Trajectory prediction method and device and storage medium

Abstract

The invention relates to a trajectory prediction method and device and a storage medium, and relates to the technical field of automobiles, in particular to the technical field of automobile trajectory prediction. The method is applied to a target vehicle and comprises the following steps: acquiring a motion state parameter and a first candidate road point of a to-be-predicted vehicle; based on the motion state parameters and motion feasibility constraint conditions of the to-be-predicted vehicle, screening out second candidate road points from the first candidate road points; and generating a motion track of the to-be-predicted vehicle based on the second candidate road point. Wherein the first candidate road point is determined based on surrounding road information of the to-be-predicted vehicle. Therefore, the technical problem of low feasibility of track prediction can be avoided.

Description

Technical Field

[0001] The present application relates to the field of automobile technology, in particular to the field of automobile trajectory prediction technology, and specifically to a trajectory prediction method, device and storage medium. Background Art

[0002] In recent years, the widespread application of deep neural networks in the field of trajectory prediction has indeed brought significant progress to the fields of autonomous driving, intelligent transportation, etc. Among them, the target-driven trajectory prediction method achieves a more accurate prediction of the vehicle's future trajectory by decomposing the problem into two subtasks: predicting possible targets and estimating motion based on contextual features. However, while pursuing low prediction errors, this method often ignores the physical feasibility of the predicted trajectory.

[0003] In the related art, it is proposed to determine the predicted trajectory of the target vehicle through the historical trajectory information of the target vehicle and the historical trajectory information of each surrounding vehicle. However, there is a problem that the predicted trajectory is only determined by historical information, resulting in low feasibility of the predicted trajectory.

[0004] In the related technology, it is proposed to predict the vehicle's driving trajectory by building an attention mechanism neural network, but there is a problem that the trajectory cannot be updated cyclically, resulting in low feasibility of predicting the trajectory.

[0005] Therefore, it is necessary to introduce more physical constraints and more complex trajectory representation methods into the prediction model to ensure that the generated predicted trajectory is both accurate and feasible. Summary of the invention

[0006] The present application provides a trajectory prediction method, device and storage medium to at least solve the technical problem of low feasibility of trajectory prediction in the related art. The technical solution of the present application is as follows:

[0007] According to a first aspect provided by the present application, a trajectory prediction method is provided, which is applied to a target vehicle, and the method includes: obtaining motion state parameters and a first candidate road point of the vehicle to be predicted; based on the motion state parameters and the motion feasibility constraints of the vehicle to be predicted, screening out a second candidate road point from the first candidate road point; based on the second candidate road point, generating a motion trajectory of the vehicle to be predicted.

[0008] The first candidate road point is determined based on the surrounding road information of the vehicle to be predicted.

[0009] It should be understood that physical feasibility is crucial in vehicle trajectory prediction because it determines whether the prediction results can be actually applied in the autonomous driving system. If the predicted trajectory violates physical feasibility, even if its average displacement error is small, it may cause the autonomous vehicle to encounter a trajectory that cannot be followed in actual driving, thus causing safety hazards.

[0010] Based on the above technical solution, the method comprehensively considers the vehicle's motion state parameters and motion feasibility constraints. The present invention can screen out candidate road points that are more in line with the vehicle's actual driving conditions, thereby generating a more accurate driving trajectory.

[0011] At the same time, this method also takes into account multiple factors such as motion feasibility constraints (road conditions, traffic rules), further improving the reliability and practicality of trajectory prediction.

[0012] In some embodiments, the motion feasibility constraint is determined based on road driving rules and / or configuration information of the vehicle to be predicted; the motion feasibility constraint includes at least one of the following: a maximum acceleration constraint of the vehicle to be predicted, a maximum deceleration constraint of the vehicle to be predicted, a maximum steering constraint of the vehicle to be predicted, and a road speed limit constraint.

[0013] Based on the above technical solution, the method comprehensively considers the above constraints to ensure that the predicted vehicle can both perform at its best and comply with road safety regulations during movement, thereby achieving safe, efficient and feasible vehicle movement.

[0014] In some embodiments, obtaining a first candidate road point includes: determining a first road segment of a preset distance in the direction of movement of the vehicle to be predicted based on the position information of the vehicle to be predicted and the surrounding road information; performing discretized sampling on the center line of the first road segment to obtain a third candidate road point; determining a first search area based on the current speed, heading angle and road factor of the vehicle to be predicted and the road factor of the first road segment; the road factor is determined based on the road segment type of the first road segment; the center line orientation of the first search area is consistent with the heading angle; the search range of the first search area is positively correlated with the current speed; and determining the first candidate road point from the third candidate road point based on the first search area.

[0015] Based on the above technical solution, the method realizes dynamic and accurate determination of the first search area by comprehensively considering the current speed, heading angle and road factors of the vehicle to be predicted in different scenarios, which helps to improve the safety of vehicle driving and the accuracy of prediction.

[0016] In some embodiments, based on the motion state parameters and the motion feasibility constraints of the vehicle to be predicted, a second candidate road point is screened out from the first candidate road point, including: screening out candidate points within the proximal deceleration range and candidate points outside the distal acceleration range from the first candidate road point to obtain the second candidate road point; wherein the proximal deceleration range is determined based on the current speed of the vehicle to be predicted and the maximum deceleration constraint; and the distal acceleration range is determined based on the current speed of the vehicle to be predicted, the maximum acceleration constraint and the road speed limit constraint.

[0017] Based on the above technical solution, this method can effectively eliminate candidate road points that are theoretically impossible for the predicted vehicle to reach within the prediction time range or are not feasible in actual driving through the above screening mechanism, thereby ensuring the accuracy and practicality of the prediction results and further optimizing the accuracy and reliability of vehicle trajectory prediction.

[0018] In some embodiments, based on the second candidate road point, a motion trajectory of the vehicle to be predicted is generated, including: determining a target road point from the second candidate road point; generating the motion trajectory of the vehicle to be predicted based on the target road point; the motion trajectory is the trajectory between the current position of the vehicle to be predicted and the target road point.

