Lane change intention prediction method and system for vehicle, vehicle and device

Abstract

This application discloses a method, system, vehicle, and device for predicting a vehicle's lane-change intention. The method includes: obtaining the real-time position of a vehicle target; determining the motion state of the vehicle target at various times based on changes in its real-time position; obtaining the final motion state of the vehicle target based on its motion state at various times; and predicting whether the vehicle target has a lane-change intention that could affect the vehicle's driving state based on its final motion state and the positional relationship between the vehicle target and the vehicle's lane lines. By analyzing the motion state of a vehicle target and its positional relationship with the vehicle's lane lines, this application can predict whether it has a lane-change intention that could affect the vehicle's driving state. Based on the prediction results, the vehicle can plan and control its driving in advance, thereby effectively improving driving safety.

Description

Technical Field

[0001] This application relates to the field of driver assistance systems, and more particularly to a method, system, vehicle, and device for predicting a vehicle's lane change intention. Background Technology

[0002] In target perception, accurately determining the target's motion state is crucial. However, current smart cameras can only output the target's location information and cannot predict its behavioral intentions. This makes it difficult for the system to respond correctly in a timely manner when faced with a vehicle changing lanes ahead. Specifically, if the driver assistance system is accelerating, and the system cannot predict the intention of the target ahead to cut in, the sudden cut in may cause a collision risk or require emergency braking. Similarly, if the vehicle is planning to change lanes in the same direction when the target ahead is about to cut out, it may also fail to recognize the target's cutting-out behavior in time, resulting in a collision with the vehicle ahead or emergency braking, thus affecting driving safety and user experience. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, system, vehicle, and device for predicting a vehicle's lane-changing intention in order to address the aforementioned technical problems. By analyzing the motion state of the vehicle target and its positional relationship with the vehicle's lane lines, it is possible to predict whether the vehicle has a lane-changing intention that may affect the vehicle's driving. Based on the prediction results, the vehicle can plan and control its driving in advance, thereby effectively improving driving safety.

[0004] Firstly, a method for predicting a vehicle's lane-changing intention is provided, including: Obtain the real-time location of the vehicle target; Based on the real-time position changes of the vehicle target, the motion state of the vehicle target at each of multiple time points is determined; Based on the motion state of the vehicle target at each of the multiple time points, the final motion state of the vehicle target is obtained; Based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line of the vehicle, it can be predicted whether the vehicle target has the intention to change lanes in a way that affects the driving state of the vehicle.

[0005] In some examples, the process of obtaining the real-time location of the vehicle target also includes: Obtain nearby targets for the vehicle; The vehicle target is selected based on the type, heading angle, and location of the nearby targets.

[0006] In some examples, filtering the vehicle target based on the type, heading angle, and location of the nearby targets includes: Based on the type of the nearby targets, nearby targets that are not vehicles are removed; Based on the heading angle of the nearby targets, eliminate nearby targets whose heading is opposite to that of the vehicle; Based on the location of the nearby targets, nearby targets whose lateral position relative to the vehicle is greater than a preset value are eliminated to filter out the vehicle target.

[0007] In some examples, the lane markings for the vehicle are determined as follows: When the vehicle does not detect a lane line, the trajectory of the vehicle is calculated based on the vehicle's speed and yaw rate, and a virtual lane line is generated based on the trajectory line. Otherwise, the lane line of the vehicle is obtained based on the detected lane line.

