CN115805948B - Method and device for detecting abnormal running behavior of vehicle, electronic equipment and storage medium - Google Patents
Method and device for detecting abnormal running behavior of vehicle, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115805948B CN115805948B CN202211214403.7A CN202211214403A CN115805948B CN 115805948 B CN115805948 B CN 115805948B CN 202211214403 A CN202211214403 A CN 202211214403A CN 115805948 B CN115805948 B CN 115805948B
- Authority
- CN
- China
- Prior art keywords
- behavior
- abnormal
- vehicle
- preset
- detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 153
- 238000000034 method Methods 0.000 title claims abstract description 65
- 230000006399 behavior Effects 0.000 claims abstract description 272
- 238000001514 detection method Methods 0.000 claims abstract description 143
- 238000005259 measurement Methods 0.000 claims abstract description 33
- 230000008569 process Effects 0.000 claims abstract description 24
- 230000001133 acceleration Effects 0.000 claims description 93
- 238000012216 screening Methods 0.000 claims description 8
- 230000000903 blocking effect Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 abstract description 10
- 238000004590 computer program Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 206010000117 Abnormal behaviour Diseases 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- DMSMPAJRVJJAGA-UHFFFAOYSA-N benzo[d]isothiazol-3-one Chemical compound C1=CC=C2C(=O)NSC2=C1 DMSMPAJRVJJAGA-UHFFFAOYSA-N 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The disclosure provides a vehicle abnormal running behavior detection method, device, electronic equipment and storage medium, relates to the technical field of data processing, and particularly relates to the technical field of automatic driving. The specific implementation scheme comprises the following steps: acquiring detection index data corresponding to abnormal driving behaviors in the driving process of the automatic driving vehicle; determining whether the abnormal running behavior exists in the automatic driving vehicle according to the detection index data and a preset detection strategy corresponding to the abnormal running behavior; and if so, determining the measurement index data of the abnormal driving behavior. The method and the device can rapidly and accurately detect abnormal driving behaviors in the driving process of the automatic driving vehicle; and the abnormal driving behavior can be quantitatively analyzed.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to the field of automatic driving technologies, and in particular, to a method, an apparatus, an electronic device, a storage medium, and a computer program product for detecting abnormal driving behavior of a vehicle.
Background
With the rapid development of vehicle technology and electronic technology, autopilot automobiles are increasingly appearing in people's lives. The automatic driving automobile is also called an unmanned automobile, a computer driving automobile or a wheel type mobile robot, and is an intelligent automobile for realizing unmanned through a computer system. In the use process, the automatic driving automobile can autonomously and safely operate the automobile to normally run according to a preset running route without manual operation.
Disclosure of Invention
The present disclosure provides a vehicle abnormal running behavior detection method, apparatus, electronic device, storage medium, and computer program product.
According to an aspect of the present disclosure, there is provided a vehicle abnormal driving behavior detection method including:
acquiring detection index data corresponding to abnormal driving behaviors in the driving process of the automatic driving vehicle;
determining whether the automatic driving vehicle has abnormal driving behaviors or not according to the detection index data and a preset detection strategy corresponding to the abnormal driving behaviors;
if so, determining the measurement index data of the abnormal driving behavior.
According to an aspect of the present disclosure, there is provided a vehicle abnormal running behavior detection apparatus including:
The data acquisition module is used for acquiring detection index data corresponding to abnormal driving behaviors in the driving process of the automatic driving vehicle;
the detection module is used for determining whether the automatic driving vehicle has abnormal driving behaviors or not according to the detection index data and a preset detection strategy corresponding to the abnormal driving behaviors;
and the measurement module is used for determining measurement index data of the abnormal running behavior if the abnormal running behavior exists.
According to another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the vehicle abnormal driving behavior detection method of any embodiment of the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the vehicle abnormal running behavior detection method of any embodiment of the present disclosure.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the vehicle abnormal running behavior detection method of any embodiment of the present disclosure.
According to the technology disclosed by the invention, abnormal running behaviors in the running process of the automatic driving vehicle can be detected rapidly and accurately; and the abnormal driving behavior can be quantitatively analyzed.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
fig. 1 is a schematic flow chart of a method for detecting abnormal driving behavior of a vehicle according to an embodiment of the present disclosure;
FIG. 2a is a flow chart of yet another method for detecting abnormal driving behavior of a vehicle according to an embodiment of the present disclosure;
FIG. 2b is a schematic diagram of the movement of a vehicle relative to a planned path under the Frenet reference frame provided by an embodiment of the present disclosure;
FIG. 2c is a graph of lateral offset velocity versus time for a typical existing Tornado drive test data segment provided by an embodiment of the present disclosure;
FIG. 2d is a plot of the lateral offset velocity of a segment of normal drive test data over time provided by an embodiment of the present disclosure;
FIG. 2e is a graph of the lateral offset velocity maxima in a data set with sloshing or Dragon behavior problems provided by an embodiment of the present disclosure;
FIG. 2f is a graph of the lateral offset velocity maxima in a normal dataset provided by an embodiment of the present disclosure;
fig. 3 is a flowchart of still another method for detecting abnormal driving behavior of a vehicle according to an embodiment of the present disclosure;
FIG. 4 is a logic flow diagram of a method for detecting abnormal driving behavior of a vehicle provided by an embodiment of the present disclosure;
fig. 5 is a schematic structural view of a vehicle abnormal running behavior detection apparatus provided in an embodiment of the present disclosure;
fig. 6 is a block diagram of an electronic device for implementing a vehicle abnormal running behavior detection method according to an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one 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.
