Vehicle Trajectory Planning Method, Device, Computer Equipment and Storage Medium

Abstract

The present application relates to a vehicle trajectory planning method, apparatus, computer device, storage medium, and computer program product. The method includes: obtaining the current speed and reference speed corresponding to at least one target traffic object; the target traffic object is a traffic object moving around the target vehicle, and the reference speed is determined based on the historical movement environment information of the target traffic object; determining an abnormal traffic object from each target traffic object based on the speed difference between the reference speed and the current speed; generating a movement loss based on the current speed and reference speed corresponding to the abnormal traffic object, and generating a current efficiency impact degree corresponding to the abnormal traffic object based on the movement loss; determining a target trajectory from each candidate trajectory corresponding to the target vehicle based on the current efficiency impact degree. Using this method can increase the efficiency evaluation time, make the evaluation more stable, and thus improve the accuracy of the trajectory efficiency evaluation of autonomous vehicles.

Description

Technical Field

[0001] The present application relates to the field of computer technologies, and particularly to a vehicle trajectory planning method, apparatus, computer device, storage medium, and computer program product. Background Art

[0002] With the development of computer technologies, autonomous driving technologies have emerged. Autonomous driving technologies adopt advanced communication, computer, network, and control technologies, enabling computer devices to automatically and safely operate vehicles without any active operation by humans.

[0003] In traditional technologies, when performing trajectory planning for a vehicle, usually the self-information of the trajectory is evaluated. For example, the speed, length, time taken, etc. of candidate trajectories are evaluated, and a target trajectory is determined from multiple candidate trajectories based on the evaluation results. However, determining the target trajectory only based on the self-information of the trajectory has limited reference information and there is a problem of inaccurate trajectory planning. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a vehicle trajectory planning method, apparatus, computer device, computer-readable storage medium, and computer program product that can improve the accuracy of trajectory planning.

[0005] The present application provides a vehicle trajectory planning method. The method includes:

[0006] Obtain the current speed and reference speed of at least one target traffic object; the target traffic object is a traffic object moving around the target vehicle, and the reference speed is determined based on the historical motion environment information of the target traffic object;

[0007] Determine an abnormal traffic object from each target traffic object based on the speed difference between the reference speed and the current speed;

[0008] Generate a motion loss based on the current speed and reference speed of the abnormal traffic object, and generate a current efficiency impact degree corresponding to the abnormal traffic object based on the motion loss;

[0009] Determine an intermediate trajectory corresponding to the abnormal traffic object from each candidate trajectory corresponding to the target vehicle, and generate trajectory efficiency information corresponding to the intermediate trajectory based on the current efficiency impact degree;

[0010] Determine a target trajectory from each candidate trajectory based on the trajectory efficiency information.

[0011] The present application also provides a vehicle trajectory planning apparatus. The apparatus includes:

[0012] A speed acquisition module, configured to acquire the current speed and the reference speed corresponding to at least one target traffic object; the target traffic object is a traffic object moving around the target vehicle, and the reference speed is determined based on the historical motion environment information of the target traffic object;

[0013] An abnormal traffic object determination module, configured to determine an abnormal traffic object from each target traffic object based on the speed difference between the reference speed and the current speed;

[0014] A current efficiency impact calculation module, configured to generate a motion loss based on the current speed and the reference speed corresponding to the abnormal traffic object, and generate the current efficiency impact corresponding to the abnormal traffic object based on the motion loss;

[0015] A trajectory efficiency information determination module, configured to determine an intermediate trajectory corresponding to the abnormal traffic object from each candidate trajectory corresponding to the target vehicle, and generate trajectory efficiency information corresponding to the intermediate trajectory based on the current efficiency impact;

[0016] A target trajectory determination module, configured to determine a target trajectory from each candidate trajectory based on the trajectory efficiency information.

[0017] A computer device, comprising a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above vehicle trajectory planning method are implemented.

[0018] A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above vehicle trajectory planning method are implemented.

[0019] A computer program product, comprising a computer program, and when the computer program is executed by a processor, the steps of the above vehicle trajectory planning method are implemented.

[0020] The above vehicle trajectory planning method, device, computer device, storage medium, and computer program product obtain the current speed and reference speed corresponding to at least one target traffic object; the target traffic object is a traffic object moving around the target vehicle, and the reference speed is determined based on the historical movement environment information of the target traffic object; based on the speed difference between the reference speed and the current speed, determine the abnormal traffic object from each target traffic object; based on the current speed and reference speed corresponding to the abnormal traffic object, generate a movement loss, and generate the current efficiency impact degree corresponding to the abnormal traffic object based on the movement loss; determine the intermediate trajectory corresponding to the abnormal traffic object from each candidate trajectory corresponding to the target vehicle, generate the trajectory efficiency information corresponding to the intermediate trajectory based on the current efficiency impact degree, and determine the target trajectory from each candidate trajectory based on the trajectory efficiency information. In this way, the target traffic object is a traffic object moving around the target vehicle. Based on the speed difference between the current speed and the reference speed corresponding to the target traffic object, the abnormal traffic object can be determined from the target traffic objects. The abnormal traffic object can have a greater impact on the driving of the target vehicle. When planning the driving trajectory of the target vehicle, referring to the relevant information of the abnormal traffic object can effectively improve the accuracy of trajectory planning. Further, the movement loss can be generated based on the current speed and reference speed corresponding to the abnormal traffic object, the current efficiency impact degree corresponding to the abnormal traffic object can be generated based on the movement loss, the current efficiency impact degree can reflect the impact degree of the abnormal traffic object on the trajectory efficiency of the driving trajectory of the target vehicle, the trajectory efficiency information of the candidate trajectory corresponding to the abnormal traffic object can be generated based on the current efficiency impact degree, and the target trajectory can be determined from each candidate trajectory corresponding to the target vehicle based on the trajectory efficiency information, which can effectively improve the accuracy of trajectory planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is an application environment diagram of the vehicle trajectory planning method in an embodiment;

[0022] Figure 2 It is a flowchart of the vehicle trajectory planning method in an embodiment;

[0023] Figure 3 It is a schematic diagram for determining whether a traffic object is a reference traffic object in an embodiment;

[0024] Figure 4 It is an image of the speed change of a traffic participant in an embodiment;

[0025] Figure 5 It is a flowchart of determining the trajectory efficiency information corresponding to the intermediate trajectory in an embodiment;

[0026] Figure 6 It is a schematic diagram for determining whether an abnormal traffic object affects the trajectory in an embodiment;

[0027] Figure 7 is a structural block diagram of a vehicle trajectory planning device in an embodiment;

[0028] Figure 8 is an internal structure diagram of a computer device in an embodiment;

[0029] Figure 9 is an internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0030] In order to make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0031] The vehicle trajectory planning method provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or other network servers. The terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart TVs, smart vehicle-mounted devices, etc. The portable wearable devices can be smart watches, smart head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster or a cloud server composed of multiple servers. The terminal 102 and the server 104 can be directly or indirectly connected through wired or wireless communication methods, and the present application does not make any restrictions here.

