Vehicle control method, device and vehicle

Abstract

The present disclosure provides a vehicle control method, device and vehicle, and relates to the field of automatic driving technology. The method comprises: acquiring current status information of the vehicle, the status information comprising position information and posture information; determining a preview tracking point from a plurality of path points of a target path to be tracked by the vehicle according to reference information, the reference information comprising a preview time; determining a first turning angle and a second turning angle of a front wheel of the vehicle according to the position information and the posture information, the first turning angle being used to eliminate a distance error between the vehicle and the preview tracking point, and the second turning angle being used to eliminate a heading error between the vehicle and the preview tracking point; performing weighted calculation on the first turning angle and the second turning angle to determine a target turning angle for controlling the front wheel, the minimum distance among a plurality of distances between the vehicle and a plurality of path points being the first distance, and when the first distance is within a preset distance range, at least one parameter in the weight corresponding to the preview time and the first turning angle is positively correlated with the first distance.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, and in particular to a vehicle control method, device and vehicle. Background Art

[0002] In recent years, due to various advantages, the autonomous driving technology for vehicles, especially for various off-road vehicles, is developing rapidly. For example, applying autonomous driving technology to agricultural vehicles can reduce the intensity of manual labor and improve the quality of operation and land utilization. Summary of the invention

[0003] According to one aspect of an embodiment of the present disclosure, a vehicle control method is provided, comprising: acquiring current state information of the vehicle, the state information comprising position information and posture information; determining a preview tracking point from a plurality of path points of a target path to be tracked by the vehicle according to reference information, the reference information comprising a preview time; determining a first turning angle and a second turning angle of a front wheel of the vehicle according to the position information and the posture information, the first turning angle being used to eliminate a distance error between the vehicle and the preview tracking point, and the second turning angle being used to eliminate a heading error between the vehicle and the preview tracking point; and performing weighted calculation on the first turning angle and the second turning angle to determine a target turning angle for controlling the front wheel, wherein a minimum distance among a plurality of distances between the vehicle and the plurality of path points is a first distance, and when the first distance is within a preset distance range, at least one parameter in the weight corresponding to the preview time and the first turning angle is positively correlated with the first distance.

[0004] In some embodiments, the weight corresponding to the second turning angle is negatively correlated with the weight corresponding to the first turning angle.

[0005] In some embodiments, the sum of the weight corresponding to the second angle and the weight corresponding to the first angle is equal to 1.

[0006] In some embodiments, when the first distance is within the preset distance range, each of the at least one parameter varies within the preset parameter range; when the first distance is greater than or equal to the upper limit of the preset distance range, each of the at least one parameter is equal to the upper limit of the preset parameter range; and when the first distance is less than or equal to the lower limit of the preset distance range, each of the at least one parameter is equal to the lower limit of the preset parameter range.

[0007] In some embodiments, the method further includes: determining a proportional coefficient that varies within a preset coefficient range based on the first distance, each parameter of the at least one parameter being positively correlated with the proportional coefficient; wherein, when the first distance is within the preset distance range, the proportional coefficient is positively correlated with the first distance; when the first distance is greater than or equal to the upper limit of the preset distance range, the proportional coefficient is equal to the upper limit of the preset coefficient range; and when the first distance is less than or equal to the lower limit of the preset distance range, the proportional coefficient is equal to the lower limit of the preset coefficient range.

[0008] In some embodiments, the lower limit of the preset coefficient range is 0, and the upper limit of the preset coefficient range is 1.

[0009] In some embodiments, when the first distance is within the preset distance range, the proportionality coefficient is equal to the ratio of the first distance to an upper limit of the preset distance range.

[0010] In some embodiments, when the first distance is within the preset distance range, each parameter of the at least one parameter is linearly correlated with the first distance.

[0011] According to another aspect of an embodiment of the present disclosure, a vehicle control method is provided, comprising: acquiring current status information of the vehicle, the status information comprising position information and posture information; determining a preview tracking point from a plurality of path points of a target path to be tracked by the vehicle according to reference information, the reference information comprising a preview time; and determining a target turning angle for controlling a front wheel of the vehicle according to the position information, the posture information and the preview tracking point, wherein a minimum distance among a plurality of distances between the vehicle and the plurality of path points is a first distance, and when the first distance is within a preset distance range, the preview time is positively correlated with the first distance.

[0012] In some embodiments, the method also includes: determining a trend line reflecting changes in each of a plurality of candidate paths; determining a second distance between the vehicle and the trend line based on the position information; determining an angle between a traveling direction of the vehicle and an extension direction of the trend line based on the posture information; and selecting one from the plurality of candidate paths as the target path based on the second distance and the angle.

[0013] In some embodiments, based on the second distance and the angle, selecting one from the candidate paths as the target path includes: determining a first difference between each candidate path and the vehicle based on the second distance; determining a second difference between each candidate path and the vehicle based on the angle; performing a weighted calculation on the first difference and the second difference to obtain a third difference between each candidate path and the vehicle; and selecting one from the multiple candidate paths as the target path based on the third difference.

[0014] In some embodiments, determining a first difference between each candidate path and the vehicle based on the second distance includes: normalizing the second distance to obtain the first difference.

[0015] In some embodiments, the first difference is Wherein, d2 is the second distance, and W is the reference distance.

[0016] In some embodiments, when the plurality of candidate paths include only two candidate paths whose trend lines are parallel to each other, the reference distance is equal to half of the distance between the trend lines of the two candidate paths.

[0017] In some embodiments, the path point closest to the vehicle on each candidate path is the first path point, and in other cases except for a preset situation, the reference distance is the maximum value of multiple Euclidean distances between the vehicle and multiple first path points of the multiple candidate paths, wherein the preset situation is that the multiple candidate paths only include two candidate paths whose trend lines are parallel to each other.

[0018] In some embodiments, determining the second difference of each candidate path according to the angle includes: normalizing the angle to obtain the second difference.

[0019] In some embodiments, the method further includes: after determining the target path, determining another target path only when a preset condition is met, the preset condition including that the target path is completed or a user instruction is received.

[0020] In some embodiments, the reference information also includes a setting method of the multiple path points, and the setting method includes a first setting method or a second setting method, wherein: in the first setting method, the lengths of the straight line segments between adjacent path points in the multiple path points are the same, and in the second setting method, the lengths of the line segments along the target path between adjacent path points in the multiple path points are the same.

[0021] In some embodiments, the method further comprises: controlling the front wheels of the vehicle to turn at the target turning angle.

[0022] In some embodiments, a first line parallel to a tangent line tangent to the target path at the preview tracking point, a second line perpendicular to the tangent line, and an extension line of the vehicle's travel direction intersect at a first point, and the distance between the first point and the tangent line is a third distance; the first turning angle is equal to arctan(third distance / preview distance); and the second turning angle is equal to the angle between the extension direction of the tangent line and the vehicle's travel direction.

[0023] According to another aspect of an embodiment of the present disclosure, a vehicle control device is provided, comprising: an acquisition module, configured to acquire current state information of the vehicle, the state information comprising position information and posture information; a determination module, configured to determine a preview tracking point from a plurality of path points of a target path to be tracked by the vehicle according to reference information, the reference information comprising a preview time; determine a first turning angle and a second turning angle of a front wheel of the vehicle according to the position information and the posture information, the first turning angle being used to eliminate a distance error between the vehicle and the preview tracking point, and the second turning angle being used to eliminate a heading error between the vehicle and the preview tracking point; and weighted calculation of the first turning angle and the second turning angle being performed to determine a target turning angle for controlling the front wheel, wherein a minimum distance among a plurality of distances between the vehicle and the plurality of path points is a first distance, and when the first distance is within a preset distance range, at least one parameter in the weight corresponding to the preview time and the first turning angle is positively correlated with the first distance.

[0024] According to another aspect of an embodiment of the present disclosure, a control device for a vehicle is provided, comprising: an acquisition module, configured to acquire current status information of the vehicle, the status information including position information and posture information; and a determination module, configured to determine a preview tracking point from multiple path points of a target path to be tracked by the vehicle according to reference information, the reference information including a preview time; and determine a target turning angle for controlling the front wheels according to the position information, the posture information and the preview tracking point, wherein a minimum distance among multiple distances between the vehicle and the multiple path points is a first distance, and when the first distance is within a preset distance range, the preview time is positively correlated with the first distance.

[0025] According to another aspect of an embodiment of the present disclosure, a control device for a vehicle is provided, comprising: a memory; and a processor coupled to the memory, configured to execute the method described in any one of the above embodiments based on instructions stored in the memory.

[0026] According to another aspect of the embodiments of the present disclosure, a vehicle is provided, comprising: the vehicle control device described in any one of the above embodiments.

[0027] In some embodiments, the vehicle comprises an off-road vehicle.

[0028] In some embodiments, the off-road vehicle comprises an agricultural vehicle.

[0029] According to another aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, comprising computer program instructions, wherein when the computer program instructions are executed by a processor, the method described in any one of the above embodiments is implemented.

[0030] According to another aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method described in any one of the above embodiments is implemented.

[0031] In the disclosed embodiment, the preview tracking point is determined according to the preview time, and the first and second turning angles of the front wheels of the vehicle determined according to the position information and posture information of the vehicle are weighted to determine the target turning angle for controlling the front wheels of the vehicle. If the first distance reflecting the distance error between the vehicle and the target path is within a preset distance range, at least one parameter in the weight corresponding to the preview time and the first turning angle is dynamically adjusted to change positively correlated with the change of the distance error between the vehicle and the target path. In this way, the accuracy of path tracking can be improved.

[0032] The technical solution of the present disclosure is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 is a flow chart of a vehicle control method according to some embodiments of the present disclosure;

[0035] Figure 2 is a schematic diagram of a plurality of waypoints of a vehicle and a target path according to some embodiments of the present disclosure;

[0036] Figure 3 is a flowchart of a vehicle control method according to other embodiments of the present disclosure;

[0037] Figure 4 is a flowchart of determining a target path according to some embodiments of the present disclosure;

[0038] Figure 5 is a schematic diagram of a vehicle and a plurality of candidate paths according to some embodiments of the present disclosure;

[0039] Figure 6 is a schematic structural diagram of a vehicle control device according to some embodiments of the present disclosure;

[0040] Figure 7 is a schematic structural diagram of a vehicle control device according to other embodiments of the present disclosure;

[0041] Figure 8 It is a schematic diagram of the structure of a vehicle control device according to some other embodiments of the present disclosure. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0043] Unless specifically stated otherwise, the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0044] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0045] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0046] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0047] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0048] At present, the path tracking accuracy of vehicles during autonomous driving is low. Taking agricultural vehicles as an example, low path tracking accuracy will lead to reduced operation quality of agricultural vehicles and reduced land utilization rate.

[0049] In view of this, the present disclosure provides the following solution, which can improve the accuracy of path tracking.

[0050] Figure 1 is a flowchart of a vehicle control method according to some embodiments of the present disclosure.

[0051] like Figure 1 As shown, the vehicle control method includes steps 102 to 108.

[0052] In step 102, the current status information of the vehicle is obtained.

[0053] Here, the state information includes position information and posture information. In some embodiments, the state information also includes speed information.

[0054] The position information can reflect the current position of the vehicle, and the position of the vehicle can be represented by the position of any component of the vehicle. For example, the position of the vehicle can be represented by the position of the midpoint of the front wheels of the vehicle. The vehicle posture information can reflect the current driving direction of the vehicle.

[0055] In some embodiments, the vehicle may be an off-road vehicle, such as an agricultural vehicle. The agricultural vehicle may include, but is not limited to, a tractor, a rice transplanter, and the like.

[0056] In step 104, a preview tracking point is determined from a plurality of path points of a target path to be tracked by the vehicle according to the reference information.

[0057] Here, the reference information includes the preview time.

[0058] In some embodiments, the reference information also includes a setting method of multiple path points of the target path. That is, according to the setting method of the multiple path points and the preview time, the preview tracking point is determined. The setting method includes a first setting method or a second setting method. The first setting method and the second setting method are respectively introduced below.

[0059] In the first setting mode, the lengths of the straight line segments between adjacent path points in the plurality of path points are the same, that is, the plurality of path points are arranged at equal intervals S.

[0060] In this case, the index value n of the preview tracking point can be calculated according to the following formula (1):

[0061]

[0062] Where v is the speed of the vehicle, t pre is the preview time, and D0 is the minimum preview distance. The minimum preview distance can be set according to actual conditions.

[0063] In the second setting mode, the lengths of the line segments along the target path between adjacent path points in the plurality of path points are the same, that is, when the vehicle speed is constant, the plurality of path points are set at equal time intervals T.

[0064] In this case, the index value n of the preview tracking point can be calculated according to the following formula (2):

[0065]

[0066] In step 106, a first turning angle and a second turning angle of the front wheels of the vehicle are determined based on the position information and the posture information.

[0067] Here, the first turning angle is used to eliminate the distance error between the vehicle and the preview tracking point, and the second turning angle is used to eliminate the heading error between the vehicle and the preview tracking point.

[0068] For example, the distance error and heading error between the vehicle and the preview tracking point. By adjusting the front wheels of the vehicle to rotate at the first turning angle and the second turning angle, the distance error and heading error between the vehicle and the preview tracking point can be eliminated, so that the vehicle can travel to the preview tracking point. Figure 2 The embodiment further illustrates the first corner and the second corner.

[0069] In step 108 , a weighted calculation is performed on the first turning angle and the second turning angle to determine a target turning angle for controlling the front wheels.

[0070] In some embodiments, after determining a target turning angle for controlling the front wheels, the front wheels of the vehicle may be controlled to turn at the target turning angle.

[0071] In some embodiments, the sum of the weight corresponding to the first corner and the weight corresponding to the second corner is not equal to 1. In other embodiments, the sum of the weight corresponding to the first corner and the weight corresponding to the second corner is equal to 1.

[0072] The minimum distance among the multiple distances between the vehicle and the multiple path points is the first distance. In other words, the first distance is the distance between the vehicle and the nearest path point.

[0073] Here, when the first distance is within a preset distance range, at least one parameter of the preview time and the weight corresponding to the first turning angle is positively correlated with the first distance.

[0074] For example, when the first distance is within a preset distance range, at least one parameter of the preview time and the weight corresponding to the first turning angle may be linearly correlated with the first distance.

[0075] It should be understood that the first distance is within the preset distance range, which means that the first distance is greater than or equal to the lower limit of the preset distance range and less than or equal to the upper limit of the preset distance range. For example, the preset distance range may be [0, d ref ],d ref It can be a preset reference distance.

[0076] The larger the first distance is, the larger the distance between the vehicle and the nearest path point is, which indicates that the distance error between the vehicle and the target path is larger. Conversely, the smaller the first distance is, the smaller the distance error between the vehicle and the target path is.

[0077] In some embodiments, when the first distance is within a preset distance range, the preview time is positively correlated with the first distance. In these embodiments, for example, the weight corresponding to the first turning angle may be a fixed preset value.

[0078] When the first distance is within the preset distance range, the greater the distance error between the vehicle and the target path, the longer the preview time; the smaller the distance error between the vehicle and the target path, the shorter the preview time. Compared with a fixed preview time, the preview time is dynamically adjusted to change positively with the change of the distance error between the vehicle and the target path, and the vehicle can accurately drive to the preview tracking point. In this way, the accuracy of path tracking can be improved.

[0079] In other embodiments, when the first distance is within a preset distance range, the weight corresponding to the first turning angle is positively correlated with the first distance. In these embodiments, for example, the preview time may be a fixed preset value.

[0080] When the first distance is within the preset distance range, the greater the distance error between the vehicle and the target path, the greater the weight corresponding to the first turning angle; the smaller the distance error between the vehicle and the target path, the smaller the weight corresponding to the first turning angle. Compared with the fixed weight corresponding to the first turning angle, the weight corresponding to the first turning angle is dynamically adjusted to change positively with the change of the distance error between the vehicle and the target path, so that the vehicle can accurately drive to the preview tracking point. In this way, the accuracy of path tracking can be improved.

[0081] In some other embodiments, when the first distance is within a preset distance range, the preview time and the weights corresponding to the first turning angle are both positively correlated with the first distance.

[0082] Dynamically adjusting the preview time and the weight corresponding to the first turning angle changes positively correlated with the change of the distance error between the vehicle and the target path, so that the vehicle can drive to the preview tracking point more accurately. In this way, the accuracy of path tracking can be further improved.

[0083] In the above embodiment, the preview tracking point is determined according to the preview time, and the first and second turning angles of the front wheels of the vehicle determined according to the position information and posture information of the vehicle are weighted to determine the target turning angle for controlling the front wheels of the vehicle. If the first distance reflecting the distance error between the vehicle and the target path is within a preset distance range, at least one parameter in the weight corresponding to the preview time and the first turning angle is dynamically adjusted to change positively correlated with the change of the distance error between the vehicle and the target path. In this way, the accuracy of path tracking can be improved.

[0084] Taking agricultural machinery vehicles as an example, the operation accuracy of agricultural machinery vehicles is improved as the accuracy of path tracking is improved, which means that the operation quality and land utilization rate of agricultural machinery vehicles are also improved accordingly.

[0085] Combine the following Figure 2 The illustrated embodiment describes a first corner and a second corner. Figure 2 is a schematic diagram of multiple waypoints of a vehicle and a target path according to some embodiments of the present disclosure.

[0086] like Figure 2 As shown, in the same reference coordinate system, point p v (x0, y0, θ0) represents the vehicle, point p i (x i ,y i ,θ i ) represents the path point that is currently closest to the vehicle among multiple path points of the target path (hereinafter referred to as the nearest path point), and point p j (x j ,y j ,θ j ) indicates that the vehicle has passed the preview time t pre The preview tracking point you expect to drive to.

[0087] Specifically, at point p v In (x0, y0, θ0), x0 and y0 represent the position of the vehicle, θ0 represents the direction of travel of the vehicle, and v represents the speed of the vehicle. i (x i ,y i ,θ i ), x i and i represents the position of the nearest path point, θ i represents the extension direction of the tangent line tangent to the target path at the nearest path point, and i represents the index value of the nearest path point. j (x j ,y j ,θ j ), x j and jrepresents the position of the preview tracking point, θ j It represents the extension direction of the tangent line tangent to the target path at the preview tracking point, and j represents the index value of the preview tracking point.

[0088] See also Figure 2 , tangent to the target path at the preview tracking point p j The tangent line l T Parallel to the first line l1, perpendicular to the tangent line l T The second line l2 and the extended line l of the vehicle's traveling direction E Intersect at the first point P1. The first point P1 and the tangent line l T The distance between them is the third distance.

[0089] In these embodiments, the first rotation angle f(d err ) = arctan(d err / d t ), where d err is the third distance, d t is the preview distance. The second turning angle f(θ err ) is equal to the tangent line l that is tangent to the target path at the preview tracking point T The angle between the extension direction and the driving direction of the vehicle.

[0090] The preview distance may be related to the speed of the vehicle. For example, the preview distance may be positively correlated with the speed of the vehicle. For another example, the preview distance may be linearly correlated with the speed of the vehicle. As some implementations, the preview distance is equal to the speed of the vehicle / preset gain factor.

[0091] That is, in these embodiments, the first turning angle and the second turning angle of the vehicle are determined based on the position information, posture information, and speed information of the vehicle.

[0092] The following further describes some examples Figure 1 The vehicle control method shown.

[0093] As described above, in some embodiments, when the first distance is within the preset distance range, the weight corresponding to the first angle is positively correlated with the first distance. In these embodiments, the weight corresponding to the second angle is negatively correlated with the weight corresponding to the first angle. That is, the greater the weight corresponding to the first angle, the smaller the weight corresponding to the second angle.

[0094] As some implementations, the sum of the weight corresponding to the second turning angle and the weight corresponding to the first turning angle is equal to 1. That is, in these implementations, the first turning angle and the second turning angle can be weighted according to the following formula (3) to obtain the target turning angle δ t :

[0095] δ t =ωδ ×f(d err )+(1-ω δ )×f(θ err ) (3)

[0096] Among them, f(d err ) is the first rotation angle, f(θ err ) is the second rotation angle, ω δ is the weight corresponding to the first corner.

[0097] In the above embodiment, when the distance error between the vehicle and the target path is large, the weight corresponding to the first corner is increased and the weight corresponding to the second corner is decreased, which is conducive to quickly eliminating the distance error between the vehicle and the preview tracking point and improving the efficiency of path tracking. Conversely, when the distance error between the vehicle and the target path is small, the weight corresponding to the first corner is decreased and the weight corresponding to the second corner is increased, which is conducive to quickly eliminating the heading error between the vehicle and the preview tracking point and improving the smoothness of path tracking. In this way, a balance between the efficiency and smoothness of path tracking can be achieved while improving the accuracy of path tracking.

[0098] In some embodiments, when the first distance is within a preset distance range, each parameter of at least one of the preview time and the weight corresponding to the first turning angle varies within a preset parameter range.

[0099] In these embodiments, when the first distance is greater than or equal to the upper limit of the preset distance range, each parameter of at least one parameter is equal to the upper limit of the preset parameter range, and when the first distance is less than or equal to the lower limit of the preset distance range, each parameter of at least one parameter is equal to the lower limit of the preset parameter range.

[0100] It should be understood that the preview time and the weight corresponding to the first turning angle may have different preset parameter ranges.

[0101] For example, the preset parameter range of the preview time can be [t min , t max ], t min is the preset minimum preview time, t max is the preset maximum preview time; the preset parameter range of the weight corresponding to the first turning angle can be [ω min ,ω max ],ω min is the minimum weight corresponding to the preset first corner, ω max It is the maximum weight corresponding to the preset first corner.

[0102] As some implementations, a proportional coefficient that changes within a preset coefficient range may also be determined according to the first distance. For example, the preset coefficient range is [0, 1], that is, the lower limit of the preset coefficient range is 0 and the upper limit is 1.

[0103] Specifically, when the first distance is within the preset distance range, the proportional coefficient is positively correlated with the first distance; when the first distance is greater than or equal to the upper limit of the preset distance range, the proportional coefficient is equal to the upper limit of the preset coefficient range; when the first distance is less than or equal to the lower limit of the preset distance range, the proportional coefficient is equal to the lower limit of the preset coefficient range.

[0104] For example, when the first distance is within the preset distance range, the proportional coefficient may be equal to the ratio of the first distance to the upper limit of the preset distance range. That is, the proportional coefficient k may be calculated according to the following formula (4):

[0105]

[0106] Among them, d1 is the first distance, d ref is the upper limit of the preset distance range.

[0107] In these implementations, each parameter of the at least one parameter is positively correlated to the scaling factor.

[0108] For example, the preview time t can be calculated according to the following formula (5): pre :

[0109] t pre =max(t min ,min(t min +k(t max -t min ),t max )) (5)

[0110] For example, the weight ω corresponding to the first turning angle can be calculated according to the following formula (6): δ :

[0111] ω δ =max(ω min ,min(ω min +k(ω max -ω min ),ω max )) (6)

[0112] In the above implementation, the first distance is normalized to obtain a proportionality coefficient, and then the weights corresponding to the preview time and the first turning angle can be determined respectively according to the same proportionality coefficient. In this way, the accuracy of path tracking can be improved while simplifying calculations, reducing processing pressure, and improving the efficiency of determining the target turning angle.

[0113] In some embodiments, after determining the target path, another target path is determined only if a preset condition is met. Here, the preset condition includes the end of the target path or the receipt of a user instruction. For example, the user instruction may instruct the vehicle to stop autonomous driving and be manually taken over, or instruct to switch the target path. In this way, the vehicle can be prevented from frequently switching between different paths during autonomous driving, thereby improving driving safety and improving the efficiency of the vehicle in completing the target path.

[0114] Figure 3 It is a flowchart of a vehicle control method according to other embodiments of the present disclosure.

[0115] like Figure 3 As shown, the vehicle control method may include steps 302 to 306 .

[0116] In step 302, the current status information of the vehicle is obtained.

[0117] Here, the state information includes position information and posture information. In some embodiments, the state information also includes speed information.

[0118] In step 304, a preview tracking point is determined from a plurality of path points of a target path to be tracked by the vehicle according to the reference information.

[0119] Here, the reference information includes the preview time. In some embodiments, the reference information also includes the setting mode of multiple path points of the target path.

[0120] In step 306, a target turning angle for controlling the front wheels is determined based on the position information, the attitude information and the preview tracking point.

[0121] For example, based on the position information, posture information and preview tracking point, a first turning angle for eliminating the distance error between the vehicle and the preview tracking point and a second turning angle for eliminating the heading error between the vehicle and the preview tracking point can be determined, and the first turning angle and the second turning angle are weighted to obtain a target turning angle for controlling the front wheels of the vehicle.

[0122] In some embodiments, the sum of the weight corresponding to the first corner and the weight corresponding to the second corner is not equal to 1.

[0123] In some other embodiments, the sum of the weight corresponding to the first corner and the weight corresponding to the second corner is equal to 1. For example, the weight corresponding to the first corner and the weight corresponding to the second corner are equal, that is, they are respectively equal to 0.5. For another example, the weight corresponding to the first corner and the weight corresponding to the second corner are not equal.

[0124] Here, the minimum distance among the multiple distances between the vehicle and the multiple path points is the first distance. When the first distance is within the preset distance range, the preview time is positively correlated with the first distance.

[0125] In the above embodiment, the preview tracking point is determined according to the preview time, and the target turning angle for controlling the front wheels of the vehicle is determined according to the position information, posture information and preview tracking point of the vehicle. If the first distance reflecting the distance error between the vehicle and the target path is within the preset distance range, the preview time is dynamically adjusted to change positively correlated with the change of the first distance. In this way, the accuracy of path tracking can be improved.

[0126] Figure 3 Other various embodiments of the vehicle control method shown can be found in Figure 1 The relevant embodiments of the vehicle control method shown are not described in detail here.

[0127] exist Figure 1 and Figure 3 In the vehicle control method shown, the target path may be a path specified by a user, or a path automatically determined according to the method of the following embodiment.

[0128] Figure 4 It is a flowchart of determining a target path according to some embodiments of the present disclosure.

[0129] like Figure 4 As shown, the vehicle control method may include steps 402 to 408.

[0130] At step 402 , a trend line reflecting changes in each of a plurality of candidate paths is determined.

[0131] For example, multiple candidate paths may be input by a user, and each candidate path may include multiple discrete path points. The trend line of the candidate path can reflect the change trend of the candidate path as a whole.

[0132] As some implementations, linear fitting may be performed on multiple path points of the candidate path to obtain a trend line of the candidate path.

[0133] As another implementation manner, the line between the starting path point and the ending path point of the candidate path may be used as the trend line of the candidate path.

[0134] In these implementations, the angle θ representing the extension direction of the trend line can be first calculated based on formula (7): L :

[0135]

[0136] Among them, x m andm represents the position of the starting path point of the candidate path, and x1 and y1 represent the position of the ending path point of the candidate path.

[0137] The angle θ representing the extension direction of the trend line is calculated. L After that, the trend line can be expressed as the following expression (8):

[0138]

[0139] Where b is the intercept of the trend line. The intercept can be obtained by substituting the position of the starting path point or the ending path point into formula (8).

[0140] In step 404, a second distance between the vehicle and the trend line is determined based on the current position information of the vehicle.

[0141] For example, the second distance d2 between the vehicle and the trend line can be calculated based on the formula (9) for calculating the distance between a point and a straight line:

[0142]

[0143] Among them, x0 and y0 represent the position of the vehicle.

[0144] In step 406, the angle between the driving direction of the vehicle and the extension direction of the trend line is determined based on the current posture information of the vehicle.

[0145] The angle between the vehicle's direction of travel and the extension direction of the trend line is equal to θ L -θ.

[0146] In step 408, one is selected from the plurality of candidate paths as a target path according to the second distance and the angle.

[0147] It should be understood that the second distance and the angle between the vehicle's traveling direction and the extension direction of the trend line can reflect the difference between the candidate path and the vehicle's posture. For example, the smaller the second distance and the smaller the angle between the vehicle's traveling direction and the extension direction of the trend line, this indicates that the difference between the candidate path and the vehicle's posture is smaller.

[0148] A candidate path with the smallest difference from the vehicle's posture is selected from multiple candidate paths as the target path.

[0149] In the above embodiment, according to the second distance reflecting the distance error between the vehicle and the candidate path and the angle reflecting the heading error between the vehicle and the candidate path, one of the multiple candidate paths is selected as the target path. In this way, a candidate path with the smallest difference between the position and posture of the vehicle can be selected from the multiple candidate paths as the target path, so as to improve the efficiency of the vehicle in completing the target path.

[0150] It should be understood that if there are still multiple candidate paths left after the vehicle completes the target path, Figure 4 The illustrated method continues with determining another target path.

[0151] As some implementations, in step 408, a first difference between each candidate path and the vehicle may be determined based on the second distance, and a second difference between each candidate path and the vehicle may be determined based on the angle between the vehicle's travel direction and the extension direction of the trend line. Then, a weighted calculation may be performed on the first difference and the second difference to obtain a third difference between each candidate path and the vehicle.

[0152] It should be understood that the first difference is positively correlated with the second distance, and the second difference is positively correlated with the included angle.

[0153] In these implementations, one of the plurality of candidate paths may be selected as the target path based on a third difference between each candidate path and the vehicle.

[0154] In the above implementation, the first difference and the second difference between the candidate path and the vehicle are determined according to the second distance and the angle, and then one is selected from the multiple candidate paths as the target path according to the third difference obtained by weighted calculation of the first difference and the second difference. In this way, a candidate path with the smallest difference between the position and posture of the vehicle can be selected from the multiple candidate paths as the target path more accurately, thereby further improving the efficiency of the vehicle in completing the target path.

[0155] In some embodiments, the first difference may be the value of the second distance, and the second difference may be the value of the angle. For example, if the second distance is 80 meters, the first difference is 80. For another example, if the angle between the driving direction of the vehicle and the extension direction of the trend line is 50 degrees, the second difference is 50.

[0156] In some embodiments, the second distance may be normalized to obtain the first difference. In other embodiments, the angle between the driving direction of the vehicle and the extension direction of the trend line may be normalized to obtain the second difference.

[0157] In these embodiments, the second distance and the angle are normalized to obtain the first difference and the second difference between the candidate path and the vehicle, and then one candidate path is selected as the target path according to the third difference obtained by weighted calculation of the first difference and the second difference. In this way, a candidate path with the smallest difference between the position and posture of the vehicle can be selected as the target path from the multiple candidate paths more accurately, thereby further improving the efficiency of the vehicle in completing the target path.

[0158] As some implementations, the first difference between the candidate path and the vehicle is Wherein, d2 is the second distance, and W is the reference distance. As another implementation, the second difference between the candidate path and the vehicle is

[0159] In these implementations, for example, the first difference and the second difference may be weighted based on the following formula (10) to obtain the third difference C:

[0160]

[0161] Among them, ω c is the weight corresponding to the second difference.

[0162] The inventors have noticed that, in different situations, using different reference distances to normalize the second distance helps to accurately select a candidate path with the smallest difference from the vehicle's posture from multiple candidate paths as the target path.

[0163] In some embodiments, the plurality of candidate paths includes only two candidate paths whose trend lines are parallel to each other.

[0164] See also Figure 5 , the multiple candidate paths include two candidate paths (candidate path 1 and candidate path 2) whose trend lines (L1 and L2) are parallel to each other.

[0165] In this case, the base distance is equal to one-half the distance between the trend lines of the two candidate paths.

[0166] In other embodiments, the path point closest to the vehicle on each candidate path is the first path point (i.e., the nearest path point). In other cases except for the preset case, the reference distance is the maximum value of multiple Euclidean distances between the vehicle and multiple first path points of multiple candidate paths.

[0167] Here, the preset situation is that the multiple candidate paths only include two candidate paths whose trend lines are parallel to each other. In other words, other situations besides the preset situation may include, for example, the multiple candidate paths only include two candidate paths whose trend lines are not parallel to each other, the multiple candidate paths include more than two candidate paths, etc.

[0168] In this way, the second distance can be normalized based on a suitable reference distance to obtain a first difference, so that a candidate path with the smallest difference with the vehicle's posture can be accurately selected from multiple candidate paths as the target path based on the first difference, thereby helping to improve the efficiency of the vehicle in completing the target path.

[0169] Figure 6is a schematic diagram of the structure of a vehicle control device according to some embodiments of the present disclosure.

[0170] like Figure 6 As shown, the vehicle control device 600 includes an acquisition module 601 and a determination module 602 .

[0171] The acquisition module 601 is configured to acquire the current state information of the vehicle. The state information includes position information and posture information.

[0172] The determination module 602 is configured to determine the preview tracking point from a plurality of path points of a target path to be tracked by the vehicle according to the reference information; determine the first turning angle and the second turning angle of the front wheel of the vehicle according to the position information and the posture information; and perform weighted calculation on the first turning angle and the second turning angle to determine the target turning angle for controlling the front wheel. Here, the reference information includes the preview time. The first turning angle is used to eliminate the distance error between the vehicle and the preview tracking point, and the second turning angle is used to eliminate the heading error between the vehicle and the preview tracking point.

[0173] The minimum distance among the multiple distances between the vehicle and the multiple path points is the first distance. When the first distance is within the preset distance range, at least one parameter of the preview time and the weight corresponding to the first turning angle is positively correlated with the first distance.

[0174] It should be understood that the vehicle control device 600 may also include various other modules to perform Figure 1 And a vehicle control method of a related embodiment.

[0175] Figure 7 It is a schematic diagram of the structure of a vehicle control device according to other embodiments of the present disclosure.

[0176] like Figure 7 As shown, the vehicle control device 700 includes an acquisition module 701 and a determination module 702 .

[0177] The acquisition module 701 is configured to acquire the current state information of the vehicle. The state information includes position information and posture information.

[0178] The determination module 702 is configured to determine a preview tracking point from a plurality of path points of a target path to be tracked by the vehicle according to the reference information; and determine a target turning angle for controlling the front wheel according to the position information, the posture information and the preview tracking point. Here, the reference information includes the preview time, and the minimum distance among the plurality of distances between the vehicle and the plurality of path points is the first distance.

[0179] When the first distance is within a preset distance range, the preview time is positively correlated with the first distance.

[0180] It should be understood that the vehicle control device 700 may also include various other modules to perform Figure 3 And a vehicle control method of a related embodiment.

[0181] Figure 8 It is a schematic diagram of the structure of a vehicle control device according to some other embodiments of the present disclosure.

[0182] like Figure 8 As shown, the control device 800 of the vehicle includes a memory 801 and a processor 802 coupled to the memory 801 , and the processor 802 is configured to execute the method of any one of the above embodiments based on the instructions stored in the memory 801 .

[0183] The memory 801 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs.

[0184] The vehicle control device 800 may also include an input / output interface 803, a network interface 804, a storage interface 805, etc. These interfaces 803, 804, 805, and the memory 801 and the processor 802 may be connected, for example, via a bus 806. The input / output interface 803 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 804 provides a connection interface for various networked devices. The storage interface 805 provides a connection interface for external storage devices such as an SD card and a USB flash drive.

[0185] The disclosed embodiments further provide a vehicle, comprising the vehicle control device of any one of the above embodiments (eg, the vehicle control device 600, 700 or 800). In some embodiments, the vehicle is a non-road vehicle, such as an agricultural vehicle.

[0186] The embodiments of the present disclosure further provide a computer-readable storage medium, comprising computer program instructions, which implement the method of any one of the above embodiments when executed by a processor.

[0187] The embodiments of the present disclosure further provide a computer program product, including a computer program, which implements the method of any one of the above embodiments when executed by a processor.

[0188] So far, various embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0189] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the embodiments of the device and the vehicle, since they basically correspond to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0190] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0191] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present disclosure. It should be understood that the functions specified in one or more processes in the flowchart and / or one or more blocks in the block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the functions specified in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0192] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0193] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0194] Although some specific embodiments of the present disclosure have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified or some technical features may be replaced by equivalents without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A vehicle control method, comprising: Acquire current status information of the vehicle, wherein the status information includes position information and posture information; Determining a preview tracking point from a plurality of path points of a target path to be tracked by the vehicle according to reference information, wherein the reference information includes a preview time; Determine a first turning angle and a second turning angle of the front wheels of the vehicle according to the position information and the posture information, wherein the first turning angle is used to eliminate a distance error between the vehicle and the preview tracking point, and the second turning angle is used to eliminate a heading error between the vehicle and the preview tracking point; as well as performing a weighted calculation on the first turning angle and the second turning angle to determine a target turning angle for controlling the front wheel, Among them, the minimum distance among the multiple distances between the vehicle and the multiple path points is the first distance, the smaller the first distance is, the smaller the distance error is, and when the first distance is within a preset distance range, at least one parameter in the preview time and the weight corresponding to the first turning angle is positively correlated with the first distance.

2. The method according to claim 1, wherein: The weight corresponding to the second turning angle is negatively correlated with the weight corresponding to the first turning angle.

3. The method according to claim 2, wherein: The sum of the weight corresponding to the second corner and the weight corresponding to the first corner is equal to 1.

4. The method according to claim 1, wherein: When the first distance is within the preset distance range, each parameter of the at least one parameter varies within a preset parameter range; When the first distance is greater than or equal to an upper limit of the preset distance range, each parameter of the at least one parameter is equal to an upper limit of the preset parameter range; and When the first distance is less than or equal to a lower limit of the preset distance range, each parameter of the at least one parameter is equal to a lower limit of the preset parameter range.

5. The method according to claim 4, further comprising: Determine, according to the first distance, a proportional coefficient that varies within a preset coefficient range, wherein each parameter of the at least one parameter is positively correlated with the proportional coefficient; Wherein, when the first distance is within the preset distance range, the proportionality coefficient is positively correlated with the first distance; In the case where the first distance is greater than or equal to an upper limit of the preset distance range, the proportional coefficient is equal to an upper limit of the preset coefficient range; and When the first distance is less than or equal to the lower limit of the preset distance range, the proportional coefficient is equal to the lower limit of the preset coefficient range.

6. The method according to claim 5, wherein: The lower limit of the preset coefficient range is 0, and the upper limit of the preset coefficient range is 1.

7. The method according to claim 5, wherein: When the first distance is within the preset distance range, the proportionality coefficient is equal to a ratio of the first distance to an upper limit of the preset distance range.

8. The method according to claim 1, wherein: When the first distance is within the preset distance range, each parameter of the at least one parameter is linearly correlated with the first distance.

9. A method for controlling a vehicle, comprising: Acquire current status information of the vehicle, wherein the status information includes position information and posture information; Determining a preview tracking point from a plurality of path points of a target path to be tracked by the vehicle according to reference information, wherein the reference information includes a preview time; as well as determining a target turning angle for controlling the front wheels of the vehicle according to the position information, the posture information and the preview tracking point, Among them, the minimum distance among the multiple distances between the vehicle and the multiple path points is the first distance, the smaller the first distance is, the smaller the distance error is, and when the first distance is within a preset distance range, the preview time is positively correlated with the first distance.

10. The method according to any one of claims 1 to 9, further comprising: determining a trend line reflecting the change in each of the plurality of candidate paths; determining a second distance between the vehicle and the trend line based on the position information; Determining, based on the posture information, an angle between a traveling direction of the vehicle and an extending direction of the trend line; as well as According to the second distance and the angle, one is selected from the multiple candidate paths as the target path.

11. The method according to claim 10, wherein: Selecting one of the candidate paths as the target path according to the second distance and the angle includes: determining a first difference between each candidate path and the vehicle based on the second distance; Determining a second difference between each candidate path and the vehicle based on the angle; Performing weighted calculation on the first difference and the second difference to obtain a third difference between each candidate path and the vehicle; and According to the third difference, one of the plurality of candidate paths is selected as the target path.

12. The method according to claim 11, wherein: Determining a first difference between each candidate path and the vehicle based on the second distance includes: The second distance is normalized to obtain the first difference.

13. The method according to claim 12, wherein: The first difference is , where d2 is the second distance and W is the reference distance.

14. The method according to claim 13, wherein: In a case where the plurality of candidate paths include only two candidate paths whose trend lines are parallel to each other, the reference distance is equal to half of the distance between the trend lines of the two candidate paths.

15. The method according to claim 13, wherein: The path point closest to the vehicle on each candidate path is the first path point; In other cases except the preset case, the reference distance is the maximum value of multiple Euclidean distances between the vehicle and multiple first path points of the multiple candidate paths, wherein the preset case is that the multiple candidate paths only include two candidate paths whose trend lines are parallel to each other.

16. The method according to claim 11, wherein: Determining the second difference of each candidate path according to the angle includes: The angle is normalized to obtain the second difference.

17. The method according to any one of claims 1 to 9, further comprising: After the target path is determined, another target path is determined only when a preset condition is met, wherein the preset condition includes that the target path is traveled to the end or a user instruction is received.

18. The method according to any one of claims 1 to 9, wherein: The reference information further includes a setting method of the plurality of path points, wherein the setting method includes a first setting method or a second setting method, wherein: In the first setting mode, the lengths of the straight line segments between adjacent path points in the plurality of path points are the same, In the second setting mode, the lengths of line segments along the target path between adjacent path points among the plurality of path points are the same.

19. The method according to any one of claims 1 to 9, further comprising: The front wheels of the vehicle are controlled to turn at the target turning angle.

20. The method according to any one of claims 1 to 8, wherein: A first line parallel to a tangent line of the target path tangent to the preview tracking point, a second line perpendicular to the tangent line, and an extension line of the vehicle's driving direction intersect at a first point, and a distance between the first point and the tangent line is a third distance; The first rotation angle is equal to arctan(third distance / preview distance); and The second turning angle is equal to the angle between the extending direction of the tangent line and the driving direction of the vehicle.

21. A vehicle control device, comprising: An acquisition module is configured to acquire current status information of the vehicle, wherein the status information includes position information and posture information; A determination module is configured to determine a preview tracking point from a plurality of path points of a target path to be tracked by the vehicle according to reference information, the reference information including a preview time; determine a first turning angle and a second turning angle of a front wheel of the vehicle according to the position information and the posture information, the first turning angle being used to eliminate a distance error between the vehicle and the preview tracking point, and the second turning angle being used to eliminate a heading error between the vehicle and the preview tracking point; and perform weighted calculation on the first turning angle and the second turning angle to determine a target turning angle for controlling the front wheel, wherein a minimum distance among a plurality of distances between the vehicle and the plurality of path points is a first distance, the smaller the first distance is, the smaller the distance error is, and when the first distance is within a preset distance range, at least one parameter in the weight corresponding to the preview time and the first turning angle is positively correlated with the first distance.

22. A vehicle control device, comprising: An acquisition module is configured to acquire current status information of the vehicle, wherein the status information includes position information and posture information; as well as A determination module is configured to determine a preview tracking point from a plurality of path points of a target path to be tracked by the vehicle according to reference information, wherein the reference information includes a preview time; and determine a target turning angle for controlling the front wheels according to the position information, the posture information and the preview tracking point, wherein a minimum distance among a plurality of distances between the vehicle and the plurality of path points is a first distance, and the smaller the first distance is, the smaller the distance error is, and when the first distance is within a preset distance range, the preview time is positively correlated with the first distance.

23. A vehicle control device, comprising: Memory; as well as A processor coupled to the memory, configured to execute the method of any one of claims 1-20 based on instructions stored in the memory.

24. A vehicle comprising: A control device for a vehicle as described in any one of claims 21 to 23.

25. The vehicle of claim 24, wherein: The vehicle comprises an off-road vehicle.

26. The vehicle of claim 25, wherein: The off-road vehicles include agricultural vehicles.

27. A computer-readable storage medium comprising computer program instructions, wherein: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 20 is implemented.

28. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 20 is implemented.

Images