A method and device for constructing high-risk scenarios involving following and alongside other vehicles.

Abstract

This application provides a method and electronic device for constructing high-risk scenarios in following and side-by-side vehicle insertion scenarios. The method includes: acquiring scenario elements to be tested in the following and side-by-side vehicle insertion scenarios; using Spearman correlation test to select scenario elements with strong correlation to driving risk from the scenario elements to be tested, and constructing a dangerous scenario; calculating the headway between the selected vehicle and the vehicle in front in the dangerous scenario; simulating the motion state of the vehicle, calculating the relative distance between the vehicle and the vehicle in front in real time, and determining the relative distance between the two vehicles when both the vehicle and the vehicle in front brake to a stop when their speeds are both 0; and constructing a high-risk scenario based on the headway between the vehicle and the vehicle in front and the relative distance between the two vehicles when they brake to a stop. This solution helps improve the efficiency of autonomous driving system detection and reduce detection costs.

Description

Technical Field

[0001] This invention belongs to the field of autonomous driving test scenario construction technology, and specifically relates to a method and device for constructing high-risk scenarios such as following and side-by-side vehicle insertion scenarios. Background Technology

[0002] With the introduction of a series of strategic plans in my country, such as "Made in China 2025," "Internet Plus," and the Intelligent Manufacturing Development Plan, the primary task for all industries is to promote the deep integration of the Internet of Things, big data, artificial intelligence, and the real economy, and to develop advanced manufacturing, with the goal of comprehensively supporting the construction of a manufacturing powerhouse and a cyber powerhouse. As a core indicator of a country's manufacturing level, the automotive industry has made the deployment of autonomous vehicles on real roads a key development goal. Autonomous driving testing and performance evaluation are crucial steps in promoting the maturity of intelligent vehicles.

[0003] Considering the numerous factors that can affect the actual deployment of intelligent vehicles, leading to varying degrees of safety issues, it is necessary to utilize specially constructed high-test-demand scenarios for comprehensive testing and evaluation to ensure the safety of autonomous vehicles. Furthermore, although there has been considerable research both domestically and internationally on methods for constructing test scenarios for autonomous vehicles, the spatial elements of road traffic are infinite, resulting in an endless set of test scenarios that cannot guarantee comprehensive testing.

[0004] To enrich the dataset of autonomous driving test scenarios and improve testing efficiency and reliability to ensure the safety of autonomous driving systems, this invention proposes a method for constructing high-risk scenarios involving following and side-by-side vehicle insertion. This method involves real-time simulation of vehicle states and iterative calculation of scenario selection indicators. It provides technical support and theoretical backing for the targeted construction of test scenarios that meet high-level and stringent requirements, thereby improving the testing efficiency of autonomous driving systems, reducing testing costs, and accelerating the deployment and application of intelligent vehicles. Summary of the Invention

[0005] The purpose of the embodiments in this specification is to provide a method and device for constructing high-risk scenarios involving following or alongside other vehicles.

[0006] To solve the above-mentioned technical problems, the embodiments of this application are implemented in the following ways:

[0007] Firstly, this application provides a method for constructing high-risk scenarios involving following or side-by-side vehicles, the method comprising:

[0008] Obtain the scene elements to be tested from the following and adjacent vehicle insertion scenarios;

[0009] Using the Spearman correlation test, scene elements with strong correlation to driving risks are selected from the scene elements to be tested, and dangerous scenarios are constructed.

[0010] Calculate the headway between the selected vehicle and the vehicle in front in a hazardous scenario;

[0011] Simulate the motion state of the vehicle, calculate the relative distance between the vehicle and the vehicle in front in real time, and determine the relative distance between the two vehicles when they brake to a stop when both the vehicle and the vehicle in front have a speed of 0.

[0012] High-risk scenarios are constructed based on the headway between the vehicle and the vehicle in front and the relative distance between the two vehicles when they brake to a stop.

[0013] In one embodiment, the Spearman correlation test is used to filter out scene elements with strong correlation to driving risks from the scene elements to be tested, and to construct a hazardous scene, including:

[0014] Obtain the element variables and corresponding driving risks of the scene elements to be tested, sort all element variables and driving risks from low to high, and determine the first rank corresponding to each element variable and the second rank corresponding to each driving risk.

