Vehicle trajectory prediction method, device, storage medium and electronic terminal
By obtaining vehicle status information and calculating its status in the Frenet coordinate system, judging vehicle intentions and predicting lanes, the deviation and complexity of vehicle trajectory prediction in the prior art are solved, and efficient and real-time trajectory prediction is achieved.
Patent Information
- Application Number
- CN202411034577.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-07-31
Smart Images

Figure CN118560505B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of vehicle trajectory prediction, and in particular to a vehicle trajectory prediction method, device, storage medium and electronic terminal. Background Art
[0002] Trajectory prediction is to predict the future movement trajectory of a vehicle by mining its past driving status. It has shown great application potential in the fields of traffic scheduling optimization, location-based personalized services, and autonomous driving assistance systems. By accurately predicting vehicle trajectories, traffic managers can identify potential congested areas in advance and implement effective traffic diversion strategies; drivers can obtain real-time route adjustment suggestions to avoid unnecessary delays.
[0003] However, vehicle trajectory prediction faces many challenges, the most prominent of which are the complexity of the road network, the dynamics of urban traffic, and the uncertainty of driving conditions. These factors lead to a high degree of uncertainty in the future behavior intentions of the predicted object. Even in the same scenario, different vehicles may show completely different driving paths due to differences in the subjective decisions of the drivers. The existence of such multimodal decision-making behaviors greatly increases the difficulty of trajectory prediction.
[0004] At present, trajectory prediction methods can be mainly divided into four categories: physics-based, machine learning, deep learning, and reinforcement learning. Although the latter three have certain advantages in prediction accuracy and generalization ability, they are all highly dependent on large-scale data collection and annotation, as well as a long model training process, which is difficult to achieve in many practical application scenarios. In contrast, the physics-based method does not require a complex data preparation process, and directly derives the vehicle's driving trajectory based on the assumed conditions, which has the advantages of high computational efficiency and low implementation cost. However, traditional physics-based methods often ignore the constraints of map information on the vehicle's motion trajectory, resulting in deviations between the prediction results and the actual situation.
[0005] Therefore, how to solve the deficiencies and shortcomings of existing technologies through effective vehicle trajectory prediction methods has become an important issue that researchers in this field need to solve urgently. Summary of the invention
[0006] The purpose of the present invention is to address the above-mentioned problem and to provide a lane prediction method, device, storage medium and electronic terminal for a vehicle.
[0007] The technical solution of the present invention is: a method for predicting vehicle trajectory, comprising the following steps: obtaining the state information of the vehicle, predicting the duration T and the frequency I, wherein the state information at least includes: all lanes on the road where the vehicle is traveling; , ,..., , the position of the vehicle and the speed of the vehicle, where N is a natural number and N≥2; based on the state information, the lane in which the vehicle is located is calculated , and the vehicle is in the lane The state of the Frenet coordinate system for reference , based on the state, determine the intention of the vehicle and calculate the predicted lane of the vehicle ,in, is the longitudinal displacement, is the lateral displacement, is the velocity in the longitudinal displacement, represents the velocity in lateral displacement, is the interpolation of the speed and the curvature of the projection point; based on the prediction duration T, the prediction frequency I and the vehicle prediction lane A predicted trajectory of the vehicle is generated.
[0008] As an improvement of the embodiment of the present invention, the "obtaining the vehicle status information" specifically includes: obtaining all lanes on the road on which the vehicle is traveling , ,..., ,Lane Include Center Line ,Left Lane ,Right Lane and the following lanes , , where i and j are both positive integers, , ; Get the position of the vehicle and speed , and are the X-axis and Y-axis components of the position in a preset Cartesian coordinate system, respectively, and are respectively the X-axis and Y-axis components of the velocity in the preset Cartesian coordinate system.
[0009] As an improvement of the embodiment of the present invention, the vehicle is in a lane The state of the Frenet coordinate system for reference is ; ; ; ; ; ; ; ; ; ; ;in, is the position of the vehicle in the lane The projection point in is the longitudinal displacement, is the lateral displacement, is the velocity in the longitudinal displacement, is the velocity in the lateral displacement, is the interpolation of velocity and curvature of the projection point.
