Vehicle driving planning method and device and vehicle

Abstract

The invention discloses a vehicle driving planning method and device and a vehicle, and relates to the technical field of intelligent driving. The method comprises the following steps: determining a target vehicle which is about to meet with the own vehicle based on first driving information of the own vehicle and second driving information of at least one other vehicle; determining an expected meeting position between the own vehicle and the target vehicle based on the first obstacle position of the target vehicle and the second obstacle position of the own vehicle; and performing meeting driving prediction between the own vehicle and the target vehicle according to the expected meeting position to obtain predicted meeting driving information, and generating a driving track of the own vehicle according to the predicted meeting driving information. According to the method, the requirement for safe meeting avoidance in a low-speed driving scene can be met, the collision risk of meeting driving of the vehicle and other vehicles is greatly reduced, and therefore the accuracy of vehicle driving planning is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a vehicle driving planning method and device, and a vehicle. Background Art

[0002] With the rapid development of intelligent driving technology, driverless vehicles will follow the real-time planned path when driving on the road. During the driving process, when other vehicles drive in front of the self-driving vehicle from the opposite direction, the self-driving vehicle will plan to meet the other vehicle to avoid vehicle collision during the meeting process.

[0003] At present, the vehicle driving planning in existing meeting scenarios is usually based on lane lines to avoid direct collision between the oncoming vehicle and the own vehicle. However, in scenarios where lane lines are unclear or low-speed meeting (such as underground garages), the safe meeting needs of the own vehicle and other vehicles cannot be met, which increases the collision risk between the own vehicle and other vehicles, thereby reducing the effectiveness and accuracy of vehicle driving planning. Summary of the invention

[0004] In view of this, the present application provides a vehicle driving planning method and device, and a vehicle, the main purpose of which is to solve the problem of poor effectiveness and accuracy of existing vehicle driving planning.

[0005] According to one aspect of the present application, a vehicle driving planning method is provided, comprising:

[0006] Determine a target vehicle that the self-vehicle is about to meet based on first driving information of the self-vehicle and second driving information of at least one other vehicle;

[0007] Determine an expected meeting position between the ego vehicle and the target vehicle based on a first obstacle position of the target vehicle and a second obstacle position of the ego vehicle;

[0008] A passing travel prediction is performed between the ego vehicle and the target vehicle according to the expected passing position to obtain predicted passing travel information, and a travel trajectory of the ego vehicle is generated according to the predicted passing travel information.

[0009] The embodiment of the present application determines the oncoming position between the target vehicle and the own vehicle, and predicts the oncoming driving trend to meet the safe oncoming and avoidance requirements in low-speed driving scenarios, thereby greatly reducing the collision risk between the own vehicle and other vehicles, thereby improving the accuracy of vehicle driving planning.

[0010] Further, the expected meeting position includes an expected longitudinal meeting position and an expected lateral meeting position, and determining the expected meeting position between the ego vehicle and the target vehicle based on the first obstacle position of the target vehicle and the second obstacle position of the ego vehicle includes:

[0011] Determine the lateral safety distance and longitudinal safety distance between the self-vehicle and the target vehicle;

[0012] Determining the expected longitudinal meeting position according to the travel compensation distance of the target vehicle, the longitudinal safety distance, the first obstacle position, and the second obstacle position;

[0013] The expected lateral meeting position is determined according to the lateral safety distance and the lateral limit distance of the target vehicle.

[0014] Further, the lateral limit distance includes a lateral minimum distance and a lateral maximum distance, and determining the expected lateral meeting position according to the lateral safety distance and the lateral limit distance of the target vehicle includes:

[0015] Under the condition that the minimum lateral distance or the maximum lateral distance meets a preset distance threshold, determining the expected lateral meeting position based on the minimum lateral distance and the lateral safety distance;

[0016] Under the condition that both the lateral minimum distance and the lateral maximum distance do not meet the preset distance threshold, the expected lateral meeting position is determined based on the lateral maximum distance and the lateral safety distance.

[0017] Furthermore, before determining the expected longitudinal meeting position according to the travel compensation distance of the target vehicle, the longitudinal safety distance, the first obstacle position, and the second obstacle position, the method further includes:

[0018] Under the condition that the driving angle of the target vehicle meets a preset turning angle range, the driving compensation distance is generated based on the first profile information of the target vehicle and the driving angle.

[0019] Further, the determining of a target vehicle traveling with the self-vehicle to be met based on the first driving information of the self-vehicle and the second driving information of at least one other vehicle comprises:

[0020] Acquire the lateral travel speed and the longitudinal relative distance between the own vehicle and the other vehicle in the second travel information;

[0021] Under the condition that the lateral travel speed is less than a preset lateral movement trend threshold or the longitudinal relative distance is less than a preset longitudinal movement trend threshold, obtaining the body length and longitudinal travel speed of the other vehicle;

[0022] Under the condition that the vehicle body length and the longitudinal travel speed match a preset meeting range, the other vehicle is determined as the target vehicle.

[0023] Furthermore, the method further comprises:

[0024] determining a relative driving direction according to a first driving direction in the first driving information and a second driving direction in the second driving information;

[0025] Under the condition that the relative driving direction does not conform to the preset meeting direction range, the other vehicle is determined as a non-target vehicle.

