Vehicle scene data collection method and device, storage medium and electronic equipment

Abstract

The application discloses a kind of acquisition method, device, storage medium and electronic equipment of vehicle scene data.Therein, the method comprises: in the process of vehicle driving, the target data determined by the automatic driving system of the vehicle is acquired, wherein the target data includes at least one of the following: the control instruction of the automatic driving system to the vehicle, the perception data perceived by the automatic driving system to the environment where the vehicle is located, the positioning data of the vehicle determined by the automatic driving system, the prediction planning data predicted by the automatic driving system;Whether the vehicle is in target scene is determined according to the target data;In the case where it is determined that the vehicle is in the target scene, vehicle scene data of the vehicle in the target scene is collected.The above technical scheme is used, and the problem that the obtained vehicle scene data is less is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication, in particular to a vehicle scene data collection method and device, a storage medium and an electronic device. BACKGROUND

[0002] With the rapid development of science and technology, the field of vehicle automatic driving develops rapidly, but automatic driving can be divided into different levels, the higher the level of automatic driving, the more scenes it can adapt to, that is, it can achieve automatic driving without limiting the scene, that is, the development of high-level automatic driving system should take the scene without boundary limitation as the verification hypothesis, and has the coverage ability to complex environment and unfamiliar, sudden scenes.

[0003] The automatic driving algorithm needs to deal with many and complex scenes, and the algorithm life cycle is long, which needs long-time iteration and optimization, but in the process of testing the existing automatic driving system, it is tested according to the fixed test scene, when it is found that the automatic driving algorithm cannot cover the current working condition, the tester manually records the problem, optimizes the software, and then tests, which is low in efficiency, and some edge scenes cannot be identified and tested, resulting in the inability to find all the problems of the software. That is, the collection of existing scene data is simulated by people, and then the collection of the scene is manually triggered by the tester, so that the obtainable scene data is less and lacks authenticity.

[0004] For the problem of less vehicle scene data obtained in related technologies, no effective solution has been proposed so far.

[0005] Therefore, it is necessary to improve the related technology to overcome the defects in the related technology. SUMMARY

[0006] Therefore, it is necessary to improve the related technology to overcome the defects in the related technology.

[0007] In order to achieve the above-mentioned purpose, in a first aspect, the present application provides a vehicle scene data collection method, which comprises: acquiring target data determined by an automatic driving system of a vehicle during driving of the vehicle, wherein the target data comprises at least one of the following: control instructions of the automatic driving system to the vehicle, perception data perceived by the automatic driving system to the environment where the vehicle is located, positioning data of the vehicle determined by the automatic driving system, and prediction planning data predicted by the automatic driving system; determining whether the vehicle is in a target scene according to the target data; and collecting vehicle scene data of the vehicle in the target scene when it is determined that the vehicle is in the target scene.

[0008] In an example embodiment, in a case where the target data comprises the control instruction, determining whether the vehicle is in a target scenario according to the target data comprises: in a case where it is determined that the vehicle is in an automatic driving mode, and the control instruction indicates to set an acceleration of the vehicle in a first direction to a first acceleration, and the value of the first acceleration exceeds a first threshold, determining that the vehicle is in an abnormal driving scenario, wherein the first direction is a forward direction of the vehicle, and the first acceleration exceeds the first threshold; in a case where it is determined that the vehicle is in an automatic driving mode, the control instruction indicates to set an acceleration of the vehicle in a second direction to a second acceleration, and indicates to set a change rate of a turning angle of a tire of the vehicle to a target change rate of the turning angle, and the second acceleration exceeds a second threshold, and the target change rate of the turning angle exceeds a third threshold, and an included angle between the first direction and the second direction is a preset included angle, determining that the vehicle is in the abnormal driving scenario; in a case where it is determined that the vehicle is in a manual driving mode, determining a target control instruction issued by a target object to the vehicle; comparing the target control instruction with the control instruction in the target data, and in a case where a similarity between the target control instruction and the control instruction is less than a fourth threshold, determining that the vehicle is in a predicted control instruction abnormal scenario; wherein the target scenario comprises the abnormal driving scenario and the predicted control instruction abnormal scenario.

[0009] In an example embodiment, in a case where the target data comprises the perception data, determining whether the vehicle is in a target scenario according to the target data comprises: in a case where it is determined according to the perception data that a type of a first obstacle perceived by a perception module of the automatic driving system changes within a first preset time length, determining that the vehicle is in a perception module abnormal scenario; in a case where it is determined according to the perception data that an identity of the first obstacle changes within the first preset time length, determining that the vehicle is in the perception module abnormal scenario; in a case where it is determined according to the perception data that a change amount of a moving speed of the first obstacle within the first preset time length exceeds a fifth threshold, determining that the vehicle is in the perception module abnormal scenario; in a case where it is determined according to the perception data that a position of a second obstacle perceived by the perception module changes within the first preset time length, determining that the vehicle is in the perception module abnormal scenario; in a case where it is determined according to the perception data that a position of a third obstacle perceived by the perception module overlaps with a position of the vehicle, determining that the vehicle is in the perception module abnormal scenario; in a case where the perception data is preset perception data, and vehicle body data of the vehicle is preset vehicle body data, determining that the vehicle is in a preset scenario; wherein the target scenario comprises the perception module abnormal scenario and the preset scenario.

[0010] In an example embodiment, when the target data comprises the positioning data, determining whether the vehicle is in a target scenario according to the target data comprises: determining that the vehicle is in a positioning module abnormal scenario when a variation of a position of the vehicle within a second preset time length determined according to the positioning data exceeds a sixth threshold value; determining that the vehicle is in the positioning module abnormal scenario when a variation of a moving direction of the vehicle within the second preset time length determined according to the positioning data exceeds a seventh threshold value; determining that the vehicle is in the positioning module abnormal scenario when the position of the vehicle determined according to the positioning data does not change within the second preset time length, but a speed of the vehicle is a target speed; wherein the target scenario comprises the positioning module abnormal scenario.

[0011] In an example embodiment, when the target data comprises the prediction planning data, determining whether the vehicle is in a target scenario according to the target data comprises: determining a similarity between a predicted moving state of a third obstacle indicated by the prediction planning data and a target moving state of the third obstacle, and determining that the vehicle is in a prediction planning module abnormal scenario when the similarity is less than an eighth threshold value, wherein the target moving state is a moving state obtained after detecting the third obstacle; determining a feasibility of a planned moving trajectory of the vehicle indicated by the prediction planning data, and determining that the vehicle is in the prediction planning module abnormal scenario when the feasibility is less than a ninth threshold value; determining whether there is an obstacle on the planned moving trajectory of the vehicle indicated by the prediction planning data, and determining that the vehicle is in the prediction planning module abnormal scenario when it is determined that there is an obstacle on the planned moving trajectory; determining that the vehicle is in a manual control scenario when the prediction planning data indicates that the automatic driving system cannot control the vehicle; wherein the target scenario comprises the prediction planning module abnormal scenario and the manual control scenario.

