Track planning method and device, vehicle and storage medium

Abstract

The invention discloses a trajectory planning method and device, a vehicle and a storage medium, and the method comprises the steps: predicting a vehicle state of the vehicle at a first time point and a vehicle state of a vehicle following the vehicle at the first time point under the condition that the vehicle is in a congestion road condition, and taking the vehicle states as an initial state of a starting time point of a first planning time period; the first time point is after the starting time point of the first planning time period; and according to the initial state, predicting a prediction trajectory of the vehicle in the first planning time period. According to the method provided by the invention, the trajectory planning of the vehicle under the congested road condition is realized.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and more specifically, to a trajectory planning method, device, vehicle and storage medium. Background Art

[0002] At present, with the continuous development of economic level, cars are becoming more and more popular. However, with the continuous mention of cars, traffic congestion is gradually becoming a problem that needs to be solved. Therefore, in the field of autonomous driving, there is an urgent need for a means to predict the driving trajectory of vehicles under congested road conditions. Summary of the invention

[0003] The present application proposes a trajectory planning method, device, vehicle and storage medium to provide a means for predicting the driving trajectory of a vehicle under congested road conditions.

[0004] In a first aspect, an embodiment of the present application provides a trajectory planning method, the method comprising:

[0005] When the vehicle is in a congested road condition, predicting the vehicle state of the vehicle at a first time point and the vehicle state of the preceding vehicle followed by the vehicle at the first time point as the initial state at the start time point of the first planning period; the first time point is after the start time point of the first planning period;

[0006] Based on the initial state, predict the predicted trajectory of the ego vehicle in the first planning period.

[0007] In a second aspect, an embodiment of the present application provides a trajectory planning method, the method comprising:

[0008] An acquisition module is used to predict the vehicle state of the vehicle at a first time point and the vehicle state of the preceding vehicle followed by the vehicle at the first time point when the vehicle is in a congested road condition, as the initial state at the start time point of the first planning period; the first time point is after the start time point of the first planning period;

[0009] The planning module is used to predict the predicted trajectory of the vehicle in the first planning period based on the initial state.

[0010] In a third aspect, an embodiment of the present application further provides a vehicle, comprising: one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method of the first aspect above.

[0011] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a program code executable by a processor, and when the program code is executed by the processor, the processor executes the above method.

[0012] The present application provides a trajectory planning method, device, vehicle and storage medium. In the present application, it is determined that the vehicle is in a congested road condition, and a preview processing of the vehicle state is performed - the vehicle state after the start time point of the first planning period is used as the initial state corresponding to the start time point, and based on the initial state after preview, the trajectory is predicted to obtain the predicted trajectory of the first planning period, thereby realizing the trajectory planning under congested road conditions. Secondly, the vehicle state is also previewed to ensure that the vehicle can respond to the change of the motion state of the preceding vehicle in advance, improve the response speed of the vehicle, reduce the peak acceleration and deceleration of the vehicle, and effectively improve the ride comfort of the vehicle under congested road conditions, so that the safety and comfort of the trajectory planned under congested road conditions are both high; at the same time, through the preview processing, the response speed of the vehicle is improved, and the situation of being constantly blocked by the adjacent vehicles in the congested scene can be reduced.

[0013] Other features and advantages of the embodiments of the present application will be described in the subsequent description, and partly become apparent from the description, or can be understood by practicing the embodiments of the present application. The purposes and other advantages of the embodiments of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 A schematic diagram of a vehicle hardware environment suitable for an embodiment of the present application is shown.

[0016] Figure 2 A flow chart of a trajectory planning method proposed according to an embodiment of the present application is shown.

[0017] Figure 3 A flow chart of a trajectory planning method proposed according to another embodiment of the present application is shown.

[0018] Figure 4 Shows Figure 3 The steps after step S120 in the corresponding embodiment are a flowchart in an embodiment.

[0019] Figure 5 Shows Figure 3 The steps after step S120 in the corresponding embodiment are in a flowchart of another embodiment.

[0020] Figure 6Shows Figure 2 The steps after step S120 in the corresponding embodiment are in the flowchart of yet another embodiment.

[0021] Figure 7 A transition diagram of acceleration and deceleration of a leading vehicle in an embodiment of the present application is shown.

[0022] Figure 8 A schematic diagram showing a trajectory planning process in an embodiment of the present application.

[0023] Fig. 9 A structural block diagram of a trajectory planning device proposed in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0024] In order to make those skilled in the art better understand the present application scheme, the technical scheme in the present application embodiment will be clearly and completely described below in conjunction with the drawings in the present application embodiment. Obviously, the described embodiment is only a part of the present application embodiment, rather than all the embodiments. The components of the present application embodiment usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application for protection, but merely represents the selected embodiment of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0025] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0026] Reference Figure 1 , Figure 1 A schematic diagram of a vehicle hardware environment suitable for an embodiment of the present application is shown, wherein the vehicle 100 includes a driving system 110, which may have multiple built-in autonomous driving functions. The driving system 110 may store an electronic map, and the driving system 110 may plan a driving route based on the electronic map stored in the driving system, and may also control the vehicle's autonomous driving based on the planned driving route.

[0027] The driving system 110 may include a data acquisition device 111 , one or more (only one is shown in the figure) processors 112 , and a memory 113 .

[0028] The data acquisition device 111 is used to detect various signals or data of the vehicle. For example, the data acquisition device 111 can collect the vehicle status of the vehicle itself and the vehicle status of vehicles around the vehicle. The data acquisition device 111 can include, for example, a radar and a camera.

[0029] The processor 112 may be a microcontroller unit (MCU) having a built-in memory 113 . The memory 113 stores a program that can execute the contents of the following embodiments, and the processor 112 may execute the program stored in the memory 113 .

[0030] The processor 112 may include one or more processors. The processor 112 uses various interfaces and lines to connect various parts of the entire vehicle 100, and executes various functions of the vehicle 100 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 113, and calling data stored in the memory 113.

[0031] The memory 113 may include a random access memory (RAM) or a read-only memory (ROM). The memory 15 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 15 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc.

[0032] See also Figure 2 Figure 2 A flow chart of a trajectory planning method proposed according to an embodiment of the present application is shown, which is used for a vehicle, and the method includes:

[0033] S110, when the vehicle is in a congested road condition, predicting the vehicle state of the vehicle at a first time point and the vehicle state of the preceding vehicle followed by the vehicle at the first time point as the initial state at the start time point of the first planning period.

[0034] The first time point is after the start time point of the first planning period.

[0035] The vehicle in this embodiment may be an electric vehicle or a fuel vehicle, or may be a sedan, an SUV, a bus, a truck, etc., and the self-vehicle may refer to the vehicle itself.

[0036] In this application, when the vehicle lane where the vehicle is located is congested, it means that the vehicle lane is congested, and the vehicle is determined to be in a congested road condition; it may also be when the vehicle lane where the vehicle is located and the adjacent vehicle lane are both congested, which means that both the vehicle lane and the adjacent vehicle lane are congested, and the vehicle changes lanes to the adjacent vehicle lane and is still congested, and the vehicle is determined to be in a congested road condition. Among them, the adjacent vehicle lane refers to the lane adjacent to the vehicle lane, and the adjacent vehicle lane can be the left adjacent vehicle lane on the left or the right adjacent vehicle lane on the right.

