Vehicle trajectory planning method, device and equipment and storage medium

Abstract

The invention discloses a vehicle trajectory planning method, device and equipment and a storage medium, relates to the technical field of path planning, is applied to a current vehicle running on a main road, and comprises the steps of collecting vehicle feature information of each target vehicle located in an afflux area in a vehicle afflux scene; the afflux area comprises a main road and a ramp area; based on the road feature information of the vehicle afflux scene and the feature information of each vehicle, performing afflux intention prediction on each target vehicle by using a preset neural network to obtain each prediction result; the preset neural network is a neural network constructed based on a three-layer bidirectional long-short-term memory network; and planning the driving track of the current vehicle according to each prediction result to obtain a target driving track for avoiding each target vehicle. Therefore, the vehicle on the main road can predict the intention of each target vehicle on the ramp to merge into the main road in advance in the vehicle merge scene, the driving track capable of avoiding each target vehicle can be planned, and the vehicle driving safety is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a vehicle trajectory planning method, device, equipment and storage medium. Background Art

[0002] When a vehicle passes through a main road with a merging area, when it is driving in the main road lane close to the merging ramp, it is often invaded by vehicles merging into the main road from the ramp; in this case, it will cause greater lateral interference to the driving state of vehicles on the main road. At this time, the effect of direct trajectory prediction is often poor, which has a greater impact on the vehicle's lateral and longitudinal planning control modules, and ultimately has a greater impact on the vehicle's safety.

[0003] It can be seen that how to plan the paths of vehicles traveling on the main road in the vehicle merging scenario to eliminate the potential safety hazards caused when vehicles on the ramp merge into the main road is a problem to be solved in this field. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a vehicle trajectory planning method, device, equipment and storage medium, so that vehicles traveling on the main road can predict in advance the intention of each target vehicle located on the ramp to merge into the main road in the vehicle merging scenario, and can more accurately plan a driving trajectory that can avoid each target vehicle, thereby improving vehicle driving safety. The specific scheme is as follows:

[0005] In a first aspect, the present application provides a vehicle trajectory planning method, which is applied to a current vehicle traveling on a main road, comprising:

[0006] In a vehicle merging scenario, vehicle characteristic information of each target vehicle located in a merging area is collected; the merging area includes a main road and a ramp area that meets a preset distance condition from the main road;

[0007] Based on the road feature information of the vehicle merging scene and the feature information of each vehicle, a preset neural network is used to predict the merging intention of each target vehicle to obtain corresponding prediction results; the preset neural network is a neural network constructed based on a three-layer bidirectional long short-term memory network;

[0008] The driving trajectory of the current vehicle is planned according to each of the prediction results to obtain a target driving trajectory for avoiding each of the target vehicles in the vehicle merging scenario.

[0009] Optionally, before collecting vehicle feature information of each target vehicle located in the merging area in the vehicle merging scenario, the method further includes:

[0010] Determine whether the current vehicle driving scene matches the preset imported scene based on the surrounding map data of the current vehicle;

[0011] If the current vehicle driving scenario matches the preset merging scenario, a topological map is drawn based on the surrounding map data to obtain a merging area topological map, so as to collect vehicle feature information of each target vehicle located in the merging area under the vehicle merging scenario based on the merging area topological map.

[0012] Optionally, the collecting of vehicle characteristic information of each target vehicle located in the merging area in the vehicle merging scenario includes:

[0013] In a vehicle merging scenario, the attribute values ​​of each target vehicle located in the merging area are collected by a camera and / or a radar, and the attribute values ​​are marked in a topological map of the merging area to obtain vehicle feature information of each target vehicle.