[0012] In an example embodiment, collecting vehicle scenario data of the vehicle in the target scenario comprises: collecting vehicle body data of the vehicle within a preset time period, wherein the vehicle is in the target scenario within the preset time period; collecting chassis data of the vehicle within the preset time period; collecting process data and control instruction data generated by the automatic driving system of the vehicle within the preset time period; collecting perception data of an environment in which the vehicle is located determined by an image acquisition device and a radar sensor of the vehicle within the preset time period.

[0013] In an example embodiment, after the vehicle scene data of the vehicle in the target scene is collected, the method further comprises: sending the vehicle scene data to a cloud server, so that the cloud server adjusts an algorithm of the automatic driving system according to the vehicle scene data; obtaining the target algorithm adjusted by the cloud server, and updating the algorithm of the automatic driving system to the target algorithm.

[0014] In a second aspect, the present application further provides a vehicle scene data collection device, which comprises: an acquisition module, configured to acquire target data determined by an automatic driving system of a vehicle during driving of the vehicle, wherein the target data comprises at least one of the following: a control instruction of the vehicle by the automatic driving system, perception data perceived by the automatic driving system for an environment in which the vehicle is located, positioning data of the vehicle determined by the automatic driving system, and prediction planning data predicted by the automatic driving system; a determination module, configured to determine whether the vehicle is in a target scene according to the target data; and a collection module, configured to collect vehicle scene data of the vehicle in the target scene when it is determined that the vehicle is in the target scene.

[0015] In a third aspect, the present application further provides a computer readable storage medium comprising a stored program, wherein the program, when executed, controls a device in which the computer readable storage medium is located to perform the vehicle scene data collection method described in any of the technical solutions above.

[0016] In a fourth aspect, the present application further provides an electronic device comprising one or more processors; a storage device configured to store one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement a program for running, wherein the program is configured to execute the vehicle scene data collection method described in any of the technical solutions above when running.

[0017] In the present application, during driving of a vehicle, whether the vehicle is in a set target scene is automatically determined, and data collection is triggered. Since the ability of a vehicle to recognize a scene is stronger than that of a human to recognize a scene, the vehicle can recognize more scenes, and the scenes in which the vehicle is located during driving are diverse, so that a large amount of real and diverse scene data can be collected, thereby solving the problem of less vehicle scene data.

[0018] In order to make the above objectives, characteristics and advantages of the present application more apparent and easy to understand, a preferred embodiment is described in detail below, and the accompanying drawings are referred to as follows. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the general description of the application given above and the detailed description of the embodiments given below serve to explain the principles of the present application. In the drawings:

[0020] Figure 1 is a hardware structure block diagram of a computer terminal of a vehicle scene data collection method according to an embodiment of the present application;

[0021] Figure 2 is a flow chart of a vehicle scene data collection method according to an embodiment of the present application;

[0022] Figure 3 is a hardware architecture of a vehicle data collection unit according to an embodiment of the present application;

[0023] Figure 4 is a data collection trigger mechanism diagram (one) according to an embodiment of the present application;

[0024] Figure 5 is a data collection trigger scene schematic diagram according to an embodiment of the present application;

[0025] Figure 6 is a data collection trigger mechanism diagram (two) according to an embodiment of the present application;

[0026] Figure 7 is a structure block diagram of a vehicle scene data collection device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In the following, specific embodiments of the present application will be described in detail with reference to the accompanying drawings, but are not intended to limit the present application.

[0028] It should be understood that various modifications can be made to the embodiments disclosed herein. Therefore, the above description should not be taken as limiting, but merely as exemplification of the embodiments. Other modifications within the scope and spirit of the application will occur to those skilled in the art to which the present application pertains.

[0029] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the general description of the application given above and the detailed description of the embodiments given below serve to explain the principles of the present application.

[0030] These and other characteristics of the present application will become apparent from the following description of the preferred forms given, by way of non-limiting example only, with reference to the attached drawings.

[0031] It should also be understood that, although the present application has been described in relation to the foregoing specific embodiments, many other modifications and / or alternative forms of embodiment of the present application can be executed beyond the limit of the recitations of the claims.

[0032] The above and other aspects, features and advantages of the present application will become more apparent from the following detailed description, taken in conjunction with the accompanying drawings, in which:

[0033] Specific embodiments of the present application will be described hereinafter with reference to the accompanying drawings. However, it would be appreciated that the disclosed embodiments are merely examples of the present application, which can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that obscure the present application. Therefore, the specific structural and functional details disclosed herein are not intended to be limiting, but are merely to be used as a basis for the claims and a representative basis for teaching one skilled in the art to variously employ the present application in virtually any appropriate detailed structure.

[0034] It should be noted that the terms "first", "second", and the like, in the description and in the claims of the present application as well as above-mentioned drawings mean for distinguishing between like objects and do not necessarily indicate a described particular order or sequence. It should be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in other sequences than those explicitly described or otherwise shown as preferred or desired. Moreover, the terms "include", "have", and "exist", and any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, a method, a system, a product, or an apparatus that includes a list of steps or units not necessarily limited to the clearly listed steps or units but can include other steps or units not clearly listed or inherent to such processes, methods, products, or apparatuses.

[0035] The present specification can use the phrases "in one embodiment", "in another embodiment", "in yet another embodiment", or "in other embodiments", which can refer to one or more of the same or different embodiments of the application.

[0036] The present application will be further described with reference to the drawings and specific embodiments.

[0037] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal or similar computing device. Taking the computer terminal as an example, Figure 1 is a hardware structure block diagram of a computer terminal of the vehicle scene data acquisition method of the embodiments of the present application. As Figure 1 shown, the computer terminal can include one or more (CPU) central processing units, Figure 1The computer terminal shown in FIG. 1 includes only one processor 102 (the processor 102 can include, but is not limited to, a Microprocessor Unit (MPU) or a Programmable logic device (PLD)) and a memory 104 for storing data. In an exemplary embodiment, the computer terminal can further include a transmission device 106 for communication function and an input / output device 108. Those skilled in the art can understand that, Figure 1 The structure shown in FIG. 1 is only illustrative and does not limit the structure of the computer terminal. For example, the computer terminal can include more or less components than those shown in FIG. 1, or have a different configuration with the same or more functions than those shown in FIG. 1. Figure 1 The structure shown in FIG. 1 is only illustrative and does not limit the structure of the computer terminal. For example, the computer terminal can include more or less components than those shown in FIG. 1, or have a different configuration with the same or more functions than those shown in FIG. 1. Figure 1 The structure shown in FIG. 1 is only illustrative and does not limit the structure of the computer terminal. For example, the computer terminal can include more or less components than those shown in FIG. 1, or have a different configuration with the same or more functions than those shown in FIG. 1. Figure 1 The structure shown in FIG. 1 is only illustrative and does not limit the structure of the computer terminal. For example, the computer terminal can include more or less components than those shown in FIG. 1, or have a different configuration with the same or more functions than those shown in FIG. 1.

