CN115891868A

CN115891868A - Fault detection method, device, electronic apparatus, and medium for autonomous vehicle

Info

Publication number: CN115891868A
Application number: CN202211357024.3A
Authority: CN
Inventors: 方雪健
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2022-11-01
Filing date: 2022-11-01
Publication date: 2023-04-04

Abstract

The present disclosure provides a method, an apparatus, an electronic device, and a medium for detecting a failure of an autonomous vehicle, which relate to the field of autonomous driving, and in particular, to the field of failure detection in the field of autonomous driving. The specific implementation scheme is as follows: a method of fault detection for an autonomous vehicle, comprising: in the process of carrying out virtual simulation test on the automatic driving vehicle, under the condition that the target abnormality of the automatic driving vehicle is detected, determining candidate faults corresponding to the target abnormality in a preset data set, wherein the preset data set comprises candidate faults corresponding to at least two preset abnormalities, the target abnormality is any one of the at least two preset abnormalities, and the candidate faults are faults of preset function modules in the automatic driving vehicle; and determining a target fault in candidate faults corresponding to the target abnormity, wherein the target fault is a fault occurring in a preset functional module in the process of virtual simulation test. The present disclosure can improve the efficiency of fault detection.

Description

Fault detection method, device, electronic apparatus, and medium for autonomous vehicle

Technical Field

The present disclosure relates to the field of autopilot, and more particularly, to the field of fault detection in the field of autopilot. And more particularly, to a method, apparatus, electronic device, and medium for detecting a failure of an autonomous vehicle.

Background

In the process of performing the virtual simulation test on the autonomous vehicle, when the autonomous vehicle is abnormal, the reason for the abnormality is generally checked. In the related art, the means for examining the cause of the occurrence of the abnormality is generally: abnormalities of the respective modules in the autonomous vehicle are checked separately to determine the cause of the abnormality.

Disclosure of Invention

The present disclosure provides a fault detection method, apparatus, electronic device, and medium for an autonomous vehicle.

According to a first aspect of the present disclosure, there is provided a fault detection method of an autonomous vehicle, including:

in the process of carrying out virtual simulation test on the automatic driving vehicle, under the condition that the target abnormality of the automatic driving vehicle is detected, determining candidate faults corresponding to the target abnormality in a preset data set, wherein the preset data set comprises at least two candidate faults corresponding to the preset abnormality, the target abnormality is any one of the at least two preset abnormalities, the candidate faults corresponding to the target abnormality are partial candidate faults in the candidate faults contained in the preset data set, and the candidate faults are faults of a preset function module in the automatic driving vehicle;

and determining a target fault in the candidate faults corresponding to the target abnormity, wherein the target fault is a fault of the preset functional module in the virtual simulation test process.

According to a second aspect of the present disclosure, there is provided a failure detection apparatus of an autonomous vehicle, comprising:

a first determining unit, configured to determine, in a process of performing a virtual simulation test on the autonomous vehicle, a candidate fault corresponding to a target abnormality in a preset data set when the autonomous vehicle is detected to have the target abnormality, where the preset data set includes candidate faults corresponding to at least two preset abnormalities, the target abnormality is any one preset abnormality of the at least two preset abnormalities, and the candidate fault corresponding to the target abnormality is a partial candidate fault in candidate faults included in the preset data set, and the candidate fault is a fault of a preset function module in the autonomous vehicle;

and a second determining unit, configured to determine a target fault in candidate faults corresponding to the target exception, where the target fault is a fault occurring in the preset functional module in the virtual simulation test process.

According to a third aspect of the present disclosure, there is provided an electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of the first aspect.

According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of the first aspect.

According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of the first aspect.

In the embodiment of the disclosure, by establishing the corresponding relationship between the preset abnormality and the candidate faults in advance, when the target abnormality of the autonomous vehicle is detected, the candidate faults corresponding to the target faults can be determined first, and then the target faults are determined in the target faults, so as to complete the fault detection process. In the embodiment of the disclosure, only the candidate faults corresponding to the target fault need to be checked, and the candidate faults corresponding to the target fault are only partial candidate faults in the candidate faults included in the preset data set, so that the fault checking range can be effectively reduced, and the fault detection efficiency is further improved.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a flow chart of a method of fault detection for an autonomous vehicle provided by an embodiment of the disclosure;

fig. 2 is a schematic structural diagram of a fault detection device of an autonomous vehicle according to an embodiment of the present disclosure;

fig. 3 is a schematic structural diagram of a second determination unit in the embodiment of the present disclosure;

FIG. 4 is a block diagram of an electronic device for implementing a fault detection method for an autonomous vehicle provided by an embodiment of the disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of embodiments of the present disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Referring to fig. 1, fig. 1 is a schematic flow chart of a fault detection method for an autonomous vehicle according to an embodiment of the present disclosure, where the fault detection method for the autonomous vehicle includes the following steps:

step S101, in the process of carrying out virtual simulation test on the automatic driving vehicle, under the condition that the target abnormality of the automatic driving vehicle is detected, determining candidate faults corresponding to the target abnormality in a preset data set, wherein the preset data set comprises at least two candidate faults corresponding to the preset abnormality, the target abnormality is any one of the at least two preset abnormalities, the candidate faults corresponding to the target abnormality are partial candidate faults in the candidate faults contained in the preset data set, and the candidate faults are faults of a preset function module in the automatic driving vehicle;

step S102, determining a target fault in candidate faults corresponding to the target abnormity, wherein the target fault is a fault of the preset functional module in the virtual simulation test process.

The virtual simulation test of the autonomous vehicle may specifically be: and carrying out virtual simulation test on the automatic driving vehicle under various test scenes. The test scenes may include various driving scenes that may be encountered during the driving process of the automatic driving vehicle, for example, the test scenes may include driving scenes such as a pedestrian crossing road scene, a preceding vehicle lane changing scene, and a normal following scene. The automatic driving vehicle is subjected to simulation test based on the test scenes, so that whether the corresponding functional modules in the automatic driving vehicle can accurately identify the test scenes or not is determined, and corresponding responses are made according to different test scenes. For example, when the autonomous vehicle is virtually simulated for testing based on the pedestrian crossing a road scene, it is determined whether the autonomous vehicle is capable of decelerating or reasonably avoiding so that subsequent autonomous vehicles can respond accordingly to various driving scenes.

