Track planning method and device, electronic equipment, vehicle, storage medium and product

Abstract

The invention relates to a trajectory planning method and device, electronic equipment, a vehicle, a storage medium and a program product, and the method comprises the steps: carrying out the trajectory planning based on the position information of trajectory points of a plurality of trajectories, and determining a target cost function corresponding to a planned candidate trajectory; the target cost function is constructed based on at least one of trajectory point spacing information, trajectory point fusion feature information and trajectory curvature information of the candidate trajectory; and optimizing the candidate trajectory according to the target cost function, and determining a target trajectory. According to the invention, the stability of the planned trajectory can be improved, and the vehicle use experience of a user is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a trajectory planning method, device, electronic equipment, vehicle, storage medium and product. Background Art

[0002] With the development of autonomous driving related technologies, automatic assisted navigation driving (Navigate on Autopilot, noa) is one of the basic functions of vehicles.

[0003] However, faced with massive and non-standardized complex driving scenarios, the planned trajectory frequently jumps due to reasons such as switching of decision-making scenarios and random changes in the status of traffic participants. The output trajectory is very unstable, affecting the user's car experience. Summary of the invention

[0004] The embodiments of the present application provide a trajectory planning method, device, electronic device, vehicle, storage medium and program product, which aim to improve the stability of the planned trajectory, thereby improving the user's vehicle experience, so as to at least partially solve the above-mentioned technical problems.

[0005] In order to achieve the above object, according to a first aspect of the present application, a trajectory planning method is provided, comprising:

[0006] Performing trajectory planning based on the position information of the trajectory points of the plurality of trajectories, and determining a target cost function corresponding to the planned candidate trajectory; the target cost function is constructed based on at least one of the trajectory point spacing information, the trajectory point fusion feature information, and the trajectory curvature information of the candidate trajectory;

[0007] The candidate trajectories are optimized according to the target cost function to determine the target trajectory.

[0008] Optionally, the multiple trajectories include a first trajectory and a second trajectory, and the trajectory planning is performed based on the position information of the trajectory points of the multiple trajectories to determine the target cost function corresponding to the planned candidate trajectory; including:

[0009] Determine, based on the position information, overlapping trajectory points and non-overlapping trajectory points in the first trajectory and the second trajectory;

[0010] Trajectory planning is performed based on the position information of non-overlapping trajectory points in the first trajectory and the second trajectory to obtain a planned candidate trajectory, and a target cost function corresponding to the planned candidate trajectory is determined.

[0011] Optionally, the performing trajectory planning based on the position information of non-overlapping trajectory points in the first trajectory and the second trajectory to obtain the planned candidate trajectory includes:

[0012] Performing trajectory point fusion based on position information of non-overlapping trajectory points in the first trajectory and the second trajectory to obtain fused trajectory points;

[0013] The planned candidate trajectory is determined based on the fused trajectory points and the coincident trajectory points, and a target cost function corresponding to the planned candidate trajectory is determined.

[0014] Optionally, the performing trajectory point fusion based on position information of non-overlapping trajectory points in the first trajectory and the second trajectory to obtain fused trajectory points includes:

[0015] Determine trajectory points to be fused among non-overlapping trajectory points of the first trajectory and the second trajectory;

[0016] Plan the trajectory points to be fused and the corresponding fused trajectory points.

[0017] Optionally, the step of determining the track point spacing information of the candidate track comprises:

[0018] The distances between adjacent trajectory points on the candidate trajectory are calculated to obtain trajectory point distance information of the candidate trajectory.

[0019] Optionally, the step of determining the trajectory point fusion feature information of the candidate trajectory includes:

[0020] Based on the fused trajectory point and the distance between the fused trajectory point and the non-overlapping trajectory point corresponding to the fused trajectory point, the trajectory point fusion feature information of the candidate trajectory is determined.

[0021] Optionally, the step of determining the trajectory curvature information includes:

[0022] For three adjacent trajectory points on the candidate trajectory, calculating the slopes of adjacent trajectory points among the three adjacent trajectory points;

[0023] Based on the slope, trajectory curvature information corresponding to the three adjacent trajectory points is determined.

[0024] Optionally, determining, based on the position information, overlapping trajectory points and non-overlapping trajectory points in the first trajectory and the second trajectory includes:

[0025] sorting the first trajectory and the second trajectory based on the position information;

[0026] Based on the sorting result, coincident trajectory points and non-coincident trajectory points in the first trajectory and the second trajectory are determined.

[0027] Optionally, the position information includes a horizontal position and a vertical position of the track point, and the sorting of the first track and the second track based on the position information includes:

[0028] sorting the track points in the first track and the second track according to the lateral position; or,

[0029] The track points in the first track and the second track are sorted according to the longitudinal position.

[0030] Optionally, the target cost function is constructed based on a target vector, and the target vector is composed of at least one of the trajectory point spacing information, trajectory point fusion feature information and trajectory curvature information.

[0031] Optionally, optimizing the target trajectory according to the target cost function to determine the target trajectory includes:

[0032] Determining a target hard constraint according to a reference trajectory among the multiple trajectories, wherein the reference trajectory is a previous trajectory among the multiple trajectories;

[0033] The candidate trajectories are optimized according to the target hard constraints and the target cost function to determine the target trajectory.

[0034] Optionally, determining the target hard constraint according to the reference trajectory among the multiple trajectories includes:

[0035] The target hard constraint is determined based on the distance between the trajectory point on the planned candidate trajectory and the reference trajectory.

[0036] Optionally, the target hard constraint includes that the distance between the trajectory point on the planned candidate trajectory and the reference trajectory is less than a preset distance threshold,

[0037] The step of optimizing the candidate trajectory according to the target hard constraint and the target cost function to determine the target trajectory includes:

[0038] Minimizing the value of the target cost function as the optimization target to optimize the candidate trajectory to obtain the target trajectory point;

[0039] If the distance between the target trajectory point and the reference trajectory is less than a preset distance threshold, a target trajectory is generated according to the target trajectory point.