[0038] The memory 104 can be used to store computer programs, such as software programs of application software and modules, for example, a computer program corresponding to the vehicle scene data collection method in the embodiments of the present application. The processor 102 can execute various functional applications and data processing by running the computer programs stored in the memory 104, i.e., implement the above-mentioned method. The memory 104 can include a high-speed random access memory and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely arranged with respect to the processor 102, and these remote memories can be connected to the computer terminal through a network. Examples of the network can include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0039] The transmission device 106 is used to receive or send data via a network. Specific examples of the network can include a wireless network provided by a communication provider of the computer terminal. In an example, the transmission device 106 includes a network adapter (NIC) which can be connected to other network devices through a base station so as to communicate with the Internet. In an example, the transmission device 106 can be a radio frequency (RF) module which is used to communicate with the Internet in a wireless manner.

[0040] Since the automatic driving vehicle can collect a large amount of real scene data when driving, in order to efficiently screen out the scene required by automatic driving from a large amount of scene data, the present application proposes a vehicle scene data collection method, which respectively collects real scene data in automatic driving and manual driving states, the automatic driving system continuously runs, outputs instructions to control the vehicle driving in the automatic driving mode, and outputs virtual instructions to compare the difference with the actual driver in the manual driving mode, and through automatic driving abnormal scene identification, vehicle-difference comparison analysis and set interesting scene, the real scene data of the vehicle end is effectively triggered and collected.

[0041] In the present embodiment, a vehicle scene data collection method is provided, Figure 2 is a flowchart of the vehicle scene data collection method according to the embodiment of the present application, which comprises the following steps:

[0042] Step S202: In the process of driving the vehicle, target data determined by the automatic driving system of the vehicle is acquired, wherein the target data comprises at least one of the following: control instructions of the automatic driving system to the vehicle, perception data perceived by the automatic driving system to the environment where the vehicle is located, positioning data of the vehicle determined by the automatic driving system, and prediction planning data predicted by the automatic driving system;

[0043] As an optional example, the control instructions include but are not limited to: control vehicle acceleration, control vehicle brake, control vehicle deceleration, control vehicle turning, control vehicle U-turn, control vehicle opening light, etc.

[0044] As an optional example, the perception data includes but is not limited to: the number, type, identification, speed, position, driving state, etc. of the obstacles around the vehicle.

[0045] As an optional example, the positioning data includes but is not limited to: the position of the vehicle, the moving direction (heading) of the vehicle, etc.

[0046] As an optional example, the prediction planning data includes but is not limited to: the moving state of the predicted obstacle (for example, the obstacle moves in xx direction at x speed), the planned vehicle travel trajectory, etc.

[0047] Step S204: Determine whether the vehicle is in a target scene according to the target data;

[0048] It should be noted that the target scene is a scene in which the test personnel want to collect vehicle scene data, and the target scene includes but is not limited to: an abnormal driving scene, a predicted control instruction abnormal scene, a perception module abnormal scene, a preset scene defined by the test personnel, a positioning module abnormal scene, a prediction and planning module abnormal scene, and a manual control scene. The scenes will be described below, and will not be described here.

[0049] Step S206: In a case where it is determined that the vehicle is in the target scene, vehicle scene data of the vehicle in the target scene is collected.

[0050] As an optional example, the collection of vehicle scene data of the vehicle in the target scene can be realized by the following way:

[0051] Collecting vehicle body data of the vehicle in a preset time period, wherein the vehicle is in the target scene in the preset time period; collecting chassis data of the vehicle in the preset time period; collecting process data and control instruction data generated by the automatic driving system of the vehicle in the preset time period; and collecting perception data of the environment in which the vehicle is located, which is determined by the image acquisition device and the radar sensor of the vehicle in the preset time period.

[0052] It should be noted that the vehicle scene data includes: vehicle body data, chassis data, process data and control instruction data generated by the automatic driving system, and perception data.

[0053] Specifically, Figure 3 is a hardware architecture of a vehicle-end data acquisition unit according to an embodiment of the application, and the collection of vehicle scene data can be realized by a vehicle-end data acquisition unit as shown in Figure 3 , wherein the vehicle-end data acquisition unit includes: a data acquisition trigger calculation unit and a data storage unit.

[0054] The input of the vehicle-end data acquisition unit includes:

[0055] (1) vehicle body data and chassis data of the vehicle transmitted through the gateway;

[0056] (2) process data and control instruction data generated by the automatic driving control unit of the automatic driving system;

[0057] (3) perception data perceived by the vehicle through an image acquisition device (for example, a camera) and a radar sensor (for example, a laser radar).

[0058] As an optional example, after the above step S206 is performed, the vehicle scene data needs to be sent to a cloud server, so that the cloud server adjusts an algorithm of the automatic driving system according to the vehicle scene data; the target algorithm adjusted by the cloud server is acquired, and the algorithm of the automatic driving system is updated to the target algorithm.

[0059] Optionally, the vehicle scene data stored in the data storage unit in the vehicle-end data acquisition unit can be uploaded to the cloud server through a communication module as shown in the figure. Figure 3

[0060] Through the above steps, in the process of vehicle driving, whether the vehicle is in a set target scene is automatically judged by the vehicle, and then data acquisition is triggered. Since the ability of the vehicle to identify the scene is stronger than that of artificial identification of the scene, the vehicle can identify more scenes, and the scene in which the vehicle is located when driving is diverse, so a large amount of real and diverse scene data can be collected, thereby solving the problem of less vehicle scene data.

[0061] As an optional example, in the case where the target data includes the control instruction, whether the vehicle is in a target scene is determined according to the target data by the following ways one to three:

[0062] Way one: in the case where it is determined that the vehicle is in an automatic driving mode, and the control instruction indicates that the acceleration of the vehicle in a first direction is set to a first acceleration, it is determined that the vehicle is in an abnormal driving scene, wherein the first direction is the forward direction of the vehicle, the value of the first acceleration exceeds a first threshold, and the target scene includes the abnormal driving scene.