[0010] As an improvement of the embodiment of the present invention, the “calculating the lane where the vehicle is located based on the state information” and the vehicle is in the lane The state of the Frenet coordinate system for reference "Specifically includes: calculating the position of the vehicle To each lane Center line The distance of the lane with the smallest distance The lane in which the vehicle is located Calculate the vehicle in the lane The state of the Frenet coordinate system for reference .
[0011] As an improvement to the embodiment of the present invention, the “judging the intention of the vehicle based on the state, calculating the predicted lane of the vehicle” "Specifically including: interpolation based on the velocity and the curvature of the projection point Determine the intention of the vehicle and set the intention to go straight; if and and and , the intention is to change lane right, and the vehicle predicts lane ;like and and , the intention is to change lane left, and the vehicle predicts lane If the intention is to go straight, the vehicle predicts lane ,in, , ;
[0012] Continuously perform the following steps: calculate the position projection point of the vehicle, and the position projection point and the vehicle predicted lane Points in If the distance D between , then the vehicle prediction lane The center line of the following lane Splice in the predicted lane for the vehicle Center line Behind, when Stop executing subsequent steps.
[0013] As an improvement of the embodiment of the present invention, the “based on the prediction time T, the prediction frequency I and the vehicle prediction lane Generating the predicted trajectory of the vehicle specifically includes: calculating the vehicle in the predicted lane The initial position in the reference Frenet coordinate system and the end position ,in, , , , ; Based on the initial position, the end position, the predicted duration T and the predicted frequency I, the Frenet coordinates of the vehicle in the predicted duration T are calculated , the Frenet coordinates Convert to default Cartesian coordinates Traj , the Cartesian coordinate Traj is the predicted trajectory of the vehicle.
[0014] As an improvement of the embodiment of the present invention, the , ;in, ; .
[0015] To achieve one of the above-mentioned purposes, an embodiment of the present invention provides a vehicle trajectory prediction device, comprising the following modules: an information acquisition module, for acquiring the state information of the vehicle, the prediction duration T and the prediction frequency I, wherein the state information at least includes: all lanes on the road on which the vehicle is traveling; , ,..., , the position of the vehicle and the speed of the vehicle, wherein N is a natural number and N≥2; a calculation module, for obtaining the lane in which the vehicle is located based on the state information and the vehicle is in the lane The state of the Frenet coordinate system for reference , determine the intention of the vehicle based on the state, and calculate the vehicle's predicted lane centerline ; Trajectory prediction module, used to predict the lane centerline based on the prediction duration T, prediction frequency I and the vehicle A predicted trajectory of the vehicle is generated.
[0016] To achieve one of the above objects of the invention, an embodiment of the present invention provides a storage medium storing program instructions, wherein the program instructions implement the prediction method as described in any one of the above items when executed.
[0017] To achieve one of the above objects of the invention, an embodiment of the present invention provides an electronic terminal, including a processor and a memory, wherein the memory stores program instructions, and the processor executes the program instructions to implement the prediction method as described in any one of the above items.
[0018] The lane prediction method, device, storage medium and electronic terminal for vehicles provided by the embodiments of the present invention have the following advantages: by combining vehicle status information, Frenet coordinate system and vehicle intention prediction, the shortcomings of the prior art that ignore map information, rely on complex models and large amounts of data are overcome. By accurately acquiring key status information such as the vehicle's position, speed and lane on the road, the present invention can quickly map the vehicle state to a Frenet coordinate system with the lane centerline as a reference, so as to more intuitively understand the vehicle's motion state and judge the vehicle's driving intention, thereby predicting the lane that the vehicle may travel in the future. Finally, by combining the prediction duration and prediction frequency, a continuous and accurate vehicle prediction trajectory is generated, which not only improves the accuracy of trajectory prediction, but also greatly reduces the dependence on external data and computational complexity, and realizes efficient and real-time vehicle trajectory prediction. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1 A schematic diagram of a flow chart of a method for predicting vehicle trajectories provided in an embodiment of the present invention;
[0020] Figure 2 A comparison diagram of left-turn effects of the vehicle trajectory prediction method provided by an embodiment of the present invention;
[0021] Figure 3 A comparison diagram of the straight-line effect of the vehicle trajectory prediction method provided by an embodiment of the present invention;
[0022] Figure 4 A comparison diagram of the right turn effect of the vehicle trajectory prediction method provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0023] The present invention will be described in detail below in conjunction with the embodiments shown in the accompanying drawings. However, the embodiments do not limit the present invention, and any structural, methodological, or functional changes made by a person skilled in the art based on the embodiments are all within the protection scope of the present invention.
