A trajectory planning method, device, equipment and storage medium

Abstract

The application discloses a trajectory planning method, device and equipment and a storage medium. The method comprises the following steps: obtaining vehicle driving data and driving environment data of a target vehicle; inputting the vehicle driving data and the driving environment data into a trajectory prediction model to obtain a plurality of predicted driving paths corresponding to the target vehicle and a plurality of predicted speed distribution data; determining a current driving scene of the target vehicle based on the driving environment data; performing curvature smoothing on the plurality of predicted driving paths based on the current driving scene to obtain a plurality of candidate driving paths; and performing trajectory synthesis on the predicted speed distribution data and the candidate driving paths to obtain a target driving trajectory. The application can improve the accuracy and safety of the determination of the driving trajectory of the target vehicle by optimizing the predicted driving path and screening the candidate driving path based on the predicted speed distribution data to obtain the target driving trajectory.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a trajectory planning method, device, equipment and storage medium. BACKGROUND

[0002] For trajectory planning of an autonomous vehicle, related technologies mainly generate multiple candidate driving trajectories based on historical driving data of the vehicle and surrounding environment information. These candidate trajectories provide possible future driving paths for the vehicle, providing decision-making reference for downstream planning modules.

[0003] However, the trajectories generated by the trajectory prediction model in different scenarios may have defects in the motion trajectory, causing the vehicle to be unable to pass according to the expected trajectory, thereby affecting the accuracy and safety of trajectory planning. SUMMARY

[0004] In view of the above defects of the related art, the technical problem to be solved by the present application is how to improve the accuracy and safety of target driving trajectory determination.

[0005] To solve at least one of the above technical problems, the present application discloses a trajectory planning method, device, equipment and storage medium.

[0006] According to an aspect of the present disclosure, a trajectory planning method is provided, comprising:

[0007] Obtaining vehicle driving data and driving environment data of a target vehicle;

[0008] Inputting the vehicle driving data and the driving environment data into a trajectory prediction model to obtain multiple predicted driving paths and multiple predicted speed distribution data corresponding to the target vehicle;

[0009] Based on the driving environment data, determining a current driving scenario of the target vehicle;

[0010] Based on the current driving scenario, respectively smoothing the curvatures of the multiple predicted driving paths to obtain multiple candidate driving paths;

[0011] Performing trajectory synthesis on the predicted speed distribution data and the candidate driving paths to obtain a target driving trajectory.

[0012] In some possible embodiments, the determining of the current driving scenario of the target vehicle based on the driving environment data comprises:

[0013] Determining map location information corresponding to the target vehicle based on the vehicle driving data and the driving environment data;

[0014] determine a plurality of sampling points based on the map position information, and calculate average sampling point curvatures of the plurality of sampling points;

[0015] determine the current driving scene based on the average sampling point curvatures.

[0016] In some possible embodiments, the curvature smoothing of the plurality of predicted driving paths based on the current driving scene respectively, to obtain the plurality of candidate driving paths, comprises:

[0017] determine a preset curvature smoothing condition matched with the current driving scene;

[0018] perform curvature smoothing on the plurality of predicted driving paths based on the preset curvature smoothing condition, to obtain the plurality of candidate driving paths.

[0019] In some possible embodiments, the curvature smoothing of the plurality of predicted driving paths based on the preset curvature smoothing condition respectively, to obtain the plurality of candidate driving paths, comprises:

[0020] determine a plurality of first control points and a plurality of second control points corresponding to the plurality of predicted driving paths respectively; the first control point is a starting point of each predicted driving path, and the second control point is a terminal point of each predicted driving path;

[0021] perform curvature calculation based on the plurality of predicted driving paths, to obtain a plurality of average curvatures; each predicted driving path corresponds to an average curvature;

[0022] determine a plurality of intermediate control points from the corresponding predicted driving path based on each average curvature;

[0023] perform curvature smoothing on the plurality of predicted driving paths respectively based on the first smoothing condition, the plurality of first control points, the plurality of second control points and the plurality of intermediate control points, to obtain the plurality of candidate driving paths.

[0024] In some possible embodiments, the curvature smoothing of the plurality of predicted driving paths based on the preset curvature smoothing condition respectively, to obtain the plurality of candidate driving paths, comprises:

[0025] obtain a preset tracking distance;

[0026] perform curvature smoothing on the plurality of predicted driving paths respectively based on the second smoothing condition and the preset tracking distance, to obtain the plurality of candidate driving paths.

[0027] In some possible embodiments, the trajectory synthesis of the predicted speed distribution data and the candidate driving path, to obtain a target driving trajectory, comprises:

[0028] data smoothing is performed on the predicted speed distribution data to obtain target speed distribution data;

[0029] trajectory synthesis is performed based on the target speed distribution data and the candidate driving path to obtain the target driving trajectory.