[0063] It should be noted that if the control instruction indicates that the acceleration of the vehicle in the first direction is set to the first acceleration, it means that the automatic driving system needs to control the vehicle to brake suddenly, that is, the current vehicle is in a sudden extreme state, that is, in an abnormal driving scene.

[0064] Way two: in the case where it is determined that the vehicle is in an automatic driving mode, the control instruction indicates that the acceleration of the vehicle in a second direction is set to a second acceleration, and indicates that the change rate of the turning angle of the tire of the vehicle is set to a target change rate of the turning angle, it is determined that the vehicle is in an abnormal driving scene, wherein the second acceleration exceeds a second threshold, the target change rate of the turning angle exceeds a third threshold, and the included angle between the first direction and the second direction is a preset included angle.

[0065] ​It should be noted that if the control instruction indicates that the acceleration of the vehicle in the second direction is set to the second acceleration, and indicates that the rate of change of the turning angle of the tire of the vehicle is set to the target rate of change of the turning angle, it is indicated that the automatic driving needs to control the vehicle to make a sharp turn, and the current vehicle is in an extreme state, i.e., in an abnormal driving scene.

[0066] Option 3: In a case where it is determined that the vehicle is in a manual driving mode, a target control instruction issued by the target object to the vehicle is determined; the target control instruction is compared with the control instruction in the target data, and in a case where the similarity between the target control instruction and the control instruction is less than a fourth threshold, it is determined that the vehicle is in a predicted control instruction abnormal scene, wherein the target scene includes: the predicted control instruction abnormal scene.

[0067] It should be noted that in the manual driving mode, the automatic driving system is simulated to run, and the control instruction issued by the automatic driving system does not directly control the vehicle. At this time, the operation behavior of the driver and the actual state of the vehicle are analyzed with the control instruction of the automatic driving system. When the difference between the two exceeds the set fourth threshold, it is determined that the vehicle is in a predicted control instruction abnormal scene.

[0068] Optionally, if the target control instruction is to control the vehicle to turn left, and the control instruction is to control the vehicle to turn right, it is indicated that the similarity between the two is less than the fourth threshold.

[0069] As an optional example, in a case where the target data includes the perception data, whether the vehicle is in a target scene can be determined according to the target data by the following modes 4 to 9:

[0070] Mode 4: In a case where it is determined according to the perception data that the type of the first obstacle perceived by the perception module of the automatic driving system changes within a first preset time length, it is determined that the vehicle is in a perception module abnormal scene, wherein the target scene includes: the perception module abnormal scene.

[0071] Optionally, the first preset time length can be 1 second, 2 seconds, etc., and the first obstacle is a movable obstacle (for example, a movable pedestrian or vehicle on the road). If the type of the first obstacle changes within the first preset time length (for example, it is a pedestrian at first and then a vehicle), it is indicated that the type of the perceived obstacle jumps, i.e., the perception module is abnormal, and the vehicle is in a perception module abnormal scene.

[0072] Mode 5: In a case where it is determined according to the perception data that the identity of the first obstacle changes within a first preset time length, it is determined that the vehicle is in a perception module abnormal scene.

[0073] It should be noted that if the identification of the first obstacle changes within the first preset time length (for example: the identification of the first obstacle is vehicle 1 at first, and then changes to vehicle 2), it means that the identification of the perceived obstacle jumps, that is, the perception module is abnormal, and the vehicle is in the perception module abnormal scene.

[0074] Sixth way: in the case where it is determined according to the perception data that the change amount of the moving speed of the first obstacle within the first preset time length exceeds the fifth threshold value, it is determined that the vehicle is in the perception module abnormal scene.

[0075] It should be noted that if the change amount of the moving speed of the first obstacle within the first preset time length exceeds the fifth threshold value, it means that the speed of the perceived obstacle jumps, that is, the perception module is abnormal, and the vehicle is in the perception module abnormal scene.

[0076] Seventh way: in the case where it is determined according to the perception data that the position of the second obstacle perceived by the perception module changes within the first preset time length, it is determined that the vehicle is in the perception module abnormal scene.

[0077] It should be noted that the second obstacle is a stationary obstacle (for example, a tree, a house, etc.), and if the position of the second obstacle changes within the first preset time length, it means that the position of the stationary obstacle jumps, that is, the perception module is abnormal, and the vehicle is in the perception module abnormal scene.

[0078] Eighth way: in the case where it is determined according to the perception data that the position of the third obstacle perceived by the perception module overlaps with the position of the vehicle, it is determined that the vehicle is in the perception module abnormal scene.

[0079] It should be noted that the third obstacle includes the first obstacle and the second obstacle.

[0080] Ninth way: in the case where the perception data is preset perception data, and the vehicle body data of the vehicle is preset vehicle body data, it is determined that the vehicle is in a preset scene, wherein the target scene includes the preset scene.

[0081] Optionally, the automatic driving system will be developed for specific scenes, so data collection for specific scenes is needed. Specifically, the cloud server can configure the preset scene of interest, and according to the specific needs, the scene for which data needs to be collected is sent to the vehicle. When the vehicle receives the preset scene requirement, it identifies the scene and triggers data recording and uploads to the cloud server. For example, if automatic driving lane changing scene data needs to be collected, it can be sent to the vehicle, which then identifies the vehicle lane changing behavior according to the perception data, and then records the whole process data of lane changing and uploads it to the cloud storage application.

[0082] The preset scene can be comprehensively determined according to perception, positioning and high-precision map information, for example: (1) road type (highway / urban / garden…), shape (straight road / curve / turn…), number of lanes, traffic light; (2) number, type, position and speed of obstacles; (3) current speed, acceleration and light state of the vehicle. Among them, the preset perception data includes but is not limited to (1) above, and the preset vehicle body data includes but is not limited to (3) above.

[0083] As an optional example, in a case where the target data includes the positioning data, determining whether the vehicle is in a target scene according to the target data can be determined in the following manner ten to manner twelve:

[0084] Manner ten: in a case where a variation of a position of the vehicle within a second preset time length determined according to the positioning data exceeds a sixth threshold value, it is determined that the vehicle is in a positioning module abnormal scene, wherein the target scene includes the positioning module abnormal scene.

[0085] Optionally, the second preset time length can be 1 second or 2 seconds.

[0086] It should be noted that if the variation of the position of the vehicle within the second preset time length exceeds the sixth threshold value (for example: the position changes from Beijing to Wuhan), it means that the position of the vehicle itself jumps, that is, the positioning module of the autonomous driving system is abnormal, and the vehicle is in the positioning module abnormal scene.

[0087] Manner eleven: in a case where a variation of a moving direction of the vehicle within the second preset time length determined according to the positioning data exceeds a seventh threshold value, it is determined that the vehicle is in the positioning module abnormal scene.