[0024] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.
[0025] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be indirectly connected through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.
[0026] Embodiment 1 of the present invention provides a method for predicting vehicle trajectory, such as Figure 1 As shown, the prediction method comprises the following steps:
[0027] Step 101: Obtain the vehicle's status information, prediction duration T and prediction frequency I, the status information at least including: all lanes on the road the vehicle is traveling on , ,..., , the position of the vehicle and the speed of the vehicle, where N is a natural number and N ≥ 2;
[0028] In practice, all lanes on the road the vehicle is currently traveling on can be obtained through the vehicle's onboard GPS (Global Positioning System) system or map service API (Application Programming Interface) , ,..., and the position of the vehicle. The current speed of the vehicle is obtained through the vehicle's speed sensor or GPS speed data. The prediction duration is set according to actual needs. For example, in order to support the path planning of the autonomous driving system, it is necessary to predict the vehicle trajectory within the next 8 seconds. Therefore, T can be set to 8 seconds. In order to ensure the real-time and accuracy of the trajectory, a higher prediction frequency can be set, such as I=1 second. Afterwards, the acquired road information, vehicle position, vehicle speed, and the set prediction duration T and prediction frequency I are integrated into a unified data structure for subsequent trajectory prediction calculations.
[0029] Step 102: Calculate the lane the vehicle is in based on the state information , and the vehicle is in the lane The state of the Frenet coordinate system for reference , based on the state, determine the intention of the vehicle and calculate the predicted lane of the vehicle ,in, is the longitudinal displacement, is the lateral displacement, is the velocity in the longitudinal displacement, represents the velocity in lateral displacement, is the interpolation of velocity and curvature of the projection point;
[0030] In practice, the lane a vehicle is in can be determined based on its position. , for example, to get all lanes , ,..., One-to-one correspondence between N middle lines , ,..., , then, calculate the position of the vehicle To each lane Center line The lane with the smallest distance to the center line is the lane ; Optionally, the middle line can be represented by multiple points.
[0031] Here, the Frenet coordinate system is a way to express the road position more intuitively than the traditional Cartesian coordinate system. Under the Frenet coordinate system, the motion state of the car can be simplified into a third-order motion system. Under the Frenet coordinate system, the vehicle motion can be decomposed into two parts: motion along the center line and motion perpendicular to the center line of the road. is the distance along the road (also called longitudinal displacement), is the left-right position on the road (also called lateral displacement).
[0032] Step 103: Based on the predicted duration T, predicted frequency I and the predicted lane of the vehicle A predicted trajectory of the vehicle is generated.
[0033] Here, if Figures 2 to 4 Shown are comparison diagrams of the effects of left turn, straight driving and right turn of the prediction method, wherein ① is the actual driving trajectory of the vehicle, ② is the driving trajectory generated by the prediction method of the present invention, ③ and ④ are the driving trajectories generated by the Kalman filter-based method and the motion model-based method, respectively. It can be seen that the prediction method of the present invention can accurately predict the trajectory of the vehicle and realize efficient and real-time vehicle trajectory prediction.
[0034] In this embodiment, the "obtaining the vehicle status information" specifically includes: obtaining all lanes on the road on which the vehicle is traveling , ,..., ,Lane Include Center Line ,Left Lane ,Right Lane and the following lanes , , where i and j are both positive integers, , ; Get the position of the vehicle and speed , and are the X-axis and Y-axis components of the position in a preset Cartesian coordinate system, respectively, and are respectively the X-axis and Y-axis components of the velocity in the preset Cartesian coordinate system.
[0035] Here, the Cartesian coordinate system is a set of mutually perpendicular axes with a common origin, which is used to determine the position of a point in a plane or space. Among them, the two-dimensional Cartesian coordinate system consists of two mutually perpendicular X-axis and Y-axis, which is used to describe a point on a plane.