Specifically, various traffic elements and traffic paramedics in the test scenario may be modeled in advance based on simulation software to obtain a virtual simulation world. The modeling can be carried out according to the actual road traffic scene, and actual attribute parameters are given to each traffic element and the traffic parameter values. In addition, road traffic scenes can be constructed, and actual attribute parameters are given to each traffic element and traffic parameter value.

It can be understood that after the modeling process is completed, corresponding attribute information may be given to each element in the set-up virtual simulation world based on preset simulation parameters, where the attribute information includes the position, speed, heading, and state information of each traffic identifier of each traffic parameter value. Then, virtual simulation is performed.

The preset data set may include the at least two preset anomalies and candidate faults corresponding to the preset anomalies, where the preset anomalies and the candidate faults corresponding to the preset anomalies may be stored in an associated manner. In this manner, when it is determined that a target abnormality occurs in the autonomous vehicle, a candidate fault corresponding to the target abnormality may be determined in the preset data set based on a correspondence between preset abnormalities and candidate faults.

The preset function module may be various function modules in the autonomous vehicle, and for example, may include a sensing module, a positioning module, a map module, and the like.

The preset abnormality may be various abnormal driving behaviors in the driving process of the autonomous vehicle, for example, the preset abnormality may include: abnormal conditions such as retrograde motion, running a red light, sudden braking, chief complaint collision, vehicle shaking, dragon drawing, exiting from an automatic driving mode and the like. Accordingly, the candidate faults may include faults that may occur in each functional module in the autonomous vehicle, for example, the candidate faults may include: the sensing module detects frame loss faults and sensing error faults in the process of detecting the target object; positioning drift faults of the positioning module, and the like.

It is to be understood that the candidate faults corresponding to the preset exception may include: all faults that can cause the autonomous vehicle to experience the preset anomaly. For example, when the preset exception is a chief collision fault, for the sensing module, the candidate fault corresponding to the chief collision fault may include: target frame loss, target delay selection, excessive target position error, target type error, virtual target and the like. And the target frame loss is a frame loss fault in the process of detecting the target object. The target delay selection is that the time for locking the target in the process of detecting the target object is too late, the error of the target position is too large, the error of the target type is the type identification error of the target object, the target which is a virtual target and is about to not exist is identified as an entity target, for example, the reflection of the tree is identified as a vehicle.

It is to be understood that whether the above-described preset abnormality occurs in the autonomous vehicle during the virtual simulation test may be detected based on the detection means in the related art, and the preset abnormality occurring in the autonomous vehicle may be determined as the target abnormality. For example, it may be determined that the autonomous vehicle has a wrong-way driving fault when it is detected that the traveling direction of the autonomous vehicle is opposite to the traveling direction indicated by the lane of the autonomous vehicle by detecting the traveling direction of the autonomous vehicle and comparing the traveling direction of the autonomous vehicle with the traveling direction indicated by the lane of the autonomous vehicle. In addition, the specific time of the red light of the traffic indicator light at each position in the virtual simulation world can be directly obtained from the simulation information, and the time of the automatic driving vehicle actually entering and exiting a certain traffic intersection can be obtained from the detection data of the automatic driving vehicle, so that when the fact that the time of the automatic driving vehicle entering and exiting the certain traffic intersection is within the time period of the red light at the traffic intersection is detected, the automatic driving vehicle is determined to have the red light running abnormality. And when the fact that the automatic driving vehicle is overlapped with the front vehicle in the virtual simulation picture is detected, determining that collision abnormity occurs. Meanwhile, the positions of the automatic driving vehicles in a plurality of continuous frames in the simulation picture can be detected, and when the change values of the transverse positions of the automatic driving vehicles between adjacent pictures in the continuous multi-frame pictures exceed the set threshold value, whether the automatic driving vehicles have shaking faults or dragon drawing faults or not is determined. When the automatic driving vehicle exits the automatic driving mode, triggering a corresponding signal for exiting the automatic driving mode, and when the signal for exiting the automatic driving mode is obtained, determining that the automatic driving vehicle has a fault for exiting the automatic driving mode.

Accordingly, in the case where it is determined that the candidate fault corresponding to the target abnormality occurs, it may be detected whether the candidate fault occurs in a preset function module in the autonomous vehicle in the course of the virtual simulation test based on a detection means in the related art, and it may be determined that the candidate fault output from the autonomous vehicle is the target fault.

In this embodiment, by establishing a correspondence between the preset abnormality and the candidate fault in advance, when the target abnormality of the autonomous vehicle is detected, the candidate fault corresponding to the target fault may be determined first, and then the target fault is determined among the target faults, so as to implement the process of completing the fault detection. In the embodiment of the present disclosure, only the candidate faults corresponding to the target fault need to be checked, and the candidate faults corresponding to the target fault are only partial candidate faults in the candidate faults included in the preset data set, so that the fault checking range can be effectively narrowed, and the fault detection efficiency can be further improved.

Optionally, the candidate faults corresponding to the target anomaly include at least two first faults, and the determining a target fault in the candidate faults corresponding to the target anomaly includes:

acquiring a detection parameter set and a simulation parameter set, wherein the detection parameter set comprises detection attribute parameters for detecting a target object by the automatic driving vehicle in the virtual simulation test process; the simulation parameter set comprises a true value attribute parameter of the target object in the virtual simulation test process; the target object includes at least one of: the autonomous vehicle and a driving environment object outside the autonomous vehicle;

determining the target fault among the at least two first faults based on the set of detection parameters and the set of simulation parameters.

The first fault may be a fault that may occur in various functional modules in the autonomous vehicle. For example, the method can include that a sensing module detects frame loss faults and sensing error faults in the process of detecting the target object; positioning drift faults of the positioning module, and the like.

In the process of carrying out the virtual simulation test on the automatic driving vehicle, the automatic driving vehicle usually senses the external driving environment information through the sensing module and then outputs corresponding driving actions based on the sensed external driving environment information. However, when the sensed information is erroneous, the above-described preset abnormality may be caused to occur in the autonomous vehicle. And typically a specific detection data error will result in a specific abnormal driving behavior, for example, when an error is detected for a preceding vehicle, it may result in a collision of the autonomous vehicle with the preceding vehicle.