[0088] It should be noted that if the variation of the moving direction of the vehicle within the second preset time length exceeds the seventh threshold value (for example: the vehicle changes from driving forward to suddenly driving backward), it means that the heading of the vehicle itself jumps, that is, the positioning module of the autonomous driving system is abnormal, and the vehicle is in the positioning module abnormal scene.

[0089] Manner twelve: in a case where the position of the vehicle does not change within the second preset time length determined according to the positioning data, but the speed of the vehicle is a target speed, it is determined that the vehicle is in the positioning module abnormal scene.

[0090] It should be noted that if the position of the vehicle does not change, but the vehicle has a speed, it means that the positioning module of the autonomous driving system is abnormal, and the vehicle is in the positioning module abnormal scene.

[0091] As an optional example, in the case where the target data includes the prediction data, the determination of whether the vehicle is in a target scenario according to the target data can be determined in the following ways thirteen to sixteen:

[0092] Way thirteen: in the case where the prediction data is used to indicate a predicted moving state of a third obstacle, the similarity between the predicted moving state and a target moving state of the third obstacle is determined, and in the case where the similarity is less than an eighth threshold value, it is determined that the vehicle is in a prediction planning module abnormal scenario, wherein the target moving state is a moving state obtained after detecting the third obstacle, and the target scenario includes the prediction planning module abnormal scenario.

[0093] It should be noted that if the predicted moving state of the third obstacle predicted by the automatic driving module and the actual moving state of the detected third obstacle are greatly different, it indicates that the prediction planning module of the automatic driving system is abnormal, that is, the vehicle is in the prediction planning module abnormal scenario.

[0094] Way fourteen: in the case where the prediction planning data is used to indicate a planned moving trajectory of the vehicle, the feasibility of the planned moving trajectory is determined, and in the case where the feasibility is less than a ninth threshold value, it is determined that the vehicle is in a prediction planning module abnormal scenario.

[0095] Way fifteen: in the case where the prediction planning data is used to indicate a planned moving trajectory of the vehicle, it is determined whether there is an obstacle on the planned moving trajectory, and in the case where it is determined that there is an obstacle on the planned moving trajectory, it is determined that the vehicle is in a prediction planning module abnormal scenario.

[0096] Way sixteen: in the case where the prediction planning data is used to indicate that the automatic driving system cannot control the vehicle, it is determined that the vehicle is in a manual control scenario, wherein the target scenario includes the manual control scenario.

[0097] Obviously, the above-described embodiments are only a part of the embodiments of the present application, not all. In order to better understand the above-mentioned vehicle scene data acquisition method, the above process is described in combination with the following embodiments, but not used to limit the technical scheme of the embodiments of the present application, specifically:

[0098] In order to realize the full and effective collection of real scene data of the automatic driving vehicle, the present application proposes a vehicle scene data acquisition method, which can trigger data acquisition in the mode of automatic driving and manual driving, and is specifically divided into automatic driving abnormality recognition, vehicle difference analysis recognition and interesting scene recognition, and then the data is uploaded to the cloud server for storage and application.

[0099] When the vehicle is in an autonomous driving mode, Figure 4 is a data collection trigger mechanism diagram (one) according to an embodiment of the application, as shown in the accompanying Figure 4 The data collection trigger mechanism is divided into two cases,

[0100] (1) Autonomous driving abnormal scenario recognition

[0101] The abnormal scenario recognition of autonomous driving mainly includes five cases, Figure 5 is a data collection trigger scenario diagram according to an embodiment of the application;

[0102] The specific description is as follows:

[0103] (11) Autonomous driving abnormal takeover (equivalent to the above-mentioned human-controlled scene)

[0104] When the autonomous driving is running, a scene that the system cannot control appears, prompting the driver to manually take over, and data recording can be triggered for such a scene according to the takeover signal.

[0105] (12) Autonomous driving control instruction abnormality (equivalent to the above-mentioned driving abnormality scene)

[0106] When the autonomous driving is running and emergency braking occurs, it indicates that the vehicle is currently in an abnormal or extreme scenario, and data needs to be recorded for further analysis. Data recording can be triggered according to the longitudinal (equivalent to the first direction in the above-mentioned embodiment) acceleration exceeding a certain threshold value.

[0107] When the autonomous driving is running and emergency steering occurs, it indicates that the current is an abnormal or extreme scenario, and data needs to be recorded for further analysis. Data recording can be triggered according to the lateral (equivalent to the second direction in the above-mentioned embodiment) acceleration exceeding a certain threshold value and the rate of change of the steering angle exceeding a certain threshold value.

[0108] (13) Perception data abnormality (equivalent to the above-mentioned perception module abnormality scenario)

[0109] Comprehensive judgment is made on historical perception data for a period of time, and when it is found that the type of perceived obstacles jumps, the speed of perceived obstacles jumps, the ID of perceived obstacles jumps, the position of stationary obstacles jumps, etc., data recording is triggered.

[0110] When the obstacle recognition position overlaps with the ego vehicle and other common sense errors occur, data recording is triggered.

[0111] (14) Positioning data abnormality (equivalent to the above-mentioned positioning module abnormality scenario)

[0112] Comprehensive judgment is made on historical positioning data for a period of time, and when it is found that the ego vehicle position jumps, the ego vehicle heading jumps, the ego vehicle position does not change although there is vehicle speed, etc., data recording is triggered.

[0113] (15) Abnormal prediction planning data (equivalent to the abnormal scenario of the planning prediction module in the above embodiments)

[0114] The system comprehensively evaluates historical prediction and planning data over a period of time. When anomalies are found, such as a large difference between the predicted obstacle and the actual obstacle, the inability to plan a feasible trajectory, or a collision between the planned trajectory and the obstacle, data recording is triggered.

[0115] It should be noted that autonomous driving systems generally include perception, localization, prediction, and planning modules. When a functional module in an autonomous driving system malfunctions, data recording is triggered.

[0116] (2) Identification of scenes of interest (equivalent to the preset scenes in the above embodiments)

[0117] Autonomous driving systems are developed for specific scenarios, therefore data collection for these specific scenarios is necessary. (See attached image) Figure 4 As shown, scenarios of interest are configured in the cloud, and the scenarios to be collected are sent to the vehicle according to specific needs. When the vehicle receives the request for a scenario of interest, it identifies the scenario, triggers data recording, and uploads it to the cloud. For example, if it is necessary to collect autonomous driving lane-changing scenario data, it can be sent to the vehicle. The vehicle then identifies the vehicle's lane-changing behavior based on the perception data, records the entire lane-changing process, and uploads it to the cloud for storage and application.

