for quantifying the safety of an autonomous driving system, characterized in that: include: The safety performance of the autonomous driving system is evaluated using the quantitative objectives in the method described in any one of claims 1-9.

11. The method according to claim 10, characterized in that The evaluating the safety performance of the autonomous driving system comprises: Determine the lane line detection error through the detected lane line position; Comparing the lane line detection error with the quantized target corresponding to the lane line position detection error; Based on the comparison results, the safety performance of the autonomous driving system is evaluated.

12. The method according to claim 10, characterized in that The evaluating the safety performance of the autonomous driving system comprises: Determine the lane centerline detection error through the detected lane centerline position; Comparing the lane centerline detection error with a quantized target corresponding to the lane center position detection error; Based on the comparison results, the safety performance of the autonomous driving system is evaluated.

13. The method according to claim 11 or 12, characterized in that: Also includes: If the evaluated safety performance does not meet the preset requirements, the corresponding algorithm will be optimized and tested again.

14. The method according to claim 11 or 12, characterized in that: Also includes: If the evaluated safety performance meets the preset requirements, the corresponding algorithm will be deployed to the autonomous driving system.

15. An electronic device, comprising: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the method described in any one of claims 1 to 14.

16. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 14 are implemented.

17. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 14 are implemented.

18. A movable platform comprising the electronic device according to claim 15.

Images