Heuristic lane-changing path planning method for vehicle, electronic device and storage medium

Abstract

The application discloses a heuristic lane-changing path planning method. The method determines desired state information for vehicle lane-changing through current state information of the vehicle; determines a preset area range for vehicle lane-changing according to the desired state information and a lane-changing direction, performs a first sampling operation on the preset area range to determine a heuristic trajectory corresponding to the desired state information; performs a second sampling operation on a sampling result range obtained by performing the first sampling operation according to the heuristic trajectory to obtain a plurality of trajectory curves for vehicle lane-changing; and performs a pruning operation on the plurality of trajectory curves to obtain a planning trajectory for vehicle lane-changing from the plurality of trajectory curves. The application also discloses an electronic device and a storage medium. The application uses heuristic trajectories for point sampling, improves sampling efficiency, and ensures the quality of point sampling.

Description

Technical Field

[0001] The disclosed embodiments of this application relate to the field of autonomous driving technology, and more specifically, to a heuristic path planning method for vehicle lane changing, electronic devices, and storage media. Background Technology

[0002] Path planning is one of the core technologies in autonomous driving. It mainly involves planning the vehicle's short-term driving trajectory based on information collected about the vehicle's surrounding environment, location, and current vehicle status. Existing path planning schemes primarily involve scattering points in different rows along perpendicular lane lines and smoothly connecting adjacent rows using a fifth-order polynomial. The interval between points within each row depends on factors such as vehicle speed, road structure, and lane changes.

[0003] Sampling directly impacts vehicle control, but existing solutions struggle to balance sampling quality and efficiency, particularly in lane-changing scenarios. Prioritizing completeness leads to longer processing times and lower efficiency, potentially causing sluggish responses in autonomous vehicle systems. Conversely, reducing sampling points for efficiency may result in inefficient paths that fail to adapt to complex road conditions. Therefore, achieving precise vehicle control requires a balance between sampling completeness and time consumption, making path planning that simultaneously balances sampling space completeness and time consumption crucial. Summary of the Invention

[0004] This application proposes a heuristic path planning method, electronic device, and storage medium for vehicle lane changing to solve the problem that the completeness of the sampling space cannot be balanced with the sampling time in the above-mentioned path planning.

[0005] A first aspect of this application discloses an exemplary heuristic path planning method for vehicle lane changing, comprising: acquiring current state information of a vehicle, and determining desired state information for vehicle lane changing based on the current state information; determining a preset area range for vehicle lane changing based on the desired state information and the vehicle lane changing direction, performing a first sampling operation on the preset area range, and determining a heuristic trajectory corresponding to the desired state information; performing a second sampling operation on the sampling result range obtained by performing the first sampling operation based on the heuristic trajectory, to obtain multiple trajectory curves for vehicle lane changing; and performing a pruning operation on the multiple trajectory curves to obtain a planned trajectory for vehicle lane changing from the multiple trajectory curves.

[0006] In some embodiments, the sampling result range is obtained by filtering the sampling results obtained by performing the first sampling operation on the preset region range.

[0007] In some embodiments, the sampling result includes multiple sampling points in the horizontal direction, wherein the multiple sampling points include a first layer sampling point and a second layer sampling point; the sampling result range includes either the first layer sampling point or the second layer sampling point; the step of performing a second sampling operation on the sampling result range obtained by performing the first sampling operation based on the heuristic trajectory to obtain multiple trajectory curves for vehicle lane changing includes: determining the intersection point of the heuristic trajectory with the first layer sampling point or the second layer sampling point; performing a densification sampling operation in a preset area of ​​the intersection point to obtain starting point state information for vehicle lane changing; and obtaining the multiple trajectory curves based on the starting point state information.

[0008] In some embodiments, the pruning operation includes at least one of the following operations: deleting a first trajectory curve from the plurality of trajectory curves, wherein the first trajectory curve represents a trajectory curve in which the ratio of lateral change to longitudinal change is greater than a preset value; deleting a second trajectory curve from the plurality of trajectory curves, wherein the second trajectory curve represents a trajectory curve in which the lateral movement in the direction of the vehicle lane change exceeds the sum of the current lateral position in the current state information and a preset value; deleting a third trajectory curve from the plurality of trajectory curves, wherein the third trajectory curve represents a trajectory curve in which the lateral value of a sampling point directly faces the direction and exceeds the lateral sampling range in which the sampling point is located; and deleting a fourth trajectory curve from the plurality of trajectory curves, wherein the fourth trajectory curve represents a trajectory curve in which the lateral values ​​of any two adjacent sampling points fluctuate within a specific range.

