CN117585016A - Left turn path control method and device, vehicle and storage medium - Google Patents

Abstract

The embodiment of the invention relates to the technical field of automatic driving, and discloses a left-turning path control method, a left-turning path control device, a vehicle and a storage medium, wherein the method comprises the following steps: acquiring a target driving direction of the self-vehicle at the next intersection, and determining a target lane corresponding to left turn; obtaining the lane length of a target lane, wherein the lane length is the length of the target lane between a current intersection and a next intersection; and planning a path of the own vehicle from the current lane of the current intersection to the target lane based on the size relation between the lane length of the target lane and the passing threshold value. By applying the technical scheme of the invention, the error in selecting the target lane in the passable lane can be avoided, the risk of left turn failure is reduced, and the overall passing efficiency is improved.

Description

Left turn path control method and device, vehicle and storage medium

Technical Field

The embodiment of the invention relates to the technical field of automatic driving, in particular to a left-turning path control method, a left-turning path control device, a vehicle and a storage medium.

Background

In the left turn control of the driving support system (Advanced Driver Ass istance Systems, ADAS) in the related art, lane change is required to be performed a plurality of times to travel in a correct lane.

Disclosure of Invention

In view of the above problems, the embodiments of the present invention provide a left turn path control method, apparatus, vehicle and storage medium, which are used to solve the problem in the prior art that a vehicle turns left and can travel in a correct lane only by changing lanes multiple times.

According to an aspect of the embodiment of the present invention, there is provided a left turn path control method applied to a bicycle, the method including: acquiring a target driving direction of the self-vehicle at the next intersection, and determining a target lane corresponding to left turn; obtaining the lane length of a target lane, wherein the lane length is the length of the target lane between a current intersection and the next intersection; and planning a path of the own vehicle from the current lane of the current intersection to the target lane based on the magnitude relation between the lane length of the target lane and the passing threshold.

According to another aspect of the embodiment of the present invention, there is provided a left turn path control apparatus including: the lane acquisition module is used for acquiring the target driving direction of the self-vehicle at the next intersection and determining a target lane corresponding to left turn; the length acquisition module is used for acquiring the lane length of a target lane, wherein the lane length is the length of the target lane between a current intersection and the next intersection; and the path planning module is used for planning a path for the vehicle to turn left from the current lane of the current intersection to the target lane based on the magnitude relation between the lane length of the target lane and the passing threshold value.

According to another aspect of an embodiment of the present invention, there is provided a vehicle including: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus; the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation of the left-turning path control method.

According to still another aspect of the embodiments of the present invention, there is provided a computer-readable storage medium having stored therein at least one executable instruction for causing a vehicle/apparatus to perform the operations of the aforementioned one left-turn path control method.

According to the technical scheme provided by the embodiment of the invention, the target lane corresponding to the left turn is determined by acquiring the target running direction of the own vehicle at the next intersection, the path from the current lane of the own vehicle to the target lane is planned based on the size relation between the lane length of the target lane and the passing threshold value, the target running direction of the next intersection can be acquired in advance before the own vehicle turns left at the current intersection, so that the target lane of the own vehicle when turning left at the current intersection is determined, the path from the current lane of the own vehicle to the target lane is planned, and the passing efficiency of the own vehicle at the next intersection after turning left is improved.

The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and may be implemented according to the content of the specification, so that the technical means of the embodiments of the present invention can be more clearly understood, and the following specific embodiments of the present invention are given for clarity and understanding.

Drawings

The drawings are only for purposes of illustrating embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:

fig. 1 shows a schematic flow chart of a left turn path control method provided by the invention;

fig. 2 is a schematic flow chart of a left turn path control method according to the present invention;

FIG. 3 is a schematic flow chart of a left-turn path control method according to the present invention

Fig. 4 shows an application scenario diagram of a left-turn path control method provided by the invention;

fig. 5 shows a schematic structural diagram of a left-turn path control device provided by the invention;

FIG. 6 shows a schematic structural diagram of a vehicle provided by the present invention;

FIG. 7 shows another schematic structural view of a vehicle provided by the present invention;

Fig. 8 shows another schematic structural view of a vehicle provided by the present invention.

Detailed Description

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein.