[0040] According to a second aspect of the present application, a trajectory planning device is provided, comprising:

[0041] A function determination module, configured to perform trajectory planning based on the position information of the trajectory points of the plurality of trajectories, and determine a target cost function corresponding to the planned candidate trajectory; the target cost function is constructed based on at least one of the trajectory point spacing information, the trajectory point fusion feature information, and the trajectory curvature information of the candidate trajectory;

[0042] The trajectory optimization module is used to optimize the candidate trajectories according to the target cost function to determine the target trajectory.

[0043] In a third aspect, this embodiment further provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0044] In a fourth aspect, this embodiment further provides a vehicle, which includes the above-mentioned electronic device.

[0045] In a fifth aspect, this embodiment further provides a computer-readable storage medium, which includes a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of the above method.

[0046] In the sixth aspect, this embodiment also provides a computer program product, including a computer program, which is stored in a computer-readable storage medium; when the processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device performs the steps of the above method.

[0047] To sum up, in the embodiment of the present application, through the above-mentioned technical scheme, the present application can plan candidate trajectories based on multiple trajectories, and then construct a target cost function based on at least one of the trajectory point spacing information, trajectory point fusion feature information and trajectory curvature information of the candidate trajectory, so that the target cost function can effectively characterize the smoothness characteristics of the candidate trajectory. In this way, a smooth target trajectory can be obtained by optimizing the candidate trajectory using the target cost function, avoiding the trajectory jump problem that occurs when multiple trajectories are spliced, so that the vehicle can change lanes smoothly according to the target trajectory, effectively improving the car experience.

[0048] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without creative work.

[0050] In order to more completely understand the present application and its beneficial effects, the following description will be given in conjunction with the accompanying drawings, wherein the same figure numbers represent the same parts in the following description.

[0051] Figure 1It is a schematic diagram of a vehicle lane changing scenario provided by this application;

[0052] Figure 2 It is the first schematic diagram of trajectory planning provided by this application;

[0053] Figure 3 is a second schematic diagram of trajectory planning provided in an embodiment of the present application;

[0054] Figure 4 is a third schematic diagram of a trajectory planning process provided in an exemplary embodiment of the present application;

[0055] Figure 5 is a schematic diagram of trajectory point fusion provided in an exemplary embodiment of the present application;

[0056] Figure 6 is a schematic diagram of trajectory planning effect provided in an exemplary embodiment of the present application;

[0057] Figure 7 is a schematic diagram of trajectory planning effect provided in an exemplary embodiment of the present application;

[0058] Figure 8 It is a schematic diagram of the architecture of an electronic device provided in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0060] Combined with the above background technology description of this application, with the development of autonomous driving related technologies, NOA is one of the basic functions of vehicles.

[0061] The overall solution for autonomous driving will classify scenarios into various types, including but not limited to cruising, emergency avoidance, active lane change, etc. For example, Figure 1 The cruising and emergency avoidance scenarios shown, such as Figure 2 As shown in the figure, when the vehicle is driving in the lane and encounters an obstacle to avoid, the trajectory will jump. In order to solve the problem of trajectory jumping, the traditional solution is to splice two segments of trajectory and smooth the combined trajectory after splicing.

[0062] However, if Figure 3 As shown, the most important problem is to select the position of the two end tracks for splicing, and smoothing will change the original position of the track.

[0063] In general, the most common solution at present is to smooth the path of the current scene and the path of the scene to be switched after splicing, but the existing solutions have at least the following defects:

[0064] (1) Smoothing will change the physical trajectory, which may cause collisions;

[0065] (2) Stitching first and then smoothing will waste a lot of computer computing power;

[0066] (3) The stitching position needs to be specified manually, which may not be suitable for all scenarios.

[0067] In order to solve the above problems, the present application provides a trajectory planning method, device, electronic device, computer-readable storage medium, computer program product and vehicle to achieve trajectory smoothing, ensure the stability of the output trajectory, avoid steering wheel angle jumping, and improve the car experience.

[0068] Specifically, the trajectory planning method in the embodiment of the present application is as follows: Figure 4 As shown, the following steps may be included:

[0069] S10, performing trajectory planning based on the position information of the trajectory points of the plurality of trajectories, and determining a target cost function corresponding to the planned candidate trajectory; the target cost function is constructed based on at least one of the trajectory point spacing information, the trajectory point fusion feature information, and the trajectory curvature information of the candidate trajectory;

[0070] It should be noted that, in this embodiment, Figure 2 As shown in the figure, the vehicle can change lanes in an emergency to avoid obstacles during driving, or it can actively change lanes and perform trajectory prediction during the lane change process, for example, Figure 3 As shown, the vehicle can determine the trajectory of the current scene (ie, the first trajectory) and the trajectory of the scene to be switched (ie, the second trajectory), wherein each trajectory can include multiple trajectory points.

[0071] On this basis, the vehicle can perform trajectory planning based on the position information of the trajectory points of multiple trajectories and determine the target cost function corresponding to the candidate trajectory.

[0072] It can be understood that, in this embodiment, the candidate trajectories can be multiple trajectories after the fusion of multiple trajectories, and then the vehicle can determine the target cost function corresponding to the candidate trajectories, so as to determine the target trajectory from the subsequent candidate trajectories using the target cost function.

[0073] The target cost function in this embodiment is constructed based on at least one of the trajectory point spacing information, trajectory point fusion feature information and trajectory curvature information of the candidate trajectory.