[0037] In some embodiments, the lane congestion identification result of the own vehicle lane can be determined based on the average speed of the traffic in the own vehicle lane where the own vehicle is located and the reference relative distance; the reference relative distance is the relative distance between the front vehicle followed by the own vehicle and the front-front vehicle followed by the front vehicle; the adjacent lane congestion identification result of the adjacent lane is determined based on the average speed of the traffic in the adjacent lane adjacent to the own vehicle lane and the road space occupancy rate of the adjacent lane; the lane change status information of the adjacent lane is determined; the lane change indication information is used to indicate whether the adjacent lane is a lane changeable by the own vehicle; based on the lane congestion identification result, the adjacent lane congestion identification result and the lane change status information, it is determined whether the own vehicle is in a congested road condition.

[0038] In this embodiment, the traffic flow in the ego vehicle lane may refer to the first related vehicles within a certain range in the ego vehicle lane, and the average speed of the first related vehicles is used as the average speed of the traffic flow in the ego vehicle lane. For example, the certain range of the ego vehicle lane may be 30 meters before and after the ego vehicle, and for another example, the first related vehicles may include the ego vehicle, the preceding vehicle (the vehicle followed by the ego vehicle), and the preceding preceding vehicle (the vehicle followed by the preceding vehicle).

[0039] The self-vehicle can collect the speed of the traffic in the self-vehicle lane and determine the average speed of the traffic in the self-vehicle lane. At the same time, the self-vehicle collects the reference relative distance. If it is determined that the duration of the average speed of the traffic in the self-vehicle lane being less than the first speed threshold (for example, 30 km / h) reaches a first duration (the first duration is, for example, 100 seconds or 120 seconds, etc.) and / or the duration of the reference relative distance being less than the first distance threshold (for example, 10m or 15m) reaches a second duration (the second duration is, for example, 100 seconds or 120 seconds, etc.), the self-vehicle lane congestion identification result is determined to be congested. On the contrary, if it is determined that the duration of the average speed of the traffic in the self-vehicle lane being less than the first speed threshold does not reach the first duration and / or the duration of the reference relative distance being less than the first distance threshold does not reach the second duration, the self-vehicle lane congestion identification result is determined to be uncongested.

[0040] Similarly, the traffic flow in the adjacent lane may refer to the second related vehicles within a certain range in the adjacent lane, and the average speed of the second related vehicles is used as the average speed of the traffic flow in the adjacent lane. For example, the certain range of the adjacent lane may be 30 meters before and after the vehicle, and for another example, the second related vehicles may include the nearest neighboring vehicle in the adjacent lane, the preceding vehicle in the adjacent lane (the vehicle followed by the nearest neighboring vehicle), and the preceding vehicle in the adjacent lane (the vehicle followed by the preceding vehicle in the adjacent lane).

[0041] The space occupancy rate of the adjacent vehicle lane may refer to the space occupancy rate within a certain range of the adjacent vehicle lane. For example, the certain range may be 20 meters before and after the vehicle.

[0042] The vehicle can collect the speed of the traffic in the adjacent lane and determine the average speed of the traffic in the adjacent lane. At the same time, the vehicle determines the space occupancy of the adjacent lane. If it is determined that the average speed of the traffic in the adjacent lane is less than the second speed threshold (for example, 30 km / h) for a duration of up to a third duration (the third duration is, for example, 100 seconds or 120 seconds, etc.) and / or the space occupancy of the adjacent lane is less than the occupancy threshold (the occupancy threshold can be, for example, 60% or 70%) for a duration of up to a fourth duration (the fourth duration is, for example, 100 seconds or 120 seconds, etc.), the adjacent lane congestion recognition result is determined to be adjacent lane congestion. On the contrary, if it is determined that the average speed of the traffic in the adjacent lane is less than the second speed threshold (for example, 30 km / h) for a duration of up to a third duration (the third duration is, for example, 100 seconds or 120 seconds, etc.) and / or the space occupancy of the adjacent lane is less than the occupancy threshold (the occupancy threshold can be, for example, 60% or 70%) for a duration of up to a fourth duration (the fourth duration is, for example, 100 seconds or 120 seconds, etc.), the adjacent lane congestion recognition result is determined to be adjacent lane non-congestion.

[0043] The lane change indication information is used to indicate whether the adjacent lane is a variable lane for the vehicle. If the adjacent lane is a variable lane for the vehicle, and if the lane of the vehicle is congested but the adjacent lane is not, the vehicle can change lanes to the adjacent lane to follow the vehicle. At this time, it is determined that the vehicle is not in a congested road condition. If the adjacent lane is not a variable lane for the vehicle, and if the lane of the vehicle is congested but the adjacent lane is not, the vehicle cannot change lanes to the adjacent lane to follow the vehicle. At this time, it is determined that the vehicle is in a congested road condition. Therefore, it is necessary to combine the lane change status information to determine whether the vehicle is in a congested road condition.

[0044] In this embodiment, the lane line category of the adjacent vehicle lane and the road sign comparison result can be obtained to determine the lane change status information of the adjacent vehicle lane; the adjacent vehicle lane line is the lane line between the own vehicle lane and the adjacent vehicle lane, the road sign comparison result is the comparison result between the road sign of the own vehicle lane and the road signs of the adjacent vehicle lane and the own vehicle lane, and the adjacent vehicle lane is the lane adjacent to the own vehicle lane; wherein, if the lane line category is a dotted line and the road sign comparison result is consistent, it is determined that the lane change status information indicates that the adjacent vehicle lane is a variable lane for the own vehicle; if the lane line category is a solid line and / or the road sign comparison result is inconsistent, it is determined that the lane change status information indicates that the adjacent vehicle lane is not a variable lane for the own vehicle.

[0045] In this embodiment, the road sign may refer to a guide line sign in a lane, and the road sign may be, for example, a straight sign, a left turn sign, a right turn sign, a U-turn sign, etc.

[0046] The lane line category of dashed line means that the lane change to the adjacent lane is compliant, and the road sign comparison result is consistent, which means that the lane change to the adjacent lane does not need to change the driving behavior of the vehicle. Therefore, when the lane line category is dashed line and the road sign comparison result is consistent, it is determined that the lane change state information indicates that the adjacent lane is the variable lane of the vehicle. On the contrary, the lane line category of realization means that the lane change to the adjacent lane is not compliant, so it is determined that the lane change state information indicates that the adjacent lane is not the variable lane of the vehicle. At the same time, the road sign comparison result is inconsistent, which means that the lane change to the adjacent lane of the vehicle may need to change the driving behavior of the vehicle. Therefore, it is determined that the lane change state information indicates that the adjacent lane is not the variable lane of the vehicle.