Fig. 1 shows a flowchart of a first embodiment of a left-turn path control method of the present invention, which is executed by a vehicle apparatus. As shown in fig. 1, the method comprises the steps of:

step 110, the target driving direction of the self-vehicle at the next intersection is obtained, and the target lane corresponding to the left turn is determined.

In the embodiment of the invention, the target running direction of the own vehicle at the next intersection is determined by the target point and the passing point which the own vehicle needs to reach.

For example, when the own vehicle determines a target lane corresponding to left turn based on the target traveling direction of the next intersection, if the target traveling direction of the own vehicle at the next intersection is right turn, the target lane corresponding to the own vehicle at the current intersection is right turn lane; if the target running direction of the own vehicle at the next intersection is straight, the target lane corresponding to the left turn of the own vehicle at the current intersection is a straight lane.

Step 120, the lane length of the target lane is obtained.

The lane length is the length of the target lane between the current intersection and the next intersection.

In an optional mode, when the lane length of the target lane is acquired, the own vehicle can send an acquisition request to the big data traffic management platform, so that the lane length of the target lane issued by the big data traffic management platform is received, the left turn path of the own vehicle is conveniently planned, and the passing efficiency and reliability of the own vehicle at the next intersection after the left turn are improved.

In an optional manner, when the lane length of the target lane is acquired, the own vehicle can accurately determine the lane length of the target lane through an image recognition method based on the front-view camera configured by the own vehicle, and plan a left turn path of the own vehicle based on the lane length of the target lane. In addition, in some special scenarios, if the intersection signboard has a communication function, the intersection signboard can also establish communication connection with the own vehicle, so that the own vehicle directly receives the lane length of the target lane sent by the intersection signboard.

And 130, planning a path for the self-vehicle to turn left from the current lane of the current intersection to the target lane based on the magnitude relation between the lane length of the target lane and the passing threshold.

Wherein the traffic threshold is determined based on congestion information between the current intersection and the next intersection.

In an alternative way, when determining the traffic threshold, congestion information of the current road of the traffic-available lane can be acquired first, and the traffic-available lane comprises a lane between the current intersection and the next intersection; then determining the congestion level of the passable lane based on the congestion information; and determining a traffic threshold based on the congestion level and a minimum lane change threshold, wherein the minimum lane change threshold is the minimum distance required for changing lanes from the adjacent lane of the target lane to the target lane after the vehicle turns left.

Specifically, since the determination of the traffic threshold Dmin is dependent on road-level congestion information, the congestion information may be obtained from the navigation system, after the congestion information of the traffic lane is obtained, the traffic threshold Dmin may be interpolated based on the congestion information of the traffic lane, and the minimum distance Dx required for changing from the adjacent lane of the target lane to the target lane after the vehicle turns left may be considered, and the minimum distance Dx may be a fixed threshold calibrated later. The relationship between the congestion information and the congestion level of the travelable lane is shown in table 1.

TABLE 1 relationship between Congestion information and Congestion level of passable lanes

In the table, D1 > D2 > D3 > D4, that is, the higher the congestion level is, the larger the set pass threshold Dmin is, and Dmin > Dx is. In other embodiments, the congestion level may be adjusted according to actual needs.

In an optional manner, when planning a path from a current lane of a current intersection to a target lane in a left-turn manner based on a magnitude relation between a lane length of the target lane and a traffic threshold, the lane length of the target lane and the traffic threshold can be compared to obtain a threshold comparison result; and then, carrying out a path planning on the self-vehicle from the current lane to the right-turn lane according to the threshold comparison result.

Specifically, the lane length of the target lane may be compared with the traffic threshold value, so as to determine whether the lane length of the target lane is less than or equal to the traffic threshold value, and when the lane length of the target lane is less than or equal to the traffic threshold value, it indicates that after the vehicle turns left at the current intersection, if the lane turned left is not the target lane, there is not enough lane changing space to change the lane to the target lane, so that the vehicle cannot travel to the target traveling direction of the next intersection. At this time, the path planning mode is determined to be the direct left turn from the current lane to the target lane. The target lane may be unique (for example, the target driving direction is right turn, only one right turn lane into which the current lane can enter is provided), or may be non-unique (for example, the target driving direction is right turn, and a plurality of right turn lanes into which the current lane can enter are provided), and if the target lane is unique, the route of the own vehicle from the current lane to the target lane is planned directly based on the target lane; if the target lane is not unique, the distance between each target lane and the target driving direction may be determined, i.e. the target lane closest to the target driving direction is preferentially selected.