[0036] In this embodiment, the vehicle is in a lane The state of the Frenet coordinate system for reference is ; ; ; ; ; ; ; ; ; ; ;in, is the position of the vehicle in the lane The projection point in is the longitudinal displacement, is the lateral displacement, is the velocity in the longitudinal displacement, is the velocity in the lateral displacement, is the interpolation of velocity and curvature of the projection point.
[0037] here, is the position of the vehicle in the lane The projection point in the image, r is the position of the vehicle to The index of the minimum coordinate of the Euclidean distance. The Euclidean distance can be calculated by the Pythagorean theorem. Interpolation is to interpolate a continuous function based on discrete data so that this continuous curve passes through all given discrete data points. Interpolation can be used to estimate the approximate value of the function at other points based on the value of the function at a finite number of points. It can be understood that this can make the predicted path more accurate and smooth.
[0038] In this embodiment, the “calculating the lane where the vehicle is located based on the state information” and the vehicle is in the lane The state of the Frenet coordinate system for reference "Specifically includes: calculating the position of the vehicle To each lane Center line The distance of the lane with the smallest distance The lane in which the vehicle is located Calculate the vehicle in the lane The state of the Frenet coordinate system for reference .
[0039] In this embodiment, the "determining the intention of the vehicle based on the state and calculating the predicted lane of the vehicle" "Specifically including: interpolation based on the velocity and the curvature of the projection point Determine the intention of the vehicle and set the intention to go straight; if and and and , the intention is to change lane right, and the vehicle predicts lane ;like and and , the intention is to change lane left, and the vehicle predicts lane If the intention is to go straight, the vehicle predicts lane ,in, , ;
[0040] Continuously perform the following steps: calculate the position projection point of the vehicle, and the position projection point and the vehicle predicted lane Points in If the distance D between , then the vehicle prediction lane The center line of the following lane Splice in the predicted lane for the vehicle Center line Behind, when Stop executing subsequent steps.
[0041] In practice, first, according to the vehicle's velocity interpolation and projection point curvature interpolation , combined with the preset angle change threshold theta_thr=0.26278 and the lateral distance threshold dis_thr=0.5, the vehicle's driving intention is comprehensively judged to be a left lane change, a right lane change or a straight drive. If it is determined to be a left lane change, the left lane line is selected as the vehicle's predicted lane If it is determined to be a right lane change, the right lane line is selected as the vehicle predicted lane If it is determined to be going straight, the current lane line is directly used as the predicted lane of the vehicle. After that, the current position of the vehicle is calculated in the vehicle prediction lane The projection point on the vehicle is calculated and the projection point is calculated to the predicted lane of the vehicle middle If D is less than 40 meters, it means that the current reference path is not enough to cover the future driving distance, and the vehicle prediction lane The center line of the following lane Splice in the predicted lane for the vehicle Center line Later, the reference path is extended. This process is repeated until the projection point reaches the predicted lane of the vehicle. The distance D is greater than or equal to 40 meters, thereby ensuring the continuity and accuracy of the predicted trajectory.
[0042] In this embodiment, the “based on the predicted duration T, predicted frequency I and the predicted lane of the vehicle Generating the predicted trajectory of the vehicle specifically includes: calculating the vehicle in the predicted lane The initial position in the reference Frenet coordinate system and the end position ,in, , , , ; Based on the initial position, the end position, the predicted duration T and the predicted frequency I, the Frenet coordinates of the vehicle in the predicted duration T are calculated , the Frenet coordinates Convert to default Cartesian coordinates Traj , the Cartesian coordinate Traj is the predicted trajectory of the vehicle.
