Detection method and device for abnormal swinging behavior of unmanned vehicle and automatic driving vehicle

Abstract

The present disclosure provides a detection method, device and autonomous driving vehicle for abnormal swinging behavior of an unmanned vehicle, and relates to the field of data processing, and in particular to the field of autonomous driving. The specific implementation scheme is: obtain the current target orientation angle of the unmanned vehicle, determine the target index according to the preset index mapping algorithm, determine the target center orientation angle based on the current target orientation angle and the target index corresponding to the target historical orientation angle, each index is used to record the orientation angle corresponding to the index at the acquisition moment, and any two acquisition moments separated by an integer number of preset cycles correspond to the same index. If the current target orientation angle, the target historical orientation angle and the target center orientation angle meet the preset conditions, it is determined that the unmanned vehicle has abnormal swinging behavior. By determining whether the unmanned vehicle's orientation angle meets the preset conditions, it is determined whether the unmanned vehicle has abnormal swinging behavior, and the detection of abnormal swinging behavior of the unmanned vehicle is realized. At the same time, the number of indexes recording the orientation angle is much smaller than the number of acquisition moments, which greatly reduces the amount of data processing.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to the field of autonomous driving technology. Background Art

[0002] During the autonomous driving process, due to abnormalities in the unmanned vehicle system or decision-making module, the planned path may deviate from the actual position and posture of the unmanned vehicle, which will cause abnormal swinging behavior of the unmanned vehicle, that is, the unmanned vehicle will swing back and forth on the road. Summary of the invention

[0003] The present disclosure provides a method and device for detecting abnormal swinging behavior of an unmanned vehicle, and an autonomous driving vehicle, which are used to detect abnormal swinging behavior of an unmanned vehicle.

[0004] According to one aspect of the present disclosure, a method for detecting abnormal swinging behavior of an unmanned vehicle is provided, comprising:

[0005] Get the current target orientation angle of the unmanned vehicle;

[0006] Based on the acquisition time of the current target orientation angle, determine the target index corresponding to the acquisition time of the current target orientation angle according to a preset index mapping algorithm;

[0007] Based on the current target heading angle and the target historical heading angle recorded by the target index, determine the target center heading angle at the acquisition moment between the current target heading angle and the target historical heading angle; wherein each index is used to record the heading angle corresponding to the index at the acquisition moment, and any two acquisition moments separated by an integer number of preset periods correspond to the same index;

[0008] If the current target orientation angle, the target historical orientation angle, and the target center orientation angle meet preset conditions, it is determined that the unmanned vehicle exhibits abnormal swinging behavior.

[0009] According to another aspect of the present disclosure, a device for detecting abnormal swinging behavior of an unmanned vehicle is provided, comprising:

[0010] The target orientation angle acquisition module is used to obtain the current target orientation angle of the unmanned vehicle;

[0011] A target index determination module, configured to determine, based on the acquisition time of the current target orientation angle, a target index corresponding to the acquisition time of the current target orientation angle according to a preset index mapping algorithm;

[0012] A target centering heading angle determination module, used to determine a target centering heading angle whose acquisition moment is between the current target heading angle and the target historical heading angle recorded by the target index based on the current target heading angle and the target historical heading angle recorded by the target index; wherein each index is used to record the heading angle corresponding to the index at the acquisition moment, and any two acquisition moments separated by an integer number of preset periods correspond to the same index;

[0013] The unmanned vehicle abnormal swing behavior determination module is used to determine that the unmanned vehicle has abnormal swing behavior if the current target orientation angle, the target historical orientation angle and the target center orientation angle meet preset conditions.

[0014] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any of the above-mentioned methods for detecting abnormal swinging behavior of an unmanned vehicle.

[0018] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any of the above-mentioned methods for detecting abnormal swinging behavior of an unmanned vehicle.

[0019] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for detecting abnormal swinging behavior of an unmanned vehicle.

[0020] According to another aspect of the present disclosure, an autonomous driving vehicle is provided, comprising the electronic device as described above.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0023] Figure 1 is a schematic diagram of a first embodiment of a method for detecting abnormal swinging behavior of an unmanned vehicle provided by the present disclosure;

[0024] Figure 2 It is a schematic diagram of determining whether the current target heading angle, the target historical heading angle, and the target centering heading angle meet preset conditions in the present disclosure;

[0025] Figure 3 is a schematic diagram of a second embodiment of a method for detecting abnormal swinging behavior of an unmanned vehicle provided by the present disclosure;

[0026] Figure 4 is a schematic diagram of a specific embodiment of a method for detecting abnormal swinging behavior of an unmanned vehicle provided by the present disclosure;

[0027] Figure 5 is a schematic diagram of a specific example of a method for detecting abnormal swinging behavior of an unmanned vehicle provided by the present disclosure;

[0028] Figure 6 is a schematic diagram of a first embodiment of a detection device for abnormal swinging behavior of an unmanned vehicle provided by the present disclosure;

[0029] Figure 7 is a schematic diagram of a second embodiment of a detection device for abnormal swinging behavior of an unmanned vehicle provided by the present disclosure;

[0030] Figure 8 It is a block diagram of an electronic device used to implement the method for detecting abnormal swinging behavior of an unmanned vehicle according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0032] For various reasons, such as system anomalies or unreasonable planning in the planning module, the unmanned vehicle will swing back and forth on the road. This abnormal swinging behavior of the unmanned vehicle during driving is also called dragon-drawing behavior. This behavior is difficult to avoid from the planning module alone. When the unmanned vehicle has abnormal swinging behavior, it is very easy to collide or drive off the normal road, resulting in a high risk. At present, there is no device that can detect the abnormal swinging behavior of the unmanned vehicle, resulting in the inability to detect the abnormal swinging behavior of the unmanned vehicle in time, so as to take timely countermeasures to reduce the risk.

[0033] Based on this, the present disclosure provides a method, device and autonomous driving vehicle for detecting abnormal swinging behavior of an unmanned vehicle. The following first describes an exemplary method for detecting abnormal swinging behavior of an unmanned vehicle provided by the present disclosure.

[0034] The method of the embodiment of the present disclosure can be applied to electronic devices such as servers and autonomous driving vehicles, which are not specifically limited in the embodiment of the present disclosure.

[0035] The unmanned vehicle may be an unmanned vehicle or an intelligent vehicle that supports both manual and unmanned driving, etc., and the embodiments of the present disclosure do not specifically limit this.

[0036] The unmanned vehicle abnormal swing behavior detection method provided by the present disclosure can be applied to unmanned vehicle systems, etc. Figure 1 , Figure 1 1 is a schematic diagram of a first embodiment of a method for detecting abnormal swinging behavior of an unmanned vehicle provided by the present disclosure. The method may include the following steps:

[0037] Step S110, obtaining the current target orientation angle of the unmanned vehicle.