And secondly, comparing the lane length of the target lane with a traffic threshold value so as to judge whether the lane length of the target lane is larger than the traffic threshold value, and when the lane length of the target lane is larger than the traffic threshold value, indicating that the self-vehicle has enough lane changing space to change the lane to the target lane when the left-turning lane is not the target lane after the left-turning at the current intersection, thereby changing the lane to the target lane corresponding to the target running direction. At this time, determining the path planning mode includes directly turning left to the target lane and turning left to other lanes from the current lane and then changing lanes to the target lane, but because the number of changeable lane modes is large, the optimal lane changing mode can be determined based on the scores of the lane changing modes.

Compared with the left turn control mode that the vehicle can travel in the correct lane only by changing lanes for multiple times in the left turn control of the related art, the left turn path control method of the embodiment of the invention determines the target lane corresponding to the left turn by acquiring the target travel direction of the vehicle at the next intersection, plans the path from the current lane of the vehicle at the current intersection to the target lane based on the magnitude relation between the lane length of the target lane and the passing threshold value, and can acquire the target travel direction of the next intersection in advance before the vehicle turns left at the current intersection, thereby determining the target lane when the vehicle turns left at the current intersection, planning the path from the current lane to the target lane of the vehicle at the current intersection, and further improving the passing efficiency of the vehicle at the next intersection after turning left.

Fig. 2 shows a flowchart of another embodiment of the left-turn path control method of the present invention, which is performed by a vehicle device. As shown in fig. 2, the method comprises the steps of:

step 210, the target driving direction of the self-vehicle at the next intersection is obtained, and the target lane corresponding to the left turn is determined.

Please refer to step 110 in the embodiment shown in fig. 1 in detail, which is not described herein.

Step 220, the lane length of the target lane is obtained.

Please refer to step 120 in the embodiment shown in fig. 1 in detail, which is not described herein.

And 230, planning a path for the own vehicle to turn left from the current lane of the current intersection to the target lane based on the magnitude relation between the lane length of the target lane and the passing threshold.

Specifically, the step 230 includes:

in step 2301, if the lane length of the target lane is less than or equal to the traffic threshold, determining that the path planning mode is to directly turn left from the current lane to the target lane, and determining whether the target lane is unique.

Specifically, if the lane length of the target lane is smaller than or equal to the traffic threshold, it indicates that when the lane turned left after the current intersection turns left is not the target lane, there is not enough lane changing space to change the lane to the target lane, so that the vehicle cannot travel to the target travel direction of the next intersection, and therefore the path planning mode is determined to be that the vehicle directly turns left from the current lane to the target lane. Considering that the target lane may or may not be unique, in order to improve the efficiency of the vehicle entering the target traveling direction of the next intersection, it is necessary to determine the uniqueness of the target lane.

And 2302, if the target lane is unique, planning a path for the own vehicle to turn left from the current lane to the target lane based on the path planning mode.

Specifically, if the target lane is unique, the route of the vehicle from the current lane to the target lane is planned directly based on the target lane, so that the vehicle is prevented from running in the left-turn lane, when the green light is directly running, the left turn can enter the waiting area, if the route planning is to perform route fitting according to the current lane of the vehicle and the corresponding lane after the left turn enters the road, but the target lane is not selected according to the target running direction of the next intersection, and the left turn control is performed on the left-turn route planning through the corresponding relation between the position of the current lane of the vehicle and the target lane, so that the situation that part of scenes can not run in the target lane due to overlarge turning radius and insufficient passing space is caused, or the situation that the vehicle can not run in the target lane after the left turn enters the corresponding lane of the road after the road is changed for a plurality of times is avoided.

For example, if the target lane is unique, the host vehicle directly travels into the lane corresponding to the target traveling direction. The next intersection is a right-turn lane which needs to enter a passable lane (target road) if the next intersection is a right-turn, and enters a left-turn lane of the passable lane in advance if the next intersection is a left-turn; if the next intersection is straight, the target lane is the straight lane.

And 2303, if the target lane is not unique, obtaining a first path score of the vehicle from the current lane to the target lane.

Wherein the first path score is determined based on the respective target lane and the target travel direction.