[0026] Further, the predicting of the oncoming vehicle between the ego vehicle and the target vehicle according to the expected oncoming vehicle position to obtain the predicted oncoming vehicle information includes:

[0027] Acquire the maximum travel curvature of the reference trajectory of the expected travel of the ego vehicle, and determine the relative meeting time based on the expected longitudinal meeting position and the longitudinal relative speed in the expected meeting position;

[0028] Under the condition that it is determined based on the maximum driving curvature or the lateral limit distance of the target vehicle that the on-coming driving of the ego vehicle and the target vehicle complies with a preset avoidance planning strategy, a lateral on-coming speed is determined based on the expected on-coming position and the relative on-coming time, and predicted on-coming driving information is generated based on the relative on-coming time and the lateral on-coming speed, so as to perform trajectory planning based on the predicted on-coming driving information including the relative on-coming time and the lateral on-coming speed.

[0029] According to another aspect of the present application, a vehicle driving planning device is provided, comprising:

[0030] A first determination module is used to determine a target vehicle that the self-vehicle is about to meet based on first driving information of the self-vehicle and second driving information of at least one other vehicle;

[0031] A second determination module is used to determine an expected meeting position between the ego vehicle and the target vehicle based on a first obstacle position of the target vehicle and a second obstacle position of the ego vehicle;

[0032] The prediction module is used to predict the oncoming vehicle between the ego vehicle and the target vehicle according to the expected oncoming vehicle position, obtain predicted oncoming vehicle driving information, and generate the driving trajectory of the ego vehicle according to the predicted oncoming vehicle driving information.

[0033] Further, the expected meeting position includes an expected longitudinal meeting position and an expected lateral meeting position, and the second determining module includes:

[0034] A first determining unit is used to determine a lateral safety distance and a longitudinal safety distance between the self-vehicle and the target vehicle to be met;

[0035] a second determining unit, configured to determine the expected longitudinal meeting position according to the travel compensation distance of the target vehicle, the longitudinal safety distance, the first obstacle position, and the second obstacle position;

[0036] The third determining unit is used to determine the expected lateral meeting position according to the lateral safety distance and the lateral limit distance of the target vehicle.

[0037] Furthermore, the lateral limit distance includes a lateral minimum distance and a lateral maximum distance.

[0038] The third determination unit is specifically configured to determine the expected lateral meeting position based on the minimum lateral distance and the lateral safety distance when the minimum lateral distance or the maximum lateral distance meets a preset distance threshold; and to determine the expected lateral meeting position based on the maximum lateral distance and the lateral safety distance when neither the minimum lateral distance nor the maximum lateral distance meets the preset distance threshold.

[0039] Furthermore, the device also includes:

[0040] A generating module is used to generate the driving compensation distance based on the first profile information of the target vehicle and the driving angle under the condition that the driving angle of the target vehicle meets the preset turning angle range.

[0041] Furthermore, the first determining module includes:

[0042] A generating unit, configured to obtain a lateral travel speed and a longitudinal relative distance between the own vehicle and the other vehicle in the second travel information;

[0043] an acquisition unit, configured to acquire the body length and longitudinal travel speed of the other vehicle under the condition that the lateral travel speed is less than a preset lateral movement trend threshold or the longitudinal relative distance is less than a preset longitudinal movement trend threshold;

[0044] The fourth determining unit is used to determine the other vehicle as the target vehicle under the condition that the vehicle body length and the longitudinal driving speed match a preset meeting range.

[0045] Furthermore, the device also includes:

[0046] a third determining module, configured to determine a relative driving direction according to the first driving direction in the first driving information and the second driving direction in the second driving information;

[0047] The fourth determination module is used to determine the other vehicle as a non-target vehicle under the condition that the relative driving direction does not conform to a preset meeting direction range.

[0048] Furthermore, the prediction module is specifically used to obtain the maximum driving curvature of the reference trajectory of the expected driving of the ego vehicle, and determine the relative meeting time based on the expected longitudinal meeting position in the expected meeting position and the longitudinal relative speed; under the condition that it is determined based on the maximum driving curvature or the lateral limit distance of the target vehicle that the meeting driving of the ego vehicle and the target vehicle meets the preset avoidance planning strategy, determine the lateral meeting speed based on the expected meeting position and the relative meeting time, and generate predicted meeting driving information based on the relative meeting time and the lateral meeting speed, so as to perform trajectory planning based on the predicted meeting driving information including the relative meeting time and the lateral meeting speed.

[0049] According to one aspect of the present application, a vehicle is provided, comprising the above-mentioned vehicle driving planning device.

[0050] According to another aspect of the present application, a readable storage medium is provided, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the vehicle driving planning method as described above are implemented.

[0051] According to another aspect of the present application, a computer device is provided, comprising: at least one processor, the processor is coupled to a memory, the memory stores a program or instruction running on the processor, and the program or instruction, when executed by the processor, implements the steps of the vehicle driving planning method as described above.

[0052] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0054] Figure 1 A flow chart of a vehicle driving planning method provided in an embodiment of the present application is shown;

[0055] Figure 2 A schematic diagram of a vehicle reversing and meeting scenario provided in an embodiment of the present application is shown;

[0056] Figure 3 A schematic diagram of a vehicle meeting scenario without lane lines provided in an embodiment of the present application is shown;

[0057] Figure 4 A block diagram of a vehicle driving planning device provided in an embodiment of the present application is shown;

[0058] Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0059] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0060] The present application embodiment provides a vehicle driving planning method, such as Figure 1 As shown, the method includes:

[0061] 101. Determine a target vehicle that the self-vehicle is about to meet based on first driving information of the self-vehicle and second driving information of at least one other vehicle.

