A trajectory prediction method, device and vehicle networking device

Abstract

The present invention provides a trajectory prediction method, apparatus and vehicle networking device. The method is applied to a host vehicle, and the method includes: obtaining n sets of historical trajectory points in a vehicle body coordinate system; wherein, one set of the historical trajectory points is obtained from the historical trajectory of a remote vehicle; screening the n sets of historical trajectory points to obtain m sets of target historical trajectory points; wherein, 1≤m≤n, and m and n are positive integers; mapping each historical trajectory point in the m sets of target historical trajectory points to the driving direction of the host vehicle to obtain a set of mapped coordinate points; and forming a predicted trajectory of the host vehicle according to the set of mapped coordinate points. The solution of the present invention can avoid the problem of prediction error caused by single or inaccurate sample data, and ensure the accuracy of trajectory prediction.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and in particular, to a trajectory prediction method, apparatus, and vehicle networking device. Background Art

[0002] V2X (Vehicle to Everything) is a communication method for vehicles to exchange information with the outside world, including: direct communication between vehicles (V2V), communication between vehicles and pedestrians (V2P), communication between vehicles and road infrastructure (V2I), and communication between vehicles and the cloud through a mobile network (V2N). V2X is a key technology for future intelligent transportation systems, which enables us to effectively obtain a series of traffic information such as real-time road conditions, road information, and pedestrian information, thereby improving driving safety, reducing congestion, and enhancing traffic efficiency.

[0003] Currently, the V2V scenarios mainly include 9 scenarios such as forward collision warning and intersection collision warning. The triggering of these scenarios all requires determining the target classification according to the relative position relationship between the host vehicle and the remote vehicle. When the target classification meets the conditions, the relevant warning functions are triggered. In a mapless scenario, the input of the target classification algorithm depends on the output of the trajectory prediction algorithm. To ensure the correctness of the target classification, the accuracy of the trajectory prediction must be guaranteed.

[0004] In a curve scenario in a mapless mode, the existing trajectory predictions are mainly divided into two categories: First, for short-term prediction, generally predicting the trajectory of a vehicle in the next 0-1 second, mainly based on the vehicle kinematic model, including: Constant Velocity (CV), Constant Acceleration (CA), CTRV (Constant Turn Rate and Velocity), and Constant Curvature and Acceleration (CCA). Second, for long-term prediction, generally predicting the trajectory of a vehicle in the next 1-10 seconds, and the common methods include: Kalman filter model, Hidden Markov model, Long Short-Term Memory network model (LSTM), etc.

[0005] The existing model-based trajectory prediction methods will bring large prediction errors when the sample data is single or not accurate enough. Therefore, how to ensure the accuracy of trajectory prediction is an urgent problem to be solved. Summary of the Invention

[0006] The present invention provides a trajectory prediction method, apparatus, and vehicle networking device, which solve the problem that the existing model-based trajectory prediction methods will bring large prediction errors when the sample data is single or not accurate enough.

[0007] In a first aspect, an embodiment of the present invention provides a trajectory prediction method, which is applied to a host vehicle. The method includes:

[0008] Obtain n sets of historical trajectory points in the vehicle body coordinate system; wherein, one set of historical trajectory points is obtained from the historical trajectory of a remote vehicle;

[0009] Screen the n sets of historical trajectory points to obtain m sets of target historical trajectory points; wherein, 1≤m≤n, and m and n are positive integers;

[0010] Map each historical trajectory point in the m sets of target historical trajectory points to the driving direction of the host vehicle to obtain a set of mapped coordinate points;

[0011] Form the predicted trajectory of the host vehicle according to the set of mapped coordinate points.

[0012] Optionally, the screening of the n sets of historical trajectory points to obtain m sets of target historical trajectory points includes:

[0013] Screen t sets of first historical trajectory points that meet the first screening rule from the n sets of historical trajectory points; 1≤t≤n, and t is a positive integer;

[0014] Based on the priority screening rule, obtain the m sets of target historical trajectory points with the highest priority from the t sets of first historical trajectory points: wherein, the priority screening rule is determined by the minimum inclination angle between the historical trajectory corresponding to each set of first historical trajectory points and the driving direction of the host vehicle.

[0015] Optionally, the first screening rule includes:

[0016] In the vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the abscissa of the first trajectory point in the historical trajectory corresponding to the set of historical trajectory points is less than the abscissa of the current position of the host vehicle;

[0017] The broken-line distance between the target trajectory point and the current position of the remote vehicle is greater than a preset distance threshold; wherein, the target trajectory point is the trajectory point with the smallest distance from the host vehicle in each set of historical trajectory points;

[0018] The absolute value of the minimum inclination angle is less than a preset inclination angle threshold;

[0019] In the vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the absolute value of the lateral offset between the host vehicle and the historical trajectory corresponding to the set of historical trajectory points is less than a preset offset threshold; wherein, the lateral offset is the distance between the straight line corresponding to the minimum inclination angle and the host vehicle.

[0020] Optionally, the priority screening rule includes: the minimum tilt angle is negatively correlated with the priority of the first historical trajectory point set.

[0021] Optionally, the mapping of each historical trajectory point in the m target historical trajectory point sets to the driving direction of the host vehicle to obtain a set of mapped coordinate points includes:

[0022] Based on a preset mapping rule, map each historical trajectory point in the m target historical trajectory point sets to the driving direction of the host vehicle to obtain a set of mapped coordinate points;

[0023] wherein, the preset mapping rule is related to the lateral distance and the tilt angle corresponding to each historical trajectory point in the target historical trajectory point set; the lateral offset is the distance between the straight line corresponding to the minimum tilt angle of each historical trajectory and the host vehicle.

[0024] Optionally, the preset mapping rule includes:

[0025] If the lateral offset between the host vehicle and the target vehicle is greater than 0, the mapped coordinate point is on the first side of the historical trajectory of the target vehicle, and the first side is the right side of the driving direction of the target vehicle;

[0026] If the lateral offset between the host vehicle and the target vehicle is less than 0, the mapped coordinate point is on the second side of the historical trajectory of the target vehicle, and the second side is the left side of the driving direction of the target vehicle.

[0027] Optionally, the preset mapping rule includes:

[0028] When the tilt angle θ corresponding to the i-th historical trajectory point i is in the range of (0, π) and d > 0, or θ i is in the range of (π, 2π) and d < 0, the mapped coordinate point corresponding to the i-th historical trajectory point is P1(x mapping_1 , y mapping_1 ), where:

[0029]

[0030] y mapping_1 = k i * x mapping_1 + b i ;

[0031] When the tilt angle θ corresponding to the i-th historical trajectory point i is in the range of (0, π) and d < 0, or θ iWhen the value range of maPPing_2 is (π, 2π) and d > 0, the mapped coordinate point corresponding to the i-th historical trajectory point is P2(x mapping_2 ), y

[0032]

[0033] where: mapping_2 y i = k mapping_2 * x i + b

[0034] Among them, the i-th historical trajectory point is any historical trajectory point in each of the target historical trajectory point sets, i ≥ 1 and i is a positive integer; (x i , y i ) is the coordinate of the i-th historical trajectory point; d is the lateral offset; B = 2 * k i * b i - 2 * x i - 2 * k i * y i ; C = x i 2 + b i 2 - 2 * b i * y i + y i 2 - d 2 ; θ i is the inclination angle corresponding to the i-th historical trajectory point; k i is the slope of the normal line corresponding to the first straight line at the i-th historical trajectory point, the first straight line is the straight line where the i-th historical trajectory point and the i + 1-th historical trajectory point are located, the i + 1-th historical trajectory point and the i-th historical trajectory point are on the same historical trajectory, and the i + 1-th historical trajectory point is adjacent to the i-th historical trajectory point; b i is the longitudinal intercept of the straight line where the normal line is located in the vehicle body coordinate system, and the vehicle body coordinate system takes the current position of the host vehicle as the coordinate origin.