[0074] Among them, the trajectory point spacing information of the candidate trajectory can be understood as the distance information between two adjacent trajectory points in the candidate trajectory, the trajectory point fusion feature information can be understood as the movement information of the trajectory point in the candidate trajectory relative to the corresponding trajectory point in multiple trajectories, and the trajectory curvature information can be understood as the curvature of the candidate trajectory.

[0075] Thus, in this embodiment, the vehicle may construct a target cost function corresponding to the candidate trajectory using at least one of the trajectory point spacing information, the trajectory point fusion feature information, and the trajectory curvature information of the candidate trajectory.

[0076] S20, optimizing the candidate trajectories according to the target cost function to determine a target trajectory.

[0077] In this embodiment, after constructing the target cost function corresponding to the candidate trajectory, the vehicle can optimize the candidate trajectory by minimizing the value of the target cost function to determine the target trajectory.

[0078] It is worth noting that in this embodiment, combined with the above description, the track point spacing information between two adjacent track points in the candidate track should be as small as possible (meaning that the smaller the distance between adjacent track points, the smoother the change in the curvature of the track, thereby reducing sharp turns or mutations), the moving distance of the fused track points in the candidate track should be as small as possible (meaning the possibility of track point jump is lower), and the curvature in the candidate track should be as small as possible (meaning the higher the track smoothness). Through the above-mentioned multiple cost items, the smooth characteristics of the solved target track are guaranteed, and the smooth splicing of multiple tracks is achieved, so that the steering wheel angle will not jump when the vehicle changes lanes according to the output target track, ensuring the stability of the vehicle body. In this way, in this embodiment, the value of the objective function can be minimized as the optimization goal, and the candidate track is optimized to ensure the smoothness of the solved track.

[0079] For example, in this embodiment, a target cost function can be constructed by means of quadratic optimization. The target cost function can include trajectory point spacing information, trajectory point fusion feature information, and trajectory curvature information. It can be understood that the target cost function in this embodiment can be the target function in a quadratic programming problem, which has a wide range of applications in many fields. By solving the quadratic programming problem, the value of the vector that minimizes (or maximizes) this quadratic function can be found while satisfying a set of linear constraints.

[0080] Therefore, in an embodiment of the present application, the vehicle can perform trajectory planning based on the position information of the trajectory points of multiple trajectories, determine the target cost function corresponding to the candidate trajectory, and the target cost function is constructed based on at least one of the trajectory point spacing information, trajectory point fusion feature information, and trajectory curvature information of the candidate trajectory, and then the vehicle can optimize the candidate trajectory with the minimum target cost function to determine the target trajectory. In this way, compared with the prior art method of splicing two trajectories and then smoothing them, the present application can plan candidate trajectories based on multiple trajectories, and then construct a target function based on at least one of the trajectory point spacing information, trajectory point fusion feature information, and trajectory curvature information of the candidate trajectory, so that the target cost function represents the smoothness characteristics of the candidate trajectory. In this way, the target cost function is used to optimize the candidate purchase machine to obtain a smooth target trajectory, avoiding the trajectory jump problem that occurs when multiple trajectories are spliced, so that the vehicle can change lanes smoothly according to the target trajectory, effectively improving the vehicle experience.

[0081] In one embodiment, the plurality of trajectories include a first trajectory and a second trajectory. In the above S10, “performing trajectory planning based on the position information of the trajectory points of the plurality of trajectories, and determining the target cost function corresponding to the planned candidate trajectory” may include:

[0082] S101, determining overlapping trajectory points and non-overlapping trajectory points in the first trajectory and the second trajectory based on the position information;

[0083] S102, performing trajectory planning based on the position information of non-overlapping trajectory points in the first trajectory and the second trajectory, obtaining a planned candidate trajectory, and determining a target cost function corresponding to the planned candidate trajectory.

[0084] It should be noted that, in this embodiment, the multiple trajectories may include a first trajectory and a second trajectory, wherein each trajectory may include multiple trajectory points, such as Figure 5 shown.

[0085] On this basis, in this embodiment, after determining multiple trajectories and the position information of the trajectory points in the multiple trajectories, the vehicle can determine that there are multiple overlapping trajectory points between the trajectory points in the first trajectory and the second trajectory (ie, Figure 5 The trajectory points are framed by the dashed box in the figure), as well as non-coincident trajectory points.

[0086] It is understandable that the main reasons for the overlap between two trajectories when the vehicle is planning a trajectory are as follows: (1) Failure to consider the vehicle's lane changing behavior. In a multi-lane scenario, if the trajectory planning model does not consider the vehicle's lane changing behavior, it may cause the trajectories to cross or overlap; (2) The limitations of the trajectory planning algorithm. The trajectory planning algorithm may not be able to effectively handle the interaction between vehicles in complex scenarios; (3) The uncertainty of model prediction. The trajectory prediction model may not be able to accurately capture the dynamic behavior of the vehicle, especially in terms of lane change intention recognition and trajectory prediction; (4) Insufficient environmental perception. If the vehicle's sensors or perception system cannot accurately identify the status and intention of the surrounding vehicles, the planned trajectory may overlap with the trajectories of other vehicles.

[0087] In this embodiment, after determining the overlapping trajectory points and the non-overlapping trajectory points between the first trajectory and the second trajectory, the vehicle can perform trajectory planning based on the position information of the non-overlapping trajectory points in the first trajectory and the second trajectory to obtain the planned candidate trajectory, and determine the target cost function corresponding to the planned candidate trajectory.

[0088] In a specific embodiment, in the above S102, “performing trajectory planning based on the position information of non-overlapping trajectory points in the first trajectory and the second trajectory to obtain the planned candidate trajectory, and determining the target cost function corresponding to the planned candidate trajectory” may include:

[0089] S1021, performing trajectory point fusion based on position information of non-overlapping trajectory points in the first trajectory and the second trajectory to obtain fused trajectory points;

[0090] S1022, determining a planned candidate trajectory based on the fused trajectory points and the coincident trajectory points, and determining a target cost function corresponding to the planned candidate trajectory.