[0118] It should be noted that the scenes of interest can be determined based on a combination of perception, positioning, and high-precision map information:

[0119] (21) Road type (expressway / city / industrial park…), shape (straight road / curve / U-turn…), number of lanes, traffic lights;

[0120] (22) The number, type, location, speed, etc. of obstacles;

[0121] (23) The vehicle’s current speed, acceleration, and lighting status.

[0122] When the vehicle is in manual driving mode Figure 6 This is a diagram (II) illustrating the data acquisition triggering mechanism according to an embodiment of the present invention, as shown in the attached diagram. Figure 3 As shown, the data collection triggering mechanism is divided into three cases:

[0123] (1) Analysis and identification of differences between people and vehicles

[0124] In the manual driving mode, the automatic driving system is simulated to run, and the control instruction does not directly control the vehicle, at this time, the operation behavior of the driver and the actual state of the vehicle are analyzed with the control instruction of the automatic driving system, when the difference between the two exceeds the set threshold (when the difference between the two exceeds the set threshold, it means that the vehicle is in the abnormal scene of the predicted control instruction), the data record is triggered.

[0125] (2) Automatic driving anomaly recognition

[0126] In the manual driving mode, the automatic driving anomaly recognition includes perception data anomaly, positioning data anomaly and planning data anomaly, and the triggering methods of the three types of anomalies are consistent with those in the automatic driving mode.

[0127] (3) Interesting scene recognition

[0128] The interesting scene recognition in the manual driving mode is consistent with that in the automatic driving mode.

[0129] It should be noted that, in order to realize the effective collection of vehicle-end data of the automatic driving system, triggering mechanisms are designed in the automatic driving mode and the manual driving mode to collect and store data.

[0130] In the automatic driving mode, automatic driving anomaly scene data triggering and interesting scene triggering are designed to improve the effective collection of data in the automatic driving mode. In the manual driving mode, through the virtual running of the automatic driving system, on the basis of collecting automatic driving anomaly scene data and interesting scenes, the triggering of the man-vehicle difference scene is increased, which can quickly collect the gap between the automatic driving system and the manual driver, effectively improve the coverage of the vehicle-end scene, and provide scene data support for the optimization and development of the automatic driving system.

[0131] Among them, in order to effectively collect automatic driving anomaly scene data, data collection is triggered in five cases, including automatic driving anomaly takeover scene, automatic driving control instruction anomaly, perception data anomaly, positioning data anomaly and prediction planning data anomaly, which can effectively trigger the anomaly scene from the whole and the module.

[0132] In order to realize specific scene data collection, an interesting scene recognition module is designed, and a cloud-end scene configuration function is designed, which can remotely issue interesting scenes in the cloud to quickly realize specific scene data collection.

[0133] Those skilled in the art can clearly understand, through the description of the foregoing embodiments, that the method according to the foregoing embodiments can be implemented by means of software on a general hardware platform as necessary, and of course can also be implemented by hardware, but in many cases the former is a better implementation. Based on such understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk) and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device) to execute the method of each embodiment of the present application.

[0134] In this embodiment, a vehicle scene data collection device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware or a combination of software and hardware is also possible and contemplated.

[0135] Figure 7 is a structural block diagram of a vehicle scene data collection device according to an embodiment of the present application, which comprises:

[0136] The acquisition module 72 is configured to acquire target data determined by an automatic driving system of a vehicle during driving of the vehicle, wherein the target data comprises at least one of the following: a control instruction of the vehicle by the automatic driving system, perception data perceived by the automatic driving system for an environment in which the vehicle is located, positioning data of the vehicle determined by the automatic driving system, and prediction planning data predicted by the automatic driving system.

[0137] The determination module 74 is configured to determine whether the vehicle is in a target scene according to the target data.

[0138] The collection module 76 is configured to collect vehicle scene data of the vehicle in the target scene when it is determined that the vehicle is in the target scene.

[0139] Through the above device, during driving of the vehicle, whether the vehicle is in a set target scene is automatically determined, and data collection is triggered. Since the ability of the vehicle to recognize a scene is stronger than that of manual recognition of a scene, the vehicle can recognize more scenes, and the scenes in which the vehicle is located during driving are diverse, so a large amount of real and diverse scene data can be collected, thereby solving the problem of less vehicle scene data.

[0140] In an example embodiment, the determining module is configured to determine whether the vehicle is in a target scenario in the case that the target data comprises the control instruction by: determining that the vehicle is in a driving abnormal scenario in the case that it is determined that the vehicle is in an autonomous driving mode and the control instruction indicates that an acceleration of the vehicle in a first direction is set to a first acceleration, wherein the first direction is a forward direction of the vehicle and the value of the first acceleration exceeds a first threshold; or determining that the vehicle is in a driving abnormal scenario in the case that it is determined that the vehicle is in an autonomous driving mode, the control instruction indicates that an acceleration of the vehicle in a second direction is set to a second acceleration and indicates that a rate of change of a turning angle of a tire of the vehicle is set to a target rate of change of the turning angle, wherein the second acceleration exceeds a second threshold and the target rate of change of the turning angle exceeds a third threshold, and an included angle between the first direction and the second direction is a preset included angle; determining a target control instruction issued by a target object to the vehicle in the case that it is determined that the vehicle is in a manual driving mode; comparing the target control instruction with the control instruction in the target data, and determining that the vehicle is in a predicted control instruction abnormal scenario in the case that a similarity between the target control instruction and the control instruction is less than a fourth threshold; and wherein the target scenario comprises the driving abnormal scenario and the predicted control instruction abnormal scenario.

[0141] In an example embodiment, the determining module is configured to determine whether the vehicle is in a target scenario in the case that the target data comprises the perception data by: determining that the vehicle is in a perception module abnormal scenario in the case that it is determined from the perception data that a type of a first obstacle perceived by a perception module of the autonomous driving system changes within a first preset time length; or determining that the vehicle is in a perception module abnormal scenario in the case that it is determined from the perception data that an identity of the first obstacle changes within the first preset time length; or determining that the vehicle is in a perception module abnormal scenario in the case that it is determined from the perception data that a variation of a moving speed of the first obstacle within the first preset time length exceeds a fifth threshold; or determining that the vehicle is in a perception module abnormal scenario in the case that it is determined from the perception data that a position of a second obstacle perceived by the perception module changes within the first preset time length; or determining that the vehicle is in a perception module abnormal scenario in the case that it is determined from the perception data that a position of a third obstacle perceived by the perception module overlaps with a position of the vehicle; or determining that the vehicle is in a preset scenario in the case that the perception data is preset perception data and vehicle body data of the vehicle is preset vehicle body data; and wherein the target scenario comprises the perception module abnormal scenario and the preset scenario.