In this embodiment, during the running process of the autonomous vehicle, the course angle of the autonomous vehicle changes due to the rotation of the steering wheel, and at this time, due to the action of the centripetal force and the lateral force applied to the vehicle body, the passengers in the vehicle can sense the lateral movement of the autonomous vehicle, and the passengers feel the lateral body feeling. However, for various reasons, for example, in the case of abnormal system or unreasonable planning of the planning module, abnormal driving behavior of the autonomous vehicle may occur, and the abnormal driving behavior may affect not only the lateral stability of the vehicle, but also the lateral feeling of the vehicle may be abnormal, that is, the lateral comfort of the passengers may be affected. It is therefore necessary to evaluate the abnormal running behavior that may exist in real time during the running of the autonomous vehicle so that the autonomous system corrects the abnormal running behavior. In order to detect the abnormal driving behavior, the lateral body feeling of the vehicle in the automatic driving running state is optionally manually evaluated by a safety person (passenger), so as to further identify whether the vehicle has the abnormal driving behavior. However, this way of assessment is qualitative and the perception of lateral comfort by different security personnel (passengers) is different, and at the same time, a certain labor cost is required with this means. In another approach, the vehicle is evaluated for abnormal driving behavior by detecting a steering wheel angle or a change in heading angle of the vehicle in an autopilot running state. But this approach has some noise as an external signal due to the use of signals from the vehicle chassis (steering angle) or IMU (Inertial Measurement Unit, self inertial measurement unit) (heading angle); in addition, it is not easy to distinguish whether the change in the curvature of the lane in which the vehicle is located (e.g., a turn) or the change in the steering wheel rotation or heading angle is caused by an abnormal running of the vehicle during the detection. In another mode, the running track of the automatic driving vehicle is collected and is combined with a high-precision map or a sensing lane line to evaluate whether the abnormal running behavior of the vehicle exists or not, but the running track is required to be collected in advance for processing in the mode, so that the method is only suitable for offline playback, and real-time performance of online detection is difficult to meet in terms of calculation efficiency. Considering that the above methods for identifying abnormal driving behaviors have certain defects, the method for detecting the abnormal driving behaviors of the vehicle is provided, and the detection index and the detection strategy required for identifying each abnormal driving behavior are redetermined, so that the abnormal driving behaviors are identified, and meanwhile, the existing abnormal driving behaviors are quantitatively measured. The specific implementation flow of the disclosed scheme can be seen in the following examples.
Fig. 1 is a flowchart of a method for detecting abnormal driving behavior of a vehicle according to an embodiment of the present disclosure, where the embodiment may be applicable to detecting abnormal driving behavior existing during driving of an autonomous vehicle. The method may be performed by a vehicle abnormal driving behavior detection device implemented in software and/or hardware and integrated on an electronic device, for example in an autonomous vehicle.
Specifically, referring to fig. 1, the vehicle abnormal running behavior detection method is as follows:
s101, acquiring detection index data corresponding to abnormal driving behaviors in the driving process of the automatic driving vehicle.
In the present embodiment, the abnormal running behavior is optionally a running behavior affecting the lateral body feeling of the passenger. Alternatively, abnormal running behaviors occurring during running of the automatically driven vehicle may be classified into various types, for example, abnormal running behaviors including at least one of lateral acceleration overrun behavior, lateral shake behavior, and tukey behavior; the lateral acceleration overrun behavior refers to that the lateral acceleration is overlarge in the running process of the automatic driving vehicle; the lateral shaking behavior refers to the existence of lateral shaking in the running process of the automatic driving vehicle; the Dragon behavior refers to that an automatic driving vehicle swings back and forth on a road to advance. The detection index data corresponding to the lateral acceleration overrun behavior is the lateral acceleration of the automatic driving vehicle, and the detection index data corresponding to the lateral shaking behavior and the dragon drawing behavior is optionally the lateral offset speed or the yaw rate. When the detection index data corresponding to the abnormal driving behavior is obtained, the detection index data may be directly obtained from a related sensor or a related functional module, or may be obtained by calculation through a data operation mode, which is not particularly limited herein.
S102, determining whether the automatic driving vehicle has abnormal driving behaviors according to the detection index data and a preset detection strategy corresponding to the abnormal driving behaviors.
In this embodiment, each abnormal driving behavior corresponds to a preset detection policy, that is, different detection policies are adopted for different types of abnormal driving behaviors to perform abnormal detection. The preset detection strategy at least comprises a method or a judgment condition for judging whether abnormal running behaviors exist or not according to the detection index data. Therefore, after the detection index data corresponding to any abnormal driving behavior is obtained, the method or the judgment condition in the preset detection strategy can be directly called to determine whether the abnormal driving behavior exists in the automatic driving vehicle, and the rapid detection of the abnormal driving behavior is realized.
And S103, when the abnormal running behavior exists, determining measurement index data of the abnormal running behavior.
After determining that the automatic driving vehicle has abnormal driving behavior, metric index data of the abnormal driving behavior can be further determined, wherein the metric index data is index data for measuring the severity of the abnormal driving behavior, and therefore quantitative analysis of the abnormal driving behavior is achieved.
In the scheme, the abnormal running behavior is limited to at least one of the lateral acceleration overrun behavior, the lateral shaking behavior and the Dragon behavior, so that the abnormal running behavior affecting the lateral body feeling of the passenger can be comprehensively detected; each abnormal driving behavior corresponds to a preset detection strategy, and abnormal driving behaviors in the driving process of the automatic driving vehicle can be detected rapidly and accurately; meanwhile, the existing abnormal driving behavior can be quantitatively analyzed to determine the severity of the abnormal driving behavior.
Fig. 2a is a flow chart of yet another vehicle abnormal driving behavior detection method according to an embodiment of the present disclosure. In this embodiment, when the automatic driving vehicle travels in different scenes, the detection index data corresponding to the same abnormal traveling behavior may be different, for example, in a high-speed scene, the traveling speed of the automatic driving vehicle is greater than or equal to a preset speed threshold, and at this time, the detection index data corresponding to the lateral shake behavior and the picture-in-dragon behavior are lateral offset speeds. In the high speed domain scenario, the process of determining whether the automatic driving vehicle has lateral shake behavior or picture dragon behavior can be seen in fig. 2a.
S201, acquiring the current transverse offset speed of the automatic driving vehicle at the current moment and the historical transverse offset speed of the automatic driving vehicle within the preset time before the current moment in the running process of the automatic driving vehicle.
S202, taking the current transverse offset speed and the historical transverse offset speed as detection index data corresponding to transverse shaking behaviors or picture-dragon behaviors.