[0014] Optionally, the predicting of the merging intention of each target vehicle based on the road feature information of the vehicle merging scene and the feature information of each vehicle to obtain corresponding prediction results includes:

[0015] Performing feature extraction processing on the road feature information of the scene where the vehicle enters through a first bidirectional long short-term memory network to obtain a corresponding map tensor;

[0016] Performing feature extraction processing on each of the vehicle feature information through a second bidirectional long short-term memory network to obtain a corresponding target tensor;

[0017] The third bidirectional long short-term memory network is used to predict the merging intention of each target vehicle by using the map tensor and the target tensor to obtain corresponding prediction results.

[0018] Optionally, the prediction result represents the probability of the target vehicle merging from the ramp area into the main road at each time point and the corresponding position point.

[0019] Optionally, planning the driving trajectory of the current vehicle according to each of the prediction results includes:

[0020] According to each of the prediction results, obstacle information is marked on the position points corresponding to each of the target vehicles at each time point, so as to plan the driving trajectory of the current vehicle based on the obstacle information.

[0021] Optionally, planning the driving trajectory of the current vehicle according to each of the prediction results to obtain a target driving trajectory for avoiding each of the target vehicles in the vehicle merging scenario includes:

[0022] The driving trajectory of the current vehicle is planned based on each of the prediction results, the road feature information, and each of the vehicle feature information to obtain a target driving trajectory for avoiding each of the target vehicles in the vehicle merging scenario.

[0023] In a second aspect, the present application provides a vehicle trajectory planning device, which is applied to a current vehicle traveling on a main road, comprising:

[0024] An information collection module, used to collect vehicle feature information of each target vehicle located in a merging area in a vehicle merging scenario; the merging area includes a main road and a ramp area that meets a preset distance condition from the main road;

[0025] A prediction module, for predicting the merging intention of each target vehicle based on the road feature information of the vehicle merging scene and the feature information of each vehicle, using a preset neural network to obtain corresponding prediction results; the preset neural network is a neural network constructed based on a three-layer bidirectional long short-term memory network;

[0026] A planning module is used to plan the driving trajectory of the current vehicle according to each of the prediction results to obtain a target driving trajectory for avoiding each of the target vehicles in the vehicle merging scenario.

[0027] In a third aspect, the present application provides an electronic device, including:

[0028] Memory, used to store computer programs;

[0029] A processor is used to execute the computer program to implement the vehicle trajectory planning method as described above.

[0030] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, which, when executed by a processor, implements the vehicle trajectory planning method as described above.

[0031] It can be seen that in this application, the current vehicle traveling on the main road can collect vehicle characteristic information of each target vehicle located in the merging area in the vehicle merging scenario; the merging area includes the main road and the ramp area that meets the preset distance condition with the main road; then, based on the road characteristic information of the vehicle merging scenario and each vehicle characteristic information, the merging intention of each target vehicle is predicted to obtain corresponding prediction results; then, according to each prediction result, the driving trajectory of the current vehicle is planned to obtain a target driving trajectory for avoiding each target vehicle in the vehicle merging scenario. In this way, in this application, the vehicle traveling on the main road can predict the intention of each target vehicle located on the ramp to merge into the main road in advance in the vehicle merging scenario, and obtain corresponding prediction results; then, combined with the prediction results, a driving trajectory that can avoid each target vehicle can be more accurately planned, thereby improving the vehicle driving safety in the vehicle merging scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0033] Figure 1 A flow chart of a vehicle trajectory planning method disclosed in this application;

[0034] Figure 2 A schematic diagram of a vehicle merging scenario disclosed in this application;

[0035] Figure 3 A schematic diagram of a network framework disclosed in this application;

[0036] Figure 4 A flow chart of a specific vehicle trajectory planning method disclosed in this application;

[0037] Figure 5 A schematic diagram of a specific network structure disclosed in this application;

[0038] Figure 6 A schematic diagram of the structure of a vehicle trajectory planning device disclosed in this application;

[0039] Figure 7 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] See also Figure 1 As shown, an embodiment of the present invention discloses a vehicle trajectory planning method, which is applied to a current vehicle traveling on a main road, comprising:

[0042] Step S11, in a vehicle merging scenario, collecting vehicle feature information of each target vehicle located in a merging area; the merging area includes a main road and a ramp area that meets a preset distance condition from the main road.