[0015] Based on all first-rank and second-rank variables, determine the Spearman correlation coefficients of each element variable and the corresponding driving risks;

[0016] Filter the scene elements corresponding to Spearman correlation coefficients that meet the criteria;

[0017] Construct dangerous scenarios based on the selected scene elements.

[0018] In one embodiment, the Spearman correlation coefficient P between each element variable and its corresponding driving risk is determined based on all first-rank and second-rank variables. i for:

[0019]

[0020] in, Among them, R i For first rank, H i It is the second rank, R i and H i X i Y i rank, X i Y is an element variable. i For X i The corresponding driving risks.

[0021] In one embodiment, the scene elements corresponding to the Spearman correlation coefficients that meet the criteria are selected as follows:

[0022] Spearman correlation coefficient P i Satisfy -1 <P i<-0.5 and 0.5 <P i <1 corresponds to the scene element.

[0023] In one embodiment, the headway THW between the selected vehicle and the vehicle in front in the hazardous scenario is calculated as follows:

[0024]

[0025] Among them, S n (t) represents the distance between the front ends of the vehicle and the vehicle in front at time t; v n (t) represents the vehicle speed at time t.

[0026] In one embodiment, an intelligent driver model is used to simulate the vehicle's motion state, wherein the intelligent driver model is:

[0027]

[0028]

[0029] In the formula: a n (t) represents the acceleration of the vehicle at time t; a max v is the maximum acceleration expected by the driver of the vehicle. n (t) represents the vehicle speed at time t; v max S is the speed desired by the driver; σ is the acceleration parameter; S n (t) represents the distance between the front ends of the two vehicles at time t; St represents the expected headway between the two vehicles at time t; S0 represents the expected headway between the two vehicles when the driver of the self-vehicle stops; S1 represents the distance parameter; T represents the expected headway between the two vehicles by the driver of the self-vehicle; Δv n (t) represents the speed difference between the vehicle and the vehicle in front; b represents the deceleration expected by the driver of the vehicle.

[0030] In one embodiment, the motion state of the vehicle is simulated, the relative distance between the vehicle and the vehicle in front is calculated in real time, and the relative distance between the two vehicles when they brake to a stop is determined when both the vehicle and the vehicle in front have a speed of 0. This includes:

[0031] Obtain the scene elements of the own vehicle and the vehicle in front in the dangerous scenario at the moment t1 when the vehicle in front begins braking. The scene elements of the own vehicle and the vehicle in front include: the speed of the vehicle in front v0, and the speed of the own vehicle v. n (t1), the distance between the front ends of the two vehicles S n (t1), the speed difference between the two vehicles Δv n (t1);

[0032] By incorporating the scene elements of the vehicle and the vehicle in front into the intelligent driver model, the acceleration 'a' of the vehicle at time t1 is calculated. n (t1);

[0033] The state of each vehicle at time t2 is determined based on its state at time t1, where the difference between time t2 and time t1 is Δt.

[0034] Speed ​​of the vehicle in front: v(t2)=v0-a·Δt

[0035] Vehicle speed: v n (t2)=v n (t1)-a n (t1)·Δt

[0036] Speed ​​difference between the two vehicles: Δv n (t2)=v n (t2)-v(t2)=[v n (t1)-a n [(t1)·Δt]-[v0-a·Δt]

[0037] Position of the car in front:

[0038] The vehicle's location:

[0039] Calculate the distance S between the two vehicles at time t2 based on the positions of the vehicle in front and the vehicle itself. n (t2):

[0040] S n (t2)=S n (t1)+D 前 (t2)-D 自 (t2)

[0041] This process continues until t. n The calculation stops when both vehicles reach a speed of 0, and the relative distance after braking to a stop at that moment is calculated:

[0042] D IDM (t n ) = S n (t n )-l A

[0043] Among them, l A The length of the vehicle in front.

[0044] In one embodiment, a high-risk scenario is constructed based on the headway between the vehicle and the vehicle in front and the relative distance between the two vehicles when they brake to a stop, including:

[0045] High-risk scenarios are constructed by selecting scenarios from dangerous scenarios that simultaneously satisfy the conditions that the headway between the vehicle and the vehicle in front is less than or equal to a preset time and the relative distance between the two vehicles when they brake to a stop is less than or equal to a preset distance.