[0019] Based on the above technical solution, the method selects the target road point from the second candidate road point and generates a motion trajectory based on the point. The embodiment of the present application can more accurately predict the future driving path of the vehicle, reduce the prediction error, and further improve the reliability and practicality of the trajectory prediction.

[0020] In some embodiments, determining a target road point from the second candidate road points includes: inputting the position information, motion state parameters and position information of the candidate road points of the vehicle to be predicted into a graph attention network model to obtain a target road point with the highest attention coefficient among the second candidate road points; the attention coefficient is used to characterize the confidence of the vehicle to be predicted in the candidate road points.

[0021] Based on the above technical solution, this method introduces a graph attention network model, so that the embodiment of the present application can more accurately capture the relationship between the vehicle and the road points, as well as the potential impact of different road points on the vehicle's driving path. The attention mechanism enables the model to adaptively focus on the candidate road points that have the greatest impact on the vehicle's driving path, thereby improving the accuracy and robustness of trajectory prediction.

[0022] In some embodiments, a motion trajectory of a vehicle to be predicted is generated based on a target road point, including: determining a reference path of the vehicle to be predicted based on the target road point; the reference path is an estimated path between a lane segment where the vehicle to be predicted is located and a lane segment where the target road point is located; determining multiple driving coordinates of the vehicle to be predicted based on the reference path and position information of the vehicle to be predicted; generating a motion trajectory of the vehicle to be predicted based on the multiple driving coordinates; the motion trajectory is a trajectory between the current position of the vehicle to be predicted and the target road point.

[0023] Based on the above technical solution, the method comprehensively considers the position information, motion state and position information of the target road point of the vehicle to be predicted, so that the embodiment of the present application can generate a reference path and motion trajectory that is more in line with the actual driving conditions of the vehicle.

[0024] In addition, the process of determining driving coordinates and generating motion trajectories fully considers the vehicle's dynamic characteristics and road conditions, further improving the accuracy and reliability of trajectory prediction.

[0025] In some embodiments, the reference path includes multiple preview points; the preview points are used to represent the expected coordinates on the reference path; based on the reference path and the position information of the vehicle to be predicted, multiple driving coordinates of the vehicle to be predicted are determined, including: for each of the multiple preview points, based on the motion state parameters of the vehicle to be predicted, determining the steering angle required for the vehicle to be predicted to travel to the preview point; based on the position information of the vehicle to be predicted and the target road point, determining the acceleration of the vehicle to be predicted; based on the acceleration and the steering angle, determining the driving coordinates of the vehicle to be predicted, so as to obtain multiple driving coordinates of the vehicle to be predicted.

[0026] Based on the above technical solution, the method continuously updates the position of the preview point and repeatedly executes the above pure tracking algorithm calculation and steering angle adjustment process. Through continuous iteration and optimization, the predicted vehicle can gradually approach and stably maintain driving on the reference path, thereby generating multiple driving coordinates of the predicted vehicle.

[0027] In some embodiments, based on the target road point, a reference path of the vehicle to be predicted is determined, including: obtaining a lane segment set between the target lane segment and the lane segment where the vehicle to be predicted is located; the target lane segment is the lane segment where the target road point is located; each lane segment in the lane segment set is sampled equidistantly along the lane centerline to generate a reference path between the target lane segment and the lane segment where the vehicle to be predicted is located.

[0028] Based on the above technical solution, the method obtains a lane segment set between the target lane segment and the lane segment where the vehicle to be predicted is located, and performs equidistant sampling along the lane center line. In this way, the embodiment of the present application can generate a reference path that is more in line with the actual driving conditions of the vehicle, and the accuracy and reliability of the reference path are significantly improved, providing strong support for the vehicle's automatic driving and path planning.

[0029] According to a second aspect provided by the present application, a trajectory prediction device is provided, the device comprising: a processing unit and an acquisition unit; the acquisition unit is used to acquire motion state parameters and a first candidate road point of a vehicle to be predicted; the first candidate road point is determined based on surrounding road information of the vehicle to be predicted; the processing unit is used to filter out second candidate road points from the first candidate road points based on the motion state parameters and motion feasibility constraints of the vehicle to be predicted; the processing unit is also used to generate a motion trajectory of the vehicle to be predicted based on the second candidate road point.

[0030] According to a third aspect provided by the present application, a vehicle is provided, comprising a trajectory prediction device according to the second aspect.

[0031] According to the fourth aspect provided by the present application, an electronic device is provided, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to execute instructions to implement the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0032] According to the fifth aspect provided by the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method in the above-mentioned first aspect and any possible implementation method thereof.

[0033] According to the sixth aspect provided by the present application, a computer program product is provided, the computer program product comprising computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0034] Therefore, the above technical features of the present application have the following beneficial effects:

[0035] (1) By comprehensively considering the vehicle's motion state parameters and motion feasibility constraints, the present invention can screen out candidate road points that are more in line with the vehicle's actual driving conditions, thereby generating a more accurate driving trajectory.

[0036] At the same time, the embodiment of the present application also takes into account various factors such as motion feasibility constraints (road conditions, traffic rules), further improving the reliability and practicality of trajectory prediction.

[0037] (2) The embodiments of the present application comprehensively consider the above constraints to ensure that the vehicle to be predicted can both perform at its best and comply with road safety regulations during movement, thereby achieving safe, efficient and feasible vehicle movement.

[0038] (3) The embodiment of the present application realizes dynamic and accurate determination of the first search area by comprehensively considering the current speed, heading angle and road factors of the vehicle to be predicted in different scenarios, which helps to improve the safety of vehicle driving and the accuracy of prediction.

[0039] (4) The embodiment of the present application can effectively eliminate candidate road points that are theoretically impossible for the predicted vehicle to reach within the prediction time range or are not feasible in actual driving through the above-mentioned screening mechanism, thereby ensuring the accuracy and practicality of the prediction results and further optimizing the accuracy and reliability of vehicle trajectory prediction.

[0040] (5) By selecting a target road point from the second candidate road point and generating a motion trajectory based on the point, the embodiment of the present application can more accurately predict the future driving path of the vehicle, reduce the prediction error, and further improve the reliability and practicality of the trajectory prediction.