Since the lateral shaking behavior or the picture-in-the-dragon behavior is a motion process which lasts for a certain time, whether the lateral shaking behavior or the picture-in-the-dragon behavior exists or not needs to be determined, and the lateral offset speed of each time point within a certain time period needs to be obtained. When the method is realized, the current transverse offset speed at the current moment can be acquired firstly, then the historical transverse offset speed of the automatic driving vehicle in the preset time before the current moment is acquired, and further the current transverse offset speed and the historical transverse offset speed are used as detection index data corresponding to transverse shaking behaviors or picture-dragon behaviors. In another embodiment, a slidable time window with a certain duration may be predetermined, and during the running of the automatic driving vehicle, the time window automatically slides forward along the time axis, so only the lateral offset speed of each time point under the current time window needs to be determined, and the lateral offset speed of each time point is used as the detection index data corresponding to the lateral shaking behavior or the tuon behavior.
The reason why the lateral shift speed is selected as the detection index data of the picture-in-picture behavior or the lateral shake behavior is that the lateral shift speed is significantly increased when the picture-in-picture behavior or the lateral shake behavior occurs. The lateral offset speed in this embodiment may be obtained directly by measurement by a measurement device, or may be obtained by calculating a lateral offset distance of the autonomous vehicle with respect to the planned path, and performing a time derivative operation on the lateral offset distance.
In this embodiment, when deriving the lateral offset velocity, reference is made to FIG. 2b, which shows a schematic diagram of the motion of the vehicle relative to the planned path in the Frenet reference frame, and the coordinates of the vehicle rear axle center point vector in the geodetic coordinate system areWhere the arguments s and d are the coordinates of the point in the Frenet reference frame formed with the planned path, where d represents the lateral offset distance of the rear axle center relative to the planned path, and s is the distance of the vehicle from the path origin. />And->The normal vector and the tangential vector of the center point are respectively, wherein the direction of the tangential vector is the speed direction of the center of the rear axle of the vehicle, and the course angle is +.>The projection point vector of the center of the rear axle of the vehicle on the planned path is +. >The tangential vector and normal vector corresponding to the point are +.>Andthe corresponding course angle is +.>The vector of the center point of the rear axle of the vehicle can be expressed asThe sum of the projection point vector and the lateral offset vector can be expressed as:
the lateral offset distance can be expressed as:
normal vector of projection pointDenoted as->It is differentiated with time as:
wherein, kappa r The angular velocity of the proxel is indicated.
The lateral offset distance is derived over time to obtain a lateral offset speed of:
wherein, the normal vector of the projection pointAnd the tangential vector of the center point of the rear axle +.>Respectively denoted asAnd->
Thus, the lateral offset speed may be obtained by multiplying the running speed of the vehicle by the sine value of the heading angle of the vehicle relative to the planned path.
On the basis of the above, for the lateral offset speed of any time point, the current lateral offset speed can be determined according to the running speed of the automatic driving vehicle at the current time and the course angle of the automatic driving vehicle at the current time relative to the planned path, specifically, the sine value of the course angle of the automatic driving vehicle at the current time relative to the planned path is multiplied by the running speed of the current time point, and the product result is used as the lateral offset speed of the time point. Therefore, the transverse offset speed of each time point can be rapidly and accurately determined, and the acquisition efficiency of the detection index data corresponding to the transverse offset behavior or the picture-dragon behavior is further ensured.
In this embodiment, to determine whether there is a picture-in-dragon behavior or a lateral shake behavior, a preset detection policy of the two abnormal behaviors in a high-speed domain scene needs to be predetermined. Alternatively, the preset detection policy may be determined by offline statistics. Specifically, a problem scene that the vehicle generates lateral shaking/Dragon behavior in an automatic driving state is screened from the road test problem, a positive sample set is formed, one sample in the positive sample set is arbitrarily taken, and the change of the lateral offset speed with time is calculated, as shown in fig. 2c, wherein the sampling frequency of the lateral offset speed is 10Hz, and it is known that significant fluctuation exists in the Dragon behavior generation stage (the direction stipulates that the vehicle is positive on the left side of a planned path and negative on the right side). A sample of the negative samples (normal samples) was taken for analysis, having a length of 500 seconds or more, to obtain a lateral offset velocity as shown in fig. 2d, in which the horizontal axis represents time and the vertical axis represents lateral offset velocity in m/s. It can be seen that the lateral offset speed in normal conditions without lateral shaking or Dragon behavior is substantially in the range of-0.22 to 0.22 m/s.
Based on the above analysis, the distribution at the lateral offset velocity maximum was counted from the lateral sloshing/churn behavior positive sample set (about 114 problem fragments) and the negative sample set (about 100 fragments), respectively. As shown in fig. 2e below, the horizontal axis represents the serial number of the sample, the vertical axis represents the lateral offset velocity, and it can be seen that the lateral offset velocity distribution of the positive sample of the scotch behavior is almost all located on the upper and lower sides of the upper and lower dividing lines, while in the negative sample (fig. 2 f), it is located substantially inside the upper and lower dividing lines, so that it can be significantly determined whether the automatic driving vehicle is sloshing/dragons with the lateral offset velocity. Thus, the determined preset detection strategy includes a lateral offset speed interval (e.g., -0.22-0.22) when no abnormal running behavior exists, and the specific detection strategy is that the lateral offset speed is not within the lateral offset speed interval, and specifically can be expressed by the following expression:
Wherein delta v0 Equal to 0.22./>And->Respectively representing the peaks and valleys of the lateral offset velocity. Therefore, whether the dragon drawing behavior or the transverse shaking behavior of the vehicle in the high-speed domain can be rapidly and accurately determined through the preset detection strategy.
Based on the above, the process of determining whether the autonomous vehicle has abnormal driving behavior according to the detection index data and the preset detection strategy corresponding to the abnormal driving behavior may refer to steps S203 to S205.
S203, determining the peak value and the valley value of the transverse offset speed from the historical transverse offset speed and the current transverse offset speed.
S204, judging whether the peak value and the valley value of the transverse offset speed meet a preset detection strategy or not; the preset detection strategy comprises a transverse deviation speed interval when no abnormal running behavior exists.
That is, judging whether the peak value and the valley value of the lateral shift speed are satisfiedThis condition.
S205, under the condition that a preset detection strategy is met, determining that the automatic driving vehicle has lateral shaking behavior or picture dragon behavior.
S206, determining measurement index data of the transverse shaking behavior or the picture dragon behavior.
