Method, device, equipment, and storage medium for constructing intersection collision accident simulation scenarios

Abstract

The present application discloses a method and apparatus, device, and storage medium for constructing a simulation scenario for an intersection collision accident. The method comprises: obtaining drive test data of an intersection area, the drive test data including lane sequence information at the intersection, obstacle vehicle status information, and host vehicle status information; when determining that the host vehicle satisfies pre-collision determination conditions between the host vehicle and the obstacle vehicle based on the lane sequence information at the intersection, the obstacle vehicle status information, and the host vehicle status information, extracting a first time when the host vehicle enters a collision state with the obstacle vehicle and a second time when the host vehicle performs an emergency braking action; intercepting drive test data within a time period from the first time to the second time from the drive test data to obtain drive test data when the host vehicle enters a collision state with the obstacle vehicle; and constructing an intersection collision accident simulation scenario based on the drive test data when the host vehicle enters a collision state with the obstacle vehicle. The present application can reduce the use of human resources, simplify the operation process, improve the efficiency of simulation scenario construction, and make the simulation scenario quality more objective.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method, device, equipment, and storage medium for constructing a simulation scenario for an intersection collision accident. Background Art

[0002] In the field of autonomous driving technology, using drive test data for simulation is a common approach. However, the volume of drive test data is extremely large and cannot be directly used for simulation. Existing simulation scenario construction techniques often require annotators to manually annotate a complete set of drive test data according to the requirements of different simulation scenarios. They then extract the drive test data corresponding to the annotated locations to construct the corresponding simulation scenarios. For example, an intersection collision accident occurs when an autonomous vehicle (i.e., the driver) collides with an obstacle vehicle at an intersection. Before simulating this intersection collision accident, a simulation scenario for the intersection collision accident is typically constructed. Before constructing this intersection collision accident simulation scenario, annotators must identify the intersection collision accident based on the complete drive test data, manually annotate the start and end times of the collision accident, and then, using the annotated start and end times as time nodes, extract the drive test data segments corresponding to these start and end times from the annotated complete drive test data to construct the intersection collision accident simulation scenario.

[0003] However, the existing simulation scene construction methods have the following problems: the existing simulation scene construction methods not only require a large amount of human resources, are cumbersome to operate, and have low efficiency in simulation scene construction, but also the quality of the simulation scene mainly depends on the experience of the annotator. Different annotators may obtain different annotation results, resulting in a lack of objectivity in the quality of the simulation scene. Summary of the Invention

[0004] To this end, the technical problem solved by the embodiments of the present application is to provide a method and device, equipment, and storage medium for constructing a simulation scene of an intersection collision accident, which can not only effectively reduce the use of human resources, greatly simplify the operation process, and improve the efficiency of simulation scene construction, but also make the quality of the simulation scene more objective.

[0005] In order to solve the above technical problems, the technical solutions adopted in this application are as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for constructing a simulation scenario of an intersection collision accident, comprising:

[0007] Acquire drive test data of the intersection area, wherein the drive test data includes lane sequence information of the intersection, state information of the obstacle vehicle, and state information of the host vehicle;

[0008] When it is determined that the host vehicle meets the pre-collision determination condition between the host vehicle and the obstacle vehicle based on the lane sequence information of the intersection, the obstacle vehicle status information, and the host vehicle status information, extracting a first time when the host vehicle enters a collision state with the obstacle vehicle and a second time when the host vehicle performs an emergency braking action;

[0009] intercepting the drive test data within a time period from the first time to the second time from the drive test data, and obtaining the drive test data of the main vehicle entering a collision state with the obstacle vehicle;

[0010] The intersection collision accident simulation scenario is constructed based on the road test data of the main vehicle entering a collision state with the obstacle vehicle.

[0011] Optionally, the pre-collision judgment conditions between the main vehicle and the obstacle vehicle include: the main vehicle passes through the intersection area, the main vehicle brakes suddenly in the intersection area, the obstacle vehicle is within the intersection area, the intersection lane sequence information of the obstacle vehicle and the main vehicle are different or the obstacle vehicle and the main vehicle turn in the same direction, the minimum distance between the obstacle vehicle and the main vehicle in the intersection area is less than a preset distance, and the lane sequence information of the obstacle vehicle and the main vehicle is identifiable.