[0038] Step S120: Based on the acquisition time of the current target orientation angle, determine the target index corresponding to the acquisition time of the current target orientation angle according to a preset index mapping algorithm.

[0039] Step S130, based on the current target orientation angle and the target historical orientation angle recorded in the target index, determine a target center orientation angle that is between the current target orientation angle and the target historical orientation angle at an acquisition time.

[0040] Each index is used to record the orientation angle corresponding to the acquisition moment, and any two acquisition moments separated by an integer number of preset periods correspond to the same index. The specific value of the preset period can be manually determined, such as 2s, 3s, etc.

[0041] Step S140: If the current target orientation angle, the target historical orientation angle, and the target center orientation angle meet preset conditions, it is determined that the unmanned vehicle has abnormal swinging behavior.

[0042] In the disclosed embodiment, after obtaining the current target orientation angle of the unmanned vehicle, the target index corresponding to the current target orientation angle is determined based on the acquisition time of the current target orientation angle according to the preset index mapping algorithm, and the target center orientation angle between the current target orientation angle and the target historical orientation angle recorded by the target index is determined based on the current target orientation angle and the target historical orientation angle recorded at the target index. Each index is used to record the orientation angle corresponding to the index at the acquisition time, and any two acquisition times separated by an integer number of preset cycles correspond to the same index. Then, it is determined whether the current target orientation angle, the target historical orientation angle, and the target center orientation angle meet the preset conditions. If they do, it is determined that the unmanned vehicle has abnormal swinging behavior. By using the disclosed embodiment, the index records the last acquisition time and the heading angle corresponding to the index. Since any two acquisition times separated by an integer number of preset periods correspond to the same index, the acquisition time of the target historical heading angle recorded by the target index is separated by a preset period from the acquisition time of the current target heading angle, and the current target heading angle is the heading of the unmanned vehicle at the end of the preset period, the target historical heading angle is the heading angle of the unmanned vehicle at the beginning of the preset period, and the center heading angle is the heading angle of the unmanned vehicle within the preset period. Therefore, the current target heading angle, the target historical heading angle, and the target center heading angle can reflect the change of the heading angle of the unmanned vehicle within the period, thereby determining whether the unmanned vehicle has abnormal swinging behavior within the period. The detection of abnormal swinging behavior of the unmanned vehicle is realized, so that the abnormal swinging behavior of the unmanned vehicle can be discovered in time, and the unmanned vehicle can be effectively taken over in an emergency to avoid accidents and ensure the safety of people and vehicles. At the same time, only one index needs to be maintained for all acquisition moments that are separated by an integer number of cycles, so the number of indexes is much smaller than the number of historical orientation angles, so that when detecting abnormal swinging behavior of unmanned vehicles, only a small number of historical orientation angles recorded in indexes need to be detected, without the need to query all historical orientation angles, which greatly reduces the amount of data processing. Therefore, the efficiency of detecting abnormal swinging behavior of unmanned vehicles can be effectively improved.

[0043] The above steps S110 to S140 are exemplarily described below.

[0044] The heading angle is the angle between the front of the vehicle and the preset direction. In the embodiment of the present disclosure, the heading angle of the unmanned vehicle can be obtained by a heading angle measurement module built into the unmanned vehicle, or by a roadside unit external to the unmanned vehicle and having a heading angle measurement function. Moreover, the heading angle in the present disclosure can be directly measured or calculated based on the measured data.

[0045] The above-mentioned unmanned vehicle heading angle can be obtained in real time, or can be periodically obtained according to a preset collection time interval. For example, the current heading angle of the unmanned vehicle can be obtained every 0.1S. This disclosure does not make specific limitations on this.

[0046] When obtaining the current target heading angle of the unmanned vehicle, headingcur can be used to record the specific value of the current target heading angle, and Tcur can be used to record the acquisition time of the current target heading angle, that is, the time when headingcur is collected. The unit of the moment can be seconds, minutes, milliseconds, etc., and the value of the moment can retain two decimal places, one decimal place, etc. As a specific implementation method of the embodiment of the present disclosure, the positive and negative directions of the heading angle can be manually pre-defined, and accordingly, the specific value of the current target heading angle can be a value with positive and negative signs.

[0047] The above-mentioned unmanned vehicle heading angles can be stored in a hash storage manner. As a specific implementation, the sampling index corresponding to each heading angle can be obtained based on the collection time of each heading angle according to the above-mentioned preset index mapping algorithm, and the value of each heading angle and the collection time of each heading angle are stored corresponding to the above-mentioned sampling index, that is, the sampling index is used to identify the value of each heading angle and the collection time of each heading angle.

[0048] Exemplarily, according to the preset index mapping algorithm, based on the acquisition time of the current target heading angle of the unmanned vehicle, the sampling index corresponding to the current target heading angle can be obtained as the target index. The value of the current target heading angle headingcur and the corresponding acquisition time Tcur are stored corresponding to the target index.

[0049] The preset index mapping algorithm may be a modulo algorithm determined based on a preset sampling window TW and a preset sampling resolution R. The duration of the preset sampling window TW is manually preset, such as 2s, 3s, etc. The sampling resolution R represents the number of heading angles collected per second, such as 10, 15, etc.

[0050] As a specific implementation, when determining the target index corresponding to the acquisition time of the current target orientation angle according to the preset index mapping algorithm, it can be determined in the following manner:

[0051] The remainder of dividing the second product by the first product is calculated as the target index corresponding to the acquisition time of the current target orientation angle.

[0052] The first product is the product of the above-mentioned preset sampling window and the preset sampling resolution; the second product is the product of the second summation result and the preset sampling resolution, wherein the second summation result is the integer part of the acquisition time of the current target direction angle modulo the third preset constant, plus the decimal part of the acquisition time of the current target direction angle.

[0053] Exemplarily, the target index may be determined by using the following preset index mapping algorithm:

[0054] Indexcur=(Ti%10+Tf)*R%(TW*R).

[0055] Among them, Indexcur is the target index; Ti is the integer part of the current target direction angle acquisition time, that is, Ti=Interger(Tcur); Tf is the decimal part of the current target direction angle acquisition time, that is, Tf=Float(Tcur); R is the preset sampling resolution; TW is the preset sampling window. The 10 in the preset index mapping algorithm is the third preset constant, which can also be other constants.

[0056] It can be seen that when determining the target index, the result of (Ti%10+Tf)*R modulo TW*R is calculated. Therefore, two moments separated by a duration of TW correspond to the same index, and the target index range obtained is within R*TW. It can be seen that the duration of the above-mentioned preset period can be the same as the preset sampling window TW.