Specifically, if the target lane is not unique, a first path score of the vehicle from the current lane to each target lane is obtained, so that the planning of the vehicle left-turn path is performed based on the first path score of each target lane. When determining the first path score of each target lane, determination may be made based on the distance between each right turn lane and the target travel direction of the next intersection and the congestion information of each target lane; the determination may be based only on the distance between each right turn lane and the target traveling direction of the next intersection, that is, the closer to the target traveling direction of the next intersection, the higher the score of the target lane, and no limitation is made here.

For example, if the target driving direction is right turn, the numbers of right turn lanes which can be accessed after left turn from the current lane are 3, 2 and 1 in turn, the first path of the host vehicle from the current lane to the target lane with the number of 3 is scored highest, the first path of the host vehicle from the current lane to the target lane with the number of 2 is scored a plurality of times, and the first path of the host vehicle from the left turn to the target lane with the number of 1 is scored lowest.

And 2304, planning a path for the own vehicle to turn left from the current lane to the target lane based on the path planning mode and the first path score.

Specifically, the route from the current lane to the target lane is planned based on the route planning mode and the first route score, so that the situation that the self-vehicle fails to turn left due to overlarge turning radius and insufficient passing space in part of scenes or the self-vehicle can travel in the target lane only after turning left to the corresponding lane of the road for many times if the route planning is to fit the route according to the current lane of the self-vehicle and the corresponding lane after entering the road in the left turn, but the target lane is not selected according to the target traveling direction of the next intersection, and the left turn is controlled on the route planning of the left turn according to the corresponding relation between the position of the current lane of the self-vehicle and the target lane, thereby causing part of scenes to fail in the left turn due to overlarge turning radius and insufficient passing space, or the situation that the self-vehicle can travel in the target lane after turning left to the corresponding lane of the road for many times.

In an optional manner, if the path planning manner is to directly turn left from the current lane to the target lane, when planning a path of the own vehicle from the current lane to the target lane, the step 2301 specifically includes:

Step a1, obtaining the current position point of the own vehicle.

The current position point of the own vehicle is acquired, so that the planning of a left turn path based on the current position point of the own vehicle is facilitated.

And a2, fitting the current position point of the vehicle and the central line of the target lane to obtain a fitting result.

Fitting the current position point of the vehicle and the central line of the target lane to obtain a fitting result, and providing necessary conditions for path planning of the vehicle from the current lane to the target lane.

And a step a3, planning a path of the own vehicle from the current lane to the target lane based on the fitting result.

The route of the vehicle from the current lane to the target lane is planned based on the fitting result, so that the current position point of the vehicle and the center line of the target lane can be fitted, instead of fitting according to the current driving lane and the target lane to form a target track, the vehicle can be driven by pressing the lane line, instead of carrying out track planning only according to the limiting direction of the lane line, and the situation that the turning radius is too large is avoided.

In the embodiment of the application, if the lane length of the target lane is smaller than or equal to the passing threshold, determining that the path planning mode is to directly turn left from the current lane to the target lane, determining whether the target lane is unique, if the target lane is unique, planning the path from the current lane to the target lane based on the path planning mode, and if the target lane is not unique, obtaining a first path score from the current lane to each target lane, and further improving the passing efficiency of the vehicle at the next intersection after turning left.

Fig. 3 shows a flowchart of another embodiment of the left-turn path control method of the present invention, which is performed by a vehicle device. As shown in fig. 3, the method comprises the steps of:

step 310, the target driving direction of the self-vehicle at the next intersection is obtained, and the target lane corresponding to the left turn is determined.

Please refer to step 110 in the embodiment shown in fig. 1 in detail, which is not described herein.

Step 320, the lane length of the target lane is obtained.

Please refer to step 120 in the embodiment shown in fig. 1 in detail, which is not described herein.

And 330, planning a path for the own vehicle to turn left from the current lane of the current intersection to the target lane based on the magnitude relation between the lane length of the target lane and the passing threshold.

Specifically, the step 330 includes:

in step 3301, if the lane length of the target lane is greater than the traffic threshold, determining the path planning mode includes directly turning left to the target lane and turning left from the current lane to other lanes and then changing lanes to the target lane.