Therefore, in the embodiment of the present disclosure, when it is required to determine whether a certain first fault occurs in the process of performing the virtual simulation test on the autonomous vehicle, it is only required to determine whether the detection data of the first fault is abnormal in the process of performing the virtual simulation test on the autonomous vehicle, that is, it may be determined whether the first fault occurs in the autonomous vehicle in the process of performing the virtual simulation test. Specifically, when the detection data that can cause the first fault is abnormal, it is determined that the first fault occurs in the autonomous vehicle during the virtual simulation test.

Therefore, in the process of carrying out the virtual simulation test on the automatic driving vehicle, the information sensed by each module in the automatic driving vehicle is stored in the detection parameter set, so that when whether a certain first fault occurs in the automatic driving vehicle is determined, data corresponding to the first fault in the detection parameter set is detected to determine whether the first fault occurs. Wherein the information perceived by the modules may include: the original information collected by each module may also include information obtained after the original information is processed by each module, that is, the detection parameter set may include the original information collected by each module and the information obtained after the original information is processed by each module.

In the process of performing the virtual simulation test on the autonomous vehicle, the state of the autonomous vehicle and the external driving environment are generally required to be sensed, so the detection parameter set includes the detection attribute parameters of the autonomous vehicle and the detection attribute parameters of the driving environment objects other than the autonomous vehicle. The detection attribute parameter is an attribute value detected by detecting the target object. For example, when the target object is a vehicle ahead of an autonomous vehicle, the detection attribute parameters may include: position, speed, etc. of the vehicle ahead.

In addition, since the detection parameter set includes detection attribute parameters of a target object, in order to determine whether data in the detection parameter set is abnormal, it is necessary to acquire real attribute parameters of the target object. Therefore, whether the detection parameters are correct or not can be determined by comparing the parameters in the detection parameter set with the real attribute parameters corresponding to the simulation parameter set.

Specifically, in the process of performing virtual simulation test, the real attributes of each target object in the virtual world at the initial time of simulation are usually manually input by related personnel, so the real attributes of the target object can be directly obtained from the simulation. In this way, the set of simulation parameters can be derived from the real properties of the target object given in the simulation software.

In this embodiment, when it is required to determine whether a certain first abnormality occurs in the autonomous vehicle in the virtual simulation test process, it may be determined whether the first abnormality occurs by comparing the detected attribute parameter corresponding to the first abnormality with the corresponding real attribute parameter, so as to implement the determination process of the target abnormality.

Optionally, said determining a target fault among the at least two first faults based on the set of detection parameters and the set of simulation parameters comprises:

determining a first candidate fault as the target fault under the condition that the first attribute parameter is not matched with the second attribute parameter;

the first candidate fault is one of the at least two first faults, and the first candidate fault is used for representing that the target attribute of the preset functional module is abnormal; the first attribute parameter is an attribute parameter in the detection parameter set and is used for representing the target attribute of the preset functional module; the second attribute parameter is an attribute parameter in the simulation parameter set, which is used for representing the target attribute of the preset functional module.

The first fault candidate described above may be various types of faults that may occur in the respective function modules in the autonomous vehicle. For example, the first candidate fault may be any fault in candidate faults corresponding to the sensing module, that is, the first candidate fault may be any fault in "target frame loss, target delay selection, target position error too large, target type error, and target as a dummy target".

The mismatch between the first attribute parameter and the second attribute parameter may mean that the first attribute parameter and the second attribute parameter are not equal to each other, or that a difference between the first attribute parameter and the second attribute parameter exceeds a preset threshold.

In an embodiment of the present disclosure, the test scenario may be a scenario in which a preceding vehicle changes lanes to a lane of a main vehicle, where the main vehicle is the above-mentioned automatic driving vehicle. The first candidate fault may be target delay selection, the preset function module is a sensing module, and the target attribute is time for the sensing module to select a target object. When the selection time of the current vehicle to the front vehicle is too late due to the lane change of the current vehicle, the current vehicle may collide with the front vehicle or the current vehicle may be suddenly braked, and therefore, the target abnormality may be a main responsible collision or sudden brake.

Specifically, when the front vehicle starts to change lanes, the main vehicle selects and identifies the front vehicle. Therefore, in order to determine whether the delayed checkup failure occurs in the host vehicle, the first attribute parameter may be a point in time at which the sensing module of the host vehicle starts to check the preceding vehicle, and the first attribute parameter may be directly obtained from the detected attribute parameter. And the second attribute parameter may be a time point at which the preceding vehicle starts to change lanes, and the time point may be directly obtained from the simulation parameter set. In this way, a judgment threshold value may be set in advance, and when the time difference between the first attribute parameter and the second attribute parameter is larger than the judgment threshold value, it is determined that the delayed hit fault occurs in the host vehicle, and the delayed hit fault is determined as a target fault and output.

In this embodiment, when determining whether a certain abnormality occurs in a preset function module of the autonomous vehicle, since the abnormality specifically indicates that an abnormality occurs in a target attribute of a specific function module in the autonomous vehicle, a first attribute parameter corresponding to the target attribute may be acquired from the detection parameter set, and a second attribute parameter corresponding to the target attribute may be acquired from the simulation parameter set, and then, it is determined whether the first attribute parameter matches the second attribute parameter to determine whether the abnormality occurs in the autonomous vehicle during the virtual simulation test.

Optionally, the preset function module includes a sensing module and a positioning module, and before determining that the first candidate fault is the target fault, the method further includes:

determining a matching state of the first attribute parameter and the second attribute parameter based on a first matching condition if the first candidate fault is a fault of the sensing module; determining a matching state of the first attribute parameter and the second attribute parameter based on a second matching condition if the first candidate fault is a fault of the positioning module;

wherein the first matching condition is different from the second matching condition.

The first matching condition may include a determination condition for determining whether each attribute parameter in the sensing module is abnormal, and correspondingly, the second matching condition may include a determination condition for determining whether each attribute parameter in the positioning module is abnormal. And the first matching condition and the second matching condition may be preset.

It will be appreciated that the target anomaly may be an anomaly caused by a fault in the sensing module and may also be an anomaly caused by a fault in the positioning module. In addition, the failure of the sensing module and the failure of the positioning module may correspond to the same preset abnormality. Thus, the at least two first faults may comprise a fault of the perception module and/or a fault of the localization module.