[0046] In one embodiment, the method further includes:

[0047] In a high-risk scenario, a vehicle is randomly selected as the driver, and scene elements at time t are extracted: the driver's speed v. n (t), the speed difference between the two vehicles Δv n (t), the distance between the front ends of the two vehicles S n (t);

[0048] Based on the scene elements at time t, recalculate the headway between the vehicle and the vehicle in front, as well as the relative distance between the two vehicles when they brake to a stop.

[0049] The high-risk scenario is updated based on the recalculated headway between the vehicle and the vehicle in front, as well as the relative distance between the two vehicles when they brake to a stop.

[0050] Secondly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements a high-risk scenario construction method for following and side-by-side vehicle insertion scenarios as described in the first aspect.

[0051] As can be seen from the technical solutions provided in the embodiments of this specification above, this solution: constructs comprehensive and diverse test scenario data for following and side-by-side vehicles in high-risk scenarios, which can improve the testing efficiency of autonomous driving systems and reduce testing costs. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 A flowchart illustrating the high-risk scenario construction method for following and side-by-side vehicle insertion scenarios provided in this application;

[0054] Figure 2 A classification diagram of the elements of the following vehicle scenario provided in this application;

[0055] Figure 3 This is a schematic diagram of the relative distance between the two vehicles at time t2 provided in this application;

[0056] Figure 4 A high-risk scenario screening diagram provided for this application;

[0057] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0058] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0059] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0060] Various modifications and variations can be made to the specific embodiments described in this application without departing from the scope or spirit of this application, as will be apparent to those skilled in the art. Other embodiments derived from this application will be obvious to those skilled in the art. This application specification and embodiments are merely exemplary.

[0061] The terms “include,” “including,” “have,” “contain,” etc., used in this article are all open-ended terms, meaning that they include but are not limited to.

[0062] Unless otherwise specified, "parts" in this application refers to parts by weight.

[0063] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0064] Reference Figure 1 The diagram illustrates a flowchart of a high-risk scenario construction method applicable to following and side-by-side vehicle insertion scenarios provided in the embodiments of this application. The premise for using this method is that the scenario elements constituting the test scenario and their corresponding driving risk levels can be obtained by any method, assuming that the driving risk levels corresponding to the scenario elements are known; and that a scenario constructed from scenario elements with a high correlation to their corresponding driving risks is considered a high-risk scenario, referred to as a dangerous scenario.

[0065] like Figure 1 As shown, a method for constructing high-risk scenarios involving following or alongside other vehicles may include:

[0066] S110: Obtain the scene elements to be tested from the following and adjacent vehicle insertion scenes.

[0067] Specifically, taking the construction of a vehicle-following scenario as an example (the following explanations will all use vehicle-following scenario construction as an example), the classification of vehicle-following scenario elements (or scenario elements, i.e., the scenario elements to be tested) is as follows: Figure 2 As shown, it includes two main categories: traffic environment elements and scene subject elements, as well as 10 subcategories such as weather and lighting. Among them, traffic environment elements include weather type, lighting conditions, road type, and traffic density in the following scenario, while scene subject elements include vehicle type, vehicle position, and movement status of the self vehicle and the target vehicle.

[0068] S120. Using the Spearman correlation test, select scene elements with strong correlation to driving risks from the scene elements to be tested, and construct hazardous scenarios, including:

[0069] Obtain the element variables and corresponding driving risks of the scene elements to be tested, sort all element variables and driving risks from low to high, and determine the first rank corresponding to each element variable and the second rank corresponding to each driving risk.

[0070] Based on all first-rank and second-rank variables, determine the Spearman correlation coefficients of each element variable and the corresponding driving risks;

[0071] Filter the scene elements corresponding to Spearman correlation coefficients that meet the criteria;

[0072] Construct dangerous scenarios based on the selected scene elements.

[0073] Specifically, Spearman Rank Correlation is a statistical method used to evaluate the correlation between two variables. Its most significant characteristic is that it does not require consideration of sample size or population distribution characteristics, making it quick and robust. Spearman Rank Correlation requires that the two variables be paired ordinal ratings, or ordinal data transformed from continuous variable observations, without needing to consider the population distribution or sample size. Since the focus is on examining the correlation between scene elements and their corresponding driving risks, which involves correlation analysis between continuous data and categorized data, Spearman Rank Correlation analysis is a more appropriate choice.