[0032] Both the terminal and the server can be separately used to execute the vehicle trajectory planning method provided in the embodiments of the present application.

[0033] For example, the terminal obtains the current speed and the reference speed corresponding to at least one target traffic object, and determines the abnormal traffic object from each target traffic object based on the speed difference between the reference speed and the current speed. Among them, the target traffic object is a traffic object moving around the target vehicle, and the reference speed is determined based on the historical movement environment information corresponding to the target traffic object. The terminal generates a movement loss based on the current speed and the reference speed corresponding to the abnormal traffic object, generates the current efficiency influence degree corresponding to the abnormal traffic object based on the movement loss, determines the intermediate trajectory corresponding to the abnormal traffic object from each candidate trajectory corresponding to the target vehicle, and generates the trajectory efficiency information corresponding to the intermediate trajectory based on the current efficiency influence degree. The terminal determines the target trajectory from each candidate trajectory based on the trajectory efficiency information.

[0034] The terminal and the server can also cooperate to execute the vehicle trajectory planning method provided in the embodiments of the present application.

[0035] For example, the terminal sends a vehicle trajectory planning request to the server. The server obtains the current speed and the reference speed corresponding to at least one target traffic object, and determines the abnormal traffic object from each target traffic object based on the speed difference between the reference speed and the current speed. Among them, the target traffic object is a traffic object moving around the target vehicle, and the reference speed is determined based on the historical motion environment information corresponding to the target traffic object. The server generates a motion loss based on the current speed and the reference speed corresponding to the abnormal traffic object, generates the current efficiency impact degree corresponding to the abnormal traffic object based on the motion loss, determines the intermediate trajectory corresponding to the abnormal traffic object from each candidate trajectory corresponding to the target vehicle, and generates the trajectory efficiency information corresponding to the intermediate trajectory based on the current efficiency impact degree. The server determines the target trajectory from each candidate trajectory based on the trajectory efficiency information. The server sends the target trajectory to the terminal. The terminal can display the target trajectory or drive according to the target trajectory.

[0036] In one embodiment, the terminal 102 can be installed with an application capable of implementing vehicle trajectory planning. The server 104 can be the background server of the vehicle trajectory planning application installed in the terminal 102. In one embodiment, the terminal 102 is the target vehicle.

[0037] In one embodiment, as Figure 2 shown, a vehicle trajectory planning method is provided. Taking the application of this method to a computer device as an example for description, the computer device can be a terminal or a server, and includes the following steps:

[0038] Step S202, obtaining the current speed and the reference speed corresponding to at least one target traffic object; the target traffic object is a traffic object moving around the target vehicle, and the reference speed is determined based on the historical motion environment information of the target traffic object.

[0039] Among them, the traffic object refers to an object that can move on the road. For example, pedestrians, non-motor vehicles, sprinkler trucks, buses, private cars, etc. The target vehicle refers to the vehicle that needs to perform trajectory planning. The target traffic object is a traffic object moving around the target vehicle. For example, if the distance between the traffic object and the target vehicle is within a preset range, then the traffic object is the target traffic object.

[0040] The current speed corresponding to the target traffic object refers to the speed of the target traffic object in the current time period, which can reflect the current movement condition of the target traffic object. The reference speed corresponding to the target traffic object is determined based on the historical movement environment information corresponding to the target traffic object, which can reflect the past movement condition of the target traffic object. The historical movement environment information is used to reflect the movement environment of the target traffic object in the historical time period, and the historical movement environment information may include at least one of the movement information corresponding to the surrounding moving objects of the target traffic object or the traffic speed limit information corresponding to the target traffic object in the historical time period.

[0041] Specifically, when the computer device performs trajectory planning on the target vehicle, it can obtain the traffic objects moving around the target vehicle as the target traffic objects, obtain the current speed and the reference speed corresponding to at least one target traffic object, and perform trajectory planning with reference to the current speed and the reference speed corresponding to the target traffic object, so as to improve the accuracy of trajectory planning.

[0042] Step S204: Determine the abnormal traffic objects from each target traffic object based on the speed difference between the reference speed and the current speed.

[0043] Among them, the abnormal traffic object refers to the target traffic object whose current movement condition and historical movement condition have a large difference.

[0044] Specifically, after the computer device obtains the current speed and the reference speed of each target traffic object corresponding to the target vehicle, it compares the current speed and the reference speed of the same target traffic object, and determines the abnormal traffic objects from each target traffic object based on the speed difference between the reference speed and the current speed. For example, the target traffic object with a speed difference greater than the preset difference can be determined as the abnormal traffic object. It can be understood that if the speed difference between the reference speed and the current speed is large, it indicates that there is a large difference between the current movement condition and the historical movement condition of the target traffic object, and the target traffic object has an abnormal condition. Such a target traffic object will have a certain impact on the driving of the target vehicle. Such a target traffic object can be used as an abnormal traffic object, and then referring to the relevant information of the abnormal traffic object when performing trajectory planning on the target vehicle can effectively improve the accuracy of trajectory planning.

[0045] Step S206: Generate a movement loss based on the current speed and the reference speed corresponding to the abnormal traffic object, and generate the current efficiency influence degree corresponding to the abnormal traffic object based on the movement loss.

[0046] Among them, the motion loss refers to the loss caused by the abnormal traffic object traveling at the current speed and the reference speed, which is used to reflect the motion difference of the abnormal traffic object in the past and present. The current efficiency impact degree refers to the impact degree of the abnormal traffic object on the trajectory efficiency of the target vehicle's driving trajectory, which is used to reflect the impact degree of the abnormal traffic object on the trajectory efficiency of the target vehicle's driving trajectory.

[0047] Specifically, after determining the abnormal traffic object, the computer device can calculate the motion loss based on the current speed and the reference speed corresponding to the abnormal traffic object. For example, it can calculate the speed difference between the current speed and the reference speed corresponding to the abnormal traffic object, and obtain the motion loss based on the speed difference. Furthermore, the computer device can calculate the current efficiency impact degree corresponding to the abnormal traffic object based on the motion loss. The computer device can use a variety of methods to calculate the current efficiency impact degree based on the motion loss. For example, it can directly use the motion loss as the current efficiency impact degree; it can use the product of the motion loss and a preset value as the current efficiency impact degree; and so on.

[0048] Step S208: Determine the intermediate trajectory corresponding to the abnormal traffic object from each candidate trajectory corresponding to the target vehicle, and generate trajectory efficiency information corresponding to the intermediate trajectory based on the current efficiency impact degree.

[0049] Among them, the candidate trajectory refers to the driving trajectories available for selection by the target vehicle. The intermediate trajectory refers to the candidate trajectory corresponding to the abnormal traffic object, that is, the candidate trajectory that will be affected by the abnormal traffic object. The trajectory efficiency information is used to characterize the driving efficiency of the vehicle on this trajectory and to characterize the trajectory efficiency of the driving trajectory.