[0043] In practice, based on the predicted lane The initial position and terminal position in the reference Frenet coordinate system, as well as the set prediction time T and prediction frequency I, can be used to calculate the Frenet coordinate trajectory of the vehicle within the prediction time T by interpolation or optimization algorithm. In this process, the Frenet coordinates of each time step are calculated to describe the motion state of the vehicle in the future prediction time period. Afterwards, these Frenet coordinates are converted into coordinates Traj in the preset Cartesian coordinate system to form the predicted trajectory of the vehicle in the global space. Preferably, the present invention uses interpolation to calculate the Frenet coordinate trajectory of the vehicle within the prediction time T. Interpolation is a method of estimating or predicting unknown data points through mathematical functions between discrete data points. In vehicle trajectory prediction, interpolation is widely used to calculate the continuous Frenet coordinate trajectory of the vehicle within the prediction time period according to the given initial and terminal Frenet coordinates, as well as the prediction time T and prediction frequency I. First, determine the discrete data points that need to be interpolated, that is, the initial and terminal Frenet coordinates. According to the distribution characteristics of the data points and the prediction requirements, select a suitable interpolation function. Optionally, the interpolation function includes linear interpolation, polynomial interpolation, spline interpolation, etc. For polynomial interpolation or spline interpolation, it is necessary to set parameters such as the order of the interpolation polynomial or the smoothness of the spline curve. Using the selected interpolation function and parameters, new data points are calculated between discrete data points to form a continuous trajectory. It can be understood that the interpolation method can provide efficient, accurate and smooth trajectory prediction results for the vehicle in vehicle trajectory prediction.
[0044] In this embodiment, the , ;in, ; .
[0045] Embodiment 2 of the present invention provides a vehicle trajectory prediction device, comprising the following modules: an information acquisition module, for acquiring the vehicle status information, prediction duration T and prediction frequency I, wherein the status information at least includes: all lanes on the road on which the vehicle is traveling; , ,..., , the position of the vehicle and the speed of the vehicle, wherein N is a natural number and N≥2; a calculation module, for obtaining the lane in which the vehicle is located based on the state information and the vehicle is in the lane The state of the Frenet coordinate system for reference , determine the intention of the vehicle based on the state, and calculate the vehicle's predicted lane centerline ; Trajectory prediction module, used to predict the lane centerline based on the prediction duration T, prediction frequency I and the vehicle A predicted trajectory of the vehicle is generated.
[0046] Embodiment 3 of the present invention provides a storage medium storing program instructions, wherein the program instructions, when executed, implement the prediction method as described in any one of the above items.
[0047] A fourth embodiment of the present invention provides an electronic terminal, including a processor and a memory, wherein the memory stores program instructions, and the processor executes the program instructions to implement any of the above prediction methods.
[0048] The present invention may be a system, a method and / or a computer program product. The computer program product may include a readable storage medium carrying computer readable program instructions for causing a processor to implement various aspects of the present invention.
[0049] The storage medium can be a tangible device that holds and stores instructions used by the instruction execution device. The storage medium can include, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a protruding structure in a groove on which instructions are stored, and any suitable combination thereof.
[0050] It should be understood that although this specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each implementation mode may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.
[0051] The series of detailed descriptions listed above are only specific descriptions of feasible implementation methods of the present invention. They are not intended to limit the scope of protection of the present invention. Any equivalent implementation methods or changes that do not deviate from the technical spirit of the present invention should be included in the scope of protection of the present invention.
Claims
1. A method for predicting vehicle trajectory, characterized in that: The following steps are involved: Obtain the vehicle's status information, predicted duration T and predicted frequency I, the status information at least including: all lanes on the road the vehicle is traveling on , ,..., , the position of the vehicle and the speed of the vehicle, wherein N is a natural number and N≥2; the "obtaining the state information of the vehicle" specifically includes: obtaining all lanes on the road on which the vehicle is traveling , ,..., ,Lane Include Center Line ,Left Lane ,Right Lane and the following lanes , , where i and j are both positive integers, , ; Get the position of the vehicle and speed , and are the X-axis and Y-axis components of the position in a preset Cartesian coordinate system, respectively, and are respectively the X-axis and Y-axis components of the velocity in the preset Cartesian coordinate system; Calculate the position of the vehicle To each lane Center line The distance of the lane with the smallest distance The lane in which the vehicle is located Calculate the vehicle in the lane The state of the Frenet coordinate system for reference ; The vehicle is in the lane The state of the Frenet coordinate system for reference is ; ; ; ; ; ; ; ; ; ; ; in, is the position of the vehicle in the lane The projection point in is the longitudinal displacement, is the lateral displacement, is the velocity in the longitudinal displacement, is the velocity in the lateral displacement, is the interpolation of velocity and curvature of the projection point; Interpolation based on the velocity and curvature of the projected point Determine the intention of the vehicle and set the intention to go straight; if and and and , the intention is to change lane right, and the vehicle predicts lane ;like and and , the intention is to change lane left, and the vehicle predicts lane If the intention is to go straight, the vehicle predicts lane ,in, , ; Continuously perform the following steps: calculate the position projection point of the vehicle, and the position projection point and the vehicle predicted lane Points in If the distance D between them is less than or equal to 40 m, the vehicle is predicted to be in the lane The center line of the following lane Splice in the predicted lane for the vehicle Center line Later, when D>40m, the subsequent steps are stopped, where: is the longitudinal displacement, is the lateral displacement, is the velocity in the longitudinal displacement, represents the velocity in lateral displacement, is the interpolation of velocity and curvature of the projection point; Based on the prediction time T, the prediction frequency I and the vehicle prediction lane A predicted trajectory of the vehicle is generated.