[0062] In the embodiment of the present application, during the trajectory planning process of the unmanned intelligent vehicle, the automatic driving processor as the current execution subject can be a processor configured on the vehicle side, or a cloud server matching the vehicle, etc. At this time, the current execution subject is the processor of the vehicle itself, so as to obtain the driving information of the vehicle itself (that is, the current vehicle configured with the current execution subject) and other vehicles relative to the current vehicle (that is, other vehicles). Among them, the first driving information is the speed, position, direction or angle information perceived in real time during the driving process of the vehicle itself, and the second driving information is the speed, position, direction or angle information perceived in real time during the driving process of the other vehicle, which is not specifically limited in the embodiment of the present application. At this time, since the ego vehicle will encounter at least one other vehicle when driving on the road, including on a road without lane lines and in low-speed driving in a basement, and the target vehicle to be met may or may not exist, the current execution subject determines the target vehicle to be met by the ego vehicle based on the first driving information and the second driving information. For example, based on the driving direction of the other vehicle and the driving direction of the ego vehicle, it is determined whether the other vehicle is the vehicle that the current ego vehicle is about to meet. Among them, the to-be-met driving may include but is not limited to relative meeting on opposite driving routes, or reverse meeting on the same driving route, so as to determine a target vehicle to be met from multiple other vehicles.

[0063] It should be noted that the vehicle is a vehicle with an automatic control system in the autonomous driving scenario, including passenger cars and commercial vehicles. Common models of passenger cars include but are not limited to sedans, sport utility vehicles, multi-person commercial vehicles, etc. Common models of commercial vehicles include but are not limited to pickup trucks, microvans, self-unloading vehicles, trucks, tractors, trailers and mining vehicles, etc. At this time, the vehicle can achieve autonomous driving based on the automatic control system.

[0064] 102. Determine an expected meeting position between the ego vehicle and the target vehicle based on a first obstacle position of the target vehicle and a second obstacle position of the ego vehicle.

[0065] In the embodiment of the present application, since the target vehicle may be another vehicle that is on the same driving route as the vehicle itself but is in reverse, such as Figure 2 As shown in , it can also be another vehicle that is normally traveling in the opposite direction when the lane line is unclear, such as Figure 3As shown, at this time, different other vehicles are used as different obstacle positions for meeting, that is, the first obstacle position is used to characterize the position of the target vehicle when it is about to meet and the expected meeting collision occurs, which may include but is not limited to the contour position of the vehicle, such as the contour position of the front or rear of the target vehicle, and the second obstacle position is used to characterize the position of the self-vehicle when it is about to meet and the expected meeting collision occurs, which may include but is not limited to the contour position of the vehicle, such as the contour position of the front or rear of the self-vehicle, which is not specifically limited in the embodiment of the present application. Since the current execution subject is the processor of the self-vehicle, at this time, the obstacle position of the self-vehicle is preferably the contour position of the front of the self-vehicle, which is not specifically limited in the embodiment of the present application.

[0066] It should be noted that, in order to avoid a collision between the ego vehicle and the target vehicle during the meeting process, the current executing entity determines the expected meeting position based on the first obstacle position and the second obstacle position. At this time, the expected meeting position is the extreme position that ensures that the target vehicle and the ego vehicle do not collide during the meeting process. The expected meeting position may include the expected longitudinal meeting position and the expected lateral meeting position to indicate the specific lateral and longitudinal positions in the coordinate system, which is not specifically limited in the embodiments of the present application.

[0067] 104. Predict a meeting travel between the ego vehicle and the target vehicle according to the expected meeting position to obtain predicted meeting travel information, and generate a travel trajectory of the ego vehicle according to the predicted meeting travel information.

[0068] In the embodiment of the present application, in order to ensure the safety of the self-vehicle and the other vehicle when meeting at the expected meeting position, the current execution subject predicts the meeting driving based on the expected meeting position, and the prediction method may include but is not limited to big data deduction, dynamic simulation, etc., so as to obtain the predicted meeting driving information. Among them, since the predicted meeting driving information is the driving information predicted at the expected meeting position, the current execution subject performs trajectory planning through the predicted meeting driving information including the relative meeting time and the lateral meeting speed. In a specific implementation scenario, the self-vehicle and the other vehicle can predict multiple lateral driving positions at each driving time point according to the relative meeting time and the lateral meeting speed, so that the lateral driving positions corresponding to the multiple driving time points are used as planning constraints for the driving trajectory.

[0069] In another embodiment of the present application, the step of determining the expected meeting position between the ego vehicle and the target vehicle based on the first obstacle position of the target vehicle and the second obstacle position of the ego vehicle comprises:

[0070] Determine the lateral safety distance and longitudinal safety distance between the self-vehicle and the target vehicle;

[0071] Determining the expected longitudinal meeting position according to the travel compensation distance of the target vehicle, the longitudinal safety distance, the first obstacle position, and the second obstacle position;

[0072] The expected lateral meeting position is determined according to the lateral safety distance and the lateral limit distance of the target vehicle.