Specifically, if the lane length of the target lane is greater than the passing threshold, determining that the path planning mode includes directly turning left to the target lane and turning left to other lanes from the current lane and then turning to the target lane, indicating that if the left-turned lane is not the target lane after the left-turned lane at the current intersection, enough lane changing space is still available and then turning to the target lane, so that the lane changing to the target lane corresponding to the target running direction is not unique, namely the own vehicle can enter any lane at will and then turn to the target lane; therefore, when the left turn path planning is performed, the left turn path can be planned to be directly left turned to the target lane and changed to the target lane after being left turned to other lanes from the current lane.

In step 3302, a second path score of entering the lane after the left turn corresponding to each path planning mode is obtained.

Specifically, when the path planning of the self-vehicle from the current lane to the target lane at the current intersection is performed, a second path score of directly turning left to the target lane and turning left to the target lane after turning left to other lanes from the current lane can be obtained, so that the path of the self-vehicle from the current lane to the target lane is planned based on the second path score.

In step 3303, a path for the host vehicle to turn left from the current lane of the current intersection to the target lane is planned based on the path planning mode and the second path score.

Specifically, the path from the current lane of the current intersection to the target lane is planned based on the path planning mode and the second path score, so that the situation that the self-vehicle fails to turn left due to overlarge turning radius and insufficient passing space in part of scenes or the self-vehicle enters the corresponding lane of the road for multiple times to change lanes to drive in the target lane after entering the road for the left turn can be avoided.

In an alternative manner, the step 3301 specifically includes:

and b1, obtaining path parameters of the self-vehicle from the current intersection to each lane and corresponding parameter weights.

The path parameters comprise a detour parameter, a turning failure parameter, a left turn passing time and a direct parameter of a direct target lane of the own vehicle at the left turn of the current intersection.

Specifically, the detour parameter of the left transition road of the own vehicle at the current intersection is determined by the own vehicle based on the front obstacle target of any path planned by the path planning mode, so as to obtain an evaluation result C1 value (a parameter value corresponding to the detour parameter), and the detour route value is not required to be higher. That is, the detour parameter is determined based on the number of times the detour is required before the host vehicle turns left to the passable lane (the smaller the number is, the higher the C1 value), the obstacle detour difficulty coefficient (the smoother the trajectory of the host vehicle and the higher the probability of detour success, the) and the type of obstacle detoured (the stationary obstacle type > moving cart > two-wheeled cart > pedestrian).

The turning failure parameter is that the minimum threshold value R1 and the maximum threshold value R2 are set by detecting the turning radius before the left turn to the passable lane and written in by the later-period real vehicle calibration, and the setting requirement is in the range of (R1, R2). When the turning radius is too large, the larger the required turning space is, the higher the failure probability is, the smaller the turning radius is, and the higher the failure probability is when the control limit of the vehicle is exceeded. Calculating turning radii of the tracks to obtain an evaluation result value C2 (a parameter value corresponding to a turning failure parameter), and taking a first certain value (to be calibrated) by C2 when the turning radius is in a range of (R1, R2); when the turning radius is larger than R2, the C2 value takes a value of 0; and C2 takes a second fixed value when the turning radius is smaller than R1.

The left turn passing time is calculated by detecting the information such as the path length and the vehicle speed before the left turn reaches the passable lane, and the evaluation result C3 value (the parameter value corresponding to the left turn passing time) is obtained by comparing the passing time, and the smaller the time is, the higher the C3 value is.

The direct parameter of the direct target lane is determined by the distance between the host vehicle and the target traveling direction of the next intersection after the host vehicle turns left from the current lane to each target lane, that is, the closer to the target traveling direction of the next intersection, the better the target lane is, that is, the higher the C4 value (the parameter value corresponding to the direct parameter) is. If the target driving direction is right turn, the numbers of right turn lanes which can be accessed after left turn from the current lane are 3, 2 and 1 in sequence, the first path of the own vehicle from the current lane to the target lane with the number of 3 is highest in score, the first path of the own vehicle from the current lane to the target lane with the number of 2 is scored for times, and the first path of the own vehicle from the left turn to the target lane with the number of 1 is lowest in score.

And b2, obtaining a second path score of entering the lane after the left turn corresponding to each path planning mode based on each parameter in the path parameters and the corresponding parameter weight.