In this embodiment, the swing intensity and the swing number are introduced as the measurement index of the lateral swing or the dragon drawing behavior in the high-speed domain, and the specific process of determining the swing number is as follows: determining the swinging times according to the peak value and the valley value of the transverse offset speed; wherein, every time a peak value and a valley value appear, the swing is considered to be once; the more the number of swings, the more serious the behavior of the automatic driving vehicle is in a dragon drawing or a lateral shaking.
The procedure for determining the pre-swing intensity is as follows: determining a maximum lateral offset speed according to the peak value and the valley value of the lateral offset speed, for example, taking the value with the largest absolute value in the peak value and the valley value as the maximum lateral offset speed; calculating the swing strength according to the maximum transverse offset speed, the preset upper threshold limit and the preset lower threshold limit of the transverse offset speed; wherein the value range of the swing intensity is between 0 and 1. Illustratively, the swing strength Sa is calculated according to the following formula:
wherein, |v d I is the determined maximum lateral offset velocity; delta v1 The upper threshold value representing the setting of the lateral offset speed is generally obtained by counting the maximum values of all lateral offset speeds, delta, in a lateral sloshing or Dragon behavior data set in a high-speed domain v0 The lower threshold, which represents a set threshold, is a calibrated value for distinguishing whether sloshing or dragons are occurring, typically obtained by counting the lateral offset speeds in the high-speed domain sloshing or dragons dataset and in the normal dataset, for example, the value is 0.22 in the high-speed domain.
And taking the swinging times and swinging intensity as measurement index data corresponding to the transverse swinging behavior and the dragon drawing behavior.
In the embodiment, whether the dragon drawing behavior or the transverse shaking behavior of the vehicle in the high-speed domain can be rapidly and accurately determined through the preset detection strategy; and the purpose of quantitatively analyzing abnormal driving behaviors is realized by taking the swinging times and the swinging intensity as measurement index data.
In the embodiment of the disclosure, for an automatic driving vehicle running in a city or suburb, the vehicle speed is generally lower than 80km/h, when the vehicle speed is lower, the problem of missing detection and false detection exists when the lateral deviation speed index is adopted for carrying out the picture dragon or lateral shaking judgment, and the missing detection is that the smaller the vehicle speed is, the smaller the lateral deviation speed is, and therefore the detection threshold value needs to be adjusted. When the detection threshold is reduced, the automatic driving road condition of the urban area is generally more complex than that of the high-speed area, and more curves and turning scenes are included, so that some false detection is probably caused. Therefore, in the low-speed domain, it is necessary to newly determine the detection index of the picture-in-dragon behavior or the lateral shake behavior. The applicant found that when the vehicle is subjected to a scotch or a lateral sway, the yaw rate of the vehicle is significantly changed, and the yaw rate is also significantly changed during normal turning and turning of the vehicle, so that the yaw rate can be used for measuring the swing degree of the vehicle. In order to distinguish whether the vehicle is in abnormal dragon-drawing behavior or normal turning, lane changing and turning, yaw rate is limited, yaw rate acceleration is introduced, namely yaw rate and yaw rate acceleration are used as detection index data corresponding to the horizontal shaking behavior and the dragon-drawing behavior in a low speed zone (the running speed of the automatic driving vehicle is smaller than a preset speed threshold). On this basis, the specific implementation process of the vehicle abnormal behavior detection method in the low speed domain can be seen in the following embodiments.
Fig. 3 is a flowchart of still another vehicle abnormal driving behavior detection method according to an embodiment of the present disclosure. The method and the device are suitable for determining abnormal driving behaviors existing in the driving process of the vehicle in the low-speed-range scene. Referring to fig. 3, the vehicle abnormal running behavior detection method is specifically as follows:
s301, acquiring detection index data corresponding to abnormal driving behaviors in the driving process of the automatic driving vehicle.
In this embodiment, when the detection index data is acquired, the yaw rate and the yaw acceleration at different time points under the current time outlet are determined first. The yaw rate can be obtained from a positioning module of the vehicle, and the yaw rate is obtained by performing time difference and first-order Butterworth filtering on the yaw rate. Further, the peak value and the valley value of the yaw rate and the peak value and the valley value of the yaw rate acceleration are used as detection index data.
After obtaining the detection index data, determining whether the automatic driving vehicle has abnormal driving behavior according to the preset detection strategy corresponding to the abnormal driving behavior of the detection index data may refer to step S302, which includes:
s302, if the yaw rate and the yaw acceleration meet target screening conditions included in a preset detection strategy, determining that abnormal running behaviors exist in the automatic driving vehicle.
Wherein, the target screening conditions include: (1) The magnitude difference between the peak and valley of the yaw rate is smaller than the preset angular rate threshold, for example, the bar can be expressed by the following formula:wherein w is min Is the yaw rate valley value, w max For yaw rate peak, r a Is a preset threshold. (2) The time difference between the peak occurrence time of the yaw angle and the valley occurrence time of the yaw rate is smaller than a preset time threshold. (3) The yaw acceleration is outside the preset yaw acceleration interval, and this bar can be expressed by the following formula, for example: max (|α) min |,|α max |)>δ α0 The method comprises the steps of carrying out a first treatment on the surface of the Wherein alpha is min Is the yaw acceleration valley value alpha max For yaw acceleration peak, delta α0 Is a lower limit of a preset yaw acceleration threshold.
It should be noted that, condition 1 is to filter normal turning or turning around of the vehicle, condition 2 is to filter that the vehicle is in a scene of normal borrowing, changing track, etc., and condition 3 is to measure whether the swing of the vehicle reaches a perceptible degree. Therefore, only if the three screening conditions are met, the existence of the dragon drawing behavior or the transverse shaking behavior can be accurately determined.
Furthermore, in order to further ensure the accuracy of detecting abnormal driving behaviors (Dragon behaviors or transverse shaking behaviors) in a low-speed region, the driving scene of the automatic driving vehicle can be judged. For example, determining a current driving scene in which the automatic driving vehicle is located, and judging whether the current driving scene belongs to a target driving scene; the target driving scene comprises a scene that an automatic driving vehicle passes through a bifurcation or convergence lane, a scene that the automatic driving vehicle changes lanes immediately after turning, and a scene that the automatic driving vehicle encounters blocking and detouring; if the driving behavior does not belong to the target driving scene, determining that the automatic driving vehicle has abnormal driving behavior, namely, has a Dragon behavior or a lateral shaking behavior. It should be noted that, according to the planned path of the vehicle and the attribute of the lane where the vehicle is located obtained from the high-precision map, for example, the lane type, the curvature of the center line of the lane, and the like, it is determined whether the current driving scene is a bifurcation or convergence lane scene or a scene that changes lanes immediately after turning. Whether the current driving scene is a scene encountering a blocking detour or not can be judged by acquiring the main vehicle perceived blocking state and the decision state.