[0030] In some possible embodiments, the trajectory synthesis is performed based on the target speed distribution data and the candidate driving path to obtain the target driving trajectory, including:

[0031] trajectory synthesis is performed based on the target speed distribution data and the candidate driving path to obtain a plurality of to-be-screened driving trajectories;

[0032] trajectory screening is performed on the plurality of to-be-screened driving trajectories based on a preset trajectory screening condition to obtain the target driving trajectory; and the target driving trajectory has a plurality of quantities.

[0033] According to a second aspect of the present disclosure, a trajectory planning device is provided, which includes:

[0034] a data acquisition module configured to acquire vehicle driving data and driving environment data of a target vehicle;

[0035] a data prediction module configured to input the vehicle driving data and the driving environment data into a trajectory prediction model to obtain a plurality of predicted driving paths and a plurality of predicted speed distribution data corresponding to the target vehicle;

[0036] a scene determination module configured to determine a current driving scene of the target vehicle based on the driving environment data;

[0037] a curvature smoothing module configured to perform curvature smoothing on the plurality of predicted driving paths based on the current driving scene to obtain a plurality of candidate driving paths;

[0038] a trajectory determination module configured to perform trajectory synthesis on the predicted speed distribution data and the candidate driving path to obtain a target driving trajectory.

[0039] There can be other module division manners, and the present application does not limit the module division manner of the device for implementing the above functions. For example, the above data acquisition module, data prediction module, scene determination module, curvature smoothing module, and trajectory determination module can be integrated / implemented as one or more processing modules.

[0040] According to a third aspect of the present disclosure, an electronic device is provided, which includes a processor. The processor can execute the trajectory planning method according to any of the above. Optionally, the electronic device can further include a memory, which stores at least one instruction and at least one program, and the at least one instruction and the at least one program are loaded and executed by the processor to implement the trajectory planning method according to the above.

[0041] According to a fourth aspect of the present disclosure, a computer storage medium is provided, which stores at least one instruction and at least one program, and the at least one instruction and the at least one program are loaded and executed by a processor to implement the trajectory planning method according to the above. For example, the medium can be a computer readable storage medium.

[0042] According to a fifth aspect of the present disclosure, a chip system is provided, which includes at least one processor and at least one interface circuit, the at least one interface circuit is configured to perform a transceiving function and send an instruction to the at least one processor, and when the at least one processor executes the instruction, the at least one processor executes the trajectory planning method according to the first aspect and any of the designs thereof.

[0043] According to a sixth aspect of the present disclosure, a computer program product is provided, which includes a computer program / instruction, and when the computer program / instruction is executed by a processor, the trajectory planning method according to the above is implemented.

[0044] According to a seventh aspect of the present disclosure, a trajectory planning method is provided, which can be executed by an electronic device, which can be a component level (such as a chip) or a whole machine level (such as a vehicle), and the method can include: obtaining a candidate driving path, the candidate driving path being obtained by performing curvature smoothing on a predicted driving path; and controlling driving based on the candidate driving path.

[0045] Optionally, the controlling driving based on the candidate driving path includes: performing trajectory synthesis on the predicted speed distribution data and the candidate driving path to obtain a target driving trajectory.

[0046] The present disclosure has the following beneficial effects:

[0047] In the present application, the vehicle driving data and the driving environment data corresponding to the target vehicle are input into the trajectory prediction model to obtain a plurality of predicted driving paths and corresponding predicted speed distribution data, and the current driving scene of the target vehicle is determined according to the driving environment data, and the candidate driving path is obtained by smoothing the curvature of the predicted driving path according to the current driving scene, so that the candidate driving path can meet the actual driving demand in the scene corresponding to different path curvatures, avoiding the steering problem caused by insufficient trajectory curvature or sudden change of curvature, thereby improving the safety and accuracy of the candidate driving path. In addition, the candidate driving path is combined with the predicted speed distribution data, so that the obtained target driving trajectory can consider the constraints of road conditions, traffic rules and dynamic environment (such as the speed of the preceding vehicle, the time of the traffic light, etc.), thereby improving the dynamic adaptability of trajectory planning; at the same time, the speed distribution data is combined with the candidate driving path, which can avoid unreasonable acceleration, deceleration or excessive lateral acceleration, and thus can better meet the vehicle dynamics model, avoid loss of control due to excessive speed, and improve the driving safety of the vehicle and the comfort of the user riding the vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0049] Figure 1 The flowchart of the trajectory planning method provided by the embodiment of the present application is shown in the figure.