In this embodiment, by presetting the first matching condition and the second matching condition, when it is required to determine whether a corresponding first fault occurs in the sensing module and the positioning module during the virtual simulation test of the autonomous vehicle, the determination process of the target fault may be implemented by performing discrimination based on the first matching condition and the second matching condition.

Optionally, the first matching condition comprises at least one of:

when the first candidate fault is a detection frame loss fault and the number of detection frames for the target object is not matched with the number of shooting frames for the target object, determining that the first attribute parameter is not matched with the second attribute parameter, wherein the first attribute parameter comprises the number of detection frames and the second attribute parameter comprises the number of shooting frames;

determining that the first attribute parameter is not matched with the second attribute parameter when the first candidate fault is a delayed opt-in fault and a difference value between a first time point and a second time point is greater than a first threshold, wherein the first time point is an actual opt-in time point of the target object by the autonomous vehicle, the second time point is a time point when the target object enters a detection range of the autonomous vehicle, the first attribute parameter comprises the first time point, and the second attribute parameter comprises the second time point;

determining that the first attribute parameter does not match the second attribute parameter if the first candidate fault is a detection fault for an attribute of a target obstacle, and a first attribute detection parameter of the target obstacle does not match a first attribute true parameter of the target obstacle, the target object including the target obstacle, the first attribute parameter including the first attribute detection parameter, the second attribute parameter including the first attribute true parameter, the attribute of the target obstacle including at least one of: a location attribute, a speed attribute, and a type attribute;

determining that the first attribute parameter does not match the second attribute parameter when the first candidate fault is a detection fault of an attribute of a lane line and the second attribute detection parameter of the lane line does not match the second attribute true parameter of the lane line, the target object including the lane line, the first attribute parameter including the second attribute detection parameter, the second attribute parameter including the second attribute true parameter, the attribute of the lane line including at least one of: the form attribute of the lane line and the position attribute of the lane line.

The target object may be a preset object, for example, in a preceding vehicle lane change test scenario, the target object may be a preceding vehicle. The following takes the target object as a leading vehicle in a leading vehicle lane change test scene as an example, and further explains the method provided by the embodiment of the disclosure.

The frame loss detection fault can be a fault of missing detection in the process of identifying the target object. Specifically, after the target object is selected by the host vehicle, the target object is continuously photographed and the photographed image is transmitted to the sensing module, and the sensing module recognizes the target object in the photographed image to determine the real-time position of the target object. However, in the process of recognizing the target object in the captured image by the sensing module, there may be a problem of missing detection, that is, the image content of the target object is included in a certain frame of captured image, but the sensing module does not output the position of the target object for the frame of captured image, which may result in an erroneous driving decision of the autonomous vehicle. The number of detection frames of the target object may be the number of captured images including the target object detected by the sensing module in the virtual simulation test process of the sensing module, and the number may be directly obtained from the detection parameter set. And the number of the shooting frames of the target object, namely the number of the shooting times of the target object after the target object is selected by the host vehicle, can be directly obtained from the simulation parameter set, so that whether the frame loss detection fault occurs can be determined by determining whether the number of the detection frames of the target object is equal to the number of the shooting frames of the target object.

The delayed hit fault is a fault that is hit too late for the target object. The above detection range may refer to a lane where the host vehicle is located, that is, the second time point is a time actual point at which the target object starts changing lanes. In this way, the delay time of the target object selected by the host vehicle can be determined by comparing the first time point of the target object selected by the host vehicle with the time point at which the target object actually starts to change lanes, and the delayed selection fault of the host vehicle is determined when the delay time is greater than the first threshold value.

The detecting the fault of the attribute of the target obstacle may specifically include: location detection faults, speed detection faults, and type detection faults. The position detection failure may be that an error between a detected position of the target obstacle and an actual position of the target obstacle exceeds a preset position error. The speed detection fault may be that an error between a detected speed of the target obstacle and an actual speed of the target obstacle exceeds a preset speed error. The above-described type of detection failure is a detection error of the type of the target obstacle, for example, a pedestrian is erroneously detected as a vehicle. The first attribute detection parameters may include a position detection parameter, a speed detection parameter, and a type detection parameter for a target obstacle. The first attribute true parameters may include a true position parameter, a true velocity parameter, and a true type parameter of the target obstacle.

Correspondingly, when the first candidate fault is a position detection fault of a target obstacle, and the position detection parameter of the target obstacle is not matched with the real position parameter of the target obstacle, the first attribute parameter is determined not to be matched with the second attribute parameter. Wherein, the mismatch between the position detection parameter and the actual position parameter may be: the distance between the location indicated by the location detection parameter and the location indicated by the true location parameter exceeds a preset distance threshold.

And when the first candidate fault is a speed detection fault of a target obstacle, and the speed detection parameter of the target obstacle is not matched with the real speed parameter of the target obstacle, determining that the first attribute parameter is not matched with the second attribute parameter. Wherein, the speed detection parameter not matching with the real speed parameter may be: the distance between the speed indicated by the speed detection parameter and the speed indicated by the real speed parameter exceeds a preset speed threshold.

And when the first candidate fault is a type detection fault of a target obstacle and the type detection parameter is different from the real type parameter, determining that the first attribute parameter is not matched with the second attribute parameter.

The form attribute of the lane line: the length of the lane line and whether the lane line is missing may be included, and the position attribute of the lane line may include: the lane line change state attribute, the relative position attribute of two lane lines of the same lane, and the position error attribute of the lane line. Accordingly, the detecting the failure of the attribute of the lane line may include: the method comprises the following steps of detecting the length of a lane line, shaking the lane line, detecting the internal and external eight faults of the lane line, missing faults of single side and double sides of the lane line and position error faults of the lane line.

Accordingly, the second attribute detection parameter may include: the detected length of the lane line, the detected state of change in the position of the lane line, the detected form of the lane line, and the detected position of the lane line. The second attribute true parameter may include: the actual length of the lane line, the actual lane line position, the actual lane line shape, and the actual lane line shape.

And when the first candidate fault is a lane line length detection fault and the difference value between the detected length of the lane line and the real length of the lane line is smaller than a preset length threshold value, determining that the first attribute parameter is not matched with the second attribute parameter.