[0091] In this embodiment, there is no need to process the overlapping trajectory points in the first trajectory and the second trajectory. However, for the non-overlapping trajectory points, in order to ensure that the vehicle can smoothly transition from the first trajectory to the second trajectory without the problem of trajectory jump, it is necessary to fuse the position information of the non-overlapping trajectory points to obtain the fused trajectory points.

[0092] In this way, the vehicle can determine the planned candidate trajectory based on the fused trajectory points and the overlapping trajectory points, as well as the target cost function corresponding to the planned candidate trajectory. That is, the candidate trajectory includes the fused trajectory points and the overlapping trajectory points, which together constitute the candidate trajectory. For example, the fused trajectory points and the overlapping trajectory points can be sorted according to the lateral position to generate a candidate trajectory.

[0093] In a specific embodiment, in the above S1021, “fusing trajectory points based on position information of non-overlapping trajectory points in the first trajectory and the second trajectory to obtain fused trajectory points” may include:

[0094] Step a, determining the trajectory points to be fused among the non-overlapping trajectory points of the first trajectory and the second trajectory;

[0095] Step b: planning the trajectory points to be fused and the corresponding fused trajectory points.

[0096] In this embodiment, the vehicle may determine the trajectory points to be merged among the non-overlapping trajectory points of the first trajectory and the second trajectory according to the position information of the non-overlapping trajectory points.

[0097] Specifically, for example, Figure 5 As shown, the track points framed by the dotted lines are overlapping track points, and the track points not framed by the dotted lines are non-overlapping track points, wherein there are paired track points or multiple track points to be fused between the first track and the second track, for example, Figure 5 The first trajectory point a1 on the first trajectory and the second trajectory point b2 on the second trajectory.

[0098] In this embodiment, the method for determining the trajectory points to be fused may specifically include:

[0099] (1) Determine the non-overlapping trajectory points on the second trajectory, and for each non-overlapping trajectory point bi, determine the first trajectory point ai on the first trajectory that is closest to bi;

[0100] (2) Taking the first trajectory point ai as a reference, a target area is constructed so that the non-overlapping trajectory points bi can move in the target area to obtain the fused trajectory points. By moving the non-overlapping trajectory points bi multiple times until the target cost function is minimized, the target trajectory consisting of the fused trajectory points and the overlapping trajectory points is obtained.

[0101] The target area can be understood as a position constraint on the fused trajectory points to ensure that there is no jump problem in the fused trajectory. The target area can be a rectangular area or other types of areas, and there is no specific limitation on this.

[0102] Through the above method, in the embodiment of the present application, two trajectories can be fused to obtain multiple candidate trajectories.

[0103] On this basis, the value of the corresponding target cost function can be calculated by combining the trajectory point spacing information, trajectory point fusion feature information and trajectory curvature information of the candidate trajectory. In this way, the value of the corresponding target cost function can be obtained by moving the non-overlapping trajectory points bi multiple times in the above-mentioned area until the minimum value of the target cost function in the area is obtained. At this time, the candidate trajectory corresponding to the minimum target cost function is the target trajectory, so that the smoothness characteristics of the output target trajectory are optimal, without the need for splicing and smoothing, and the smoothness of the lane change trajectory is guaranteed.

[0104] In one embodiment, the step of determining the trajectory point spacing information of the candidate trajectory may include:

[0105] The distances between adjacent trajectory points on the candidate trajectory are calculated to obtain trajectory point distance information of the candidate trajectory.

[0106] In this embodiment, the vehicle may calculate the distance between adjacent track points on the candidate track to obtain track point distance information of the candidate track.

[0107] Specifically, for example, the vehicle can calculate the Euclidean distance x1=sqrt(dx 2 +dy 2 ), where dx is the longitudinal distance and dy is the lateral distance, and then the sum of all the calculated Euclidean distances is used as the trajectory point spacing information.

[0108] In one embodiment, the step of determining the trajectory point fusion feature information of the candidate trajectory includes:

[0109] Based on the fused trajectory point and the distance between the fused trajectory point and the non-overlapping trajectory point corresponding to the fused trajectory point, the trajectory point fusion feature information of the candidate trajectory is determined.

[0110] It should be noted that, in this embodiment, combined with the above description, the trajectory points to be fused in this embodiment can be determined by determining the non-overlapping trajectory points on the second trajectory, and for each non-overlapping trajectory point bi, determining the first trajectory point ai on the first trajectory that is closest to bi; using the first trajectory point ai as a reference, constructing a target area so that the non-overlapping trajectory point bi can move in the target area to obtain the fused trajectory points, and by moving the non-overlapping trajectory points multiple times until the target cost function is minimized.

[0111] On this basis, for each fused trajectory point (x new ,y new ), we can calculate its corresponding non-coincident trajectory point (x raw ,y raw ) between x2=sqrt((x new -xraw ) 2 +(y new -y raw ) 2 ), which can represent the moving distance of the fused trajectory point (i.e., the new trajectory point) compared to the corresponding non-overlapping trajectory point (i.e., the old trajectory point).

[0112] Furthermore, multiple distances can be combined to obtain the trajectory point fusion feature information of the candidate trajectory.

[0113] In one embodiment, the step of determining the trajectory curvature information includes:

[0114] For three adjacent trajectory points on the candidate trajectory, calculating the slopes of adjacent trajectory points among the three adjacent trajectory points;

[0115] Based on the slope, trajectory curvature information corresponding to the three adjacent trajectory points is determined.

[0116] In this embodiment, in combination with the above description, the trajectory points in the candidate trajectory may include fused trajectory points and overlapping trajectory points, and then, the slopes of adjacent trajectory points among the three adjacent trajectory points may be calculated, and based on multiple slopes, the trajectory curvature information corresponding to the three adjacent trajectory points may be determined.

[0117] Specifically, for example, the trajectory curvature information corresponding to three adjacent trajectory points is x3=(m2-m1) / [(1+m1 2 ) 3 / 2 +(1+m2 2 ) 3 / 2 ], where m1 and m2 are the slopes of two adjacent points among the three points. In this way, the curvature calculated based on the three adjacent points on the candidate trajectory is the trajectory curvature information of the candidate trajectory.

[0118] It is worth noting that in this embodiment, the trajectory point spacing information between two adjacent trajectory points in the candidate trajectory should be as small as possible, the moving distance of the trajectory points after fusion in the candidate trajectory should be as small as possible, and the curvature in the candidate trajectory should be as small as possible. Through this constraint, the smoothness of the solved target trajectory is guaranteed, and the smooth splicing of multiple trajectories is achieved, so that the steering wheel angle will not jump when the vehicle changes lanes according to the output target trajectory, thereby ensuring the stability of the vehicle body.

[0119] In one embodiment, in the above S101, “determining, based on the position information, overlapping trajectory points and non-overlapping trajectory points in the first trajectory and the second trajectory” may include:

[0120] S1011, sorting the first trajectory and the second trajectory based on the position information;

[0121] S1012: Determine overlapping trajectory points and non-overlapping trajectory points in the first trajectory and the second trajectory based on the sorting result.

[0122] In this embodiment, when the multiple trajectories include the first trajectory and the second trajectory, the position information of each trajectory point in the first trajectory and the second trajectory is extracted, and the multiple trajectory points are sorted according to the position information to obtain a sorting result.

[0123] Specifically, for example, the distance between the trajectory point and the lane to be changed can be calculated based on the position information, and the multiple trajectory points can be sorted from far to near in terms of distance to obtain a sorting result.

[0124] Furthermore, the vehicle may determine overlapping trajectory points and non-overlapping trajectory points in the first trajectory and the second trajectory based on the sorting result.

[0125] It is understandable that after arranging the plurality of trajectory points in sequence according to the position information, it is possible to directly determine that the trajectory points at the same position between the first trajectory and the second trajectory are the coincident trajectory points (for example Figure 5 The track points framed by the dotted line are track points in both the first track and the second track), and the other track points are non-coincident track points.

[0126] In a specific embodiment, the position information includes the horizontal position and the vertical position of the track point. In the above S1011, “sorting the first track and the second track based on the position information” may include:

[0127] sorting the track points in the first track and the second track according to the lateral position; or,

[0128] The track points in the first track and the second track are sorted according to the longitudinal position.

[0129] In this embodiment, when the track points in the first track and the second track are sorted, the track points can be sorted according to the horizontal position of the track points, or according to the vertical position of the track points. The vertical direction in this embodiment can be understood as the direction in which the vehicle is traveling along the road, and the horizontal direction can be understood as the direction in which the vehicle is perpendicular to the road.

[0130] In this way, in the embodiment of the present application, by sorting the trajectory points, overlapping trajectory points and non-overlapping trajectory points between two tracks can be determined, so as to further merge the non-overlapping trajectory points, so that the generated target trajectory is smoother.

[0131] In one embodiment, the target cost function is constructed based on a target vector, and the target vector is composed of at least one of the trajectory point spacing information, the trajectory point fusion feature information, and the trajectory curvature information.

[0132] In this embodiment, the target cost function may be constructed based on the target vector, and the target vector may be composed of at least one of the above-calculated trajectory point spacing information, trajectory point fusion feature information, and trajectory curvature information.

[0133] For example, the target cost function in this embodiment can simultaneously include the track point spacing information, the track point fusion feature information, and the track curvature information, and the three can be spliced ​​into the target vector x, so that the target cost function f(x) = x T px+q T x, wherein the weights p and q can be set according to human experience and are not specifically limited thereto.

[0134] It is worth noting that in the process of objective function optimization, the trajectory point spacing information between two adjacent trajectory points in the candidate trajectory should be as small as possible, the moving distance of the fused trajectory points in the candidate trajectory should be as small as possible, and the curvature in the candidate trajectory should be as small as possible, which ensures the smoothness of the solved target trajectory and realizes the smooth splicing of multiple trajectories.

[0135] In one embodiment, in the above S20, “optimizing the target trajectory according to the target cost function to determine the target trajectory” may include:

[0136] S201, determining a target hard constraint according to a reference trajectory among the multiple trajectories, wherein the reference trajectory is a previous trajectory among the multiple trajectories;

[0137] S202: Optimize the candidate trajectories according to the target hard constraint and the target cost function to determine the target trajectory.

[0138] It should be noted that, in this embodiment, hard constraints can be understood as constraints that must be strictly satisfied, and these constraints cannot be violated during the trajectory optimization process.

[0139] On this basis, this embodiment can determine the target hard constraint according to the previous trajectory among the multiple trajectories. For example, if the multiple trajectories include a first trajectory in front and a second trajectory in the back, then the first trajectory can be set as a reference trajectory, and the target constraint can be determined according to the reference trajectory.

[0140] Then, according to the target hard constraints, the candidate trajectories can be optimized with the minimum target cost function to determine the optimal target trajectory, for example, Figure 6 As shown in Figure 3, the target trajectory is smoother than the trajectory after direct splicing.

[0141] In a specific embodiment, in the above S201, “determining the target hard constraint according to the reference trajectory among the multiple trajectories” may include:

[0142] S2011, determining the target hard constraint based on the distance between the trajectory point on the planned candidate trajectory and the reference trajectory.

[0143] It is worth noting that in this embodiment, in order to ensure that the vehicle changes from the first trajectory in front to the second trajectory in the back without steering wheel turning and realize smooth lane change, the first trajectory in front can be used as a reference, and the target hard constraint can be determined based on the distance between the trajectory point on the planned candidate trajectory and the first trajectory.

[0144] In a specific embodiment, the target hard constraint includes that the distance between a trajectory point on the planned candidate trajectory and a reference trajectory is less than a preset distance threshold.

[0145] Among them, the preset distance threshold can be set based on experience to ensure the smoothness of the vehicle's overall lane change.

[0146] On this basis, in the above S202, “optimizing the candidate trajectory according to the target hard constraint and the target cost function to determine the target trajectory” may include:

[0147] S2021, optimizing the candidate trajectory by minimizing the value of the target cost function as the optimization target to obtain a target trajectory point;

[0148] S2021: If the distance between the target trajectory point and the reference trajectory is less than a preset distance threshold, generate a target trajectory according to the target trajectory point.

[0149] In this embodiment, the target cost function is minimized as the optimization target to optimize the candidate trajectory, and the target trajectory point is obtained. Then, the first trajectory can be used as a hard constraint to calculate the distance g(x) between the target trajectory point and the first trajectory.

[0150] If the distance is less than or equal to the preset distance threshold h, the target trajectory can be generated according to the target trajectory point.

[0151] If the distance is greater than the preset distance threshold h, the target trajectory point can be ignored. Combined with the above description, the fused trajectory points are repeatedly adjusted until the target trajectory is generated.

[0152] In this way, the present application can construct a target cost function through secondary optimization and use the previous trajectory as a hard constraint until the optimal target trajectory is calculated, thereby ensuring the smoothness of the solved target trajectory and achieving smooth splicing of multiple trajectories.

[0153] Accordingly, the present application also provides a trajectory planning device, such as Figure 7 As shown, the device may include:

[0154] A function determination module 1001 is used to perform trajectory planning based on the position information of the trajectory points of the plurality of trajectories, and determine a target cost function corresponding to the planned candidate trajectory; the target cost function is constructed based on at least one of the trajectory point spacing information, the trajectory point fusion feature information, and the trajectory curvature information of the candidate trajectory;

[0155] The trajectory optimization module 1002 is used to optimize the candidate trajectories according to the target cost function to determine the target trajectory.

[0156] Optionally, the multiple trajectories include a first trajectory and a second trajectory, and the function determination module 1001 is further configured to:

[0157] Determine, based on the position information, overlapping trajectory points and non-overlapping trajectory points in the first trajectory and the second trajectory;

[0158] Trajectory planning is performed based on the position information of non-overlapping trajectory points in the first trajectory and the second trajectory to obtain a planned candidate trajectory, and a target cost function corresponding to the planned candidate trajectory is determined.

[0159] Optionally, the function determination module 1001 is further used to:

[0160] Performing trajectory point fusion based on position information of non-overlapping trajectory points in the first trajectory and the second trajectory to obtain fused trajectory points;

[0161] The planned candidate trajectory is determined based on the fused trajectory points and the coincident trajectory points, and a target cost function corresponding to the planned candidate trajectory is determined.

[0162] Optionally, the function determination module 1001 is further used to:

[0163] Determine trajectory points to be fused among non-overlapping trajectory points of the first trajectory and the second trajectory;

[0164] Plan the trajectory points to be fused and the corresponding fused trajectory points.

[0165] Optionally, the function determination module 1001 is further used to:

[0166] The step of determining the track point spacing information of the candidate track comprises:

[0167] The distances between adjacent trajectory points on the candidate trajectory are calculated to obtain trajectory point distance information of the candidate trajectory.

[0168] Optionally, the function determination module 1001 is further used to:

[0169] Based on the fused trajectory point and the distance between the fused trajectory point and the non-overlapping trajectory point corresponding to the fused trajectory point, the trajectory point fusion feature information of the candidate trajectory is determined.

[0170] Optionally, the function determination module 1001 is further used to:

[0171] For three adjacent trajectory points on the candidate trajectory, calculating the slopes of adjacent trajectory points among the three adjacent trajectory points;

[0172] Based on the slope, trajectory curvature information corresponding to the three adjacent trajectory points is determined.

[0173] Optionally, the function determination module 1001 is further used to:

[0174] sorting the first trajectory and the second trajectory based on the position information;

[0175] Based on the sorting result, coincident trajectory points and non-coincident trajectory points in the first trajectory and the second trajectory are determined.

[0176] Optionally, the position information includes a horizontal position and a vertical position of the track point, and the function determination module 1001 is further used to:

[0177] The sorting of the first track and the second track based on the position information includes:

[0178] sorting the track points in the first track and the second track according to the lateral position; or,

[0179] The track points in the first track and the second track are sorted according to the longitudinal position.

[0180] Optionally, the target cost function is constructed based on a target vector, and the target vector is composed of at least one of the trajectory point spacing information, trajectory point fusion feature information and trajectory curvature information.

[0181] Optionally, the trajectory optimization module 1002 is further configured to:

[0182] Determining a target hard constraint according to a reference trajectory among the multiple trajectories, wherein the reference trajectory is a previous trajectory among the multiple trajectories;

[0183] The candidate trajectories are optimized according to the target hard constraints and the target cost function to determine the target trajectory.

[0184] Optionally, the trajectory optimization module 1002 is further configured to:

[0185] The target hard constraint is determined based on the distance between the trajectory point on the planned candidate trajectory and the reference trajectory.