[0050] Figure 2 The flowchart of the current driving scene determination provided by the embodiment of the present application is shown in the figure.

[0051] Figure 3 The flowchart of the trajectory curvature smoothing provided by the embodiment of the present application is shown in the figure.

[0052] Figure 4 The flowchart of the target trajectory determination provided by the embodiment of the present application is shown in the figure.

[0053] Figure 5 The structure diagram of the trajectory planning device provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0054] With reference to the drawings, the technical solutions in the embodiments of the present specification will be described clearly and completely. Obviously, the described embodiments are only some of the embodiments of the present specification, rather than all the embodiments. Based on the embodiments in the present specification, all other embodiments obtained by those skilled in the art without creative efforts can fall within the scope of the present application.

[0055] It should be noted that the terms "first", "second" and the like in the description and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in other than the order illustrated or described herein. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server comprising a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0056] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numbers in the drawings represent functionally the same or similar elements. Although various aspects of the embodiments are illustrated in the drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

[0057] The word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any implementation described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other implementations.

[0058] The term "and / or", merely used to describe the associated relationship of associated objects, means that there can be three relationships, for example, A and / or B, which can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. In addition, the term "at least one" herein means any one of the plurality or any combination of at least two of the plurality, for example, including at least one of A, B and C, which can mean including any one or more elements selected from the set consisting of A, B and C.

[0059] In addition, in order to better illustrate the present disclosure, a large number of specific details are given in the specific embodiments below. Those skilled in the art should understand that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, elements and circuits well known to those skilled in the art are not described in detail, in order to highlight the main idea of the present disclosure.

[0060] Figure 1A flowchart of a trajectory planning method provided by an embodiment of the present application is shown. The execution subject can be any terminal capable of executing the trajectory planning method, such as a controller, a server, or the like, or can be a corresponding module capable of implementing or assisting in implementing the terminal function, such as a chip. Please refer to Figure 1 A trajectory planning method, comprising:

[0061] Step S101: obtaining vehicle driving data and driving environment data of a target vehicle;

[0062] In a feasible embodiment, the vehicle driving data can include current position information and current speed information of the target vehicle, and the driving environment data can include position information and speed information of other vehicles around the target vehicle on the road, map data information, and red light information, lane line information, dynamic obstacle information, and static obstacle information obtained through sensors.

[0063] The map data information can include lane line information, such as left boundary line, right boundary line, and center line, and the lane line information includes point coordinates and attributes (color, solid or dashed, type, etc.) of these lines. In addition, the lane line information can also include connection relationships (previous, next, left neighbor, right neighbor) between lanes. The map data information can also include intersection information, such as intersection contour information, intersection type information, and connection relationship with non-intersection for a crossroad that does not include lane lines. At the same time, the map data information can also include road marking information, such as turning arrows on the lane. The map data information and the information obtained through sensors, such as lane line information, partially overlap, and the information obtained through the two methods can verify the accuracy of the driving environment data.

[0064] Step S102: inputting the vehicle driving data and the driving environment data into a trajectory prediction model to obtain a plurality of predicted driving paths and a plurality of predicted speed distribution data corresponding to the target vehicle;

[0065] In a specific embodiment, after obtaining the above information, the information is input into a pre-trained trajectory prediction model. The trajectory prediction model performs reasoning on the input information to obtain N predicted driving paths and M predicted speed distribution data. Each predicted driving path can correspond to K predicted speed distribution data, i.e., M=N*K, where the values of K and N can be set according to specific requirements. For example, K can be 6 and N can be 10, i.e., there are 10 predicted driving paths, and each predicted driving path can correspond to 6 predicted speed distribution data. In addition, after inputting the vehicle driving data and the driving environment data into the trajectory prediction model, the predicted trajectories corresponding to the dynamic obstacle information and the surrounding vehicle information can also be obtained.

[0066] For the predicted speed distribution data, its form can be the position on the predicted driving path at a given time, such as 0.1s at 1 meter from the starting point on the path, 0.2s at 3 meters from the starting point, and each predicted driving path and the corresponding speed distribution can be synthesized into a trajectory. The difference between the path and the trajectory is that the path is only a pure point, and the trajectory contains time, i.e. the time at which each point is located. Setting K predicted speed distribution data corresponding to each predicted driving path can provide more possibilities for subsequent trajectory selection, so as to find a more suitable trajectory and improve the safety, accuracy and adaptability to specific form requirements of trajectory planning.

[0067] The inference, i.e. the forward inference of the trajectory prediction model, receives the encoded data input in the specified format, automatically performs calculation in the processor, and outputs the calculation result. Since the embodiment of the present application is for post-processing of the model output result, the structure of the model itself and the training process are not described in detail.