And when the first candidate fault is a lane line shaking fault and the detected lane line position change state indicates that the standard deviation of the position error change quantity between the positions of the lane lines shot by continuous multiple frames exceeds a preset threshold, determining that the first attribute parameter is not matched with the second attribute parameter.

And when the first candidate fault is a lane line internal and external eight faults and the detected lane line form indicates that the slope of the lane line in continuous multi-frame images exceeds a preset slope threshold, determining that the first attribute parameter is not matched with the second attribute parameter.

And when the first candidate fault is a single-side and double-side missing fault of the lane line and continuous frames of actual lane lines exist in simulation time but the lane line is not detected, determining that the first attribute parameter is not matched with the second attribute parameter.

When the first candidate fault is a lane line position error fault and the difference between the detected lane line position and the real lane line position is greater than a set position error threshold, determining that the first attribute parameter is not matched with the second attribute parameter.

Please refer to table 1 below for the definition of the fault existing in the sensing module in an embodiment of the present disclosure, and refer to table 2 below for the corresponding relationship between the detection policy corresponding to each fault type in the first matching condition:

TABLE 1

TABLE 2

Please refer to table 3, where table 3 shows candidate faults of the sensing module corresponding to the preset abnormality.

TABLE 3

/>

In table 3, "O" indicates that there is a correspondence, and "X" indicates that there is no correspondence, for example, the candidate faults in the sensing module corresponding to the preset abnormality "chief complaint collision" include: target frame loss, target delay selection, overlarge target speed error, overlarge target position error and wrong target type.

In the embodiment, the fault types possibly existing in the sensing module are determined in advance, and the detection strategy corresponding to each fault is preset, so that when it is required to determine whether the sensing module has the corresponding fault in the virtual simulation test process, the preset detection strategy can be directly adopted for detection, and the fault detection process of the sensing module is realized.

Optionally, the second matching condition comprises at least one of:

determining that the first attribute parameters include the detected location parameters and the second attribute parameters include the actual location parameters when the first candidate fault is a location drift fault of the autonomous vehicle and the detected location parameters of the autonomous vehicle do not match the actual location parameters of the autonomous vehicle, the location drift fault including a position drift fault and a heading angle drift fault;

and under the condition that the first candidate fault is a positioning jump fault of the automatic driving vehicle and a first position change parameter is not matched with a second position change parameter, determining that the first attribute parameter is not matched with the second attribute parameter, wherein the first position change parameter is a position change parameter detected by the automatic driving vehicle, the second position change parameter is a real position change parameter of the automatic driving vehicle, the first attribute parameter comprises the first position change parameter, the second attribute parameter comprises the real positioning parameter, and the positioning jump fault comprises a positioning jump fault and a course angle jump fault.

Please refer to table 4 below for the definition of the fault existing in the positioning module in an embodiment of the present disclosure, and refer to table 5 below for the corresponding relationship between the detection policy corresponding to each fault type in the second matching condition:

TABLE 4

TABLE 5

/>

The position error described in table 5 refers to the coordinate of the center point of the rear axle of the vehicle output by the positioning module in the cartesian coordinate system established with the center of the rear axle of the automatically driven vehicle in the simulation as the origin, the front side of the vehicle as the x-axis, the side of the vehicle as the y-axis, and the vertical direction as the z-axis, and the course angle error is the same.

In addition, according to the situation of the road test problem, the positioning drift may cause abnormal driving behaviors such as shaking/dragon drawing, collision risk or road shoulder collision of the vehicle, and the positioning jump may cause abnormal driving behaviors such as vehicle exit from automatic driving, so that the relation between the abnormal behavior of the main vehicle and the positioning problem can be established similarly to the analysis of the perception problem, and the tracing analysis of the abnormal behavior problem of the main vehicle is facilitated.

In the embodiment, the fault types possibly existing in the positioning module are determined in advance, and the detection strategy corresponding to each fault is preset, so that when it is required to determine whether the positioning module has the corresponding fault in the virtual simulation test process, the preset detection strategy can be directly adopted for detection, so as to realize the fault detection process of the positioning module.

Optionally, the preset function module further includes a map module, the candidate faults corresponding to the target anomaly further include at least two second faults, the second faults are faults of the map module, and determining a target fault in the candidate faults corresponding to the target anomaly further includes:

determining the target failure among the at least two second failures if it is determined that the first candidate failure is a failure of the sensing module and a module other than the positioning module based on the first matching condition and the second matching condition, and there is no failure in the module other than the mapping module.

Because the map module usually provides an indication function for other modules, and does not need to collect data nor process data, it is impossible to detect a fault by a method similar to the above-described positioning module and sensing module, that is, it is impossible to detect whether a fault exists by comparing a detection value with a real value. In the related art, a map is mainly provided, the failure rate of the map is relatively low, and the failure rates of the sensing module and the positioning module are relatively high. Therefore, when the target abnormality occurs in the automatic driving vehicle, the map module can be used as the cause of the target abnormality under the condition that the sensing module and the positioning module are determined not to have faults. And carrying out fault detection in the candidate faults corresponding to the map module.

As described above, based on the first matching condition and the second matching condition, the first candidate fault is determined to be a fault of the sensing module and another module except the positioning module, that is, based on the first matching condition and the second matching condition, it is determined that the sensing module and the positioning module are not faulty in the process of the virtual simulation test.

It is understood that the absence of a fault in a module other than the map module means that: in the process of the virtual simulation test, faults do not exist in other modules except the map module, the perception module and the positioning module. Specifically, in order to ensure that no fault occurs in the map module, the sensing module, and the other modules except for the positioning module during the virtual simulation test, the map module, the sensing module, and the other modules except for the positioning module may be set to an ideal state in the simulation software. In this way, in the process of performing the virtual simulation test, when the target is abnormal, only the modules in the map module, the sensing module and the positioning module may be abnormal. And when it is determined that the sensing module and the positioning module are not in fault based on the first matching condition and the second matching condition, the target abnormality may be considered as an abnormality caused by a fault of the map module. Accordingly, the target failure may be determined among the at least two second failures.

In this embodiment, when the first candidate fault is determined to be a fault of the module other than the sensing module and the positioning module based on the first matching condition and the second matching condition, and when there is no fault in the module other than the map module, the target fault is determined among the at least two second faults, so as to ensure that fault detection can be performed quickly even when the map module has a fault.