[0035] Optionally, after obtaining the predicted trajectory according to the set of mapped coordinate points, the method further includes:

[0036] Sampling the predicted trajectory according to a first sampling distance to obtain a set of trajectory prediction points; wherein, the first sampling distance is related to the sampling time interval and the vehicle speed of the host vehicle.

[0037] In a second aspect, an embodiment of the present invention provides a vehicle networking device, including: a transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the trajectory prediction method described in the first aspect are implemented.

[0038] In a third aspect, an embodiment of the present invention provides a trajectory prediction device applied to a host vehicle, including:

[0039] An acquisition module, configured to acquire n sets of historical trajectory points; wherein, one set of historical trajectory points is obtained from the historical trajectory of a remote vehicle;

[0040] A screening module, configured to screen the n sets of historical trajectory points to obtain m sets of target historical trajectory points; wherein, 1 ≤ m ≤ n, and m and n are positive integers;

[0041] A mapping module, configured to map each historical trajectory point in the m sets of target historical trajectory points to the driving direction of the host vehicle to obtain a set of mapped coordinate points;

[0042] A generation module, configured to form a predicted trajectory of the host vehicle according to the set of mapped coordinate points.

[0043] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. The computer program, when executed by a processor, implements the steps of the trajectory prediction method described in the first aspect.

[0044] The beneficial effects of the above technical solutions of the present invention are as follows:

[0045] In the above solution, by acquiring n sets of historical trajectory points of n remote vehicles and screening the n sets of historical trajectory points, m sets of target historical trajectory points are obtained. Based on the m sets of target historical trajectory points, a forward road map can be constructed in a mapless scenario. Further, each historical trajectory point in the m sets of target historical trajectory points is mapped to the driving direction of the host vehicle to obtain a set of mapped coordinate points, and a predicted trajectory of the host vehicle is formed according to the set of mapped coordinate points. In this way, a predicted trajectory of the host vehicle can be obtained in a mapless scenario. In this embodiment, by acquiring multiple historical trajectories of the RV, accurate prediction of the trajectory of the host vehicle can be performed without performing trajectory prediction based on a model, which can avoid measurement errors caused by single or inaccurate samples, and has real-time performance. Moreover, by mapping the m sets of target historical trajectory points corresponding to the m historical trajectories, a predicted trajectory of the vehicle itself is obtained, and the prediction effect is more stable and the robustness is stronger. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flowchart showing the trajectory prediction method according to an embodiment of the present invention;

[0047] Figure 2 Schematic diagram of sampling historical trajectory points in an embodiment of the present invention;

[0048] Figure 3 Schematic diagram of screening a set of trajectory points in an embodiment of the present invention;

[0049] Figure 4 Schematic diagram of determining mapping point coordinates in an embodiment of the present invention;

[0050] Figure 5 Structural block diagram of a trajectory prediction device in an embodiment of the present invention;

[0051] Figure 6 Structural block diagram of a vehicle networking device of the present invention. Detailed implementation manners

[0052] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help a comprehensive understanding of the embodiments of the present invention. Therefore, those skilled in the art should clearly understand that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. In addition, descriptions of known functions and structures are omitted for clarity and conciseness.

[0053] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that a specific feature, structure or characteristic related to the embodiment is included in at least one embodiment of the present invention. Therefore, the "in one embodiment" or "in an embodiment" that appears throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner.

[0054] In various embodiments of the present invention, it should be understood that the magnitudes of the serial numbers of the following processes do not mean the order of execution is prior or subsequent, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0055] In addition, the terms "system" and "network" are often used interchangeably herein.

[0056] In the embodiments provided in the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0057] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0058] Specifically, an embodiment of the present invention provides a trajectory prediction, device and vehicle networking device, which solves the problem that the existing model-based trajectory prediction method will bring large prediction errors when the sample data is single or inaccurate.

[0059] The First Embodiment

[0060] As Figure 1 shown, an embodiment of the present invention provides a trajectory prediction method, which is applied to a host vehicle (HV), and specifically includes the following steps:

[0061] Step 101: Obtain n historical trajectory point sets in the body coordinate system; where, one of the historical trajectory point sets is obtained from the historical trajectory of a remote vehicle (RV).

[0062] In this step, the on-board unit (OBU) located in the RV is responsible for broadcasting the historical trajectory of the RV as part of the basic safety message (BSM) message through the direct communication interface PC5. The OBU on the HV is responsible for receiving and parsing the BSM message of the RV to obtain the historical trajectory of each remote vehicle. Each historical trajectory is a set of historical trajectory point coordinates, and each historical trajectory point set is a set of several historical trajectory point coordinates of the RV obtained according to a certain sampling rule.

[0063] Specifically, when implemented, the sampling rule of the historical trajectory points in each historical trajectory point set includes:

[0064] Refer to Figure 2 , assuming that the RV travels from point A to point B. If points A and B are not on the same straight line, after extending the normal vectors of the headings of points A and B, they will intersect at a point O. Point O is the center of the circle formed by the arc from point A to point B. Connect A and B to form line segment AB. Draw a perpendicular line on line segment AB, which intersects the arc AB at point C, and the foot of the perpendicular is point D. The length of line segment CD is recorded as the chord error. If the chord error CD is greater than the chord error threshold (ChordErrorThreshold), the coordinates of point B will be added to the historical trajectory point set.

[0065] It should be noted that the historical trajectory point coordinates sent by the remote vehicle are coordinate points in the WGS84 coordinate system, which are used to describe the vehicle's driving trajectory. Optionally, generally, the number of trajectory points in each set of historical trajectory points does not exceed 23. In specific applications, the historical trajectory point coordinates are converted from the WGS84 coordinate system to the ENU coordinate system, and then from the ENU coordinate system to the FLU vehicle body coordinate system, and finally, the set of historical trajectory points of each historical trajectory in the vehicle body coordinate system is obtained.

[0066] Specifically, the WGS84 coordinate system is a global geographic coordinate system or a longitude-latitude-altitude coordinate system, that is, (longitude, latitude, and altitude). That is, in the WGS84 coordinate system, each coordinate point includes three dimensions: latitude, longitude, and elevation. In this disclosure, elevation is not considered, and it is defaulted that all points are at the same height.

[0067] The ENU coordinate system is a local tangent plane coordinate system with the user's location as the coordinate origin. The coordinate system is defined as follows: the X-axis points to the east; the Y-axis points to the north; the Z-axis points to the zenith. In this disclosure, the Z-direction coordinate is not considered, and it is defaulted that all points are at the same height.