And S303, under the condition that abnormal driving behaviors exist, determining measurement index data of transverse shaking behaviors or dragon drawing behaviors in a low-speed domain.
In this embodiment, the swing strength and the swing times are introduced as measurement indexes for measuring the lateral swing or the dragon drawing behavior in the low-speed domain, and specifically, the swing times are determined as follows: determining the swing times according to the peak value and the valley value of the yaw rate; wherein, every time a peak value and a valley value appear, the swing is considered to be once; the more the number of swings, the more serious the behavior of the automatic driving vehicle is in a dragon drawing or a lateral shaking.
The procedure for determining the pre-swing intensity is as follows: determining a maximum yaw acceleration from the peak value and the valley value of the yaw acceleration, for example, taking the value with the largest absolute value in the peak value and the valley value as the maximum yaw acceleration; calculating swing strength according to the maximum yaw acceleration, a preset upper threshold limit and a preset lower threshold limit of the yaw acceleration; wherein the value range of the swing intensity is between 0 and 1. Illustratively, the swing strength Sa is calculated according to the following formula:
wherein delta α1 The upper threshold limit set for yaw acceleration is generally obtained by counting all yaw acceleration maxima in the urban (i.e., low-speed) lateral sloshing/cyclostyle dataset, δ α0 And setting a threshold lower limit for the yaw angular acceleration, and obtaining the yaw angular acceleration calibration by counting the lateral shaking/drawing behavior data set and the normal data set of the urban area.
And taking the swinging times and the swinging strength as measurement index data corresponding to the transverse swinging behaviors and the Dragon behaviors in the low-speed domain.
In the embodiment, through presetting the target screening conditions in the detection strategy, whether the vehicle has a picture-dragon behavior or a transverse shaking behavior in a low-speed domain can be rapidly and accurately determined; and the purpose of quantitatively analyzing abnormal driving behaviors is realized by taking the swinging times and the swinging intensity as measurement index data.
Fig. 4 is a logic flow diagram of a vehicle abnormal running behavior detection method according to an embodiment of the present disclosure. Referring to fig. 4, the vehicle abnormal running behavior detection method is as follows:
s401, acquiring detection index data corresponding to abnormal driving behaviors in the driving process of the automatic driving vehicle.
In this embodiment, the abnormal running behavior to be focused is a lateral acceleration overrun behavior, and the detection index data corresponding to the lateral acceleration overrun behavior is the detected lateral acceleration of the automatic driving vehicle; whereas the lateral acceleration of the autonomous vehicle may be obtained from a positioning module of the vehicle. It should be noted that the acquisition is performed in the positioning module, not directly in the self-inertial measurement unit (Inertial Measurement Unit, IMU for short), because if the acquisition is performed directly from the IMU, noise is present in the obtained data; in contrast, the positioning module performs filtering processing on the lateral acceleration containing noise, so that the lateral acceleration acquired from the positioning module does not contain noise; thereby ensuring the accuracy of subsequent abnormality detection.
S402, judging whether the detected transverse acceleration of the automatic driving vehicle is in a preset transverse acceleration section.
In this embodiment, the detection policy for detecting whether the lateral acceleration exceeds the limit includes a preset lateral acceleration interval, where the lower limit of the preset lateral acceleration interval is determined according to the current scene of the automatic driving vehicle and the lateral acceleration threshold values of different pre-calibrated scenes, for example, the lateral acceleration calibration may be performed in advance according to different vehicle speeds of different scenes, so as to obtain a lateral acceleration threshold calibration table, and further determine the lower limit of the lateral acceleration interval according to the current scene of the vehicle and the road curvature radius under the scene; the upper limit of the preset lateral acceleration section is determined based on the detection history data of the lateral acceleration, for example, the maximum lateral acceleration in the history detection data is set as the upper limit.
And S403, if the transverse acceleration is in the preset transverse acceleration interval, determining that the transverse acceleration overrun behavior exists in the automatic driving vehicle.
S404, determining measurement index data of the lateral acceleration overrun behavior.
Optionally, the overrun intensity is calculated according to the detected lateral acceleration of the automatic driving vehicle and the lower limit and the upper limit of the preset lateral acceleration interval, and the overrun intensity is used as the measurement index data of the abnormal driving behavior. For example, the overrun strength s may be determined according to the following formula a ：
Wherein a is y For the acquired lateral acceleration; t is t a For presetting the lower limit of the transverse acceleration interval, t a,max The upper limit of the lateral acceleration interval is preset.
In the embodiment, whether the lateral acceleration overrun behavior exists or not can be timely detected, so that the lateral comfort of the vehicle is further obtained; the severity of lateral acceleration overrun is analyzed by quantification of overrun intensity.
Fig. 5 is a schematic structural diagram of a vehicle abnormal running behavior detection apparatus according to an embodiment of the present disclosure, which is applicable to a case of detecting abnormal running behavior existing during running of an autonomous vehicle. Referring to fig. 5, the apparatus includes:
the data acquisition module 501 is configured to acquire detection index data corresponding to abnormal driving behavior during a driving process of the autonomous vehicle;
the detection module 502 is configured to determine whether an abnormal driving behavior exists in the automatic driving vehicle according to the detection index data and a preset detection policy corresponding to the abnormal driving behavior;
the measurement module 503 is configured to determine measurement index data of the abnormal driving behavior if the abnormal driving behavior exists.
On the basis of the above-described embodiment, optionally, the abnormal running behavior includes at least one of a lateral acceleration overrun behavior, a lateral shake behavior, and a picture-dragon behavior.
On the basis of the above embodiment, optionally, if the running speed of the automatic driving vehicle is greater than or equal to the preset speed threshold, the detection index data corresponding to the lateral shake behavior and the picture-in-dragon behavior is the lateral offset speed.