[0074] The Spearman correlation test is performed as follows:

[0075] Let X be the variable of each following scenario element to be tested, and Y be the corresponding driving risk. Sort the scenario element variables and their corresponding driving risks from low to high:

[0076] X = {X1, X2, ..., X} n}

[0077] Y = {Y1,Y2,…,Y} n}

[0078] Where n is the number of scene elements to be tested, X i Let Y be the i-th element variable. i For X i The corresponding driving risks, where i = 1, 2, ..., n. The driving risks corresponding to the state of each scene element are analyzed independently and do not affect each other. For example, X1 and Y1 are analyzed independently, X... n and Y n Independent analysis.

[0079] The permutations of X and Y are as follows:

[0080] R = {R1, R2, ..., R} n}

[0081] S = {S1,S2,…,S} n}

[0082] R i S i X i Y i Rank.

[0083] Calculate the X of various scene elements i Corresponding driving risk Y i The Spearman correlation coefficient (or simply correlation coefficient) between them. i :

[0084]

[0085] In the formula:

[0086] The above tests were performed on each element of the following vehicle scenario.

[0087] In order to screen scene elements that are highly correlated with driving risks and thus construct dangerous scenarios of following and side-car insertion, scene elements with a correlation coefficient close to 1 or -1 are selected, i.e., those satisfying -1. <P i <-0.5, 0.5 <P i Scene elements with a value between 1 and 1 are considered dangerous scenes.

[0088] The Spearman correlation coefficient is a nonparametric indicator that measures the dependence between two variables. It ranges from -1 to +1, with 0 indicating no correlation between the two variables. If there are no duplicate values ​​in the data and the two variables are perfectly monotonically correlated, the Spearman correlation coefficient is +1 or -1. When X increases, Y tends to increase; the Spearman correlation coefficient is positive. Conversely, when X increases and Y tends to decrease, the Spearman correlation coefficient is negative.

[0089] The purpose of this step is to filter scenario elements that are highly correlated with driving risks, thereby constructing dangerous scenarios of following and side-car insertion. Therefore, the range of correlation coefficients is selected as -1. <P i <-0.5 and 0.5 <P i <1, construct a hazardous scenario based on the corresponding scenario elements to be tested within this range.

[0090] S130. Calculate the time headway (THW) between the selected vehicle and the vehicle in front in the hazardous scenario:

[0091]

[0092] Among them, S n (t) represents the distance (m) between the front ends of the two vehicles at time t; v n (t) represents the vehicle speed (m / s) at time t.

[0093] S140. Use an intelligent driver model (IDM) to simulate the motion state of the vehicle, calculate the relative distance between the vehicle and the vehicle in front in real time, and determine the relative distance between the two vehicles when they brake to a stop when both the vehicle and the vehicle in front have a speed of 0.

[0094] Specifically, the Intelligent Driver Model (IDM) is a continuous function that considers the driver's speed, the distance between the front and rear vehicles, and the speed difference between the two vehicles. It is a commonly used car-following model. This model uses the driver's acceleration to describe the vehicle's car-following state and can fit the vehicle trajectory data during the car-following process well. Its numerical simulation matches the actual data, and it can reproduce complex macroscopic traffic phenomena. It has a wide range of applications and can describe both free flow and congested flow. Therefore, the IDM vehicle car-following model was chosen to simulate the state of the vehicles in front and behind.

[0095] The IDM model is as follows:

[0096]

[0097]

[0098] In the formula: a n (t) represents the acceleration of the vehicle at time t; amax v is the maximum acceleration expected by the driver of the vehicle. n (t) represents the vehicle speed at time t; v max S is the speed desired by the driver; σ is the acceleration parameter, which can be 4; S n (t) represents the distance between the front ends of the two vehicles at time t; St represents the expected headway between the two vehicles at time t; S0 represents the expected headway between the two vehicles when the driver of the self-vehicle stops; S1 is a distance parameter, which can be 0; T represents the expected headway between the two vehicles by the driver of the self-vehicle; Δv n (t) represents the speed difference between the vehicle and the vehicle in front; b represents the deceleration expected by the driver of the vehicle.