[0068] The FLU coordinate system is a vehicle body coordinate system with the current position of the HV as the coordinate origin. The coordinate system is defined as follows: the positive direction of the X-axis is the heading angle of the HV, and the normal vector of the direction vector of the HV heading angle is the positive direction of the Y-axis.

[0069] Step 102: Screen the n sets of historical trajectory points to obtain m sets of target historical trajectory points; where 1 ≤ m ≤ n, and m and n are positive integers;

[0070] Optionally, in the scenario where it is determined that the host vehicle is driving outside an intersection, screen the n sets of historical trajectory points to obtain m sets of target historical trajectory points.

[0071] In specific implementation, if the absolute value of the difference between the heading angles of the host vehicle and the remote vehicle is within the first range, it is determined that there is an intersection within a certain distance in front of the host vehicle, and the host vehicle is in the scenario of driving at an intersection; if the absolute value of the difference between the heading angles of the host vehicle and the remote vehicle is not within the first range, it is determined that there is no intersection within a certain distance in front of the host vehicle, and the host vehicle is in the scenario of driving outside an intersection.

[0072] Optionally, the first range is: [90 - AngleThreshold, 90 + AngleThreshold]; where AngleThreshold is the intersection angle judgment threshold, such as 10 degrees.

[0073] Step 103: Map each historical trajectory point in the m sets of target historical trajectory points to the driving direction of the host vehicle to obtain a set of mapped coordinate points;

[0074] In this step, the historical trajectory points in the m target historical trajectory point sets can be used to construct the forward road map in a mapless scenario. By mapping each historical trajectory point in the m target historical trajectory point sets to the driving direction of the host vehicle, a set of mapped coordinate points can be obtained, and based on this set of mapped coordinate points, the predicted trajectory of the host vehicle can be obtained in a mapless scenario.

[0075] Step 104: Form the predicted trajectory of the host vehicle according to the set of mapped coordinate points.

[0076] In this step, for the coordinate points in the set of mapped coordinate points, connecting two adjacent mapped coordinate points pairwise in position can obtain the predicted trajectory of the host vehicle.

[0077] In the above embodiment, by obtaining n historical trajectory point sets of n remote vehicles and screening the n historical trajectory point sets, m target historical trajectory point sets are obtained. Based on the m target historical trajectory point sets, the forward road map can be constructed in a mapless scenario. Further, each historical trajectory point in the m target historical trajectory point sets is mapped to the driving direction of the host vehicle to obtain a set of mapped coordinate points, and according to the set of mapped coordinate points, the predicted trajectory of the host vehicle is formed. In this way, the predicted trajectory of the host vehicle can be obtained in a mapless scenario. In this embodiment, by obtaining multiple historical trajectories of the RV, the trajectory prediction of the host vehicle can be accurately predicted without relying on a model for trajectory prediction, which can avoid measurement errors caused by single or inaccurate samples, and has real-time performance. Moreover, by mapping the m target historical trajectory point sets corresponding to the m historical trajectories, the predicted trajectory of the vehicle itself is obtained, and the prediction effect is more stable and the robustness is stronger.

[0078] In an embodiment of the present application, the screening of the n historical trajectory point sets to obtain m target historical trajectory point sets includes:

[0079] Selecting t first historical trajectory point sets that meet the first screening rule from the n historical trajectory point sets; 1≤t≤n, where n and t are positive integers;

[0080] Based on the priority screening rule, m target historical trajectory point sets with the highest priority are obtained from the t first historical trajectory point sets: where the priority screening rule is determined by the minimum inclination angle between the historical trajectory corresponding to each first historical trajectory point set and the driving direction of the host vehicle.

[0081] It should be noted that each historical trajectory point corresponds to an inclination angle, which is defined as follows: in the vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the vector formed by the current historical trajectory point and the adjacent next historical trajectory point is denoted as the direction vector of the historical trajectory point (note: the direction vector corresponding to the last historical trajectory point is the same as the direction vector corresponding to its previous historical trajectory point), and the included angle formed by the direction vector corresponding to the current historical trajectory point and the heading angle of the host vehicle (i.e., the driving direction of the host vehicle) is the inclination angle of the current historical trajectory point. The value range of the inclination angle is: [0, 2π]. Among them, the minimum inclination angle of each historical trajectory is: the inclination angle of the historical trajectory point closest to the host vehicle.

[0082] When specifically implemented, in the vehicle body coordinate system of the HV, on the historical trajectory of a remote vehicle, three consecutive points closest to the host vehicle are selected (that is, three consecutive points with the smallest sum of the straight-line distances to the host vehicle). If these three points are not on a straight line, these three points are denoted as P1, P2, and P3. The first straight line P1P2 is obtained by using P1 and P2, and the second straight line P2P3 is obtained by using P2 and P3. The minimum inclination angle of this historical trajectory is the minimum value of the included angles between the first straight line and the second straight line and the X-axis. If the three consecutive points closest to the host vehicle are on a straight line H, then the minimum inclination angle of this historical trajectory is the included angle between the straight line H and the positive direction of the X-axis.

[0083] In a specific embodiment of the present application, the first screening rule includes the following 4 conditions:

[0084] Condition 1: In the vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the abscissa of the first trajectory point in the historical trajectory corresponding to the historical trajectory point set is less than the abscissa of the current position of the host vehicle;

[0085] In this Condition 1, the first historical trajectory point in the historical trajectory of the remote vehicle is behind the current position of the host vehicle, that is, in the vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the abscissa of the first trajectory point is less than 0. The first historical trajectory point can be understood as the initial position point of the historical trajectory.

[0086] Condition 2: The broken-line distance between the target trajectory point and the current position of the remote vehicle is greater than a preset distance threshold; wherein, the target trajectory point is the trajectory point with the smallest distance from the host vehicle in each historical trajectory point set;

[0087] In this Condition 2, the broken-line distance is the distance of the line segment formed by connecting two adjacent historical trajectory points in sequence. Exemplarily, the preset distance threshold is 100 meters.

[0088] Condition 3: The absolute value of the minimum inclination angle is less than a preset inclination angle threshold;

[0089] In this condition 3, the minimum inclination angle between the historical trajectory of the remote vehicle and the driving direction of the host vehicle is less than a preset inclination angle threshold, for example, the minimum inclination angle is less than 10 degrees.

[0090] Condition 4: In the vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the absolute value of the lateral offset of the historical trajectory corresponding to the host vehicle and the historical trajectory point set is less than a preset offset threshold; wherein, the lateral offset is the distance between the straight line corresponding to the minimum inclination angle and the host vehicle.

[0091] When specifically implemented, assume that on a historical trajectory of a remote vehicle, three consecutive points closest to the host vehicle are selected. If these three points are not on a straight line, these three points are denoted as P1, P2, and P3. The first straight line P1P2 is obtained by using P1 and P2, and the second straight line P2P3 is obtained by using P2 and P3. Assume that the minimum inclination angle of this historical trajectory is the angle between the first straight line P1P2 and the X-axis. Then, the distance from the origin to the first straight line P1P2 is the lateral offset d of this historical trajectory. If the three consecutive points closest to the host vehicle are on a straight line H, then the minimum inclination angle of this historical trajectory is the angle between the straight line H and the positive direction of the X-axis, and the distance from the origin to the straight line H is the lateral offset d between the host vehicle and this historical trajectory.