[0012] Optionally, the intersection lane sequence information includes several lane lines, several intersection start stop lines and several intersection end stop lines; any intersection start stop line, any intersection end stop line, and the lane line connecting any intersection start stop line and any intersection end stop line constitute a lane sequence set.

[0013] Optionally, the host vehicle status information includes host vehicle position information; the host vehicle lane sequence information is identifiable, wherein the host vehicle lane sequence information identification method includes:

[0014] Determine whether the starting stop line and the ending stop line of the intersection of the host vehicle are determined:

[0015] If yes, then obtain the lane sequence of the host vehicle according to the intersection start stop line and the intersection end stop line;

[0016] If not, the lane sequence of the host vehicle is determined according to the host vehicle position information.

[0017] Optionally, the barrier vehicle status information includes barrier vehicle position information; the barrier vehicle lane sequence information is identifiable, wherein the barrier vehicle lane sequence information identification method includes:

[0018] Determine whether the starting stop line and the ending stop line of the intersection of the obstacle vehicle are determined:

[0019] If yes, then the lane sequence of the obstacle vehicle is obtained according to the starting stop line and the ending stop line of the intersection;

[0020] If not, the lane sequence of the obstacle vehicle is determined according to the position information of the obstacle vehicle.

[0021] Optionally, after constructing the intersection collision accident simulation scenario based on the road test data of the main vehicle entering a collision state with an obstacle vehicle, the method further includes:

[0022] After constructing the intersection collision accident simulation scenario based on the road test data of the main vehicle entering a collision state with the obstacle vehicle, an evaluation index of the simulation scenario is configured to determine whether the simulated vehicle reproduces the intersection collision accident in the intersection collision accident simulation scenario.

[0023] Optionally, configuring evaluation indicators for the simulation scenario includes:

[0024] Obtain the driving behavior of the main vehicle after being taken over by the safety officer;

[0025] The driving behavior of the main vehicle after being taken over by the safety officer is defined as the expected driving behavior;

[0026] An evaluation index of the simulation scenario is obtained according to the expected driving behavior.

[0027] Optionally, the evaluation index of the simulation scene includes: a minimum distance between the main vehicle and the obstacle vehicle.

[0028] Optionally, the lane sequence information of the intersection is obtained by clustering adjacent elements of the semantic map elements using a depth-first algorithm.

[0029] In a second aspect, an embodiment of the present application provides a device for constructing a simulation scenario of a road intersection collision accident, comprising:

[0030] An acquisition module is used to acquire drive test data of the intersection area, wherein the drive test data includes lane sequence information of the intersection, state information of the obstacle vehicle, and state information of the host vehicle;

[0031] an extraction module configured to extract a first time when the host vehicle enters a collision state with the obstacle vehicle and a second time when the host vehicle performs an emergency braking action when it is determined that the host vehicle meets a pre-collision determination condition between the host vehicle and the obstacle vehicle based on the lane sequence information of the intersection, the obstacle vehicle state information, and the host vehicle state information;

[0032] a processing module, configured to intercept the drive test data within a time period from the first time to the second time from the drive test data, and obtain the drive test data of the main vehicle entering a collision state with the obstacle vehicle;

[0033] The construction module is used to construct the intersection collision accident simulation scenario based on the road test data of the main vehicle entering a collision state with the obstacle vehicle.

[0034] In a third aspect, an embodiment of the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the computer program, the steps of the method for constructing a simulation scenario of an intersection collision accident as described above are implemented.

[0035] In a fourth aspect, an embodiment of the present application provides a computer storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the method for constructing a simulation scenario of an intersection collision accident as described above are implemented.

[0036] In summary, compared with the prior art, the technical solutions provided by the embodiments of the present application have at least the following beneficial effects:

[0037] 1. The embodiments of the present application mainly adopt the technical means of extracting the first time when the main vehicle enters the collision state with the obstacle vehicle and the second time when the main vehicle performs an emergency braking behavior when it is determined that the main vehicle meets the pre-collision judgment conditions between the main vehicle and the obstacle vehicle based on the lane sequence information of the intersection, the obstacle vehicle status information and the main vehicle status information; intercepting the road test data in the time period from the first time to the second time in the road test data to obtain the road test data of the main vehicle entering the collision state with the obstacle vehicle; and constructing the intersection collision accident simulation scenario based on the road test data of the main vehicle entering the collision state with the obstacle vehicle. The pre-collision judgment conditions between the main vehicle and the obstacle vehicle are used to automatically extract the first time when the main vehicle enters the collision state with the obstacle vehicle and the second time when the main vehicle performs an emergency braking behavior. The start and end times of the simulation scenario can be obtained without human intervention, which greatly reduces the cost of human resources. Moreover, the first time when the main vehicle enters a collision state with the obstacle vehicle and the second time when the main vehicle performs an emergency braking behavior are obtained through the pre-collision judgment conditions between the main vehicle and the obstacle vehicle. Since the pre-collision judgment conditions between the main vehicle and the obstacle vehicle are pre-set, no matter how many times the intersection collision accident simulation scene construction method described in the embodiment of the present application is executed, the consistency of the first time when the main vehicle enters a collision state with the obstacle vehicle and the second time when the main vehicle performs an emergency braking behavior can be ensured, thereby making the quality of the constructed simulation scene more objective.

[0038] 2. In an embodiment of the present application, the lane sequence of the host vehicle can be intelligently determined through the host vehicle's lane sequence information recognition method, thereby directly determining the host vehicle's status, such as left turn, U-turn, straight ahead, or right turn.

[0039] 3. In the embodiment of the present application, the lane sequence information recognition method of the obstructing vehicle can intelligently determine the lane sequence of the obstructing vehicle, thereby directly determining the state of the obstructing vehicle, such as turning left, turning around, going straight, or turning right. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flowchart of a method for constructing a simulation scenario of an intersection collision accident provided by one of the exemplary embodiments of the present application.

[0041] Figure 2 This is a schematic diagram of lane sequence information at an intersection provided by one of the exemplary embodiments of the present application.

[0042] Figure 3 It is a structural diagram of a device for constructing a simulation scenario of an intersection collision accident provided by one of the exemplary embodiments of the present application.

[0043] Figure 4 It is a structural diagram of an electronic device provided by one of the exemplary embodiments of the present application. DETAILED DESCRIPTION

[0044] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0045] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0046] The term "comprise" and any variations thereof in the specification and claims of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to those steps or units expressly listed, but may include other steps or units not expressly listed or inherent to such process, method, product or apparatus.

[0047] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0048] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0049] Figure 1 A method for constructing a simulation scenario of an intersection collision accident is provided in one of the exemplary embodiments of the present application, comprising:

[0050] Acquire drive test data of the intersection area, wherein the drive test data includes lane sequence information of the intersection, state information of the obstacle vehicle, and state information of the host vehicle;

[0051] When it is determined that the host vehicle meets the pre-collision determination condition between the host vehicle and the obstacle vehicle based on the lane sequence information of the intersection, the obstacle vehicle status information, and the host vehicle status information, extracting a first time when the host vehicle enters a collision state with the obstacle vehicle and a second time when the host vehicle performs an emergency braking action;

[0052] intercepting the drive test data within a time period from the first time to the second time from the drive test data, and obtaining the drive test data of the main vehicle entering a collision state with the obstacle vehicle;

[0053] The intersection collision accident simulation scenario is constructed based on the road test data of the main vehicle entering a collision state with the obstacle vehicle.

[0054] This embodiment mainly adopts the technical means of extracting the first time when the main vehicle enters the collision state with the obstacle vehicle and the second time when the main vehicle performs an emergency braking behavior when it is determined that the main vehicle meets the pre-collision judgment conditions between the main vehicle and the obstacle vehicle based on the lane sequence information of the intersection, the obstacle vehicle status information and the main vehicle status information; intercepting the road test data in the time period from the first time to the second time in the road test data to obtain the road test data of the main vehicle entering the collision state with the obstacle vehicle; and constructing the intersection collision accident simulation scene based on the road test data of the main vehicle entering the collision state with the obstacle vehicle. The first time when the main vehicle enters the collision state with the obstacle vehicle and the second time when the main vehicle performs an emergency braking behavior are automatically extracted through the pre-collision judgment conditions between the main vehicle and the obstacle vehicle, and the start and end times of the simulation scene can be obtained without human intervention, which greatly reduces the cost of human resources. Moreover, the first time when the main vehicle enters a collision state with the obstacle vehicle and the second time when the main vehicle performs an emergency braking behavior are obtained through the pre-collision judgment conditions between the main vehicle and the obstacle vehicle. Since the pre-collision judgment conditions between the main vehicle and the obstacle vehicle are pre-set, no matter how many times the intersection collision accident simulation scene construction method described in the embodiment of the present application is executed, the consistency of the first time when the main vehicle enters a collision state with the obstacle vehicle and the second time when the main vehicle performs an emergency braking behavior can be ensured, thereby making the quality of the constructed simulation scene more objective.