[0041] (6) By introducing a graph attention network model, the embodiment of the present application can more accurately capture the relationship between the vehicle and the road points, as well as the potential impact of different road points on the vehicle's driving path. The attention mechanism enables the model to adaptively focus on the candidate road points that have the greatest impact on the vehicle's driving path, thereby improving the accuracy and robustness of trajectory prediction.

[0042] (7) The embodiment of the present application comprehensively considers the position information, motion state and position information of the target road point of the vehicle to be predicted, so that the embodiment of the present application can generate a reference path and motion trajectory that is more in line with the actual driving conditions of the vehicle.

[0043] In addition, the process of determining driving coordinates and generating motion trajectories fully considers the vehicle's dynamic characteristics and road conditions, further improving the accuracy and reliability of trajectory prediction.

[0044] (8) The embodiment of the present application continuously updates the position of the preview point and repeatedly executes the above-mentioned pure tracking algorithm calculation and steering angle adjustment process. Through continuous iteration and optimization, the vehicle to be predicted can gradually approach and stably maintain driving on the reference path, thereby generating multiple driving coordinates of the vehicle to be predicted.

[0045] (9) The embodiment of the present application obtains a lane segment set between the target lane segment and the lane segment where the vehicle to be predicted is located, and performs equidistant sampling along the center line of the lane. In this way, the embodiment of the present application can generate a reference path that is more in line with the actual driving conditions of the vehicle, and the accuracy and reliability of the reference path are significantly improved, providing strong support for the vehicle's automatic driving and path planning.

[0046] It should be noted that the technical effects brought about by any implementation method in the second to sixth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.

[0047] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0049] Figure 1 is a schematic structural diagram of a vehicle according to an exemplary embodiment;

[0050] Figure 2 is a block diagram of a trajectory prediction system according to an exemplary embodiment;

[0051] Figure 3 is a flow chart of a trajectory prediction method according to an exemplary embodiment;

[0052] Figure 4 is a scene diagram of a trajectory prediction method according to an exemplary embodiment;

[0053] Figure 5 is a scene diagram of another trajectory prediction method according to an exemplary embodiment;

[0054] Figure 6 is a geometric relationship diagram of a preview point shown according to an exemplary embodiment;

[0055] Figure 7 is a block diagram of another trajectory prediction device according to an exemplary embodiment;

[0056] Figure 8 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0057] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0058] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0059] In the embodiments of the present application, words such as "exemplary", "for example", or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary", "for example", or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example", or "for example" is intended to present related concepts in a specific way.

[0060] First, the relevant technologies involved in this application are explained to facilitate understanding by those skilled in the art.

[0061] In recent years, the widespread application of deep neural networks in trajectory prediction has indeed brought significant progress to autonomous driving, intelligent transportation and other fields. Among them, the target-driven trajectory prediction method achieves a more accurate prediction of the vehicle's future trajectory by decomposing the problem into two subtasks: predicting possible targets and estimating motion based on contextual features. However, while pursuing low prediction errors, these methods often ignore the physical feasibility of the predicted trajectory, which is an issue worthy of in-depth exploration.

[0062] To solve the above problems, the goal can be to use a more complex trajectory representation method to more comprehensively describe the vehicle's occupancy in space, and then generate a predicted trajectory for the vehicle to overcome the problem of low feasibility. This method can more accurately reflect the actual space occupied by the vehicle, thereby improving the physical feasibility of the prediction results.

[0063] In summary, although deep learning-based trajectory prediction methods have achieved remarkable results in reducing prediction errors, physical feasibility is still one of the key factors restricting its practical application. In the future, researchers need to introduce more physical constraints and more complex trajectory representation methods into the prediction model to ensure that the generated prediction trajectory is both accurate and feasible. This will provide more reliable guarantees for the practical application of intelligent transportation systems such as autonomous driving.

[0064] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0065] The trajectory prediction method provided in the embodiment of the present application can be applied in a vehicle. Figure 1 , which is a schematic diagram of a vehicle structure provided by an embodiment of the present application, the vehicle 100 may include a chassis 110, a body 120, and wheels 130. It is understandable that the vehicle 100 may be a fuel vehicle, an electric vehicle, a hybrid vehicle, a gas vehicle, a methanol vehicle, a solar vehicle, etc.

[0066] For example, the vehicle 100 may be a passenger vehicle such as a sedan, a sport utility vehicle (SUV), a multi-purpose vehicle (MPV), or a bus, a truck, a semi-trailer, etc. This application does not impose any specific restrictions on this.

[0067] It is understandable that the above components are merely examples of some components of the vehicle 100 and are not limitations on the specific structure of the vehicle 100 .

[0068] Optionally, in order to control the vehicle, the vehicle 100 may further include a trajectory prediction system 140. The trajectory prediction system 140 may predict the motion trajectory of the vehicle to be predicted around the vehicle 100.

[0069] like Figure 2 As shown, the present embodiment provides a block diagram of a trajectory prediction system 140. The trajectory prediction system 140 includes a screening module 210 and a trajectory prediction module 220.

[0070] Among them, the screening module 210 is used to screen out the second candidate road point from the first candidate road point according to the feasible motion constraints of the vehicle to be predicted and the acquired motion state parameters of the vehicle to be predicted, and send the second candidate road point to the trajectory prediction module 220.

[0071] The trajectory prediction module 220 is used to generate the motion trajectory of the vehicle to be predicted according to the second candidate road point.

[0072] It should be noted that the trajectory prediction system 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. A person of ordinary skill in the art will know that with the evolution of electronic devices and the emergence of other electronic devices, the technical solution provided by the embodiment of the present application is also applicable to similar technical problems. The methods in the following embodiments can all be implemented in a trajectory prediction system having the above hardware structure.

[0073] The methods in the following embodiments can all be implemented in a trajectory prediction system having the above hardware structure.

[0074] The vehicle steering control method provided by the embodiment of the present application is described in detail below in conjunction with the accompanying drawings.