[0043] In this embodiment, in the vehicle merging scenario, the merging area may include the main road and the connected ramp area. The target vehicle located in the ramp area may merge into the main road at any time; and the current vehicle traveling on the main road can collect vehicle characteristic information of each target vehicle in the merging area in the vehicle merging scenario, so as to plan the trajectory of the current vehicle according to the vehicle characteristic information of each target vehicle.

[0044] In a specific embodiment, before collecting the vehicle characteristic information of each target vehicle located in the merging area in the vehicle merging scenario, it may also include: judging whether the current vehicle driving scenario is consistent with the preset merging scenario based on the surrounding map data of the current vehicle; if the current vehicle driving scenario is consistent with the preset merging scenario, drawing a topological map based on the surrounding map data to obtain a merging area topological map, so as to collect the vehicle characteristic information of each target vehicle located in the merging area in the vehicle merging scenario based on the merging area topological map. Specifically, when the current vehicle is driving on the main road, it can be judged based on the surrounding map data whether the current vehicle driving scenario is consistent with the preset merging scenario; the vehicle merging scenario can be as follows: Figure 2 As shown in the figure, the merging area of ​​the vehicle merging scene can be divided into three parts: Figure 2The road in the green box is the main road, the road in the red box is the ramp, and the unframed part is the acceleration and deceleration lane; it can be understood that if the scene where the current vehicle is traveling is consistent with the above-mentioned vehicle merging scene, a topological map of the corresponding merging area can be drawn based on the surrounding map data, and then the attribute values ​​of each target vehicle in the merging area can be collected, and each attribute value can be marked in the topological map, and the vehicle characteristic information of each target vehicle in the ramp area can be obtained. In a specific embodiment, the attribute values ​​of target vehicles in other lanes in the main road can also be considered, and the lane change intention of the relevant vehicle from its lane to the lane of the current vehicle is predicted, so as to plan the driving trajectory of the current vehicle and avoid dangerous situations.

[0045] In another specific embodiment, the collecting of vehicle characteristic information of each target vehicle located in the merging area in the vehicle merging scenario may include: in the vehicle merging scenario, collecting vehicle characteristic information of each target vehicle located in the merging area through a camera and / or a radar. Specifically, the current vehicle may collect attribute values ​​such as speed, acceleration, vehicle type, and heading angle information of each target vehicle located in the merging area through a camera or a radar, and finally obtain the vehicle characteristic information of each target vehicle.

[0046] Step S12: Based on the road feature information of the vehicle merging scene and the feature information of each vehicle, a preset neural network is used to predict the merging intention of each target vehicle to obtain corresponding prediction results; the preset neural network is a neural network constructed based on a three-layer bidirectional long short-term memory network.

[0047] In this embodiment, the vehicle characteristic information of each target vehicle in the vehicle merging scenario can be obtained through the above steps, and then the merging intention of each target vehicle from the ramp area to the main road can be predicted based on the road characteristic information corresponding to the vehicle merging scenario and the related vehicle characteristic information. A neural network is pre-constructed based on a three-layer long short-term memory network, and the prediction result corresponding to each target vehicle merging from the ramp into the main road can be predicted through the preset neural network.