Optionally, the at least two second faults include a second candidate fault, the autonomous vehicle performing the virtual simulation test based on map information in the map module, the determining the target fault in the at least two second faults includes:

determining that the second candidate fault is a target fault when the second candidate fault is a target map element tagging fault and it is detected that the target map element in the map information has a tagging fault, where the target map element includes at least one of: speed limit signs, lane lines, traffic indicator lights and lanes;

determining that the second candidate fault is the target fault when the second candidate fault is a binding relation fault between map elements and the binding relation fault is detected to exist between the map elements in the map information, wherein the binding relation comprises at least one of the following: the binding relationship between different lanes, and the binding relationship between the traffic light and the lane.

Referring to table 6 below, possible faults of the map module may include: the method comprises the following steps of element missing labeling fault, element error labeling fault, element binding relation missing fault, element binding relation error fault and element labeling error overlarge fault.

TABLE 6

The map speed limit loss refers to the loss of the speed limit mark of the lane where the main vehicle is located, and at the moment, the main vehicle can be caused to overspeed. A successive (or subsequent) absence of the host lane is: since in the map, the road ahead or behind the lane in which the host vehicle is located is missing.

Specifically, the correspondence between the candidate fault and the preset abnormality in the map module may be established in advance. In this way, when it is determined that a target abnormality occurs in the host vehicle during the virtual simulation test and it is determined that the abnormality is not caused by the perception module and the localization module, the at least two second faults may be determined among the faults that may exist in the map module using the correspondence based on the type of abnormality according to the target abnormality. And detecting whether the map module has the second fault by means in the related art to determine a target fault.

In the virtual simulation test, when the host vehicle has pause/dragon drawing, the smoothness of a map lane is not enough or the binding of the inheritance relationship of the lane is wrong; when the main vehicle exits from the automatic driving mode, the lane inheritance relationship is possibly lost; when the vehicle runs in the wrong direction, the lane direction marking error is probably caused; when the vehicle runs the red light, the traffic light corresponding to the main vehicle lane may be unbound or incorrectly bound.

In the embodiment, the possible fault types of the map module are determined in advance, and the preset abnormity corresponding to each fault type is preset, so that when the main vehicle is abnormal in target, at least two second faults can be screened out from the possible faults of the map module, and the fault detection efficiency is improved conveniently.

Optionally, the preset anomaly comprises at least one of: collision, braking deceleration exceeding preset deceleration, vehicle shaking amplitude exceeding preset amplitude, exiting automatic driving mode, reversing and running red light.

The collision can be a main vehicle owner duty collision, sudden braking occurs when the braking deceleration exceeds a preset deceleration, and vehicle shaking amplitude exceeds a preset amplitude, namely the vehicle shakes.

It can be understood that means in the related art may be adopted to detect whether the preset abnormality occurs in the autonomous driving vehicle in the virtual simulation test process, and when the preset abnormality occurs, the abnormality information may be output, so that subsequent related personnel may determine the reason causing the preset abnormality based on the fault detection method provided by the present disclosure.

In the embodiment, the abnormal types of various preset abnormalities are preset, and the candidate faults corresponding to each preset abnormality are set, so that when the preset abnormalities occur in the process of carrying out the virtual simulation test on the automatic driving vehicle, the fault troubleshooting range can be reduced, and the fault detection efficiency is further improved.

It should be noted that, in the specific example, only the sensing module, the map module and the positioning module are described. The method of the disclosed embodiments may also be applied to the fault detection process of other modules of an autonomous vehicle.

In addition, in another embodiment of the present disclosure, during the virtual simulation test, the above fault detection method may be used to test each module in the autonomous vehicle one by one. For example, when a map module is tested, other modules except the map module are set to be in an ideal state, then the map module is tested based on various test scenes, then, when a target fault occurs, the candidate fault in the map module corresponding to the target fault is determined based on the corresponding relation between the preset fault and the candidate fault, and fault detection is performed from the determined candidate fault.

The fault detection method provided by the embodiment of the disclosure has the following beneficial effects: firstly, since fault detection is performed only when the autonomous vehicle is abnormal, related personnel can firstly pay attention to the abnormal problem of the autonomous vehicle, so that the problem positioning efficiency is improved, and the situation that indexes exceed the limit but do not affect the operation of the autonomous vehicle is ignored. Secondly, because each module is detected only when abnormal driving behaviors occur, the simulation operation efficiency can be improved, and the computing resources are saved.

Referring to fig. 2, fig. 2 is a schematic structural diagram of a fault detection device 200 of an autonomous vehicle according to an embodiment of the present disclosure, where the fault detection device 200 of the autonomous vehicle includes:

a first determining unit 201, configured to determine, in a preset data set, candidate faults corresponding to a target abnormality when the target abnormality of the autonomous vehicle is detected in a process of performing a virtual simulation test on the autonomous vehicle, where the preset data set includes candidate faults corresponding to at least two preset abnormalities, the target abnormality is any one preset abnormality of the at least two preset abnormalities, and the candidate fault corresponding to the target abnormality is a partial candidate fault in the candidate faults included in the preset data set, where the candidate fault is a fault of a preset function module in the autonomous vehicle;

a second determining unit 202, configured to determine a target fault in candidate faults corresponding to the target anomaly, where the target fault is a fault occurring in the preset functional module in the virtual simulation test process.

Optionally, referring to fig. 3, the candidate faults corresponding to the target anomaly include at least two first faults, and the second determining unit 202 includes:

an obtaining subunit 2021, configured to obtain a detection parameter set and a simulation parameter set, where the detection parameter set includes a detection attribute parameter for detecting a target object by the autonomous vehicle in the virtual simulation test process; the simulation parameter set comprises a true value attribute parameter of the target object in the virtual simulation test process; the target object includes at least one of: the autonomous vehicle and a driving environment object outside the autonomous vehicle;

a determining subunit 2022, configured to determine the target fault among the at least two first faults based on the detection parameter set and the simulation parameter set.

Optionally, the determining subunit 2022 is specifically configured to determine, when the first attribute parameter does not match the second attribute parameter, that the first candidate fault is the target fault;

the first candidate fault is one of the at least two first faults, and the first candidate fault is used for representing that the target attribute of the preset functional module is abnormal; the first attribute parameter is an attribute parameter in the detection parameter set and used for representing the target attribute of the preset functional module; the second attribute parameter is an attribute parameter in the simulation parameter set, which is used for representing the target attribute of the preset functional module.