Specifically, the parameter weights of the detour parameter, the turn failure parameter, the left turn passing time and the direct parameter of the direct target lane are respectively K1, K2, K3 and K4, wherein K1, K2, K3 and K4 can be set based on requirements, and when the second path score of entering the lane after the left turn corresponding to each path planning mode is obtained based on each parameter in the path parameters and the corresponding parameter weight, the second path score can be obtained by carrying out weighted summation based on each parameter in the path parameters and the corresponding parameter weight. That is, y=k1 c1+k2 c2+k3 c3+k4 c4. When the second path score is higher, the route is indicated as the optimal route.

In the embodiment of the invention, if the lane length of the target lane is greater than the passing threshold, the lane is directly left-turned to the target lane and the second path from the current lane to the other lane is scored, and the path from the current lane to the target lane of the current intersection is planned, so that the passing efficiency of the vehicle at the next intersection after the left-turned intersection is improved.

Compared with a left turn control mode that a user can drive in a correct lane only by carrying out lane change for multiple times in left turn control in the related art, the left turn path control method of the embodiment of the invention determines the target lane corresponding to left turn by acquiring the target driving direction of the user vehicle at the next intersection, plans the path from the current lane of the user vehicle at the current intersection to the target lane based on the size relationship between the lane length of the target lane and the passing threshold value, can acquire the target driving direction of the next intersection in advance before the user vehicle is left turned at the current intersection, thereby determining the target lane when the user vehicle is left turned at the current intersection, planning the path from the current lane to the target lane of the user vehicle, avoiding the error in selecting the target lane in the passable lane, reducing the risk of left turn failure and improving the overall passing efficiency.

The flow of the left-turn path control method provided in the embodiment of the present application is described in detail below with a specific example.

Referring to fig. 4, in step one, a target driving direction of a vehicle at a next intersection is acquired, and a target lane corresponding to a left turn is determined.

Specifically, the travelable lanes after left-turning of the lane where the own vehicle arrives at the current intersection can be marked as a route (2) and a route (4), and the travelable lanes after left-turning of other vehicles adjacent to the own vehicle can be marked as a route (1) and a route (3).

And step two, acquiring the lane length of the target lane.

Specifically, the length of the target lane between the current intersection and the next intersection is taken as the lane length.

And thirdly, planning a path for the self-vehicle to turn left from the current lane of the current intersection to the target lane based on the magnitude relation between the lane length of the target lane and the passing threshold value.

Specifically, if the lane length of the target lane is smaller than or equal to the traffic threshold, that is, D is smaller than or equal to Dmin, whether the target lane is unique needs to be determined, and if the target lane is unique, the host vehicle directly travels into the lane corresponding to the target traveling direction. The next intersection is a right-turn lane which needs to enter a passable lane (target road), namely a lane corresponding to the route (4); if the next intersection is left-turning, entering a left-turning lane of the passable lane in advance; if the next intersection is straight, the target lane is the straight lane. If the target lane is not unique, if the target driving direction is right turn, the numbers of right turn lanes which can enter after left turn from the current lane are 3, 2 and 1 in sequence, the first path of the own vehicle from the current lane to the target lane with the number of 3 is highest in score, the first path of the own vehicle from the current lane to the target lane with the number of 2 is scored for a plurality of times, the first path of the own vehicle from the left turn to the target lane with the number of 2 is lowest in score, and the left turn from the first path with the highest score is selected to the left turn with the number of 3. When a control mode of directly turning left from a current lane to a target lane is used for planning a path of a vehicle turning left from the current lane to the target lane, a current position point of the vehicle and a center line of the target lane can be used for fitting instead of fitting according to the current driving lane and the target lane to form a target track, namely when the target lane has a route (2), the vehicle can press the lane to drive instead of planning the track only according to a limited direction of the lane, and the situation that the turning radius is too large is avoided.

Further, if the lane length of the target lane is greater than the traffic threshold, i.e., D > Dmin, determining the path planning mode includes directly turning left to the target lane and turning left from the current lane to other lanes and then turning to the target lane, obtaining the path parameters and corresponding parameter weights of the own vehicle from the current intersection to each lane, and obtaining a second path score of entering the lane after turning left corresponding to each path planning mode based on each parameter and corresponding parameter weight in the path parameters. The parameter weights of the detour parameter C1, the turn failure parameter C2, the left turn passing time C3 and the direct parameter C4 of the direct target lane are respectively K1, K2, K3 and K4, and when the second path score of the entering lane after the left turn corresponding to each path planning mode is obtained based on each parameter in the path parameters and the corresponding parameter weight, the second path score can be obtained by carrying out weighted summation based on each parameter in the path parameters and the corresponding parameter weight. That is, y=k1 c1+k2 c2+k3 c3+k4 c4. When the second path score is higher, the route is indicated as the optimal route.

