Vehicle drift detection method and device

Abstract

The present disclosure provides a method and device for detecting vehicle drift. The present disclosure utilizes the characteristics that the lateral control error value can sensitively respond to subtle changes in the lateral direction of the vehicle, and utilizes the characteristics that the lateral control error shows abnormal continuous jumps or the statistical percentile value is too large during drift, and determines whether the vehicle is drifting by using multiple lateral control error values ​​within a preset detection time period. In a short period of time, it can capture both large drifts of the vehicle and slow and small drifts of the vehicle. It helps the vehicle to automatically take measures to control the vehicle's posture in a timely manner, ensuring the safety of the vehicle's driving. It does not rely on point cloud matching, has a small amount of calculation, and improves detection efficiency.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent vehicle technology, and in particular to a method and device for detecting vehicle drift. Background Art

[0002] Smart vehicles need to obtain their own position information in real time through the fusion positioning system during driving, and the accuracy of the position information usually needs to reach the centimeter level. The fusion positioning system includes: Global Navigation Satellite System (GNSS), Inertial Measurement Unit and LiDAR.

[0003] Currently, GNSS and IMU usually introduce the point cloud of laser radar and chassis information fed back by the vehicle chassis to assist in accurately estimating the vehicle posture on urban roads. However, this method is often affected by the external environment, such as building occlusion, interference from rain, snow and trees, vehicle side slip, vibration, random walk and temperature drift, which causes the estimation result to produce positioning drift and affects the stability of positioning.

[0004] Therefore, the present disclosure provides a method for detecting vehicle drift to solve one of the above-mentioned technical problems. Summary of the invention

[0005] The purpose of the present disclosure is to provide a method and device for detecting vehicle drift, which can solve at least one of the above-mentioned technical problems. The specific solution is as follows:

[0006] According to a specific embodiment of the present disclosure, in a first aspect, the present disclosure provides a method for detecting vehicle drift, comprising:

[0007] Obtaining lateral control error values ​​of the vehicle at multiple first time points within a preset detection time period;

[0008] Whether the vehicle drifts within a preset detection time period is determined based on the lateral control error values ​​at the multiple first time points.

[0009] Optionally, the determining whether the vehicle drifts within a preset detection time period based on the lateral control error values ​​at the multiple first time points includes:

[0010] Obtaining the positioning information of the vehicle at multiple second time points within a preset detection time period;

[0011] obtaining the number of lateral bounces of the vehicle based on the lateral control error values ​​at the plurality of first time points, and,

[0012] Obtaining the number of track mutations of the vehicle's driving track based on the positioning information of the multiple second time points;

[0013] In response to a difference between the number of lateral jumps and the number of trajectory mutations being greater than a preset change threshold, it is determined that the vehicle has drifted within a preset detection time period.

[0014] Optionally, obtaining the number of lateral bounces of the vehicle based on the lateral control error values ​​at the multiple first time points includes:

[0015] Obtaining error change values ​​of lateral control error values ​​of any two adjacent first time points based on the multiple lateral control error values ​​at the first time points;

[0016] The error change values ​​greater than a preset error change threshold are counted to obtain the number of lateral bounces of the vehicle.

[0017] Optionally, obtaining the error change value of the lateral control error values ​​of any two adjacent first time points based on the lateral control error values ​​at the multiple first time points includes:

[0018] Insert them into the candidate queue in sequence according to the time sequence of the first time point corresponding to each lateral control error value;

[0019] In response to inserting a first lateral control error value into the candidate queue, a first error change value is obtained based on the first lateral control error value and a second lateral control error value, wherein in the candidate queue, the second lateral control error value is ranked adjacent to the first lateral control error value.

[0020] Optionally, the counting of error change values ​​greater than a preset error change threshold to obtain the number of lateral bounces of the vehicle includes:

[0021] In response to obtaining the first error change value, if the absolute value of the first error change value is greater than a preset error change threshold, the number of lateral jumps is increased by one; if the absolute value of the first error change value is less than or equal to the preset error change threshold, the number of lateral jumps is reduced by one, wherein the minimum value of the number of lateral jumps is zero.

[0022] Optionally, the obtaining of the number of track mutations of the vehicle's driving track based on the positioning information of the multiple second time points includes:

[0023] Obtaining a projection trajectory curve of the vehicle on a horizontal plane based on the positioning information of the multiple second time points;

[0024] Obtaining a curvature value at each second time point based on the projection trajectory curve;

[0025] Obtaining curvature change values ​​of any two adjacent second time points based on the curvature values ​​of the plurality of second time points;

[0026] The curvature change values ​​greater than a preset curvature change threshold are counted to obtain the number of track mutations of the vehicle's driving track.

[0027] Optionally, the determining whether the vehicle drifts within a preset detection time period based on the lateral control error values ​​at the multiple first time points includes:

[0028] Obtaining a preset percentile value based on the lateral control error values ​​at the plurality of first time points;

[0029] In response to the preset percentile value being greater than the preset percentile threshold, it is determined that the vehicle drifts within a preset detection time period.

[0030] Optionally, the preset percentile value includes a 90th percentile value or a 99th percentile value.

[0031] Optionally, the preset detection time period includes 1.0 to 2.0 seconds.

[0032] According to a specific embodiment of the present disclosure, in a second aspect, the present disclosure provides a vehicle drift detection device, comprising:

[0033] An obtaining unit, used to obtain lateral control error values ​​of the vehicle at a plurality of first time points within a preset detection time period;

[0034] A determination unit is used to determine whether the vehicle drifts within a preset detection time period based on the lateral control error values ​​at the multiple first time points.

[0035] Optionally, the determining unit includes:

[0036] A first obtaining subunit is used to obtain the positioning information of the vehicle at multiple second time points within a preset detection time period;

[0037] A second obtaining subunit is configured to obtain the number of lateral bounces of the vehicle based on the lateral control error values ​​at the plurality of first time points; and

[0038] A third obtaining subunit, configured to obtain the number of track mutations of the driving track of the vehicle based on the positioning information of the plurality of second time points;

[0039] The first determination subunit is configured to determine that the vehicle has drifted within a preset detection time period in response to a difference between the number of lateral jumps and the number of track mutations being greater than a preset change threshold.

[0040] Optionally, the second obtaining subunit includes:

[0041] A fourth obtaining subunit, configured to obtain an error change value of the lateral control error values ​​at any two adjacent first time points based on the lateral control error values ​​at the multiple first time points;

[0042] The fifth obtaining subunit is used to collect statistics on the error change values ​​that are greater than a preset error change threshold value to obtain the number of lateral bounces of the vehicle.

[0043] Optionally, the fourth obtaining subunit includes:

[0044] An inserting subunit, used to sequentially insert each lateral control error value into the candidate queue according to the time sequence of the first time point corresponding to each lateral control error value;

[0045] A response subunit is used to obtain a first error change value based on the first lateral control error value and a second lateral control error value in response to inserting the first lateral control error value into the candidate queue, wherein, in the candidate queue, the second lateral control error value is ranked adjacent to the first lateral control error value.

[0046] Optionally, the fifth obtaining subunit includes:

[0047] A counting subunit is used for responding to obtaining the first error change value. If the absolute value of the first error change value is greater than a preset error change threshold, the number of lateral jumps is increased by one; if the absolute value of the first error change value is less than or equal to the preset error change threshold, the number of lateral jumps is decreased by one, wherein the minimum value of the number of lateral jumps is zero.

[0048] Optionally, the third obtaining subunit includes:

[0049] a sixth obtaining subunit, configured to obtain a projection trajectory curve of the vehicle on a horizontal plane based on the positioning information of the plurality of second time points;

[0050] a seventh obtaining subunit, configured to obtain a curvature value at each second time point based on the projection trajectory curve;

[0051] an eighth obtaining subunit, configured to obtain curvature change values ​​of any two adjacent second time points based on the curvature values ​​of the plurality of second time points;

[0052] The statistical subunit is used to count the curvature change values ​​greater than a preset curvature change threshold value to obtain the number of track mutations of the vehicle's driving track.

[0053] Optionally, the determining unit includes:

[0054] a ninth obtaining subunit, configured to obtain a preset percentile value based on the lateral control error values ​​at the plurality of first time points;

[0055] The second determination subunit is used to determine that the vehicle drifts within a preset detection time period in response to a preset percentile value being greater than a preset percentile threshold.

[0056] Optionally, the preset percentile value includes a 90th percentile value or a 99th percentile value.

[0057] Optionally, the preset detection time period includes 1.0 to 2.0 seconds.

[0058] Compared with the prior art, the above solution of the embodiment of the present disclosure has at least the following beneficial effects:

[0059] The present disclosure provides a method and device for detecting vehicle drift. The present disclosure utilizes the characteristics that the lateral control error value can sensitively respond to subtle changes in the lateral direction of the vehicle, and utilizes the characteristics that the lateral control error shows abnormal continuous jumps or the statistical percentile value is too large during drift, and determines whether the vehicle is drifting by using multiple lateral control error values ​​within a preset detection time period. In a short period of time, it can capture both large drifts of the vehicle and slow and small drifts of the vehicle. It helps the vehicle to automatically take measures to control the vehicle's posture in a timely manner, ensuring the safety of the vehicle's driving. It does not rely on point cloud matching, has a small amount of calculation, and improves detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A flow chart of a method for detecting vehicle drift according to an embodiment of the present disclosure is shown;

[0061] Figure 2 A unit block diagram of a vehicle drift detection device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the present disclosure will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0063] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments, and are not intended to limit the present disclosure. The singular forms "a", "said" and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0064] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0065] It should be understood that although the terms first, second, third, etc. may be used to describe in the disclosed embodiments, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the disclosed embodiments, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0066] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0067] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the commodity or device including the elements.

[0068] It should be particularly noted that any symbols and / or numbers in the specification that are not marked in the accompanying drawings are not drawing marks.

[0069] The optional embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0070] Example 1

[0071] The present disclosure provides an embodiment, that is, an embodiment of a method for detecting vehicle drift.

[0072] Combine the following Figure 1 The embodiments of the present disclosure are described in detail.

[0073] Step S101, obtaining lateral control error values ​​of the vehicle at multiple first time points within a preset detection time period.

[0074] The lateral control error value refers to the deviation between the vehicle position and the expected position. For example, the vehicle is currently at x=1, and it should actually be at x=1.1 at the next moment. However, after positioning drift, the vehicle thinks it is at x=3. This position change that violates the characteristics of the vehicle itself will definitely be reflected in the changing trend of the lateral control error. Any vehicle must have a lateral control error value during driving, and the deviation needs to be eliminated by controlling the throttle and steering wheel of the vehicle. The lateral control error value of the vehicle is usually calculated based on the actual posture of the vehicle and the posture of the reference point. The embodiment of the present disclosure sets multiple first time points within a preset detection time period, and obtains a lateral control error value at each first time point. The lateral control error value can sensitively respond to subtle changes in the lateral direction of the vehicle. The lateral control error value may be caused by passive factors (such as icy road surface) or human factors.

[0075] The method described in the embodiment of the present disclosure can be applied to a vehicle that is in motion to detect the drift of the vehicle in real time. When the vehicle is in motion, a lateral control error value detected in a preset detection time period can be obtained every detection cycle. For example, if the detection cycle is 1 second, the vehicle obtains a lateral control error value detected in a preset detection time period immediately before the current time point every 1 second.

[0076] It can also be used to analyze the drift of the vehicle after the vehicle is driven. The lateral control error value detected in a preset detection time period can be obtained according to the detection cycle, or several target preset detection time periods can be selected to obtain the lateral control error value detected in each target preset detection time period.

[0077] The interval time period of the detection cycle may be less than or equal to the preset detection time period, or may be greater than the preset detection time period. Optionally, the preset detection time period includes 1.0 to 2.0 seconds, so as to achieve a real-time detection effect.

[0078] Step S102: determining whether the vehicle drifts within a preset detection time period based on the lateral control error values ​​at the multiple first time points.

[0079] Drifting refers to a large angle between the direction of the front of the vehicle and the actual direction of movement of the vehicle body, causing the vehicle body to slide sideways. Drifting is often caused by passive, non-human factors. Usually, when a vehicle is driving on the road, severe drifting often causes the vehicle to slide out of the normal driving lane, leading to an accident.

[0080] The disclosed embodiment utilizes the difference in lateral control error values ​​during the vehicle's straight-line driving and curve driving to determine whether the vehicle is drifting.

[0081] In a specific embodiment, the determining whether the vehicle drifts within a preset detection time period based on the lateral control error values ​​at the multiple first time points comprises the following steps:

[0082] Step S102a-1, obtaining the positioning information of the vehicle at multiple second time points within a preset detection time period.

[0083] The embodiment of the present disclosure sets a plurality of second time points within a preset detection time period, and obtains positioning information at each second time point.

[0084] It can be understood that the vehicle detects multiple lateral control error values ​​in real time within a preset detection time period, and at the same time, also detects multiple positioning information of the vehicle in real time. The number of multiple first time points can be the same as the number of multiple second time points, or the first time point and the second time point can be the same time point or different time points. The number of multiple first time points can also be different from the number of multiple second time points. This is not limited in the embodiments of the present disclosure.

[0085] Step S102a-2, obtaining the number of lateral jumps of the vehicle based on the lateral control error values ​​at the multiple first time points, and obtaining the number of trajectory mutations of the vehicle's driving trajectory based on the positioning information at the multiple second time points.

[0086] Lateral jump refers to a sudden change in the lateral control error value of the vehicle during driving. The number of lateral jumps refers to the number of lateral jumps. This lateral jump may be caused by drift or by changes in the turning angle of the vehicle due to unexpected factors during driving. The embodiment of the present disclosure is to eliminate the interference of unexpected factors.

[0087] In a specific embodiment, obtaining the number of lateral bounces of the vehicle based on the lateral control error values ​​at the multiple first time points comprises the following steps:

[0088] Step S102a-2a-1, obtaining an error change value of the lateral control error values ​​at any two adjacent first time points based on the lateral control error values ​​at the multiple first time points.

[0089] The error change value includes the error change difference or the error change rate. Error change difference = A m -A n , or the error change difference = A n -A m ; Error change rate = (A m -A n ) / A n , or error change rate = (A m -A n ) / A m, or error change rate = (A n -A m ) / A n , or error change rate = (A n -A m ) / A m Among them, A n The first time point corresponding to A m The corresponding first time point.

[0090] For example, there are 7 sequentially arranged first time points within the preset detection time period. If the lateral control error value of each first time point is 8, 7, 6, 11, 8.2, 7 and 8.6 respectively, then the lateral control error values ​​of two adjacent first time points are (8, 7), (7, 6), (6, 11), (11, 8.2), (8.2, 7) and (7, 8.6) respectively; the corresponding error change values ​​are 1, 1, -5, 2.8, 1.2, -1.6 respectively.

[0091] In a specific embodiment, obtaining the error change value of the lateral control error values ​​of any two adjacent first time points based on the lateral control error values ​​of the multiple first time points comprises the following steps:

[0092] Step S102a-2a-1-1, inserting each lateral control error value into the candidate queue in sequence according to the time sequence of the first time point corresponding to each lateral control error value.

[0093] The candidate queue is a special linear list. The special thing is that it only allows deletion operations at the front end of the list and insertion operations at the back end of the list. It performs the "first in, first out" operation like a stack. The queue is a linear list with restricted operations. The end where the insertion operation is performed is called the tail of the queue, and the end where the deletion operation is performed is called the head of the queue. For example, the length of the preset detection time period is 1.0 second, and the lateral control error value is obtained every 0.01 seconds. The candidate queue can save 100 lateral control error values; whenever a new lateral control error value is obtained, the lateral control error value at the head of the queue is deleted, and the new lateral control error value is inserted at the end of the queue. In this way, 100 lateral control error values ​​are always saved in the candidate queue.

[0094] Step S102a-2a-1-2, in response to inserting a first lateral control error value into the candidate queue, obtaining a first error change value based on the first lateral control error value and the second lateral control error value.

[0095] Among them, in the candidate queue, the second lateral control error value is arranged in a position adjacent to the first lateral control error value. For example, in the candidate queue, A1, A2, A3, ..., A98, A99, A100, a total of 100 lateral control error values ​​are stored. When a new lateral control error value A101 is obtained, A1 at the head of the candidate queue is deleted, and then A101 is inserted into the candidate queue. Since A100 is arranged in a position adjacent to A101 in the candidate queue, the first error change value between A100 and A101 is calculated.

[0096] The first error change value includes an error change difference or an error change rate. For example, continuing the above example, the error change difference = A100-A101, or the error change difference = A101-A100; the error change rate = (A100-A101) / A100, or the error change rate = (A100-A101) / A101, or the error change rate = (A101-A100) / A100, or the error change rate = (A101-A100) / A100.

[0097] In this specific embodiment, an error change value is calculated each time a new lateral control error value is inserted into the candidate queue, so that the error change values ​​of all lateral control error values ​​in the candidate queue can be obtained during the insertion process. Of course, when a lateral control error value in the candidate queue is deleted, the error change value related to the deleted lateral control error value is also discarded.

[0098] Step S102a-2a-2, counting the error change values ​​that are greater than a preset error change threshold, and obtaining the number of lateral bounces of the vehicle.

[0099] Specifically, after obtaining the first lateral control error value, performing an error change value operation with the second lateral control error value in the candidate queue to obtain the first error change value, counting the error change values ​​greater than a preset error change threshold to obtain the number of lateral bounces of the vehicle, includes the following steps:

[0100] Step S102a-2a-2-1, in response to obtaining the first error change value, if the absolute value of the first error change value is greater than the preset error change threshold, the number of lateral jumps is increased by one; if the absolute value of the first error change value is less than or equal to the preset error change threshold, the number of lateral jumps is reduced by one.

[0101] The minimum value of the lateral jump times is zero.

[0102] For example, the preset error change threshold is 3, and the initial value of the lateral jump number is zero; the first error change values ​​are: 1, 1, -5, 2.8, 1.2, -1.6; when the first 1 is obtained, the lateral jump number is zero; when the second 1 is obtained, the lateral jump number is zero; when -5 is obtained, the lateral jump number is 1; when 2.8 is obtained, the lateral jump number is zero; when 1.2 is obtained, the lateral jump number is zero; when -1.6 is obtained, the lateral jump number is zero.

[0103] The above step S102a-2a-2-1 excludes the pseudo lateral control error value from the range of statistical data related to drift by means of numerical statistics. Only when a large number of absolute values ​​of the first error change values ​​are obtained in a short period of time and are greater than the preset error change threshold, can the statistical data be determined as the basis for judging whether drift occurs, thereby ensuring the accuracy of the drift result.

[0104] The track mutation refers to a sudden change in the driving track of the vehicle during the driving process.

[0105] The number of trajectory mutations refers to the number of times the trajectory mutates.

[0106] In another specific embodiment, obtaining the number of track mutations of the vehicle's driving track based on the positioning information of the multiple second time points comprises the following steps:

[0107] Step S102a-2b-1, obtaining a projection trajectory curve of the vehicle on a horizontal plane based on the positioning information of the multiple second time points.

[0108] The vehicle positioning information is the three-dimensional position information in a preset three-dimensional coordinate system obtained by the vehicle fusion positioning system. In order to facilitate calculation, the embodiment of the present disclosure projects the positioning information onto any horizontal plane in the preset three-dimensional coordinate system, connects the projected position information of the positioning information according to the order in which the positioning information is obtained, and generates a projection trajectory curve.

[0109] Step S102a-2b-2, obtaining the curvature value of each second time point based on the projection trajectory curve.

[0110] The curvature of a curve is the rotation rate of the tangent direction angle to the arc length at a certain point on the curve. It is defined by differentiation and indicates the degree to which the curve deviates from a straight line. Mathematically, it is a numerical value indicating the degree of curvature of a curve at a certain point. It can be understood as the angle at which the vehicle body swings between two adjacent second time points on the driving trajectory. The greater the curvature, the greater the curvature of the curve. The process of obtaining the curvature value of each second time point by projecting the trajectory curve is not described in detail in this embodiment, and can be implemented with reference to various implementation methods in the prior art.

[0111] Step S102a-2b-3, obtaining the curvature change values ​​of any two adjacent second time points based on the curvature values ​​of multiple second time points.

[0112] The curvature change value includes the curvature error change difference or the curvature error change rate. For example, the curvature error change difference = C i -C j , or curvature error change difference = C j -C i ; Curvature error change rate = (C i -C j ) / C i , or the curvature error change rate = (C i -C j ) / C i , or the curvature error change rate = (C j -C i ) / C j , or the curvature error change rate = (C j -C i ) / C j , where C i The corresponding second time point is adjacent to C j The corresponding second time point.

[0113] Step S102a-2b-4, counting the curvature change values ​​greater than a preset curvature change threshold, and obtaining the number of track mutations of the vehicle's driving track.

[0114] When the curvature change value is greater than the preset curvature change threshold, it can be determined that the vehicle's trajectory has undergone a sudden change during driving, which can be understood as artificially causing the driving trajectory to undergo a sudden change. The purpose of counting the number of trajectory mutations is to eliminate the human factor in the lateral control error value.

[0115] This specific embodiment uses the vehicle's driving trajectory as a reference for determining whether drift occurs, and takes advantage of the fact that the vehicle's driving trajectory changes slowly when the vehicle's posture changes. As a reference, the detection can capture small drifts, thereby improving the sensitivity of the detection.

[0116] Step S102a-3, in response to the difference between the number of lateral jumps and the number of trajectory mutations being greater than a preset change threshold, determining that the vehicle drifts within a preset detection time period.

[0117] Since the number of lateral jumps includes the number of passive lateral jumps caused by passive factors and the number of active lateral jumps caused by human factors, the disclosed embodiment excludes the number of active lateral jumps from the number of lateral jumps by using the number of trajectory mutations. When the number of passive lateral jumps is greater than the preset change threshold, it is determined that the vehicle has drifted. Otherwise, it is determined that the vehicle has not drifted.

[0118] In a specific embodiment, the determining whether the vehicle drifts within a preset detection time period based on the lateral control error values ​​at the multiple first time points comprises the following steps:

[0119] Step S102b-1, obtaining a preset percentile value based on the lateral control error values ​​at the multiple first time points.

[0120] Percentile is one of the characteristic numbers of random variables. Divide the area enclosed by the random variable distribution curve and the X-axis into n equal parts, and get n-1 values ​​(X1, X2, ..., Xn-1), which are called n-percentile values. It can be understood that if there are 100 values, arranged from small to large, the 10th value is the 10th percentile value, the 50th value is the 50th percentile value, also called the median value, the 90th value is the 90th percentile value, and the 99th value is the 99th percentile value. Compared with the average value, the percentile value can better explain the arrangement pattern. If 99 values ​​are 1 and 1 value is 10000, the average is 100, and the median is 1. Because the 50th value is 1. Percentile values ​​will not cause numerical deviations due to individual extreme values. For example, 8, 7, 6, 11, 8.2, 7 and 8.6, a total of 7 lateral control error values ​​arranged in the order of the first time point, are sorted by size: 6, 7, 7, 8, 8.2, 8.6, 11.

[0121] Optionally, the preset percentile value includes a 90th percentile value or a 99th percentile value. The larger the preset percentile value, the more accurate the drift detection is.

[0122] Step S102b-2, in response to the preset percentile value being greater than the preset percentile threshold, determining that the vehicle drifts within a preset detection time period.

[0123] For example, continuing the above example, the multiple quantile values ​​are: 6, 7, 7, 8, 8.2, 8.6, 11, where the quantile value is 8; if the preset equal division threshold is 7.6, it means that 50% of the data in the multiple quantile values ​​are beyond the normal driving range, then it is determined that the vehicle has drifted within the preset detection time period. Otherwise, it is determined that the vehicle has not drifted within the preset detection time period.

[0124] This specific embodiment utilizes the quantile values ​​of multiple lateral control error values ​​within a preset detection time period, which can quickly determine whether the vehicle has drifted, thereby improving detection efficiency. In addition, the flexibility of detection can be improved by requiring various equally divided quantile values.

[0125] The disclosed embodiment utilizes the characteristics that the lateral control error value can sensitively respond to the subtle changes in the lateral direction of the vehicle, and utilizes the characteristics that the lateral control error shows abnormal continuous jumps or the statistical percentile value is too large during drift, and determines whether the vehicle is drifting through multiple lateral control error values ​​within a preset detection time period. In a short period of time, it can capture both large drifts of the vehicle and slow and small drifts of the vehicle. It helps the vehicle to take timely and automatic measures to control the vehicle's posture, ensuring the safety of the vehicle's driving. It does not rely on point cloud matching, has a small amount of calculation, and improves detection efficiency.

[0126] Example 2

[0127] The present disclosure also provides an apparatus embodiment that is consistent with the above-mentioned embodiment, and is used to implement the method steps described in the above-mentioned embodiment. The explanation based on the same name meaning is the same as that of the above-mentioned embodiment, and has the same technical effect as that of the above-mentioned embodiment, and will not be repeated here.

[0128] like Figure 2 As shown, the present disclosure provides a vehicle drift detection device 200, comprising:

[0129] An obtaining unit 201 is used to obtain lateral control error values ​​of the vehicle at a plurality of first time points within a preset detection time period;

[0130] The determination unit 202 is configured to determine whether the vehicle drifts within a preset detection time period based on the lateral control error values ​​at the multiple first time points.

[0131] Optionally, the determining unit 202 includes:

[0132] A first obtaining subunit is used to obtain the positioning information of the vehicle at multiple second time points within a preset detection time period;

[0133] A second obtaining subunit is configured to obtain the number of lateral bounces of the vehicle based on the lateral control error values ​​at the plurality of first time points; and

[0134] A third obtaining subunit, configured to obtain the number of track mutations of the driving track of the vehicle based on the positioning information of the plurality of second time points;

[0135] The first determination subunit is configured to determine that the vehicle has drifted within a preset detection time period in response to a difference between the number of lateral jumps and the number of track mutations being greater than a preset change threshold.

[0136] Optionally, the second obtaining subunit includes:

[0137] A fourth obtaining subunit, configured to obtain an error change value of the lateral control error values ​​at any two adjacent first time points based on the lateral control error values ​​at the multiple first time points;

[0138] The fifth obtaining subunit is used to collect statistics on the error change values ​​that are greater than a preset error change threshold value to obtain the number of lateral bounces of the vehicle.

[0139] Optionally, the fourth obtaining subunit includes:

[0140] An inserting subunit, used to sequentially insert each lateral control error value into the candidate queue according to the time sequence of the first time point corresponding to each lateral control error value;

[0141] A response subunit is used to obtain a first error change value based on the first lateral control error value and a second lateral control error value in response to inserting the first lateral control error value into the candidate queue, wherein, in the candidate queue, the second lateral control error value is ranked adjacent to the first lateral control error value.

[0142] Optionally, the fifth obtaining subunit includes:

[0143] A counting subunit is used for responding to obtaining the first error change value. If the absolute value of the first error change value is greater than a preset error change threshold, the number of lateral jumps is increased by one; if the absolute value of the first error change value is less than or equal to the preset error change threshold, the number of lateral jumps is decreased by one, wherein the minimum value of the number of lateral jumps is zero.

[0144] Optionally, the third obtaining subunit includes:

[0145] a sixth obtaining subunit, configured to obtain a projection trajectory curve of the vehicle on a horizontal plane based on the positioning information of the plurality of second time points;

[0146] a seventh obtaining subunit, configured to obtain a curvature value at each second time point based on the projection trajectory curve;

[0147] an eighth obtaining subunit, configured to obtain curvature change values ​​of any two adjacent second time points based on the curvature values ​​of the plurality of second time points;

[0148] The statistical subunit is used to count the curvature change values ​​greater than a preset curvature change threshold value to obtain the number of track mutations of the vehicle's driving track.

[0149] Optionally, the determining unit 202 includes:

[0150] a ninth obtaining subunit, configured to obtain a preset percentile value based on the lateral control error values ​​at the plurality of first time points;

[0151] The second determination subunit is used to determine that the vehicle drifts within a preset detection time period in response to a preset percentile value being greater than a preset percentile threshold.

[0152] Optionally, the preset percentile value includes a 90th percentile value or a 99th percentile value.

[0153] Optionally, the preset detection time period includes 1.0 to 2.0 seconds.

[0154] The disclosed embodiment utilizes the characteristics that the lateral control error value can sensitively respond to the subtle changes in the lateral direction of the vehicle, and utilizes the characteristics that the lateral control error shows abnormal continuous jumps or the statistical percentile value is too large during drift, and determines whether the vehicle is drifting through multiple lateral control error values ​​within a preset detection time period. In a short period of time, it can capture both large drifts of the vehicle and slow and small drifts of the vehicle. It helps the vehicle to take timely and automatic measures to control the vehicle's posture, ensuring the safety of the vehicle's driving. It does not rely on point cloud matching, has a small amount of calculation, and improves detection efficiency.

[0155] Finally, it should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the system or device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0156] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A method for detecting vehicle drift, characterized in that: include: Obtaining lateral control error values ​​of the vehicle at multiple first time points within a preset detection time period; Determining whether the vehicle drifts within a preset detection time period based on the lateral control error values ​​at the multiple first time points; The determining whether the vehicle drifts within a preset detection time period based on the lateral control error values ​​at the multiple first time points includes: Obtaining the positioning information of the vehicle at multiple second time points within a preset detection time period; obtaining the number of lateral bounces of the vehicle based on the lateral control error values ​​at the plurality of first time points, and, Obtaining the number of track mutations of the vehicle's driving track based on the positioning information of the multiple second time points; In response to a difference between the number of lateral jumps and the number of track mutations being greater than a preset change threshold, determining that the vehicle has drifted within a preset detection time period; The obtaining the number of lateral bounces of the vehicle based on the lateral control error values ​​at the multiple first time points includes: Obtaining error change values ​​of lateral control error values ​​of any two adjacent first time points based on the multiple lateral control error values ​​at the first time points; The error change values ​​greater than a preset error change threshold are counted to obtain the number of lateral bounces of the vehicle.

2. The method according to claim 1, characterized in that The step of obtaining the error change value of the lateral control error values ​​of any two adjacent first time points based on the lateral control error values ​​of the multiple first time points includes: Insert them into the candidate queue in sequence according to the time sequence of the first time point corresponding to each lateral control error value; In response to inserting a first lateral control error value into the candidate queue, a first error change value is obtained based on the first lateral control error value and a second lateral control error value, wherein in the candidate queue, the second lateral control error value is ranked adjacent to the first lateral control error value.

3. The method according to claim 2, characterized in that The step of counting the error change values ​​greater than a preset error change threshold to obtain the number of lateral bounces of the vehicle includes: In response to obtaining the first error change value, if the absolute value of the first error change value is greater than a preset error change threshold, the number of lateral jumps is increased by one; if the absolute value of the first error change value is less than or equal to the preset error change threshold, the number of lateral jumps is reduced by one, wherein the minimum value of the number of lateral jumps is zero.

4. The method according to claim 1, characterized in that: The obtaining the number of track mutations of the vehicle's driving track based on the positioning information of the plurality of second time points includes: Obtaining a projection trajectory curve of the vehicle on a horizontal plane based on the positioning information of the multiple second time points; Obtaining a curvature value at each second time point based on the projection trajectory curve; Obtaining curvature change values ​​of any two adjacent second time points based on the curvature values ​​of the plurality of second time points; The curvature change values ​​greater than a preset curvature change threshold are counted to obtain the number of track mutations of the vehicle's driving track.

5. The method according to claim 1, characterized in that The determining whether the vehicle drifts within a preset detection time period based on the lateral control error values ​​at the multiple first time points includes: Obtaining a preset percentile value based on the lateral control error values ​​at the plurality of first time points; In response to the preset percentile value being greater than the preset percentile threshold, it is determined that the vehicle drifts within a preset detection time period.

6. The method according to claim 5, characterized in that The preset percentile value includes a 90th percentile value or a 99th percentile value.

7. The method according to claim 1, characterized in that The preset detection time period includes 1.0 to 2.0 seconds.

8. A vehicle drift detection device, characterized in that: include: An obtaining unit, used to obtain lateral control error values ​​of the vehicle at a plurality of first time points within a preset detection time period; a determination unit, configured to determine whether the vehicle drifts within a preset detection time period based on the lateral control error values ​​at the plurality of first time points; The determining whether the vehicle drifts within a preset detection time period based on the lateral control error values ​​at the multiple first time points includes: Obtaining the positioning information of the vehicle at multiple second time points within a preset detection time period; obtaining the number of lateral bounces of the vehicle based on the lateral control error values ​​at the plurality of first time points, and, Obtaining the number of track mutations of the vehicle's driving track based on the positioning information of the multiple second time points; In response to a difference between the number of lateral jumps and the number of track mutations being greater than a preset change threshold, determining that the vehicle has drifted within a preset detection time period; The obtaining the number of lateral bounces of the vehicle based on the lateral control error values ​​at the multiple first time points includes: Obtaining error change values ​​of lateral control error values ​​of any two adjacent first time points based on the multiple lateral control error values ​​at the first time points; The error change values ​​greater than a preset error change threshold are counted to obtain the number of lateral bounces of the vehicle.

Images