[0009] In some embodiments, performing a pruning operation on the plurality of trajectory curves includes: deleting a preset number of trajectory curves from the plurality of trajectory curves, wherein the ratio of the preset number of trajectory curves to the plurality of trajectory curves satisfies a preset value.

[0010] In some embodiments, obtaining a planned trajectory for vehicle lane changing from the plurality of trajectory curves includes: obtaining a planned trajectory for vehicle lane changing from the plurality of trajectory curves according to a preset method, wherein the preset method indicates that the planned trajectory meets preset conditions.

[0011] In some embodiments, the preset conditions include at least one of the following: the lateral value of the endpoint on the planned trajectory is less than a first predetermined value and the derivative of the lateral value of the endpoint with respect to the longitudinal value is less than a second predetermined value; and the similarity between the planned trajectory and the preset trajectory in different time periods meets a preset similarity.

[0012] A second aspect of this application discloses a lane-changing method for a vehicle, comprising: acquiring a lane trajectory for the vehicle to change lanes; and performing a lane change on the lane trajectory; wherein the lane trajectory is obtained by a path planning method for heuristic vehicle lane changing as described in any one of the first aspects.

[0013] A third aspect of this application discloses an electronic device including a memory and a processor coupled to each other, the processor being configured to execute program instructions stored in the memory to implement the path planning method for heuristic vehicle lane changing as described in any one aspect of the first aspect, or to implement the vehicle lane changing method described in the second aspect.

[0014] The fourth aspect of this application discloses a non-volatile computer storage medium storing program instructions thereon, which, when executed by a processor, implement the path planning method for heuristic vehicle lane changing as described in the first aspect, or implement the vehicle lane changing method described in the second aspect.

[0015] The beneficial effects of this application are as follows: Based on the current state information of the vehicle, the desired state information for lane changing is determined; based on the desired state information and the direction of lane changing, a preset area range for lane changing is determined, and a first sampling operation is performed on the preset area range to determine the heuristic trajectory corresponding to the desired state information; based on the heuristic trajectory, a second sampling operation is performed on the sampling result range obtained from the first sampling operation to obtain multiple trajectory curves for lane changing; a pruning operation is performed on the multiple trajectory curves to obtain the planned trajectory for lane changing from the multiple trajectory curves. This achieves the utilization of desired state information, reduces blind sampling, and improves sampling efficiency. Simultaneously, the second sampling operation, based on the sampling results obtained from the first sampling operation, achieves encrypted sampling without causing unnecessary time consumption, resulting in more accurate path planning.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this application. Attached Figure Description

[0017] The present application will be further described below with reference to the accompanying drawings and embodiments. In the drawings:

[0018] Figure 1 This is a flowchart illustrating the heuristic vehicle lane-changing path planning method according to an embodiment of this application.

[0019] Figure 2 This is a schematic diagram of the preset area range of the heuristic vehicle lane-changing path planning method according to an embodiment of this application.

[0020] Figure 3 This is a schematic diagram of a longitudinal filtering scenario for the heuristic vehicle lane-changing path planning method according to an embodiment of this application.

[0021] Figure 4 This is a schematic diagram of an encrypted sampling scenario of the heuristic vehicle lane-changing path planning method according to an embodiment of this application;

[0022] Figure 5 This is a schematic flowchart of a vehicle lane-changing method according to an embodiment of this application;

[0023] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application;

[0024] Figure 7 This is a schematic diagram of the structure of a non-volatile computer-readable storage medium according to an embodiment of this application. Detailed Implementation

[0025] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0026] In this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Additionally, the character " / " generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, "many" in this application means two or more. Moreover, the term "at least one" in this application means any combination of at least two of any one or more of a plurality of objects. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C. Furthermore, the terms "first," "second," and "third" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features.

[0027] To enable those skilled in the art to better understand the technical solution of this application, the technical solution of this application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0028] Please see Figure 1 , Figure 1 This is a flowchart illustrating the heuristic path planning method for lane changing in this application. This method can be applied to electronic devices with computing or other functions, such as in-vehicle equipment. This in-vehicle equipment can be installed on an autonomous vehicle. It should be noted that if substantially the same result is obtained, the method of this application is not necessarily identical. Figure 1 The sequence of processes shown is limited.

[0029] In some possible implementations, this method can be implemented by the processor calling computer-readable instructions stored in memory, such as... Figure 1 As shown, the method may include the following steps:

[0030] S11: Obtain the current status information of the vehicle, and determine the desired status information for the vehicle to change lanes based on the current status information.

[0031] The vehicle's current state information represents the current state of the autonomous vehicle in the Frenet coordinate system. In the Frenet coordinate system, the longitudinal direction 's' represents the direction of the autonomous vehicle's movement along the road, and the lateral direction 'l' represents the direction perpendicular to the road (where left is positive). The current state information can include the autonomous vehicle's speed in the current state, the lateral coordinate 'l' in the Frenet coordinate system, the derivative 'dl' of the lateral coordinate 'l' with respect to the longitudinal coordinate 's', the derivative 'dl' of the derivative 'dl' with respect to the longitudinal coordinate 's', and the angle difference between the autonomous vehicle's orientation and the preset reference line.

[0032] The desired state information represents the expected ending state of a lane change, which may include the desired ending position. Based on the current state information, the desired state information for lane changes can be determined. Specifically, based on the driver's behavior, a mapping relationship is established between the driver's driving state and the corresponding lane change position. The driver's driving state is represented by the following parameters: the driver's position coordinates in Cartesian coordinates, the driver's orientation, and the trajectory curve of the driver's position point. Subsequently, using this mapping relationship, the desired state information for lane changes is determined based on the current state information.

[0033] It should be noted that the number of expected end positions in the expected state information is not limited; multiple expected end positions can be obtained based on the current state information.

[0034] S12: Based on the desired state information and the vehicle lane change direction, determine the preset range for the vehicle lane change, perform the first sampling operation on the preset range, and determine the heuristic trajectory corresponding to the desired state information.

[0035] The direction of a vehicle lane change can include changing lanes to the left and changing lanes to the right. Using the desired state information and the direction of the vehicle lane change, a preset range for the vehicle lane change can be determined. For example, if the desired state information includes a desired ending position at a point on the right lane and the lane change direction is to change lanes to the right, then the preset range is the area between the vehicle's current position to the right and the desired ending position.

[0036] After determining the preset area range, a first sampling operation is performed on this preset area range. This first sampling operation can be based on Frenet coordinate system (SL) sampling. That is, within the preset area range, SL sampling points are scattered to obtain sampling points for different layers in the horizontal and vertical directions, such as... Figure 2 As shown, Figure 2 This is a schematic diagram of the preset area range of the heuristic vehicle lane-changing path planning method in this application embodiment. The vehicle 201 is in the current lane 1 and is about to change lanes to the target lane 2. The sampling points of sl are scattered to obtain sampling points at different layers in the lateral and longitudinal directions.

[0037] Based on the desired state information and the vehicle's lane-changing direction, a heuristic trajectory corresponding to the desired state information is determined. In other words, using the desired ending position and lane-changing direction from the desired state information, a heuristic trajectory is generated. The starting point of this heuristic trajectory is a point on the vehicle itself, such as the position of the center of the vehicle's rear axle. The trajectory connecting the position of the center of the vehicle's rear axle to the desired ending position is the heuristic trajectory.

[0038] S13: Based on the heuristic trajectory, perform a second sampling operation on the range of sampling results obtained from the first sampling operation to obtain multiple trajectory curves for vehicle lane changing.

[0039] The second sampling operation can also be based on Frenet coordinate system SL sampling, i.e., scattering SL sampling points. The second sampling operation is based on the sampling results obtained from the first sampling operation. That is, combined with the heuristic trajectory, SL sampling points are scattered based on the sampling points at different layers in the horizontal and vertical directions obtained from the first sampling operation, thus achieving a second sampling operation on a preset area, i.e., refining the sampling results obtained from the first sampling operation. For example, SL sampling points can be scattered at the intersection of a certain layer of sampling points in the horizontal direction and the heuristic trajectory.

[0040] Based on the sampling points obtained from the first sampling operation in different layers in the horizontal and vertical directions, SL sampling points are then scattered. For example, SL sampling points can be scattered in the sampling point layer that is closer to the vehicle, thus completing the second sampling operation on the sampling result range obtained from the first sampling operation. The sampling point layer that is closer to the vehicle, such as... Figure 2 For example, in lane 1 where the vehicle is currently located, the sampling point layer that is closer to the vehicle can be the first sampling point in the horizontal direction in front of the vehicle 201 or the second sampling point in the horizontal direction.

[0041] After the second sampling operation, multiple trajectory curves for vehicle lane changing can be obtained. For example, the corresponding trajectory curve can be obtained by smoothing the connection of the scattered points between adjacent rows using a polynomial algorithm.

[0042] S14: Perform pruning operations on multiple trajectory curves to obtain a planned trajectory for vehicle lane changing from the multiple trajectory curves.

[0043] The pruning operation is to delete trajectory curves. For example, it can delete trajectory curves that do not meet preset conditions, i.e., delete unreasonable trajectory curves.

[0044] Pruning multiple trajectory curves is equivalent to deleting one or more of them, thereby selecting a trajectory curve from the remaining curves as the planned trajectory.

[0045] In this embodiment, the desired state information for lane changing is determined by the vehicle's current state information. Based on the desired state information and the vehicle's lane changing direction, a preset area range for lane changing is determined. A first sampling operation is performed on the preset area range to determine the heuristic trajectory corresponding to the desired state information. According to the heuristic trajectory, a second sampling operation is performed on the sampling result range obtained from the first sampling operation to obtain multiple trajectory curves for lane changing. A pruning operation is performed on the multiple trajectory curves to obtain the planned trajectory for lane changing from the multiple trajectory curves. This achieves the utilization of desired state information, reduces blind sampling, and improves sampling efficiency. At the same time, the second sampling operation, based on the sampling result obtained from the first sampling operation, achieves encrypted sampling without causing unnecessary time consumption, resulting in more accurate path planning.

[0046] In some embodiments, the sampling result range is obtained by filtering the sampling results obtained from the first sampling operation within a preset area.

[0047] The initial sampling range, i.e., the preset area for vehicle lane changes, can be sampled at different levels both horizontally and vertically within this range to obtain status information from several sampling points. The preset area range includes the sampling result range. Specifically, the sampling result range is obtained by filtering the sampling results from the first sampling operation within the preset area range. This means setting the range of values ​​for the horizontal coordinate *l* and the vertical coordinate *s* in the Frenet coordinate system based on the vehicle's desired lane change endpoint and lane change direction. For example, if the desired endpoint is a point on the right lane and the lane change direction is to the right, then horizontal filtering (setting the range of the horizontal coordinate *l*) can be used, for example, setting the range of the horizontal coordinate *l* between the center lines of the current lane and the target lane; vertical filtering (setting the range of the vertical coordinate *s*) can be used, for example, sampling ten layers vertically along the lane. The vertical range is set based on whether a lane change is possible. This can be understood as follows: if the starting point of the sampling point in the target lane is too close, the vehicle will not appear at that position during the actual lane change. In this case, by combining this with the desired lane change endpoint, a more reasonable judgment is made to set the range of values ​​for the vertical coordinate *s*. Figure 3 As shown, Figure 3 This is a schematic diagram of a longitudinal filtering scenario for the heuristic vehicle lane-changing path planning method according to an embodiment of this application. The value range of the longitudinal coordinate s can be the two layers of sampling points in front of the vehicle 201 when the vehicle is in the current lane 1, and the two layers of sampling points on the target lane 2 near the expected end position.

[0048] In this embodiment, the sampling results obtained from the first sampling operation within the preset area are filtered. Specifically, the range of values ​​for the lateral coordinate l and the longitudinal coordinate s in the Frenet coordinate system are set according to the vehicle's expected lane change endpoint and lane change direction. This limits the range of blindly scattered points and uses lane change trends and approximate destinations to approximate human driver behavior, thereby improving sampling efficiency.

[0049] In some embodiments, the sampling result includes multiple layers of sampling points in the horizontal direction, wherein the multiple layers of sampling points include a first layer of sampling points and a second layer of sampling points; the range of the sampling result includes either the first layer of sampling points or the second layer of sampling points.

[0050] The sampling results include multiple sampling points in the lateral direction, meaning multiple sampling points are taken longitudinally between the vehicle's current lane and the target lane. Each sampling layer can consist of multiple lateral sampling points under the same vertical coordinate. These multiple sampling points include first-layer and second-layer sampling points, meaning the first and second-layer sampling points can be the sampling layers closest to the vehicle. The sampling result range is obtained by filtering the sampling results from the first sampling operation performed on the preset area for vehicle lane changing. Specifically, the range of values ​​for the lateral coordinate *l* and the longitudinal coordinate *s* in the Frenet coordinate system are set according to the vehicle's desired lane change endpoint and direction. This range can include either the first-layer or second-layer sampling point closest to the vehicle.

[0051] In some embodiments, based on a heuristic trajectory, a second sampling operation is performed on the sampling result range obtained by performing the first sampling operation to obtain multiple trajectory curves for vehicle lane changing, including: determining the intersection point of the heuristic trajectory with the first layer sampling point or the second layer sampling point; performing a densification sampling operation in a preset area of ​​the intersection point to obtain the starting point state information for vehicle lane changing; and obtaining multiple trajectory curves based on the starting point state information.

[0052] Specifically, determining the intersection of the heuristic trajectory with the first or second layer sampling point involves performing a first sampling operation on a preset area to obtain the heuristic trajectory corresponding to the desired state information. The intersection of the heuristic trajectory with the first layer sampling point closest to the starting point or the heuristic trajectory with the second layer sampling point closest to the starting point is then determined through calculation. The intersection information may include the intersection location information, the orientation of the corresponding trajectory curve, and the curvature of the trajectory curve.

[0053] Furthermore, in the preset area of ​​the intersection point, an encrypted sampling operation is performed, that is, by performing discrete sampling encryption in the adjacent areas of the intersection point position and the curve orientation, the sampling density in the preset area of ​​the intersection point is increased to obtain the starting point state information for vehicle lane changing. Here, the starting point is a point of the vehicle itself, such as the position of the center of the vehicle's rear axle. The trajectory is obtained by connecting the position of the center of the vehicle's rear axle with the desired ending position. The starting point state information may include position information, the corresponding trajectory curve orientation, and the trajectory curve curvature, etc.

[0054] Furthermore, based on the starting point state information, multiple trajectory curves are obtained. That is, multiple trajectory curves are generated based on the starting point state information and the desired lane change endpoint state information. The orientation of the trajectory curve directly connected to the vehicle's head can be adjusted to ensure its rationality. Figure 4 As shown, Figure 4This is a schematic diagram of the encrypted sampling scenario of the heuristic vehicle lane-changing path planning method in this application embodiment. The intersection of the heuristic trajectory and the first layer of sampling points in front of the vehicle in the current lane 1 where vehicle 201 is located is determined. In the preset area of ​​the intersection, the encrypted sampling operation is performed to increase the sampling density, and then multiple trajectory curves are obtained based on the starting point state information.

[0055] In this embodiment, the intersection of the heuristic trajectory with the first-layer sampling point or the second-layer sampling point is determined. In the preset area of ​​the intersection, a dense sampling operation is performed to obtain the starting state information for vehicle lane changing. Based on the starting state information, multiple trajectory curves are obtained. In this process, since the closer to the vehicle, the less uncertainty there is, that is, the clearer the environmental perception information, the higher the quality requirements of the path layer, such as safety, smoothness, and stability, by dense sampling in the preset area of ​​the intersection, the trend of lane changing can be included, while the uncertainty of the destination can be retained, resulting in a more reasonable and accurate path planning.

[0056] In some embodiments, the pruning operation includes at least one of the following operations: deleting a first trajectory curve from a plurality of trajectory curves, wherein the first trajectory curve represents a trajectory curve in which the ratio of lateral change to longitudinal change is greater than a preset value; deleting a second trajectory curve from a plurality of trajectory curves, wherein the second trajectory curve represents a trajectory curve in which the lateral movement in the direction of vehicle lane change exceeds the sum of the current lateral position in the current state information and a preset value; deleting a third trajectory curve from a plurality of trajectory curves, wherein the third trajectory curve represents a trajectory curve in which the lateral value of a sampling point directly faces the direction and exceeds the lateral sampling range in which the sampling point is located; and deleting a fourth trajectory curve from a plurality of trajectory curves, wherein the fourth trajectory curve represents a trajectory curve in which the lateral values ​​of any two adjacent sampling points fluctuate within a specific range.

[0057] The first trajectory curve represents the trajectory curve in which the ratio of the lateral change to the longitudinal change is greater than a preset value. This means judging the rationality of the mapping relationship between the position and orientation of the trajectory curve, which is to judge the magnitude of the ratio of the lateral change to the longitudinal change compared to the preset value. If the ratio of the lateral change to the longitudinal change of the trajectory curve is greater than the preset value, that is, the curvature requirement cannot be met, then it needs to be deleted.

[0058] The second trajectory curve represents the trajectory curve whose lateral movement in the direction of lane change exceeds the sum of the current lateral position and the preset value in the current state information. That is, it determines whether the range of change of the lateral coordinate l in the Frenet coordinate system of the trajectory curve exceeds the preset range. It can be understood that when a vehicle changes lanes to the right, it is unlikely to move to the left. If the range of lateral movement in the direction of lane change of the trajectory curve exceeds the sum of the current lateral position and the preset value in the current state information, such as a vehicle changing lanes to the right moving to the left or moving beyond the target lane, then it needs to be deleted.

[0059] The third trajectory curve represents the trajectory curve with a direct connection orientation and a horizontal value of the sampling point that exceeds the horizontal sampling range of the sampling point. That is, by judging whether the trajectory curve has a direct connection orientation and whether the horizontal value of the sampling point is within the horizontal sampling range of the sampling point, the rationality of the trajectory is determined. If the horizontal coordinate value of the corresponding sampling point of the trajectory curve of the direct connection origin exceeds the horizontal sampling range of the sampling layer, it needs to be deleted.

[0060] The fourth trajectory curve represents the trajectory curve in which the lateral values ​​of any two adjacent sampling points fluctuate within a specific range. That is, by judging the fluctuation of the lateral values ​​of any two adjacent sampling points within a specific range, the rationality of the trajectory is further judged. In other words, there is no left-right swaying when a human is driving a vehicle. If there is a trajectory curve in which the lateral values ​​of any two adjacent sampling points fluctuate within a specific range, that is, the vehicle is swaying left and right, then it needs to be deleted.

[0061] In this embodiment, pruning operations are performed on multiple trajectory curves, i.e., deleting planned trajectories that do not meet preset conditions. These operations include deleting trajectory curves where the ratio of lateral change to longitudinal change is greater than a preset value; deleting trajectory curves where the lateral movement in the direction of vehicle lane change exceeds the sum of the current lateral position and the preset value in the current state information; deleting trajectory curves where the lateral value of the sampling point is directly connected to the direction of the vehicle and exceeds the lateral sampling range of the sampling point; and deleting trajectory curves where the lateral values ​​of any two adjacent sampling points fluctuate within a specific range. This approach aims to improve sampling efficiency by avoiding unnecessary time consumption during localized encrypted sampling.

[0062] In some embodiments, performing a pruning operation on multiple trajectory curves includes: deleting a preset number of trajectory curves from the multiple trajectory curves, wherein the ratio of the preset number of trajectory curves to the multiple trajectory curves satisfies a preset value.

[0063] A preset number of invalid trajectory curves are deleted from multiple trajectory curves using pruning operations. The ratio of the preset number of trajectory curves to the multiple trajectory curves satisfies a preset value. The preset value can be understood as the ratio of invalid curves deleted through preset check operations to all sampled curves. By comparing the ratio of invalid curves deleted under pruning operations to all sampled curves with the ratio of invalid curves deleted under preset check operations, it is determined whether the pruning operation to delete invalid curves is reasonable.

[0064] In some embodiments, obtaining a planned trajectory for vehicle lane changing from multiple trajectory curves includes: obtaining a planned trajectory for vehicle lane changing from multiple trajectory curves according to a preset method, wherein the preset method indicates that the planned trajectory meets preset conditions.

[0065] Based on the heuristic trajectory, a sampling operation is performed on a preset area to obtain multiple trajectory curves for vehicle lane changing. Then, a pruning operation is performed on the multiple trajectory curves to obtain a planned trajectory for vehicle lane changing from the multiple trajectory curves according to a preset method. The preset method means that the planned trajectory meets preset conditions, that is, a reasonable planned trajectory that conforms to dynamic constraints.

[0066] In some embodiments, the preset conditions include at least one of the following: the lateral value of the endpoint on the planned trajectory is less than a first predetermined value and the derivative of the lateral value of the endpoint with respect to the longitudinal value is less than a second predetermined value; and the similarity between the planned trajectory and the preset trajectory in different time periods meets the preset similarity.

[0067] Efficiency cost is defined based on lane change length. For a lane change sampling trajectory, the longitudinal coordinate value s from the vehicle's current position to the lane change end position is the lane change length. The lateral value of the endpoint on the planned trajectory is less than a first predetermined value, and the derivative of the lateral value of the endpoint with respect to the longitudinal value is less than a second predetermined value. That is, the lane change end position is such that the lateral coordinate l and the derivative dl of the lateral coordinate l with respect to the longitudinal coordinate s on the sampling trajectory are both less than preset values, such as l less than 0.5 and dl less than 0.02.

[0068] The similarity between the planned trajectory and the preset trajectory in different time periods meets the preset similarity. For example, the results of sampling space or heuristic trajectory can be compared with human trajectories according to the Euclidean distance. At the same time, the results of different time periods can be evaluated separately. For example, the trajectories corresponding to sampling times of 1 to 5 seconds can be evaluated separately. It can be understood that the closer to the vehicle's position, the more accurate the planning result will be, and it is also desirable to be as close as possible to human trajectories.

[0069] Please see Figure 5 , Figure 5 This is a flowchart illustrating a lane-changing method for a vehicle according to an embodiment of this application. This method can be applied to electronic devices with functions such as computing. The electronic device can be an in-vehicle device. In some possible implementations, this method can be implemented by a processor calling computer-readable instructions stored in memory, specifically including the following steps:

[0070] S51: Obtain the lane trajectory used for vehicle lane changes.

[0071] The lane trajectory is obtained through the heuristic vehicle lane change path planning method described above. Specifically, a preset area range for vehicle lane change is determined by using the vehicle's desired state information and lane change direction. A first sampling operation is performed on the preset area range to obtain the heuristic trajectory corresponding to the desired state information. Based on the heuristic trajectory, a second sampling operation is performed on the sampling result range obtained from the first sampling operation to obtain multiple trajectory curves for vehicle lane change. A pruning operation is performed on the multiple trajectory curves to obtain the planned trajectory for vehicle lane change from the multiple trajectory curves.

[0072] S52: Perform a lane change within the lane trajectory.

[0073] Based on the planned trajectory for vehicle lane changing that meets the preset conditions, the vehicle completes the lane change from the current lane to the target lane.

[0074] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0075] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. The electronic device 600 includes a memory 601 and a processor 602 coupled to each other. The processor 602 is used to execute program instructions stored in the memory 601 to implement the steps of the above-described heuristic vehicle lane-changing path planning method embodiment, or to implement the steps of the above-described vehicle lane-changing method embodiment. In a specific implementation scenario, the electronic device 600 may include, but is not limited to, a microcomputer or a server.

[0076] Specifically, processor 602 controls itself and memory 601 to implement the steps of the above-described heuristic vehicle lane-changing path planning method embodiment, or to implement the steps of the above-described vehicle lane-changing method embodiment. Processor 602 can also be called a CPU (Central Processing Unit), and may be an integrated circuit chip with signal processing capabilities. Processor 602 can also be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor. Furthermore, processor 602 can be implemented using integrated circuit chips.

[0077] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of a non-volatile computer-readable storage medium according to an embodiment of this application. The non-volatile computer-readable storage medium 700 is used to store a computer program 701. When executed by the processor 602, the computer program 701 is used to implement the steps of the above-described heuristic vehicle lane-changing path planning method embodiment, or to implement the steps of the above-described vehicle lane-changing method embodiment.

[0078] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0079] In the several embodiments provided in this application, it should be understood that the disclosed methods and related devices can be implemented in other ways. For example, the related device implementations described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication disconnection shown or discussed may be indirect coupling or communication disconnection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0080] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0081] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0082] Those skilled in the art will readily recognize that numerous modifications and variations can be made to the apparatus and method while maintaining the teachings of this application. Therefore, the above disclosure should be considered limited only by the scope of the appended claims.

Claims

1. A heuristic path planning method for vehicle lane changing, characterized in that, include: Obtain the current status information of the vehicle, and determine the desired status information for the vehicle to change lanes based on the current status information; Based on the desired state information and the vehicle lane change direction, a preset area range for vehicle lane change is determined, and a first sampling operation is performed on the preset area range to determine the heuristic trajectory corresponding to the desired state information. The heuristic trajectory is the trajectory connecting the vehicle's current position and the desired end position. Based on the heuristic trajectory, a second sampling operation is performed on the sampling result range obtained by performing the first sampling operation to obtain multiple trajectory curves for vehicle lane changing; A pruning operation is performed on the plurality of trajectory curves to obtain a planned trajectory for vehicle lane changing from the plurality of trajectory curves; The sampling results include multiple sampling points in the horizontal direction, wherein the multiple sampling points include a first layer of sampling points and a second layer of sampling points close to the current position of the vehicle; The sampling result range includes either the first layer sampling points or the second layer sampling points; Based on the heuristic trajectory, a second sampling operation is performed on the sampling result range obtained from the first sampling operation to obtain multiple trajectory curves for vehicle lane changing, including: Determine the intersection point of the heuristic trajectory with either the first layer sampling point or the second layer sampling point; In a preset area at the intersection, an encrypted sampling operation is performed to obtain the starting point state information for vehicle lane changing; Based on the starting point state information, the multiple trajectory curves are obtained.

2. The method according to claim 1, characterized in that, The sampling result range is obtained by filtering the sampling results obtained from the first sampling operation performed on the preset area range.

3. The method according to claim 1, characterized in that, The pruning operation includes at least one of the following operations: The operation of deleting the first trajectory curve among the plurality of trajectory curves, wherein the first trajectory curve represents a trajectory curve in which the ratio of the lateral change to the longitudinal change is greater than a preset value, and the ratio of the lateral change to the longitudinal change is used to represent the curvature of the trajectory curve; The operation of deleting the second trajectory curve from the plurality of trajectory curves, wherein the second trajectory curve represents a trajectory curve whose lateral movement in the direction of the vehicle lane change exceeds the sum of the current lateral position and a preset value in the current state information; The operation of deleting the third trajectory curve from the plurality of trajectory curves, wherein the third trajectory curve represents a trajectory curve with a directly connected orientation and a lateral value of the sampling point exceeding the lateral sampling range of the sampling point; and The operation of deleting the fourth trajectory curve among the plurality of trajectory curves, wherein the fourth trajectory curve represents the trajectory curve in which the lateral value of any two adjacent sampling points fluctuates within a specific range, and the specific range is used to determine whether the vehicle is swaying left and right during its movement.

4. The method according to claim 1, characterized in that, The pruning operation on the plurality of trajectory curves includes: A predetermined number of trajectory curves are deleted from the plurality of trajectory curves, wherein the ratio of the predetermined number of trajectory curves to the plurality of trajectory curves satisfies a predetermined value.

5. The method according to any one of claims 1-4, characterized in that, The planned trajectory for vehicle lane changing is obtained from the plurality of trajectory curves, including: According to a preset method, a planned trajectory for vehicle lane changing is obtained from the plurality of trajectory curves, wherein the preset method indicates that the planned trajectory meets preset conditions.

6. The method according to claim 5, characterized in that, The preset conditions include at least one of the following: The lateral value of the endpoint on the planned trajectory is less than a first predetermined value, and the derivative of the lateral value of the endpoint with respect to the longitudinal value is less than a second predetermined value; and The similarity between the planned trajectory and the preset trajectory in different time periods meets the preset similarity.

7. A method for changing lanes for a vehicle, characterized in that, include: Obtain the lane trajectory used for vehicle lane changes; Perform a lane change on the lane trajectory; The lane trajectory is obtained through the path planning method for heuristic vehicle lane changing as described in any one of claims 1-6.

8. An electronic device, characterized in that, It includes a memory and a processor coupled to each other, the processor being configured to execute program instructions stored in the memory to implement the path planning method for heuristic vehicle lane changing as described in any one of claims 1 to 6, or to implement the vehicle lane changing method as described in claim 7.

9. A non-volatile computer storage medium storing program instructions thereon, characterized in that, When the program instructions are executed by the processor, they implement the path planning method for heuristic vehicle lane changing as described in any one of claims 1 to 6, or the vehicle lane changing method as described in claim 7.

Images