[0092] Exemplarily, screening t first historical trajectory point sets that meet the first screening rule from n historical trajectory point sets may include the following steps. See Figure 3 :

[0093] Step 31. Determine whether the abscissa of the first trajectory point in a historical trajectory corresponding to each historical trajectory point set is less than 0; if so, proceed to step two, otherwise end.

[0094] Step 32. Select three consecutive historical trajectory points closest to the host vehicle, and determine whether these three consecutive historical trajectory points are on a straight line H; if so, proceed to step 33, otherwise proceed to step 34.

[0095] Step 33. Take the angle between the straight line H and the positive direction of the X-axis as the minimum inclination angle of this historical trajectory, and take the distance from the origin to the straight line H as the lateral offset d between the host vehicle and this historical trajectory.

[0096] Step 34. Denote these three consecutive historical trajectory points as P1, P2, and P3. The first straight line P1P2 is obtained by using P1 and P2, and the second straight line P2P3 is obtained by using P2 and P3. Determine the minimum value of the angles between the first straight line P1P2 and the second straight line P2P3 and the X-axis as the minimum inclination angle of this historical trajectory; determine the distance from the origin to the straight line (the first straight line or the second straight line) corresponding to the minimum inclination angle as the lateral offset d of this historical trajectory.

[0097] Step 35: Determine whether the minimum tilt angle is less than a preset tilt angle threshold and the absolute value of the lateral offset is less than a preset offset threshold; if so, proceed to Step 36, otherwise end.

[0098] Step 36: Take this set of historical trajectory points as the first set of historical trajectory points.

[0099] In the above embodiment, from n sets of historical trajectory points, the sets of historical trajectory points that meet the above Conditions 1 to 4 are screened out and used as t first sets of historical trajectory points.

[0100] In a specific embodiment of the present application, the priority screening rule includes: the minimum tilt angle is negatively correlated with the priority of the first set of historical trajectory points.

[0101] In this embodiment, the minimum tilt angle of the historical trajectory corresponding to each first set of historical trajectory points is obtained, and the magnitudes of the minimum tilt angles are arranged in ascending order. The smaller the minimum tilt angle, the higher the priority of the first set of historical trajectory points; m first sets of historical trajectory points with the highest priority are obtained from the t first sets of historical trajectory points and used as m sets of target historical trajectory points.

[0102] In a specific embodiment, the mapping of each historical trajectory point in the m sets of target historical trajectory points to the driving direction of the host vehicle to obtain a set of mapped coordinate points includes:

[0103] Based on a preset mapping rule, each historical trajectory point in the m sets of target historical trajectory points is mapped to the driving direction of the host vehicle to obtain a set of mapped coordinate points;

[0104] wherein, the preset mapping rule is related to the lateral distance and the tilt angle corresponding to each historical trajectory point in the set of target historical trajectory points; the lateral offset is the distance between the line corresponding to the minimum tilt angle of each historical trajectory and the host vehicle.

[0105] It should be noted that each historical trajectory point corresponds to a tilt angle, which is defined as: in the vehicle body coordinate system with the host vehicle as the coordinate origin, the vector formed by the current historical trajectory point and the adjacent next historical trajectory point is denoted as the direction vector of the historical trajectory point (note: the direction vector corresponding to the last historical trajectory point is the same as the direction vector corresponding to its previous historical trajectory point), and the angle formed by the direction vector corresponding to the current historical trajectory point and the host vehicle's heading angle (i.e., the driving direction of the host vehicle) is the tilt angle of the current historical trajectory point. The value range of the tilt angle is: [0, 2π].

[0106] During specific implementation, the classification discussion on how to correctly map the historical trajectory points of the remote vehicle to the driving direction of the local vehicle can be carried out based on the value range of the tilt angle corresponding to the historical trajectory points of the remote vehicle and the positive and negative of the lateral offset.

[0107] In the above embodiments, since the inclination angle of the historical trajectory points is related to the driving direction of the host vehicle, the inclination angle of the historical trajectory points can reflect the driving direction of the host vehicle. Thus, based on the inclination angle of the historical trajectory points and the lateral offset between each historical trajectory and the host vehicle, the historical trajectory points in the target set of historical trajectory points can be mapped to the driving direction of the host vehicle to obtain a set of mapped coordinate points.

[0108] Specifically, the preset mapping rule includes:

[0109] If the lateral offset between the host vehicle and the target remote vehicle is greater than 0, the mapped coordinate point is located on the first side of the historical trajectory of the target remote vehicle, and the first side is the right side of the driving direction of the target remote vehicle;

[0110] If the lateral offset between the host vehicle and the target remote vehicle is less than 0, the mapped coordinate point is located on the second side of the historical trajectory of the target remote vehicle, and the second side is the left side of the driving direction of the target remote vehicle.

[0111] That is, in the vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, if the coordinate origin is below the straight line closest to it, the lateral offset takes a positive value, and if the coordinate origin is above the straight line closest to it, the lateral offset takes a negative value. Among them, the straight line closest to the origin is the straight line corresponding to the minimum inclination angle of the historical trajectory.

[0112] Specifically, the preset mapping rule includes:

[0113] When the inclination angle θ corresponding to the i-th historical trajectory point i is in the range of (0, π) and d > 0, or θ i is in the range of (π, 2π) and d < 0, the mapped coordinate point corresponding to the i-th historical trajectory point is P1(x mapping_1 , y mapping_1 ), where:

[0114]

[0115] y mapping_1 = k i * x mapping_1 + b i ;

[0116] When the inclination angle θ corresponding to the i-th historical trajectory point i is in the range of (0, π) and d < 0, or θ i is in the range of (π, 2π) and d > 0, the mapped coordinate point corresponding to the i-th historical trajectory point is P2(x mapping_2 , ymapping_2 ),where:

[0117]

[0118] y mapping_2 = k i * x mapping_2 + b i ;

[0119] where the i-th historical trajectory point is any historical trajectory point in each of the target historical trajectory point sets, i ≥ 1 and i is a positive integer; (x i , y i ) is the coordinate of the i-th historical trajectory point; d is the lateral offset; B = 2 * k i * b i - 2 * x i - 2 * k i * y i ; C = x i 2 + b i 2 - 2 * b i * y i + y i 2 - d 2 ; θ i is the inclination angle corresponding to the i-th historical trajectory point; k i is the slope of the normal line corresponding to the first straight line at the i-th historical trajectory point. The first straight line is the straight line where the i-th historical trajectory point and the (i + 1)-th historical trajectory point are located. The (i + 1)-th historical trajectory point and the i-th historical trajectory point are on the same historical trajectory, and the (i + 1)-th historical trajectory point and the i-th historical trajectory point are adjacent; b i is the longitudinal intercept of the straight line where the normal line is located in the vehicle body coordinate system, and the vehicle body coordinate system takes the current position of the host vehicle as the coordinate origin.

[0120] Exemplarily, one target historical trajectory point set corresponds to one historical trajectory. For each historical trajectory, the lateral offset d between it and the host vehicle is obtained, as well as m historical trajectory points (x i , y i ) and the inclination angle θ i corresponding to each of its historical trajectory points (1 ≤ i ≤ m). As Figure 4 shown in, assume that the i-th historical trajectory point in a certain historical trajectory is point E, and the (i + 1)-th historical trajectory point is point F. The first straight line EF is the straight line determined by point E and point F. Denote the normal line of the first straight line at point E as straight line K, and denote the slope of straight line K as k i , and denote the longitudinal intercept of straight line K as bi , where k i = (-1) / tan(θ i ), b i = y i - k i * x i .

[0121] Find a point P on the line K, and point P is the mapping point (x mapping , y mapping ), such that the perpendicular distance from point P to the line L is d (i.e., the length of EP). Solve the system of equations:

[0122]

[0123] Where: B = 2 * k i * b i - 2 * x i - 2 * k i * y i , C = x i 2 + b i 2 - 2 * b i * y i + y i 2 - d 2 .

[0124] The coordinates of the mapping point P include the following cases:

[0125] Case 1: If the range of the inclination angle θ is (0, ) and d > 0, then the mapped point is P(x mapping , y mapping ), where:

[0126]

[0127] y mapping = k i * x mapping + b i ;

[0128] Case 2: If the range of the inclination angle θ is (0, ) and d < 0, then the mapped point is P(x mapping , y mapping ), where:

[0129]

[0130] y mapping = k i * x mapping + b i ;

[0131] Case 3: If the value range of the inclination angle θ is and d > 0, then the mapped point is P(x mapping , y mapping ), where:

[0132]

[0133] y mapping = k i * x mapping + b i ;

[0134] Case 4: If the value range of the inclination angle θ is and d < 0, then the mapped point is P(x mapping , y mapping ), where:

[0135]

[0136] y mapping = k i * x mapping + b i ;

[0137] Case 5: If the value range of the inclination angle θ is and d > 0, then the mapped point is P(x mapping , y mapping ), where:

[0138]

[0139] y mapping = k i * x mapping + b i ;

[0140] Case 6: If the value range of the inclination angle θ is and d < 0, then the mapped point is P(x mapping , y mapping ), where:

[0141]

[0142] y mapping = k i * x mapping + b i ;

[0143] Case 7: If the value range of the inclination angle θ is and d > 0, then the mapped point is P(x mapping , ymapping ),where:

[0144]

[0145] y mapping = k i * x mapping + b i ;

[0146] Case 8. If the range of the inclination angle θ is and d < 0, the mapped point is P(x mapping , y mapping ), where:

[0147]

[0148] y mapping = k i * x mapping + b i ;

[0149] In one embodiment, after obtaining the predicted trajectory according to the mapped coordinate point set, the method further includes:

[0150] Sampling the predicted trajectory according to a first sampling distance to obtain a set of trajectory prediction points; wherein, the first sampling distance is related to the sampling time interval and the vehicle speed of the host vehicle.

[0151] Specifically, on the predicted trajectory, points are taken at equal time intervals, and the sampling distance = time interval * the current speed of the vehicle itself (assuming the host vehicle has a constant speed), and a series of trajectory prediction points of the host vehicle can be obtained.

[0152] Among them, the maximum prediction time cannot exceed a preset duration threshold, and at the same time, the maximum prediction distance cannot exceed a preset distance threshold.

[0153] In one embodiment, before the step of screening the n historical trajectory point sets in step 102 to obtain m target historical trajectory point sets, it further includes:

[0154] For each historical trajectory, after parsing the historical trajectory point coordinates of the remote vehicle, linear interpolation processing is performed on two consecutive historical trajectory points to obtain a set of historical trajectory points after interpolation processing.

[0155] The following introduces an example of the trajectory prediction method. It mainly includes the following steps:

[0156] Step 1, in a non-intersection scenario, the host vehicle will obtain the historical trajectories of multiple remote vehicles. Each historical trajectory contains G interpolated historical trajectory points, and the coordinates of each point in the WGS84 coordinate system are: (latitude, longitude).

[0157] Step 2, convert the coordinates of the G interpolated historical trajectory points in the WGS84 coordinate system to the coordinates in the ENU coordinate system: (ENU _x , ENU_y). Further, convert the coordinates of each point in the ENU coordinate system to the coordinates in the FLU vehicle body coordinate system (x i , y i ).

[0158] Step 3, the host vehicle selects t first historical trajectory point sets through the first screening rule, and each first historical trajectory point set corresponds to a historical trajectory; if the number of the first historical trajectory point sets is less than 2, exit the trajectory prediction based on the historical trajectory and perform the trajectory prediction of the kinematic model; if the number of the first historical trajectory point sets is greater than or equal to 2, select the m first historical trajectory point sets with the highest priority as the m target historical trajectory point sets based on the priority screening rule.

[0159] Step 4, map the historical trajectory points in the m target historical trajectory point sets based on the mapping rule to obtain a series of mapped coordinate points, and then connect the mapped coordinate points in pairs as the predicted trajectory.

[0160] Step 5, perform sampling processing on the predicted trajectory to obtain a series of sampling points.

[0161] Specifically, points are taken at equal time intervals (T = 0.2s), and the sampling distance = time interval (0.2s) × the current speed of the host vehicle.

[0162] Exemplarily, the sampling of the trajectory prediction points is limited by time and distance, that is, the maximum prediction distance does not exceed 300 meters (i.e., the preset distance threshold is 300m), and at the same time, the longest prediction time does not exceed 10s (i.e., the preset duration threshold is 10s).

[0163] Second Embodiment

[0164] As Figure 5 shown, an embodiment of the present invention provides a trajectory prediction device 500, which is applied to the host vehicle and includes:

[0165] An acquisition module 501, configured to acquire n historical trajectory point sets; wherein, one of the historical trajectory point sets is obtained from the historical trajectory of a remote vehicle;

[0166] A screening module 502, configured to screen the n historical trajectory point sets to obtain m target historical trajectory point sets; where 1 ≤ m ≤ n, and m and n are positive integers;

[0167] A mapping module 503, configured to map each historical trajectory point in the m target historical trajectory point sets to the driving direction of the host vehicle to obtain a set of mapped coordinate points;

[0168] A generation module 504, configured to form a predicted trajectory of the host vehicle according to the set of mapped coordinate points.

[0169] Optionally, the screening module 502 includes:

[0170] A first screening sub-module, configured to screen and obtain t first historical trajectory point sets that meet the first screening rule from the n historical trajectory point sets; 1 ≤ t ≤ n, and t is a positive integer;

[0171] A second screening sub-module, configured to obtain the m target historical trajectory point sets with the highest priority from the t first historical trajectory point sets based on a priority screening rule: where the priority screening rule is determined by the minimum inclination angle between the historical trajectory corresponding to each first historical trajectory point set and the driving direction of the host vehicle.