[0055] In another embodiment of the present application, the pre-collision judgment conditions between the main vehicle and the obstacle vehicle include: the main vehicle passes through the intersection area, the main vehicle brakes suddenly in the intersection area, the obstacle vehicle is within the intersection area, the intersection lane sequence information of the obstacle vehicle and the main vehicle are different or the obstacle vehicle and the main vehicle turn in the same direction, the minimum distance between the obstacle vehicle and the main vehicle in the intersection area is less than a preset distance, and the lane sequence information of the obstacle vehicle and the main vehicle is identifiable.

[0056] By using the specific content of the pre-collision determination conditions between the host vehicle and the obstacle vehicle, the accuracy of obtaining the first time when the host vehicle enters a collision state with the obstacle vehicle and the second time when the host vehicle performs an emergency braking behavior can be improved.

[0057] It should be noted that the preset distance is 10m.

[0058] Specifically, if Figure 2 As shown, the lane sequence information of the intersection includes lane lines 1, 2, 3, 4, 5, the starting stop lines b, d, f, h of the intersection and the ending stop lines a, c, e, g of the intersection;

[0059] Among them, any intersection start stop line, any intersection end stop line, and the lane line connecting the any intersection start stop line and any intersection end stop line constitute a lane sequence set.

[0060] For example, Figure 2 The lane sequences shown in the figure include a U-turn lane sequence, a through lane sequence, and a left-turn lane sequence.

[0061] Among them, for the intersection start stop line b and the intersection end stop line a, the U-turn lane sequence is composed of lane line 1, lane line 3 and lane line 4. At this time, the vehicle is in a U-turn state.

[0062] For the intersection start stop line b and the intersection end stop line e, the straight lane sequence is composed of lane line 1 and lane line 2. At this time, the vehicle is in a straight state.

[0063] For the intersection start stop line b and the intersection end stop line g, the left turn lane sequence is composed of lane line 1, lane line 3 and lane line 5. At this time, the vehicle is in a left turn state.

[0064] In another embodiment of the present application, when the lane sequence information of the obstructing vehicle and the host vehicle is identifiable, the type of the intersection collision accident is marked according to the identification result of the lane sequence information of the obstructing vehicle and the host vehicle.

[0065] By marking the type of intersection collision accident, it is easier to find it later. For example, based on the lane sequence information of the main vehicle, it can be identified that the main vehicle is in a lane sequence that is turning left, while the obstacle vehicle is in a lane sequence that is going straight. This makes it easy to find the collision scenario where the main vehicle is turning left and the obstacle vehicle is going straight.

[0066] In another embodiment of the present application, the host vehicle status information includes host vehicle position information; the host vehicle lane sequence information is identifiable, wherein a method for identifying the host vehicle lane sequence information includes:

[0067] Determine whether the starting stop line and the ending stop line of the intersection of the host vehicle are determined:

[0068] If yes, then obtain the lane sequence of the host vehicle according to the intersection start stop line and the intersection end stop line;

[0069] If not, the lane sequence of the host vehicle is determined according to the host vehicle position information.

[0070] By using the above-mentioned method for identifying lane sequence information of the host vehicle, the lane sequence of the host vehicle can be intelligently determined, thereby directly determining the state of the host vehicle, such as turning left, turning around, going straight, or turning right.