[0048] In a specific embodiment, based on the road feature information of the vehicle merging scene and the feature information of each vehicle, a preset neural network is used to predict the merging intention of each target vehicle to obtain corresponding prediction results, which may include: performing feature extraction processing on the road feature information of the vehicle merging scene through a first bidirectional long short-term memory network to obtain a corresponding map tensor; performing feature extraction processing on the feature information of each vehicle through a second bidirectional long short-term memory network to obtain a corresponding target tensor; and performing merging intention prediction on each target vehicle through a third bidirectional long short-term memory network and using the map tensor and the target tensor to obtain corresponding prediction results. Specifically, in the process of predicting the merging intention of each target vehicle, three bidirectional long short-term memory networks are used to extract features for intention prediction; the first bidirectional long short-term memory network extracts road features and performs feature extraction processing on the road feature information of the vehicle merging scene. The input information mainly includes the topological structure of the road, and the output is the corresponding map tensor; the second bidirectional long short-term memory network extracts the features of the target vehicle. The input information mainly includes the geodetic coordinate system coordinates, lateral and longitudinal speeds, lateral and longitudinal accelerations, vehicle type, length, width, height and heading angle of the target vehicle, and finally outputs the target tensor corresponding to the target vehicle; the third bidirectional long short-term memory network can predict the intention of each target vehicle based on the map tensor and target tensor obtained by the above two long short-term memory networks, and predict the intention of each target vehicle to merge into the main road from the corresponding ramp area to obtain the corresponding prediction results. The framework of the three-layer bidirectional long short-term memory network (Bi-directionalLong Short-Term Memory, Blstm) is shown as follows: Figure 3 In a specific embodiment, the prediction result represents the probability of the target vehicle merging from the ramp area into the main road at each time point and the corresponding position point.

[0049] Step S13: planning the driving trajectory of the current vehicle according to each of the prediction results to obtain a target driving trajectory for avoiding each of the target vehicles in the vehicle merging scenario.

[0050] In this embodiment, the above steps can obtain the prediction results that each target vehicle in the vehicle merging scenario will merge into the main road from the ramp area, and then the driving trajectory of the current vehicle can be planned based on the prediction results, so that the current vehicle can avoid the target vehicles when executing the planned driving trajectory, thereby ensuring the safety of vehicle driving.

[0051] In a specific embodiment, the planning of the driving trajectory of the current vehicle according to each of the prediction results may include: marking obstacle information at the position points corresponding to each of the target vehicles at each time point according to each of the prediction results, so as to plan the driving trajectory of the current vehicle based on the obstacle information. Specifically, the prediction results of each target vehicle represent the probability of the target vehicle merging from the ramp area to the main road at each time point and the corresponding position points, and the obstacle information is marked at the position points corresponding to each of the target vehicles at each time point, and the driving trajectory of the current vehicle can be planned based on the obstacle information.

[0052] In another specific embodiment, the planning of the driving trajectory of the current vehicle according to each of the prediction results to obtain a target driving trajectory for avoiding each of the target vehicles in the vehicle merging scenario may include: planning the driving trajectory of the current vehicle based on each of the prediction results, the road characteristic information, and each of the vehicle characteristic information to obtain a target driving trajectory for avoiding each of the target vehicles in the vehicle merging scenario. Specifically, in the process of trajectory planning, the prediction results of the target vehicle, the road characteristic information of the vehicle merging scenario, and each of the vehicle characteristic information may be considered, and the driving trajectory of the current vehicle may be planned in combination with a pre-set path planning algorithm; the path planning algorithm used may be an A-star algorithm, and the trajectory of the current vehicle is planned in combination with the prediction results corresponding to each of the target vehicles to obtain a suitable safe driving trajectory that can avoid the vehicle.

[0053] It can be seen that in the present application, vehicles traveling on the main road can predict in advance the intention of each target vehicle located on the ramp to merge into the main road in the vehicle merging scenario, and use the three-layer long short-term memory network to predict the merging intention of each target vehicle in the merging area to obtain the corresponding prediction results; then, combined with the intention prediction results, it is possible to more accurately plan a driving trajectory that can avoid each target vehicle, thereby improving the vehicle driving safety in the vehicle merging scenario.