[0008] In some examples, determining the motion state of the vehicle target at each of multiple time points based on the real-time position changes of the vehicle target includes: Calculate the absolute value of the lateral position change of the vehicle target; When the lateral position change is positive and the absolute value is greater than the first lateral movement threshold, it is determined that the vehicle target is in a state of rapid lateral movement to the left. When the lateral position change is positive and the absolute value is between the second lateral movement threshold and the first lateral movement threshold, it is determined that the vehicle target is in a state of lateral movement to the left at a normal speed. When the lateral position change is positive and the absolute value is between the third lateral movement threshold and the second lateral movement threshold, it is determined that the vehicle target is in a slow lateral movement state to the left. When the lateral position change is negative and the absolute value is greater than the first lateral movement threshold, it is determined that the vehicle target is in a state of rapid lateral movement to the right. When the lateral position change is negative and the absolute value is between the second lateral movement threshold and the first lateral movement threshold, it is determined that the vehicle target is in a state of lateral movement to the right at a normal speed. When the lateral position change is negative and the absolute value is between the third lateral movement threshold and the second lateral movement threshold, it is determined that the vehicle target is in a slow lateral movement to the right, wherein the first lateral movement threshold is greater than the second lateral movement threshold and the second lateral movement threshold is greater than the third lateral movement threshold.

[0009] In some examples, predicting whether the vehicle target has a lane-changing intention that could affect the vehicle's driving state, based on the vehicle target's final motion state and the positional relationship between the vehicle target and the lane lines the vehicle is traveling in, includes: Based on the final motion state of the vehicle target, determine whether the vehicle target intends to change lanes; If so, then the lane-changing behavior of the vehicle target is predicted based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line on which the vehicle is traveling.

[0010] In some examples, predicting the lane-changing behavior of the vehicle target based on its final motion state and the positional relationship between the vehicle target and the lane line it is traveling in includes: When the vehicle target is located to the right of the vehicle, and the vehicle target is outside the lane line, and the vehicle target is eventually in a lateral movement to the left, it is predicted that the vehicle target will soon cut in to the left. When the vehicle target is located to the right of the vehicle, and the vehicle target is within the lane line, and the vehicle target is eventually in a lateral movement to the left, it is predicted that the vehicle target will soon intrude to the left. When the vehicle target is located to the left of the vehicle, and the vehicle target is within the lane line, and the vehicle target is eventually in a lateral movement to the left, it is predicted that the vehicle target will soon cut out to the left. When the vehicle target is located to the left of the vehicle, and the vehicle target is outside the lane line, and the vehicle target is eventually in a lateral movement to the right, it is predicted that the vehicle target will soon cut in to the right. When the vehicle target is located to the left of the vehicle, and the vehicle target is within the lane line, and the vehicle target is eventually in a lateral movement to the right, it is predicted that the vehicle target will soon intrude to the right. When the vehicle target is located to the right of the vehicle, and the vehicle target is within the lane line, and the vehicle target is eventually in a lateral movement to the right, it is predicted that the vehicle target will soon cut out to the right.

[0011] Secondly, a vehicle lane-change intention prediction system is provided, including: The acquisition module is used to obtain the real-time location of the vehicle target; The determination module is used to determine the motion state of the vehicle target at each time point in multiple time points based on the real-time position changes of the vehicle target. The calculation module is used to obtain the final motion state of the vehicle target based on the motion state of the vehicle target at each time point in multiple time periods. The prediction module is used to predict whether the vehicle target has a lane-changing intention that would affect the driving state of the vehicle, based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line on which the vehicle is traveling.

[0012] Thirdly, a vehicle is provided, including: a lane change intention prediction system for the vehicle as described in the second aspect above.

[0013] Fourthly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the method for predicting the lane change intention of a vehicle as described in the first aspect and any possible implementation of the first aspect.

[0014] The embodiments of this application first obtain the real-time position of the vehicle target; then, based on the changes in the real-time position of the vehicle target, determine the motion state of the vehicle target at each of multiple time points; next, based on the motion state of the vehicle target at each of the multiple time points, obtain the final motion state of the vehicle target; finally, based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane lines of the vehicle, predict whether the vehicle target has a lane-changing intention that may affect the driving state of the vehicle. Therefore, by analyzing the motion state of the vehicle target and its positional relationship with the lane lines of the vehicle, it is possible to predict whether it has a lane-changing intention that may affect the driving state of the vehicle. Based on the prediction results, the vehicle can plan and control its driving in advance, thereby effectively improving driving safety. Attached Figure Description