[0186] Optionally, the target hard constraint includes that the distance between the trajectory point on the planned candidate trajectory and the reference trajectory is less than a preset distance threshold,

[0187] The trajectory optimization module 1002 is further used for:

[0188] Minimizing the value of the target cost function as the optimization target to optimize the candidate trajectory to obtain the target trajectory point;

[0189] If the distance between the target trajectory point and the reference trajectory is less than a preset distance threshold, a target trajectory is generated according to the target trajectory point.

[0190] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0191] Accordingly, the present application also provides an electronic device, such as Figure 8 As shown, Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 1100 includes a processor 1101 having one or more processing cores, a memory 1102 having one or more computer-readable storage media, and a computer program stored in the memory 1102 and executable on the processor. The processor 1101 is electrically connected to the memory 1102. It will be understood by those skilled in the art that the vehicle structure shown in the figure does not constitute a limitation on the vehicle, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0192] The processor 1101 is the control center of the electronic device 1100, and uses various interfaces and lines to connect various parts of the entire electronic device 1100. By running or loading software programs and / or units stored in the memory 1102, and calling data stored in the memory 1102, the processor 1101 executes various functions of the electronic device 1100 and processes data, thereby monitoring the electronic device 1100 as a whole. The processor 1101 can be a processor (Central Processing Unit, CPU), a graphics processing unit (graphics processing unit, GPU), a network processor (Network Processor, NP), etc., and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application.

[0193] In the embodiment of the present application, the processor 1101 in the electronic device 1100 will load instructions corresponding to the processes of one or more application programs into the memory 1102 according to the following steps, and the processor 1101 will run the application programs stored in the memory 1102 to implement various functions, such as:

[0194] Performing trajectory planning based on the position information of the trajectory points of the plurality of trajectories, and determining a target cost function corresponding to the planned candidate trajectory; the target cost function is constructed based on at least one of the trajectory point spacing information, the trajectory point fusion feature information, and the trajectory curvature information of the candidate trajectory;

[0195] The candidate trajectories are optimized according to the target cost function to determine the target trajectory.

[0196] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0197] Optional, such as Figure 8 As shown, the electronic device 1100 further includes: a touch screen 1103, a radio frequency circuit 1104, an audio circuit 1105, an input unit 1106, and a power supply 1107. The processor 1101 is electrically connected to the touch screen 1103, the radio frequency circuit 1104, the audio circuit 1105, the input unit 1106, and the power supply 1107, respectively. Those skilled in the art can understand that Figure 8 The vehicle structure shown in the figure does not constitute a limitation on the vehicle, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0198] The touch display screen 1103 can be used to display a graphical user interface and receive operation instructions generated by the user acting on the graphical user interface. The touch display screen 1103 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user and various graphical user interfaces of the vehicle, which can be composed of graphics, text, icons, videos and any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD, Liquid Crystal Display), an organic light-emitting diode (OLED, Organic Light-Emitting Diode), etc. The touch panel can be used to collect the user's touch operation on or near it (such as the user uses any suitable object or accessory such as a finger, stylus, etc. on the touch panel or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute the corresponding program. Optionally, the touch panel may include two parts: a touch display system and a touch controller. Among them, the touch display system detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch display system, converts it into the touch point coordinates, and then sends it to the processor 1101, and can receive the command sent by the processor 1101 and execute it. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 1101 to determine the type of touch event, and then the processor 1101 provides a corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present application, the touch panel and the display panel can be integrated into the touch display screen 1103 to realize the input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize the input and output functions. That is, the touch display screen 1103 can also be used as a part of the input unit 1106 to realize the input function.

[0199] The RF circuit 1104 may be used to send and receive RF signals to establish wireless communication with network devices or other vehicles through wireless communication, and to send and receive signals with network devices or other vehicles.

[0200] The audio circuit 1105 can be used to provide an audio interface between the user and the vehicle through a speaker and a microphone. The audio circuit 1105 can transmit the electrical signal converted from the received audio data to the speaker, which is converted into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 1105 and converted into audio data, and then the audio data is output to the processor 1101 for processing, and then sent to another vehicle through the radio frequency circuit 1104, or the audio data is output to the memory 1102 for further processing. The audio circuit 1105 may also include an earplug jack to provide communication between an external headset and the vehicle.

[0201] The input unit 1106 may be used to receive input numbers, character information or user feature information (such as fingerprint, iris, facial information, etc.), and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0202] The power supply 1107 is used to supply power to various components of the electronic device 1100. Optionally, the power supply 1107 can be logically connected to the processor 1101 through a power management device, so that the power management device can manage charging, discharging, power consumption and other functions. The power supply 1107 can also include one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0203] although Figure 8 Not shown, the electronic device 1100 may also include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be described in detail here.

[0204] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0205] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0206] To this end, an embodiment of the present application provides a computer-readable storage medium, in which a plurality of computer programs are stored. The computer program can be loaded by a processor to execute any trajectory planning method provided in the embodiment of the present application. The computer program can execute the steps of the following trajectory planning method:

[0207] Performing trajectory planning based on the position information of the trajectory points of the plurality of trajectories, and determining a target cost function corresponding to the planned candidate trajectory; the target cost function is constructed based on at least one of the trajectory point spacing information, the trajectory point fusion feature information, and the trajectory curvature information of the candidate trajectory;

[0208] The candidate trajectories are optimized according to the target cost function to determine the target trajectory.

[0209] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0210] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0211] Since the computer program stored in the computer-readable storage medium can execute any trajectory planning method provided in the embodiments of the present application, the beneficial effects that can be achieved by any trajectory planning method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0212] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0213] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0214] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0215] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0216] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0217] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0218] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated communication signals and carrier waves.

[0219] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0220] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0221] The embodiments, implementation methods and related technical features of the present application can be combined and replaced with each other without conflict.

[0222] The above are only preferred embodiments of the present application and do not constitute any form of limitation to the present application. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application are still within the scope of the technical solution of the present application.