[0099] The values ​​for the above indicators can be found in Table 1:

[0100] Table 1 Reference Values ​​for IDM Model Indicators

[0101] parameter describe Minimum value Maximum value unit <![CDATA[a max ]]> The maximum acceleration expected by the driver 0 8 <![CDATA[m / s 2 ]]> b The deceleration that the driver expects to use 0 8 <![CDATA[m / s 2 ]]> <![CDATA[v max ]]> Expected speed 14 40 m / s <![CDATA[S0]]> Desired front-end clearance when parking 1 5 m T Expected safe headway 0 4 s

[0102] In one implementation case, the motion state of the vehicle is simulated, the relative distance between the vehicle and the vehicle in front is calculated in real time, and the relative distance between the two vehicles when they brake to a stop is determined when both the vehicle and the vehicle in front have a speed of 0. This includes:

[0103] Obtain the scene elements of the own vehicle and the vehicle in front in the dangerous scenario at the moment t1 when the vehicle in front begins braking. The scene elements of the own vehicle and the vehicle in front include: the speed of the vehicle in front v0, and the speed of the own vehicle v. n (t1), the distance between the front ends of the two vehicles S n (t1), the speed difference between the two vehicles Δv n (t1);

[0104] By incorporating the scene elements of the vehicle and the vehicle in front into the intelligent driver model, the acceleration 'a' of the vehicle at time t1 is calculated. n (t1);

[0105] The state of each vehicle at time t2 is determined based on its state at time t1, where the difference between time t2 and time t1 is Δt.

[0106] Speed ​​of the vehicle in front: v(t2)=v0-a·Δt

[0107] Vehicle speed: v n (t2)=v n (t1)-a n (t1)·Δt

[0108] Speed ​​difference between the two vehicles: Δv n (t2)=v n (t2)-v(t2)=[v n (t1)-a n[(t1)·Δt]-[v0-a·Δt]

[0109] Position of the car in front:

[0110] The vehicle's location:

[0111] Here, 'a' refers to the acceleration of the vehicle in front, which is considered to be known and constant.

[0112] Based on the position of the vehicle and the position of the vehicle in front at time t2, such as Figure 3 As shown, calculate the distance S between the front ends of the two vehicles at time t2. n (t2) and the relative distance D between the two vehicles IDM (t2):

[0113] S n (t2)=S n (t1)+D 前 (t2)-D 自 (t2)

[0114] D IDM (t2)=S n (t2)-l A

[0115] Among them, l A The length of the vehicle in front.

[0116] Based on the calculated state at time t2: v n (t2), S n (t2), Δv n Substituting (t2) back into the IDM model, we can calculate the vehicle acceleration a at time t2. n (t2);

[0117] Then, based on the state at time t2, determine the state at time t3, substitute it back into the IDM model, calculate and determine the state at time t4, and repeat this process until t3. n The calculation stops when both vehicles reach a speed of 0, and the relative distance after braking to a stop at that moment is calculated:

[0118] D IDM (t n ) = S n (t n )-l A

[0119] Among them, l A This is the current vehicle length.

[0120] S150. Based on the headway between the vehicle and the vehicle in front and the relative distance between the two vehicles when they brake to a stop, construct high-risk scenarios, including:

[0121] High-risk scenarios are constructed by selecting scenarios from dangerous scenarios that simultaneously satisfy the conditions that the headway between the current vehicle and the following vehicle is less than or equal to a preset time and the relative distance between the two vehicles when they brake to a stop is less than or equal to a preset distance.

[0122] Specifically, both the preset duration and preset distance can be set according to actual needs. For example, the preset duration is 2 seconds and the preset distance is 1 meter. Figure 4 The relative distance D shown satisfies the braking and stopping conditions of the two vehicles. IDM (t n Scenarios where the distance between the front ends of the two vehicles is less than 1 meter and the distance between the front ends of the two vehicles is less than 2 seconds are considered high-risk scenarios.

[0123] In one embodiment, the method for constructing high-risk scenarios involving following or side-by-side vehicles further includes:

[0124] In a high-risk scenario, randomly select one vehicle as the driver and extract the scene elements at time t: the speed v of the following vehicle. n (t), the speed difference between the two vehicles Δv n (t), the distance between the front ends of the two vehicles S n (t);

[0125] Based on the scene elements at time t, recalculate the headway between the vehicle and the vehicle in front, as well as the relative distance between the two vehicles when they brake to a stop.

[0126] The high-risk scenario is updated based on the recalculated headway between the vehicle and the vehicle in front, as well as the relative distance between the two vehicles when they brake to a stop.

[0127] This application provides a method for constructing high-risk scenarios for following and side-by-side vehicle insertion scenarios. Based on the field of autonomous driving testing, it focuses on the problem that current testing scenarios cannot meet the needs of autonomous driving testing. It innovatively proposes a method for constructing high-risk scenarios for following and side-by-side vehicle insertion scenarios. The Spearman correlation test is used to reduce the dimensionality of the elements of the following and side-by-side vehicle insertion scenarios to construct dangerous scenarios. Then, the time distance between the vehicle and the front is calculated (THW). The IDM model is used to simulate the state of the vehicle at different times and calculate the relative distance between the two vehicles after braking and stopping. The THW and the relative distance between the two vehicles after braking and stopping are used as indicators to screen out high-risk scenarios and continuously supplement and correct them.

[0128] Its application value lies in the fact that this method of constructing scenarios enriches the dataset of test scenarios for autonomous vehicles, reduces the R&D costs of autonomous vehicles, and improves the efficiency of autonomous driving simulation testing. It can specifically meet the testing needs of autonomous driving systems, improve the safety of autonomous vehicles, and promote the deployment and application of autonomous vehicles on real roads.

[0129] Specific application examples:

[0130] ① To enrich more test scenario data: First, based on the high-risk scenario construction method provided in this application, the basic scenarios (i.e. dangerous scenarios) of typical following and side-car insertion scenarios are determined. Then, the elements of different dangerous scenarios are extracted and the two indicators of THW and the relative distance between the two vehicles after braking and stopping are recalculated. High-risk scenarios are screened and continuously supplemented and improved, thereby achieving the purpose of enriching test scenario data.

[0131] ② To improve the efficiency of autonomous driving simulation testing: First, a relatively complete high-risk scenario can be constructed based on the high-risk scenario construction method. Then, the autonomous driving system is simulated and tested in the constructed high-risk scenario, thereby detecting the deficiencies of the autonomous driving system's capabilities and discovering its problems. This helps to improve the efficiency of autonomous driving system testing and reduce testing costs.

[0132] In summary, the high-risk scenario construction method for following and side-by-side vehicle insertion scenarios provided in this application generates comprehensive and diverse test scenario data in these scenarios, providing a theoretical basis and technical support for improving the testing efficiency and reducing the testing cost of autonomous driving systems.

[0133] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 5 The diagram shows a structural schematic of an electronic device 500 suitable for implementing embodiments of this application.

[0134] like Figure 5 As shown, the electronic device 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage section 508 into a random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the device 500. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0135] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 506 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0136] In particular, according to embodiments of this disclosure, the above references Figure 1 The described process can be implemented as a computer software program. For example, embodiments of this disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program containing program code for performing the high-risk scenario construction method for the above-described following and side-by-side vehicle insertion scenarios. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511.

[0137] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated 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 diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0138] The units or modules described in the embodiments of this application can be implemented in software or hardware. The described units or modules can also be located in a processor. The names of these units or modules do not necessarily constitute a limitation on the unit or module itself.

[0139] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, a laptop computer, a mobile phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0140] It should be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0141] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