On the basis of the above embodiment, optionally, the data acquisition module includes:
the first acquisition unit is used for acquiring the current transverse offset speed of the automatic driving vehicle at the current moment and the historical transverse offset speed of the automatic driving vehicle within the preset time before the current moment;
the second acquisition unit is used for taking the current transverse offset speed and the historical transverse offset speed as detection index data corresponding to the transverse shaking behavior and the picture-dragon behavior.
On the basis of the above embodiment, optionally, the first obtaining unit is further configured to:
and determining the current transverse offset speed according to the running speed of the automatic driving vehicle at the current moment and the course angle of the automatic driving vehicle relative to the planned path at the current moment.
On the basis of the above embodiment, optionally, the detection module is further configured to include:
determining the peak value and the valley value of the transverse offset speed from the historical transverse offset speed and the current transverse offset speed;
Judging whether the peak value and the valley value of the transverse offset speed meet a preset detection strategy or not; the method comprises the steps that a preset detection strategy comprises a transverse offset speed interval when no abnormal running behavior exists;
if yes, determining that the automatic driving vehicle has lateral shaking behaviors and dragon drawing behaviors.
Based on the above embodiment, optionally, the metric module is further configured to:
determining the swinging times according to the peak value and the valley value of the transverse offset speed; wherein, every time a peak value and a valley value appear, the swing is considered to be once;
determining the maximum transverse offset speed according to the peak value and the valley value of the transverse offset speed;
calculating the swing strength according to the maximum transverse offset speed, the preset upper threshold limit and the preset lower threshold limit of the transverse offset speed;
and taking the swinging times and swinging intensity as measurement index data corresponding to the transverse swinging behavior and the dragon drawing behavior.
On the basis of the above embodiment, optionally, if the running speed of the autonomous vehicle is less than the preset speed threshold, the detection index data corresponding to the lateral shake behavior and the picture-in-dragon behavior are yaw rate and yaw rate acceleration.
On the basis of the above embodiment, optionally, the detection module is further configured to:
If the yaw rate and the yaw acceleration meet target screening conditions included in a preset detection strategy, determining that the automatic driving vehicle has abnormal driving behaviors;
wherein, the target screening conditions include: the amplitude difference between the peak value and the valley value of the yaw rate is smaller than a preset angular rate threshold value;
the time difference between the peak occurrence time of the yaw angle and the valley occurrence time of the yaw rate is less than a preset time threshold;
the yaw angular acceleration is outside the preset yaw angular acceleration interval.
On the basis of the above embodiment, optionally, the method further includes a scene verification module, configured to:
determining a current running scene of the automatic driving vehicle, and judging whether the current running scene belongs to a target running scene or not; the target driving scene comprises a scene that an automatic driving vehicle passes through a bifurcation or convergence lane, a scene that the automatic driving vehicle changes lanes immediately after turning, and a scene that the automatic driving vehicle encounters blocking and detouring;
if the driving situation does not belong to the target driving scene, determining that the automatic driving vehicle has abnormal driving behaviors.
Based on the above embodiment, optionally, the metric module is further configured to:
determining the swing times according to the peak value and the valley value of the yaw rate; wherein, every time a peak value and a valley value appear, the swing is considered to be once;
Determining a maximum yaw acceleration according to the peak value and the valley value of the yaw acceleration;
calculating swing strength according to the maximum yaw acceleration, a preset upper threshold limit and a preset lower threshold limit of the yaw velocity;
and taking the swinging times and swinging intensity as measurement index data corresponding to the transverse swinging behavior and the dragon drawing behavior.
On the basis of the above embodiment, optionally, the detection index data corresponding to the lateral acceleration overrun behavior is the detected lateral acceleration of the automatically driven vehicle;
the detection module is also used for:
judging whether the detected lateral acceleration of the automatic driving vehicle is in a preset lateral acceleration interval; the lower limit of the preset transverse acceleration interval is determined according to the current scene of the automatic driving vehicle and transverse acceleration thresholds of different pre-calibrated scenes; the upper limit of the preset transverse acceleration interval is determined according to the detection historical data of the transverse acceleration;
if yes, determining that the automatic driving vehicle has the lateral acceleration overrun behavior.
Based on the above embodiment, optionally, the metric module is further configured to:
and calculating out the out-of-limit strength according to the detected transverse acceleration of the automatic driving vehicle and the lower limit and the upper limit of a preset transverse acceleration interval, and taking the out-of-limit strength as measurement index data of abnormal driving behaviors.
The vehicle abnormal running behavior detection device provided by the embodiment of the disclosure can execute the vehicle abnormal running behavior detection method provided by any embodiment of the disclosure, and has the corresponding functional modules and beneficial effects of the execution method. Reference is made to the description of any method embodiment of the disclosure for details not explicitly described in this embodiment.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 6 illustrates a schematic block diagram of an example electronic device 600 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 telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the apparatus 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data required for the operation of the device 600 may also be stored. The computing unit 601, ROM602, and RAM603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Various components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, mouse, etc.; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The calculation unit 601 performs the respective methods and processes described above, such as a vehicle abnormal running behavior detection method. For example, in some embodiments, the vehicle abnormal driving behavior detection method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM602 and/or the communication unit 609. When the computer program is loaded into the RAM603 and executed by the computing unit 601, one or more steps of the vehicle abnormal running behavior detection method described above may be executed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the vehicle abnormal driving behavior detection method by any other suitable means (e.g. by means of firmware).
Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code 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 code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. 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. The 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 portable 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 pointing device (e.g., a mouse or 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 may 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 input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background 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 background, 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 a client and a server. The client and server are typically 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 incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (20)
1. A vehicle abnormal running behavior detection method, comprising:
acquiring detection index data corresponding to abnormal driving behaviors in the driving process of the automatic driving vehicle;
determining whether the abnormal running behavior exists in the automatic driving vehicle according to the detection index data and a preset detection strategy corresponding to the abnormal running behavior; the abnormal running behaviors refer to lateral acceleration overrun behaviors, lateral shaking behaviors or Dragon behaviors, and different abnormal running behaviors correspond to different detection index data and different preset detection strategies;
And if so, determining the measurement index data of the abnormal driving behavior.
2. The method of claim 1, wherein the detection index data corresponding to the lateral sway behavior and the picture-in-dragon behavior is a lateral offset speed if the running speed of the autonomous vehicle is greater than or equal to a preset speed threshold.