[0068] Step S103: determining the current driving scene of the target vehicle based on the driving environment data;

[0069] In a specific embodiment, the current driving scene is determined, wherein the driving scene can include a large curve, a U-turn, a left and right turn, etc., the purpose is to distinguish the scene with high curvature in the predicted driving path and optimize it to make up for the defects in the output path. Therefore, the left and right turns can be classified into a category and distinguished by different directions.

[0070] Figure 2 A flowchart for trajectory curvature smoothing corresponding to the embodiment of the present application is shown in FIG. 1. Figure 2 As shown in FIG. 1, step S103 can specifically include:

[0071] Step S201: determining the map position information corresponding to the target vehicle based on the vehicle driving data and the driving environment data;

[0072] In a specific embodiment, the position of the target vehicle in the map can be determined according to the vehicle position information and the map data information, and the map position information can represent that the target vehicle is located on the lane or at the intersection in combination with the map data information.

[0073] Step S202: determining a plurality of sampling points based on the map position information and calculating the average sampling point curvature of the plurality of sampling points;

[0074] In a specific embodiment, when the target vehicle is located on the lane, a sampling point is determined at an interval of x meters from the current position of the target vehicle along the lane for S meters, for example, a sampling point is determined at an interval of 1 meter from 100 meters behind the target vehicle, thereby obtaining a plurality of sampling points and calculating the average sampling point curvature of the sampling points.

[0075] Step S203: determining the current driving scene based on the average sampling point curvature.

[0076] In one specific embodiment, the average sampling point curvature is compared with a preset average sampling point threshold value, and if the average sampling point curvature is greater than the average sampling point threshold value, it is determined that the target vehicle is in a curved path, and the current driving scene of the target vehicle is determined to be a curve. The average sampling point threshold value can be preset according to different driving requirements.

[0077] In another specific embodiment, when the target vehicle is at an intersection, the closest lane or virtual lane at the intersection is found, the included angle corresponding to the direction of the points at the head and tail of the lane is calculated, and if the included angle exceeds a preset included angle threshold value, it is considered to be a left or right turn or a U-turn. The included angle threshold value can be preset according to different driving requirements. In addition, since the curvature of the path corresponding to the U-turn is much larger than the curvature of the path corresponding to the left or right turn, the current driving scene can be further determined to be a left or right turn or a U-turn according to the curvature value; for a left or right turn, the positive or negative sign of the average curvature can be used to distinguish.

[0078] Step S104: based on the current driving scene, performing curvature smoothing on the plurality of predicted driving paths respectively to obtain a plurality of candidate driving paths;

[0079] In one specific embodiment, since the predicted driving paths output by the trajectory prediction model may have problems of insufficient curvature or sudden change, curvature smoothing can be performed on the predicted driving paths to solve the problems caused by insufficient curvature or sudden change of curvature, and to obtain a candidate driving path corresponding to each predicted driving path. The curvature smoothing manner of the predicted driving path is determined according to the driving scene, which can improve the adaptability of the curvature smoothing of the predicted driving path, and further improve the reliability of the smoothing result, i.e., the candidate driving path.

[0080] Figure 3 A flowchart corresponding to the trajectory curvature smoothing provided by the embodiment of the present application is shown in FIG. 4. As shown in FIG. 4, step S104 can include: Figure 3

[0081] Step S301: determining a preset curvature smoothing condition matched with the current driving scene;

[0082] ​In one specific embodiment, the preset curvature smoothing condition can include a first smoothing condition, a second smoothing condition, and a third smoothing condition; the first smoothing condition can correspond to a large curve and a left-right turn scene, and can use a high-order Bezier curve for curvature smoothing; the second smoothing condition can correspond to a U-turn scene, and can use a pure tracking method for curvature smoothing; the third smoothing condition can correspond to a general scene, i.e., a scene other than the left-right turn, large curve, and U-turn scenes, and can use a high-order Bezier curve for curvature smoothing; and then the plurality of predicted driving paths are respectively subjected to curvature smoothing based on the preset curvature smoothing condition to obtain a plurality of candidate driving paths.

[0083] Specifically, the plurality of predicted driving paths are respectively subjected to curvature smoothing based on the preset curvature smoothing condition to obtain a plurality of candidate driving paths, which can include:

[0084] Step S302: determining a plurality of first control points and a plurality of second control points corresponding to the plurality of predicted driving paths; the first control point is the starting point of each predicted driving path, and the second control point is the terminal point of each predicted driving path;

[0085] In one specific embodiment, for the large curve and left-right turn scene, the high-order Bezier curve is used for curvature smoothing, and first the starting point of each predicted driving path is determined as the first control point, and the second control point is the terminal point, and the first control point and the second control point are the first and last points of the curve smoothing.