[0172] Optionally, the first screening rule includes:

[0173] In a vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the abscissa of the first trajectory point in the historical trajectory corresponding to the historical trajectory point set is less than the abscissa of the current position of the host vehicle;

[0174] The broken line distance between the target trajectory point and the current position of the far vehicle is greater than a preset distance threshold; where the target trajectory point is the trajectory point with the smallest distance from the host vehicle in each historical trajectory point set;

[0175] The absolute value of the minimum inclination angle is less than a preset inclination angle threshold;

[0176] In a vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the absolute value of the lateral offset between the host vehicle and the historical trajectory corresponding to the historical trajectory point set is less than a preset offset threshold; where the lateral offset is the distance between the line corresponding to the minimum inclination angle and the host vehicle.

[0177] Optionally, the priority screening rule includes: the minimum inclination angle is negatively correlated with the priority of the first historical trajectory point set.

[0178] Optionally, the mapping module 503 is specifically configured to:

[0179] Based on a preset mapping rule, map each historical trajectory point in the m target historical trajectory point sets to the driving direction of the host vehicle to obtain a set of mapped coordinate points;

[0180] wherein, the preset mapping rule is related to the lateral distance and the inclination angle corresponding to each historical trajectory point in the target historical trajectory point set; the lateral offset is the distance between the straight line corresponding to the minimum inclination angle of each historical trajectory and the host vehicle.

[0181] Optionally, the preset mapping rule includes:

[0182] If the lateral offset between the host vehicle and the target vehicle is greater than 0, the mapped coordinate point is located on the first side of the historical trajectory of the target vehicle, and the first side is the right side of the driving direction of the target vehicle;

[0183] If the lateral offset between the host vehicle and the target vehicle is less than 0, the mapped coordinate point is located on the second side of the historical trajectory of the target vehicle, and the second side is the left side of the driving direction of the target vehicle.

[0184] Optionally, the preset mapping rule includes:

[0185] When the value range of the inclination angle θ corresponding to the i-th historical trajectory point is (0, π) and d > 0, or the value range of θ is (π, 2π) and d < 0, the mapped coordinate point corresponding to the i-th historical trajectory point is P1(x i , y i ), where: mapping_1 , y mapping_1 )

[0186]

[0187] y mapping_1 = k i * x mapping_1 + b i ;

[0188] When the value range of the inclination angle θ corresponding to the i-th historical trajectory point is (0, π) and d < 0, or the value range of θ is (π, 2π) and d > 0, the mapped coordinate point corresponding to the i-th historical trajectory point is P2(x i , y i ), where: mapping_2 , y mapping_2 )

[0189]

[0190] y mapping_2 = k i * x mapping_2 + bi ;

[0191] wherein, the i-th historical trajectory point is any historical trajectory point in each of the target historical trajectory sets, i≥1 and i is a positive integer; (x i , y i ) is the coordinate of the i-th historical trajectory point; d is the lateral offset; B = 2 * k i * b i - 2 * x i - 2 * k i * y i ; C = x i 2 + b i 2 - 2 * b i * y i + y i 2 - d 2 ; θ i is the inclination angle corresponding to the i-th historical trajectory point; k i is the slope of the normal line corresponding to the first straight line at the i-th historical trajectory point, the first straight line is the straight line where the i-th historical trajectory point and the (i + 1)-th historical trajectory point are located, the (i + 1)-th historical trajectory point and the i-th historical trajectory point are on the same historical trajectory, and the (i + 1)-th historical trajectory point is adjacent to the i-th historical trajectory point; b i is the longitudinal intercept of the straight line where the normal line is located in the vehicle body coordinate system, and the vehicle body coordinate system takes the current position of the host vehicle as the coordinate origin.

[0192] Optionally, the above device 500 further includes:

[0193] a sampling processing module, configured to perform sampling processing on the predicted trajectory according to a first sampling distance to obtain a trajectory prediction point set; wherein, the first sampling distance is related to the sampling time interval and the vehicle speed of the host vehicle.

[0194] The second embodiment of the present invention corresponds to the method of the above first embodiment. All the implementation means in the above first embodiment are applicable to the embodiment of the trajectory prediction device 500 and can achieve the same technical effects.

[0195] Third Embodiment

[0196] To better achieve the above object, as Figure 6 shown, the third embodiment of the present invention further provides an Internet of Vehicles device, which is applied to the host vehicle and includes:

[0197] A processor 600; and a memory 620 connected to the processor 600 through a bus interface, where the memory 620 is used to store programs and data used by the processor 600 when performing operations, and the processor 600 calls and executes the programs and data stored in the memory 620.

[0198] Among them, a transceiver 610 is connected to the bus interface and is used to receive and send data under the control of the processor 600; the processor 600 is used to read the program in the memory 620 and execute the following steps:

[0199] Obtain n sets of historical trajectory points in the vehicle body coordinate system; among them, one set of historical trajectory points is obtained from the historical trajectory of a far vehicle;

[0200] Screen the n sets of historical trajectory points to obtain m sets of target historical trajectory points; where 1 ≤ m ≤ n, and m and n are positive integers;

[0201] Map each historical trajectory point in the m sets of target historical trajectory points to the driving direction of the host vehicle to obtain a set of mapped coordinate points;

[0202] Form the predicted trajectory of the host vehicle according to the set of mapped coordinate points.

[0203] Among them, in Figure 6 The bus architecture may include any number of interconnected buses and bridges, specifically various circuits represented by one or more processors represented by the processor 600 and a memory represented by the memory 620 are linked together. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, so they will not be further described herein. The bus interface provides an interface. The transceiver 610 may be multiple components, that is, including a transmitter and a transceiver, and provides a unit for communicating with various other devices on the transmission medium. For different terminals, the user interface 630 may also be an interface capable of externally connecting and internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, etc. The processor 600 is responsible for managing the bus architecture and general processing, and the memory 620 may store data used by the processor 600 when performing operations.

[0204] Optionally, the processor 600 is used to read the program in the memory 620 and execute the following steps:

[0205] Screen from the n sets of historical trajectory points to obtain t sets of first historical trajectory points that meet the first screening rule; 1 ≤ t ≤ n, and t is a positive integer;

[0206] Based on the priority screening rule, m target historical trajectory point sets with the highest priority are obtained from the t first historical trajectory point sets: wherein, the priority screening rule is determined by the minimum inclination angle between the historical trajectory corresponding to each first historical trajectory point set and the driving direction of the host vehicle.

[0207] Optionally, the first screening rule includes:

[0208] In the vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the abscissa of the first trajectory point in the historical trajectory corresponding to the historical trajectory point set is less than the abscissa of the current position of the host vehicle;

[0209] The broken line distance between the target trajectory point and the current position of the far vehicle is greater than a preset distance threshold; wherein, the target trajectory point is the trajectory point with the smallest distance from the host vehicle in each historical trajectory point set;

[0210] The absolute value of the minimum inclination angle is less than a preset inclination angle threshold;

[0211] In the vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the absolute value of the lateral offset between the host vehicle and the historical trajectory corresponding to the historical trajectory point set is less than a preset offset threshold; wherein, the lateral offset is the distance between the straight line corresponding to the minimum inclination angle and the host vehicle.

[0212] Optionally, the priority screening rule includes: the minimum inclination angle is negatively correlated with the priority of the first historical trajectory point set.