[0057] For example, if the acquisition time of the current target heading angle is 3.71s, then the integer part Ti is 3 and the decimal part Tf is 0.71. If the preset resolution R is 10 and the sampling window TW is 2s, then the target index corresponding to the current target heading angle is indexcur=(3%10+0.71)*10%(10*2)=17.1.

[0058] In this embodiment, the acquisition time of each orientation angle is mapped to an index through the above-mentioned preset index mapping algorithm, and the above-mentioned index is used to identify the value of each orientation angle and the acquisition time of each orientation angle. Since the above-mentioned preset index mapping algorithm is a modulo algorithm for the product of the sampling window TW and the sampling resolution R, the range of the obtained sampling index is within R*TW, that is, the number of obtained sampling indexes is much smaller than the number of moments of collecting the orientation angles. In other words, by applying this embodiment, it is not necessary to store all the collected orientation angles, saving storage space, and the amount of data processing is less when searching for historical orientation angles later.

[0059] As described above, in this embodiment, all the collected orientation angles may not be stored, so the sampling window TW may represent the sampling duration corresponding to the stored orientation angles, and two moments separated by the sampling duration TW correspond to the same sampling index. The duration may be manually preset, such as 10s, 15s, etc.

[0060] As described above, two moments of the interval sampling duration TW correspond to the same sampling index. Therefore, after determining the target index according to the preset index mapping algorithm based on the current target heading angle acquisition moment, the historical heading angle identified by the target index can be determined as the target historical heading angle. Ideally, the target historical heading angle is acquired before the TW duration of the current target heading angle acquisition moment.

[0061] Afterwards, the target centering angle can be determined as the target centering angle, which is collected at a time between the collection time of the target historical orientation angle and the collection time of the current target orientation angle. Ideally, the target centering angle is collected TW / 2 time before the collection time of the current target orientation angle.

[0062] Afterwards, it may be determined whether the target historical orientation angle, the current target orientation angle, and the target center orientation angle meet preset conditions.

[0063] It is understandable that when the unmanned vehicle exhibits abnormal swinging behavior, it will swing back and forth. In other words, the unmanned vehicle's heading angle will be the same multiple times in a short period of time, and in two consecutive situations where the unmanned vehicle's heading angle is the same, the changing trend of the heading angle is opposite. In other words, the magnitude relationship between the current heading angle and the center heading angle in two consecutive situations where the unmanned vehicle's heading angle is the same is opposite.

[0064] Therefore, the above-mentioned preset conditions may include a preset same orientation angle condition and a preset orientation angle relationship condition. The above-mentioned same orientation angle condition may be used to determine whether the unmanned vehicle currently has the same orientation angle. The above-mentioned orientation angle relationship condition may be used to determine whether the change trend of the orientation angle is opposite in two consecutive situations where the unmanned vehicle has the same orientation angle.

[0065] In one embodiment of the present disclosure, Figure 2 As shown, determining whether the above-mentioned target historical heading angle, current target heading angle, and target centering heading angle meet the preset heading angle same condition and the preset heading angle relationship condition can be achieved by taking the following steps:

[0066] Step S141, determining whether the current target orientation angle and the target historical orientation angle satisfy a preset orientation angle sameness condition.

[0067] Exemplarily, the above-mentioned preset orientation angle same condition may be: the difference between the current target orientation angle and the target historical orientation angle is less than a preset maximum error value.

[0068] The maximum error value can be preset manually, such as 10°, 12°, etc. If the difference between the current target heading angle and the target historical heading angle is less than the preset maximum error value, the current target heading angle and the target historical heading angle can be considered equal, that is, the heading angles are the same.

[0069] Step S142: If the current target heading angle and the target historical heading angle satisfy the preset heading angle same condition, determine whether the current target heading angle and the target centering heading angle satisfy the preset heading angle relationship condition.

[0070] Exemplarily, the preset heading angle relationship condition is: the size relationship between the current target heading angle and the target center heading angle is the same as the size relationship between the current heading angle and the center heading angle when the heading angle is the same as the heading angle in the historical record, and the time interval between the time when the current target heading angle is acquired and the time when the heading angle is the same as the historical record is less than a preset time window.

[0071] The same situation of the orientation angle in the above historical records can specifically be the same situation of the last orientation angle. Exemplarily, the same situation of the last orientation angle is the same situation of the orientation angle recorded during the last round of abnormal swinging behavior detection of the unmanned vehicle. When recording the same situation of the orientation angle, the corresponding current orientation angle, the time of occurrence of the same situation of the orientation angle (i.e., the collection time of the current orientation angle), the historical orientation angle recorded by the sampling index corresponding to the current orientation angle, and the centering orientation angle can be recorded.

[0072] The above time window is manually preset, such as 2s, 2.5s, etc. The time window may be equal to or different from the above sampling window.

[0073] like Figure 2 As shown, in step S143, if the current target orientation angle and the target center orientation angle satisfy the preset orientation angle relationship condition, it is determined that the unmanned vehicle exhibits abnormal swinging behavior.

[0074] If the vehicle is found to be swinging abnormally, the abnormality can be reported and the unmanned vehicle can be urgently taken over and braked to avoid accidents. The unmanned vehicle can also be controlled to issue a warning sound to remind people around the unmanned vehicle to avoid it.

[0075] In the application of the disclosed embodiments, the unmanned vehicle's current target heading angle, target historical heading angle and target center heading angle are used to determine whether the unmanned vehicle is currently facing the same heading angle, as well as the relationship between the current target heading angle and the target center heading angle when the current heading angles are the same, and whether the current heading angle and the center heading angle are the same as the last time the heading angles were the same, to determine whether the unmanned vehicle has abnormal swinging behavior. There is no need to make judgments based on the various heading angles collected historically, the amount of data processing is small, and implementation is relatively convenient.

[0076] In other embodiments of the present disclosure, when judging whether the same orientation angle currently occurs, the following steps may also be used to judge:

[0077] Determine whether the current target heading angle, the target historical heading angle, and the target center heading angle satisfy a preset second heading angle same condition. The preset second heading angle same condition may be that the magnitude relationship between the current target heading angle and the target historical heading angle is opposite to the magnitude relationship between the current heading angle and the corresponding target historical heading angle obtained last time, and the difference between the current target heading angle and the target historical heading angle is less than a preset maximum tolerance value, and the difference between the current target heading angle and the target center heading angle is greater than a preset minimum drop value.

[0078] In this embodiment, the collection time of each heading angle can be a series of discrete time points. The current heading angle obtained last time can be the heading angle obtained at a time point before the current time Tcur. For example, assuming that heading angle 1 is obtained at t=0s, heading angle 2 is obtained at t=0.05s, heading angle 3 is obtained at t=0.1, and heading angle 4 is obtained at t=0.15, and the target heading angle is heading angle 4, then the current heading angle obtained last time is heading angle 3.