[0086] Step S303: performing curvature calculation based on the plurality of predicted driving paths to obtain a plurality of average curvatures; each predicted driving path corresponds to an average curvature;

[0087] Step S304: determining a plurality of intermediate control points from the corresponding predicted driving path based on each average curvature;

[0088] In one specific embodiment, for the intermediate control points of curvature smoothing, the average curvature of each predicted driving path can be used for determination. Specifically, for any predicted driving path, the curvature of each point can be calculated first, and then the average curvature of this predicted driving path is calculated; for the predicted driving path, each point corresponding to a curvature greater than the average curvature is set as an intermediate control point, and for the point corresponding to a curvature less than the average curvature, every 2 points are set as an intermediate control point. The same method is used to determine the intermediate control points of each predicted driving path.

[0089] According to the selection of the intermediate control points based on the curvature, the control points are dense in the place with large curvature, and the control points are sparse in the place with small curvature, so as to realize the curvature smoothing of each predicted driving path and reduce the influence of insufficient curvature on the accuracy of the predicted driving path.

[0090] Step S305: based on the first smoothing condition, the plurality of first control points, the plurality of second control points and the plurality of intermediate control points, respectively performing curvature smoothing on the plurality of predicted driving paths to obtain a plurality of candidate driving paths.

[0091] In one specific embodiment, a high-order Bezier curve is used, and the first control point and the second control point of each predicted driving path are respectively taken as the first and last points of curvature smoothing, and the plurality of intermediate control points are used to perform curvature smoothing on each predicted driving path respectively, and a candidate driving path corresponding to each predicted driving path is obtained.

[0092] Alternatively, based on a preset curvature smoothing condition, the plurality of predicted driving paths are respectively subjected to curvature smoothing to obtain a plurality of candidate driving paths, including:

[0093] Step S306: obtaining a preset tracking distance;

[0094] Step S307: based on the second smoothing condition and the preset tracking distance, respectively performing curvature smoothing on the plurality of predicted driving paths to obtain a plurality of candidate driving paths.

[0095] In one specific embodiment, since the curvature of the U-turn path is larger than the curvature of the trajectory corresponding to other scenes, the pure tracking method is selected to perform curvature smoothing on the predicted driving path. The pure tracking method can not only smooth the curvature, but also increase the curvature, thereby making up for the problem of insufficient curvature of the path corresponding to the U-turn, thereby improving the accuracy, reliability and safety of the driving trajectory determination.

[0096] Specifically, the preset tracking distance, i.e., the preview distance, can be set according to specific driving requirements. For example, the preset tracking distance can be set to 20 m.

[0097] Alternatively, based on a preset curvature smoothing condition, the plurality of predicted driving paths are respectively subjected to curvature smoothing to obtain a plurality of candidate driving paths, including:

[0098] Step S302: determining a plurality of first control points and a plurality of second control points corresponding to a plurality of predicted driving paths; the first control point is the starting point of each predicted driving path, and the second control point is the termination point of each predicted driving path;

[0099] Step S308: determining a plurality of intermediate control points from the plurality of predicted driving paths with a preset control point interval;

[0100] Step S309: based on the third smoothing condition, the first control point, the second control point and the intermediate control point, respectively performing curvature smoothing on the plurality of predicted driving paths to obtain a plurality of candidate driving paths.

[0101] In a specific embodiment, when the driving scene is a general scene, the curvature smoothness corresponds to a third smoothness condition, and the determination of the first control point and the second control point is the same as that in the first smoothness condition, which will not be repeated here.

[0102] In a general scene, a plurality of intermediate control points can be determined from each predicted driving path according to each point on the predicted driving path, i.e., the distance corresponding to a preset control point interval, and then a plurality of intermediate control points corresponding to the plurality of predicted driving paths are determined.

[0103] Step S105: Trajectory synthesis is performed on the predicted speed distribution data and the candidate driving path to obtain a target driving trajectory.

[0104] In a specific embodiment, trajectory synthesis is performed using the candidate driving path and the speed distribution data to obtain a target driving trajectory. The planning points in the driving path are connected to obtain a polyline composed of many line segments, and the sum of the distances of the polyline is the distance to the starting point. In combination with the position given by the speed distribution to the starting point, the coordinates can be calculated by interpolation of the polyline, and the coordinates are the trajectory points. Each trajectory point corresponding to a candidate driving path is connected to obtain a target driving trajectory. For example, the distance between the 3rd point and the 1st point (starting point) is 10 meters, the distance between the 4th point and the starting point is 13 meters, and the speed distribution gives 0.5s at 11 meters from the starting point. Then, the coordinates of 11 meters can be calculated by interpolation of the 3rd point and the 4th point, and the coordinates are the coordinates of 0.5s, which is a trajectory point.