3. The method of claim 2, wherein obtaining detection index data for abnormal driving behavior from the correspondence comprises:
acquiring the current transverse offset speed of the automatic driving vehicle at the current moment and the historical transverse offset speed of the automatic driving vehicle within the preset time before the current moment;
and taking the current transverse offset speed and the historical transverse offset speed as detection index data corresponding to the transverse shaking behavior and the Dragon behavior.
4. A method according to claim 3, wherein obtaining a current lateral offset speed of the autonomous vehicle at a current time comprises:
and determining the current transverse offset speed according to the running speed of the automatic driving vehicle at the current moment and the course angle of the automatic driving vehicle relative to a planned path at the current moment.
5. The method of claim 3, wherein determining whether the autonomous vehicle has the abnormal driving behavior according to the detection index data and a preset detection policy corresponding to the abnormal driving behavior comprises:
determining the peak value and the valley value of the transverse offset speed from the historical transverse offset speed and the current transverse offset speed;
judging whether the peak value and the valley value of the transverse offset speed meet the preset detection strategy or not; the preset detection strategy comprises a transverse offset speed interval when no abnormal running behavior exists;
if yes, determining that the automatic driving vehicle has the lateral shaking behavior and the dragon drawing behavior.
6. The method of claim 5, wherein determining metric data of the abnormal driving behavior comprises:
determining the swinging times according to the peak value and the valley value of the transverse offset speed; wherein, every time a peak value and a valley value appear, the swing is considered to be once;
determining a maximum transverse offset speed according to the peak value and the valley value of the transverse offset speed;
calculating the swing strength according to the maximum transverse offset speed, a preset upper threshold limit and a preset lower threshold limit of the transverse offset speed;
And taking the swinging times and the swinging strength as measurement index data corresponding to the transverse swinging behaviors and the dragon drawing behaviors.
7. The method according to claim 1, wherein if the running speed of the autonomous vehicle is less than a preset speed threshold, the detection index data corresponding to the lateral shake behavior and the picture-in-picture behavior are yaw rate and yaw acceleration.
8. The method of claim 7, wherein determining whether the autonomous vehicle has the abnormal driving behavior according to the detection index data and a preset detection policy corresponding to the abnormal driving behavior comprises:
if the yaw rate and the yaw acceleration meet target screening conditions included in a preset detection strategy, determining that abnormal running behaviors exist in the automatic driving vehicle;
wherein the target screening conditions include: the amplitude difference between the peak value and the valley value of the yaw rate is smaller than a preset angular rate threshold value;
the time difference between the peak value occurrence time of the yaw rate and the valley value occurrence time of the yaw rate is smaller than a preset time threshold;
the yaw acceleration is outside a preset yaw acceleration interval.
9. The method of claim 7, further comprising:
determining a current running scene of the automatic driving vehicle, and judging whether the current running scene belongs to a target running scene or not; the target driving scene comprises a scene that an automatic driving vehicle passes through a bifurcation or convergence lane, a scene that the automatic driving vehicle changes lanes immediately after turning, and a scene that the automatic driving vehicle encounters a blocking detour;
and if the driving situation does not belong to the target driving scene, determining that the automatic driving vehicle has abnormal driving behaviors.
10. The method of claim 7, wherein determining metric data of the abnormal driving behavior comprises:
determining the swing times according to the peak value and the valley value of the yaw rate; wherein, every time a peak value and a valley value appear, the swing is considered to be once;
determining a maximum yaw acceleration according to the peak value and the valley value of the yaw acceleration;
calculating swing strength according to the maximum yaw acceleration, a preset upper threshold limit and a preset lower threshold limit of the yaw velocity;
and taking the swinging times and the swinging strength as measurement index data corresponding to the transverse swinging behaviors and the dragon drawing behaviors.
11. The method according to claim 1, wherein the detection index data corresponding to the lateral acceleration overrun behavior is a detected lateral acceleration of the automatically driven vehicle;
determining whether the abnormal driving behavior exists in the automatic driving vehicle according to the detection index data and a preset detection strategy corresponding to the abnormal driving behavior comprises the following steps:
judging whether the detected transverse acceleration of the automatic driving vehicle is in a preset transverse acceleration interval or not; the lower limit of the preset lateral acceleration interval is determined according to the current scene of the automatic driving vehicle and the lateral acceleration threshold value of different pre-calibrated scenes; the upper limit of the preset transverse acceleration interval is determined according to the detection historical data of the transverse acceleration;
if yes, determining that the automatic driving vehicle has the lateral acceleration overrun behavior.
12. The method of claim 11, wherein determining metric data of the abnormal driving behavior comprises:
and calculating out the out-of-limit strength according to the detected transverse acceleration of the automatic driving vehicle and the lower limit and the upper limit of the preset transverse acceleration interval, and taking the out-of-limit strength as the measurement index data of the abnormal driving behavior.
13. An abnormal running behavior detection device of a vehicle, comprising:
the data acquisition module is used for acquiring detection index data corresponding to abnormal driving behaviors in the driving process of the automatic driving vehicle;
the detection module is used for determining whether the automatic driving vehicle has the abnormal driving behavior or not according to the detection index data and a preset detection strategy corresponding to the abnormal driving behavior; the abnormal running behaviors refer to lateral acceleration overrun behaviors, lateral shaking behaviors or Dragon behaviors, and different abnormal running behaviors correspond to different detection index data and different preset detection strategies;
and the measurement module is used for determining measurement index data of the abnormal running behavior if the abnormal running behavior exists.
14. The apparatus of claim 13, wherein the detection index data corresponding to the lateral sway behavior and the picture-in-dragon behavior is a lateral offset speed if the travel speed of the autonomous vehicle is greater than or equal to a preset speed threshold.
15. The apparatus of claim 14, wherein the data acquisition module comprises:
a first obtaining unit, configured to obtain a current lateral offset speed of the autonomous vehicle at a current time, and a historical lateral offset speed of the autonomous vehicle within a preset duration before the current time;
The second acquisition unit is used for taking the current transverse offset speed and the historical transverse offset speed as detection index data corresponding to the transverse shaking behavior and the Dragon behavior.
16. The apparatus of claim 15, wherein the first acquisition unit is further configured to:
and determining the current transverse offset speed according to the running speed of the automatic driving vehicle at the current moment and the course angle of the automatic driving vehicle relative to a planned path at the current moment.