[0054] like Figure 4 As shown, the embodiment of the present application discloses a vehicle trajectory planning method, which is applied to a current vehicle traveling on a main road, and specifically includes:

[0055] In this embodiment, the current vehicle traveling on the main road can determine whether the current driving scene is a merging scene based on the high-precision map data of the surrounding environment; if it is determined that the current moment meets the vehicle merging scene, the surrounding scene information can be extracted to draw a topological map of the merging area, and then the target vehicles located in the ramp area identified by the perception camera data or radar data can be assigned to the merging area topological map; then the trajectory of each target vehicle can be predicted in combination with the topological map, and the target vehicles that conflict with the future planned trajectory of the current vehicle (self-vehicle) can be specifically analyzed to plan and adjust the trajectory of the self-vehicle. Among them, the judgment of the vehicle merging scene can be based on positioning data and high-precision map data. The main basis for judgment is whether there is a merge (the connection area between the main road and the ramp) and the distance from the merge point. It can be understood that the planned trajectory of the self-vehicle may include the x, y, z, heading angle, speed, and acceleration information of the trajectory points generated based on the self-vehicle coordinate system every 0.1 seconds in the future; the high-precision map data includes split and merge information, lane line information, lane width, and speed limit information. The positioning data includes the latitude and longitude coordinates of the self-vehicle. Perception camera data or radar data refers to the attribute values ​​detected by the target vehicle, including x, y, z, speed, acceleration, vehicle type, and heading angle information generated by the target vehicle based on the ego vehicle coordinate system. Furthermore, when allocating target vehicles on the topological map, the target vehicles are allocated based on the x, y, z and heading angle of the ego vehicle coordinate system, and only the vehicles that have a risk of collision with the ego vehicle in time and space are allocated on the topological map. For example, the distances of the ego vehicle and the target vehicle from the merging point are divided by their respective vehicle speeds to obtain t1 and t2, respectively. If the absolute value of the difference between t1 and t2 is less than 10 seconds, it is considered that there is a risk of collision. Accordingly, when predicting the merging intention of the target vehicle, the merging intention of the target vehicle within 5 seconds can be predicted (or the intention prediction can be started only when it is in the acceleration and deceleration lanes of the merging area), and the intention includes two types: the intention to merge into the main road and the intention not to merge into the main road.

[0056] In a specific embodiment, when performing intention prediction through a three-layer bidirectional long short-term memory network, such as Figure 5As shown in the figure, A participates in the forward calculation and A' participates in the reverse calculation; the final output value y depends on the sum of A and A', and several y represent the predicted position of the target in each frame. Based on these y, the target intention is counted, so that the final predicted result will be more accurate. Among them, A represents the forward prediction result, A' represents the reverse prediction result; X refers to the input of each frame, including the map tensor and the target tensor, y is the position point predicted in each frame, S represents the hidden layer of the forward operation, and S' represents the hidden layer of the reverse operation. Further, the formula for calculating A and A' and the formula for calculating y can be: y2=g(VA2+V'A'2); A'2=f(W'A'3+U'x2); A2=f(WA1+Ux2); among them, W represents the weight parameter of the forward operation, W' represents the weight parameter of the reverse operation, U is the cell state of the forward operation, and U' is the cell state of the reverse operation. f and g represent model parameters, V represents the forward splicing weight, and V' represents the reverse splicing weight. Furthermore, after predicting the trajectory of each target vehicle through the above steps, the trajectory of the ego vehicle can be planned based on the corresponding prediction results in combination with the A* algorithm; the distance between the ego vehicle and the point with the highest merging probability of the target vehicle at each time point (0.1 second interval) is calculated, and then obstacle information is assigned at this position, so that the A* algorithm can plan a suitable driving trajectory for the ego vehicle that can avoid each target vehicle in the merging scene.

[0057] It can be seen that in this application, vehicles traveling on the main road can predict in advance the intention of each target vehicle located on the ramp to merge into the main road in the vehicle merging scenario, and use the three-layer long short-term memory network to predict the merging intention of each target vehicle in the merging area to obtain the corresponding prediction results; then, combined with the intention prediction results, a more accurate driving trajectory that can avoid each target vehicle can be planned, and low-cost and low-computing-power driving trajectory planning can improve vehicle driving safety in the vehicle merging scenario.