[0073] In order to accurately determine the expected meeting position for vehicle driving planning, thereby effectively improving the safety of the meeting between the self-vehicle and the other vehicle during the meeting process, the current execution subject first obtains the lateral safety distance and longitudinal safety distance of the vehicle to be met, and determines the expected longitudinal meeting position and the expected lateral meeting position in combination with the first obstacle position and the second obstacle position. Among them, the expected longitudinal meeting position is the minimum longitudinal position of the target vehicle and the self-vehicle in the Frenet coordinate system to ensure that the target vehicle and the self-vehicle do not collide, and the expected lateral meeting position is the minimum lateral position of the target vehicle and the self-vehicle in the Frenet coordinate system to ensure that the target vehicle and the self-vehicle do not collide. At the same time, the lateral safety distance and the longitudinal safety distance can be pre-configured based on the vehicle driving scenario, driving safety requirements, etc., and can also be determined in real time based on the relative speed, safety time distance, dynamic safety space, vehicle width, etc. between the self-vehicle and other vehicles, such as the lateral safety distance lat_safe_distance = dynamic safety space dynamic_safe_dist + vehicle width vchicle_width*0.5, the longitudinal safety distance lon_meeting_safe_dist = 0.5+min(1.0, relative speed relative_vel*safety time distance care_t), among which the above-mentioned relative speed, safety time distance, dynamic safety space, vehicle width and other data can be perceived and identified in real time based on the perception system on the current self-vehicle, and are not specifically limited in the embodiments of the present application.

[0074] It should be noted that in the embodiment of the present application, the current execution subject can perceive the driving conditions of the self-vehicle and the target vehicle in the Frenet coordinate system. Therefore, when determining the expected longitudinal meeting position, it can be determined specifically according to the driving compensation distance, longitudinal safety distance, and first obstacle position and second obstacle position of the target vehicle. Among them, the driving compensation distance is used to characterize the distance for safety compensation of the target vehicle during driving, which can be generated by the first profile information and the driving angle of the target vehicle, or can be configured based on the safety requirements of the vehicle's safe driving. The embodiment of the present application does not make specific restrictions. In a specific application scenario of reverse meeting, the self-vehicle is driving forward and the target vehicle is reversing backward. At this time, the target vehicle and the self-vehicle are both in the Frenet coordinate system, the first obstacle position of the target vehicle is the rear contour position obj_back_x, and the second obstacle position of the self-vehicle is the front contour position ego_front_x. The expected longitudinal meeting position = (the rear contour position of the other vehicle obj_back_x + driving compensation distance) - the front contour position of the self-vehicle ego_front_x - longitudinal safety distance. At the same time, the expected lateral meeting position is determined in the Frenet coordinate system according to the lateral safety distance and the lateral limit distance of the target vehicle, wherein the lateral limit distance is used to characterize the maximum distance and the minimum distance of the lateral movement of the target vehicle in the Frenet coordinate system, and includes the lateral minimum distance and the lateral maximum distance. It can be determined by the perception system identifying the road width or the drivable road width in the scene, and the embodiment of the present application does not make specific limitations to determine the expected lateral meeting position.

[0075] In another embodiment of the present application, the step of determining the expected lateral meeting position according to the lateral safety distance and the lateral limit distance of the target vehicle includes:

[0076] Under the condition that the minimum lateral distance or the maximum lateral distance meets a preset distance threshold, determining the expected lateral meeting position based on the minimum lateral distance and the lateral safety distance;

[0077] Under the condition that both the lateral minimum distance and the lateral maximum distance do not meet the preset distance threshold, the expected lateral meeting position is determined based on the lateral maximum distance and the lateral safety distance.

[0078] In order to accurately determine the expected lateral meeting position as the basis for driving trajectory planning, thereby improving the accuracy of the driving planning of the vehicle and achieving safe meeting. When the current execution subject determines the expected lateral meeting position, specifically, it determines whether the lateral minimum distance or the lateral maximum distance meets the preset distance threshold. At this time, the preset distance threshold can be configured as 0, for example, the lateral minimum distance obj_min_y>0.0, or the lateral maximum distance obj_max_y>0.0, which is not specifically limited in the embodiment of the present application. When the lateral minimum distance or the lateral maximum distance meets the preset distance threshold, the current execution subject determines the expected lateral meeting position based on the lateral minimum distance and the lateral safety distance, that is, the expected lateral meeting position = lateral minimum distance obj_min_y-lateral safety distance lat_safe_distance, which is not specifically limited in the embodiment of the present application. When both the lateral minimum distance and the lateral maximum distance do not meet the preset distance threshold, the current execution subject determines the expected lateral meeting position based on the lateral maximum distance and the lateral safety distance, that is, the expected lateral meeting position = lateral maximum distance obj_max_y+lateral safety distance lat_safe_distance, which is not specifically limited in the embodiment of the present application.

[0079] In another embodiment of the present application, before determining the expected longitudinal meeting position according to the travel compensation distance of the target vehicle, the longitudinal safety distance, and the first obstacle position and the second obstacle position, the method further includes:

[0080] Under the condition that the driving angle of the target vehicle meets a preset turning angle range, the driving compensation distance is generated based on the first profile information of the target vehicle and the driving angle.