[0050] Specifically, after determining the current efficiency impact degree corresponding to the abnormal traffic object, the computer device can determine the target trajectory from each candidate trajectory corresponding to the target vehicle based on the current efficiency impact degree. First, the computer device can determine the intermediate trajectory corresponding to the abnormal traffic object from each candidate trajectory corresponding to the target vehicle. For example, it can use the candidate trajectory that overlaps with the driving trajectory of the abnormal traffic object as the intermediate trajectory corresponding to the abnormal traffic object; it can use the candidate trajectory that is in the same motion direction as the abnormal traffic object as the intermediate trajectory corresponding to the abnormal traffic object; it can use the candidate trajectory that makes the absolute distance between the abnormal traffic object and the target vehicle less than a preset distance as the intermediate trajectory corresponding to the abnormal traffic object; and so on. Furthermore, the computer device can generate trajectory efficiency information corresponding to the intermediate trajectory based on the current efficiency impact degree corresponding to the abnormal traffic object. For example, it can use the current efficiency impact degree as the trajectory efficiency information; it can perform a scaling process on the current efficiency impact degree to obtain the trajectory efficiency information; and so on.

[0051] Step S210: Determine the target trajectory from each candidate trajectory based on the trajectory efficiency information.

[0052] Among them, the target trajectory refers to the driving trajectory finally determined by the target vehicle.

[0053] Specifically, after determining the trajectory efficiency information corresponding to the intermediate trajectory, the computer device can determine the target trajectory from each candidate trajectory based on the trajectory efficiency information. For example, if the smaller the trajectory efficiency information indicates the higher the trajectory efficiency, the candidate trajectory with the smallest trajectory efficiency information is used as the target trajectory. After determining the target trajectory, the computer device can instruct the target vehicle to drive according to the target trajectory to improve the driving efficiency of the target vehicle.

[0054] It can be understood that, in addition to the intermediate trajectory, the trajectory efficiency information of other candidate trajectories can be preset efficiency information or calculated based on a custom formula or algorithm.

[0055] In one embodiment, the candidate trajectories can be divided into a first type of trajectory and a second type of trajectory. The first type of trajectory is the intermediate trajectory, which refers to the candidate trajectory that will be affected by abnormal traffic objects. The second type of trajectory refers to the candidate trajectory that will not be affected by abnormal traffic objects. The computer device can generate the trajectory efficiency information corresponding to the corresponding first type of trajectory based on the current efficiency influence degree of the corresponding abnormal traffic object, and generate the trajectory efficiency information corresponding to the second type of trajectory based on the trajectory efficiency information corresponding to the first type of trajectory. The trajectory efficiency indicated by the trajectory efficiency information corresponding to the second type of trajectory is higher than the trajectory efficiency indicated by the trajectory efficiency information corresponding to the first type of trajectory. For example, the candidate trajectories include trajectory A and trajectory B. Trajectory A is the first type of trajectory, and trajectory B is the second type of trajectory. The trajectory efficiency information corresponding to trajectory A is generated based on the current efficiency influence degree of the abnormal traffic object that affects trajectory A, and the trajectory efficiency information corresponding to trajectory B is generated based on the trajectory efficiency information corresponding to trajectory A. If the smaller the trajectory efficiency information indicates the higher the trajectory efficiency, at this time, the trajectory efficiency information corresponding to trajectory B should be less than the trajectory efficiency information corresponding to trajectory A.

[0056] It can be understood that, compared with the first type of trajectory, the target vehicle is not affected by abnormal traffic objects when driving on the second type of trajectory. Therefore, the trajectory efficiency of the second type of trajectory is higher than that of the first type of trajectory.

[0057] In one embodiment, the target vehicle is an autonomous vehicle, and the candidate trajectories are generated by the trajectory planning module of the autonomous vehicle. Candidate trajectories can be generated for the autonomous vehicle at regular intervals. Multiple candidate trajectories can be generated in each planning cycle, and the target trajectory is determined from each candidate trajectory based on the trajectory efficiency information within each trajectory cycle. Further, in addition to the trajectory efficiency information, other information can also be combined to comprehensively determine the target trajectory from each candidate trajectory. For example, the target trajectory can be determined from each candidate trajectory based on the trajectory efficiency information, trajectory safety information, and trajectory comfort information, and the trajectory evaluation is comprehensively carried out from three aspects of safety, comfort, and efficiency to help the target vehicle make a final trajectory selection.

[0058] In the above vehicle trajectory planning method, the current speed and the reference speed corresponding to at least one target traffic object are obtained; the target traffic object is a traffic object moving around the target vehicle, and the reference speed is determined based on the historical motion environment information of the target traffic object; based on the speed difference between the reference speed and the current speed, the abnormal traffic object is determined from each target traffic object; based on the current speed and the reference speed corresponding to the abnormal traffic object, the motion loss is generated, and the current efficiency impact degree corresponding to the abnormal traffic object is generated based on the motion loss; the intermediate trajectory corresponding to the abnormal traffic object is determined from each candidate trajectory corresponding to the target vehicle, the trajectory efficiency information corresponding to the intermediate trajectory is generated based on the current efficiency impact degree, and the target trajectory is determined from each candidate trajectory based on the trajectory efficiency information. In this way, the target traffic object is a traffic object moving around the target vehicle. Based on the speed difference between the current speed and the reference speed corresponding to the target traffic object, the abnormal traffic object can be determined from the target traffic objects. The abnormal traffic object can have a greater impact on the driving of the target vehicle. When planning the driving trajectory of the target vehicle, referring to the relevant information of the abnormal traffic object can effectively improve the accuracy of trajectory planning. Further, the motion loss can be generated based on the current speed and the reference speed corresponding to the abnormal traffic object, and the current efficiency impact degree corresponding to the abnormal traffic object is generated based on the motion loss. The current efficiency impact degree can reflect the degree of influence of the abnormal traffic object on the trajectory efficiency of the driving trajectory of the target vehicle. The trajectory efficiency information of the candidate trajectory corresponding to the abnormal traffic object is generated based on the current efficiency impact degree, and the target trajectory is determined from each candidate trajectory corresponding to the target vehicle based on the trajectory efficiency information, which can effectively improve the accuracy of trajectory planning.

[0059] In one embodiment, step S202 includes:

[0060] Obtain a traffic object that is within the target range of the distance from the current target traffic object in the historical time period and has the same movement direction as the current target traffic object as the reference traffic object corresponding to the current target traffic object; the target range increases as the historical speed of the current target traffic object in the historical time period increases, and there is no traffic barrier object between the current target traffic object and the reference traffic object; count the movement speed of the reference traffic object in the historical time period to obtain the reference sub-speed corresponding to the current target traffic object in the historical time period; based on the reference sub-speed corresponding to the current target traffic object in the historical time period, obtain the reference speed corresponding to the current target traffic object.

[0061] Among them, the current target traffic object refers to the target traffic object being currently processed. The current target traffic object can be any target traffic object. The reference traffic object refers to a traffic object that has the same movement direction as the target traffic object, moves within the target range of the target traffic object, and there is no traffic barrier object between it and the target traffic object. The traffic barrier object refers to an object such as a traffic light, a sidewalk, and a stop sign that can block traffic objects.

[0062] Specifically, the computer device can count the movement speeds of the traffic objects moving around the target traffic object in the historical time period to generate the reference speed corresponding to the target traffic object.