[0105] Figure 4 A corresponding flowchart of a target trajectory determination provided by an embodiment of the present application is shown in FIG. 5. Figure 4 As shown in FIG. 5, step S105 can specifically include:

[0106] Step S401: Data smoothing is performed on the predicted speed distribution data to obtain target speed distribution data.

[0107] In a specific embodiment, before trajectory synthesis, data smoothing can be performed on the predicted speed distribution data. One-dimensional and polynomial smoothing can be used to perform data smoothing on the predicted speed distribution data, respectively, so that the speed change is more continuous, the trajectory acceleration fluctuation caused by sudden speed change is reduced, and data noise is reduced.

[0108] Specifically, for all the predicted speed distribution data, Savi zkg-Gol ag filter algorithm can be used for smoothing to obtain target speed distribution data respectively; further, the acceleration and jerk of the target speed distribution data are calculated to determine whether there is discontinuous change exceeding the corresponding threshold; if there is, it means that the target speed distribution data after smoothing does not meet the requirements, and the target speed distribution data that does not meet the requirements is smoothed again to reduce the overall noise. The threshold corresponding to the acceleration and the jerk can be a percentage, for example, the acceleration difference between each two points is calculated, all the differences are averaged, and then it is checked whether there are differences exceeding 2 times or 3 times of the average, if there are, it is considered that the discontinuity is relatively high.

[0109] Further, based on the target speed distribution data and the candidate driving path, trajectory synthesis is performed to obtain a target driving trajectory, which can include:

[0110] Step S402: based on the target speed distribution data and the candidate driving path, trajectory synthesis is performed to obtain a plurality of to-be-screened driving trajectories;

[0111] In one specific embodiment, trajectory synthesis can use target speed distribution data and candidate driving paths, so as to reduce the noise influence of predicted speed distribution data and the noise influence of predicted driving path, and the plurality of to-be-screened driving trajectories obtained have higher reliability and safety compared with unprocessed data.

[0112] Step S403: based on a preset trajectory screening condition, trajectory screening is performed on the plurality of to-be-screened driving trajectories to obtain a target driving trajectory; the number of target driving trajectories is multiple.

[0113] In one specific embodiment, the plurality of to-be-screened driving trajectories can be sorted according to the preset trajectory screening condition, and a plurality of target driving trajectories meeting the condition are screened out. Specifically, the preset trajectory screening condition can include obstacle distance, vehicle driving speed and traffic rules, for example, the closer to the obstacle, the lower the score; the slower the speed, the lower the score; the more traffic rules violated (such as red light, solid line and other rules), the lower the score, etc. After sorting the plurality of to-be-screened driving trajectories according to the score, the first Q can be selected as the target driving trajectory, for example, Q can be 3. Selecting the plurality of to-be-screened driving trajectories as the target driving trajectory can provide more selection space and serve as alternative schemes to improve the reliability and safety of trajectory planning.

[0114] The embodiment of the present application also provides a trajectory planning device, as shown in the figure, the device comprises: Figure 5 as shown, the device comprises:

[0115] The data acquisition module 510 is configured to acquire vehicle driving data and driving environment data of a target vehicle.

[0116] The data prediction module 520 is configured to input the vehicle driving data and the driving environment data into a trajectory prediction model to obtain a plurality of predicted driving paths and a plurality of predicted speed distribution data corresponding to the target vehicle.

[0117] The scene determination module 530 is configured to determine a current driving scene of the target vehicle based on the driving environment data.

[0118] The curvature smoothing module 540 is configured to perform curvature smoothing on the plurality of predicted driving paths based on the current driving scene to obtain a plurality of candidate driving paths.

[0119] The trajectory determination module 550 is configured to perform trajectory synthesis on the predicted speed distribution data and the candidate driving paths to obtain a target driving trajectory.

[0120] In some embodiments, the scene determination module 530 further includes:

[0121] A position determination module is configured to determine map position information corresponding to the target vehicle based on the vehicle driving data and the driving environment data.

[0122] A data calculation module is configured to determine a plurality of sampling points based on the map position information and calculate an average sampling point curvature of the plurality of sampling points.

[0123] An information determination module is configured to determine the current driving scene based on the average sampling point curvature.

[0124] In some embodiments, the curvature smoothing module 540 further includes:

[0125] A first condition determination module is configured to determine a preset curvature smoothing condition matched with the current driving scene.