[0081] In order to improve the safety of vehicle-on-vehicle driving, in a specific implementation scenario, when the current execution subject obtains the driving compensation distance, it first determines whether the driving angle of the target vehicle matches the preset turning angle range. Among them, in the Frenet coordinate system, the driving angle of the target vehicle can be perceived in real time by the perception system installed on the vehicle, and the driving direction of the target vehicle can also be converted in the Frenet coordinate system to characterize the movement direction of the target vehicle, which is not specifically limited in the embodiment of the present application. At the same time, the preset turning angle range can be configured based on the road conditions in the meeting scene, such as the preset turning angle range can be (11 / 12*π, 2 / 3*π), when 11 / 12*π>driving angle obj_frenet_yaw>2 / 3*π, the driving compensation distance is generated based on the first contour information and driving angle of the target vehicle, that is, the driving compensation distance = first contour information obj_length*cos(π-driving angle obj_frenet_yaw), which is not specifically limited in the embodiment of the present application.

[0082] In another embodiment of the present application, the step of determining a target vehicle traveling with the self-vehicle to be met based on the first driving information of the self-vehicle and the second driving information of at least one other vehicle comprises:

[0083] Acquire the lateral travel speed and the longitudinal relative distance between the own vehicle and the other vehicle in the second travel information;

[0084] Under the condition that the lateral travel speed is less than a preset lateral movement trend threshold or the longitudinal relative distance is less than a preset longitudinal movement trend threshold, obtaining the body length and longitudinal travel speed of the other vehicle;

[0085] Under the condition that the vehicle body length and the longitudinal travel speed match a preset meeting range, the other vehicle is determined as the target vehicle.

[0086] Since other vehicles traveling together with the ego vehicle in the scene may include vehicles with a long driving distance or vehicles with a short driving distance, in order to accurately select which other vehicles are target vehicles to be driven by the ego vehicle, so as to serve as a basis for determining the expected position of the driving, and to improve the accuracy of the driving plan of the driving, the current execution subject selects the target vehicle to be driven by the ego vehicle from at least one other vehicle. Specifically, the current execution subject first obtains the lateral driving speed and the longitudinal relative distance in the second driving information, wherein the lateral driving speed is used to characterize the lateral movement speed of the other vehicle, and the longitudinal relative distance is the minimum distance for determining the other vehicle as the range of the ego vehicle to meet and avoid. The lateral driving speed can be based on the real-time perception and recognition of the perception system, and the longitudinal relative distance can be determined based on the longitudinal minimum distance of the other vehicle and the front contour position of the ego vehicle, such as the longitudinal relative distance diff_relative_x1=the longitudinal minimum distance obj_min_x-the front contour position ego_front_x of the ego vehicle, which is not specifically limited in the embodiment of the present application. At this time, the preset lateral motion trend threshold is used to characterize the maximum lateral stability value of the vehicle to be met by the own vehicle, and the preset longitudinal motion trend threshold is used to characterize the maximum longitudinal stability value of the vehicle to be met by the own vehicle. Both can be configured based on the driving difference. For example, the preset longitudinal motion trend threshold is 5.0m, which is not specifically limited in the embodiment of the present application. When the lateral driving speed is less than the preset lateral motion trend threshold or the longitudinal relative distance is less than the preset longitudinal motion trend threshold, the current execution subject obtains the body length and longitudinal driving speed of the other vehicle to determine whether it meets the preset meeting range. Among them, the second contour information of the other vehicle may include the contour position of the other vehicle, and then the body length vehicle_param_length can be obtained. The longitudinal driving speed can be identified and obtained based on the perception coefficient, which is not specifically limited in the embodiment of the present application.

[0087] It should be noted that the preset meeting range is used to limit the longitudinal distance and the longitudinal speed at the same time. Therefore, the vehicle body length and the longitudinal driving speed are constrained respectively. The preset meeting range includes the vehicle body length threshold and the longitudinal speed threshold. Among them, the vehicle body length threshold can be obtained based on the longitudinal maximum distance of the other vehicle and the front contour position of the own vehicle, that is, the vehicle body length threshold diff_relative_x2 = the longitudinal maximum distance obj_max_x-the front contour position ego_front_x of the own vehicle. In a specific implementation scenario, when diff_relative_x2>-3 / 4*vehicle_param_length, it means that the vehicle body length is less than the vehicle body length threshold; when the longitudinal driving speed obj_lon_v<0.5*v_limit, it means that the longitudinal driving speed is less than the longitudinal speed threshold (that is, the maximum speed limit, which can be configured by the maximum driving speed in the driving scene), so that the vehicle body length and the longitudinal driving speed match the preset meeting range, and the other vehicle can be determined as the target vehicle.

[0088] In another embodiment of the present application, the steps further include:

[0089] determining a relative driving direction according to a first driving direction in the first driving information and a second driving direction in the second driving information;

[0090] Under the condition that the relative driving direction does not conform to the preset meeting direction range, the other vehicle is determined as a non-target vehicle.

[0091] In order to effectively exclude other vehicles that are not oncoming vehicles and to improve the accuracy of screening the target vehicle, the current execution subject first parses the first driving direction in the first driving information and the second driving direction in the second driving information, thereby comparing and obtaining the relative driving direction. Among them, in the Frenet coordinate system, the first driving direction ego_frenet_yaw and the second driving direction obj_frenet_yaw can be perceived and identified based on the perception system, thereby obtaining the relative driving direction diff_frenet_yaw=obj_frenet_yaw-ego_frenet_yaw, which is not specifically limited in the embodiment of the present application. In the process of excluding non-target vehicles, the current execution subject compares the relative driving direction with the preset oncoming direction range. At this time, the preset oncoming direction range can be configured based on the oncoming requirements in the driving scene, such as the preset oncoming direction range is greater than 5 / 9*π or less than 4 / 9*π, which is not specifically limited in the embodiment of the present application. In a specific implementation scenario, when 4 / 9*π<|diff_frenet_yaw|<5 / 9*π, it means that the other vehicle is perpendicular to the own vehicle at this time, so it can be determined as a non-target vehicle. When |diff_frenet_yaw|>5 / 6*π (the other vehicle is an oncoming vehicle at this time) or diff_frenet_yaw>3 / 4*π (the other vehicle is a reversing vehicle at this time), the other vehicle can be further screened, such as executing the steps of obtaining the lateral driving speed in the second driving information and the longitudinal relative distance between the own vehicle and the other vehicle and the subsequent steps to determine the target vehicle.