[0142] In an example embodiment, the determining module is configured to determine whether the vehicle is in a target scenario in the case that the target data comprises the positioning data, by: determining that the vehicle is in a positioning module abnormal scenario in the case that a variation of a position of the vehicle within a second preset time length determined according to the positioning data exceeds a sixth threshold value; or determining that the vehicle is in a positioning module abnormal scenario in the case that a variation of a moving direction of the vehicle within the second preset time length determined according to the positioning data exceeds a seventh threshold value; or determining that the vehicle is in a positioning module abnormal scenario in the case that the position of the vehicle determined according to the positioning data does not change within the second preset time length, but a speed of the vehicle is a target speed; wherein the target scenario comprises the positioning module abnormal scenario.

[0143] In an example embodiment, the determining module is configured to determine whether the vehicle is in a target scenario in the case that the target data comprises the prediction planning data, by: determining a similarity between a predicted moving state of a third obstacle indicated by the prediction planning data and a target moving state of the third obstacle, and determining that the vehicle is in a prediction planning module abnormal scenario in the case that the similarity is less than an eighth threshold value, wherein the target moving state is a moving state obtained after detecting the third obstacle; or determining a feasibility of a planned moving trajectory of the vehicle indicated by the prediction planning data, and determining that the vehicle is in a prediction planning module abnormal scenario in the case that the feasibility is less than a ninth threshold value; or determining whether there is an obstacle on the planned moving trajectory of the vehicle indicated by the prediction planning data, and determining that the vehicle is in a prediction planning module abnormal scenario in the case that there is an obstacle on the planned moving trajectory; or determining that the vehicle is in a manual control scenario in the case that the prediction planning data indicates that the autonomous driving system cannot control the vehicle; wherein the target scenario comprises the prediction planning module abnormal scenario and the manual control scenario.

[0144] In an example embodiment, the determining module is configured to collect vehicle scenario data of the vehicle in the target scenario by: collecting vehicle body data of the vehicle within a preset time period, wherein the vehicle is in the target scenario within the preset time period; collecting chassis data of the vehicle within the preset time period; collecting process data and control instruction data generated by the autonomous driving system of the vehicle within the preset time period; and collecting perception data of an environment in which the vehicle is located determined by an image acquisition device and a radar sensor of the vehicle within the preset time period.

[0145] In an example embodiment, the device further comprises a processing module configured to, after collecting the vehicle scene data of the vehicle in the target scene, send the vehicle scene data to a cloud server, so that the cloud server adjusts an algorithm of the autonomous driving system according to the vehicle scene data; and obtain the target algorithm adjusted by the cloud server, and update the algorithm of the autonomous driving system to the target algorithm.

[0146] Embodiments of the present application also provide a computer readable storage medium, which stores a computer program, wherein the computer program is configured to execute the steps in any of the method embodiments when running.

[0147] Optionally, in the present embodiment, the storage medium is configured to store a computer program for executing the following steps:

[0148] S1, during driving of a vehicle, obtaining target data determined by an autonomous driving system of the vehicle, wherein the target data comprises at least one of the following: a control instruction of the vehicle by the autonomous driving system, perception data perceived by the autonomous driving system for an environment in which the vehicle is located, positioning data of the vehicle determined by the autonomous driving system, and prediction planning data predicted by the autonomous driving system.

[0149] S2, determining whether the vehicle is in a target scene according to the target data.

[0150] S3, in a case where it is determined that the vehicle is in the target scene, collecting vehicle scene data of the vehicle in the target scene.

[0151] In an example embodiment, the computer readable storage medium can include, but is not limited to, a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store computer programs.

[0152] The specific examples in the present embodiment can refer to the examples described in the above embodiments and example embodiments, which will not be described herein again.

[0153] It should be noted that the storage medium of the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the above. The computer readable storage medium may, for example, be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of computer readable storage media can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present application, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any storage medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained in the storage medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, an RF (radio frequency) or the like, or any suitable combination of the above.

[0154] Embodiments of the present application also provide an electronic device comprising a memory and a processor, the memory storing a computer program, and the processor being configured to execute the computer program to perform the steps of any of the above method embodiments.

[0155] Optionally, in the present embodiment, the processor can be configured to perform the following steps by the computer program:

[0156] S1, during driving of a vehicle, obtaining target data determined by an automatic driving system of the vehicle, wherein the target data comprises at least one of the following: a control instruction of the vehicle by the automatic driving system, perception data perceived by the automatic driving system for an environment in which the vehicle is located, positioning data of the vehicle determined by the automatic driving system, and prediction planning data predicted by the automatic driving system;

[0157] S2, determining whether the vehicle is in a target scene according to the target data;

[0158] S3, in a case where it is determined that the vehicle is in the target scene, collecting vehicle scene data of the vehicle in the target scene.

[0159] In one example embodiment, the electronic device described above can further include a transmission device connected to the processor and an input / output device connected to the processor.

[0160] The specific examples in the embodiments can refer to the examples described in the above embodiments and exemplary implementation, which will not be described here again.

[0161] Obviously, those skilled in the art should understand that the modules or steps of the present application described above can be realized by general computing devices, which can be concentrated on a single computing device or distributed on a network composed of multiple computing devices, which can be realized by program codes executable by computing devices, so that they can be stored in storage devices and executed by computing devices, and in some cases, the steps shown or described can be executed in different order, or they can be made into individual integrated circuit modules, or multiple modules or steps can be made into a single integrated circuit module. Thus, the present application is not limited to any specific combination of hardware and software.

[0162] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Those skilled in the art can make various modifications and changes to the present application. Any modification, equivalent replacement, improvement, etc. within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for collecting vehicle scene data, characterized in that, The method includes: During vehicle operation, target data determined by the vehicle's autonomous driving system is acquired, wherein the target data includes at least one of the following: control commands from the autonomous driving system to the vehicle, perception data of the environment in which the vehicle is located by the autonomous driving system, positioning data of the vehicle determined by the autonomous driving system, and prediction planning data predicted by the autonomous driving system. The vehicle is determined to be in a target scenario based on the target data, wherein the target scenario includes at least one of the following: abnormal driving scenario, abnormal predictive control command scenario, abnormal perception module scenario, preset scenario, abnormal positioning module scenario, abnormal predictive planning module scenario, and scenario requiring manual control. When it is determined that the vehicle is in the target scenario, vehicle scenario data of the vehicle in the target scenario is collected; The process of collecting vehicle scene data in the target scenario includes: Collect vehicle body data within a preset time period, wherein the vehicle is in the target scene during the preset time period; Collect chassis data of the vehicle within the preset time period; Collect process data and control command data generated by the autonomous driving system of the vehicle within the preset time period; The system collects perception data of the vehicle's environment, determined by an image acquisition device and a radar sensor, within the preset time period. The method further includes: when the target data includes the control command, determining whether the vehicle is in a target scenario based on the target data, including: If it is determined that the vehicle is in autonomous driving mode and the control command instructs to set the acceleration of the vehicle in the first direction to a first acceleration, it is determined that the vehicle is in the abnormal driving scenario, wherein the first direction is the forward direction of the vehicle, and the value of the first acceleration exceeds a first threshold. If it is determined that the vehicle is in autonomous driving mode, the control command instructs to set the acceleration of the vehicle in the second direction to a second acceleration, and instructs to set the rate of change of the vehicle's tire angle to a target rate of change of angle, then it is determined that the vehicle is in the abnormal driving scenario, wherein the second acceleration exceeds a second threshold, the target rate of change of angle exceeds a third threshold, and the angle between the first direction and the second direction is a preset angle.