[0079] Of course, the last acquired heading angle may also be any heading angle acquired before the current target heading angle and acquired within a preset time period (e.g., 0.15s). Still taking the example of heading angles 1-4 as an example, the last acquired current heading angle may be any heading angle among heading angles 1-3.

[0080] The above-mentioned maximum tolerance value and minimum drop value can be preset manually. For example, the above-mentioned maximum tolerance value can be 20°, 18°, etc. The above-mentioned minimum drop value can be 5°, 4°, etc.

[0081] If the current target heading angle, the target historical heading angle, and the target center heading angle satisfy any of the above-mentioned preset heading angle same conditions, it can be considered that the current heading angle is the same.

[0082] If the current target heading angle, the target historical heading angle, and the target center heading angle meet the preset heading angle same condition, and do not meet the preset heading angle relationship condition, then the current target heading angle, the acquisition time of the current target heading angle, and the target center heading angle are used to update the same heading angle situation of the historical records, and the current target heading angle is used to update the historical heading angle corresponding to the target index. In this way, only the last same heading angle situation can be recorded, reducing the amount of data that needs to be stored and reducing the amount of subsequent data queries.

[0083] In this embodiment, ST can be used to mark the occurrence time of the same historical heading angle. Once the same heading angle is updated by using the current target heading angle, the acquisition time of the current target heading angle and the target centering heading angle to update the historical record, the value of Tcur can be used to update ST.

[0084] In this way, by updating the historical records of the same orientation angle, only the last same orientation angle situation can be recorded, without recording each same orientation angle situation, thus saving storage space, and when querying the same historical orientation angle situation, the data query amount is small.

[0085] In one embodiment of the present disclosure, based on Figure 1 ,like Figure 3 As shown, the above step S130, based on the current target orientation angle and the target historical orientation angle recorded in the target index, determines that the acquisition time is before the target center orientation angle between the current target orientation angle and the target historical orientation angle, and may also include:

[0086] Step S330: If the historical orientation angle recorded in the target index and the current target orientation angle meet the preset first determination condition, the historical orientation angle recorded in the target index is used as the target historical orientation angle.

[0087] Step S340: If the historical orientation angle recorded in the target index and the current target orientation angle do not satisfy the preset first judgment condition, search forward or backward based on the target index until a historical orientation angle satisfying the preset first judgment condition is found as the target historical orientation angle.

[0088] The above-mentioned preset first judgment condition is: the time interval between the acquisition time of the historical orientation angle recorded in the target index and the acquisition time of the current target orientation angle is less than nTW and greater than 1 / R; wherein n is the first preset constant, such as 1.5, 1.3, etc.; TW is the preset sampling window; R is the preset sampling resolution.

[0089] It is understandable that due to disturbance or temporary equipment failure, the heading angle may be missed or over-sampled, resulting in the sampling duration of the heading angle actually recorded by each index not being equal to the above-mentioned preset sampling window. If the abnormal swinging behavior of the unmanned vehicle is detected on this basis, the detection result will be inaccurate. Therefore, the influence of the heading angle collection failure on the abnormal swinging behavior detection of the unmanned vehicle can be avoided by determining whether the historical heading angle recorded by the target index and the current target heading angle meet the preset first judgment condition.

[0090] If the historical orientation angle recorded in the target index and the current target orientation angle meet the first determination condition, it can be determined that the historical orientation angle is a normally recorded historical orientation angle. Therefore, the historical orientation angle can be used as the target historical orientation angle for subsequent calculations.

[0091] If the historical orientation angle recorded by the target index and the current target orientation angle do not meet the first determination condition, it can be determined that the historical orientation angle is the historical orientation angle of the abnormal record. As mentioned above, the range of the sampling index is within R*TW and is limited. Therefore, it is possible to search forward or backward based on the target index to find the historical orientation angle that meets the first determination condition as the target historical orientation angle for subsequent calculation. Of course, the target historical orientation angle can also be determined by traversing each sampling index or manually specifying.

[0092] By searching for an orientation angle that satisfies a preset first determination condition when the historical orientation angle corresponding to the target index does not satisfy the preset first determination condition, the probability of obtaining the historical orientation angle of the target can be increased.

[0093] In one embodiment of the present disclosure, based on Figure 1 ,like Figure 3 As shown, the above-mentioned determination of the target centering orientation angle between the current target orientation angle and the target historical orientation angle recorded by the target index at the acquisition time based on the current target orientation angle and the target historical orientation angle can be implemented by the following steps:

[0094] Step S131, based on the index corresponding to the historical orientation angle of the target, determine the target center index according to a preset center index search algorithm;

[0095] The above-mentioned preset centering index search algorithm is: calculate the remainder of the first summation result divided by the first product as the target centering index; wherein the first product is the product of the preset sampling window and the preset sampling resolution; the first summation result is the sum of half of the first product and the index corresponding to the target historical heading angle.

[0096] Exemplarily, the above-mentioned center index search algorithm is:

[0097] Indexmid=(Indexfound+R*TW / 2)%(R*TW)

[0098] Among them, Indexmid is the target center index; Indexfound is the index corresponding to the historical orientation angle of the target; R is the preset sampling resolution; TW is the preset sampling window.

[0099] In this embodiment, the Indexfound may be the target index indexcur, or may be the sampling index corresponding to the historical orientation angle of the target that meets the first determination condition.

[0100] If indexfound is 17.1, R is 10, and TW is 2s, then the target center index indexmid = (17.1 + 10*2 / 2)% (2*10) = 7.1.

[0101] Step S132: If the historical orientation angle recorded in the target centering index and the current target orientation angle meet a preset second determination condition, the historical orientation angle recorded in the target centering index is used as the target centering orientation angle.

[0102] The preset second judgment condition is: the time interval between the acquisition time of the historical orientation angle recorded in the target index and the acquisition time of the current target orientation angle is less than mTW and greater than TW / 2; wherein, TW is the preset sampling window, and m is the second preset constant, such as 1.5, 1.3, etc., and m can be equal to n or different from n.

[0103] As mentioned above, ideally, the collection time of the historical orientation angle corresponding to the target centering index should be TW / 2 time before the current target orientation angle collection time Tcur. Therefore, if the historical orientation angle corresponding to the target centering index meets the above second judgment condition, it can be determined that the historical orientation angle is collected normally, and the historical orientation angle can be used as the target centering orientation angle.

[0104] Step S133, if the historical orientation angle recorded in the target centering index and the current target orientation angle do not satisfy the preset second judgment condition, search forward or backward based on the target centering index until a historical orientation angle satisfying the preset second judgment condition is found as the target intermediate orientation angle.

[0105] In step S133, the historical orientation angles satisfying the preset second determination condition may be searched forward and backward in sequence with a step number of 1 for subsequent calculation. Of course, the target center orientation angle may also be determined by traversing each sampling index or manually specifying.