[0126] A path smoothing module is configured to perform curvature smoothing on the plurality of predicted driving paths based on the preset curvature smoothing condition to obtain the plurality of candidate driving paths.

[0127] In some embodiments, the path smoothing module further includes:

[0128] A first control point determination module is configured to determine a plurality of first control points and a plurality of second control points corresponding to the plurality of predicted driving paths; the first control point is a starting point of each predicted driving path, and the second control point is a terminal point of each predicted driving path.

[0129] A curvature calculation module is configured to perform curvature calculation based on the plurality of predicted driving paths to obtain a plurality of average curvatures; each predicted driving path corresponds to an average curvature.

[0130] The second control point determination module is configured to determine a plurality of intermediate control points from the corresponding predicted driving path based on each average curvature.

[0131] The first path processing module is configured to perform curvature smoothing on the plurality of predicted driving paths respectively based on the first smoothing condition, the plurality of first control points, the plurality of second control points and the plurality of intermediate control points, to obtain a plurality of candidate driving paths.

[0132] In some other embodiments, the path smoothing module further comprises:

[0133] The distance acquisition module is configured to acquire a preset tracking distance.

[0134] The second path processing module is configured to perform curvature smoothing on the plurality of predicted driving paths respectively based on the second smoothing condition and the preset tracking distance, to obtain the plurality of candidate driving paths.

[0135] In some other embodiments, the trajectory determination module 550 further comprises:

[0136] The data smoothing module is configured to perform data smoothing on the predicted speed distribution data to obtain target speed distribution data.

[0137] The first trajectory synthesis module is configured to perform trajectory synthesis based on the target speed distribution data and the candidate driving paths to obtain a target driving trajectory.

[0138] In some other embodiments, the first trajectory synthesis module further comprises:

[0139] The second trajectory synthesis module is configured to perform trajectory synthesis based on the target speed distribution data and the candidate driving paths to obtain a plurality of to-be-screened driving trajectories.

[0140] The trajectory screening module is configured to perform trajectory screening on the plurality of to-be-screened driving trajectories based on a preset trajectory screening condition to obtain the target driving trajectory, and the number of the target driving trajectories is a plurality.

[0141] The device in the device embodiment and the method embodiment are based on the same inventive concept, and are used to implement the trajectory planning method described above.

[0142] The embodiments of the present application also provide an electronic device, which comprises a processor and a memory, and the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the trajectory planning method in any of the method embodiments.

[0143] The embodiment of the present application also provides a storage medium which can be arranged in a server to save at least one instruction, at least one program, a code set or an instruction set for implementing the trajectory planning method in the method embodiment, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the trajectory planning method according to any one of the method embodiments.

[0144] Optionally, in the embodiment of the present application, the storage medium can be located in at least one of a plurality of network servers of a computer network. Optionally, in the embodiment of the present application, the storage medium can include but is not limited to a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk and various media capable of storing program codes.

[0145] The embodiment of the present application also provides a computer program product including a computer program and / or instructions, which are executed by a processor to implement the trajectory planning method according to any one of the method embodiments.

[0146] As can be seen from the above embodiments of the present application, in the present application, the vehicle driving data and the driving environment data corresponding to the target vehicle are input into a trajectory prediction model to obtain a plurality of predicted driving paths and corresponding predicted speed distribution data, and the current driving scene of the target vehicle is determined according to the driving environment data, and the candidate driving path is obtained by performing curvature smoothing on the predicted driving path according to the current driving scene, so that the candidate driving path can meet the actual driving demand in different scenes, and the turning problem caused by insufficient or sudden change of trajectory curvature is avoided, thereby improving the safety and accuracy of the candidate driving path. In addition, the candidate driving path is combined with the predicted speed distribution data, which can accurately plan the driving state of the target vehicle, thereby further improving the safety and accuracy of the candidate driving path.

[0147] It should be noted that the above has described various embodiments of the present disclosure, and the above description is exemplary and is not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those skilled in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles, practical applications or technical improvements in the market of the embodiments, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