[0015] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 A flowchart illustrating the method for predicting a vehicle's lane-changing intention as provided in this application embodiment; Figure 2 A schematic diagram illustrating the execution of the vehicle lane change intention prediction method provided in this application embodiment; Figure 3 This is a structural block diagram of a vehicle lane change intention prediction system provided in an embodiment of this application; Figure 4 This is a structural block diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0016] The present application will now be described in further detail with reference to the embodiments and accompanying drawings. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the application. Furthermore, it should be noted that, for ease of description, only the parts relevant to the application are shown in the accompanying drawings.

[0017] It should be noted that, unless otherwise specified, the embodiments and features of the embodiments in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0018] The following describes in detail, with reference to the accompanying drawings, a method, system, vehicle, and device for predicting a vehicle's lane-changing intention according to embodiments of this application.

[0019] Figure 1This is a flowchart of a method for predicting a vehicle's lane-changing intention according to an embodiment of this application. Figure 1 As shown, and in combination Figure 2 The method for predicting a vehicle's lane-changing intention according to an embodiment of this application includes the following steps: S101: Obtain the real-time location of the vehicle target.

[0020] In one embodiment of this application, before obtaining the real-time location of the vehicle target, the method further includes: acquiring nearby targets of the vehicle; and filtering out the vehicle target based on the type, heading angle, and location of the nearby targets.

[0021] In one embodiment of this application, the step of filtering the vehicle target based on the type, heading angle, and position of the neighboring target includes: eliminating neighboring targets that are not vehicles based on the type of the neighboring target; eliminating neighboring targets whose heading is opposite to that of the vehicle based on the heading angle of the neighboring target; and eliminating neighboring targets whose lateral position relative to the vehicle is greater than a preset value based on the position of the neighboring target, so as to filter the vehicle target.

[0022] In a specific example, the above preset value is set to the lane width. That is, when the lateral distance of the adjacent target from the vehicle is greater than the lane width, it is assumed that the adjacent target will not immediately cut into the vehicle's lane, so it is not included in the consideration of lane change prediction.

[0023] S102: Based on the real-time position changes of the vehicle target, determine the motion state of the vehicle target at each of multiple time points.

[0024] In one embodiment of this application, determining the motion state of the vehicle target at each of multiple moments based on the real-time position change of the vehicle target includes: calculating the absolute value of the lateral position change of the vehicle target; when the lateral position change is positive and the absolute value is greater than a first lateral movement threshold, determining that the vehicle target is in a rapid leftward lateral movement state; when the lateral position change is positive and the absolute value is between a second lateral movement threshold and the first lateral movement threshold, determining that the vehicle target is in a normal leftward lateral movement state; when the lateral position change is positive and the absolute value is between a third lateral movement threshold and the second lateral movement threshold, determining... The vehicle target is determined to be in a slow lateral movement to the left; when the lateral position change is negative and the absolute value is greater than a first lateral movement threshold, the vehicle target is determined to be in a rapid lateral movement to the right; when the lateral position change is negative and the absolute value is between a second lateral movement threshold and a first lateral movement threshold, the vehicle target is determined to be in a normal lateral movement to the right; when the lateral position change is negative and the absolute value is between a third lateral movement threshold and a second lateral movement threshold, the vehicle target is determined to be in a slow lateral movement to the right, wherein the first lateral movement threshold is greater than the second lateral movement threshold, and the second lateral movement threshold is greater than the third lateral movement threshold.

[0025] Specifically, after identifying the vehicle target through the above process, the system determines whether the vehicle target is a target that the vehicle is stably tracking based on the number of tracking frames, radar camera detection status, and number of lost frames. If it is a target that is stably tracked, the system extracts the historical position information of the vehicle target and then calculates the motion state of the vehicle target at each time point in multiple time periods.