[0047] In this embodiment, when the self-lane congestion recognition result is that the self-lane is congested and the lane change status information indicates that the adjacent lane is not a lane that the self-lane can change, it means that the self-lane is congested and there is no way to change lanes, and the self-lane is determined to be in a congested road condition. When the self-lane congestion recognition result is that the self-lane is congested and the lane change status information indicates that the adjacent lane is a lane that the self-lane can change, and the adjacent lane congestion recognition result is that the adjacent lane is congested, it means that the self-lane is congested and it is still congested after changing lanes to the adjacent lane, and the self-lane is determined to be in a congested road condition.

[0048] On the contrary, if the self-lane congestion identification result is that the self-lane lane is not congested, it is determined that the self-lane is in a non-congested road condition; if the self-lane congestion identification result is that the self-lane lane is congested, the lane change status information indicates that the adjacent vehicle lane is a changeable lane for the self-lane, and the adjacent vehicle lane congestion identification result is that the adjacent vehicle lane is not congested, it means that the self-lane lane is congested, and after changing lanes to the adjacent vehicle lane, it is not congested, and it is determined that the self-lane is in a non-congested road condition. At this time, the self-lane can be controlled to change lanes to the adjacent vehicle lane, and follow the vehicle according to the driving rules under non-congested road conditions.

[0049] Generally speaking, during the driving process of the vehicle, if the trajectory of the vehicle is planned at each time point, each current time point can be used as the starting time point of the planning period for the trajectory planning of the vehicle, and the first planning period refers to each planning period with the current time point as the starting time point, that is, when each time point is reached, the time point is used as the starting time point of the first planning period. The duration of the first planning period is not limited in this application, and the duration of the first planning period is, for example, 3s or 5s.

[0050] If the trajectory of the vehicle is planned at intervals of a certain number of time points, each time point used for planning the trajectory can be used as the starting time point of the planning period for the trajectory planning of the vehicle, that is, when each time point used for planning the trajectory is reached, the time point is determined as the starting time point of the first planning period.

[0051] In this embodiment, the interval between adjacent time points can be set based on demand. For example, if the interval between adjacent time points is 0.2s, if the trajectory of the vehicle is planned at each time point, it means that the trajectory of the vehicle is planned every 0.2s. If the trajectory of the vehicle is planned at four time points, it means that the trajectory of the vehicle is planned every 1s.

[0052] The first time point may refer to any time point after the start time point of the first planning period. For example, a time point 0.4s or 0.6s away from the start time point of the first planning period may be selected as the first time point.

[0053] That is to say, the vehicle state at the first time point after the start time point of the first planning period (that is, the future time point after the start time point of the first planning period) is selected as the initial state at the start time point of the first planning period to achieve a preview of the vehicle state.

[0054] In this embodiment, the vehicle state may include the vehicle's speed, acceleration, heading angle, angular velocity and position information, etc. Therefore, the initial state at the starting time point of the first planning period may include the vehicle's speed, acceleration, heading angle, angular velocity and position information, etc. at the first time point, and the initial state at the starting time point of the first planning period may also include the vehicle's speed, acceleration, heading angle, angular velocity and position information, etc. at the first time point.

[0055] In some other embodiments, the vehicle state can be divided into a lateral vehicle state or a longitudinal vehicle state. In this case, the longitudinal vehicle state of the vehicle at the first time point and the longitudinal vehicle state of the vehicle following the vehicle at the first time point can be obtained as the initial longitudinal state at the start time point of the first planning period, and the lateral vehicle state of the vehicle at the start time point of the first planning period and the lateral vehicle state of the vehicle following the vehicle at the start time point of the first planning period can be obtained as the initial lateral state at the start time point of the first planning period. The initial lateral state and the initial longitudinal state at the start time point of the first planning period are summarized to obtain the initial state at the start time point of the first planning period. Among them, the lateral refers to the lateral direction of the vehicle body (that is, the L-axis direction of the SL coordinate system), and the longitudinal refers to the longitudinal direction of the vehicle body (that is, the S-axis direction of the SL coordinate system).

[0056] Therefore, when the current time point is used as the starting time point of the first planning period, it is only necessary to predict the longitudinal state and obtain the horizontal state at the current time point to determine the initial state of the starting time point of the first planning period, thereby reducing the amount of data that needs to be predicted and improving the efficiency of obtaining the initial state of the starting time point of the first planning period.

[0057] S120: predicting a trajectory of the vehicle in the first planning period according to the initial state.

[0058] That is to say, when the vehicle is in a congested road condition, the trajectory planning module of the vehicle plans the trajectory according to the initial state at the start time point of the first planning period to determine the predicted trajectory of the vehicle in the first planning period.

[0059] Of course, when planning the predicted trajectory of the vehicle in the first planning period, the speed of the preceding vehicle can also be used as the speed limit, and the predicted trajectory of the vehicle in the first planning period can be predicted based on the speed limit and the initial state.

[0060] However, the speed of the preceding vehicle may change in real time. Therefore, to predict the predicted trajectory of the vehicle in the first planning period, it is necessary to combine the speed limits at different time points in the first planning period to predict the predicted trajectory of the vehicle in the first planning period.

[0061] In this embodiment, it is determined that the vehicle is in a congested road condition, and a preview of the vehicle state is performed - the vehicle state after the start time point of the first planning period is used as the initial state corresponding to the start time point, and based on the initial state after preview, the trajectory is predicted to obtain the predicted trajectory of the first planning period, thereby realizing the trajectory planning under congested road conditions. Secondly, the vehicle state is also previewed to ensure that the vehicle can respond to the change of the motion state of the preceding vehicle in advance, improve the response speed of the vehicle, reduce the peak acceleration and deceleration of the vehicle, and effectively improve the ride comfort of the vehicle under congested road conditions, so that the safety and comfort of the trajectory planned under congested road conditions are both high; at the same time, through the preview processing, the response speed of the vehicle is improved, and the situation where the congested scene is constantly blocked by the adjacent vehicles can be reduced.

[0062] In one embodiment, if Figure 3 As shown, before S120, the method further includes:

[0063] S210, obtaining a reference following time distance and a reference collision distance of the vehicle under non-congested road conditions; lowering the reference following time distance and the reference collision distance to obtain a target following time distance and a target collision distance.

[0064] Following distance refers to the minimum safe distance between the vehicle in front and the vehicle in front when the vehicle is following the vehicle in front (the vehicle in front refers to the vehicle that the vehicle is following) safely. The collision distance refers to the minimum safe distance between the vehicle in front and other vehicles without collision. The reference following distance refers to the following distance of the vehicle in non-congested road conditions, and the reference reference collision distance refers to the collision distance of the vehicle in non-congested road conditions. Among them, the reference following distance and the reference collision distance can be set according to demand. Generally speaking, the reference following distance of the vehicle in non-congested road conditions is 3m, and the reference collision distance of the vehicle in non-congested road conditions is 2m.

[0065] After obtaining the reference following time distance and the reference collision distance, the reference following time distance and the reference collision distance can be lowered, and the lowered reference following time distance is obtained as the target following time distance, and the lowered reference collision distance is obtained as the target collision distance.

[0066] In some embodiments, the reference following time distance and the reference collision distance can be adjusted down by fixed values ​​to obtain the lowered target following time distance and target collision distance. For example, when the reference following time distance is 3m, the target following time distance is 2.5m, and when the reference collision distance is 2m, the target collision distance is 1.5m.

[0067] In some other embodiments, the reference following time distance and the reference collision distance may be lowered according to the speed of the vehicle to obtain the target following time distance and the target collision distance.

[0068] For example, multiple speed intervals can be set, and a mapping relationship between the following distance adjustment value and the collision distance reduction value can be established for each speed interval. Then, the speed interval in which the vehicle's speed is located is determined as the target speed interval, and the following distance adjustment value corresponding to the target speed interval is obtained as the target following distance adjustment value. The target following distance adjustment value is then subtracted from the reference following distance to obtain the target following distance. Similarly, the collision distance adjustment value corresponding to the target speed interval is obtained as the target collision distance adjustment value. The target collision distance adjustment value is then subtracted from the reference collision distance to obtain the target collision distance.

[0069] Of course, it is also possible to directly set the first functional relationship between the vehicle speed and the following distance reduction value, and the second functional relationship between the vehicle speed and the collision distance reduction value. The target following distance reduction value can be determined directly based on the vehicle speed and the first functional relationship, and the target collision distance reduction value can be determined based on the vehicle speed and the second functional relationship.

[0070] In other embodiments, the reference following distance and the minimum following distance (a following distance less than the reference following distance) can be interpolated according to the vehicle speed, and the interpolation result is used as the target following distance. Similarly, the reference collision distance and the minimum collision distance (a collision distance less than the reference collision distance) can be interpolated according to the vehicle speed, and the interpolation result is used as the target collision distance. Here, the interpolation rule is not limited, for example, linear interpolation or nonlinear difference can be used.

[0071] It can be understood that the adjustment scheme for the reference following time distance and the reference collision distance provided in the present embodiment involves reducing the reference following time distance and the reference collision distance by a fixed value, or lowering the reference following time distance and the reference collision distance according to the vehicle speed. Therefore, if the reference following time distance and the reference collision distance are reduced by a fixed value, a fixed target following time distance and a target collision distance can be determined by determining that the vehicle is in a congested road condition, and the reference following time distance and the reference collision distance are lowered according to the vehicle speed. Then, when the vehicle is in a congested road condition, the reference following time distance and the reference collision distance are adjusted in real time in combination with the real-time speed of the vehicle, so as to determine the corresponding target following time distance and target collision distance for different vehicle speeds.

[0072] It is worth mentioning that, in the present embodiment, S210 may be executed while S110 is executed, that is, when it is determined that the vehicle is in a congested road condition, S210 is directly executed without waiting for S110 to be completed before executing S210.

[0073] Accordingly, S120 may include: predicting a predicted trajectory of the vehicle in the first planning period according to the target collision distance, the target following time distance, and the initial state.

[0074] That is to say, when the vehicle is in a congested road condition, the trajectory planning module of the vehicle plans the trajectory according to the lowered target collision distance, target following time distance and the initial state at the starting time point of the first planning period to determine the predicted trajectory of the vehicle in the first planning period.

[0075] Of course, when planning the predicted trajectory of the vehicle in the first planning period, the speed of the preceding vehicle can also be used as the speed limit. Based on the speed limit, the target collision distance, the target following time distance and the initial state, the predicted trajectory of the vehicle in the first planning period is predicted.

[0076] However, the speed of the preceding vehicle may change in real time. Therefore, to predict the predicted trajectory of the vehicle in the first planning period, it is necessary to combine the speed limits at different time points in the first planning period to predict the predicted trajectory of the vehicle in the first planning period.

[0077] Since the predicted trajectory of the vehicle in the first planning period is determined based on the target collision distance, target following time distance and initial state obtained when the vehicle is in congested road conditions, the predicted trajectory of the vehicle in the first planning period is more consistent with the congested road conditions, the predicted trajectory of the vehicle in the first planning period is more accurate, and the vehicle is safer and more comfortable when driving according to the predicted trajectory in the first planning period.

[0078] In this embodiment, it is determined that the vehicle is in a congested road condition, that is, the reference following time distance and reference collision distance under non-congested road conditions are lowered to reduce the following time distance and collision distance under congested road conditions, and obtain the target following time distance and target collision distance. At the same time, a preview of the vehicle state is also performed - the vehicle state after the start time point of the first planning period is used as the initial state corresponding to the start time point, and trajectory prediction is performed based on the lowered target following time distance, the lowered target collision distance and the initial state after preview to obtain the predicted trajectory for the first planning period, thereby realizing trajectory planning under congested road conditions. Secondly, under congested road conditions, the collision distance and following time distance used for trajectory planning are adjusted to make the relevant parameters consistent with the congested road conditions, ensuring that the ego vehicle follows the vehicle in front closely, reducing the situation where the ego vehicle is constantly squeezed in by other vehicles in congested scenarios. Furthermore, the vehicle status is previewed to ensure that the ego vehicle can respond to changes in the motion state of the vehicle in front in advance, thereby improving the response speed of the ego vehicle and reducing the peak acceleration and deceleration of the ego vehicle, effectively improving the ride comfort of the ego vehicle under congested road conditions, and making the safety and comfort of the trajectory planned under congested road conditions higher. At the same time, through the preview processing, the response speed of the ego vehicle is improved, and the situation where the ego vehicle is constantly squeezed in by other vehicles in congested scenarios can be reduced.

[0079] In some embodiments, Figure 4 As shown, after S120, the method further includes:

[0080] S310: When the vehicle is traveling along the predicted trajectory in the first planning period, if it is determined that the leading vehicle is decelerating, a first reference acceleration and a first reference vehicle speed are obtained as a first vehicle state of the vehicle at the start time of the second planning period.

[0081] Among them, the front vehicle is the vehicle followed by the own vehicle; the first reference acceleration is the smaller of the acceleration of the own vehicle at the second time point and the specified acceleration, and the first reference vehicle speed is the speed of the chassis of the own vehicle at the second time point; the second time point is later than the starting time point of the second planning period; the starting time point of the second planning period is the time point for determining that the front vehicle decelerates.

[0082] During the driving process of the vehicle based on the predicted trajectory of the first planning period, it is determined that the vehicle in front is decelerating, and the time point when the vehicle in front is determined to be decelerating is used as the starting time point of the second planning period. Therefore, the second planning period may refer to a starting time point after the starting time point of the first planning period, and the duration of the second planning period and the first planning period may be the same.

[0083] The second time point refers to any time point after the start time point of the second planning period. Similar to the above, a time point 0.4s or 0.6s from the start time point of the second planning period can also be selected as the second time point.

[0084] In this embodiment, the acceleration of the vehicle can be positive or negative. A positive acceleration means that the vehicle is accelerating, and a negative acceleration means that the vehicle is decelerating. A positive acceleration is greater than a negative acceleration. Accordingly, the specified acceleration can be zero. Thus, when the vehicle is accelerating or moving at a constant speed at the second time point, the reference acceleration is determined to be zero. When the vehicle is decelerating at the second time point, the reference acceleration is determined to be a negative acceleration when the vehicle is decelerating.

[0085] Compared with the mass point of the ego vehicle, the chassis of the ego vehicle responds to the control of the ego vehicle more quickly to change the motion state. Therefore, when the front vehicle decelerates, the speed of the chassis of the ego vehicle at the second time point is determined as the first reference speed to speed up the response speed of the control to the planning, further improve the ego vehicle's response to the speed change of the front vehicle, reduce the possibility of collision between the ego vehicle and the front vehicle, and improve the driving safety of the ego vehicle.

[0086] Of course, the first vehicle state of the vehicle at the starting time point of the second planning period may also include position information, heading angle and angular velocity, and the position information, heading angle and angular velocity may all be the position information, heading angle and angular velocity of the vehicle at the second time point.

[0087] S320: Determine a predicted trajectory of the ego vehicle in a second planning period according to the first ego vehicle state, a reference following time distance, and a first vehicle speed limit.

[0088] The first speed limit is greater than the speed of the preceding vehicle. Generally speaking, the speed of the preceding vehicle can be multiplied by a fixed speed coefficient, and the product is used as the first speed limit. For example, the speed coefficient is 1.3 or 1.5.

[0089] That is to say, when it is determined that the leading vehicle is decelerating, the trajectory planning for the second planning period is performed according to the first self-vehicle state at the start time of the second planning period, the reference following time distance and the first speed limit, and the predicted trajectory of the self-vehicle in the second planning period is obtained. The trajectory planning based on the target following time distance is no longer continued. At this time, the collision distance used to plan the predicted trajectory for the second planning period is the aforementioned target collision distance.

[0090] That is, when determining that the leading vehicle is decelerating, the predicted trajectory of the second planning period is determined based on the first vehicle state at the starting time point of the second planning period, the vehicle state of the leading vehicle at the second time point, the reference following time distance, the target collision distance and the first vehicle speed limit.

[0091] However, the speed of the vehicle in front may change in real time, and the determined first speed limit will also change in real time. Therefore, to determine the predicted trajectory of the vehicle in the second planning period, it is necessary to combine the first speed limit at different time points in the second planning period to determine the predicted trajectory of the vehicle in the second planning period.

[0092] In this embodiment, when the ego vehicle decelerates, a first reference acceleration and a first reference speed are obtained as the first ego vehicle state at the starting time point of the second planning period, and a first speed limit value that is greater than the speed of the leading vehicle is obtained. Then, based on the first ego vehicle state, the reference following distance and the first speed limit value, the predicted trajectory of the ego vehicle in the second planning period is determined, thereby achieving the purpose of adjusting the trajectory planning strategy in real time according to the deceleration state of the leading vehicle, so that the determined predicted trajectory of the ego vehicle in the second planning period is more in line with the real-time road conditions, the predicted trajectory of the ego vehicle in the second planning period is more accurate, and the ego vehicle is safer when driving according to the predicted trajectory in the second planning period.

[0093] Secondly, the selected reference vehicle speed is the speed of the chassis of the ego vehicle, which speeds up the response speed of the control to the planning, further improves the response of the ego vehicle to the speed change of the front vehicle, reduces the possibility of collision between the ego vehicle and the front vehicle, and improves the driving safety of the ego vehicle.

[0094] Furthermore, by determining the deceleration status of the vehicle in front, the initial planning status and speed limit information are changed accordingly, so that the vehicle can slow down in advance, avoiding discomfort such as setbacks caused by large deceleration, and improving the riding experience in congested scenarios.

[0095] In one embodiment, if Figure 5 As shown, after S120, the method further includes:

[0096] S410: When the vehicle is traveling along the predicted trajectory of the first planning period, if it is determined that the leading vehicle is accelerating, a second reference acceleration and a second reference vehicle speed are obtained as a second vehicle state of the vehicle at the start time of the third planning period.

[0097] Among them, the front vehicle is the vehicle followed by the own vehicle; the second reference acceleration is the smaller of the acceleration of the own vehicle at the third time point and the specified acceleration; the second reference vehicle speed is the speed of the chassis of the own vehicle at the third time point; the third time point is later than the starting time point of the third planning period; the starting time point of the third planning period is the time point for determining the acceleration of the front vehicle.

[0098] During the driving process of the vehicle based on the predicted trajectory of the first planning period, it is determined that the front vehicle is accelerating, and the time point when the front vehicle is accelerating is determined as the starting time point of the third planning period. Therefore, the third planning period can refer to a starting time point after the starting time point of the first planning period, and the duration of the third planning period and the first planning period can be the same.

[0099] The third time point refers to any time point after the start time point of the third planning period. Similar to the above, a time point 0.4s or 0.6s from the start time point of the third planning period can also be selected as the third time point.

[0100] Compared with the mass point of the ego vehicle, the chassis of the ego vehicle responds to the control of the ego vehicle more quickly to change the motion state. Therefore, when the front vehicle decelerates, the speed of the chassis of the ego vehicle at the third time point is determined as the second reference speed to speed up the response speed of the control to the planning, further improve the response of the ego vehicle to the speed change of the front vehicle, reduce the possibility of collision between the ego vehicle and the front vehicle, and improve the driving safety of the ego vehicle.

[0101] Of course, the second vehicle state at the starting time point of the third planning period may also include position information, heading angle and angular velocity, and the position information, heading angle and angular velocity may all be the position information, heading angle and angular velocity of the vehicle at the third time point.

[0102] S420: Determine a predicted trajectory of the ego vehicle in a third planning period according to the second ego vehicle state, a reference following distance, and a second vehicle speed limit.

[0103] The second speed limit is the speed of the preceding vehicle.

[0104] That is, when it is determined that the leading vehicle is accelerating, the trajectory planning for the third planning period is performed according to the second vehicle state, the target following distance and the second vehicle speed limit at the start time of the third planning period, and the predicted trajectory of the vehicle in the third planning period is obtained. At this time, the collision distance used to plan the predicted trajectory for the third planning period is the aforementioned target collision distance.

[0105] That is, when determining that the leading vehicle is accelerating, the predicted trajectory of the third planning period is determined based on the second vehicle state of the leading vehicle at the starting time point of the third planning period, the vehicle state of the leading vehicle at the third time point, the target following time distance, the target collision distance and the second vehicle speed limit.

[0106] Similar to the aforementioned embodiment, the speed of the leading vehicle may change in real time, and the determined second speed limit may also change in real time. Therefore, to determine the predicted trajectory of the vehicle in the third planning period, it is necessary to combine the second speed limit at different time points in the third planning period to determine the predicted trajectory of the vehicle in the third planning period.

[0107] In this embodiment, when the ego vehicle accelerates, the second reference acceleration and the second reference speed are obtained as the second ego vehicle state at the starting time point of the second planning period, and the speed of the leading vehicle is obtained as the second speed limit. Then, based on the second ego vehicle state, the target following distance and the second speed limit, the predicted trajectory of the ego vehicle in the third planning period is determined, thereby achieving the purpose of adjusting the trajectory planning strategy in real time according to the acceleration state of the leading vehicle, so that the determined predicted trajectory of the ego vehicle in the third planning period is more in line with the real-time road conditions, the predicted trajectory of the ego vehicle in the third planning period is more accurate, and the ego vehicle is safer when driving according to the predicted trajectory in the third planning period.

[0108] Furthermore, by determining the acceleration status of the vehicle in front, the initial planning status and speed limit information are changed accordingly, so that the vehicle can accelerate in advance, avoid discomfort such as setbacks caused by large acceleration, and improve the riding experience in congested scenarios.

[0109] In one embodiment, if Figure 6 As shown, before S310, the method further includes:

[0110] S510: Obtain a first vehicle speed difference, a second vehicle speed difference, a first acceleration difference, and a second acceleration difference.

[0111] Among them, the first speed difference is the speed difference between the speed of the front vehicle and the speed of the own vehicle at the fourth time point; the second speed difference is the speed difference between the speed of the front vehicle and the speed of the own vehicle at the fifth time point; the first acceleration difference is the acceleration difference between the acceleration of the front vehicle and the acceleration of the own vehicle at the fourth time point; the second acceleration difference is the acceleration difference between the acceleration of the front vehicle and the acceleration of the own vehicle at the fifth time point; the fourth time point is earlier than the fifth time point.

[0112] Typically, during the driving process of the vehicle based on the predicted trajectory of the first planning period, the first time point of any two adjacent time points can be used as the fourth time point, and the second time point of any two adjacent time points can be used as the fifth time point. In other words, during the driving process of the vehicle based on the predicted trajectory of the first planning period, the driving state of the vehicle is monitored in real time to determine the first vehicle speed difference, the second vehicle speed difference, the first acceleration difference, and the second acceleration difference obtained at any two adjacent time points.

[0113] S520: If the first vehicle speed difference is greater than the first vehicle speed difference threshold, the first acceleration difference is greater than the first acceleration difference threshold, the second vehicle speed difference is less than the second vehicle speed difference threshold, and the second acceleration difference is less than the second acceleration difference threshold, it is determined that the leading vehicle is decelerating at the fifth time point.

[0114] S530: If the first vehicle speed difference is less than the second vehicle speed difference threshold, the first acceleration difference is less than the second acceleration difference threshold, the second vehicle speed difference is greater than the first vehicle speed difference threshold, and the second acceleration difference is greater than the first acceleration difference threshold, it is determined that the leading vehicle is accelerating at the fifth time point.

[0115] The first vehicle speed difference threshold is greater than the second vehicle speed difference threshold; the first acceleration difference threshold is greater than the second acceleration difference threshold. The first vehicle speed difference threshold, the second vehicle speed difference threshold, the first acceleration difference threshold and the second acceleration difference threshold can be set based on demand. For example, the first vehicle speed difference threshold is 0.5 km / h, the second vehicle speed difference threshold is -0.5 km / h, and the first acceleration difference threshold is 0.3 m / s 2 , the second acceleration difference threshold is -0.3m / s 2 .

[0116] That is, when the speed difference and acceleration difference between the own vehicle and the preceding vehicle become smaller, it is determined that the preceding vehicle is decelerating, and when the speed difference and acceleration difference between the own vehicle and the preceding vehicle become larger, it is determined that the preceding vehicle is accelerating.

[0117] like Figure 7 As shown, Figure 7 Among them, flag1 is the state boundary line when the vehicle speed difference is greater than the first vehicle speed difference threshold and the acceleration difference is greater than the first acceleration difference threshold, and flag2 is the state boundary line when the vehicle speed difference is less than the second vehicle speed difference threshold and the acceleration difference is less than the second acceleration difference threshold. Therefore, for any two adjacent time points, if the previous time point is flag1 and the next time point is flag2, it is determined that the front vehicle decelerates at the next time point. Similarly, if the previous time point is flag2 and the next time point is flag3, it is determined that the front vehicle accelerates at the next time point.

[0118] In this embodiment, a means for determining whether the leading vehicle is accelerating or decelerating is provided, so as to quickly determine the driving state of the leading vehicle, and then adjust the trajectory planning strategy of the own vehicle according to the driving state of the leading vehicle, thereby improving the response speed of the own vehicle.

[0119] In one embodiment, after S120, the method further includes: when the ego vehicle is driving according to the predicted trajectory of the first planning period, if it is detected that a neighboring vehicle is cutting in into the gap ahead, the ego vehicle is controlled to slow down and shift toward the target side; the neighboring vehicle refers to a vehicle located in an adjacent lane; the adjacent lane is a lane adjacent to the ego vehicle's lane; the gap ahead is the gap between the ego vehicle and the vehicle in front; the vehicle in front is the vehicle followed by the ego vehicle; and the target side is laterally away from the neighboring vehicle.

[0120] That is to say, when the car next to you cuts in, your car slows down while also avoiding the car laterally - shifting to the target side away from the car next to you, so as to ensure the safety of your car and avoid collision, while appropriately increasing the riding comfort and sense of security of the passengers, thereby improving the autonomous driving experience of your car.

[0121] In one embodiment, the trajectory planning process is as follows Figure 8 As shown, first obtain relevant information, wherein the relevant information may include information for determining whether the own vehicle lane is congested, whether the adjacent vehicle lane is congested, and whether the own vehicle can change lanes to the adjacent vehicle lane. If it is determined based on the relevant information that the own vehicle lane is not congested, then control the own vehicle to follow the front vehicle. If it is determined based on the relevant information that the own vehicle lane is congested, continue to determine whether the adjacent vehicle lane is congested (the own vehicle can change lanes to the adjacent vehicle lane), and the adjacent vehicle lane is not read, and change lanes to the adjacent vehicle lane to follow the vehicle. If the adjacent vehicle lane is congested, shorten the following distance and the collision distance (that is, determine a target following distance that is lower than the reference following distance, and determine a target following distance that is lower than the reference collision distance), and plan the trajectory in combination with the previewed vehicle state (that is, the vehicle state at the first time point is used as the initial state at the start time point of the first planning period) to obtain a predicted trajectory in the first planning period.

[0122] Afterwards, the trajectory planning parameters can be updated according to the deceleration state or acceleration state of the leading vehicle (that is, in the aforementioned embodiment, different vehicle states, following distances and speed limits are used when the leading vehicle accelerates or decelerates) to perform trajectory planning.

[0123] You can also slow down and make sideways avoidance when the car next to you cuts in to ensure safe driving.

[0124] See attached Fig. 9 , Fig. 9 The structure block diagram of a trajectory planning device proposed in one embodiment of the present application is shown. For a vehicle, the device 800 includes:

[0125] The acquisition module 810 is used to predict the vehicle state of the vehicle at a first time point and the vehicle state of the preceding vehicle followed by the vehicle at the first time point when the vehicle is in a congested road condition, as the initial state at the start time point of the first planning period; the first time point is after the start time point of the first planning period;

[0126] The planning module 820 is used to predict the predicted trajectory of the vehicle in the first planning period according to the initial state.

[0127] Optionally, the acquisition module 810 is also used to obtain a reference following time distance and a reference collision distance of the vehicle under non-congested road conditions; lower the reference following time distance and the reference collision distance to obtain a target following time distance and a target collision distance; correspondingly, the planning module 820 is also used to predict the predicted trajectory of the vehicle in the first planning period based on the target collision distance, the target following time distance and the initial state.

[0128] Optionally, the planning module 820 is also used to obtain a first reference acceleration and a first reference speed as the first self-vehicle state at the start time point of the second planning period if it is determined that the leading vehicle is decelerating during the driving process of the self-vehicle based on the predicted trajectory of the first planning period; the leading vehicle is the vehicle followed by the self-vehicle; the first reference acceleration is the smaller of the acceleration of the self-vehicle at the second time point and the specified acceleration, and the first reference speed is the speed of the chassis of the self-vehicle at the second time point; the second time point is later than the start time point of the second planning period; the start time point of the second planning period is the time point when it is determined that the leading vehicle is decelerating; the predicted trajectory of the self-vehicle in the second planning period is determined based on the first self-vehicle state, the reference following time distance and the first speed limit; the first speed limit is greater than the speed of the leading vehicle.

[0129] Optionally, the planning module 820 is also used to obtain a second reference acceleration and a second reference vehicle speed as the second self-vehicle state at the starting time point of the third planning period if it is determined that the leading vehicle is accelerating during the driving process of the self-vehicle based on the predicted trajectory of the first planning period; the leading vehicle is the vehicle followed by the self-vehicle; the second reference acceleration is the smaller of the acceleration of the self-vehicle at the third time point and the specified acceleration, and the second reference vehicle speed is the speed of the chassis of the self-vehicle at the third time point; the third time point is later than the starting time point of the third planning period; the starting time point of the third planning period is the time point when it is determined that the leading vehicle is accelerating; the predicted trajectory of the self-vehicle in the third planning period is determined based on the second self-vehicle state, the reference following time distance and the second speed limit; the second speed limit is the speed of the leading vehicle.

[0130] Optionally, the planning module 820 is further used to obtain a first vehicle speed difference, a second vehicle speed difference, a first acceleration difference, and a second acceleration difference; the first vehicle speed difference is the speed difference between the speed of the preceding vehicle and the speed of the own vehicle at the fourth time point; the second vehicle speed difference is the speed difference between the speed of the preceding vehicle and the speed of the own vehicle at the fifth time point; the first acceleration difference is the acceleration difference between the acceleration of the preceding vehicle and the acceleration of the own vehicle at the fourth time point; the second acceleration difference is the acceleration difference between the acceleration of the preceding vehicle and the acceleration of the own vehicle at the fifth time point; the fourth time point is earlier than the fifth time point; if the first vehicle speed difference is greater than the fifth time point, the vehicle speed difference between the preceding vehicle and the acceleration of the own vehicle is greater than the fifth time point. If the speed difference is greater than the first vehicle speed difference threshold, the first acceleration difference is greater than the first acceleration difference threshold, the second vehicle speed difference is less than the second vehicle speed difference threshold, and the second acceleration difference is less than the second acceleration difference threshold, it is determined that the leading vehicle is decelerating at the fifth time point; the first vehicle speed difference threshold is greater than the second vehicle speed difference threshold; the first acceleration difference threshold is greater than the second acceleration difference threshold; if the first vehicle speed difference is less than the second vehicle speed difference threshold, the first acceleration difference is less than the second acceleration difference threshold, the second vehicle speed difference is greater than the first vehicle speed difference threshold, and the second acceleration difference is greater than the first acceleration difference threshold, it is determined that the leading vehicle is accelerating at the fifth time point.

[0131] Optionally, the planning module 820 is also used to detect that a neighboring vehicle is cutting in into a gap ahead during the driving process of the ego vehicle based on the predicted trajectory of the first planning period, and control the ego vehicle to slow down and shift to a target side; the neighboring vehicle refers to a vehicle located in an adjacent lane; the adjacent lane is a lane adjacent to the ego vehicle's lane; the gap ahead is the gap between the ego vehicle and the vehicle in front; the vehicle in front is the vehicle followed by the ego vehicle; and the target side is the side laterally away from the neighboring vehicle.

[0132] Optionally, the device also includes a determination module for determining a lane congestion identification result of the own vehicle lane based on an average speed of traffic in the own vehicle lane where the own vehicle is located and a reference relative distance; the reference relative distance is the relative distance between the front vehicle followed by the own vehicle and the front-front vehicle followed by the front vehicle; determining an adjacent lane congestion identification result of the adjacent lane based on the average speed of traffic in the adjacent lane adjacent to the own vehicle lane and the road space occupancy rate of the adjacent lane; determining lane change status information of the adjacent lane; the lane change indication information is used to indicate whether the adjacent lane is a lane changeable by the own vehicle; and determining whether the own vehicle is in a congested road condition based on the own lane congestion identification result, the adjacent lane congestion identification result and the lane change status information.

[0133] Optionally, the determination module is further used to determine the lane change status information of the adjacent vehicle lane based on the lane line category of the adjacent vehicle lane and the road sign comparison result; the adjacent vehicle lane line is the lane line between the own vehicle lane and the adjacent vehicle lane, the road sign comparison result is the comparison result between the road sign of the own vehicle lane and the road signs of the adjacent vehicle lane and the own vehicle lane, and the adjacent vehicle lane is the lane adjacent to the own vehicle lane; wherein, if the lane line category is a dotted line and the road sign comparison result is consistent, it is determined that the lane change status information indicates that the adjacent vehicle lane is a variable lane for the own vehicle; if the lane line category is a solid line and / or the road sign comparison result is inconsistent, it is determined that the lane change status information indicates that the adjacent vehicle lane is not a variable lane for the own vehicle.

[0134] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0135] In addition, each function in each embodiment of the present application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software function modules.

[0136] On the other hand, the present application further provides a computer-readable storage medium, in which program code is stored. The program code can be called by a processor to execute the method described in the above method embodiment.

[0137] The computer readable storage medium can be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a cluster of ROMs. Optionally, the computer readable storage medium includes a non-transitory computer-readable storage medium. The computer readable storage medium has storage space for program codes that execute any of the method steps in the above method. These program codes can be read from or written into one or more computer program products. The program code can be compressed, for example, in an appropriate form.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A trajectory planning method, characterized in that: The method comprises: In the case where the vehicle is in a congested road condition, predicting the vehicle state of the vehicle at a first time point and the vehicle state of the preceding vehicle followed by the vehicle at the first time point as the initial state at the start time point of the first planning period; the first time point is after the start time point of the first planning period; According to the initial state, a predicted trajectory of the vehicle in the first planning period is predicted.

2. The method according to claim 1, characterized in that: Before predicting the predicted trajectory of the ego vehicle in the first planning period according to the target collision distance, the target following time distance and the initial state, the method further includes: Obtaining a reference following distance and a reference collision distance of the vehicle under non-congested road conditions; Lowering the reference following time distance and the reference collision distance to obtain a target following time distance and a target collision distance; The predicting the predicted trajectory of the vehicle in the first planning period according to the target collision distance, the target following time distance and the initial state includes: A predicted trajectory of the ego vehicle in the first planning period is predicted according to the target collision distance, the target following time distance, and the initial state.

3. The method according to claim 2, characterized in that After predicting the predicted trajectory of the vehicle in the first planning period according to the target collision distance, the target following time distance and the initial state, the method further includes: During the driving process of the self-vehicle based on the predicted trajectory of the first planning period, if it is determined that the leading vehicle is decelerating, a first reference acceleration and a first reference vehicle speed are obtained as the first self-vehicle state of the self-vehicle at the starting time point of the second planning period; the leading vehicle is a vehicle followed by the self-vehicle; the first reference acceleration is the smaller of the acceleration of the self-vehicle at the second time point and the specified acceleration, and the first reference vehicle speed is the speed of the chassis of the self-vehicle at the second time point; the second time point is later than the starting time point of the second planning period; the starting time point of the second planning period is the time point when it is determined that the leading vehicle is decelerating; A predicted trajectory of the ego vehicle in the second planning period is determined according to the first ego vehicle state, the reference following distance, and a first speed limit; the first speed limit is greater than the speed of the leading vehicle.

4. The method according to claim 2, characterized in that: After predicting the predicted trajectory of the vehicle in the first planning period according to the target collision distance, the target following time distance and the initial state, the method further includes: During the driving process of the self-vehicle based on the predicted trajectory of the first planning period, if it is determined that the leading vehicle is accelerating, a second reference acceleration and a second reference vehicle speed are obtained as the second self-vehicle state of the self-vehicle at the starting time point of the third planning period; the leading vehicle is a vehicle followed by the self-vehicle; the second reference acceleration is the smaller of the acceleration of the self-vehicle at the third time point and the specified acceleration, and the second reference vehicle speed is the speed of the chassis of the self-vehicle at the third time point; the third time point is later than the starting time point of the third planning period; the starting time point of the third planning period is the time point when it is determined that the leading vehicle is accelerating; The predicted trajectory of the ego vehicle in the third planning period is determined according to the second ego vehicle state, the reference following distance and a second speed limit; the second speed limit is the speed of the leading vehicle.

5. The method according to claim 3 or 4, characterized in that: The method further comprises: Obtaining a first vehicle speed difference, a second vehicle speed difference, a first acceleration difference, and a second acceleration difference; the first vehicle speed difference is the vehicle speed difference between the vehicle speed of the preceding vehicle and the vehicle speed of the own vehicle at a fourth time point; the second vehicle speed difference is the vehicle speed difference between the vehicle speed of the preceding vehicle and the vehicle speed of the own vehicle at a fifth time point; the first acceleration difference is the acceleration difference between the acceleration of the preceding vehicle and the acceleration of the own vehicle at a fourth time point; the second acceleration difference is the acceleration difference between the acceleration of the preceding vehicle and the acceleration of the own vehicle at a fifth time point; the fourth time point is earlier than the fifth time point; If the first vehicle speed difference is greater than a first vehicle speed difference threshold, the first acceleration difference is greater than a first acceleration difference threshold, the second vehicle speed difference is less than a second vehicle speed difference threshold, and the second acceleration difference is less than a second acceleration difference threshold, it is determined that the leading vehicle is decelerating at the fifth time point; the first vehicle speed difference threshold is greater than the second vehicle speed difference threshold; and the first acceleration difference threshold is greater than the second acceleration difference threshold; If the first vehicle speed difference is less than the second vehicle speed difference threshold, the first acceleration difference is less than the second acceleration difference threshold, the second vehicle speed difference is greater than the first vehicle speed difference threshold, and the second acceleration difference is greater than the first acceleration difference threshold, it is determined that the leading vehicle is accelerating at the fifth time point.

6. The method according to claim 1, characterized in that After predicting the predicted trajectory of the vehicle in the first planning period according to the initial state, the method further includes: During the driving process of the ego vehicle based on the predicted trajectory of the first planning period, it is detected that a neighboring vehicle is cutting in at a gap ahead, and the ego vehicle is controlled to slow down and shift to a target side; the neighboring vehicle refers to a vehicle located in an adjacent vehicle lane; the adjacent vehicle lane is a lane adjacent to the ego vehicle lane where the ego vehicle is located; the gap ahead is a gap between the ego vehicle and a preceding vehicle; the preceding vehicle is a vehicle followed by the ego vehicle; and the target side is a side laterally away from the neighboring vehicle.

7. The method according to claim 1, characterized in that Before predicting the vehicle state of the vehicle at a first time point and the vehicle state of a preceding vehicle followed by the vehicle at the first time point when the vehicle is in a congested road condition as the initial state at the start time point of the first planning period, the method further includes: Determine a lane congestion recognition result of the lane based on an average vehicle speed of the vehicle flow in the lane where the vehicle is located and a reference relative distance; the reference relative distance is a relative distance between a preceding vehicle followed by the vehicle and a preceding preceding vehicle followed by the preceding vehicle; Determining a congestion recognition result of an adjacent lane of the adjacent lane based on an average vehicle speed of a vehicle flow in an adjacent lane adjacent to the own vehicle lane and a road space occupancy rate of the adjacent lane; Determine the lane change status information of the adjacent vehicle lane; the lane change indication information is used to indicate whether the adjacent vehicle lane is a lane changeable by the own vehicle; Based on the congestion identification result of the own lane, the congestion identification result of the adjacent vehicle lane and the lane change status information, it is determined whether the own vehicle is in a congested road condition.

8. The method according to claim 7, characterized in that The determining the lane change status information of the adjacent vehicle lane includes: Determine the lane change status information of the adjacent vehicle lane according to the lane line type and the road sign comparison result of the adjacent vehicle lane; the adjacent vehicle lane line is the lane line between the own vehicle lane and the adjacent vehicle lane, the road sign comparison result is the comparison result between the road sign of the own vehicle lane and the road sign of the adjacent vehicle lane and the own vehicle lane, and the adjacent vehicle lane is the lane adjacent to the own vehicle lane; Among them, if the lane line category is a dotted line and the road sign comparison result is consistent, it is determined that the lane change status information indicates that the adjacent vehicle lane is a variable lane for the own vehicle; if the lane line category is a solid line and / or the road sign comparison result is inconsistent, it is determined that the lane change status information indicates that the adjacent vehicle lane is not a variable lane for the own vehicle.

9. A trajectory planning device, characterized in that: The device comprises: an acquisition module, for predicting, when the vehicle is in a congested road condition, a vehicle state of the vehicle at a first time point and a vehicle state of a preceding vehicle followed by the vehicle at the first time point as an initial state at a start time point of a first planning period; the first time point is after the start time point of the first planning period; A planning module is used to predict the predicted trajectory of the vehicle in the first planning period according to the initial state.

10. A vehicle, characterized in that: include: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to execute the method according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program code executable by a processor, and when the program code is executed by the processor, the processor executes the method according to any one of claims 1 to 8.

Images