[0213] Optionally, the processor 600 is configured to read the program in the memory 620 and execute the following steps:

[0214] Based on a preset mapping rule, each historical trajectory point in the m target historical trajectory point sets is mapped to the driving direction of the host vehicle to obtain a set of mapped coordinate points;

[0215] Wherein, the preset mapping rule is related to the lateral distance and the inclination angle corresponding to each historical trajectory point in the target historical trajectory point set; the lateral offset is the distance between the straight line corresponding to the minimum inclination angle of each historical trajectory and the host vehicle.

[0216] Optionally, the preset mapping rule includes:

[0217] If the lateral offset between the host vehicle and the target far vehicle is greater than 0, the mapped coordinate point is located on the first side of the historical trajectory of the target far vehicle, and the first side is the right side of the driving direction of the target far vehicle;

[0218] If the lateral offset between the host vehicle and the target remote vehicle is less than 0, the mapped coordinate point is located on the second side of the historical trajectory of the target remote vehicle, and the second side is the left side of the driving direction of the target remote vehicle.

[0219] Optionally, the preset mapping rule includes:

[0220] When the inclination angle θ corresponding to the i-th historical trajectory point i is in the range of (0, π) and d > 0, or θ I is in the range of (π, 2π) and d < 0, the mapped coordinate point corresponding to the i-th historical trajectory point is P1(x mapping_1 , y mapping_1 ), where:

[0221]

[0222] y mapping_1 = k i * x mapping_1 + b i ;

[0223] When the inclination angle θ corresponding to the i-th historical trajectory point i is in the range of (0, π) and d < 0, or θ i is in the range of (π, 2π) and d > 0, the mapped coordinate point corresponding to the i-th historical trajectory point is P2(x mapping_2 , y mapping_2 ), where:

[0224]

[0225] y m3pping_2 = k i * x mapping_2 + b i ;

[0226] Among them, the i-th historical trajectory point is any historical trajectory point in each of the target historical trajectory points sets, i ≥ 1 and i is a positive integer; (x i , y i ) is the coordinate of the i-th historical trajectory point; d is the lateral offset; B = 2 * k i * b i - 2 * x i - 2 * k i * y i ; C = x i 2 + b i 2 - 2 * b i * y i+y i 2 -d 2 ; θ i is the inclination angle corresponding to the i-th historical trajectory point; k i is the slope of the normal line at the i-th historical trajectory point of the first straight line. The first straight line is the straight line where the i-th historical trajectory point and the (i + 1)-th historical trajectory point are located. The (i + 1)-th historical trajectory point and the i-th historical trajectory point are located in the same historical trajectory, and the (i + 1)-th historical trajectory point is adjacent to the i-th historical trajectory point; b i is the longitudinal intercept of the straight line where the normal line is located in the vehicle body coordinate system, and the vehicle body coordinate system takes the current position of the host vehicle as the coordinate origin.

[0227] Optionally, the processor 600 is configured to read the program in the memory 620 and execute the following steps:

[0228] Sample the predicted trajectory according to the first sampling distance to obtain a set of trajectory prediction points; wherein, the first sampling distance is related to the sampling time interval and the vehicle speed of the host vehicle.

[0229] The present invention provides a method. By obtaining n sets of historical trajectory points of n remote vehicles and screening the n sets of historical trajectory points, m sets of target historical trajectory points are obtained. Based on the m sets of target historical trajectory points, a forward road map can be constructed in a mapless scenario. Further, each historical trajectory point in the m sets of target historical trajectory points is mapped to the driving direction of the host vehicle to obtain a set of mapped coordinate points, and according to the set of mapped coordinate points, the predicted trajectory of the host vehicle is formed. In this way, the predicted trajectory of the host vehicle can be obtained in a mapless scenario. In this embodiment, by obtaining multiple historical trajectories of the RV, the trajectory prediction of the host vehicle can be accurately predicted, without requiring a large amount of computing power, and having real-time performance. Moreover, by mapping the m sets of target historical trajectory points corresponding to the m historical trajectories, the predicted trajectory of the host vehicle is obtained, and the prediction effect is more stable and the robustness is stronger.

[0230] Those skilled in the art can understand that all or part of the steps of implementing the above embodiments can be completed by hardware, or can be completed by instructing relevant hardware through a computer program. The computer program includes instructions for executing part or all of the steps of the above method; and the computer program can be stored in a readable storage medium, and the storage medium can be any form of storage medium.

[0231] In addition, the specific embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the method in the first embodiment above are implemented. And it can achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0232] In addition, it should be noted that in the device and method of the present invention, obviously, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations shall be regarded as equivalent solutions of the present invention. Moreover, the steps of performing the above series of processes can naturally be executed chronologically in the order described, but it is not necessary to be executed necessarily in chronological order. Some steps can be executed in parallel or independently of each other. For those of ordinary skill in the art, it is possible to understand that all or any steps or components of the method and device of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in the form of hardware, firmware, software, or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0233] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a well-known general-purpose device. Therefore, the object of the present invention can also be achieved only by providing a program product containing program code for implementing the method or device. That is to say, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be noted that in the device and method of the present invention, obviously, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations shall be regarded as equivalent solutions of the present invention. Moreover, the steps of performing the above series of processes can naturally be executed chronologically in the order described, but it is not necessary to be executed necessarily in chronological order. Some steps can be executed in parallel or independently of each other.