[0092] In another embodiment of the present application, the step of performing a meeting travel prediction between the self-vehicle and the target vehicle according to the expected meeting position to obtain the predicted meeting travel information includes:

[0093] Acquire the maximum travel curvature of the reference trajectory of the expected travel of the ego vehicle, and determine the relative meeting time based on the expected longitudinal meeting position and the longitudinal relative speed in the expected meeting position;

[0094] Under the condition that it is determined based on the maximum driving curvature or the lateral limit distance of the target vehicle that the on-coming driving of the ego vehicle and the target vehicle complies with a preset avoidance planning strategy, a lateral on-coming speed is determined based on the expected on-coming position and the relative on-coming time, and predicted on-coming driving information is generated based on the relative on-coming time and the lateral on-coming speed.

[0095] In order to achieve the expected meeting position to perform the meeting deduction, and to perform the driving planning based on the deduction results, the meeting collision is greatly avoided and the safety of the meeting driving is improved. When the current execution subject predicts the meeting driving between the self-vehicle and the target vehicle according to the expected meeting position, the maximum driving curvature of the reference trajectory of the expected driving of the self-vehicle is first obtained. Since the self-vehicle is planned in the Frenet coordinate system and the driving is controlled based on the reference trajectory, the maximum driving curvature of the self-vehicle on the trajectory can be determined based on the reference trajectory. At the same time, in order to predict the meeting driving information, the current execution subject calculates the relative meeting time based on the expected longitudinal meeting position and the longitudinal relative speed. Among them, the relative meeting time t_avd = the expected longitudinal meeting position P_pre{x} in the expected meeting position P_pre{x,y} / longitudinal relative speed lon_relative_vel, the longitudinal relative speed can be determined based on the longitudinal speed of the self-vehicle and the other vehicle perceived by the perception system, and the embodiment of the present application does not make specific restrictions.

[0096] It should be noted that, in order to effectively avoid the oncoming vehicle, the avoidance strategy for curvature, distance and other characteristics is pre-configured, that is, the preset avoidance strategy is used to characterize the judgment conditions for avoiding to the left or to the right when the specific curvature condition or distance condition is met. For example, when the preset avoidance strategy matched by the maximum driving curvature max_ref_curve is |max_ref_curve|<0.02, and obj_max_y>0, the oncoming driving of the self-vehicle and the target vehicle matches the oncoming driving strategy of the self-vehicle to the right. At the same time, the lateral limit distance includes the maximum lateral distance obj_max_y and the minimum lateral distance obj_min_y. The corresponding preset avoidance strategy may include when the maximum lateral distance obj_max_y<0, and the minimum lateral distance obj_min_y<0, |max_ref_curve|>0.02, the oncoming driving of the self-vehicle and the target vehicle matches the oncoming driving strategy of the self-vehicle to the left. The embodiment of the present application does not make specific limitations.

[0097] In a specific implementation scenario, when matching the right avoidance strategy, the lateral meeting speed is determined based on the expected meeting position and the relative meeting time, specifically, the lateral meeting speed v_lat = (lateral coordinate ego_l of the ego vehicle - expected lateral meeting position P_pre{y}) / relative meeting time t_avd.

[0098] In a specific implementation scenario, when matching the left avoidance strategy, the lateral meeting speed is determined based on the expected meeting position and the relative meeting time, specifically, the lateral meeting speed v_lat = (expected lateral meeting position P_pre{y}-lateral coordinate ego_l of the ego vehicle) / relative meeting time t_avd.

[0099] After the current execution subject determines the lateral meeting speed, in the process of deduction and prediction, the corresponding lateral driving positions of the self-vehicle and the other-vehicle can be predicted at each driving time point according to the relative meeting time and the lateral meeting speed. At this time, the predicted meeting driving information generated based on the relative meeting time and the lateral meeting speed is represented by the lateral meeting speed v_lat and the relative meeting time t_avd, that is, {v_lat, t_avd}. The current execution subject can also calculate multiple lateral driving positions of the vehicles to be met within 0-relative meeting time v_lat based on the lateral meeting speed, and interpolate the position points of the multiple lateral driving positions to obtain smooth and continuous predicted meeting driving information (at this time, multiple position points), so that the corresponding relative meeting time and the lateral position after interpolation in the predicted meeting driving information are used as planning constraints for the lateral driving trajectory.

[0100] The embodiment of the present application determines the oncoming position between the target vehicle and the own vehicle, and predicts the oncoming driving trend to meet the safe oncoming and avoidance requirements in low-speed driving scenarios, thereby greatly reducing the collision risk between the own vehicle and other vehicles, thereby improving the accuracy of vehicle driving planning.