[0058] like Figure 6 As shown, the embodiment of the present application discloses a vehicle trajectory planning device, which is applied to a current vehicle traveling on a main road, comprising:

[0059] The information collection module 11 is used to collect vehicle characteristic information of each target vehicle located in a merging area in a vehicle merging scenario; the merging area includes a main road and a ramp area that meets a preset distance condition from the main road;

[0060] The prediction module 12 is used to predict the merging intention of each target vehicle based on the road feature information of the vehicle merging scene and the feature information of each vehicle using a preset neural network to obtain corresponding prediction results; the preset neural network is a neural network constructed based on a three-layer bidirectional long short-term memory network;

[0061] The planning module 13 is used to plan the driving trajectory of the current vehicle according to each of the prediction results, and obtain a target driving trajectory for avoiding each of the target vehicles in the vehicle merging scenario.

[0062] It can be seen that in the present application, vehicles traveling on the main road can predict in advance the intention of each target vehicle located on the ramp to merge into the main road in the vehicle merging scenario, and obtain corresponding prediction results; then, combined with the prediction results, a driving trajectory that can avoid each target vehicle can be more accurately planned, thereby improving the vehicle driving safety in the vehicle merging scenario.

[0063] In a specific embodiment, the device may further include:

[0064] A scene judgment module is used to judge whether the scene in which the current vehicle is traveling matches the preset imported scene based on the surrounding map data of the current vehicle;

[0065] The merging area drawing module is used to draw a topological map based on the surrounding map data to obtain a merging area topological map when the current vehicle driving scenario is consistent with the preset merging scenario, so as to collect vehicle feature information of each target vehicle located in the merging area under the vehicle merging scenario based on the merging area topological map.

[0066] In a specific embodiment, the information collection module 11 may include:

[0067] The information collection unit is used to collect the attribute values ​​of each target vehicle located in the merging area through a camera and / or a radar in a vehicle merging scenario, and mark the attribute values ​​in the merging area topology map to obtain the vehicle characteristic information of each target vehicle.

[0068] In a specific embodiment, the prediction module 12 may include:

[0069] A first feature extraction unit is used to perform feature extraction processing on the road feature information of the scene where the vehicle merges into through a first bidirectional long short-term memory network to obtain a corresponding map tensor;

[0070] A second feature extraction unit is used to perform feature extraction processing on each of the vehicle feature information through a second bidirectional long short-term memory network to obtain a corresponding target tensor;

[0071] The intention prediction unit is used to perform an input intention prediction on each of the target vehicles by using the map tensor and the target tensor through a third bidirectional long short-term memory network to obtain corresponding prediction results.

[0072] In a specific embodiment, the planning module 13 may include:

[0073] The obstacle information marking unit is used to mark obstacle information at the position points corresponding to each target vehicle at each time point according to each prediction result, so as to plan the driving trajectory of the current vehicle based on the obstacle information.

[0074] In another specific embodiment, the planning module 13 may include:

[0075] A planning unit is used to plan the driving trajectory of the current vehicle based on each of the prediction results, the road feature information and each of the vehicle feature information, so as to obtain a target driving trajectory for avoiding each of the target vehicles in the vehicle merging scenario.

[0076] Furthermore, the present application also discloses an electronic device. Figure 7 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0077] Figure 7 A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the vehicle trajectory planning method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0078] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0079] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0080] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the vehicle trajectory planning method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks.

[0081] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the vehicle trajectory planning method disclosed above is implemented. The specific steps of the method can refer to the corresponding contents disclosed in the above embodiments, and will not be repeated here.