2. The prediction method according to claim 1, characterized in that: The "based on the predicted duration T, predicted frequency I and the vehicle predicted lane Generating the predicted trajectory of the vehicle specifically includes: calculating the vehicle in the predicted lane The initial position in the reference Frenet coordinate system and the end position ,in, , , , ; Based on the initial position, the final position, the predicted duration T and the predicted frequency I, the Frenet coordinates of the vehicle in the predicted duration T are calculated. , the Frenet coordinates Convert to the default Cartesian coordinates Traj , the Cartesian coordinate Traj is the predicted trajectory of the vehicle.
3. The prediction method according to claim 2, characterized in that: Said , ;in, ; .
4. A vehicle trajectory prediction device, characterized in that: Includes the following modules: An information acquisition module is used to obtain the vehicle's status information, prediction duration T and prediction frequency I, and the status information at least includes: all lanes on the road where the vehicle is traveling , ,..., , the position of the vehicle and the speed of the vehicle, wherein N is a natural number and N≥2; the "obtaining the state information of the vehicle" specifically includes: obtaining all lanes on the road on which the vehicle is traveling , ,..., ,Lane Include Center Line ,Left Lane ,Right Lane and the following lanes , , where i and j are both positive integers, , ; Get the position of the vehicle and speed , and are the X-axis and Y-axis components of the position in a preset Cartesian coordinate system, respectively, and are respectively the X-axis and Y-axis components of the velocity in the preset Cartesian coordinate system; A calculation module for calculating the position of the vehicle To each lane Center line The distance of the lane with the smallest distance The lane in which the vehicle is located Calculate the vehicle in the lane The state of the Frenet coordinate system for reference ; The vehicle is in the lane The state of the Frenet coordinate system for reference is ; ; ; ; ; ; ; ; ; ; ; in, is the position of the vehicle in the lane The projection point in is the longitudinal displacement, is the lateral displacement, is the velocity in the longitudinal displacement, is the velocity in the lateral displacement, is the interpolation of velocity and curvature of the projection point; Interpolation based on the velocity and curvature of the projected point Determine the intention of the vehicle and set the intention to go straight; if and and and , the intention is to change lane right, and the vehicle predicts lane ;like and and , the intention is to change lane left, and the vehicle predicts lane If the intention is to go straight, the vehicle predicts lane ,in, , ; Continuously perform the following steps: calculate the position projection point of the vehicle, and the position projection point and the vehicle predicted lane Points in If the distance D between them is less than or equal to 40 m, the vehicle is predicted to be in the lane The center line of the following lane Splice in the predicted lane for the vehicle Center line Later, when D>40m, stop executing the subsequent steps is the longitudinal displacement, is the lateral displacement, is the velocity in the longitudinal displacement, represents the velocity in lateral displacement, is the interpolation of velocity and curvature of the projection point; A trajectory prediction module is used to predict the lane centerline of the vehicle based on the prediction time T, the prediction frequency I and the vehicle A predicted trajectory of the vehicle is generated.
5. A storage medium storing program instructions, characterized in that: When the program instructions are executed, the prediction method according to any one of claims 1 to 3 is implemented.
6. A terminal, characterized in that: The method comprises a processor and a memory, wherein the memory stores program instructions, and the processor executes the program instructions to implement the prediction method according to any one of claims 1 to 3.
Citation Information
Patent Citations
Vehicle control method and device, vehicle to be controlled and storage medium
CN110834644A
Vehicle trajectory prediction method and device, equipment and storage medium
CN112644518A