[0063] First, the computer device can use a traffic object that has the same movement direction as the current target traffic object, moves within the target range of the current target traffic object, and there is no traffic barrier object between it and the current target traffic object as the reference traffic object corresponding to the current target traffic object. It can be understood that when a traffic object around a certain target traffic object can be used as its reference traffic object, the following conditions should be met: 1. The absolute distance between the surrounding traffic object of the target traffic object and the target traffic object cannot exceed the distance threshold, and the distance threshold is positively correlated with the historical speed of the target traffic object in the historical time period. For example, as Figure 3 (a) shows, when the absolute distance between the surrounding traffic object of the target traffic object and the target traffic object exceeds the distance threshold, it indicates that the surrounding traffic object is too far from the current target traffic object to have an impact on the current target traffic object, so such a surrounding traffic object cannot be used as its reference traffic object. 2. The surrounding traffic object of the target traffic object and the target traffic object cannot be blocked by a traffic barrier object. For example, as Figure 3 (b) shows, the surrounding traffic object of the target traffic object and the target traffic object are blocked by a red light. If the target traffic object is behind the red light, the surrounding traffic object before the red light cannot be used as its reference traffic object. 3. The surrounding traffic object of the target traffic object should have the same movement intention as the target traffic object. For example, as Figure 3As shown in (c), the motion intention of the target traffic object is to go straight forward, and the surrounding traffic objects turning right cannot be used as its reference traffic objects. The reference traffic objects of the target traffic object can be referred to as the reference traffic flow around the target traffic object, and the other surrounding traffic objects of the target traffic object can be referred to as the non-reference traffic flow around the target traffic object. In addition, there can be at least one reference traffic object for a target traffic object.

[0064] Furthermore, the computer device statistically analyzes the motion speeds of the reference traffic objects in the historical time period, and based on the motion speeds of the reference traffic objects in the historical time period, obtains the reference sub-speeds corresponding to the current target traffic object in the historical time period. For example, the average value of the motion speeds of each reference traffic object in the historical time period can be calculated as the reference sub-speed; the weighted average value of the motion speeds of each reference traffic object in the historical time period can be calculated as the reference sub-speed, and the weight corresponding to the reference traffic object can be determined according to the distance between the reference traffic object and the current target traffic object. The closer the distance, the greater the weight; and so on. It can be understood that the computer device can obtain the motion speeds of each traffic object on the road through sensors installed on the target vehicle, sensors installed on the roadside, or from other devices. As Figure 4 shown, the reference traffic objects existing around a certain target traffic object include: a sprinkler truck, a bus, and a non-motor vehicle. Figure 4 shows the motion speeds of each reference traffic object in the historical time period. When the bus stops at a station, it will show a trend of first decelerating to 0 and then accelerating. The sprinkler truck usually travels at a nearly constant speed and keeps a low speed. Non-motor vehicles (such as bicycles) usually have large speed fluctuations, but generally maintain a low speed.

[0065] Finally, the computer device can obtain the reference speed corresponding to the current target traffic object based on the reference sub-speeds corresponding to the current target traffic object in the historical time period. For example, the reference sub-speed is used as the reference speed.

[0066] In the above embodiments, a traffic object that is within a target range from the current target traffic object during a historical time period, has the same moving direction as the current target traffic object, and has no traffic obstacle object between it and the current target traffic object is obtained as the reference traffic object corresponding to the current target traffic object. Obtaining a traffic object that can have a significant impact on the target traffic object as the reference traffic object through various restrictive conditions helps improve the accuracy of determining the reference speed of the target traffic object. The target range increases as the historical speed of the current target traffic object in the historical time period increases. The greater the moving speed of the target traffic object, the larger the selection range of the reference traffic object, which helps further improve the accuracy of determining the reference speed of the target traffic object. The moving speeds of the reference traffic objects during the historical time period are statistically analyzed to obtain the reference sub-speed corresponding to the current target traffic object during the historical time period. Based on the reference sub-speed corresponding to the current target traffic object during the historical time period, the reference speed corresponding to the current target traffic object is obtained. In this way, the historical speeds of the reference traffic objects can effectively reflect the speeds of the vehicle flow around the target traffic object. Determining the reference speed of the current target traffic object based on the moving speeds of the reference traffic objects during the historical time period can effectively improve the accuracy of the reference speed, and thus help improve the accuracy of trajectory planning.

[0067] In one embodiment, a vehicle trajectory planning method includes:

[0068] When there is no reference traffic object for the current target traffic object during the historical time period, based on the traffic speed limit information of the current target traffic object during the historical time period, the reference sub-speed corresponding to the current target traffic object during the historical time period is obtained.

[0069] Among them, the traffic speed limit information is used to limit the moving speed of traffic objects, and specifically may include the speed limit information brought by roads and objects on the roads. For example, the traffic speed limit information includes the legal speed limit of the road and the speed limits brought by objects with road semantic information. The speed limits brought by objects with road semantic information include the speed limits brought by traffic lights and the deceleration brought by stop signs, etc.

[0070] Specifically, if there is no reference traffic object for the current target traffic object during the historical time period, the computer device may calculate the reference sub-speed according to the traffic speed limit information existing on the driving road where the current target traffic object is located during the historical time period. For example, the minimum value of each speed in the traffic speed limit information may be used as the reference sub-speed; the speeds in the traffic speed limit information may be sorted from small to large, and the average value of at least two speeds ranked at the front may be calculated as the reference sub-speed; and so on.

[0071] In the above embodiments, if there is no reference traffic object for the current target traffic object in the historical time period, in order to avoid the reference sub-speed being empty, the reference sub-speed of the current target traffic object can be calculated through the traffic speed limit information existing on the road where the current target traffic object is located in the historical time period. Moreover, the traffic speed limit information can reflect the movement condition of the target traffic object from the side, and the reference sub-speed determined based on the traffic speed limit information also has a certain degree of accuracy, which also helps to effectively improve the accuracy of trajectory planning.

[0072] In one embodiment, obtaining the reference speed corresponding to the current target traffic object based on the reference sub-speed corresponding to the current target traffic object in the historical time period includes:

[0073] Obtaining the reference sub-speeds respectively corresponding to the current target traffic object in at least two historical time periods; generating a speed weight for the reference sub-speed corresponding to the historical time period based on the time difference between the historical time period and the current time period; the speed weight decreases as the time difference increases; and fusing the reference sub-speeds based on the speed weights of the respective reference sub-speeds to obtain the reference speed corresponding to the current target traffic object.

[0074] Specifically, in order to improve the accuracy of the reference speed, the computer device can obtain the reference sub-speeds respectively corresponding to the current target traffic object in at least two historical time periods, and perform weighted fusion on the respective reference sub-speeds to generate the reference speed corresponding to the target traffic object. The computer device obtains the reference sub-speeds respectively corresponding to the current target traffic object in at least two historical time periods, and generates the speed weights corresponding to the reference sub-speeds corresponding to the respective historical time periods according to the time differences between the respective historical time periods and the current time period. It can be understood that the closer the historical time period is to the current time period, the higher the reference value of the data reflected, and the farther the historical time period is from the current time period, the lower the reference value of the data reflected. Therefore, the speed weight can decrease as the time difference increases. Then, the computer device performs weighted averaging on the respective reference sub-speeds based on the speed weights corresponding to the respective reference sub-speeds to obtain the final reference speed of the target traffic object.