[0101] Furthermore, as a response to the above Figure 1 The implementation of the method shown in the figure, the embodiment of the present application provides a vehicle driving planning device, such as Figure 4 As shown, the device comprises:

[0102] A first determination module 21 is used to determine a target vehicle that the self-vehicle is about to meet based on first driving information of the self-vehicle and second driving information of at least one other vehicle;

[0103] A second determination module 22, configured to determine an expected meeting position between the ego vehicle and the target vehicle based on a first obstacle position of the target vehicle and a second obstacle position of the ego vehicle;

[0104] The prediction module 23 is used to predict the oncoming driving between the ego vehicle and the target vehicle according to the expected oncoming position, obtain predicted oncoming driving information, and generate the driving trajectory of the ego vehicle according to the predicted oncoming driving information.

[0105] Further, the expected meeting position includes an expected longitudinal meeting position and an expected lateral meeting position, and the second determining module includes:

[0106] A first determining unit is used to determine a lateral safety distance and a longitudinal safety distance between the self-vehicle and the target vehicle to be met;

[0107] a second determining unit, configured to determine the expected longitudinal meeting position according to the travel compensation distance of the target vehicle, the longitudinal safety distance, the first obstacle position, and the second obstacle position;

[0108] The third determining unit is used to determine the expected lateral meeting position according to the lateral safety distance and the lateral limit distance of the target vehicle.

[0109] Furthermore, the lateral limit distance includes a lateral minimum distance and a lateral maximum distance.

[0110] The third determination unit is specifically configured to determine the expected lateral meeting position based on the minimum lateral distance and the lateral safety distance when the minimum lateral distance or the maximum lateral distance meets a preset distance threshold; and to determine the expected lateral meeting position based on the maximum lateral distance and the lateral safety distance when neither the minimum lateral distance nor the maximum lateral distance meets the preset distance threshold.

[0111] Furthermore, the device also includes:

[0112] A generating module is used to generate the driving compensation distance based on the first profile information of the target vehicle and the driving angle under the condition that the driving angle of the target vehicle meets the preset turning angle range.

[0113] Furthermore, the first determining module includes:

[0114] A generating unit, configured to obtain a lateral travel speed and a longitudinal relative distance between the own vehicle and the other vehicle in the second travel information;

[0115] an acquisition unit, configured to acquire the body length and longitudinal travel speed of the other vehicle under the condition that the lateral travel speed is less than a preset lateral movement trend threshold or the longitudinal relative distance is less than a preset longitudinal movement trend threshold;

[0116] The fourth determining unit is used to determine the other vehicle as the target vehicle under the condition that the vehicle body length and the longitudinal driving speed match a preset meeting range.

[0117] Furthermore, the device also includes:

[0118] a third determining module, configured to determine a relative driving direction according to the first driving direction in the first driving information and the second driving direction in the second driving information;

[0119] The fourth determination module is used to determine the other vehicle as a non-target vehicle under the condition that the relative driving direction does not conform to a preset meeting direction range.

[0120] Furthermore, the prediction module is specifically used to obtain the maximum driving curvature of the reference trajectory of the expected driving of the ego vehicle, and determine the relative meeting time based on the expected longitudinal meeting position in the expected meeting position and the longitudinal relative speed; under the condition that it is determined based on the maximum driving curvature or the lateral limit distance of the target vehicle that the meeting driving of the ego vehicle and the target vehicle meets the preset avoidance planning strategy, determine the lateral meeting speed based on the expected meeting position and the relative meeting time, and generate predicted meeting driving information based on the relative meeting time and the lateral meeting speed, so as to perform trajectory planning based on the predicted meeting driving information including the relative meeting time and the lateral meeting speed.

[0121] The embodiment of the present application determines the oncoming position between the target vehicle and the own vehicle, and predicts the oncoming driving trend to meet the safe oncoming and avoidance requirements in low-speed driving scenarios, thereby greatly reducing the collision risk between the own vehicle and other vehicles, thereby improving the accuracy of vehicle driving planning.

[0122] According to one embodiment of the present application, a vehicle is provided, comprising the above-mentioned vehicle driving planning device.

[0123] According to one embodiment of the present application, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the vehicle driving planning method as described above are implemented.

[0124] Figure 5 A schematic diagram of the structure of a computer device provided according to an embodiment of the present application is shown, comprising at least one processor, the processor and a memory are coupled, the memory stores a program or instruction running on the processor, and the program or instruction is executed by the processor to implement the steps of the vehicle driving planning method as described above. The specific embodiments of the present application do not limit the specific implementation of the computer device.

[0125] like Figure 5 As shown, the computer device may include: a processor (processor) 302 , a communication interface (Communications Interface) 304 , a memory (memory) 306 , and a communication bus 308 .

[0126] The processor 302 , the communication interface 304 , and the memory 306 communicate with each other via the communication bus 308 .

[0127] The communication interface 304 is used to communicate with other devices such as clients or other servers.

[0128] The processor 302 is used to execute the program 310, and specifically can execute the relevant steps in the above-mentioned vehicle driving planning method embodiment.

[0129] Specifically, the program 310 may include program codes, which include computer operation instructions.

[0130] The processor 302 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the computer device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0131] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0132] The program 310 may be specifically configured to enable the processor 302 to perform the following operations:

[0133] Determine a target vehicle that the self-vehicle is about to meet based on first driving information of the self-vehicle and second driving information of at least one other vehicle;

[0134] Determine an expected meeting position between the ego vehicle and the target vehicle based on a first obstacle position of the target vehicle and a second obstacle position of the ego vehicle;

[0135] A passing travel prediction is performed between the ego vehicle and the target vehicle according to the expected passing position to obtain predicted passing travel information, and a travel trajectory of the ego vehicle is generated according to the predicted passing travel information.

[0136] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0137] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A vehicle driving planning method, characterized in that: include: Determine a target vehicle that the self-vehicle is about to meet based on first driving information of the self-vehicle and second driving information of at least one other vehicle; Determine an expected meeting position between the ego vehicle and the target vehicle based on a first obstacle position of the target vehicle and a second obstacle position of the ego vehicle; A passing travel prediction is performed between the ego vehicle and the target vehicle according to the expected passing position to obtain predicted passing travel information, and a travel trajectory of the ego vehicle is generated according to the predicted passing travel information.

2. The method according to claim 1, characterized in that The expected meeting position includes an expected longitudinal meeting position and an expected lateral meeting position, and determining the expected meeting position between the ego vehicle and the target vehicle based on the first obstacle position of the target vehicle and the second obstacle position of the ego vehicle includes: Determine the lateral safety distance and longitudinal safety distance between the self-vehicle and the target vehicle; Determining the expected longitudinal meeting position according to the travel compensation distance of the target vehicle, the longitudinal safety distance, the first obstacle position, and the second obstacle position; The expected lateral meeting position is determined according to the lateral safety distance and the lateral limit distance of the target vehicle.

3. The method according to claim 2, characterized in that The lateral limit distance includes a lateral minimum distance and a lateral maximum distance, and determining the expected lateral meeting position according to the lateral safety distance and the lateral limit distance of the target vehicle includes: Under the condition that the minimum lateral distance or the maximum lateral distance meets a preset distance threshold, determining the expected lateral meeting position based on the minimum lateral distance and the lateral safety distance; Under the condition that both the lateral minimum distance and the lateral maximum distance do not meet the preset distance threshold, the expected lateral meeting position is determined based on the lateral maximum distance and the lateral safety distance.

4. The method according to claim 2, characterized in that: Before determining the expected longitudinal meeting position according to the travel compensation distance of the target vehicle, the longitudinal safety distance, the first obstacle position, and the second obstacle position, the method further includes: Under the condition that the driving angle of the target vehicle meets a preset turning angle range, the driving compensation distance is generated based on the first profile information of the target vehicle and the driving angle.

5. The method according to claim 1, characterized in that The method of determining a target vehicle traveling with the self-vehicle to be met based on the first driving information of the self-vehicle and the second driving information of at least one other vehicle comprises: Acquire the lateral travel speed and the longitudinal relative distance between the own vehicle and the other vehicle in the second travel information; Under the condition that the lateral travel speed is less than a preset lateral movement trend threshold or the longitudinal relative distance is less than a preset longitudinal movement trend threshold, obtaining the body length and longitudinal travel speed of the other vehicle; Under the condition that the vehicle body length and the longitudinal travel speed match a preset meeting range, the other vehicle is determined as the target vehicle.

6. The method according to claim 5, characterized in that The method further comprises: determining a relative driving direction according to a first driving direction in the first driving information and a second driving direction in the second driving information; Under the condition that the relative driving direction does not conform to the preset meeting direction range, the other vehicle is determined as a non-target vehicle.

7. The method according to any one of claims 1 to 6, characterized in that: The predicting of the oncoming vehicle between the vehicle and the target vehicle according to the expected oncoming vehicle position to obtain the predicted oncoming vehicle information includes: Acquire the maximum travel curvature of the reference trajectory of the expected travel of the ego vehicle, and determine the relative meeting time based on the expected longitudinal meeting position and the longitudinal relative speed in the expected meeting position; Under the condition that it is determined based on the maximum driving curvature or the lateral limit distance of the target vehicle that the on-coming driving of the ego vehicle and the target vehicle complies with a preset avoidance planning strategy, a lateral on-coming speed is determined based on the expected on-coming position and the relative on-coming time, and predicted on-coming driving information is generated based on the relative on-coming time and the lateral on-coming speed, so as to perform trajectory planning based on the predicted on-coming driving information including the relative on-coming time and the lateral on-coming speed.

8. A vehicle driving planning device, characterized in that: include: A first determination module is used to determine a target vehicle that the self-vehicle is about to meet based on first driving information of the self-vehicle and second driving information of at least one other vehicle; A second determination module is used to determine an expected meeting position between the ego vehicle and the target vehicle based on a first obstacle position of the target vehicle and a second obstacle position of the ego vehicle; The prediction module is used to predict the oncoming vehicle between the ego vehicle and the target vehicle according to the expected oncoming vehicle position, obtain predicted oncoming vehicle driving information, and generate the driving trajectory of the ego vehicle according to the predicted oncoming vehicle driving information.

9. A vehicle, characterized in that: Including the vehicle travel planning device as described in claim 8.

10. A computer device, characterized in that: It includes at least one processor, which is coupled to a memory, and the memory stores a program or instruction that runs on the processor. When the program or instruction is executed by the processor, the steps of the vehicle driving planning method as described in any one of claims 1 to 7 are implemented.

11. A readable storage medium having a program or instruction stored thereon, characterized in that: When the program or instruction is executed by a processor, the steps of the vehicle driving planning method as described in any one of claims 1 to 7 are implemented.

Images