[0106] By searching for an orientation angle that satisfies the preset second determination condition when the historical orientation angle corresponding to the target centering index does not satisfy the preset second determination condition, the probability of obtaining the target centering orientation angle can be increased.

[0107] In this embodiment, by determining whether the historical orientation angle recorded in the target centering index and the current target orientation angle meet a preset second determination condition, the influence of the orientation angle collection failure on the abnormal swinging behavior detection of the unmanned vehicle can be avoided.

[0108] If no historical orientation angle that meets the preset first determination condition is found, or no historical orientation angle that meets the second determination condition is found, the historical orientation angle corresponding to the target index may be updated using the current target orientation angle.

[0109] In this embodiment, Tupdate may be used to record the time of updating the historical record. When the historical orientation angle corresponding to the target index is updated using the current target orientation angle, Tupdate may be updated using the value of Tcur.

[0110] It is understandable that due to a short-term equipment failure, it may cause over-collection or omission of the heading angle, etc. Therefore, before updating the historical record, it can be determined whether the historical record needs to be updated at present. For example, it can be determined whether Tdiff = Tcur-Tupdate satisfies Tdiff>1 / R. This can avoid the update error of the historical record due to the failure of the heading angle collection, thereby ensuring the accuracy of the abnormal swing behavior detection of the unmanned vehicle.

[0111] The following is an exemplary description of the detection method of abnormal swinging behavior of the unmanned vehicle provided by the present disclosure in conjunction with a specific embodiment:

[0112] In this example, the execution body maintains the following variables: headingcur, Tcur, indexlast, indexcur, R, TW. The execution body is defined as follows: Figure 4 The process shown realizes the detection of abnormal swinging behavior of the unmanned vehicle:

[0113] S401, obtain headingcur and Tcur.

[0114] The above headingcur represents the value of the current target heading angle, and Tcur represents the acquisition time of the current target heading angle.

[0115] S402, based on Tcur, calculate indexcur according to a preset index mapping algorithm.

[0116] S403, determine whether indexcur is not equal to indexlast, if so, execute step S404, if not, execute step S407.

[0117] indexlast is the sampling index corresponding to the current orientation angle obtained last time.

[0118] S404, judging whether to update historical information when indexlast, if so, executing step S406, if not, executing step S405.

[0119] S405, using the value headinglast of the current heading angle obtained last time and the collection time Tlast corresponding to the current heading angle obtained last time, to update the historical heading angle recorded in indexlast.

[0120] S406, update Tupdate with the value of Tlast.

[0121] Tupdate is used to record the time when the history record is updated.

[0122] S407, marking indexcur as not updating historical information.

[0123] S408, obtaining the historical heading angle collection time Thistory recorded in indexcur and the value headinghistory of the historical heading angle.

[0124] S409, whether 1 / R<Tdiff=Tcur-Thistory<1.5TW, if so, execute step S412, if not, execute step S410.

[0125] That is, it is determined whether the historical orientation angle recorded in the target index and the current target orientation angle meet a preset first determination condition.

[0126] S410, search forward to see if 1 / R<Tdiff=Tcur-Thistory<1.5TW, if so, execute step S412, if not, execute step S411.

[0127] S411, search backward to see if 1 / R<Tdiff=Tcur-Thistory<1.5TW, if so, execute step S412, if not, execute step S428.

[0128] S412, determine Indexfound.

[0129] The above steps S408-S412 are equivalent to steps S330-S340 in the present disclosure.

[0130] S413, calculate Indexmid based on Indexfound.

[0131] S414, obtaining the historical heading angle collection time Thistory recorded in Indexmid and the value headinghistory of the historical heading angle.

[0132] S415, whether TW / 2<Tdiff=Tcur-Thistory<1.5TW, if so, execute step S418, if not, execute step S416.

[0133] That is, it is determined whether the historical orientation angle recorded in the target centering index and the current target orientation angle meet the preset second determination condition.

[0134] S416, search forward to see if TW / 2<Tdiff=Tcur-Tmid_history<1.5TW, if so, execute step S418, if not, execute step S417.

[0135] S417, search backward to see if TW / 2<Tdiff=Tcur-Tmid_history<1.5TW, if so, execute step S418, if not, execute step S428.

[0136] In this embodiment, the execution order of step S416 and step S417 is not specifically limited.

[0137] S418, determining Indexmid as a sampling index corresponding to a historical orientation angle that satisfies TW / 2<Tdiff=Tcur-Tmid_history<1.5TW.

[0138] The above steps S413-S418 are equivalent to steps S131-S133 in the present disclosure.

[0139] S419, let headingmid_diff = math.abs(headingmid_history-headingcur), determine whether headingmid_diff is greater than 180°, if so, execute step S420, if not, execute step S421.

[0140] S420, set headingmid_diff=360-headingmid_diff.

[0141] In step S420, a headingmid_diff greater than 180° may be converted into a headingmid_diff within a range of 180°, thereby eliminating the need to consider the direction of the heading angle value, which is more convenient for calculation.

[0142] S421, let headinghistory_diff = math.abs(headinghistory-headingcur), determine whether headinghistory_diff is less than HME, if so, execute step S423, if not, execute step S422.

[0143] The above HME is the preset maximum error value in the present disclosure.

[0144] S422, whether the size relationship between headinghistory and headingcur is opposite to the last time, and headinghistory_diff<HMTE, and headingmid_diff>HMG, if so, execute step S423, if not, execute step S428.

[0145] The above-mentioned HMTE is the preset maximum tolerance value in the present disclosure, and the above-mentioned HMG is the minimum gap value in the present disclosure.

[0146] If any condition in step S421 or S422 is met, it can be determined that the current orientation angle is the same. In this embodiment, the execution order of the above step S421 and step S422 is not specifically limited.

[0147] S423, whether the same historical heading occurs, if so, execute step S424, if not, execute step S426.

[0148] S424, when the two headings are the same, whether the size relationship between headingcur and headingmid is opposite, if so, execute step S425, if not, execute step S426.

[0149] S425, let Tdiff = Tcur-ST, determine whether Tdiff is less than HTW, if so, execute step S431, if not, execute step S426.

[0150] HTW is the preset window in the present disclosure.

[0151] The above steps S421-S425 are equivalent to step S140 in the present disclosure.

[0152] S426, let ST = Tcur, and record the size relationship between headingcur and headingmid.

[0153] That is, the same orientation angle appears when ST is used.

[0154] S427, record the size relationship between headingcur and headinghistory.

[0155] S428, let Tdiff = Tcur-Tupdate, determine whether Tdiff is greater than 1 / R, if so, execute step S429, if not, execute step S430.

[0156] S429, indexcur=Tcur, headingcur, Tupdate=Tcur.