[0075] In one embodiment, the speed weight can be calculated by the following formula:

[0076] N = T / delta_t

[0077] t i = t O - i * delta_t

[0078] W i = 2 * (N - i) / (N * (N + 1))

[0079] Among them, T is the statistical duration of the reference speed, and delta_t is the statistical period. For example, the reference sub-speed is statistically calculated every 10 seconds, and the reference speed is calculated based on the respective reference sub-speeds in the past 5 minutes. Then delta_t is 10 seconds and T is 5 minutes. N is the total number of time frames, t0 is the current moment, and t i is a certain past moment, representing the past moment that is i statistical periods away from the current moment, and W i is for t i corresponding speed weight.

[0080] In one embodiment, the computer device calculates the speeds of the respective reference traffic objects corresponding to the target traffic object at every preset time interval. For example, the preset time interval can be 0.1 s. At the same time, the computer device calculates the average value of the speeds of all the reference traffic objects as the reference sub-speed of the target traffic object. The computer device statistically calculates the weighted average value of all the reference sub-speeds of the target traffic object in a certain past time period as the reference speed.

[0081] In the above embodiment, different speed weights are assigned to the reference sub-speeds corresponding to the respective historical time periods according to the differences between the respective historical time periods and the current time period. The closer the historical time period is to the current time period, the higher the speed weight of the reference sub-speed corresponding to it. The respective reference sub-speeds are weighted and averaged to obtain the final reference speed of the target traffic object. The reference speed calculated in this way has high accuracy and helps to improve the accuracy of trajectory planning.

[0082] In one embodiment, step S204 includes:

[0083] Based on the ratio between the speed difference and the reference speed corresponding to the same target traffic object, the speed difference ratios respectively corresponding to the respective target traffic objects are obtained; the target traffic objects with speed difference ratios greater than the preset ratio are used as abnormal traffic objects.

[0084] Among them, the speed difference corresponding to the target traffic object refers to the difference between the reference speed and the current speed of the target traffic object. The preset ratio refers to the threshold of the speed difference ratio when determining whether the target traffic object is an abnormal traffic object. When the speed difference ratio is greater than this threshold, it is determined that the target traffic object is an abnormal traffic object. The preset ratio is a preset ratio threshold and can be specifically set according to actual needs.

[0085] Specifically, the computer device obtains the reference speed and the current speed corresponding to the target traffic object, calculates the ratio of the speed difference determined by the reference speed and the current speed to the reference speed as the speed difference ratio. When the speed difference ratio corresponding to a certain target traffic object is greater than the preset ratio, it indicates that the current motion situation of the target traffic object is quite different from the historical motion situation. Therefore, it is determined that the target traffic object is an abnormal traffic object.

[0086] In one embodiment, an abnormal traffic object can be determined by the following formula:

[0087]

[0088]

[0089] where V ref is the reference speed of the target traffic object, V1 is the current speed of the target traffic object, represents the speed difference ratio, and T is the threshold of the speed difference ratio when determining whether the target traffic object is an abnormal traffic object.

[0090] When result > 0, it is determined that the target traffic object is an abnormal traffic object.

[0091] In the above embodiment, by comparing the ratio between the speed difference corresponding to the target traffic object and the reference speed with the preset ratio to determine whether the target traffic object is an abnormal traffic object, it is possible to quickly determine whether the target traffic object is an abnormal traffic object.

[0092] In one embodiment, based on the current speed and the reference speed corresponding to the abnormal traffic object, a motion loss is generated, including:

[0093] Based on the current speed of the abnormal traffic object and the preset time period, the first displacement corresponding to the abnormal traffic object is calculated. Based on the reference speed of the abnormal traffic object and the preset time period, the second displacement corresponding to the abnormal traffic object is calculated. Based on the first displacement and the second displacement, a motion loss is generated.

[0094] Wherein, the preset time period is a time period set in advance and can be set according to actual needs. In one embodiment, the preset time period can be the planning period of the vehicle trajectory. The first displacement refers to the distance that the abnormal traffic object can travel at the current speed within the preset time period. The second displacement refers to the distance that the abnormal traffic object can travel at the reference speed within the preset time period.

[0095] Specifically, the computer device obtains the current speed and the reference speed of the abnormal traffic object, calculates the first displacement and the second displacement obtained by the abnormal traffic object traveling at the current speed and the reference speed respectively within the preset time period, and finally generates a motion loss based on the first displacement and the second displacement. For example, taking the position difference between the first displacement and the second displacement as the motion loss; taking the ratio of the position difference between the first displacement and the second displacement to the second displacement as the motion loss; and so on.

[0096] In the above embodiments, based on the current speed of the abnormal traffic object and a preset time period, the first displacement corresponding to the abnormal traffic object is calculated, and based on the reference speed of the abnormal traffic object and the preset time period, the second displacement corresponding to the abnormal traffic object is calculated; based on the first displacement and the second displacement, a motion loss is generated. In this way, the loss generated by the first displacement and the second displacement can reflect the motion difference of the abnormal traffic object in the past and the present, and such a motion loss helps to improve the accuracy of calculating the current efficiency impact degree subsequently.

[0097] In one embodiment, generating the current efficiency impact degree corresponding to the abnormal traffic object based on the motion loss includes:

[0098] Obtaining the statistical count of the historical efficiency impact degree corresponding to the abnormal traffic object; generating a loss weight based on the statistical count; the loss weight increases as the statistical count increases and approaches a target value; generating the current efficiency impact degree based on the loss weight and the motion loss.

[0099] Wherein, the historical efficiency impact degree refers to the efficiency impact degree calculated for the abnormal traffic object in a historical time period. The computer device can calculate the efficiency impact degree corresponding to the abnormal traffic object at regular intervals. When calculating the current efficiency impact degree, the previously calculated efficiency impact degree is the historical efficiency impact degree. For example, the efficiency impact degree is calculated once for an abnormal traffic object in each trajectory cycle, and as the number of planning cycles increases, the statistical count of the historical efficiency impact degree also increases.

[0100] Specifically, when generating the current efficiency impact degree based on the motion loss, the calculation count of the efficiency impact degree can be referred to improve the accuracy of the current efficiency impact degree. After obtaining the motion loss corresponding to the abnormal traffic object, the computer device calculates the loss weight based on the statistical count of the historical efficiency impact degree corresponding to the abnormal traffic object. The loss weight increases as the statistical count increases, that is, the more times the efficiency impact degree is calculated, the higher the loss weight. And the loss weight approaches the target value as the statistical count increases, that is, the more times the efficiency impact degree is calculated, the loss weight does not increase blindly and will gradually smooth out and approach the target value. After obtaining the loss weight corresponding to the abnormal traffic object, the computer device calculates the current efficiency impact degree corresponding to the abnormal traffic object based on the loss weight and the motion loss. For example, taking the product of the loss weight and the motion loss as the current efficiency impact degree; taking the product of the loss weight and the motion loss plus a constant value as the current efficiency impact degree; and so on.

[0101] In one embodiment, the motion loss and the current efficiency impact degree can be calculated through the following formula:

[0102]

[0103]

[0104] Among them, i - 1 is the statistical count of the historical efficiency influence degree corresponding to the abnormal traffic object, J i is the motion loss, V ref is the reference speed of the target traffic object, V i is the current speed of the target traffic object. t i The time length of is a fixed parameter, mainly determined by the time period of the object's predicted trajectory (i.e., the trajectory planning period). For example, t i The time length of can be 5s. cost i is the efficiency influence degree calculated for the i-th time corresponding to the abnormal traffic object (which can also be called the current efficiency influence degree). γ is the ratio of the historical efficiency influence degree and the current efficiency influence degree, and it is a fixed value. For example, γ can be the fixed value 0.5. It can be understood that when i is larger, cost i will be closer to J i When i is gradually accumulated, the cost i term will gradually tend to J i to ensure that the data is smooth and will not increase infinitely with the increase of time accumulation.

[0105] In the above embodiment, the computer device generates a loss weight based on the statistical count of the historical efficiency influence degree corresponding to the abnormal traffic object, and performs a weighted calculation of the loss weight and the motion loss to obtain the current efficiency influence degree. When the statistical count is gradually accumulated, the current efficiency influence degree will gradually tend to the motion loss, which can ensure that the value of the current efficiency influence degree is smoother and will not increase with the increase of the accumulation times, improving the accuracy of the current efficiency influence degree, and further helping to effectively improve the accuracy of trajectory planning.

[0106] In one embodiment, as Figure 5 shown, step S208 includes:

[0107] Step S502, based on the current motion information of the abnormal traffic object, determine the corresponding intermediate trajectory from each candidate trajectory to obtain the intermediate trajectories corresponding to each abnormal traffic object respectively.

[0108] Step S504, generate trajectory efficiency information based on the current efficiency influence degrees of each abnormal traffic object corresponding to the same intermediate trajectory to obtain the trajectory efficiency information corresponding to each intermediate trajectory respectively.

[0109] Among them, the current motion information refers to the motion information of the abnormal traffic object at present, which is used to reflect the current motion condition of the abnormal traffic object. The current motion information may specifically include at least one of the driving trajectory, motion intention, whether there is a traffic barrier object between the abnormal traffic object and the target vehicle, and the distance between the abnormal traffic object and the target vehicle. The intermediate trajectory refers to the trajectory among the candidate trajectories of the target vehicle that is affected by the abnormal traffic object.

[0110] Specifically, the computer device acquires the current motion information of all abnormal traffic objects corresponding to the target vehicle and the candidate trajectories of the target vehicle, and determines whether each abnormal traffic object affects the candidate trajectories of the target vehicle. When the computer device determines that an abnormal traffic object affects a candidate trajectory of the target vehicle, it determines the candidate trajectory as the intermediate trajectory corresponding to the abnormal traffic object. A candidate trajectory may be affected by at least one abnormal traffic object. Therefore, when calculating the trajectory efficiency information, based on the current efficiency influence degrees of each abnormal traffic object corresponding to the same intermediate trajectory, the trajectory efficiency information corresponding to one intermediate trajectory is generated, and finally, the trajectory efficiency information corresponding to each intermediate trajectory can be obtained. For example, for an intermediate trajectory, the average value of the current efficiency influence degrees of each abnormal traffic object can be calculated as the trajectory efficiency information; the maximum value among the current efficiency influence degrees can be used as the trajectory efficiency information; and so on.

[0111] In one embodiment, the current motion information includes the driving trajectory, motion intention, whether there is a traffic barrier object between the abnormal traffic object and the target vehicle, and the distance between the abnormal traffic object and the target vehicle, etc. To determine that an abnormal traffic object does not affect the candidate trajectory, the following conditions should be met: 1. The driving trajectory of the abnormal traffic object does not hinder the driving trajectory of the target vehicle. For example, as shown in Figure 6 (a), if the trajectory of the target vehicle is to change lanes and bypass or bypass the abnormal traffic object in the lane ahead; 2. There is a traffic barrier object between the abnormal traffic object and the target vehicle. For example, as shown in Figure 6 (b), the abnormal traffic object and the target vehicle are blocked by a red light; 3. The motion intentions of the abnormal traffic object and the target vehicle are different. For example, as shown in Figure 6 (c), the motion intention of the target vehicle is to go straight forward, and the motion intention of the abnormal traffic object is to turn right; 4. The distance between the abnormal traffic object and the target vehicle is greater than the distance threshold, and the size of the distance threshold is positively correlated with the speed of the target vehicle. For example, as shown in Figure 6 (d), the distance between the abnormal traffic object and the target vehicle is greater than the distance threshold.

[0112] In one embodiment, the computer device may use the trajectory efficiency information corresponding to the intermediate trajectory as the initial trajectory efficiency, perform normalization processing on the initial trajectory efficiency to obtain the target trajectory efficiency, and use the target trajectory efficiency as the trajectory efficiency information. The normalization processing may be to determine the maximum trajectory efficiency from each initial trajectory efficiency, and use the ratio of the initial trajectory efficiency to the maximum trajectory efficiency as the target trajectory efficiency.

[0113] In the above embodiment, the computer device determines the trajectory affected by the abnormal traffic objects in the candidate trajectories of the target vehicle as the intermediate trajectory based on the current motion information of all abnormal traffic objects corresponding to the target vehicle, and calculates the trajectory efficiency information corresponding to the intermediate trajectory based on the current efficiency influence degree of all abnormal traffic objects that affect the trajectory on the intermediate trajectory, which can effectively improve the accuracy of the trajectory efficiency information corresponding to the intermediate trajectory. The intermediate trajectory is the trajectory in the candidate trajectories of the target vehicle that will be affected by abnormal traffic participants. Referring to the trajectory efficiency information of the intermediate trajectory when planning the driving trajectory of the target vehicle can effectively improve the accuracy of trajectory planning.

[0114] In a specific embodiment, the vehicle trajectory planning method may be applied to the autonomous driving scenario.

[0115] The vehicle trajectory planning method includes the following steps:

[0116] 1. Calculate the reference speed of traffic participants (i.e., target traffic objects)

[0117] Regularly calculate the reference sub - speeds of each traffic participant and record all the calculated reference sub - speeds within a certain time period. If there is a reference traffic flow around the traffic participant, use the average speed of the reference traffic flow as the reference sub - speed. If there is no reference traffic flow around the traffic participant, calculate the reference sub - speed by combining the legal speed limit of the road and the speed limit brought by objects with road semantic information. The final reference speed of the traffic participant is the result of the weighted average of the reference sub - speeds in the past period of time. This calculation can effectively reduce the fluctuations caused by inaccurate environmental or upstream data.

[0118] 2. Determine abnormal traffic participants (i.e., abnormal traffic objects) from each traffic participant

[0119] The computer device obtains the current speed of the traffic participant and determines whether the target traffic object is an abnormal traffic object through the following formula:

[0120]

[0121]

[0122] When result > 0, it is determined that the traffic participant is an abnormal traffic participant.