Optionally, the preset function module includes a sensing module and a positioning module, and the determining subunit 2022 is specifically further configured to determine, based on a first matching condition, a matching state of the first attribute parameter and the second attribute parameter when the first candidate fault is a fault of the sensing module; determining a matching state of the first attribute parameter and the second attribute parameter based on a second matching condition if the first candidate fault is a fault of the positioning module;

Optionally, the first matching condition comprises at least one of:

determining that the first attribute parameter does not match the second attribute parameter if the first candidate fault is a detection fault for an attribute of a target obstacle, and the first attribute detection parameter of the target obstacle does not match the first attribute true parameter of the target obstacle, wherein the target object includes the target obstacle, the first attribute parameter includes the first attribute detection parameter, the second attribute parameter includes the first attribute true parameter, and the attribute of the target obstacle includes at least one of: a location attribute, a velocity attribute, and a type attribute;

determining that the first attribute parameter does not match with the second attribute parameter when the first candidate fault is a detection fault of an attribute of a lane line and the second attribute detection parameter of the lane line does not match with the second attribute true parameter of the lane line, wherein the target object includes the lane line, the first attribute parameter includes the second attribute detection parameter, the second attribute parameter includes the second attribute true parameter, and the attribute of the lane line includes at least one of: the form attribute of the lane line and the position attribute of the lane line.

Optionally, the second matching condition comprises at least one of:

determining that the first attribute parameter comprises the detected positioning parameter and the second attribute parameter comprises the real positioning parameter, and the positioning drift fault comprises a position drift fault and a course angle drift fault, when the first candidate fault is the positioning drift fault of the autonomous vehicle and the detected positioning parameter of the autonomous vehicle is not matched with the real positioning parameter of the autonomous vehicle;

Optionally, the preset function module further includes a map module, the candidate faults corresponding to the target anomaly further include at least two second faults, the second faults are faults of the map module, and the determining subunit 2022 is specifically further configured to determine, based on the first matching condition and the second matching condition, that the first candidate fault is a fault of the module other than the sensing module and the positioning module, and determine the target fault in the at least two second faults when the module other than the map module has no fault.

Optionally, the at least two second faults include a second candidate fault, the autonomous vehicle performs the virtual simulation test based on the map information in the map module, and the determining subunit 2022 is further specifically configured to determine that the second candidate fault is a target fault when the second candidate fault is a target map element tagging fault and it is detected that the target map element in the map information has a tagging fault, where the target map element includes at least one of: speed limit signs, lane lines, traffic indicator lights and lanes;

the determining subunit 2022 is further specifically configured to determine that the second candidate fault is the target fault when the second candidate fault is a binding relationship fault between map elements and it is detected that the binding relationship fault exists between the map elements in the map information, where the binding relationship includes at least one of: the binding relationship between different lanes, and the binding relationship between the traffic light and the lane.

Optionally, the preset exception comprises at least one of: collision, braking deceleration exceeding preset deceleration, vehicle shaking amplitude exceeding preset amplitude, exiting automatic driving mode, reversing and running red light.

It should be noted that the fault detection apparatus 200 of an autonomous vehicle according to this embodiment can implement all technical solutions of the above-mentioned fault detection method embodiments of an autonomous vehicle, so that at least all technical effects can be achieved, and details are not described here.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the customs of public sequences.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 4 shows a schematic block diagram of an example electronic device 400 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 4, the electronic device 400 includes a computing unit 401 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 402 or a computer program loaded from a storage unit 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The calculation unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.

A number of components in the electronic device 400 are connected to the I/O interface 405, including: an input unit 406 such as a keyboard, a mouse, or the like; an output unit 407 such as various types of displays, speakers, and the like; a storage unit 408, such as a magnetic disk, optical disk, or the like; and a communication unit 409 such as a network card, modem, wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

Computing unit 401 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 401 executes the respective methods and processes described above, such as the failure detection method of the autonomous vehicle. For example, in some embodiments, the method of fault detection for an autonomous vehicle may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 400 via the ROM 402 and/or the communication unit 409. When the computer program is loaded into RAM 403 and executed by computing unit 401, one or more steps of the above described method of fault detection for an autonomous vehicle are performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the fault detection method of the autonomous vehicle by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on 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 compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A fault detection method of an autonomous vehicle, comprising:

in the process of carrying out virtual simulation test on the automatic driving vehicle, under the condition that the automatic driving vehicle is detected to have target abnormity, determining candidate faults corresponding to the target abnormity in a preset data set, wherein the preset data set comprises at least two candidate faults corresponding to the preset abnormity, the target abnormity is any one preset abnormity of the at least two preset abnormity, the candidate faults corresponding to the target abnormity are partial candidate faults in the candidate faults contained in the preset data set, and the candidate faults are faults of a preset function module in the automatic driving vehicle;

and determining a target fault in candidate faults corresponding to the target exception, wherein the target fault is a fault of the preset functional module in the process of the virtual simulation test.

2. The method of claim 1, wherein the candidate faults corresponding to the target anomaly include at least two first faults, and the determining a target fault among the candidate faults corresponding to the target anomaly comprises:

acquiring a detection parameter set and a simulation parameter set, wherein the detection parameter set comprises detection attribute parameters for detecting a target object by the automatic driving vehicle in the virtual simulation test process; the simulation parameter set comprises a true value attribute parameter of the target object in the virtual simulation test process; the target object includes at least one of: the autonomous vehicle and a driving environment object outside of the autonomous vehicle;

3. The method of claim 2, wherein said determining a target fault among said at least two first faults based on said set of detection parameters and said set of simulation parameters comprises:

4. The method of claim 3, wherein the preset functional modules include a perception module and a localization module, and wherein the method further comprises, prior to determining that the first candidate fault is the target fault:

5. The method of claim 4, wherein the first matching condition comprises at least one of:

determining that the first attribute parameter is not matched with the second attribute parameter when the first candidate fault is a delayed pick-up fault and a difference value between a first time point and a second time point is larger than a first threshold value, wherein the first time point is an actual pick-up time point of the target object by the autonomous vehicle, the second time point is a time point when the target object enters a detection range of the autonomous vehicle, the first attribute parameter comprises the first time point, and the second attribute parameter comprises the second time point;

determining that the first attribute parameter does not match the second attribute parameter if the first candidate fault is a detection fault for an attribute of a target obstacle, and the first attribute detection parameter of the target obstacle does not match the first attribute true parameter of the target obstacle, wherein the target object includes the target obstacle, the first attribute parameter includes the first attribute detection parameter, the second attribute parameter includes the first attribute true parameter, and the attribute of the target obstacle includes at least one of: a location attribute, a speed attribute, and a type attribute;

6. The method of claim 4, wherein the second matching condition comprises at least one of:

7. The method according to claim 4, wherein the preset functional modules further include a map module, the candidate faults corresponding to the target anomaly further include at least two second faults, the second faults are faults of the map module, and the determining of the target fault in the candidate faults corresponding to the target anomaly further includes:

determining the target fault among the at least two second faults if the first candidate fault is determined to be a fault of the module other than the sensing module and the positioning module based on the first matching condition and the second matching condition, and if there is no fault in the module other than the mapping module.

8. The method of claim 7, wherein the at least two second faults include a second candidate fault, the autonomous vehicle conducting the virtual simulation test based on map information in the map module, the determining the target fault among the at least two second faults comprising:

determining that the second candidate fault is the target fault when the second candidate fault is a binding relation fault between map elements and it is detected that the binding relation fault exists between the map elements in the map information, where the binding relation includes at least one of: the binding relationship between different lanes, and the binding relationship between the traffic light and the lane.

9. The method of any one of claims 1 to 8, wherein the preset anomalies include at least one of: collision, braking deceleration exceeding preset deceleration, vehicle shaking amplitude exceeding preset amplitude, exiting automatic driving mode, reversing and running red light.

10. A fault detection device of an autonomous vehicle, comprising:

the automatic driving vehicle virtual simulation testing method comprises a first determining unit, a second determining unit and a third determining unit, wherein the first determining unit is used for determining candidate faults corresponding to target abnormity in a preset data set under the condition that the automatic driving vehicle is detected to have the target abnormity in the process of carrying out virtual simulation testing on the automatic driving vehicle, the preset data set comprises at least two candidate faults corresponding to the preset abnormity, the target abnormity is any one of the at least two preset abnormity, the candidate faults corresponding to the target abnormity are partial candidate faults in the candidate faults contained in the preset data set, and the candidate faults are faults of preset function modules in the automatic driving vehicle;

and a second determining unit, configured to determine a target fault in candidate faults corresponding to the target exception, where the target fault is a fault occurring in the preset function module in the virtual simulation test process.

11. The apparatus of claim 10, wherein the candidate faults corresponding to the target anomaly include at least two first faults, and the second determining unit includes:

an obtaining subunit, configured to obtain a detection parameter set and a simulation parameter set, where the detection parameter set includes a detection attribute parameter for detecting, by the autonomous vehicle, a target object in the virtual simulation test process; the simulation parameter set comprises a true value attribute parameter of the target object in the virtual simulation test process; the target object includes at least one of: the autonomous vehicle and a driving environment object outside the autonomous vehicle;

a determining subunit, configured to determine the target fault among the at least two first faults based on the detection parameter set and the simulation parameter set.

12. The apparatus according to claim 11, wherein the determining subunit is specifically configured to determine, in case that the first attribute parameter does not match the second attribute parameter, that the first candidate fault is the target fault;

13. The apparatus according to claim 12, wherein the preset function module includes a sensing module and a positioning module, and the determining subunit is further configured to determine, based on a first matching condition, a matching state of the first attribute parameter and the second attribute parameter when the first candidate fault is a fault of the sensing module; determining a matching state of the first attribute parameter and the second attribute parameter based on a second matching condition if the first candidate fault is a fault of the positioning module;

14. The apparatus of claim 13, wherein the first matching condition comprises at least one of:

15. The apparatus of claim 13, wherein the second matching condition comprises at least one of:

and under the condition that the first candidate fault is a positioning jump fault of the automatic driving vehicle and the first position change parameter is not matched with the second position change parameter, determining that the first attribute parameter is not matched with the second attribute parameter, wherein the first position change parameter is a position change parameter detected by the automatic driving vehicle, the second position change parameter is a real position change parameter of the automatic driving vehicle, the first attribute parameter comprises the first position change parameter, the second attribute parameter comprises the real positioning parameter, and the positioning jump fault comprises a positioning jump fault and a course angle jump fault.

16. The apparatus according to claim 13, wherein the preset functional modules further include a map module, the candidate faults corresponding to the target anomaly further include at least two second faults, the second faults are faults of the map module, and the determining subunit is further configured to determine the target fault among the at least two second faults if it is determined that the first candidate fault is a fault of the module other than the sensing module and the positioning module based on the first matching condition and the second matching condition, and no fault exists in the module other than the map module.

17. The apparatus of claim 16, wherein the at least two second faults include a second candidate fault, the autonomous vehicle performs the virtual simulation test based on map information in the map module, and the determining subunit is further configured to determine that the second candidate fault is a target map element annotation fault if the second candidate fault is the target map element annotation fault and it is detected that there is an annotation fault for the target map element in the map information, and the target map element includes at least one of: speed limit signs, lane lines, traffic indicating lamps and lanes;

the determining subunit is specifically further configured to determine that the second candidate fault is the target fault when the second candidate fault is a binding relationship fault between map elements and it is detected that the binding relationship fault exists between the map elements in the map information, where the binding relationship includes at least one of: the binding relationship between different lanes, and the binding relationship between the traffic light and the lane.

18. The apparatus of any one of claims 10 to 17, wherein the preset anomaly comprises at least one of: collision, brake deceleration exceeding a preset deceleration, vehicle shaking amplitude exceeding a preset amplitude, exit from an automatic driving mode, reverse running and running a red light.

19. An electronic device, comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of fault detection for an autonomous vehicle of any of claims 1-9.

20. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the steps of the method of fault detection of an autonomous vehicle of any of claims 1-9.

21. A computer program product comprising a computer program which, when executed by a processor, carries out the steps of the method of fault detection of an autonomous vehicle of any of claims 1-9.