2. The method for collecting vehicle scene data according to claim 1, characterized in that, When the target data includes the control command, determining whether the vehicle is in the target scenario based on the target data includes: If the vehicle is determined to be in manual driving mode, the target control command issued by the target object to the vehicle is determined; the target control command is compared with the control command in the target data, and if the similarity between the target control command and the control command is less than a fourth threshold, the vehicle is determined to be in a predicted control command abnormal scenario.

3. The method for collecting vehicle scene data according to claim 1, characterized in that, When the target data includes the perceived data, determining whether the vehicle is in the target scene based on the target data includes: If the type of the first obstacle perceived by the perception module of the autonomous driving system changes within a first preset time period based on the perception data, the vehicle is determined to be in an abnormal scenario of the perception module. If the identification of the first obstacle changes within a first preset time period based on the perception data, it is determined that the vehicle is in an abnormal scenario of the perception module. If, based on the perception data, the change in the moving speed of the first obstacle within a first preset time period exceeds a fifth threshold, it is determined that the vehicle is in an abnormal scenario of the perception module. If the position of the second obstacle sensed by the sensing module changes within a first preset time period based on the sensing data, it is determined that the vehicle is in an abnormal scenario of the sensing module. If, based on the perception data, the position of the third obstacle sensed by the perception module overlaps with the position of the vehicle, it is determined that the vehicle is in an abnormal scenario of the perception module. If the perceived data is preset perceived data and the vehicle body data is preset body data, then the vehicle is determined to be in the preset scenario.

4. The method for collecting vehicle scene data according to claim 1, characterized in that, When the target data includes the positioning data, determining whether the vehicle is in the target scene based on the target data includes: If the location of the vehicle changes by more than a sixth threshold within a second preset time period based on the location data, it is determined that the vehicle is in an abnormal scenario of the positioning module. If, based on the positioning data, the change in the vehicle's direction of movement within the second preset time exceeds a seventh threshold, the vehicle is determined to be in a positioning module malfunction scenario. If the vehicle's position remains unchanged within the second preset time period based on the positioning data, but the vehicle's speed is the target speed, then the vehicle is determined to be in an abnormal scenario of the positioning module.

5. The method for collecting vehicle scene data according to claim 1, characterized in that, When the target data includes the predicted planning data, determining whether the vehicle is in the target scenario based on the target data includes: When the prediction planning data is used to indicate the predicted movement state of a third obstacle, the similarity between the predicted movement state and the target movement state of the third obstacle is determined, and if the similarity is less than an eighth threshold, the vehicle is determined to be in an abnormal scenario of the prediction planning module, wherein the target movement state is the movement state obtained after detecting the third obstacle. When the predicted planning data is used to indicate the planned movement trajectory of the vehicle, the feasibility of the planned movement trajectory is determined, and if the feasibility is less than a ninth threshold, the vehicle is determined to be in an abnormal scenario of the predicted planning module. When the predicted planning data is used to indicate the planned movement trajectory of the vehicle, it is determined whether there are obstacles on the planned movement trajectory, and if it is determined that there are obstacles on the planned movement trajectory, it is determined that the vehicle is in an abnormal scenario of the predicted planning module. When the predicted planning data indicates that the autonomous driving system is unable to control the vehicle, it is determined that the vehicle is in the scenario requiring manual control.

6. The method for collecting vehicle scene data according to claim 1, characterized in that, After collecting vehicle scene data of the vehicle in the target scenario, the method further includes: The vehicle scene data is sent to a cloud server so that the cloud server can adjust the algorithm of the autonomous driving system based on the vehicle scene data. Obtain the target algorithm adjusted by the cloud server, and update the algorithm of the autonomous driving system to the target algorithm.

7. A vehicle scene data acquisition device, characterized in that, include: The acquisition module is used to acquire target data determined by the autonomous driving system of the vehicle during the vehicle's operation. The target data includes at least one of the following: control commands from the autonomous driving system to the vehicle, perception data of the environment in which the vehicle is located by the autonomous driving system, positioning data of the vehicle determined by the autonomous driving system, and prediction planning data predicted by the autonomous driving system. The determination module is used to determine whether the vehicle is in a target scenario based on the target data, wherein the target scenario includes at least one of the following: abnormal driving scenario, abnormal predictive control command scenario, abnormal perception module scenario, preset scenario, abnormal positioning module scenario, abnormal predictive planning module scenario, and scenario requiring manual control. The acquisition module is used to acquire vehicle scene data of the vehicle in the target scene when it is determined that the vehicle is in the target scene; The acquisition module is further configured to perform the following steps: acquiring vehicle body data within a preset time period, wherein the vehicle is in the target scene during the preset time period; acquiring chassis data of the vehicle within the preset time period; acquiring process data and control command data generated by the autonomous driving system during the preset time period; and acquiring perception data of the vehicle's environment determined by the image acquisition device and radar sensor during the preset time period. The determining module is further configured to perform the following steps: when it is determined that the vehicle is in an autonomous driving mode and the control command instructs the acceleration of the vehicle in a first direction to be set to a first acceleration, the vehicle is determined to be in the abnormal driving scenario, wherein the first direction is the forward direction of the vehicle, and the value of the first acceleration exceeds a first threshold; when it is determined that the vehicle is in an autonomous driving mode, the control command instructs the acceleration of the vehicle in a second direction to be set to a second acceleration, and instructs the tire angular change rate of the vehicle to be set to a target angular change rate, the vehicle is determined to be in the abnormal driving scenario, wherein the second acceleration exceeds a second threshold, the target angular change rate exceeds a third threshold, and the angle between the first direction and the second direction is a preset angle.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the vehicle scene data acquisition method according to any one of claims 1 to 6.

9. An electronic device, characterized in that... The electronic device includes one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to run the programs, wherein the programs are configured to execute the vehicle scene data acquisition method according to any one of claims 1 to 6.

Images