[0123] 3. Calculate the current efficiency impact degree corresponding to the abnormal traffic participant

[0124] The computer device obtains the current speed and reference speed of the abnormal traffic participant, and calculates the current efficiency impact degree corresponding to the abnormal traffic participant through the following formula:

[0125]

[0126]

[0127] 4. Calculate the trajectory efficiency information of the candidate trajectories

[0128] The computer device obtains multiple candidate trajectories of the autonomous vehicle, and determines whether the abnormal traffic participant will affect the candidate trajectories according to the driving trajectory, motion intention of the abnormal traffic participant, whether there is a traffic barrier object between the abnormal traffic participant and the autonomous vehicle, and the distance between the abnormal traffic participant and the autonomous vehicle. The candidate trajectories that will be affected by the abnormal traffic participant are used as intermediate trajectories. When an intermediate trajectory corresponds to only one abnormal traffic participant, the computer device uses the current efficiency impact degree of the abnormal traffic participant as the trajectory efficiency information of the intermediate trajectory. When an intermediate trajectory corresponds to at least two abnormal traffic participants, the computer device uses the maximum value among the current efficiency impact degrees of each abnormal traffic participant as the trajectory efficiency information of the intermediate trajectory. The computer device determines the trajectory efficiency information corresponding to the remaining candidate trajectories based on the trajectory efficiency information of the intermediate trajectories, and the trajectory efficiency indicated by the trajectory efficiency information corresponding to the remaining candidate trajectories is higher than the trajectory efficiency indicated by the trajectory efficiency information corresponding to the intermediate trajectories.

[0129] 5. Determine the target trajectory from the candidate trajectories

[0130] The computer device determines the target trajectory of the autonomous vehicle based on the trajectory efficiency information of each candidate trajectory. Further, the candidate trajectories can also be evaluated from multiple aspects such as safety, comfort, and efficiency to determine the target trajectory of the autonomous vehicle. The autonomous vehicle travels according to the target trajectory.

[0131] The computer device can perform traffic flow trajectory planning regularly and update the target trajectory of the autonomous vehicle regularly.

[0132] In the above embodiments, when the computer device evaluates the trajectory efficiency, it obtains and uses the movement speed, movement intention, and movement environment information of each traffic participant in the historical time period, which can increase the observation time of the efficiency evaluation and make the evaluation more accurate and stable. When calculating the current efficiency impact degree of the abnormal traffic participant, referring to the calculation idea of the first-order low-pass filter, the calculated values at the current moment and the historical moment are weighted, reducing the impact caused by environmental changes, fluctuations in the upstream data values, etc., making the obtained current efficiency impact degree value smoother and enabling the vehicle trajectory evaluation to be more stable and accurate.

[0133] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps do not necessarily need to be executed in the order indicated by the arrows. Unless clearly stated in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily need to be executed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily need to be sequential, but can be executed alternately or in turn with at least some of the steps or stages in other steps or other steps.

[0134] Based on the same inventive concept, an embodiment of the present application further provides a vehicle trajectory planning device for implementing the vehicle trajectory planning method involved above. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the vehicle trajectory planning device provided below can refer to the limitations on the vehicle trajectory planning method in the above text, and will not be repeated here.

[0135] In one embodiment, as Figure 7 shown, a vehicle trajectory planning device is provided, including: a speed acquisition module 702, an abnormal traffic object determination module 704, a current efficiency impact degree calculation module 706, a trajectory efficiency information determination module 708, and a target trajectory determination module 710, where:

[0136] The speed acquisition module 702 is configured to acquire the current speed and the reference speed corresponding to at least one target traffic object; the target traffic object is a traffic object moving around the target vehicle, and the reference speed is determined based on the historical movement environment information of the target traffic object.

[0137] The abnormal traffic object determination module 704 is configured to determine the abnormal traffic object from each target traffic object based on the speed difference between the reference speed and the current speed.

[0138] The current efficiency impact calculation module 706 is configured to generate a motion loss based on the current speed and the reference speed of the abnormal traffic object, and generate the current efficiency impact of the abnormal traffic object based on the motion loss.

[0139] The trajectory efficiency information determination module 708 is configured to determine an intermediate trajectory corresponding to the abnormal traffic object from each candidate trajectory of the target vehicle, and generate trajectory efficiency information corresponding to the intermediate trajectory based on the current efficiency impact.

[0140] The target trajectory determination module 710 is configured to determine a target trajectory from each candidate trajectory based on the trajectory efficiency information.

[0141] In the above vehicle trajectory planning device, the target traffic object is a traffic object moving around the target vehicle. Based on the speed difference between the current speed and the reference speed of the target traffic object, an abnormal traffic object can be determined from the target traffic objects. The abnormal traffic object can have a greater impact on the driving of the target vehicle. When planning the driving trajectory of the target vehicle, referring to the relevant information of the abnormal traffic object can effectively improve the accuracy of trajectory planning. Further, a motion loss can be generated based on the current speed and the reference speed of the abnormal traffic object, and the current efficiency impact of the abnormal traffic object can be generated based on the motion loss. The current efficiency impact can reflect the degree of impact of the abnormal traffic object on the trajectory efficiency of the driving trajectory of the target vehicle. Trajectory efficiency information of the candidate trajectory corresponding to the abnormal traffic object is generated based on the current efficiency impact, and a target trajectory is determined from each candidate trajectory of the target vehicle based on the trajectory efficiency information, which can effectively improve the accuracy of trajectory planning.

[0142] In one embodiment, the speed acquisition module 702 is further configured to:

[0143] Acquire a traffic object that is within a target range from the current target traffic object in a historical time period and has the same motion direction as the current target traffic object as a reference traffic object corresponding to the current target traffic object; the target range increases as the historical speed of the current target traffic object in the historical time period increases, and there is no traffic barrier object between the current target traffic object and the reference traffic object; statistically analyze the motion speed of the reference traffic object in the historical time period to obtain a reference sub-speed corresponding to the current target traffic object in the historical time period; and obtain the reference speed of the current target traffic object based on the reference sub-speed corresponding to the current target traffic object in the historical time period.

[0144] In one embodiment, the speed acquisition module 702 is further configured to:

[0145] When there is no reference traffic object for the current target traffic object in the historical time period, based on the traffic speed limit information of the current target traffic object in the historical time period, obtain the reference sub-speed corresponding to the current target traffic object in the historical time period.

[0146] In one embodiment, the speed acquisition module 702 is further configured to:

[0147] Obtain the reference sub-speeds corresponding to the current target traffic object in at least two historical time periods respectively; generate speed weights for the reference sub-speeds corresponding to the historical time periods based on the time difference between the historical time periods and the current time period; the speed weights decrease as the time difference increases; based on the speed weights of each reference sub-speed, fuse each reference sub-speed to obtain the reference speed corresponding to the current target traffic object.