Claims

1. A trajectory planning method characterized by, The method comprises: obtaining vehicle driving data and driving environment data of a target vehicle; inputting the vehicle driving data and the driving environment data into a trajectory prediction model to obtain a plurality of predicted driving paths and a plurality of predicted speed distribution data corresponding to the target vehicle; determining a current driving scene of the target vehicle based on the driving environment data; based on the current driving scene, performing curvature smoothing on the plurality of predicted driving paths respectively to obtain a plurality of candidate driving paths; performing trajectory synthesis on the predicted speed distribution data and the candidate driving paths to obtain a target driving trajectory; the trajectory synthesis on the predicted speed distribution data and the candidate driving paths to obtain the target driving trajectory comprises: performing data smoothing on the predicted speed distribution data to obtain target speed distribution data; based on the target speed distribution data and the candidate driving paths, performing trajectory synthesis to obtain the target driving trajectory; the trajectory synthesis based on the target speed distribution data and the candidate driving paths to obtain the target driving trajectory comprises: based on the target speed distribution data and the candidate driving paths, performing trajectory synthesis to obtain a plurality of to-be-screened driving trajectories; based on a preset trajectory screening condition, performing trajectory screening on the plurality of to-be-screened driving trajectories to obtain the target driving trajectory; the number of target driving trajectories is multiple.

2. The trajectory planning method of claim 1, wherein, the determination of the current driving scene of the target vehicle based on the driving environment data comprises: determining map location information corresponding to the target vehicle based on the vehicle driving data and the driving environment data; determining a plurality of sampling points based on the map location information and calculating the average sampling point curvature of the plurality of sampling points; determining the current driving scene based on the average sampling point curvature.

3. The trajectory planning method of claim 2, wherein, the curvature smoothing on the plurality of predicted driving paths based on the current driving scene to obtain a plurality of candidate driving paths comprises: determining a preset curvature smoothing condition matched with the current driving scene; based on the preset curvature smoothing condition, performing curvature smoothing on the plurality of predicted driving paths to obtain the plurality of candidate driving paths.

4. The trajectory planning method of claim 3, wherein, the preset curvature smoothing condition comprises a first smoothing condition; the curvature smoothing on the plurality of predicted driving paths based on the preset curvature smoothing condition to obtain the plurality of candidate driving paths comprises: determining a plurality of first control points and a plurality of second control points corresponding to the plurality of predicted driving paths respectively; the first control point is the starting point of each predicted driving path, and the second control point is the termination point of each predicted driving path; based on the plurality of predicted driving paths, performing curvature calculation to obtain a plurality of average curvatures; each predicted driving path corresponds to an average curvature; based on each average curvature, determining a plurality of intermediate control points from the corresponding predicted driving path; based on the first smoothing condition, the plurality of first control points, the plurality of second control points and the plurality of intermediate control points, performing curvature smoothing on the plurality of predicted driving paths respectively to obtain the plurality of candidate driving paths.

5. The trajectory planning method of claim 3, wherein, The preset curvature smoothing condition comprises a second smoothing condition; The curvature smoothing of the plurality of predicted driving paths based on the preset curvature smoothing condition comprises: Obtaining a preset tracking distance; The curvature smoothing of the plurality of predicted driving paths based on the second smoothing condition and the preset tracking distance comprises:

6. A trajectory planning device characterized by comprising: The device comprises: A data acquisition module configured to acquire vehicle driving data and driving environment data of a target vehicle; A data prediction module configured to input the vehicle driving data and the driving environment data into a trajectory prediction model to obtain a plurality of predicted driving paths and a plurality of predicted speed distribution data corresponding to the target vehicle; A scene determination module configured to determine a current driving scene of the target vehicle based on the driving environment data; A curvature smoothing module configured to perform curvature smoothing on the plurality of predicted driving paths based on the current driving scene to obtain a plurality of candidate driving paths; A trajectory determination module configured to perform trajectory synthesis on the predicted speed distribution data and the candidate driving paths to obtain a target driving trajectory; The trajectory determination module comprises: A data smoothing module configured to perform data smoothing on the predicted speed distribution data to obtain target speed distribution data; A first trajectory synthesis module configured to perform trajectory synthesis on the target speed distribution data and the candidate driving paths to obtain the target driving trajectory; The first trajectory synthesis module comprises: A second trajectory synthesis module configured to perform trajectory synthesis on the target speed distribution data and the candidate driving paths to obtain a plurality of to-be-screened driving trajectories; A trajectory screening module configured to perform trajectory screening on the plurality of to-be-screened driving trajectories based on a preset trajectory screening condition to obtain the target driving trajectory; the number of target driving trajectories is a plurality.

7. An electronic device, comprising: The electronic device comprises a processor and a memory, the memory stores at least one instruction and at least one program, and the at least one instruction and the at least one program are loaded and executed by the processor to implement the trajectory planning method according to any one of claims 1-5.

8. A computer storage medium, characterized in that The computer storage medium stores at least one instruction and at least one program, and the at least one instruction and the at least one program are loaded and executed by the processor to implement the trajectory planning method according to any one of claims 1-5.

9. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instruction is executed by the processor to implement the trajectory planning method according to any one of claims 1-5.

Images