17. The apparatus of claim 15, wherein the detection module is further configured to include:
determining the peak value and the valley value of the transverse offset speed from the historical transverse offset speed and the current transverse offset speed;
judging whether the peak value and the valley value of the transverse offset speed meet the preset detection strategy or not; the preset detection strategy comprises a transverse offset speed interval when no abnormal running behavior exists;
if yes, determining that the automatic driving vehicle has the lateral shaking behavior and the dragon drawing behavior.
18. The apparatus of claim 17, wherein the metrics module is further to:
determining the swinging times according to the peak value and the valley value of the transverse offset speed; wherein, every time a peak value and a valley value appear, the swing is considered to be once;
Determining a maximum transverse offset speed according to the peak value and the valley value of the transverse offset speed;
calculating the swing strength according to the maximum transverse offset speed, a preset upper threshold limit and a preset lower threshold limit of the transverse offset speed;
and taking the swinging times and the swinging strength as measurement index data corresponding to the transverse swinging behaviors and the dragon drawing behaviors.
19. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the vehicle abnormal driving behavior detection method according to any one of claims 1 to 12.
20. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the vehicle abnormal running behavior detection method according to any one of claims 1 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211214403.7A CN115805948B (en) | 2022-09-30 | 2022-09-30 | Method and device for detecting abnormal running behavior of vehicle, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211214403.7A CN115805948B (en) | 2022-09-30 | 2022-09-30 | Method and device for detecting abnormal running behavior of vehicle, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115805948A CN115805948A (en) | 2023-03-17 |
| CN115805948B true CN115805948B (en) | 2023-10-31 |
Family
ID=85482713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211214403.7A Active CN115805948B (en) | 2022-09-30 | 2022-09-30 | Method and device for detecting abnormal running behavior of vehicle, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115805948B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106853830A (en) * | 2016-06-24 | 2017-06-16 | 乐视控股（北京）有限公司 | Abnormal driving Activity recognition method, device and terminal device |
| CN109242251A (en) * | 2018-08-03 | 2019-01-18 | 百度在线网络技术（北京）有限公司 | Vehicular behavior safety detecting method, device, equipment and storage medium |
| CN110942671A (en) * | 2019-12-04 | 2020-03-31 | 北京京东乾石科技有限公司 | Vehicle dangerous driving detection method and device and storage medium |
| CN112512890A (en) * | 2020-04-02 | 2021-03-16 | 华为技术有限公司 | Abnormal driving behavior recognition method |
| CN114644000A (en) * | 2022-03-14 | 2022-06-21 | 阿波罗智能技术(北京)有限公司 | Detection method, device and equipment for dragon drawing behavior of automatic driving vehicle and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6338614B2 (en) * | 2016-04-27 | 2018-06-06 | 株式会社Ｓｕｂａｒｕ | Vehicle travel control device |
-
2022
- 2022-09-30 CN CN202211214403.7A patent/CN115805948B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106853830A (en) * | 2016-06-24 | 2017-06-16 | 乐视控股（北京）有限公司 | Abnormal driving Activity recognition method, device and terminal device |
| CN109242251A (en) * | 2018-08-03 | 2019-01-18 | 百度在线网络技术（北京）有限公司 | Vehicular behavior safety detecting method, device, equipment and storage medium |
| CN110942671A (en) * | 2019-12-04 | 2020-03-31 | 北京京东乾石科技有限公司 | Vehicle dangerous driving detection method and device and storage medium |
| CN112512890A (en) * | 2020-04-02 | 2021-03-16 | 华为技术有限公司 | Abnormal driving behavior recognition method |
| CN114644000A (en) * | 2022-03-14 | 2022-06-21 | 阿波罗智能技术(北京)有限公司 | Detection method, device and equipment for dragon drawing behavior of automatic driving vehicle and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115805948A (en) | 2023-03-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113734201B (en) | Vehicle redundancy control method, device, electronic equipment and medium | |
| CN112526999A (en) | Speed planning method, device, electronic equipment and storage medium | |
| CN114643994A (en) | Vehicle transverse anomaly detection method, device, equipment and medium | |
| CN113978465A (en) | Lane-changing track planning method, device, equipment and storage medium | |
| CN116295496A (en) | Automatic driving vehicle path planning method, device, equipment and medium | |
| CN115805948B (en) | Method and device for detecting abnormal running behavior of vehicle, electronic equipment and storage medium | |
| CN116957344B (en) | Safety evaluation method, device, equipment and medium for automatic emergency braking system | |
| CN117912295A (en) | Vehicle data processing method and device, electronic equipment and storage medium | |
| CN115959154A (en) | Method and device for generating lane change track and storage medium | |
| CN115909813B (en) | Vehicle collision early warning method, device, equipment and storage medium | |
| CN114715166B (en) | Vehicle control method, device, equipment, automatic driving vehicle and storage medium | |
| JP4788590B2 (en) | Vehicle rollover risk determination device | |
| CN115214722A (en) | Automatic driving method, device, electronic equipment, storage medium and vehicle | |
| CN115991195A (en) | Automatic detection and compensation method, device and system for wheel slip in automatic driving | |
| CN113753076B (en) | Method and device for judging effective obstacle, electronic equipment and automatic driving vehicle | |
| CN112937605B (en) | Unmanned vehicle driving data determination method and device, unmanned vehicle and storage medium | |
| CN114954532A (en) | Lane line determination method, device, equipment and storage medium | |
| CN114771555A (en) | Autonomous parking fault diagnosis method and device and unmanned vehicle | |
| KR102277479B1 (en) | Apparatus and method for estimating radius of curvature in vehicle | |
| US20230294669A1 (en) | Control method, vehicle, and storage medium | |
| CN114852173B (en) | Automatic steering control method, apparatus, and computer-readable storage medium | |
| CN114889652A (en) | Obstacle screening method, device, equipment and storage medium | |
| CN118597139A (en) | Vehicle control method, device, equipment and storage medium for ponding pavement | |
| CN115861965A (en) | Obstacle misdetection recognition method and device, electronic device and medium | |
| Bao et al. | A Particle Filter Approach for Identifying Tyre Model Parameters From Full-Scale Experimental Tests |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |