Trajectory prediction method and device, related equipment and vehicle

Abstract

The invention relates to a trajectory prediction method and device, related equipment and a vehicle. The method comprises the steps of obtaining position information of a lane line and running information of the vehicle; determining a center line prediction track corresponding to the lane line according to the position information; and according to the central line prediction trajectory, adjusting the initial prediction trajectory corresponding to the operation information to obtain a target prediction trajectory of the vehicle. Therefore, the position information of the lane line is introduced, the position information of the lane line is utilized, the center line prediction track is determined, the initial prediction track of the vehicle is further adjusted by utilizing the center line prediction track, and the target prediction track of the vehicle is obtained, so that the accuracy of vehicle track prediction is improved, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a trajectory prediction method, apparatus, related equipment and vehicle. Background Art

[0002] With the development of autonomous driving technology, vehicles are becoming more and more intelligent. In order to ensure safe and intelligent driving of vehicles, it is crucial to predict the trajectory of the vehicle. However, the existing vehicle trajectory prediction solutions have low prediction accuracy, which affects the user experience. Summary of the invention

[0003] The embodiments of the present application provide a trajectory prediction method, device, electronic device, storage medium, computer program product and vehicle, which introduces the position information of the lane line, uses the position information of the lane line to determine the centerline prediction trajectory, and further uses the centerline prediction trajectory to adjust the initial prediction trajectory of the vehicle to obtain the target prediction trajectory of the vehicle, so as to improve the accuracy of vehicle trajectory prediction and improve the user experience.

[0004] The present application provides a trajectory prediction method, including:

[0005] Obtain the location information of lane lines and the operation information of vehicles;

[0006] Determine, according to the position information, a predicted centerline trajectory corresponding to the lane line;

[0007] According to the centerline predicted trajectory, the initial predicted trajectory corresponding to the operation information is adjusted to obtain the target predicted trajectory of the vehicle.

[0008] Accordingly, an embodiment of the present application provides a trajectory prediction device, comprising:

[0009] An information acquisition module is used to obtain the location information of the lane line and the operation information of the vehicle;

[0010] A centerline prediction trajectory determination module, used to determine the centerline prediction trajectory corresponding to the lane line according to the position information;

[0011] An adjustment module is used to adjust the initial predicted trajectory corresponding to the operation information according to the centerline predicted trajectory to obtain a target predicted trajectory of the vehicle.

[0012] In addition, an embodiment of the present application also provides an electronic device, including one or more processors and a memory, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to implement the trajectory prediction method provided in the embodiment of the present application.

[0013] In addition, an embodiment of the present application further provides a storage medium, wherein the storage medium stores a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute any trajectory prediction method provided in the embodiment of the present application.

[0014] In addition, an embodiment of the present application also provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements any trajectory prediction method provided in the embodiment of the present application.

[0015] In addition, an embodiment of the present application also provides a vehicle, including the above-mentioned electronic device, or the above-mentioned storage medium, or the above-mentioned computer program product.

[0016] In the embodiment of the present application, the position information of the lane line and the running information of the vehicle are obtained; the predicted centerline trajectory corresponding to the lane line is determined according to the position information; the initial predicted trajectory corresponding to the running information is adjusted according to the predicted centerline trajectory to obtain the target predicted trajectory of the vehicle. In this way, by introducing the position information of the lane line, the predicted centerline trajectory is determined by using the position information of the lane line, and the initial predicted trajectory of the vehicle is further adjusted by using the predicted centerline trajectory to obtain the target predicted trajectory of the vehicle, so as to improve the accuracy of vehicle trajectory prediction and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 This is a schematic diagram of an implementation environment scenario of the trajectory prediction method provided in an embodiment of the present application;

[0019] Figure 2 is a flow chart of a trajectory prediction method provided by an embodiment of the present application;

[0020] Figure 3 It is a schematic diagram of a centerline prediction trajectory in a straight-ahead scenario provided by an embodiment of the present application;

[0021] Figure 4 It is a schematic diagram of a centerline prediction trajectory in a lane change scenario provided by an embodiment of the present application;

[0022] Figure 5 This is a schematic diagram of a centerline prediction trajectory in a large curve scene provided by an embodiment of the present application;

[0023] Figure 6 This is a schematic diagram of a centerline prediction trajectory in a line-pressing scenario provided by an embodiment of the present application;

[0024] Figure 7 This is a schematic diagram of a target prediction trajectory in a large curve scene provided by an embodiment of the present application;

[0025] Figure 8 is a schematic diagram of a target prediction trajectory in a lane change scenario provided by an embodiment of the present application;

[0026] Fig. 9 is a schematic diagram of the structure of a trajectory prediction device provided by an embodiment of the present application;

[0027] Fig.10 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0029] In addition, the term "plurality" in the embodiments of the present application refers to two or more than two. The terms "first" and "second" in the embodiments of the present application are used to distinguish descriptions and should not be understood as implying relative importance.

[0030] The embodiments of the present application provide a trajectory prediction method, device, electronic device, storage medium, computer program product and vehicle. The trajectory prediction device can be integrated in an electronic device, which can be a server or a terminal.

[0031] Among them, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, network acceleration services (Content Delivery Network, CDN), as well as big data and artificial intelligence platforms.

[0032] The terminal may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server may be directly or indirectly connected via wired or wireless communication, and this application does not limit this.

[0033] See also Figure 1 , taking the trajectory prediction device integrated into an electronic device as an example, Figure 1 A schematic diagram of an implementation scenario of the trajectory prediction method provided in an embodiment of the present application, wherein the electronic device may be a terminal device, which obtains the position information of the lane line and the operation information of the vehicle; determines the centerline predicted trajectory corresponding to the lane line based on the position information; and adjusts the initial predicted trajectory corresponding to the operation information based on the centerline predicted trajectory to obtain the target predicted trajectory of the vehicle.

[0034] It should be noted that Figure 1 The implementation environment scenario diagram of the trajectory prediction method shown is only an example. The implementation environment scenario of the trajectory prediction method described in the embodiment of the present application is to more clearly illustrate the technical solution of the embodiment of the present application, and does not constitute a limitation on the technical solution provided by the embodiment of the present application. It is known to those skilled in the art that with the evolution of data processing and the emergence of new business scenarios, the technical solution provided by this application is also applicable to similar technical problems.

[0035] The solutions provided by the embodiments of the present application are specifically described by the following embodiments. It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments.

[0036] This embodiment will be described from the perspective of a trajectory prediction device. The trajectory prediction device may be integrated into an electronic device. The electronic device may be a terminal and / or a server, and this application does not limit this.

[0037] See also Figure 2 , Figure 2 : is a flow chart of a trajectory prediction method provided by an embodiment of the present application. The trajectory prediction method may include the following steps S101 to S103:

[0038] S101. Obtaining lane line position information and vehicle operation information.

[0039] The lane line refers to the marking used to guide and regulate vehicle driving in road traffic. The position information of the lane line refers to the position information of the lane line when it is perceived.

[0040] There are many ways to obtain the location information of lane lines, which are not limited by the embodiments of the present application. For example, it can be obtained through visual perception technology. For example, a road image is obtained by a camera sensor set on a vehicle, and lane lines and the location information of lane lines are extracted based on the road image. For another example, the lane lines and the location information of lane lines can be determined from the navigation data by obtaining navigation data.

[0041] The operation information refers to various information related to the operation of the vehicle. The operation information includes but is not limited to the speed, acceleration, steering wheel angle, and steering wheel angle rate of the vehicle. The specific content of the operation information can be adjusted according to the actual situation, and the embodiments of the present application do not limit it.

[0042] S102: Determine a center line prediction trajectory corresponding to the lane line according to the position information.

[0043] The centerline prediction trajectory is used to indicate the centerline trajectory of the lane predicted based on the position information of the lane line.

[0044] It should be noted that the existing method for obtaining the centerline prediction trajectory is: directly sampling trajectory points on the two lane lines, adding and averaging the coordinates of the trajectory points of the two lane lines at the lateral position to obtain the lane centerline trajectory points, and fitting the lane centerline trajectory points to obtain the centerline prediction trajectory, wherein the vehicle's driving direction is the longitudinal direction and the lane in which the vehicle is driving is the lateral direction.

[0045] The centerline prediction trajectory is determined through the position information of the lane line, so that the vehicle movement trend and the centerline prediction trajectory can be combined later to improve the prediction accuracy of the trajectory that the vehicle will travel.

[0046] S103. According to the centerline predicted trajectory, the initial predicted trajectory corresponding to the operation information is adjusted to obtain a target predicted trajectory of the vehicle.

[0047] The initial predicted trajectory refers to the vehicle's driving trajectory predicted based on the vehicle's operating information.

[0048] The adjustment process refers to fusing the target trajectory points on the midline prediction trajectory with the prediction trajectory points on the initial prediction trajectory to obtain fused trajectory points, and performing fitting processing on the fused trajectory points to obtain the target prediction trajectory.

[0049] It should be noted that the method used for fitting processing can be adjusted according to actual conditions, and the embodiments of the present application do not limit it. For example, the least square method is used for fitting processing. For another example, the minimum residual method is used for fitting processing.

[0050] In the embodiment of the present application, the position information of the lane line and the running information of the vehicle are obtained; the predicted centerline trajectory corresponding to the lane line is determined according to the position information; the initial predicted trajectory corresponding to the running information is adjusted according to the predicted centerline trajectory to obtain the target predicted trajectory of the vehicle. In this way, by introducing the position information of the lane line, the predicted centerline trajectory is determined by using the position information of the lane line, and the initial predicted trajectory of the vehicle is further adjusted by using the predicted centerline trajectory to obtain the target predicted trajectory of the vehicle, so as to improve the accuracy of vehicle trajectory prediction and improve the user experience.

[0051] In some embodiments, the operation information includes at least one of speed, acceleration, steering wheel angle, and steering wheel angle rate. The process of determining the centerline prediction trajectory corresponding to the lane line according to the position information may include: determining the centerline prediction trajectory corresponding to the lane line according to the position information and the operation information.

[0052] The centerline prediction trajectory is used to indicate the centerline trajectory of the lane predicted based on the position information of the lane line and the operation information of the vehicle.

[0053] The centerline prediction trajectory is determined by the position information of the lane line and combined with the vehicle operation information, so that the centerline prediction trajectory can be predicted in combination with the vehicle movement trend, thereby improving the prediction accuracy of the subsequent prediction of the trajectory that the vehicle will travel to.

[0054] In some embodiments, the process of determining the centerline predicted trajectory corresponding to the lane line based on the position information may include: determining the motion state information of the vehicle based on the operation information, wherein the motion state information includes a straight-ahead state and a lane-changing state; determining a target lane line from the lane line based on the motion state information; determining a plurality of target trajectory points based on a trajectory equation corresponding to the position information of the target lane line; and performing fitting processing based on the plurality of target trajectory points to obtain a centerline predicted trajectory corresponding to the lane line.

[0055] The motion state information is used to indicate the motion state of the vehicle.

[0056] There are many ways to obtain motion state information. For example, the motion state information of the vehicle can be obtained by analyzing the vehicle's operating information. The process of analyzing the vehicle's operating information can be: obtaining the vehicle's historical trajectory and current operating information (such as data collected by sensors) to determine the vehicle's motion trend. For another example, the vehicle's motion state information can be obtained through the vehicle's operating information and the position information of the lane line.

[0057] There are many forms of expression of motion state information, which can be set according to actual conditions. For example, the motion state information includes straight-going state and lane-changing state. Among them, the straight-going state may include: straight-going with a lane line; straight-going without a lane line; straight-going with a lane line due to the lane line not meeting the conditions; pressing the line. The lane-changing state may include: changing lanes; turning without a lane line; turning with a lane line due to the lane line not meeting the conditions; changing lanes by pressing the line; large curve scenes, etc. For another example, the motion state information of the vehicle includes: straight-going with a lane line; changing lanes; straight-going without a lane line; turning without a lane line; straight-going with a lane line due to the lane line not meeting the conditions; turning with a lane line due to the lane line not meeting the conditions; pressing the line; changing lanes by pressing the line; large curve scenes, etc. Among them, the motion status information under lane change can be further subdivided into: changing lanes to the left; changing lanes to the right; lane change successful; lane change failed; having crossed the lane line when changing lanes, but not yet judged as successful / cancelled; changing lanes to the left by pressing the line; changing lanes to the right by pressing the line; driving along the left lane line; driving along the right lane line, etc.

[0058] The target lane line refers to the lane line corresponding to the target lane used for lane centerline prediction.

[0059] The target lane line includes the first lane line and the second lane line. The first lane line and the second lane line are relative and are used to distinguish the names of the two lane lines. For example, when the first lane line is the target left lane line, the second lane line is the target right lane line. For another example, when the first lane line is the target right lane line, the second lane line is the target left lane line.

[0060] Specifically, the process of determining the target lane line from the lane lines according to the motion state information corresponding to the operating information may be: determining the target lane according to the motion state information corresponding to the operating information; and determining the target lane line from the lane lines based on the target lane.

[0061] Exemplarily, it is assumed that the first lane line is the target left lane line, and the second lane line is the target right lane line. There are multiple lane lines on the road, such as left-left lane line, left lane line, right lane line, and right-right lane line. Among them, the left-left lane line indicates the lane line on the left side of the left lane line, and the right-right lane line indicates the lane line on the right side of the right lane line. It should be noted that the current lane is the lane formed by the left lane line and the right lane line. The left lane is the lane formed by the left-left lane line and the left lane line. The naming principle of other lanes is similar and will not be repeated here.

[0062] In this example, if the vehicle's motion state information is straight driving or the lane change state is lane change failure / success, the target lane is the current lane, the first lane line is the left lane line, and the second lane line is the right lane line.

[0063] In this example, if the motion state information of the vehicle is lane change and the lane change state is lane change to the left, the target lane is the left lane, the first lane marking is the left-left lane marking, and the second lane marking is the left lane marking.

[0064] In this example, if the vehicle's motion state information is lane change and the lane change state is lane change to the right, the target lane is the right lane, the first lane marking is the right lane marking, and the second lane marking is the right-right lane marking.

[0065] In this example, if the vehicle's motion status information shows that it has crossed the lane line when changing lanes, but the lane change has not yet been determined to be successful / cancelled, the target lane is the current lane, the first lane line is the left lane line, and the second lane line is the right lane line.

[0066] In this example, when the vehicle's motion state information is changing lanes by pressing the line, if the lane changing state is changing lanes to the left by pressing the line and has not crossed the line, then the target lane is the left lane, the first lane line is the left-left lane line, and the second lane line is the left lane line; if the lane changing state is changing lanes to the right by pressing the line and has not crossed the line, then the target lane is the right lane, the first lane line is the right lane line, and the second lane line is the right-right lane line; if the lane changing state is changing lanes to the left / right by pressing the line and has crossed the line, then the target lane is the current lane, the first lane line is the left lane line, and the second lane line is the right lane line.

[0067] It should be noted that, in some embodiments, the process of determining the predicted centerline trajectory corresponding to the lane line based on the position information and the operating information may also include: when the motion state information corresponding to the operating information is straight-ahead driving, directly calculating the possible driving trajectory of the vehicle based on the lateral distance of the vehicle from the lane line and the direction of the lane line, taking a point on the trajectory as a target trajectory point, and performing fitting processing based on multiple target trajectory points to obtain the predicted centerline trajectory corresponding to the lane line.

[0068] The target lane line can be described using a trajectory equation. The trajectory equation refers to a cubic curve equation. That is, after obtaining the position information of the lane line, the position information of the lane line participates in the trajectory prediction process in the form of a cubic curve equation.

[0069] Exemplarily, the trajectory equation corresponding to the position information of the target lane line is expressed according to formula (1):

[0070] y=C0+C1*x+C2*x 2 +C3*x 3 (1)

[0071] Among them, y is used to indicate the target lane line. o is the constant term coefficient, C1 is the linear term coefficient, C2 is the quadratic term coefficient, and C3 is the cubic term coefficient. o, C1, C2, and C3 are all constant terms. x is the value of the X-axis in the vehicle coordinate system (e.g., the direction of the vehicle head is the X-axis). When x = 0, C o Indicates the lateral distance from the center of the vehicle to the lane line. C1 is the value of tan(α). α is the angle between the X-axis of the vehicle coordinate system (such as the direction of the vehicle head as the X-axis) and the lane line, with a left deviation being positive and a right deviation being negative. C2 indicates half of the curvature of the lane line. C3 indicates one sixth of the curvature change rate of the lane line.

[0072] The target trajectory point refers to the trajectory point used to fit and generate the centerline prediction trajectory.

[0073] There are many ways to determine the target trajectory point, which is not limited in the embodiments of the present application.

[0074] In one example, the target trajectory point is determined by obtaining a trajectory point sampled on the first lane line based on the position information of the first lane line, and a trajectory point sampled on the second lane line based on the position information of the second lane line, directly adding and averaging the coordinates of the corresponding trajectory points to obtain the target trajectory point.

[0075] In another example, the target trajectory point is determined as follows: based on the first trajectory point and the road width, a first predicted trajectory point is obtained, wherein the first trajectory point is used to indicate a trajectory point sampled on the first lane line based on the position information of the first lane line, and the road width is used to indicate a lane width determined based on the first lane line and the second lane line; based on the second trajectory point and the road width, a second predicted trajectory point is obtained, wherein the second trajectory point is used to indicate a trajectory point sampled on the second lane line based on the position information of the second lane line; and based on the first predicted trajectory point and the second predicted trajectory point, multiple target trajectory points are obtained.

[0076] Among them, according to the ordinate of sampling set on the vehicle coordinate system, combined with the trajectory equation of the first lane line, sampling can be performed on the first lane line to obtain multiple first trajectory points, and combined with the trajectory equation of the second lane line, sampling can be performed on the second lane line to obtain multiple second trajectory points. The number of the first trajectory points and the second trajectory points is the same, and the ordinate of the first trajectory point and the ordinate of the second trajectory point are both the set ordinate.

[0077] It should be noted that the vehicle coordinate system is a coordinate system constructed with the front direction of the vehicle as the x-axis and the front direction of the parallel vehicle as the y-axis.

[0078] It should be noted that since the quality of the lane line is related to the effective length of the lane line, when the longitudinal distance of the sampling point is much greater than the effective length of the lane line, the fitting effect is not ideal due to the inherent properties of the cubic curve. Therefore, when the sampling point is within the effective length of the lane line, the point is directly taken on the cubic curve equation of the lane line. For sampling points that exceed the effective length, the tangent equation at the end point of the lane line is calculated, and a point is taken on the tangent line.

[0079] The above example is explained below with a specific embodiment: Assume that the first lane line is the target left lane line, and the second lane line is the target right lane line.

[0080] Determine the road width according to the following formula (2):

[0081] w=C OL -C OR (2)

[0082] Where w is the road width, C OL is the constant coefficient of the trajectory equation corresponding to the target left lane, C OR is the constant coefficient of the trajectory equation corresponding to the target right lane.

[0083] When the target lane line is the target left lane line, the coordinates of the first predicted trajectory point are determined according to the following formula (3):

[0084]

[0085] Among them, X′ Li is the ordinate of the first predicted trajectory point on the target left lane, Y′ Li is the horizontal coordinate of the first predicted trajectory point on the target left lane, x i It refers to the ordinate of the first trajectory point on the left lane of the target, y i It refers to the horizontal coordinate of the first trajectory point on the target left lane. w is the road width, α0=atan(C1), α0 is used to indicate the angle between the current position of the vehicle and the target left lane line. i =α0+2*C2*x+3*C3*x2, α i It is used to indicate the location of the i-th first trajectory point, the angle between the vehicle and the target left lane line, C o is the constant term coefficient on the trajectory equation corresponding to the target left lane, C1 is the linear term coefficient on the trajectory equation corresponding to the target left lane, C2 is the quadratic term coefficient on the trajectory equation corresponding to the target left lane, C3 is the cubic term coefficient on the trajectory equation corresponding to the target left lane, and the number of the first trajectory points is (1, n), where n is a positive integer.

[0086] When the target lane line is the target right lane line, the coordinates of the second predicted trajectory point are determined according to the following formula (4):

[0087]

[0088] Among them, X′ Ri is the ordinate of the second predicted trajectory point on the target right lane, Y′ Ri is the horizontal coordinate of the second predicted trajectory point on the target right lane, x i Refers to the ordinate of the second trajectory point on the right lane of the target, y i It refers to the horizontal coordinate of the second trajectory point on the target right lane. w is the road width, α0=atan(C1), α0 is used to indicate the angle between the current position of the vehicle and the target right lane line. i =α0+2*C2*x+3*C3*x 2 , α i It is used to indicate the location of the i-th second trajectory point, the angle between the vehicle and the target right lane line, C o is the constant term coefficient on the trajectory equation corresponding to the target right lane, C1 is the linear term coefficient on the trajectory equation corresponding to the target right lane, C2 is the quadratic term coefficient on the trajectory equation corresponding to the target right lane, C3 is the cubic term coefficient on the trajectory equation corresponding to the target right lane, and the number of the second trajectory points is (1, n), where n is a positive integer.

[0089] The process of obtaining a plurality of target trajectory points according to the first predicted trajectory point and the second predicted trajectory point may include: adding and averaging the coordinates of the corresponding first predicted trajectory point and the coordinates of the corresponding second predicted trajectory point to obtain the target trajectory point.

[0090] Among them, the process of obtaining multiple target trajectory points based on the first predicted trajectory point and the second predicted trajectory point can also include: determining a first weight for the first lane line and a second weight for the second lane line based on the effective length of the first lane line and the effective length of the second lane line, wherein the effective length is used to indicate the perceived length of the corresponding lane line; and performing weighted processing on the coordinates of the first predicted trajectory point and the coordinates of the second predicted trajectory point based on the first weight and the second weight to obtain multiple target trajectory points.

[0091] The first weight is used to indicate the weight of the first predicted trajectory point on the first lane line participating in the target track determination, and the second weight is used to indicate the weight of the second predicted trajectory point on the second lane line participating in the target track determination.

[0092] Specifically, the difference between the effective length of the first lane line and the effective length of the second lane line may be calculated, and a comparison may be performed based on the difference and a preset difference, and a first weight for the first lane line and a second weight for the second lane line may be set based on the comparison result. For example, if the comparison result is that the difference is less than the preset difference, the first weight and the second weight are set equal. For another example, if the comparison result is that the difference is greater than the preset difference, and the effective length of the first lane line is longer, the first weight is set based on the difference between the effective length of the first lane line and the effective length of the second lane line, and the effective length of the first lane line, and the second weight is determined based on the sum of weights and the first weight. For another example, if the comparison result is that the difference is greater than the preset difference, and the effective length of the second lane line is longer, the second weight is set based on the difference between the effective length of the first lane line and the effective length of the second lane line, and the effective length of the second lane line, and the first weight is determined based on the sum of weights and the second weight.

[0093] Continuing from the previous specific embodiment, assuming that the preset difference is 2 meters, the process of setting the first weight and the second weight in this step is explained:

[0094] In Example A, assuming that the difference between the effective length of the target left lane line and the effective length of the target right lane line is less than the preset difference of 2 meters, the coordinates of the target trajectory point are determined according to the following formula (5):

[0095]

[0096] Among them, the first weight and the second weight are both 0.5, X′ i is the ordinate of the target trajectory point, Y′ i is the horizontal coordinate of the target trajectory point.

[0097] In Example B, assuming that the difference between the effective length of the target left lane line and the effective length of the target right lane line is greater than the preset difference of 2 meters, and the effective length of the target left lane line is greater, the coordinates of the target trajectory point are determined according to the following formula (6):

[0098] diff=D L -D R

[0099]

[0100] Among them, X′ i is the ordinate of the target trajectory point, Y′ i is the horizontal coordinate of the target trajectory point, diff is the difference between the effective length of the target left lane line and the effective length of the target right lane line, and w lane is the first weight, (1-w lane ) is the second weight.

[0101] In Example C, assuming that the difference between the effective length of the target left lane line and the effective length of the target right lane line is greater than the preset difference of 2 meters, and the effective length of the target right lane line is greater, the coordinates of the target trajectory point are determined according to the following formula (7):

[0102] diff=D R D L

[0103]

[0104] Among them, X′ i is the ordinate of the target trajectory point, Y′ i is the horizontal coordinate of the target trajectory point, diff is the difference between the effective length of the target left lane line and the effective length of the target right lane line, and w lane is the second weight, (1-w lane ) is the first weight.

[0105] like Figures 3 to 6 As shown in the figure, in different scenarios, the target trajectory points can be stably and accurately determined, and the midline prediction trajectory can be generated based on the target trajectory points. Figure 3 It is a schematic diagram of a centerline prediction trajectory in a straight-moving scenario provided by an embodiment of the present application. Figure 4 It is a schematic diagram of a centerline prediction trajectory in a lane change scenario provided by an embodiment of the present application. Figure 5 It is a schematic diagram of a centerline prediction trajectory in a large curve scene provided by an embodiment of the present application. Figure 6 It is a schematic diagram of a centerline prediction trajectory in a line-pressing scenario provided by an embodiment of the present application.

[0106] In some embodiments, it also includes: updating an angle parameter according to the first weight and the second weight, wherein the angle parameter is used to indicate the angle between the lane where the vehicle is located and the predicted trajectory of the center line; and updating the road width based on the updated angle parameter and the second lane line of the first lane line.

[0107] Following Example A, Example B and Example C in the previous specific embodiment, the process of updating the angle parameter in this step is explained:

[0108] In the above example A, the angle parameter is updated according to the following formula (8):

[0109] α=0.5*atan(C 1L )+0.5*atan(C 1R ) (8)

[0110] Among them, α is the updated angle parameter, the first weight and the second weight are both 0.5, C1L is the coefficient of the first-order term on the trajectory equation corresponding to the target left lane, C 1R is the coefficient of the first-order term on the trajectory equation corresponding to the target right lane.

[0111] In the above example B, the angle parameter is updated according to the following formula (9):

[0112] α=w lane *abs(atan(C 1L ))+(1-w lane )*abs(atan(C 1R )) (9)

[0113] Among them, α is the updated angle parameter, w lane is the first weight, (1-w lane ) is the second weight, C 1L is the coefficient of the first-order term on the trajectory equation corresponding to the target left lane, C 1R is the coefficient of the first-order term on the trajectory equation corresponding to the target right lane.

[0114] In the above example C, the angle parameter is updated according to the following formula (10):

[0115] α=(1-w lane )*abs(atan(C 1L ))+w lane *abs(atan(C 1R )) (10)

[0116] Among them, α is the updated angle parameter, w lane is the second weight, (1-w lane ) is the first weight, C 1L is the coefficient of the first-order term on the trajectory equation corresponding to the target left lane, C 1R is the coefficient of the first-order term on the trajectory equation corresponding to the target right lane.

[0117] Based on the above embodiment, the road width is updated according to the following formula (11):

[0118] w′=(C 0L -C 0R )*cos(α) (11)

[0119] Among them, w′ refers to the updated road width, α is the updated angle parameter, and C 0L is the constant coefficient of the trajectory equation corresponding to the target left lane, C 0R is the constant coefficient of the trajectory equation corresponding to the target right lane.

[0120] It should be noted that the perception effect of the lane line directly affects the quality of the lane centerline point. Generally, when the effective length of the lane line is short, especially in the curved scene, the coordinate error of the calculated target trajectory point is large. Therefore, the weight of the corresponding lane line is calculated by combining the effective length of the first lane line and the effective length of the second lane line. The first lane line and the second lane line are fused through the weight, and the road width is updated to improve the accuracy of vehicle trajectory prediction and improve the user experience.

[0121] In some embodiments, before determining multiple target trajectory points according to the trajectory equation corresponding to the position information of the target lane line, it also includes: acquiring the position information of the curb; and determining the first lane line and the second lane line in the target lane line based on the position information of the curb and the position information of the lane line.

[0122] Among them, curb refers to an object with traffic guidance and isolation functions, which is used to guide vehicles along the road and prevent vehicles from deviating from the road.

[0123] The roadside can be described using a trajectory equation. The trajectory equation refers to a cubic curve equation. That is, after obtaining the position information of the roadside, the position information of the roadside is involved in the trajectory prediction process in the form of a cubic curve equation.

[0124] It should be noted that when two lane lines are obtained, there are cases where a single lane line is valid, and cases where both lane lines are invalid. In the above cases, the target lane line needs to be repaired.

[0125] Among them, the situation where a single lane line is valid refers to the situation where only one side of the lane line exists or the lane consisting of two lane lines is invalid but it is judged that the lane line is invalid when driving along one of the lane lines.

[0126] In some embodiments, the target lane line can be repaired based on the roadside information.

[0127] Among them, when a single lane line is valid, the target lane line can be repaired according to the position information of the single-side lane line, the position information of the curb and the road width.

[0128] It should be noted that the existing method of obtaining the centerline prediction trajectory can only achieve good results when both lane lines exist and the effective distance between the two lane lines is close. However, when only one lane line exists, or the error of one of the lane lines is large, the coordinate error of the lane centerline trajectory point obtained by this method is large, and the centerline prediction trajectory cannot be accurately predicted. The present application combines the position information of the lane line and the operation information of the vehicle to predict the lane centerline trajectory, which can effectively reduce the error caused by the existence of only one lane line or one of the lane lines, thereby improving the prediction accuracy of the centerline prediction trajectory.

[0129] For example, assuming that the target left lane line is the left lane line, and only the left lane line is valid, then check whether the right curb is a valid curb. If the position information of the right curb is valid, then the right curb is used as the target right lane line. Among them, whether the position information of the right curb is valid means that the right curb exists and the road width composed of the right lane line and the left curb is less than the preset road width threshold. If the position information of the right curb is invalid, the target right lane line is determined based on the position information of the left lane line and the road width. Similarly, the right lane line is repaired in the same way.

[0130] Among them, when both lane lines are invalid, the position information of the curbs on both sides can be obtained. And detect whether the left curb and the right curb are valid curbs. If the right curb exists, the left curb exists, and the road width composed of the right curb and the left curb is less than the preset road width threshold, the left curb is used as the target left lane, and the right curb is used as the target right lane.

[0131] It should be noted that after the target lane line is determined, the road width is determined based on the two lane lines or the roadside in the target lane line. The roadside is determined based on the difference between the constant term coefficient in the trajectory equation corresponding to the target left lane and the constant term coefficient in the trajectory equation corresponding to the target right lane.

[0132] In some embodiments, the target lane line can also be repaired according to the navigation information. The process of repairing the target lane line according to the navigation information can include: obtaining navigation information through the navigation module of the vehicle, determining the road surface information on which the vehicle is traveling according to the navigation information, and repairing the target lane line according to the road surface information.

[0133] In some embodiments, the target lane line can also be repaired only according to the road width. The process of repairing the target lane line according to the road width may include: collecting road surface information during vehicle driving through a sensor. Analyzing the road surface information to obtain multiple road widths. According to a preset road width threshold, a target road width is selected from multiple road widths, wherein the target road width is close to the preset road width threshold, and the target road width is less than the preset road width threshold. The lane line corresponding to the target road width is used as the target lane line to achieve repair processing of the target lane line.

[0134] In some embodiments, before adjusting the initial predicted trajectory corresponding to the operating information according to the centerline predicted trajectory to obtain the target predicted trajectory of the vehicle, it also includes: processing the operating information based on a preset vehicle dynamics model to obtain the initial predicted trajectory.

[0135] The preset vehicle dynamics model refers to a digital model established by analyzing the movement of the vehicle. The preset vehicle dynamics model regards the vehicle as a rigid body and determines the predicted trajectory of the vehicle in combination with the vehicle's movement information. It can be understood that the more accurate the preset vehicle dynamics model is, the more accurate the description of the vehicle's movement is, and the higher the accuracy of the vehicle's trajectory prediction is.

[0136] It should be noted that the initial predicted trajectory predicted by the preset vehicle dynamics model has high confidence and is relatively stable when the vehicle is moving straight, but because the data used is relatively single, the long-distance trajectory prediction of the vehicle is quite different from the actual trajectory. For example, when the user in the vehicle turns the steering wheel quickly, the predicted trajectory will jump frequently, making it impossible to stably output an accurate predicted trajectory.

[0137] The present application combines the lane line position information and the vehicle's operating information to first predict the lane centerline trajectory, and then uses the predicted centerline prediction trajectory to adjust the initial prediction trajectory predicted by the preset vehicle dynamics model to obtain the vehicle's target prediction trajectory, which can effectively solve the instability of the trajectory and the error problem that exists in long-distance prediction.

[0138] Based on this embodiment, the process of adjusting the initial predicted trajectory corresponding to the operating information according to the centerline predicted trajectory to obtain the target predicted trajectory of the vehicle also includes: determining a third weight of the centerline predicted trajectory and a fourth weight of the initial predicted trajectory; and adjusting the initial predicted trajectory using the centerline predicted trajectory according to the third weight and the fourth weight to obtain the target predicted trajectory of the vehicle.

[0139] Among them, the third weight of the centerline prediction trajectory is determined according to at least one of the vehicle's motion state information, the angle between the vehicle and the tangent direction of the lane line, the lateral distance of the vehicle from the centerline prediction trajectory, and the longitudinal distance of the sampling point on the initial prediction trajectory from the vehicle.

[0140] In some embodiments, the process of determining the third weight of the centerline prediction trajectory and the fourth weight of the initial prediction trajectory may include: determining the third weight of each target trajectory point in the centerline prediction trajectory based on the difference in longitudinal distance between the target trajectory point on the centerline prediction trajectory and the corresponding sampling point on the initial prediction trajectory; and determining the fourth weight of the sampling point in the initial prediction trajectory corresponding to the target trajectory point based on the third weight and preset weight of each target trajectory point.

[0141] It should be noted that, since both the vehicle trajectory points calculated based on the vehicle dynamics model and the vehicle historical trajectory are relatively accurate at close distances and can more accurately reflect the vehicle's true trajectory, but the trajectory credibility at long distances is low, here different weights are assigned to lane sampling points at different distances based on the difference in the longitudinal distance between the lane sampling point and the vehicle, that is, the farther the lane sampling point is from the vehicle, the greater the weight of the sampling point, and vice versa.

[0142] In some embodiments, the process of determining the third weight of the centerline prediction trajectory and the fourth weight of the initial prediction trajectory may also include: determining the third weight of each target trajectory point in the centerline prediction trajectory according to the motion state information; and determining the fourth weight of the sampling point corresponding to the target trajectory point in the initial prediction trajectory based on the third weight and preset weight of each target trajectory point.

[0143] It should be noted that, since the sources of the trajectory points are different and the credibility is different, the third weight and the fourth weight are determined according to points with different credibility.

[0144] For example, when the motion state information is a straight state, the third weight and the fourth weight can be determined according to the credibility corresponding to the straight state. For another example, when the motion state information is a line-pressing straight state, the third weight and the fourth weight can be determined according to the credibility corresponding to the line-pressing straight state.

[0145] The following is an explanation with a specific embodiment:

[0146] The third weight is determined according to the following formula (12):

[0147]

[0148] Among them, V iIt refers to the weight of the i-th target trajectory point, L is the ordinate (i.e. x) of the target trajectory point farthest from the vehicle in the vehicle coordinate system, P1 is the weight of the target trajectory point at x=0, and P2 is the weight of the target trajectory point at x=L.

[0149] When the vehicle's motion state information is driving straight on the line, P2=1.0, P1=0.1.

[0150] Since the target trajectory point is more trusted at a long distance, when the distance between the target trajectory point and the vehicle exceeds ε, the weight of the target trajectory point is increased. At this time, the third weight is determined according to the following formula (13):

[0151]

[0152] Among them, P2=1.0, P1=0.7, L is the ordinate (ie, x) of the target trajectory point in the vehicle coordinate system, and ε is a threshold value set according to different vehicle scenarios.

[0153] For example, when the vehicle is going straight, ε = 40. When the vehicle is changing lanes, ε = 50. When the vehicle is driving on a large curve, ε = 20.

[0154] It should be noted that when the vehicle is traveling on a large curve and the absolute value of the curvature of the lane line on one side is greater than 0.03, P1=0.9, and there is no need to judge the size of P2 and P1.

[0155] When the distance between the target trajectory point and the vehicle is less than ε, the size of P1 and P2 is determined according to the following method:

[0156] According to the vehicle's motion state information, the initial values ​​of P1 and P2 are determined. When the vehicle's motion state is straight, the default values ​​of P1 and P2 are given as P min (0.5) and P max (1) When the vehicle is in lane change state, the default values ​​of P1 and P2 are given as P min (0.3) and P max (1).

[0157] When there is a certain angle between the vehicle and the target lane, it is considered that the vehicle is not completely driving along the lane. The larger the absolute value of the angle, the greater the tendency to deviate from the lane, and vice versa. Therefore, the values ​​of P1 and P2 are optimized according to the angle between the vehicle and the target lane. α is the maximum angle value that the vehicle will reach with the lane during driving, given by experience. If the absolute value x of the current angle is less than or equal to α, the optimized P1 and P2 are determined according to the following formula (14):

[0158]

[0159] The default value of Yaw_P1 is 0.1, and the default value of Yaw_P2 is 0.3. P′1 is the optimized P1, and P′2 is the optimized P2.

[0160] If x is greater than α, then P′1=0, P′2=0.

[0161] Since the driver's driving behavior cannot be accurately predicted, and there is no guarantee that he will drive along the center line of the lane, in order to more accurately predict the vehicle's driving trajectory, the maximum weight P2 and minimum weight P1 of the lane sampling points are optimized by the lateral distance of the vehicle from the center line of the target lane. The closer the vehicle is to the center line of the target lane, the closer P1 and P2 are to the default values ​​P'1 and P'2, and vice versa, the closer they are to 0. In order to reduce the trajectory jump caused by vehicle state switching, the minimum weight lower limit Yaw_P1 (0.1) and the maximum weight lower limit Yaw_P2 (0.3) are introduced when changing lanes.

[0162] When the vehicle is moving straight and the lateral distance between the vehicle and the effective lane line is x, the optimized P1 and P2 are determined according to the following formula (15):

[0163]

[0164] Where d is half of the lane width of the target lane.

[0165] When the vehicle is in the state of changing lanes or changing lanes by crossing a lane line, and the lateral distance between the vehicle and the center line of the target lane is x, the optimized P1 and optimized P2 are determined according to the following formula (16):

[0166]

[0167] Where d is the lane width of the target lane.

[0168] like Figures 7 and 8 As shown, Figure 7 This is the fusion result of the vehicle trajectory points in the wide curve scene, where the blue trajectory points are the trajectory points on the initial predicted trajectory predicted by the vehicle dynamics formula, the orange trajectory points are the trajectory points on the centerline predicted trajectory calculated by the trajectory prediction method provided by the embodiment of the present application, and the green points are the trajectory points on the fused target predicted trajectory calculated based on the initial predicted trajectory and the centerline predicted trajectory, as well as the third weight and the fourth weight. It can be seen that in the wide curve scene, the trajectory calculated only by the steering wheel and other information has a large error, will deviate from the lane, and is inconsistent with the actual situation. When the centerline predicted trajectory is added, the vehicle trajectory can be optimized to a great extent.

[0169] Figure 8This is the fusion result of the vehicle trajectory points in the lane change scenario. It can be seen that the trajectory calculated by the steering wheel and other information can well express the vehicle trajectory at a short distance when changing lanes, but it cannot predict the vehicle trajectory well at a long distance. When the lane information and vehicle status information are added, the problem of unavailability of long-distance trajectory points can be solved. Since the weight is calculated for each trajectory point, the vehicle trajectory will not completely overlap with the lane sampling point, and the vehicle trajectory can be predicted more ideally.

[0170] In order to facilitate better implementation of the trajectory prediction method provided in the embodiment of the present application, the embodiment of the present application also provides a device based on the above trajectory prediction method. The meanings of the terms are the same as those in the above trajectory prediction method, and the specific implementation details can refer to the description in the method embodiment.

[0171] For example, Fig. 9 As shown, the trajectory prediction device may include an information acquisition unit 201, a midline prediction trajectory determination unit 202, and an adjustment unit 203, as follows:

[0172] The information acquisition unit 201 is used to acquire the position information of the lane line and the operation information of the vehicle;

[0173] A centerline prediction trajectory determination unit 202, used to determine a centerline prediction trajectory corresponding to a lane line according to the position information;

[0174] The adjustment unit 203 is used to adjust the initial predicted trajectory corresponding to the operation information according to the centerline predicted trajectory to obtain a target predicted trajectory of the vehicle.

[0175] In one embodiment of the present application, the operation information includes at least one of speed, acceleration, steering wheel angle, and steering wheel angle rate; the above-mentioned centerline prediction trajectory determination unit 202 includes:

[0176] The centerline prediction trajectory determination subunit is used to determine the centerline prediction trajectory corresponding to the lane line based on the position information and the operation information.

[0177] In one embodiment of the present application, the above-mentioned midline prediction trajectory determination subunit includes:

[0178] A motion state information determination module, used to determine the motion state information of the vehicle according to the operation information, wherein the motion state information includes a straight-ahead state and a lane-changing state;

[0179] A target lane line determination module is used to determine a target lane line from lane lines according to motion state information;

[0180] A target trajectory point determination module is used to determine multiple target trajectory points according to a trajectory equation corresponding to the position information of the target lane line;

[0181] The centerline prediction trajectory determination module is used to perform fitting processing based on multiple target trajectory points to obtain the centerline prediction trajectory corresponding to the lane line.

[0182] In one embodiment of the present application, the target lane line includes a first lane line and a second lane line, and the target trajectory point determination module includes:

[0183] A first predicted trajectory point determination submodule, configured to obtain a first predicted trajectory point according to the first trajectory point and the road width, wherein the first trajectory point is used to indicate a trajectory point sampled on the first lane line based on the position information of the first lane line, and the road width is used to indicate a lane width determined based on the first lane line and the second lane line;

[0184] A second predicted trajectory point determination submodule, used to obtain a second predicted trajectory point according to the second trajectory point and the road width, wherein the second trajectory point is used to indicate a trajectory point sampled on the second lane line based on the position information of the second lane line;

[0185] The target trajectory point determination submodule is used to obtain a plurality of target trajectory points according to the first predicted trajectory point and the second predicted trajectory point.

[0186] In the embodiment of the present application, the target trajectory point determination submodule is used to:

[0187] Determine a first weight for the first lane line and a second weight for the second lane line according to an effective length of the first lane line and an effective length of the second lane line, wherein the effective length is used to indicate a perceived length of the corresponding lane line;

[0188] The coordinates of the first predicted trajectory point and the coordinates of the second predicted trajectory point are weighted according to the first weight and the second weight to obtain a plurality of target trajectory points.

[0189] In an embodiment of the present application, the above-mentioned trajectory prediction device further includes:

[0190] An angle parameter updating unit, used to update the angle parameter according to the first weight and the second weight, wherein the angle parameter is used to indicate the angle between the lane where the vehicle is located and the centerline predicted trajectory;

[0191] The road width updating unit is used to update the road width based on the updated angle parameter and the second lane line of the first lane line.

[0192] In the embodiment of the present application, before the above-mentioned target trajectory point determination module, it also includes:

[0193] A roadside acquisition module is used to obtain the location information of the roadside;

[0194] The lane line determination module is used to determine the first lane line and the second lane line in the target lane line based on the position information of the curb and the position information of the lane line.

[0195] In an embodiment of the present application, the target lane line determination module includes:

[0196] A target lane determination submodule is used to determine the target lane according to the motion state information corresponding to the operation information;

[0197] The target lane line determination submodule is used to determine the target lane line from the lane lines based on the target lane.

[0198] In the embodiment of the present application, before the adjustment unit 203, the following steps are included:

[0199] An initial predicted trajectory determination unit, used to process the operation information based on a preset vehicle dynamics model to obtain an initial predicted trajectory;

[0200] The adjustment unit 203 includes:

[0201] A weight determination module, used to determine a third weight of the midline prediction trajectory and a fourth weight of the initial prediction trajectory;

[0202] The adjustment module is used to adjust the initial predicted trajectory using the midline predicted trajectory according to the third weight and the fourth weight to obtain a target predicted trajectory of the vehicle.

[0203] In the embodiment of the present application, the weight determination module includes:

[0204] A third weight first determination submodule, configured to determine a third weight of each target trajectory point in the midline prediction trajectory according to a difference in longitudinal distance between the target trajectory point on the midline prediction trajectory and a corresponding sampling point on the initial prediction trajectory;

[0205] The fourth weight first determination submodule is used to determine the fourth weight of the sampling point corresponding to the target trajectory point in the initial predicted trajectory based on the third weight of each target trajectory point and the preset weight.

[0206] In the embodiment of the present application, the weight determination module includes:

[0207] A third weight second determination submodule, configured to determine a third weight of each target trajectory point in the centerline prediction trajectory according to the motion state information;

[0208] The fourth weight second determination submodule is used to determine the fourth weight of the sampling point corresponding to the target trajectory point in the initial predicted trajectory based on the third weight of each target trajectory point and the preset weight.

[0209] In the embodiment of the present application, the position information of the lane line and the running information of the vehicle are obtained by the information acquisition unit 201; the centerline prediction trajectory determination unit 202 determines the centerline prediction trajectory corresponding to the lane line according to the position information; the adjustment unit 203 adjusts the initial prediction trajectory corresponding to the running information according to the centerline prediction trajectory to obtain the target prediction trajectory of the vehicle. In this way, by introducing the position information of the lane line, using the position information of the lane line to determine the centerline prediction trajectory, and further using the centerline prediction trajectory to adjust the initial prediction trajectory of the vehicle, the target prediction trajectory of the vehicle is obtained, so as to improve the accuracy of the vehicle trajectory prediction and improve the user experience.

[0210] In specific implementation, the above modules can be implemented as independent entities, or can be arbitrarily combined and implemented as the same or several entities. The specific implementation methods and corresponding beneficial effects of the above modules can be found in the previous method embodiments, which will not be repeated here.

[0211] The embodiment of the present application also provides an electronic device, wherein the operating system of the electronic device includes a first operating system and a second operating system. Fig.10 As shown, it shows a schematic diagram of the structure of the electronic device involved in the embodiment of the present application, specifically:

[0212] The electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more storage media, a power supply 303, and an input unit 304. Those skilled in the art will appreciate that Fig.10 The electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0213] in:

[0214] The processor 301 is the control center of the electronic device, which uses various interfaces and lines to connect various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing computer programs and / or modules stored in the memory 302, and calling data stored in the memory 302. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 301.

[0215] The memory 302 can be used to store computer programs and modules. The processor 301 executes various functional applications and trajectory prediction by running the computer programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, a computer program required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0216] The electronic device also includes a power supply 303 for supplying power to each component. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions. The power supply 303 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0217] The electronic device may further include an input unit 304, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0218] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more computer programs into the memory 302 according to the following instructions, and the processor 301 will run the computer programs stored in the memory 302, thereby realizing various functions, such as:

[0219] Obtain the location information of lane lines and the operation information of vehicles;

[0220] According to the position information, determine the center line prediction trajectory corresponding to the lane line;

[0221] According to the centerline predicted trajectory, the initial predicted trajectory corresponding to the operation information is adjusted to obtain the target predicted trajectory of the vehicle.

[0222] It can be seen that the electronic device provided in the embodiment of the present application obtains the position information of the lane line and the operation information of the vehicle; determines the centerline prediction trajectory corresponding to the lane line according to the position information; and adjusts the initial prediction trajectory corresponding to the operation information according to the centerline prediction trajectory to obtain the target prediction trajectory of the vehicle. In this way, by introducing the position information of the lane line, using the position information of the lane line to determine the centerline prediction trajectory, and further using the centerline prediction trajectory to adjust the initial prediction trajectory of the vehicle to obtain the target prediction trajectory of the vehicle, the accuracy of the vehicle trajectory prediction is improved, and the user experience is improved.

[0223] The specific implementation methods and corresponding beneficial effects of the above operations can be found in the detailed description of the trajectory prediction method above, which will not be elaborated here.

[0224] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by a computer program, or by controlling related hardware through a computer program. The computer program may be stored in a storage medium and loaded and executed by a processor.

[0225] To this end, an embodiment of the present application provides a storage medium in which a computer program is stored, and the computer program can be loaded by a processor to execute the steps in any trajectory prediction method provided in the embodiment of the present application. For example, the computer program can execute the following steps:

[0226] Obtain the location information of lane lines and the operation information of vehicles;

[0227] According to the position information, determine the center line prediction trajectory corresponding to the lane line;

[0228] According to the centerline predicted trajectory, the initial predicted trajectory corresponding to the operation information is adjusted to obtain the target predicted trajectory of the vehicle.

[0229] It can be seen from this that the storage medium provided in the embodiments of the present application,

[0230] By obtaining the position information of the lane line and the running information of the vehicle; determining the centerline prediction trajectory corresponding to the lane line according to the position information; adjusting the initial prediction trajectory corresponding to the running information according to the centerline prediction trajectory to obtain the target prediction trajectory of the vehicle. In this way, by introducing the position information of the lane line, using the position information of the lane line to determine the centerline prediction trajectory, and further using the centerline prediction trajectory to adjust the initial prediction trajectory of the vehicle, the target prediction trajectory of the vehicle is obtained, so as to improve the accuracy of vehicle trajectory prediction and improve the user experience.

[0231] The specific implementation methods and corresponding beneficial effects of the above operations can be found in the previous embodiments and will not be described in detail here.

[0232] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0233] Since the computer program stored in the storage medium can execute the steps in any trajectory prediction method provided in the embodiments of the present application, the beneficial effects that can be achieved by any trajectory prediction method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0234] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a storage medium. A processor of a computer device reads the computer instructions from the storage medium, and the processor executes the computer instructions, so that the computer device performs the above-mentioned trajectory prediction method.

[0235] The embodiment of the present application also provides a vehicle, which includes the above-mentioned trajectory prediction device, or the above-mentioned electronic device, or the above-mentioned computer program product. The specific structure of the vehicle is not limited in this application. The specific implementation methods and corresponding beneficial effects of the above-mentioned operations of the electronic device are also applicable to the vehicle. For details, please refer to the detailed description of the trajectory prediction method above, which will not be repeated here.

[0236] The above is a detailed introduction to a trajectory prediction method, device, electronic device, storage medium and vehicle provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A trajectory prediction method, characterized in that: include: Obtain the location information of lane lines and the operation information of vehicles; Determine, according to the position information, a predicted centerline trajectory corresponding to the lane line; According to the centerline predicted trajectory, the initial predicted trajectory corresponding to the operation information is adjusted to obtain the target predicted trajectory of the vehicle.

2. The trajectory prediction method according to claim 1, characterized in that: The operation information includes at least one of speed, acceleration, steering wheel angle, and steering wheel angle rate; and determining the centerline prediction trajectory corresponding to the lane line according to the position information includes: Determine a centerline prediction trajectory corresponding to the lane line according to the position information and the operation information.

3. The trajectory prediction method according to claim 2, characterized in that: The determining, according to the position information and the operation information, a centerline prediction trajectory corresponding to the lane line includes: Determining the motion state information of the vehicle according to the operation information, wherein the motion state information includes a straight-ahead state and a lane-changing state; Determining a target lane line from the lane lines according to the motion state information; Determining a plurality of target trajectory points according to a trajectory equation corresponding to the position information of the target lane line; Fitting is performed based on the plurality of target trajectory points to obtain a centerline prediction trajectory corresponding to the lane line.

4. The trajectory prediction method according to claim 3, characterized in that: The target lane line includes a first lane line and a second lane line; The step of determining a plurality of target trajectory points according to a trajectory equation corresponding to the position information of the target lane line comprises: Obtaining a first predicted trajectory point according to the first trajectory point and the road width, wherein the first trajectory point is used to indicate a trajectory point sampled on the first lane line based on the position information of the first lane line, and the road width is used to indicate a lane width determined based on the first lane line and the second lane line; Obtaining a second predicted trajectory point according to the second trajectory point and the road width, wherein the second trajectory point is used to indicate a trajectory point sampled on the second lane line based on the position information of the second lane line; A plurality of target trajectory points are obtained according to the first predicted trajectory points and the second predicted trajectory points.

5. The trajectory prediction method according to claim 4, characterized in that: The step of obtaining a plurality of target trajectory points according to the first predicted trajectory point and the second predicted trajectory point comprises: Determining a first weight for the first lane line and a second weight for the second lane line according to an effective length of the first lane line and an effective length of the second lane line, wherein the effective length is used to indicate a perceived length of the corresponding lane line; The coordinates of the first predicted trajectory point and the coordinates of the second predicted trajectory point are weighted according to the first weight and the second weight to obtain a plurality of target trajectory points.

6. The trajectory prediction method according to claim 5, characterized in that: The method further comprises: updating an angle parameter according to the first weight and the second weight, wherein the angle parameter is used to indicate an angle between the lane where the vehicle is located and the centerline predicted trajectory; The road width is updated based on the updated angle parameter and the second lane line of the first lane line.

7. The trajectory prediction method according to claim 4, characterized in that: Before determining a plurality of target trajectory points according to the trajectory equation corresponding to the position information of the target lane line, the method further includes: Get the location information of the roadside; Based on the position information of the curb and the position information of the lane line, a first lane line and a second lane line in the target lane line are determined.

8. The trajectory prediction method according to claim 3, characterized in that: The step of determining a target lane line from the lane lines according to the motion state information includes: Determining a target lane according to the motion state information; Based on the target lane, a target lane line is determined from the lane lines.

9. The trajectory prediction method according to any one of claims 1 to 8, characterized in that: Before adjusting the initial predicted trajectory corresponding to the operation information according to the centerline predicted trajectory to obtain the target predicted trajectory of the vehicle, the method includes: Based on a preset vehicle dynamics model, the operation information is processed to obtain an initial predicted trajectory; The adjusting the initial predicted trajectory corresponding to the operation information according to the centerline predicted trajectory to obtain the target predicted trajectory of the vehicle includes: determining a third weight of the centerline predicted trajectory and a fourth weight of the initial predicted trajectory; According to the third weight and the fourth weight, the initial predicted trajectory is adjusted using the centerline predicted trajectory to obtain a target predicted trajectory of the vehicle.

10. The trajectory prediction method according to claim 9, characterized in that: The determining of the third weight of the centerline prediction trajectory and the fourth weight of the initial prediction trajectory includes: Determining a third weight of each target trajectory point in the midline prediction trajectory according to a difference in longitudinal distance between the target trajectory point on the midline prediction trajectory and a corresponding sampling point on the initial prediction trajectory; Based on the third weight of each of the target trajectory points and the preset weight, a fourth weight of the sampling point corresponding to the target trajectory point in the initial predicted trajectory is determined.

11. The trajectory prediction method according to claim 9, characterized in that: The determining of the third weight of the centerline prediction trajectory and the fourth weight of the initial prediction trajectory includes: Determining a third weight of each target trajectory point in the centerline prediction trajectory according to the motion state information; Based on the third weight of each of the target trajectory points and the preset weight, a fourth weight of the sampling point corresponding to the target trajectory point in the initial predicted trajectory is determined.

12. A trajectory prediction device, characterized in that: include: An information acquisition unit, used to acquire the position information of the lane line and the operation information of the vehicle; A centerline prediction trajectory determination unit, used to determine a centerline prediction trajectory corresponding to the lane line according to the position information; An adjustment unit is used to adjust the initial predicted trajectory corresponding to the operation information according to the centerline predicted trajectory to obtain a target predicted trajectory of the vehicle.

13. An electronic device, characterized in that: The method comprises one or more processors and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the trajectory prediction method according to any one of claims 1 to 11.

14. A storage medium, characterized in that: The invention comprises a computer program, and when the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of the trajectory prediction method according to any one of claims 1 to 11.

15. A computer program product, characterized in that The method comprises a computer program or an instruction, and when the computer program or the instruction is executed by a processor, the steps of the trajectory prediction method according to any one of claims 1 to 11 are implemented.

16. A vehicle, characterized in that: The vehicle comprises the trajectory prediction device according to claim 12, or the electronic device according to claim 13, or the storage medium according to claim 14, or the computer program product according to claim 15.

Images