[0234] The above is the preferred embodiment of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle described in the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A trajectory prediction method, characterized in that, Applied to the host vehicle, the method includes: Obtaining n sets of historical trajectory points in the vehicle body coordinate system; wherein, one set of historical trajectory points is obtained from the historical trajectory of a remote vehicle; Screening the n sets of historical trajectory points to obtain m sets of target historical trajectory points; wherein, 1 ≤ m ≤ n, and m and n are positive integers; Mapping each historical trajectory point in the m sets of target historical trajectory points to the driving direction of the host vehicle to obtain a set of mapped coordinate points; Forming a predicted trajectory of the host vehicle according to the set of mapped coordinate points; Wherein, the screening the n sets of historical trajectory points to obtain m sets of target historical trajectory points includes: Screening from the n sets of historical trajectory points to obtain t sets of first historical trajectory points that meet the first screening rule; 1 ≤ t ≤ n, and t is a positive integer; Based on the priority screening rule, obtaining the m sets of target historical trajectory points with the highest priority from the t sets of first historical trajectory points: wherein, the priority screening rule is determined by the minimum inclination angle between the historical trajectory corresponding to each set of first historical trajectory points and the driving direction of the host vehicle, and the minimum inclination angle is: the inclination angle of the historical trajectory point closest to the host vehicle; Wherein, the first screening rule includes: In the vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the abscissa of the first trajectory point in the historical trajectory corresponding to the set of historical trajectory points is less than the abscissa of the current position of the host vehicle; The broken-line distance between the target trajectory point and the current position of the remote vehicle is greater than a preset distance threshold; wherein, the target trajectory point is the trajectory point with the smallest distance from the host vehicle in each set of historical trajectory points; The absolute value of the minimum inclination angle is less than a preset inclination angle threshold; In the vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the absolute value of the lateral offset between the host vehicle and the historical trajectory corresponding to the set of historical trajectory points is less than a preset offset threshold; wherein, the lateral offset is the distance between the straight line corresponding to the minimum inclination angle and the host vehicle; Wherein, the mapping each historical trajectory point in the m sets of target historical trajectory points to the driving direction of the host vehicle to obtain a set of mapped coordinate points includes: Based on a preset mapping rule, mapping each historical trajectory point in the m sets of target historical trajectory points to the driving direction of the host vehicle to obtain a set of mapped coordinate points; The preset mapping rule includes: At the inclination angle θ corresponding to the i-th historical trajectory point i whose value range is (0, π) and d > 0, or, θ i whose value range is (π, 2π) and d < 0, the mapped coordinate point corresponding to the i-th historical trajectory point is P1(x mapping_1 , y mapping_1 ), where: y mapping_1 = k i * x mapping_1 + b i ; At the inclination angle θ corresponding to the i-th historical trajectory point i where the value range is (0, π) and d < 0, or, θ i where the value range is (π, 2π) and d > 0, the mapped coordinate point corresponding to the i-th historical trajectory point is P2(x mapping_2 , y mapping_2 ), where: y mapping_2 = k i * x mapping_2 + b i ; Wherein, the i-th historical trajectory point is any historical trajectory point in each of the target historical trajectory point sets, i≥1 and i is a positive integer; (x i , y i ) are the coordinates of the i-th historical trajectory point; d is the lateral offset; B = 2 * k i * b i - 2 * x i - 2 * k i * y i ; C = x i 2 + b i 2 - 2 * b i * y i + y i 2 - d 2 ; θ i is the inclination angle corresponding to the i-th historical trajectory point; k i is the slope of the normal line corresponding to the first straight line at the i-th historical trajectory point. The first straight line is the straight line where the i-th historical trajectory point and the (i + 1)-th historical trajectory point are located. The (i + 1)-th historical trajectory point and the i-th historical trajectory point are on the same historical trajectory, and the (i + 1)-th historical trajectory point is adjacent to the i-th historical trajectory point; b i is the longitudinal intercept of the straight line where the normal line is located in the vehicle body coordinate system, and the vehicle body coordinate system takes the current position of the host vehicle as the coordinate origin.

2. The trajectory prediction method according to claim 1, characterized in that The priority screening rule includes: the minimum inclination angle is negatively correlated with the priority of the set of first historical trajectory points.

3. The trajectory prediction method according to claim 2, characterized in that The preset mapping rule further includes: If the lateral offset between the host vehicle and the target remote vehicle is greater than 0, the mapped coordinate point is located on the first side of the historical trajectory of the target remote vehicle, and the first side is the right side of the driving direction of the target remote vehicle; If the lateral offset between the host vehicle and the target remote vehicle is less than 0, the mapped coordinate point is located on the second side of the historical trajectory of the target remote vehicle, and the second side is the left side of the driving direction of the target remote vehicle.

4. The trajectory prediction method according to claim 1, characterized in that After obtaining the predicted trajectory according to the set of mapped coordinate points, the method further includes: Sampling the predicted trajectory according to a first sampling distance to obtain a trajectory prediction point set; wherein, the first sampling distance is related to a sampling time interval and the vehicle speed of the host vehicle.

5. A vehicle networking device, comprising: A transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the trajectory prediction method according to any one of claims 1 to 3 are implemented.

6. A trajectory prediction device, characterized in that, Applied to a host vehicle, including: An acquisition module, configured to acquire n sets of historical trajectory points; wherein, one set of historical trajectory points is obtained from the historical trajectory of a remote vehicle. A screening module, configured to screen the n sets of historical trajectory points to obtain m sets of target historical trajectory points; wherein, 1≤m≤n, and m and n are positive integers. A mapping module, configured to map each historical trajectory point in the m sets of target historical trajectory points to the driving direction of the host vehicle to obtain a set of mapped coordinate points. A generation module, configured to form the predicted trajectory of the host vehicle according to the set of mapped coordinate points. Wherein, the screening module includes: A first screening sub-module, configured to screen out t sets of first historical trajectory points that meet a first screening rule from the n sets of historical trajectory points; 1≤t≤n, and t is a positive integer. A second screening sub-module, configured to obtain m sets of target historical trajectory points with the highest priority from the t sets of first historical trajectory points based on a priority screening rule: wherein, the priority screening rule is determined by the minimum inclination angle between the historical trajectory corresponding to each set of first historical trajectory points and the driving direction of the host vehicle, and the minimum inclination angle is: the inclination angle of the historical trajectory point closest to the host vehicle. Wherein, the first screening rule includes: In a vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the abscissa of the first trajectory point in the historical trajectory corresponding to the set of historical trajectory points is less than the abscissa of the current position of the host vehicle. The broken-line distance between the target trajectory point and the current position of the remote vehicle is greater than a preset distance threshold; wherein, the target trajectory point is the trajectory point with the smallest distance from the host vehicle in each set of historical trajectory points. The absolute value of the minimum inclination angle is less than a preset inclination angle threshold. In a vehicle body coordinate system with the current position of the host vehicle as the coordinate origin, the absolute value of the lateral offset between the host vehicle and the historical trajectory corresponding to the set of historical trajectory points is less than a preset offset threshold; wherein, the lateral offset is the distance between the straight line corresponding to the minimum inclination angle and the host vehicle. Wherein, the mapping module is specifically configured to: Based on a preset mapping rule, map each historical trajectory point in the m sets of target historical trajectory points to the driving direction of the host vehicle to obtain a set of mapped coordinate points. The preset mapping rule includes: At the inclination angle θ corresponding to the i-th historical trajectory point i where the value range is (0, π) and d > 0, or, θ i where the value range is (π, 2π) and d < 0, the mapped coordinate point corresponding to the i-th historical trajectory point is P1(x mapping_1 , y mapping_1 ), where: y mapping_1 = k i * x mapping_1 + b i ; At the inclination angle θ corresponding to the i-th historical trajectory point i where the value range is (0, π) and d < 0, or, θ i where the value range is (π, 2π) and d > 0, the mapped coordinate point corresponding to the i-th historical trajectory point is P2(x mapping_2 , y mapping_2 ), where: y mapping_2 = k i * x mapping_2 + b i ; Wherein, the i-th historical trajectory point is any historical trajectory point in each of the target historical trajectory sets, i≥1 and i is a positive integer; (x i , y i ) are the coordinates of the i-th historical trajectory point; d is the lateral offset; B = 2 * k i * b i - 2 * x i - 2 * k i * y i ; C = x i 2 + b i 2 - 2 * b i * y i + y i 2 - d 2 ; θ i is the inclination angle corresponding to the i-th historical trajectory point; k i is the slope of the normal line of the first straight line at the i-th historical trajectory point. The first straight line is the straight line where the i-th historical trajectory point and the (i + 1)-th historical trajectory point are located. The (i + 1)-th historical trajectory point and the i-th historical trajectory point are on the same historical trajectory, and the (i + 1)-th historical trajectory point is adjacent to the i-th historical trajectory point; b i is the longitudinal intercept of the straight line where the normal line is located in the vehicle body coordinate system, and the vehicle body coordinate system takes the current position of the host vehicle as the coordinate origin.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the trajectory prediction method according to any one of claims 1 to 3 are implemented.

Images