Claims

1. A high-risk scene construction method of a car-following, car-passing insertion scene, characterized in that, The method comprises: acquiring a scene element to be inspected in a following vehicle insertion scene or a side-by-side vehicle insertion scene; screening a scene element with a relatively strong correlation with driving risk from the scene element to be inspected by using a Spearman correlation test to construct a dangerous scene; calculating a headway time of a selected ego vehicle and a front vehicle in the dangerous scene; simulating a motion state of the ego vehicle, calculating a relative distance between the ego vehicle and the front vehicle in real time, and determining a relative distance at which the ego vehicle and the front vehicle stop by braking when the speeds of the two vehicles are both 0, comprising: simulating the motion state of the ego vehicle by using an intelligent driver model, wherein the intelligent driver model is: In the formula: is the acceleration of the ego vehicle at time t; is the maximum acceleration expected by the ego vehicle driver; is the speed of the ego vehicle at time t; is the speed expected by the driver; is the acceleration parameter; is the headway between the two vehicles at time t; is the headway expected by the ego vehicle at time t; is the headway expected by the ego vehicle driver when stopping; is the distance parameter; T is the headway expected by the ego vehicle driver; is the speed difference between the ego vehicle and the preceding vehicle; b is the deceleration expected by the ego vehicle driver; The time when the preceding vehicle starts braking before the acquisition The scene elements of the ego vehicle and the preceding vehicle in the dangerous scene, the scene elements of the ego vehicle and the preceding vehicle comprising: a speed of the preceding vehicle , a speed of the ego vehicle , a headway between the two vehicles , a speed difference between the two vehicles ; a refers to an acceleration of the preceding vehicle; Substitute the scene elements of the ego vehicle and the preceding vehicle into the intelligent driver model to calculate the acceleration of the ego vehicle at the moment ; According to The state determination The state determination The state determination The state determination : Front vehicle speed: Host vehicle speed: Speed difference between two vehicles: Position of the preceding vehicle: Position of the ego vehicle: According to the position of the preceding vehicle and the position of the own vehicle at the time point, the vehicle-to-vehicle distance at the time point is calculated :​ This cycle until When the speed of both vehicles is 0, stop calculating and calculate the relative distance after braking at this time: wherein L is the front vehicle length; constructing a high-risk scene according to the headway time of the ego vehicle and the front vehicle and the relative distance at which the two vehicles stop by braking.

2. The method of claim 1, wherein, The screening of a scene element with a relatively strong correlation with driving risk from the scene element to be inspected by using a Spearman correlation test to construct a dangerous scene comprises: acquiring element variables of the scene element to be inspected and corresponding driving risks, and sorting all element variables and driving risks from low to high, and determining a first rank of each element variable and a second rank of each driving risk; determining a Spearman correlation coefficient of each element variable and corresponding driving risk according to all first ranks and second ranks; screening a scene element corresponding to a Spearman correlation coefficient meeting a condition; constructing the dangerous scene according to the screened scene element.

3. The method of claim 2, wherein, the spearman correlation coefficient of each element variable and the corresponding driving risk is determined according to all the first ranks and the second ranks is: wherein, , wherein, is a first rank, is a second rank, and are respectively , rank of, is an element variable, is a corresponding driving risk.

4. The method of claim 2, wherein, The screening of a scene element corresponding to a Spearman correlation coefficient meeting a condition comprises: Spearman's correlation coefficient satisfies and corresponding scene elements.

5. The method of claim 1, wherein, The calculation of the headway time THW of the selected ego vehicle and the front vehicle in the dangerous scene comprises: wherein, is the distance between the two vehicle heads at time t; is the speed of the ego vehicle at time t.

6. The method of claim 1, wherein, The construction of a high-risk scene according to the headway time of the ego vehicle and the front vehicle and the relative distance at which the two vehicles stop by braking comprises: screening a scene from the dangerous scene that simultaneously meets the headway time of the ego vehicle and the front vehicle being less than or equal to a preset time length and the relative distance at which the two vehicles stop by braking being less than or equal to a preset distance to construct the high-risk scene.

7. The method of claim 1, wherein, The method further comprises: In the high-risk scene, one vehicle in the scene is randomly selected as the ego vehicle, and the scene elements at time t are extracted: the speed of the ego vehicle at time t , the speed difference between the ego vehicle and the preceding vehicle , the distance between the two vehicle heads at time t ; re-calculating the headway time of the ego vehicle and the front vehicle and the relative distance at which the two vehicles stop by braking according to a scene element at a time t; updating the high-risk scene according to the re-calculated headway time of the ego vehicle and the front vehicle and the relative distance at which the two vehicles stop by braking.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the following vehicle insertion scene or the side-by-side vehicle insertion scene high-risk scene construction method according to any one of claims 1-7 when executing the program.

Images