[0071] It should be noted that determining the lane sequence of the host vehicle according to the host vehicle position information includes:

[0072] Scan each frame of the main vehicle's drive test data in the intersection area. For each frame of drive test data, find the center point of all lane sequences of the main vehicle within the preset range, that is, W = {w1, w2, ..., w i ,…,w n},foreachw i ∈W:w i inlane_region i ,score i +1, where w i is the center point of the i-th lane sequence, lane_region i is the i-th lane sequence, score i is the score of the i-th lane sequence, i≤n, and i and n are both natural numbers. i , get a score ratio, i.e. ratio i =score i / total_frames, where total_frames is the total number of frames of the host vehicle's drive test data. Each lane sequence is traversed to obtain the score ratio for each lane sequence. The score ratios for each lane sequence are then sorted from highest to lowest. If 1stratio > 0.6 and 1stratio-2ndratio > 0.1, the host vehicle is determined to be traveling along the lane sequence with the highest score. For example, if the highest-scoring lane sequence is a left-turn lane sequence, the host vehicle is determined to be turning left.

[0073] In another embodiment of the present application, the barrier vehicle status information includes barrier vehicle position information; the barrier vehicle lane sequence information is identifiable, wherein a method for identifying the barrier vehicle lane sequence information includes:

[0074] Determine whether the starting stop line and the ending stop line of the intersection of the obstacle vehicle are determined:

[0075] If yes, then the lane sequence of the obstacle vehicle is obtained according to the starting stop line and the ending stop line of the intersection;

[0076] If not, the lane sequence of the obstacle vehicle is determined according to the position information of the obstacle vehicle.

[0077] By using the above-mentioned lane sequence information recognition method of the obstructing vehicle, the lane sequence of the obstructing vehicle can be intelligently determined, thereby directly determining the state of the obstructing vehicle, such as turning left, turning around, going straight, or turning right.

[0078] It should be noted that, according to the position information of the obstacle vehicle, determining the lane sequence of the obstacle vehicle includes:

[0079] Scan each frame of road test data of the obstacle vehicle in the intersection area. For each frame of road test data, find the center point of all lane sequences of the obstacle vehicle within the preset range, that is, W={w1,w2,…,w i ,…,w n},foreachw i ∈W:w i inlane_region i ,score i +1, where w i is the center point of the i-th lane sequence, lane_region i is the i-th lane sequence, score i is the score of the i-th lane sequence, i≤n, and i and n are both natural numbers. i , get a score ratio, i.e. ratio i =score i / total_frames, where total_frames is the total number of frames of the main vehicle's drive test data. Each lane sequence is traversed to obtain the score ratio for each lane sequence. The score ratios for each lane sequence are then sorted from highest to lowest. If 1stratio > 0.6 and 1stratio-2ndratio > 0.1, the obstacle vehicle is determined to be moving along the lane sequence with the highest score. For example, if the highest-scoring lane sequence is a straight lane sequence, the main vehicle is determined to be moving straight.

[0080] In another embodiment of the present application, after constructing the intersection collision accident simulation scenario based on the road test data of the main vehicle entering a collision state with the obstacle vehicle, the method further includes:

[0081] After constructing the intersection collision accident simulation scenario based on the road test data of the main vehicle entering a collision state with the obstacle vehicle, an evaluation index of the simulation scenario is configured to determine whether the simulated vehicle reproduces the intersection collision accident in the intersection collision accident simulation scenario.

[0082] By configuring the evaluation index of the simulation scene, it is determined whether the simulated vehicle reproduces the intersection collision accident in the intersection collision accident simulation scene, thereby quantifying the degree to which the simulation scene restores the real scene.

[0083] In another embodiment of the present application, configuring the evaluation index of the simulation scenario includes:

[0084] Obtain the driving behavior of the main vehicle after being taken over by the safety officer;

[0085] The driving behavior of the main vehicle after being taken over by the safety officer is defined as the expected driving behavior;

[0086] An evaluation index of the simulation scenario is obtained according to the expected driving behavior.

[0087] The above steps of configuring the evaluation indicators of the simulation scenario provide a clear basis for judgment for configuring the evaluation indicators of the simulation scenario, thereby further standardizing the behavior of the simulated vehicle.

[0088] Specifically, the simulation scenario evaluation metrics include the minimum distance between the host vehicle and the obstacle. For example, the minimum distance between the host vehicle and the obstacle is used to determine whether there is a safety hazard in the lane sequence where the host vehicle is located. If the minimum distance between the host vehicle and the obstacle is less than a preset threshold, an alarm is issued to notify the host vehicle of a safety hazard.

[0089] In another embodiment of the present application, the lane sequence information of the intersection is obtained by clustering adjacent elements of the semantic map elements using a depth-first algorithm.

[0090] By adopting the depth-first algorithm, the lane sequence information of the intersection can be quickly obtained from the semantic map, which improves the data processing efficiency while ensuring the accuracy of the lane sequence information of the intersection.

[0091] Figure 3 Another exemplary embodiment of the present application provides a device for constructing a road intersection collision accident simulation scenario, comprising:

[0092] An acquisition module is used to acquire drive test data of the intersection area, wherein the drive test data includes lane sequence information of the intersection, state information of the obstacle vehicle, and state information of the host vehicle;

[0093] an extraction module configured to extract a first time when the host vehicle enters a collision state with the obstacle vehicle and a second time when the host vehicle performs an emergency braking action when it is determined that the host vehicle meets a pre-collision determination condition between the host vehicle and the obstacle vehicle based on the lane sequence information of the intersection, the obstacle vehicle state information, and the host vehicle state information;

[0094] a processing module, configured to intercept the drive test data within a time period from the first time to the second time from the drive test data, and obtain the drive test data of the main vehicle entering a collision state with the obstacle vehicle;

[0095] The construction module is used to construct the intersection collision accident simulation scenario based on the road test data of the main vehicle entering a collision state with the obstacle vehicle.

[0096] Each module of the aforementioned intersection collision accident simulation scenario construction device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor within a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0097] Those skilled in the art will clearly understand that for the sake of convenience and conciseness of description, the division of the above-mentioned functional units and modules is only used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device described in this application is divided into different functional units or modules to complete all or part of the functions described above.

[0098] Figure 4 Another exemplary embodiment of the present application provides an electronic device, which may be a server. The electronic device includes a processor, a memory, and a communication interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the device can be implemented by any type of volatile or non-volatile storage device or a combination thereof, and volatile or non-volatile storage devices include but are not limited to: magnetic disks, optical disks, EEPROMs, EPROMs, SRAMs, ROMs, magnetic memories, flash memories, and PROMs. The memory of the device provides an environment for the operation of the operating system and computer programs stored therein. The communication interface of the device is a network interface, which is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps of the method for constructing a simulation scenario for an intersection collision accident described in the above embodiment are implemented.

[0099] In another embodiment of the present application, a computer storage medium is provided, the computer storage medium storing a computer program that, when executed by a processor, implements the steps of the method for constructing a road intersection collision accident simulation scenario described in the above embodiment. The storage medium includes, but is not limited to, ROM, RAM, CD-ROM, magnetic disk, and floppy disk.

[0100] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

Claims

1. A method for constructing a simulation scene of an intersection collision accident, characterized in that: include: Acquire drive test data of the intersection area, wherein the drive test data includes lane sequence information of the intersection, state information of the obstacle vehicle, and state information of the host vehicle; When it is determined that the host vehicle meets the pre-collision determination condition between the host vehicle and the obstacle vehicle based on the lane sequence information of the intersection, the obstacle vehicle status information, and the host vehicle status information, extracting a first time when the host vehicle enters a collision state with the obstacle vehicle and a second time when the host vehicle performs an emergency braking action; Specifically, the pre-collision determination conditions between the main vehicle and the obstacle vehicle include: the main vehicle passes through the intersection area, the main vehicle brakes suddenly in the intersection area, the obstacle vehicle is within the intersection area, the intersection lane sequence information of the obstacle vehicle and the main vehicle are different or the obstacle vehicle and the main vehicle turn in the same direction, the minimum distance between the obstacle vehicle and the main vehicle in the intersection area is less than a preset distance, and the lane sequence information of the obstacle vehicle and the main vehicle is identifiable; specifically, the intersection lane sequence information includes a plurality of lane lines, a plurality of intersection start-stop lines, and a plurality of intersection end-stop lines; any one intersection start-stop line, any one intersection end-stop line, and the lane line connecting any one intersection start-stop line and any one intersection end-stop line constitute a lane sequence set; intercepting the drive test data within a time period from the first time to the second time from the drive test data, and obtaining the drive test data of the main vehicle entering a collision state with the obstacle vehicle; The intersection collision accident simulation scenario is constructed based on the road test data of the main vehicle entering a collision state with the obstacle vehicle.

2. The method for constructing a road intersection collision accident simulation scene according to claim 1, characterized in that: The host vehicle status information includes host vehicle position information; the host vehicle lane sequence information is identifiable, wherein the host vehicle lane sequence information identification method includes: Determine whether the starting stop line and the ending stop line of the intersection of the host vehicle are determined: If yes, then obtain the lane sequence of the host vehicle according to the intersection start stop line and the intersection end stop line; If not, the lane sequence of the host vehicle is determined according to the host vehicle position information.

3. The method for constructing a simulation scene of an intersection collision accident according to claim 1, characterized in that: The barrier vehicle status information includes barrier vehicle position information; the barrier vehicle lane sequence information is identifiable, wherein the barrier vehicle lane sequence information identification method includes: Determine whether the starting stop line and the ending stop line of the intersection of the obstacle vehicle are determined: If yes, then the lane sequence of the obstacle vehicle is obtained according to the starting stop line and the ending stop line of the intersection; If not, the lane sequence of the obstacle vehicle is determined according to the position information of the obstacle vehicle.

4. The method for constructing a simulation scene of an intersection collision accident according to claim 1, characterized in that: After constructing the intersection collision accident simulation scenario based on the road test data of the main vehicle entering a collision state with the obstacle vehicle, the method further includes: After constructing the intersection collision accident simulation scenario based on the road test data of the main vehicle entering a collision state with the obstacle vehicle, an evaluation index of the simulation scenario is configured to determine whether the simulated vehicle reproduces the intersection collision accident in the intersection collision accident simulation scenario.

5. The method for constructing a simulation scene of an intersection collision accident according to claim 4, characterized in that: Configuring the evaluation indicators of the simulation scenario includes: Obtain the driving behavior of the main vehicle after being taken over by the safety officer; The driving behavior of the main vehicle after being taken over by the safety officer is defined as the expected driving behavior; An evaluation index of the simulation scenario is obtained according to the expected driving behavior.

6. The method for constructing a simulation scene of an intersection collision accident according to claim 5, characterized in that: The evaluation index of the simulation scene includes: the minimum distance between the main vehicle and the obstacle vehicle.

7. The method for constructing a simulation scene of an intersection collision accident according to any one of claims 1 to 6, characterized in that: The lane sequence information of the intersection is obtained by clustering adjacent elements of semantic map elements using a depth-first algorithm.

8. A device for constructing a simulation scene of a road intersection collision accident, characterized in that: include: An acquisition module is used to acquire drive test data of the intersection area, wherein the drive test data includes lane sequence information of the intersection, state information of the obstacle vehicle, and state information of the host vehicle; an extraction module configured to extract a first time when the host vehicle enters a collision state with the obstacle vehicle and a second time when the host vehicle performs an emergency braking action when it is determined that the host vehicle meets a pre-collision determination condition between the host vehicle and the obstacle vehicle based on the lane sequence information of the intersection, the obstacle vehicle status information, and the host vehicle status information; Specifically, the pre-collision determination conditions between the main vehicle and the obstacle vehicle include: the main vehicle passes through the intersection area, the main vehicle brakes suddenly in the intersection area, the obstacle vehicle is within the intersection area, the intersection lane sequence information of the obstacle vehicle and the main vehicle are different or the obstacle vehicle and the main vehicle turn in the same direction, the minimum distance between the obstacle vehicle and the main vehicle in the intersection area is less than a preset distance, and the lane sequence information of the obstacle vehicle and the main vehicle is identifiable; specifically, the intersection lane sequence information includes a plurality of lane lines, a plurality of intersection start-stop lines, and a plurality of intersection end-stop lines; any one intersection start-stop line, any one intersection end-stop line, and the lane line connecting any one intersection start-stop line and any one intersection end-stop line constitute a lane sequence set; a processing module, configured to intercept the drive test data within a time period from the first time to the second time from the drive test data, and obtain the drive test data of the main vehicle entering a collision state with the obstacle vehicle; The construction module is used to construct the intersection collision accident simulation scenario based on the road test data of the main vehicle entering a collision state with the obstacle vehicle.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the computer program, the steps of the method for constructing a road intersection collision accident simulation scene as described in any one of claims 1 to 7 are implemented.

10. A computer storage medium, characterized in that The computer storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for constructing a road intersection collision accident simulation scenario as described in any one of claims 1 to 7.

Images