[0075] The trajectory prediction method of the embodiment of the present application can be applied to predict the motion trajectory of a vehicle to be predicted. Figure 3 As shown, the trajectory prediction method may include steps 301 to 303. Step 301 may also be referred to as a process of "obtaining the motion state parameters of the vehicle to be predicted and the first candidate road point", and steps 302 to 303 may be referred to as a process of "generating the motion trajectory of the vehicle to be predicted". Steps 301 to 303 are described in detail below.

[0076] Step 301: Obtain the motion state parameters of the vehicle to be predicted and the first candidate road point.

[0077] In an embodiment related to the present application, the first candidate road point is determined based on the surrounding road information of the vehicle to be predicted; the motion state parameters include but are not limited to the current speed, acceleration, position, heading angle and other information of the vehicle to be predicted.

[0078] For example, the trajectory prediction system can obtain the motion state parameters of all the vehicles to be predicted in the scene through the on-board perception sensors and positioning system of the target vehicle. The road information around the predicted vehicle is obtained through a high-precision map, and the surrounding road information includes but is not limited to lane point positions and lane adjacency relationships, and then the first candidate road point, i.e., the initial candidate road point, is determined through the surrounding road information.

[0079] Wherein, i=0,1,2,… represents the vehicle number, i=0 represents the target vehicle, i=1,2,3… represents the vehicles to be predicted around the target vehicle, t=-T,-T+1,…,0 represents the time step, and t=0 is the current time; represents the position information of the i-th vehicle to be predicted at time t, represents the speed information of the i-th vehicle to be predicted at time t, represents the acceleration information of the i-th vehicle to be predicted at time t, Represents the heading angle information of the i-th vehicle to be predicted at time t.

[0080] In some embodiments, the trajectory prediction system can determine a first road segment of a preset distance in the direction of movement of the vehicle to be predicted based on the position information of the vehicle to be predicted and the surrounding road information, discretize the center line of the first road segment to obtain a third candidate road point, and then determine a first search area based on the current speed, heading angle and road factor of the vehicle to be predicted, and determine the first candidate road point from the third candidate road point based on the first search area.

[0081] Among them, the road factor is determined based on the road segment type of the first road segment and is used to characterize the degree of freedom of the vehicle to be predicted in the scene; the centerline direction of the first search area is consistent with the heading angle; and the search range of the first search area is positively correlated with the current speed.

[0082] For example, the trajectory prediction system uses 3M as the sampling interval to perform uniform discretization sampling on the center line of the first road segment to obtain the third candidate road point. And the first search area R can be obtained by the following formula 1: i , taking the current position of the vehicle to be predicted as the center, filter the vehicles located in the first search area R i The candidate road points within the range are taken as the first candidate road points. Figure 4 The first candidate road point is shown in .

[0083]

[0084] in, Represents the current speed of the vehicle to be predicted, R0 represents the threshold of the range (to avoid too low speed resulting in too small a search range), α represents the road factor (the value is taken according to the scene type, with a larger value for non-intersection scenes and a smaller value for intersection scenes). For example, when the vehicle to be predicted is in a non-intersection scene, a relatively large value can be assigned to the road factor to reflect the relative freedom of vehicle driving and a larger safety space in non-intersection scenes; in an intersection scene, a relatively small value can be assigned to the road factor to reflect the restrictiveness and higher safety requirements of vehicle driving in intersection scenes.

[0085] In addition, the first search area may be a semicircular search area, and the direction of the angle bisector of the first search area is the same as the current heading angle of the vehicle to be predicted. The same direction.

[0086] It should be understood that the embodiment of the present application achieves dynamic and accurate determination of the first search area by comprehensively considering the vehicle speed and road factors in different scenarios, which helps to improve the safety of predicted vehicle driving and the accuracy of prediction.

[0087] Step 302: based on the motion state parameters and the motion feasibility constraints of the vehicle to be predicted, select second candidate road points from the first candidate road points.

[0088] In an embodiment related to the present application, the motion feasibility constraints are determined based on road driving rules and / or configuration information of the vehicle to be predicted; the motion feasibility constraints include but are not limited to the maximum acceleration constraints of the vehicle to be predicted, the maximum deceleration constraints of the vehicle to be predicted, and the road speed limit constraints.

[0089] In some embodiments, the trajectory prediction system may filter out candidate points within the proximal deceleration range and candidate points outside the distal acceleration range from the first candidate road points to obtain second candidate road points.

[0090] The proximal deceleration range is determined based on the current speed of the vehicle to be predicted and the maximum deceleration constraint; the distal acceleration range is determined based on the current speed of the vehicle to be predicted, the maximum acceleration constraint and the road speed limit constraint.

[0091] Exemplarily, the trajectory prediction system can determine the distance that the vehicle to be predicted decelerates within a preset time period based on the current speed of the vehicle to be predicted and the maximum deceleration of the vehicle to be predicted, and then use the deceleration distance as the proximal deceleration range, and filter out candidate points within the proximal deceleration range from the first candidate road points.

[0092] The trajectory prediction system can also determine the distance that the vehicle to be predicted accelerates within a preset time period based on the current speed of the vehicle to be predicted, the maximum acceleration of the vehicle to be predicted, and the road speed limit constraint, and then use the accelerated distance as the far-end acceleration range, and filter out the candidate points within the far-end acceleration range from the first candidate road points; thus, the trajectory prediction system uses the remaining candidate points after filtering out the near-end deceleration range and the far-end acceleration range as the second candidate road points. For example, Figure 4 The second candidate road point is shown in .

[0093] It should be understood that when the maximum acceleration of the vehicle to be predicted reaches the road speed limit within the preset time, the vehicle to be predicted will travel at the road speed limit. The embodiment of the present application can effectively exclude candidate road points that are theoretically inaccessible or infeasible in actual driving within the prediction time range through the above-mentioned screening mechanism, thereby ensuring the accuracy and practicality of the prediction results and further optimizing the accuracy and reliability of vehicle trajectory prediction.

[0094] Step 303: Generate a motion trajectory of the vehicle to be predicted based on the second candidate road point.

[0095] In an embodiment of the present application, the trajectory prediction system can determine a target road point from the second candidate road points, and generate a motion trajectory of the vehicle to be predicted based on the target road point.

[0096] The motion trajectory is the trajectory between the current position of the vehicle to be predicted and the target road point.

[0097] In some embodiments, the trajectory prediction system inputs the position information, motion state parameters and position information of the candidate road points of the vehicle to be predicted into the graph attention network model to obtain the target road point with the highest attention coefficient among the second candidate road points.

[0098] Among them, the attention coefficient is used to characterize the confidence of the predicted vehicle in the candidate road point.

[0099] For example, Figure 4 As shown, the trajectory prediction system can encode the motion state parameters and position information of the vehicle to be predicted through the Transformer module of the cross-attention mechanism to obtain the vehicle characteristics of the vehicle to be predicted, and the vehicle characteristics include but are not limited to the current speed, acceleration, position, heading angle and other information of the vehicle to be predicted.

[0100] Then, the trajectory prediction system can determine the relative position vector r between the position feature of the second candidate road point and the vehicle to be predicted. i,j , that is, the distance between the position of the second candidate road point and the position of the vehicle to be predicted. For example, in, represents the current position information of the i-th vehicle to be predicted, p j represents the position information of the j-th second candidate road point.

[0101] The trajectory prediction system uses a multi-layer perceptron to calculate the position information p of the jth second candidate road point. j , and the relative position vector r between the second candidate point and the vehicle to be predicted i,j Encode and obtain the position feature F of the jth second candidate point j The relative position characteristics of the vehicle to be predicted.

[0102]

[0103] F j =MLP(p j ),E i,j =MLP(r i,j )

[0104] Among them, Transformer(·) is the Transformer encoding module that encodes vehicle time series information. is the motion state parameter of the vehicle to be predicted, r i,j is the relative position vector between the surrounding candidate points and the vehicle to be predicted, MLP(·) is a multi-layer perceptron, E i,j Represents the relative position feature between the second candidate point and the vehicle to be predicted.

[0105] Furthermore, the above vehicle feature F i As the vehicle node attribute, the position feature F of the jth second candidate point j As the node attribute and relative position feature of the candidate point E i,j As a directed edge attribute, a graph structure can be established based on multiple attributes.

[0106] Specifically, in the embodiment of the present application, the construction of the above graph structure can be based on the vehicle to be predicted as the starting node, and multiple second candidate road points can be introduced as other nodes. On this basis, the directed edge E is defined i,j , each with directed edge E i,j Starting from the vehicle to be predicted, point to each second candidate road point.

[0107] Next, in order to improve the information expression capability of the graph structure, corresponding attributes can be assigned to the above nodes and edges. Specifically, the attributes of the vehicle to be predicted are based on its own encoded vehicle features F i The attributes of the jth second candidate point are set according to its encoded position feature F j For directed edges, the relative position feature E is used. i,j as its attributes.

[0108] In order to facilitate subsequent graph data processing and analysis, the embodiment of the present application also constructs graph data that conforms to a specific format. Among them, the dimension of the node feature matrix is ​​set to (N_nodes, feature_dim), and the value of N_nodes is equal to 1 (representing the vehicle node) + N (representing the total number of candidate point nodes). In terms of the representation of edges, the embodiment of the present application is described in the form of an edge list or an adjacency matrix. In view of the advantages of GAT (graph attention network) in processing graph data, the embodiment of the present application tends to use an edge list to explicitly specify the neighbor nodes of each node. Specifically, in the embodiment, the neighbor nodes of vehicle node i are all candidate point nodes j. In addition, the embodiment of the present application also constructs an edge feature matrix, whose dimension is (N_edges, edge_feature_dim), where the value of N_edges is equal to N, because there is a directed edge from the vehicle node to each second candidate point node.

[0109] Furthermore, the trajectory prediction system can input the constructed graph data into a graph attention network (GAT) model, which can calculate the multi-head attention coefficient of the vehicle to be predicted for the second candidate road point based on the graph data (node ​​attributes and edge attributes), and sum them up to determine the attention coefficients of multiple second candidate points, and take the candidate road point with the highest attention coefficient among the multiple second candidate road points as the target road point.

[0110] It should be understood that the attention coefficient can also be used to characterize the degree of attention to the second candidate road point of the vehicle to be predicted. The larger the attention coefficient, the closer and more important the relationship between the vehicle to be predicted and the corresponding candidate point is, which helps the model to pay more attention to the candidate road points that have an important impact on the prediction results in subsequent processing.

[0111] In addition, the trajectory prediction system can also perform flexible maximum calculation on the attention coefficient to obtain a normalized attention coefficient, that is, the confidence score of the second candidate road point, and use the second candidate road point with the highest confidence score as the target road point.

[0112] Among them, the confidence score can be used to represent the degree of trust that the predicted vehicle has in each candidate road point.

[0113] For example, the attention coefficient can be obtained by the following formula 2.

[0114] α j =GAT(F i ,F j ,E i,j ) Formula 2

[0115] Among them, GAT(·) is the graph attention network, α j is the attention coefficient.

[0116] The normalized attention coefficient can also be obtained by the following formula 3.

[0117] α′ j =Softmax(α j ) Formula 3

[0118] Among them, Softmax(·) is the softmax function that calculates the maximum flexibility, α′ j is the normalized attention coefficient.

[0119] In some embodiments, the trajectory prediction system can determine a reference path of the vehicle to be predicted based on the target road point, and then determine multiple driving coordinates of the vehicle to be predicted based on the reference path and the position information of the vehicle to be predicted, and generate a motion trajectory of the vehicle to be predicted based on the multiple driving coordinates.

[0120] Among them, the reference path is the estimated path between the lane segment where the vehicle to be predicted is located and the lane segment where the target road point is located; the motion trajectory is the trajectory between the current position of the vehicle to be predicted and the target road point.

[0121] Exemplarily, the trajectory prediction system can obtain a lane segment set between the target lane segment and the lane segment where the vehicle to be predicted is located, and perform equidistant sampling on each lane segment in the lane segment set along the lane centerline to generate a reference path between the target lane segment and the lane segment where the vehicle to be predicted is located.

[0122] The target lane segment is the lane segment where the target road point is located.

[0123] In one scenario, Figure 5 As shown, starting from the target lane segment (lane segment A), the longitudinal rear lane segment and the lateral leading lane segment are searched and traversed until the lane segment where the vehicle to be predicted is found, thereby obtaining the lane segment set between the target lane segment and the lane segment where the vehicle to be predicted is located. For example, lane segment A, lane segment B, and lane segment C.

[0124] Furthermore, each lane segment in the lane segment set is sampled equidistantly along the lane centerline to obtain a plurality of lane center points, and the plurality of lane center points are connected to generate a reference path.

[0125] In some embodiments, the trajectory prediction system determines the driving coordinates of the vehicle to be predicted for each of the multiple preview points based on the preview point and the position information of the vehicle to be predicted, so as to obtain multiple driving coordinates of the vehicle to be predicted.

[0126] The reference path includes a plurality of preview points, and the preview points are used to represent the estimated coordinates on the reference path.

[0127] Exemplarily, the trajectory prediction system can determine the steering angle required for the vehicle to be predicted to travel to the preview point based on the motion state parameters of the vehicle to be predicted, and then determine the acceleration of the vehicle to be predicted based on the position information of the vehicle to be predicted and the target road point, and determine the driving coordinates of the vehicle to be predicted based on the acceleration and the steering angle, so as to obtain multiple driving coordinates of the vehicle to be predicted.

[0128] In one scenario, the trajectory prediction system can determine one or more preview points as short-term goals based on the position information and reference path of the vehicle to be predicted; then, a pure tracking algorithm is used to calculate and determine the steering angle (front wheel angle adjustment) of the vehicle to be predicted, and then the vehicle to be predicted is controlled to track the preview points on the reference path based on the steering angle, and the current motion state parameters (such as speed, acceleration, etc.) and path geometry characteristics of the vehicle to be predicted are updated; then, the calculated front wheel angle command is sent to the vehicle steering system to perform the steering operation; after the vehicle performs the steering operation, its state (position, speed, direction, etc.) is updated accordingly; this process is repeated continuously within the preset prediction time, and each iteration re-determines the preview point and calculates the front wheel angle based on the latest vehicle state and reference path information to achieve continuous and accurate tracking of the reference path, and finally generates a smooth vehicle motion trajectory that meets the path requirements.

[0129] It should be understood that the preview point is usually located at a certain distance in front of the vehicle to be predicted, and its selection needs to take into account factors such as the driving speed of the vehicle to be predicted, the path curvature, and the system response time to ensure that the vehicle to be predicted can adjust its driving direction in a timely and smooth manner.

[0130] Specifically, the trajectory prediction system takes the position of the vehicle to be predicted as the starting point, and previews the reference path forward at a preset forward-looking distance to obtain a preview point. It can be determined by the following formula 4.

[0131]

[0132] in, represents the speed of the i-th vehicle to be predicted at time t; represents the acceleration of the i-th vehicle to be predicted at time t; α and β represent constant coefficients, which can be adjusted according to the vehicle type and road conditions; L fc Represents the distance threshold, which is used to avoid the problem of too small forward visibility distance when the predicted vehicle is traveling at a low speed.

[0133] Furthermore, the trajectory prediction system calculates and determines the steering angle according to the position information of the vehicle to be predicted and the position information of the preview point, and then controls the vehicle to be predicted to track the preview point on the reference path according to the steering angle, thereby updating the position and posture of the vehicle to be predicted. f (Lateral control amount) can be determined by the following formula 5.

[0134]

[0135] in,

[0136] The geometric relationship between the preview point and the vehicle to be predicted is as follows: Figure 6 As shown, L represents the wheelbase of the vehicle to be predicted, α is the angle between the vehicle to be predicted and the preview point, and L f represents the distance between the vehicle to be predicted and the preview point, δ f represents the steering angle, R represents the radius; α t represents the angle between the vehicle to be predicted and the preview point at time t, represents the distance between the vehicle to be predicted and the preview point at time t, δ0 represents the preset maximum steering angle, and -δ0 represents the preset minimum steering angle;

[0137] It should be understood that if the calculated steering angle is greater than the pre-set maximum steering angle, the maximum steering constraint in the motion feasibility constraint, that is, the pre-set maximum steering angle, cannot be met, so the pre-set maximum steering angle is used as the current steering angle of the vehicle to be predicted; when the calculated steering angle is less than the pre-set minimum steering angle, the pre-set minimum steering angle is used as the current steering angle of the vehicle to be predicted.

[0138] Furthermore, the distance d between the vehicle to be predicted and the target road point is determined i , according to the prediction time, the speed and distance d of the vehicle to be predicted i Calculate the acceleration a of the vehicle to be predicted during the prediction time i,c , as another control quantity (longitudinal control quantity) to control the vehicle movement.

[0139]

[0140] in, represents the location information of the i-th vehicle to be predicted, (g i,x ,g i,y ) represents the location coordinates of the target road point, represents the coordinates of the position information of the i-th vehicle to be predicted, is the speed of the i-th vehicle to be predicted, and T′ is the prediction time.

[0141] Furthermore, the trajectory prediction system can calculate the steering angle of the vehicle to be predicted. Acceleration i,c As the lateral and longitudinal control quantities, the driving coordinates of the vehicle to be predicted at the next moment are determined, that is, the state of the vehicle to be predicted (position, speed, heading angle) is updated, which can be determined by the following formulas 8 to 11.

[0142]

[0143] in, represents the position information of the i-th vehicle to be predicted at time t, represents the heading angle of the i-th vehicle to be predicted at time t, represents the speed of the i-th vehicle to be predicted at time t, Δt is the time interval between adjacent time steps, represents the position information of the i-th vehicle to be predicted at time t+1, that is, the driving coordinates of the vehicle to be predicted at the next moment, represents the heading angle of the i-th vehicle to be predicted at time t+1, Represents the speed of the i-th vehicle to be predicted at time t+1.

[0144] After completing the update of the state of the vehicle to be predicted at the current time t, the preview point is obtained by repeating the preview along the reference path at time t+1. The position coordinates of the vehicle to be predicted at the next time are obtained by tracking the preview point through the steering angle and acceleration, and finally a motion form trajectory with controllable curvature change rate of each point is generated, such as Figure 5 As shown, the black solid line represents the generated motion trajectory within the future prediction duration.

[0145] It should be understood that physical feasibility is crucial in vehicle trajectory prediction because it determines whether the prediction results can be actually applied in the autonomous driving system. If the predicted trajectory violates physical feasibility, even if its average displacement error is very small, it may cause the autonomous driving vehicle to encounter a trajectory that cannot be followed during actual driving, thereby causing safety hazards. The trajectory prediction system provided in the embodiment of the present application comprehensively considers the vehicle's motion state parameters and motion feasibility constraints. The present invention can screen out candidate road points that are more in line with the actual driving conditions of the vehicle, thereby generating a more accurate driving trajectory.

[0146] At the same time, the embodiment of the present application also takes into account various factors such as motion feasibility constraints (road conditions, traffic rules), further improving the reliability and practicality of trajectory prediction.

[0147] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the image acquisition device or electronic device includes a hardware structure and / or software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0148] The embodiment of the present application can exemplarily divide the functional modules of the image acquisition device or electronic device according to the above method. For example, the image acquisition device or electronic device can include various functional modules corresponding to the various functional divisions, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0149] Figure 7 is a block diagram of another trajectory prediction device according to an exemplary embodiment. Figure 7 The trajectory prediction device includes: a processing unit 701 and an acquisition unit 702.

[0150] The acquisition unit 702 is used to obtain the motion state parameters and the first candidate road point of the vehicle to be predicted; the first candidate road point is determined based on the surrounding road information of the vehicle to be predicted; the processing unit 701 is used to filter out the second candidate road point from the first candidate road point based on the motion state parameters and the motion feasibility constraint conditions of the vehicle to be predicted; the processing unit 701 is also used to generate the motion trajectory of the vehicle to be predicted based on the second candidate road point.

[0151] In one possible implementation, the motion feasibility constraint is determined based on road driving rules and / or configuration information of the vehicle to be predicted; the motion feasibility constraint includes at least one of the following: a maximum acceleration constraint of the vehicle to be predicted, a maximum deceleration constraint of the vehicle to be predicted, a maximum steering constraint of the vehicle to be predicted, and a road speed limit constraint.

[0152] In a possible implementation, the processing unit 701 is specifically used to determine a first road segment of a preset distance in the direction of movement of the vehicle to be predicted based on the position information of the vehicle to be predicted and the surrounding road information; discretize the center line of the first road segment to obtain a third candidate road point; determine a first search area based on the current speed, heading angle and road factor of the vehicle to be predicted and the road factor of the first road segment; the road factor is determined based on the road segment type of the first road segment; the center line direction of the first search area is consistent with the heading angle; the search range of the first search area is positively correlated with the current speed; and determine the first candidate road point from the third candidate road point based on the first search area.

[0153] In one possible implementation, the processing unit 701 is specifically used to filter out candidate points within a proximal deceleration range and candidate points outside a distal acceleration range from the first candidate road points to obtain a second candidate road point; wherein the proximal deceleration range is determined based on the current speed of the vehicle to be predicted and a maximum deceleration constraint; and the distal acceleration range is determined based on the current speed of the vehicle to be predicted, a maximum acceleration constraint, and a road speed limit constraint.

[0154] In a possible implementation, the processing unit 701 is specifically configured to determine a target road point from the second candidate road points; generate a motion trajectory of the vehicle to be predicted based on the target road point; and the motion trajectory is a trajectory between the current position of the vehicle to be predicted and the target road point.

[0155] In one possible implementation, the processing unit 701 is specifically used to input the position information, motion state parameters and position information of the candidate road points of the vehicle to be predicted into the graph attention network model to obtain the target road point with the highest attention coefficient among the second candidate road points; the attention coefficient is used to characterize the confidence of the vehicle to be predicted in the candidate road points.

[0156] In one possible implementation, the processing unit 701 is specifically used to determine a reference path of the vehicle to be predicted based on the target road point; the reference path is an estimated path between a lane segment where the vehicle to be predicted is located and a lane segment where the target road point is located; based on the reference path and position information of the vehicle to be predicted, multiple driving coordinates of the vehicle to be predicted are determined; based on the multiple driving coordinates, a motion trajectory of the vehicle to be predicted is generated; the motion trajectory is a trajectory between the current position of the vehicle to be predicted and the target road point.

[0157] In a possible implementation, the reference path includes multiple preview points; the preview points are used to represent the expected coordinates on the reference path; the processing unit 701 is specifically used to: for each of the multiple preview points, determine the steering angle required for the vehicle to be predicted to travel to the preview point based on the motion state parameters of the vehicle to be predicted; determine the acceleration of the vehicle to be predicted based on the position information of the vehicle to be predicted and the target road point; determine the driving coordinates of the vehicle to be predicted based on the acceleration and the steering angle, so as to obtain multiple driving coordinates of the vehicle to be predicted.

[0158] In one possible implementation, the processing unit 701 is specifically used to: obtain a lane segment set between a target lane segment and a lane segment where a vehicle to be predicted is located; the target lane segment is a lane segment where a target road point is located; and perform equidistant sampling along a lane centerline on each lane segment in the lane segment set to generate a reference path between the target lane segment and the lane segment where a vehicle to be predicted is located.

[0159] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0160] Figure 8 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 8 As shown, the electronic device includes but is not limited to: a processor 801 and a memory 802 .

[0161] The memory 802 is used to store executable instructions of the processor 801. It can be understood that the processor 801 is configured to execute instructions to implement the image acquisition method in the above embodiment.

[0162] It should be noted that those skilled in the art can understand that Figure 8 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and the electronic device may include Figure 8 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0163] The processor 801 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 802, and calling data stored in the memory 802, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 801 may include one or more processing units. Optionally, the processor 801 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 801.

[0164] The memory 802 may be used to store software programs and various data. The memory 802 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one functional module (such as a determination unit, a processing unit, etc.), etc. In addition, the memory 802 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.