[0026] The specific calculation process is as follows: assuming the vehicle target's lateral position in the current frame is... Y i In the previous frame, the horizontal position was Y i-1 Then, the change in the lateral position of the vehicle target at the current moment is: So, what is the current state of motion? M single As shown in Formula 1: (1) in, D quick This is the first horizontal shift threshold; D normal This is the second horizontal shift threshold; D slow The third horizontal shift threshold; when D y When >0, it indicates that the vehicle target has moved laterally to the left. D yWhen the value is less than 0, it indicates that the vehicle target has moved laterally to the right; M single The six motion states, from top to bottom, are: rapid lateral movement to the left, normal lateral movement to the left, slow lateral movement to the left, rapid lateral movement to the right, normal lateral movement to the right, and slow lateral movement to the right.

[0027] S103: Based on the motion state of the vehicle target at each of the multiple time points, obtain the final motion state of the vehicle target.

[0028] Specifically, values ​​are assigned to the various motion states mentioned above, and the motion state where the vehicle target neither moves to the left nor to the right is assigned a value of 0. Then, the motion state values ​​of the vehicle target at all times within a preset time are summed to obtain the final motion state of the vehicle target. The specific assignment rules are shown in Formula 2: (2) in, M i for i The final motion state of the vehicle target is obtained by summing the motion state values ​​of the vehicle target at each moment within a preset time period. M Simultaneously, record the number of times the vehicle target neither moved laterally to the left nor to the right. N noMove .

[0029] S104: Based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line of the vehicle, predict whether the vehicle target has a lane-changing intention that would affect the driving state of the vehicle.

[0030] In one embodiment of this application, the lane line for the vehicle is determined as follows: when the vehicle does not detect a lane line, the trajectory line of the vehicle is calculated based on the vehicle speed and yaw rate, and a virtual lane line is generated based on the trajectory line; otherwise, the lane line for the vehicle is obtained based on the detected lane line.

[0031] Specifically, when no lane lines are detected, the radius of the vehicle's trajectory is calculated using the vehicle's yaw rate, as shown in Formula 3: (3) in, R The radius of the running trajectory; V The vehicle's speed; y yaw_rate Let yaw rate be the angular velocity of the vehicle.

[0032] Next, the vehicle trajectory fitting equation shown in Formula 4 is adopted: (4) in, L The fitted vehicle trajectory line; C 0 represents the lateral position deviation between the current vehicle and the reference path; C 1 represents the heading deviation between the current vehicle and the reference path; C 2 represents the curvature of the current path; C 3 represents the rate of change of curvature. Since the trajectory calculation is performed for the vehicle, therefore... C 0 and C 1 takes the value 0. C The value of 2 is the curvature of the vehicle's trajectory, which is 1 / 2. R And since it is assumed that the vehicle moves in a circular arc along a fixed radius at the current moment, then C The value of 3 is 0. Therefore, the fitted vehicle trajectory line, which is the vehicle's running trajectory, can be obtained.

[0033] Furthermore, virtual lane lines are generated based on the lane width. In a specific example, the lane width is selected as a typical lane width of 3.6m, meaning the lateral position deviation of the vehicle from the left and right lane lines is 1.8m. Then, combining with Formula 4, the left and right virtual lane lines are shown in Formulas 5 and 6 respectively: (5) (6) For scenarios with lane markings, the lane markings detected by the vehicle perception system can be used directly. In this scenario, when an abnormal angle occurs between the vehicle trajectory line and the lane markings, the following judgment is made: if the vehicle is in this abnormal state for a short period of time, it is assumed that the vehicle is performing lane changing or other operations; if the time in this abnormal state exceeds a preset threshold, it is assumed that the lane markings detected by the vehicle perception system may be incorrect, and the virtual lane markings are calculated according to the scenario where no lane markings are detected.

[0034] In one embodiment of this application, the step of predicting whether the vehicle target has a lane-changing intention that would affect the driving state of the vehicle based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line on which the vehicle is traveling includes: determining whether the vehicle target has a lane-changing intention based on the final motion state of the vehicle target; if so, predicting the lane-changing behavior of the vehicle target based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line on which the vehicle is traveling.