Claims

1. A trajectory planning method, characterized in that: The method is applied to a vehicle, and comprises: Performing trajectory planning based on the position information of the trajectory points of the plurality of trajectories, and determining a target cost function corresponding to the planned candidate trajectory; the target cost function is constructed based on at least one of the trajectory point spacing information, the trajectory point fusion feature information, and the trajectory curvature information of the candidate trajectory; The candidate trajectories are optimized according to the target cost function to determine the target trajectory.

2. The trajectory planning method according to claim 1, characterized in that: The multiple trajectories include a first trajectory and a second trajectory, and the trajectory planning is performed based on the position information of the trajectory points of the multiple trajectories to determine the target cost function corresponding to the planned candidate trajectory; including: Determine, based on the position information, overlapping trajectory points and non-overlapping trajectory points in the first trajectory and the second trajectory; Trajectory planning is performed based on the position information of non-overlapping trajectory points in the first trajectory and the second trajectory to obtain a planned candidate trajectory, and a target cost function corresponding to the planned candidate trajectory is determined.

3. The trajectory planning method according to claim 2, characterized in that: The trajectory planning is performed based on the position information of the non-overlapping trajectory points in the first trajectory and the second trajectory to obtain the planned candidate trajectory, including Performing trajectory point fusion based on position information of non-overlapping trajectory points in the first trajectory and the second trajectory to obtain fused trajectory points; The planned candidate trajectory is determined based on the fused trajectory points and the coincident trajectory points, and a target cost function corresponding to the planned candidate trajectory is determined.

4. The trajectory planning method according to claim 3, characterized in that: The step of fusing trajectory points based on the position information of non-overlapping trajectory points in the first trajectory and the second trajectory to obtain fused trajectory points includes: Determine trajectory points to be fused among non-overlapping trajectory points of the first trajectory and the second trajectory; Plan the trajectory points to be fused and the corresponding fused trajectory points.

5. The trajectory planning method according to claim 4, characterized in that: The step of determining the track point spacing information of the candidate track comprises: The distances between adjacent trajectory points on the candidate trajectory are calculated to obtain trajectory point distance information of the candidate trajectory.

6. The trajectory planning method according to claim 4, characterized in that: The step of determining the trajectory point fusion feature information of the candidate trajectory includes: Based on the fused trajectory point and the distance between the fused trajectory point and the non-overlapping trajectory point corresponding to the fused trajectory point, the trajectory point fusion feature information of the candidate trajectory is determined.

7. The trajectory planning method according to claim 4, characterized in that: The step of determining the trajectory curvature information comprises: For three adjacent trajectory points on the candidate trajectory, calculating the slopes of adjacent trajectory points among the three adjacent trajectory points; Based on the slope, trajectory curvature information corresponding to the three adjacent trajectory points is determined.

8. The trajectory planning method according to claim 2, characterized in that: The determining, based on the position information, overlapping trajectory points and non-overlapping trajectory points in the first trajectory and the second trajectory includes: sorting the first trajectory and the second trajectory based on the position information; Based on the sorting result, coincident trajectory points and non-coincident trajectory points in the first trajectory and the second trajectory are determined.

9. The trajectory planning method according to claim 8, characterized in that: The position information includes the horizontal position and the vertical position of the track point, and the first track and the second track are sorted based on the position information, including sorting the track points in the first track and the second track according to the lateral position; or, The track points in the first track and the second track are sorted according to the longitudinal position.

10. The trajectory planning method according to any one of claims 1 to 9, characterized in that: The target cost function is constructed based on a target vector, and the target vector is composed of at least one of the trajectory point spacing information, the trajectory point fusion feature information, and the trajectory curvature information.

11. The trajectory planning method according to any one of claims 1 to 9, characterized in that: The step of optimizing the target trajectory according to the target cost function to determine the target trajectory includes: Determining a target hard constraint according to a reference trajectory among the multiple trajectories, wherein the reference trajectory is a previous trajectory among the multiple trajectories; The candidate trajectories are optimized according to the target hard constraints and the target cost function to determine the target trajectory.

12. The trajectory planning method according to claim 11, characterized in that: The step of determining the target hard constraint according to the reference trajectory among the plurality of trajectories comprises: The target hard constraint is determined based on the distance between the trajectory point on the planned candidate trajectory and the reference trajectory.

13. The trajectory planning method according to claim 12, characterized in that: The target hard constraint includes that the distance between the trajectory point on the planned candidate trajectory and the reference trajectory is less than a preset distance threshold, The step of optimizing the candidate trajectory according to the target hard constraint and the target cost function to determine the target trajectory includes: Minimizing the value of the target cost function as the optimization target to optimize the candidate trajectory to obtain the target trajectory point; If the distance between the target trajectory point and the reference trajectory is less than a preset distance threshold, a target trajectory is generated according to the target trajectory point.

14. A trajectory planning device, characterized in that: The trajectory planning device comprises: A function determination module, configured to perform trajectory planning based on the position information of the trajectory points of the plurality of trajectories, and determine a target cost function corresponding to the planned candidate trajectory; the target cost function is constructed based on at least one of the trajectory point spacing information, the trajectory point fusion feature information, and the trajectory curvature information of the candidate trajectory; The trajectory optimization module is used to optimize the candidate trajectories according to the target cost function to determine the target trajectory.

15. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the method according to any one of claims 1 to 13.

16. A vehicle, characterized in that: The vehicle is provided with the electronic device as claimed in claim 15.

17. A computer-readable storage medium, characterized in that: It includes a computer program. When the computer program is run on an electronic device, the computer program is used to make the electronic device execute any one of the methods described in claims 1 to 13.

18. A computer program product, characterized in that It includes a computer program, which is stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device executes any one of the methods described in claims 1 to 13.

Images