[0165] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 802 including instructions. The above instructions can be executed by a processor 801 of an electronic device to implement the method in the above embodiment.

[0166] In actual implementation, Figure 7 The functions of the processing unit 701 and the acquisition unit 702 in Figure 8 The processor 801 in the embodiment calls the computer program stored in the memory 802. The specific execution process can refer to the description of the method part in the above embodiment, which will not be repeated here.

[0167] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0168] In an exemplary embodiment, the present application also provides a computer program product including one or more instructions, and the one or more instructions can be executed by the processor 801 of the electronic device to complete the method in the above embodiment.

[0169] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the above-mentioned method embodiment are implemented, and the same technical effect as the above-mentioned method can be achieved. To avoid repetition, they will not be repeated here.

[0170] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0171] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0172] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0173] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0174] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or part of the prior art that contributes to the prior art or part or all of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the methods of each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0175] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A trajectory prediction method, characterized in that: Applied to a target vehicle, the method comprises: Acquire motion state parameters of the vehicle to be predicted and a first candidate road point; the first candidate road point is determined based on surrounding road information of the vehicle to be predicted; Based on the motion state parameter and the motion feasibility constraint condition of the vehicle to be predicted, selecting a second candidate road point from the first candidate road point; Based on the second candidate road point, a motion trajectory of the vehicle to be predicted is generated.

2. The method according to claim 1, characterized in that The motion feasibility constraint condition is determined based on road driving rules and / or configuration information of the vehicle to be predicted; the motion feasibility constraint condition includes at least one of the following: The maximum acceleration constraint of the vehicle to be predicted; The maximum deceleration constraint of the vehicle to be predicted; The maximum steering constraint of the vehicle to be predicted; Road speed limit restrictions.

3. The method according to claim 2, characterized in that Get the first candidate road point, including: Determine a first road segment of a preset distance in the moving direction of the vehicle to be predicted based on the position information of the vehicle to be predicted and the surrounding road information; Performing discretization sampling on the center line of the first road segment to obtain a third candidate road point; determining a first search area based on the current speed, heading angle and road factor of the first road segment of the vehicle to be predicted; the road factor is determined based on the road segment type of the first road segment; the centerline orientation of the first search area is consistent with the heading angle; and the search range of the first search area is positively correlated with the current speed; The first candidate road point is determined from the third candidate road point based on the first search area.

4. The method according to claim 2, characterized in that: The selecting a second candidate road point from the first candidate road point based on the motion state parameter and the motion feasibility constraint condition of the to-be-predicted vehicle comprises: Eliminate the candidate points located within the near-end deceleration range and the candidate points located outside the far-end acceleration range from the first candidate road points to obtain the second candidate road points; The proximal deceleration range is determined based on the current speed of the vehicle to be predicted and the maximum deceleration constraint; the distal acceleration range is determined based on the current speed of the vehicle to be predicted, the maximum acceleration constraint and the road speed limit constraint.

5. The method according to claim 1, characterized in that The step of generating the motion trajectory of the vehicle to be predicted based on the second candidate road point includes: Determine a target road point from the second candidate road points; A motion trajectory of the vehicle to be predicted is generated based on the target road point; the motion trajectory is a trajectory between a current position of the vehicle to be predicted and the target road point.

6. The method according to claim 5, characterized in that The step of determining a target road point from the second candidate road points comprises: The position information of the vehicle to be predicted, the motion state parameters and the position information of the candidate road points are input into the graph attention network model to obtain the target road point with the highest attention coefficient among the second candidate road points; the attention coefficient is used to characterize the confidence of the vehicle to be predicted in the candidate road points.

7. The method according to claim 5, characterized in that The step of generating the motion trajectory of the vehicle to be predicted based on the target road point comprises: Based on the target road point, determining a reference path of the vehicle to be predicted; the reference path is an estimated path between the lane segment where the vehicle to be predicted is located and the lane segment where the target road point is located; Determine a plurality of driving coordinates of the vehicle to be predicted based on the reference path and the position information of the vehicle to be predicted; A motion trajectory of the vehicle to be predicted is generated according to the multiple driving coordinates; the motion trajectory is a trajectory between the current position of the vehicle to be predicted and the target road point.

8. The method according to claim 7, characterized in that The reference path includes a plurality of preview points; the preview points are used to represent the estimated coordinates on the reference path; The step of determining a plurality of driving coordinates of the vehicle to be predicted based on the reference path and the position information of the vehicle to be predicted includes: For each of the plurality of preview points, determining a steering angle required for the vehicle to be predicted to travel to the preview point based on a motion state parameter of the vehicle to be predicted; Determining the acceleration of the vehicle to be predicted based on the position information of the vehicle to be predicted and the target road point; Based on the acceleration and the steering angle, the driving coordinates of the vehicle to be predicted are determined to obtain a plurality of driving coordinates of the vehicle to be predicted.

9. The method according to claim 7, characterized in that: The step of determining a reference path of the vehicle to be predicted based on the target road point comprises: Acquire a lane segment set between a target lane segment and the lane segment where the vehicle to be predicted is located; the target lane segment is the lane segment where the target road point is located; Each lane segment in the lane segment set is sampled at equal intervals along the lane centerline to generate the reference path between the target lane segment and the lane segment where the vehicle to be predicted is located.

10. A trajectory prediction device, characterized in that: The device comprises: a processing unit and an acquisition unit; The acquisition unit is used to acquire the motion state parameters of the vehicle to be predicted and a first candidate road point; the first candidate road point is determined based on the surrounding road information of the vehicle to be predicted; The processing unit is configured to select a second candidate road point from the first candidate road point based on the motion state parameter and the motion feasibility constraint condition of the vehicle to be predicted; The processing unit is further used to generate a motion trajectory of the vehicle to be predicted based on the second candidate road point.

11. A vehicle, characterized in that: The vehicle comprises the device of claim 10.

12. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 9.

13. A computer-readable storage medium, characterized in that: When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is capable of performing the method as claimed in any one of claims 1 to 9.

14. A computer program product comprising instructions, characterized in that When the instructions are executed by a computer, the computer is caused to perform the method according to any one of claims 1 to 9.

Images