[0035] Specifically, based on the final motion state of the vehicle target obtained above... M The number of moments when the vehicle target neither moved to the left nor to the right. N noMove Make a judgment: Let the total number of judgment times be... N,when N noMove ≥ N If the vehicle target does not move for more than half the time, it is considered that the target does not intend to change lanes; and an accumulation threshold for the motion state is set. M limit When M≥ M limit At that time, it is assumed that the vehicle target is moving laterally and has the intention to change lanes, and then the prediction of the vehicle target's lane-changing behavior begins.

[0036] In one embodiment of this application, predicting the lane-changing behavior of the vehicle target based on its final motion state and the positional relationship between the vehicle target and the lane line of the vehicle is traveling includes: when the vehicle target is located to the right of the vehicle and outside the lane line, and the vehicle target is ultimately in a lateral movement state to the left, it is predicted that the vehicle target is about to cut in to the left; when the vehicle target is located to the right of the vehicle and inside the lane line, and the vehicle target is ultimately in a lateral movement state to the left, it is predicted that the vehicle target is about to intrude to the left; when the vehicle target is located to the left of the vehicle and inside the lane line... If the vehicle target is ultimately in a leftward lateral movement state, it is predicted that the vehicle target will soon cut out to the left; if the vehicle target is located to the left of the vehicle, outside the lane line, and ultimately in a rightward lateral movement state, it is predicted that the vehicle target will soon cut in to the right; if the vehicle target is located to the left of the vehicle, inside the lane line, and ultimately in a rightward lateral movement state, it is predicted that the vehicle target will soon intrude to the right; if the vehicle target is located to the right of the vehicle, inside the lane line, and ultimately in a rightward lateral movement state, it is predicted that the vehicle target will soon cut out to the right.

[0037] The above process can be represented by Formula 7: (7) in, Y target For the position of the target vehicle relative to its own vehicle, when Y target <0 indicates that the target vehicle is located to the right of the vehicle. Y target >0 indicates that the target vehicle is located to the left of the vehicle. Y lane The lane markings are for the vehicle's own travel. When the target vehicle is on the right side of the vehicle, the right lane markings are selected; when the target vehicle is on the left side of the vehicle, the left lane markings are selected.

[0038] According to the vehicle lane change intention prediction method of this application embodiment, the real-time position of the vehicle target is first obtained; then, based on the changes in the real-time position of the vehicle target, the motion state of the vehicle target at each of multiple time points is determined; next, based on the motion state of the vehicle target at each of the multiple time points, the final motion state of the vehicle target is obtained; finally, based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line of the vehicle, it is predicted whether the vehicle target has a lane change intention that may affect the driving state of the vehicle. Therefore, by analyzing the motion state of the vehicle target and its positional relationship with the lane line of the vehicle, it is possible to predict whether it has a lane change intention that may affect the driving state of the vehicle. Based on the prediction results, the vehicle can plan and control its driving in advance, thereby effectively improving driving safety.

[0039] Figure 3 This is a structural block diagram of a vehicle lane change intention prediction system according to one embodiment of this application. Figure 3 As shown, a vehicle lane change intention prediction system according to an embodiment of this application includes: an acquisition module 310, a determination module 320, a calculation module 330, and a prediction module 340, wherein: The acquisition module 310 is used to obtain the real-time location of the vehicle target; The determination module 320 is used to determine the motion state of the vehicle target at each time point in multiple time points based on the real-time position changes of the vehicle target. The calculation module 330 is used to obtain the final motion state of the vehicle target based on the motion state of the vehicle target at each of the multiple time points. The prediction module 340 is used to predict whether the vehicle target has a lane-changing intention that would affect the driving state of the vehicle, based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line on which the vehicle is traveling.

[0040] The vehicle lane change intention prediction system according to embodiments of this application first obtains the real-time position of the vehicle target; then, based on the changes in the real-time position of the vehicle target, it determines the motion state of the vehicle target at each of multiple time points; next, based on the motion state of the vehicle target at each of the multiple time points, it obtains the final motion state of the vehicle target; finally, based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane lines of the vehicle, it predicts whether the vehicle target has a lane change intention that may affect the driving state of the vehicle. Therefore, by analyzing the motion state of the vehicle target and its positional relationship with the lane lines of the vehicle, it is possible to predict whether it has a lane change intention that may affect the driving state of the vehicle. Based on the prediction results, the vehicle can plan and control its driving in advance, thereby effectively improving driving safety.

[0041] Specific limitations regarding the vehicle lane change intention prediction system can be found in the limitations of the vehicle lane change intention prediction method described above, and will not be repeated here. Each module of the aforementioned vehicle lane change intention prediction system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the computer device's memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0042] Furthermore, a vehicle is provided, comprising: a lane change intention prediction system according to any of the above embodiments. The vehicle first obtains the real-time position of a vehicle target; then, based on changes in the real-time position of the vehicle target, determines the motion state of the vehicle target at each of multiple time points; next, based on the motion state of the vehicle target at each of the multiple time points, obtains the final motion state of the vehicle target; finally, based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane lines on which the vehicle is traveling, it predicts whether the vehicle target has a lane change intention that may affect the driving state of the vehicle. Thus, by analyzing the motion state of the vehicle target and its positional relationship with the lane lines on which the vehicle is traveling, it is possible to predict whether it has a lane change intention that may affect the driving state of the vehicle. Based on the prediction results, the vehicle can plan and control its driving in advance, thereby effectively improving driving safety.

[0043] Furthermore, other components and functions of the vehicle according to the embodiments of this application are known to those skilled in the art and will not be described in detail here.

[0044] In one embodiment, a computer device is provided. Figure 4 This is a structural block diagram of the computer device provided in the embodiments of this application, with reference to... Figure 4 The computer device includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned method embodiment for predicting a vehicle's lane-changing intention. For example, it executes: obtaining the real-time location of the vehicle target; Based on the real-time position changes of the vehicle target, the motion state of the vehicle target at each of multiple time points is determined; Based on the motion state of the vehicle target at each of the multiple time points, the final motion state of the vehicle target is obtained; Based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line of the vehicle, it can be predicted whether the vehicle target has the intention to change lanes in a way that affects the driving state of the vehicle.

[0045] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0046] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0047] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A lane change intention prediction method for a vehicle, characterized by, include: Obtain the real-time location of the vehicle target; Based on the real-time position changes of the vehicle target, the motion state of the vehicle target at each of multiple time points is determined; Based on the motion state of the vehicle target at each of the multiple time points, the final motion state of the vehicle target is obtained; Based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line of the vehicle, it can be predicted whether the vehicle target has the intention to change lanes in a way that affects the driving state of the vehicle.

2. The lane change intention anticipation method of claim 1, wherein Before obtaining the real-time location of the vehicle target, the following is also included: Obtain nearby targets for the vehicle; The vehicle target is selected based on the type, heading angle, and location of the nearby targets.

3. The method for predicting a vehicle's lane-changing intention according to claim 2, characterized in that, The step of filtering vehicle targets based on the type, heading angle, and position of nearby targets includes: Based on the type of the nearby targets, nearby targets that are not vehicles are removed; Based on the heading angle of the nearby targets, eliminate nearby targets whose heading is opposite to that of the vehicle; Based on the location of the nearby targets, nearby targets whose lateral position relative to the vehicle is greater than a preset value are eliminated to filter out the vehicle target.

4. The method for predicting a vehicle's lane-changing intention according to claim 1, characterized in that, The lane markings for the vehicle are determined in the following manner: When the vehicle does not detect a lane line, the trajectory of the vehicle is calculated based on the vehicle's speed and yaw rate, and a virtual lane line is generated based on the trajectory line. Otherwise, the lane line of the vehicle is obtained based on the detected lane line.

5. The method for predicting a vehicle's lane-changing intention according to claim 1, characterized in that, The step of determining the motion state of the vehicle target at each of multiple time points based on the real-time position changes of the vehicle target includes: Calculate the absolute value of the lateral position change of the vehicle target; When the lateral position change is positive and the absolute value is greater than the first lateral movement threshold, it is determined that the vehicle target is in a state of rapid lateral movement to the left. When the lateral position change is positive and the absolute value is between the second lateral movement threshold and the first lateral movement threshold, it is determined that the vehicle target is in a state of lateral movement to the left at a normal speed. When the lateral position change is positive and the absolute value is between the third lateral movement threshold and the second lateral movement threshold, it is determined that the vehicle target is in a slow lateral movement state to the left. When the lateral position change is negative and the absolute value is greater than the first lateral movement threshold, it is determined that the vehicle target is in a state of rapid lateral movement to the right. When the lateral position change is negative and the absolute value is between the second lateral movement threshold and the first lateral movement threshold, it is determined that the vehicle target is in a state of lateral movement to the right at a normal speed. When the lateral position change is negative and the absolute value is between the third lateral movement threshold and the second lateral movement threshold, it is determined that the vehicle target is in a slow lateral movement to the right, wherein the first lateral movement threshold is greater than the second lateral movement threshold and the second lateral movement threshold is greater than the third lateral movement threshold.

6. The method for predicting a vehicle's lane-changing intention according to claim 1, characterized in that, The step of predicting whether the vehicle target has a lane-changing intention that would affect the driving state of the vehicle, based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line of the vehicle, includes: Based on the final motion state of the vehicle target, determine whether the vehicle target intends to change lanes; If so, then the lane-changing behavior of the vehicle target is predicted based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line on which the vehicle is traveling.

7. The method for predicting a vehicle's lane-changing intention according to claim 6, characterized in that, The step of predicting the lane-changing behavior of the vehicle target based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line on which the vehicle is traveling includes: When the vehicle target is located to the right of the vehicle, and the vehicle target is outside the lane line, and the vehicle target is eventually in a lateral movement to the left, it is predicted that the vehicle target will soon cut in to the left. When the vehicle target is located to the right of the vehicle, and the vehicle target is within the lane line, and the vehicle target is eventually in a lateral movement to the left, it is predicted that the vehicle target will soon intrude to the left. When the vehicle target is located to the left of the vehicle, and the vehicle target is within the lane line, and the vehicle target is eventually in a lateral movement to the left, it is predicted that the vehicle target will soon cut out to the left. When the vehicle target is located to the left of the vehicle, and the vehicle target is outside the lane line, and the vehicle target is eventually in a lateral movement to the right, it is predicted that the vehicle target will soon cut in to the right. When the vehicle target is located to the left of the vehicle, and the vehicle target is within the lane line, and the vehicle target is eventually in a lateral movement to the right, it is predicted that the vehicle target will soon intrude to the right. When the vehicle target is located to the right of the vehicle, and the vehicle target is within the lane line, and the vehicle target is eventually in a lateral movement to the right, it is predicted that the vehicle target will soon cut out to the right.

8. A vehicle lane change intention prediction system, characterized in that, include: The acquisition module is used to obtain the real-time location of the vehicle target; The determination module is used to determine the motion state of the vehicle target at each time point in multiple time points based on the real-time position changes of the vehicle target. The calculation module is used to obtain the final motion state of the vehicle target based on the motion state of the vehicle target at each time point in multiple time periods. The prediction module is used to predict whether the vehicle target has a lane-changing intention that would affect the driving state of the vehicle, based on the final motion state of the vehicle target and the positional relationship between the vehicle target and the lane line on which the vehicle is traveling.

9. A vehicle, characterized in that, include: The vehicle lane change intention prediction system according to claim 8.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for predicting the lane change intention of a vehicle according to any one of claims 1-7.

Images