[0082] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0083] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0084] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0085] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0086] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A vehicle trajectory planning method, characterized in that: Applicable to current vehicles traveling on the main road, including: In a vehicle merging scenario, vehicle characteristic information of each target vehicle located in a merging area is collected; the merging area includes a main road and a ramp area that meets a preset distance condition from the main road; Based on the road feature information of the vehicle merging scene and the feature information of each vehicle, a preset neural network is used to predict the merging intention of each target vehicle to obtain corresponding prediction results; the preset neural network is a neural network constructed based on a three-layer bidirectional long short-term memory network; The driving trajectory of the current vehicle is planned according to each of the prediction results to obtain a target driving trajectory for avoiding each of the target vehicles in the vehicle merging scenario.

2. The vehicle trajectory planning method according to claim 1, characterized in that: Before collecting vehicle feature information of each target vehicle located in the merging area in the vehicle merging scenario, the method further includes: Determine whether the current vehicle driving scene matches the preset imported scene based on the surrounding map data of the current vehicle; If the current vehicle driving scenario matches the preset merging scenario, a topological map is drawn based on the surrounding map data to obtain a merging area topological map, so as to collect vehicle feature information of each target vehicle located in the merging area under the vehicle merging scenario based on the merging area topological map.

3. The vehicle trajectory planning method according to claim 2, characterized in that: The collecting of vehicle characteristic information of each target vehicle located in the merging area in the vehicle merging scenario includes: In a vehicle merging scenario, the attribute values ​​of each target vehicle located in the merging area are collected by a camera and / or a radar, and the attribute values ​​are marked in a topological map of the merging area to obtain vehicle feature information of each target vehicle.

4. The vehicle trajectory planning method according to claim 1, characterized in that: Based on the road feature information of the vehicle merging scene and the feature information of each vehicle, a preset neural network is used to predict the merging intention of each target vehicle to obtain corresponding prediction results, including: Performing feature extraction processing on the road feature information of the scene where the vehicle enters through a first bidirectional long short-term memory network to obtain a corresponding map tensor; Performing feature extraction processing on each of the vehicle feature information through a second bidirectional long short-term memory network to obtain a corresponding target tensor; The third bidirectional long short-term memory network is used to predict the merging intention of each target vehicle by using the map tensor and the target tensor to obtain corresponding prediction results.

5. The vehicle trajectory planning method according to any one of claims 1 to 4, characterized in that: The prediction result represents the probability of the target vehicle merging from the ramp area into the main road at each time point and the corresponding position point.

6. The vehicle trajectory planning method according to claim 5, characterized in that: The planning of the driving trajectory of the current vehicle according to each of the prediction results includes: According to each of the prediction results, obstacle information is marked on the position points corresponding to each of the target vehicles at each time point, so as to plan the driving trajectory of the current vehicle based on the obstacle information.

7. The vehicle trajectory planning method according to claim 5, characterized in that: The planning of the driving trajectory of the current vehicle according to each of the prediction results to obtain a target driving trajectory for avoiding each of the target vehicles in the vehicle merging scenario includes: The driving trajectory of the current vehicle is planned based on each of the prediction results, the road feature information, and each of the vehicle feature information to obtain a target driving trajectory for avoiding each of the target vehicles in the vehicle merging scenario.

8. A vehicle trajectory planning device, characterized in that: Applicable to current vehicles traveling on the main road, including: An information collection module, used to collect vehicle feature information of each target vehicle located in a merging area in a vehicle merging scenario; the merging area includes a main road and a ramp area that meets a preset distance condition from the main road; A prediction module, for predicting the merging intention of each target vehicle based on the road feature information of the vehicle merging scene and the feature information of each vehicle, using a preset neural network to obtain corresponding prediction results; the preset neural network is a neural network constructed based on a three-layer bidirectional long short-term memory network; A planning module is used to plan the driving trajectory of the current vehicle according to each of the prediction results to obtain a target driving trajectory for avoiding each of the target vehicles in the vehicle merging scenario.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the vehicle trajectory planning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the vehicle trajectory planning method as described in any one of claims 1 to 7.

Images