[0148] In one embodiment, the abnormal traffic object determination module 704 is further configured to:

[0149] Based on the ratio between the speed difference corresponding to the same target traffic object and the reference speed, obtain the speed difference ratio corresponding to each target traffic object respectively; regard the target traffic object with a speed difference ratio greater than the preset ratio as an abnormal traffic object.

[0150] In one embodiment, the current efficiency impact calculation module 706 is further configured to:

[0151] Based on the current speed of the abnormal traffic object and the preset time period, calculate the first displacement corresponding to the abnormal traffic object, and based on the reference speed of the abnormal traffic object and the preset time period, calculate the second displacement corresponding to the abnormal traffic object; generate a motion loss based on the first displacement and the second displacement.

[0152] In one embodiment, the current efficiency impact calculation module 706 is further configured to:

[0153] Obtain the statistical times of the historical efficiency impact corresponding to the abnormal traffic object; generate a loss weight based on the statistical times; the loss weight increases as the statistical times increase and approaches the target value; generate the current efficiency impact based on the loss weight and the motion loss.

[0154] In one embodiment, the trajectory efficiency information determination module 708 is further configured to:

[0155] Based on the current motion information of the abnormal traffic object, determine the corresponding intermediate trajectory from each candidate trajectory to obtain the intermediate trajectories corresponding to each abnormal traffic object respectively; generate trajectory efficiency information based on the current efficiency impacts of each abnormal traffic object corresponding to the same intermediate trajectory to obtain the trajectory efficiency information corresponding to each intermediate trajectory respectively.

[0156] Each module in the above vehicle trajectory planning device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in or independent of the processor in a computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0157] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 8 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as reference speeds and traffic speed limit information corresponding to target traffic objects. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a vehicle trajectory planning method.

[0158] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 9As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a vehicle trajectory planning method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0159] Those skilled in the art can understand that Figure 8 , 9 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0160] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the steps in the above method embodiments are implemented.

[0161] In one embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0162] In one embodiment, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in the above method embodiments.

[0163] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0164] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0165] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0166] The above embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A vehicle trajectory planning method, characterized in that, The method includes: Obtaining the current speed and reference speed corresponding to at least one target traffic object; the target traffic object is a traffic object moving around the target vehicle, and the reference speed is determined based on the historical motion environment information of the target traffic object; Determining an abnormal traffic object from each target traffic object based on the speed difference between the reference speed and the current speed; Generating a motion loss based on the current speed and reference speed corresponding to the abnormal traffic object, and generating a current efficiency impact degree corresponding to the abnormal traffic object based on the motion loss; the current efficiency impact degree refers to the impact degree of the abnormal traffic object on the trajectory efficiency of the driving trajectory of the target vehicle; Determining an intermediate trajectory corresponding to the abnormal traffic object from each candidate trajectory corresponding to the target vehicle based on the current motion information of the abnormal traffic object, and generating trajectory efficiency information corresponding to the intermediate trajectory based on the current efficiency impact degree; Determining a target trajectory from each candidate trajectory based on the trajectory efficiency information.

2. The method according to claim 1, wherein The obtaining the current speed and reference speed corresponding to at least one target traffic object includes: Obtaining a traffic object that is within a target range from the current target traffic object during a historical time period and has the same motion direction as the current target traffic object as the reference traffic object corresponding to the current target traffic object; the target range increases as the historical speed of the current target traffic object during the historical time period increases, and there is no traffic blocking object between the current target traffic object and the reference traffic object; Counting the motion speed of the reference traffic object during the historical time period to obtain a reference sub-speed corresponding to the current target traffic object during the historical time period; Obtaining the reference speed corresponding to the current target traffic object based on the reference sub-speed corresponding to the current target traffic object during the historical time period.

3. The method according to claim 2, wherein The method further includes: When there is no reference traffic object for the current target traffic object during the historical time period, obtaining a reference sub-speed corresponding to the current target traffic object during the historical time period based on the traffic speed limit information of the current target traffic object during the historical time period.

4. The method according to claim 2, wherein The obtaining the reference speed corresponding to the current target traffic object based on the reference sub-speed corresponding to the current target traffic object during the historical time period includes: Obtaining reference sub-speeds corresponding to the current target traffic object in at least two historical time periods respectively; Generating a speed weight for the reference sub-speed corresponding to the historical time period based on the time difference between the historical time period and the current time period; the speed weight decreases as the time difference increases; Fusing each reference sub-speed based on the speed weights of each reference sub-speed to obtain the reference speed corresponding to the current target traffic object.

5. The method according to claim 1, characterized in that, The determining an abnormal traffic object from each target traffic object based on the speed difference between the reference speed and the current speed includes; Obtaining a speed difference ratio corresponding to each target traffic object based on the ratio between the speed difference and the reference speed corresponding to the same target traffic object; Take the target traffic object with a speed difference ratio greater than the preset ratio as the abnormal traffic object.

6. The method according to claim 1, wherein Generating a motion loss based on the current speed and the reference speed corresponding to the abnormal traffic object includes: Calculating a first displacement corresponding to the abnormal traffic object based on the current speed corresponding to the abnormal traffic object and a preset time period, and calculating a second displacement corresponding to the abnormal traffic object based on the reference speed corresponding to the abnormal traffic object and the preset time period; Generating the motion loss based on the first displacement and the second displacement.

7. The method according to claim 1, characterized in that, Generating the current efficiency impact degree corresponding to the abnormal traffic object based on the motion loss includes: Obtaining the statistical frequency of the historical efficiency impact degree corresponding to the abnormal traffic object; Generating a loss weight based on the statistical frequency; the loss weight increases as the statistical frequency increases and approaches a target value; Generating the current efficiency impact degree based on the loss weight and the motion loss.

8. The method according to claim 1, characterized in that Generating the trajectory efficiency information corresponding to the intermediate trajectory based on the current efficiency impact degree includes: Generating trajectory efficiency information based on the current efficiency impact degrees of each abnormal traffic object corresponding to the same intermediate trajectory, and obtaining the trajectory efficiency information corresponding to each intermediate trajectory.

9. A vehicle trajectory planning device, characterized in that, The device includes: A speed acquisition module, configured to acquire the current speed and the reference speed corresponding to at least one target traffic object; the target traffic object is a traffic object moving around the target vehicle, and the reference speed is determined based on the historical motion environment information of the target traffic object; An abnormal traffic object determination module, configured to determine an abnormal traffic object from each target traffic object based on the speed difference between the reference speed and the current speed; A current efficiency impact degree calculation module, configured to generate a motion loss based on the current speed and the reference speed corresponding to the abnormal traffic object, and generate the current efficiency impact degree corresponding to the abnormal traffic object based on the motion loss; the current efficiency impact degree refers to the impact degree of the abnormal traffic object on the trajectory efficiency of the driving trajectory of the target vehicle; A trajectory efficiency information determination module, configured to determine the intermediate trajectory corresponding to the abnormal traffic object from each candidate trajectory corresponding to the target vehicle based on the current motion information of the abnormal traffic object, and generate the trajectory efficiency information corresponding to the intermediate trajectory based on the current efficiency impact degree; A target trajectory determination module, configured to determine a target trajectory from each candidate trajectory based on the trajectory efficiency information.

10. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images