[0157] That is, the historical heading angle recorded by indexcur is updated using the value of the current target heading angle headingcur and the corresponding collection time Tcur, and the update time Tupdate of the historical record is updated using the value of Tcur.

[0158] S430, let headinglast=headingcur, indexlast=indexcur, Tlast=Tcur.

[0159] S431, determining that the vehicle has abnormal swinging behavior.

[0160] The method for detecting abnormal swinging behavior of an unmanned vehicle provided by the present disclosure will be exemplarily described below in conjunction with a specific schematic diagram of the orientation angle.

[0161] like Figure 5 As shown, if the current target heading angle is point A, the historical heading angle recorded by the sampling index corresponding to the current target heading angle is the heading angle at point B. If A and B meet the above first determination condition, B is used as the target historical heading angle. Afterwards, if the target center heading angle is determined to be C, it can be determined whether A, B, and C meet the above preset heading angle same condition and preset heading angle relationship condition.

[0162] like Figure 5 As shown, A, B, and C meet the above-mentioned preset orientation angle same condition, that is, the current orientation angle is the same. Then, it can be determined whether there is a historical orientation angle same situation. Figure 5 As shown, in the case of the same historical heading angle (the same last heading angle), the current target heading angle is D and the target centering heading angle is E. A and C meet the above preset heading angle relationship conditions, that is, the magnitude relationship of AC is opposite to the magnitude relationship of DE. Therefore, it can be determined that the unmanned vehicle is currently experiencing abnormal swinging behavior.

[0163] According to an embodiment of the present disclosure, a device for detecting abnormal swinging behavior of an unmanned vehicle is also provided. Figure 6 As shown, the device may include:

[0164] The target orientation angle acquisition module 610 is used to acquire the current target orientation angle of the unmanned vehicle;

[0165] A target index determination module 620 is used to determine the target index corresponding to the acquisition time of the current target orientation angle according to a preset index mapping algorithm based on the acquisition time of the current target orientation angle;

[0166] The target centering heading angle determination module 630 is used to determine the target centering heading angle at an acquisition time between the current target heading angle and the target historical heading angle recorded by the target index, wherein each index is used to record the heading angle corresponding to the index at the acquisition time, and any two acquisition times separated by an integer number of preset periods correspond to the same index;

[0167] The unmanned vehicle abnormal swing behavior determination module 640 is used to determine that the unmanned vehicle has abnormal swing behavior if the current target orientation angle, the target historical orientation angle, and the target center orientation angle meet preset conditions.

[0168] In the disclosed embodiment, after obtaining the current target orientation angle of the unmanned vehicle, based on the acquisition time of the current target orientation angle, according to the preset index mapping algorithm, the target index corresponding to the current target orientation angle is determined, and based on the current target orientation angle and the target historical orientation angle recorded by the target index, the target center orientation angle between the current target orientation angle and the target historical orientation angle at the acquisition time is determined. Each index is used to record the orientation angle corresponding to the index at the acquisition time, and any two acquisition times separated by an integer number of preset cycles correspond to the same index. Then, it is determined whether the current target orientation angle, the target historical orientation angle, and the target center orientation angle meet the preset conditions. If so, it is determined that the unmanned vehicle has abnormal swinging behavior. By applying the disclosed embodiment, whether the unmanned vehicle has abnormal swinging behavior is determined by whether the unmanned vehicle's orientation angle meets the preset conditions, thereby realizing the detection of abnormal swinging behavior of the unmanned vehicle, so that the abnormal swinging behavior of the unmanned vehicle can be discovered in time, and the unmanned vehicle can be effectively taken over in an emergency to avoid accidents and ensure the safety of people and vehicles. At the same time, by utilizing the index record to obtain the orientation angle corresponding to the index, and any two acquisition moments separated by an integer number of preset periods correspond to the same index, that is, the number of indexes is much smaller than the number of acquisition moments, so when detecting abnormal swinging behavior of the unmanned vehicle, it is only necessary to detect the orientation angle of each index record, without querying all historical orientation angles, and the amount of data processing is greatly reduced.

[0169] In one embodiment of the present disclosure, based on Figure 6 ,like Figure 7 As shown, the above device may also include:

[0170] The target historical heading angle determination module 730 is used to use the historical heading angle recorded in the target index as the target historical heading angle if the historical heading angle recorded in the target index and the current target heading angle meet the preset first judgment condition; wherein the preset first judgment condition is: the time interval between the acquisition time of the historical heading angle recorded in the target index and the acquisition time of the current target heading angle is less than nTW and greater than 1 / R; wherein n is the first preset constant; TW is the preset sampling window; and R is the preset sampling resolution.

[0171] In one embodiment of the present disclosure, the target historical heading angle determination module 730 can also be used to search forward or backward based on the target index if the historical heading angle recorded in the target index and the current target heading angle do not satisfy the preset first judgment condition, until a historical heading angle satisfying the preset first judgment condition is found as the target historical heading angle.

[0172] In one embodiment of the present disclosure, the target centering orientation angle determination module 630 may be used to determine the target centering index based on the index corresponding to the target historical orientation angle according to a preset centering index search algorithm; the preset centering index search algorithm is: calculating the remainder of the first summation result divided by the first product as the target centering index; wherein the first product is the product of a preset sampling window and a preset sampling resolution; the first summation result is the sum of half of the first product and the index corresponding to the target historical orientation angle;

[0173] If the historical orientation angle recorded in the target centering index and the current target orientation angle meet the preset second judgment condition, the historical orientation angle recorded in the target centering index is used as the target centering orientation angle; wherein, the preset second judgment condition is: the time interval between the acquisition time of the historical orientation angle recorded in the target index and the acquisition time of the current target orientation angle is less than mTW and greater than TW / 2; wherein m is the second preset constant; and TW is the preset sampling window.

[0174] In one embodiment of the present disclosure, the target centering orientation angle determination module 630 can also be used to search forward or backward based on the target centering index if the historical orientation angle recorded in the target centering index and the current target orientation angle do not satisfy the preset second judgment condition, until a historical orientation angle satisfying the preset second judgment condition is found as the target centering orientation angle.

[0175] In an embodiment of the present disclosure, the preset conditions may include: a preset orientation angle same condition and a preset orientation angle relationship condition;

[0176] The unmanned vehicle abnormal swing behavior determination module 640 can be used to determine whether the current target orientation angle and the target historical orientation angle meet a preset orientation angle same condition; wherein the preset orientation angle same condition is: the difference between the current target orientation angle and the target historical orientation angle is less than a preset maximum error value;

[0177] If the current target heading angle and the target historical heading angle satisfy the same condition as the preset heading angle, determine whether the current target heading angle and the target center heading angle satisfy a preset heading angle relationship condition; wherein the preset heading angle relationship condition is: the magnitude relationship between the current target heading angle and the target center heading angle is the same as the magnitude relationship between the current heading angle and the center heading angle when the heading angle in the historical record is the same, and the time interval between the time when the current target heading angle is acquired and the time when the heading angle in the historical record is the same is less than a preset time window;

[0178] If the current target orientation angle and the target center orientation angle satisfy the preset orientation angle relationship condition, it is determined that the unmanned vehicle exhibits abnormal swinging behavior.

[0179] In one embodiment of the present disclosure, based on Figure 6 ,like Figure 7 As shown, the above-mentioned device may also include a target index updating module 740, which is used to update the historical orientation angle corresponding to the target index using the current target orientation angle if the historical orientation angle that meets the preset first judgment condition is not found, or the historical orientation angle that meets the second judgment condition is not found.

[0180] In one embodiment of the present disclosure, based on Figure 6 ,like Figure 7 As shown, the above-mentioned device may also include a historical record updating module 750, which is used to use the current target heading angle, the acquisition time of the current target heading angle and the target center heading angle to update the historical record of the same heading angle if the current target heading angle, the target historical heading angle and the target center heading angle meet the same condition of the preset heading angle, but do not meet the preset heading angle relationship condition, and use the current target heading angle to update the historical heading angle corresponding to the target index.

[0181] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0182] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0183] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can 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 merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0184] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0185] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0186] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 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, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as a detection method for abnormal swinging behavior of an unmanned vehicle. For example, in some embodiments, the detection method for abnormal swinging behavior of an unmanned vehicle may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the detection method for abnormal swinging behavior of an unmanned vehicle described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the method for detecting abnormal swinging behavior of the unmanned vehicle in any other appropriate manner (for example, by means of firmware).

[0187] According to an embodiment of the present disclosure, the present disclosure further provides an autonomous driving vehicle. The autonomous driving vehicle includes the electronic device.

[0188] In one embodiment of the present disclosure, the vehicle's current target heading angle can be collected by a heading angle measurement module in the autonomous driving vehicle, or obtained from a roadside unit with a heading angle measurement function, and sent to the above-mentioned electronic device.

[0189] After acquiring the current target heading angle of the vehicle, the electronic device determines the target index corresponding to the acquisition time of the current target heading angle based on the acquisition time of the current target heading angle and according to a preset index mapping algorithm; determines the target center heading angle whose acquisition time is between the current target heading angle and the target historical heading angle based on the current target heading angle and the target index; wherein each index is used to record the heading angle corresponding to the index at the last acquisition time, and any two acquisition times separated by an integer number of preset periods correspond to the same index; if the current target heading angle, the target historical heading angle and the target center heading angle meet preset conditions, it is determined that the vehicle exhibits abnormal swinging behavior.

[0190] In a possible embodiment, the autonomous driving vehicle further includes a control module and an alarm module. When the electronic device determines that the vehicle has abnormal swinging behavior, the abnormal swinging information of the vehicle can be sent to the autonomous driving vehicle control module, so that the control module can take over and brake the autonomous driving vehicle in an emergency to avoid accidents. At the same time, the abnormal swinging information can be sent to the autonomous driving vehicle alarm module, so that the alarm module can remind passers-by to make emergency avoidance through sound and light alarms, thereby improving the safety of the autonomous driving vehicle.

[0191] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0192] The program code for implementing the method 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, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0193] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A 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, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0194] To provide interaction with a user, the systems and techniques described herein 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 the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the 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 can be received in any form (including acoustic input, voice input, or tactile input).

[0195] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0196] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0197] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0198] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for detecting abnormal swinging behavior of an unmanned vehicle, comprising: Get the current target orientation angle of the unmanned vehicle; Based on the acquisition time of the current target orientation angle, determine the target index corresponding to the acquisition time of the current target orientation angle according to a preset index mapping algorithm; Based on the current target heading angle and the target historical heading angle recorded by the target index, determine the target center heading angle whose acquisition moment is between the current target heading angle and the target historical heading angle; wherein each index is used to record the heading angle corresponding to the index at the previous acquisition moment, and any two acquisition moments separated by an integer number of preset periods correspond to the same index; the target historical heading angle is a historical heading angle that satisfies a preset first determination condition, and the target center heading angle is a historical heading angle that satisfies a preset second determination condition; the preset first determination condition is: the time interval between the acquisition moment of the historical heading angle recorded by the target index and the acquisition moment of the current target heading angle is less than nTW and greater than 1 / R; wherein n is a first preset constant; TW is a preset sampling window; R is a preset sampling resolution; the preset second determination condition is: the time interval between the acquisition moment of the historical heading angle recorded by the target index and the acquisition moment of the current target heading angle is less than mTW and greater than TW / 2; wherein m is a second preset constant; TW is the preset sampling window; If the current target orientation angle, the target historical orientation angle, and the target center orientation angle meet preset conditions, it is determined that the unmanned vehicle exhibits abnormal swinging behavior.

2. The method according to claim 1, further comprising: If the historical orientation angle recorded in the target index and the current target orientation angle meet the preset first determination condition, the historical orientation angle recorded in the target index is used as the target historical orientation angle.

3. The method according to claim 2, further comprising: If the historical orientation angle recorded in the target index and the current target orientation angle do not satisfy the preset first judgment condition, search forward or backward based on the target index until a historical orientation angle satisfying the preset first judgment condition is found as the target historical orientation angle.

4. The method according to claim 3, wherein: The step of determining the target centering orientation angle between the current target orientation angle and the target historical orientation angle recorded in the target index at the acquisition time comprises: Based on the index corresponding to the historical heading angle of the target, the target centering index is determined according to a preset centering index search algorithm; the preset centering index search algorithm is: calculating the remainder of the first summation result divided by the first product as the target centering index; wherein the first product is the product of the preset sampling window and the preset sampling resolution; the first summation result is the sum of half of the first product and the index corresponding to the historical heading angle of the target; If the historical orientation angle recorded in the target centering index and the current target orientation angle meet the preset second determination condition, the historical orientation angle recorded in the target centering index is used as the target centering orientation angle.

5. The method according to claim 4, wherein: The step of determining, based on the current target orientation angle and the target historical orientation angle recorded in the target index, a target center orientation angle between the current target orientation angle and the target historical orientation angle at the acquisition time, further includes: If the historical orientation angle recorded in the target centering index and the current target orientation angle do not satisfy the preset second judgment condition, search forward or backward based on the target centering index until a historical orientation angle satisfying the preset second judgment condition is found as the target centering orientation angle.

6. The method according to claim 1, wherein: The preset conditions include: preset orientation angle same conditions and preset orientation angle relationship conditions; The step of determining that the unmanned vehicle has abnormal swinging behavior if the current target orientation angle, the target historical orientation angle, and the target center orientation angle meet preset conditions includes: Determine whether the current target heading angle and the target historical heading angle satisfy a preset heading angle same condition; wherein the preset heading angle same condition is: the difference between the current target heading angle and the target historical heading angle is less than a preset maximum error value; If the current target heading angle and the target historical heading angle satisfy the same condition as the preset heading angle, determine whether the current target heading angle and the target center heading angle satisfy a preset heading angle relationship condition; wherein the preset heading angle relationship condition is: the magnitude relationship between the current target heading angle and the target center heading angle is the same as the magnitude relationship between the current heading angle and the center heading angle when the heading angle in the historical record is the same, and the time interval between the time when the current target heading angle is acquired and the time when the heading angle in the historical record is the same is less than a preset time window; If the current target orientation angle and the target center orientation angle satisfy the preset orientation angle relationship condition, it is determined that the unmanned vehicle exhibits abnormal swinging behavior.

7. The method according to any one of claims 2 to 5, further comprising: If the historical orientation angle that meets the preset first determination condition is not found, or the historical orientation angle that meets the preset second determination condition is not found, the historical orientation angle corresponding to the target index is updated using the current target orientation angle.

8. The method according to claim 1, wherein: The step of determining the target index corresponding to the acquisition time of the current target orientation angle according to a preset index mapping algorithm based on the acquisition time of the current target orientation angle comprises: Calculate the remainder of the second product divided by the first product as the target index corresponding to the acquisition time of the current target direction angle; wherein the first product is the product of a preset sampling window and a preset sampling resolution; the second product is the product of a second summation result and a preset sampling resolution, wherein the second summation result is the integer part of the acquisition time of the current target direction angle modulo a third preset constant, plus the decimal part of the acquisition time of the current target direction angle.

9. The method according to claim 6, further comprising: If the current target heading angle, the target historical heading angle and the target center heading angle satisfy the preset heading angle sameness condition, and do not satisfy the preset heading angle relationship condition, then the current target heading angle, the acquisition time of the current target heading angle and the target center heading angle are used to update the historical records of the same heading angles, and the current target heading angle is used to update the historical heading angle corresponding to the target index.

10. A detection device for abnormal swinging behavior of an unmanned vehicle, comprising: The target orientation angle acquisition module is used to obtain the current target orientation angle of the unmanned vehicle; A target index determination module, configured to determine, based on the acquisition time of the current target orientation angle, a target index corresponding to the acquisition time of the current target orientation angle according to a preset index mapping algorithm; A target centering heading angle determination module is used to determine a target centering heading angle whose acquisition time is between the current target heading angle and the target historical heading angle recorded by the target index, based on the current target heading angle and the target historical heading angle recorded by the target index; wherein each index is used to record the heading angle corresponding to the index at the acquisition time, and any two acquisition times separated by an integer number of preset periods correspond to the same index; the target historical heading angle is a historical heading angle that satisfies a preset first determination condition, and the target centering heading angle is a historical heading angle that satisfies a preset second determination condition; the preset first determination condition is: the time interval between the acquisition time of the historical heading angle recorded by the target index and the acquisition time of the current target heading angle is less than nTW and greater than 1 / R; wherein n is a first preset constant; TW is a preset sampling window; and R is a preset sampling resolution; the preset second determination condition is: the time interval between the acquisition time of the historical heading angle recorded by the target index and the acquisition time of the current target heading angle is less than mTW and greater than TW / 2; wherein m is a second preset constant; and TW is the preset sampling window; The unmanned vehicle abnormal swing behavior determination module is used to determine that the unmanned vehicle has abnormal swing behavior if the current target orientation angle, the target historical orientation angle and the target center orientation angle meet preset conditions.

11. The apparatus according to claim 10, further comprising: The target historical orientation angle determination module is used to use the historical orientation angle recorded in the target index as the target historical orientation angle if the historical orientation angle recorded in the target index and the current target orientation angle meet the preset first determination condition.

12. The device according to claim 11, wherein The target historical heading angle determination module is used to search forward or backward based on the target index if the historical heading angle recorded in the target index and the current target heading angle do not satisfy the preset first judgment condition, until a historical heading angle satisfying the preset first judgment condition is found as the target historical heading angle.

13. The device according to claim 12, wherein: The target centering orientation angle determination module is used to determine the target centering index based on the index corresponding to the target historical orientation angle according to a preset centering index search algorithm; the preset centering index search algorithm is: calculating the remainder of the first summation result divided by the first product as the target centering index; wherein the first product is the product of the preset sampling window and the preset sampling resolution; the first summation result is the sum of half of the first product and the index corresponding to the target historical orientation angle; If the historical orientation angle recorded in the target centering index and the current target orientation angle meet the preset second determination condition, the historical orientation angle recorded in the target centering index is used as the target centering orientation angle.

14. The device according to claim 13, wherein: The target centering direction angle determination module is used to search forward or backward based on the target centering index if the historical direction angle recorded in the target centering index and the current target direction angle do not satisfy the preset second judgment condition, until a historical direction angle that satisfies the preset second judgment condition is found as the target centering direction angle.

15. The device according to claim 10, wherein: The preset conditions include: preset orientation angle same conditions and preset orientation angle relationship conditions; The unmanned vehicle abnormal swing behavior determination module is used to determine whether the current target orientation angle and the target historical orientation angle meet a preset orientation angle same condition; wherein the preset orientation angle same condition is: the difference between the current target orientation angle and the target historical orientation angle is less than a preset maximum error value; If the current target heading angle and the target historical heading angle satisfy the same condition as the preset heading angle, determine whether the current target heading angle and the target center heading angle satisfy a preset heading angle relationship condition; wherein the preset heading angle relationship condition is: the magnitude relationship between the current target heading angle and the target center heading angle is the same as the magnitude relationship between the current heading angle and the center heading angle when the heading angle in the historical record is the same, and the time interval between the time when the current target heading angle is acquired and the time when the heading angle in the historical record is the same is less than a preset time window; If the current target orientation angle and the target center orientation angle satisfy the preset orientation angle relationship condition, it is determined that the unmanned vehicle exhibits abnormal swinging behavior.

16. The device according to any one of claims 11 to 14, further comprising: The target index updating module is used to update the historical orientation angle corresponding to the target index using the current target orientation angle if no historical orientation angle that meets the preset first judgment condition is found, or no historical orientation angle that meets the preset second judgment condition is found.

17. The apparatus according to claim 15, further comprising: A historical record updating module is used to update the historical record with the current target heading angle, the acquisition time of the current target heading angle and the target center heading angle if the current target heading angle, the target historical heading angle and the target center heading angle meet the same condition of the preset heading angle and do not meet the preset heading angle relationship condition, and to update the historical heading angle corresponding to the target index with the current target heading angle.

18. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

19. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.

20. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 9.

21. An autonomous driving vehicle comprising the electronic device as claimed in claim 18.

Images