In summary, the left turn path control method of the embodiment of the invention combines the congestion information of the passable lane and the passing threshold value to select the target lane in the passable lane (target road), and then solves the optimal solution of the target planning track of the own vehicle in a path evaluation increasing mode to obtain the optimal planning path of the own vehicle, thereby solving and avoiding the error of selecting the target lane of the passable lane (target road), reducing the risk of left turn failure and improving the overall passing efficiency.

Fig. 5 shows a schematic structural view of an embodiment of a left-turn path control device of the present invention. As shown in fig. 5, the apparatus includes:

the lane obtaining module 510 is configured to obtain a target driving direction of the vehicle at the next intersection, and determine a target lane corresponding to the left turn.

The length obtaining module 520 is configured to obtain a lane length of the target lane, where the lane length is a length of the target lane between the current intersection and the next intersection.

The path planning module 530 is configured to plan a path for the host vehicle to turn left from the current lane of the current intersection to the target lane based on a magnitude relation between a lane length of the target lane and a traffic threshold.

In an alternative embodiment, path planning module 530 includes:

the first threshold value determining submodule is used for determining that the path planning mode is to directly turn left from the current lane to the target lane if the lane length of the target lane is smaller than or equal to the traffic threshold value, and determining whether the target lane is unique or not.

And the first path planning sub-module is used for planning a path of the own vehicle from the current lane to the target lane based on a path planning mode if the target lane is unique.

The first path evaluation sub-module is used for acquiring a first path score of the self-vehicle from the current lane to each target lane if the target lane is not unique, and the first path score is determined based on each target lane and the target driving direction.

And the second path planning sub-module is used for planning the path of the own vehicle from the current lane to the target lane in a left-turning manner based on the path planning mode and the first path score.

And the second threshold value determining submodule is used for determining a path planning mode to directly turn left to the target lane and turn left to other lanes from the current lane and then turn to the target lane if the lane length of the target lane is greater than the passing threshold value.

And the second path evaluation sub-module is used for acquiring second path scores of the left turn entering lanes corresponding to each path planning mode.

And the third path planning sub-module is used for planning the path of the own vehicle from the current lane to the target lane at the current intersection based on the path planning mode and the second path score.

In some optional embodiments, the second path evaluation submodule includes:

the parameter acquisition unit is used for acquiring path parameters of the self-vehicle from the current intersection to each lane and corresponding parameter weights, wherein the path parameters comprise a detour parameter, a turning failure parameter, a left turn passing time and a direct parameter of the self-vehicle in a left turn lane of the current intersection.

And the scoring calculation unit is used for obtaining a second path score of entering the lane after the left turn corresponding to each path planning mode based on each parameter in the path parameters and the corresponding parameter weight.

In some alternative embodiments, the first path planning sub-module includes:

and the position acquisition unit is used for acquiring the current position point of the self-vehicle.

And the position aggregation unit is used for fitting the current position point of the vehicle and the central line of the target lane to obtain a fitting result.

And the path planning unit is used for planning a path of the own vehicle from the current lane to the target lane based on the fitting result.

In some alternative embodiments, the first threshold determination submodule includes:

the traffic jam information acquisition unit is used for acquiring traffic jam information of the current road of the passable lane, wherein the passable lane comprises a lane between the current intersection and the next intersection.

And the congestion level determining unit is used for determining the congestion level of the passable lane based on the congestion information.

The traffic threshold determining unit is used for determining a traffic threshold based on the congestion level and a minimum lane change threshold, wherein the minimum lane change threshold is the minimum distance required by the lane change from the adjacent lane of the target lane to the target lane after the vehicle turns left.

Further functional descriptions of the above respective modules and units are the same as those of the above corresponding method embodiments, and are not repeated here.

Through the device and the components thereof, the technical scheme provided by the embodiment of the invention has the following advantages:

Compared with a left turn control mode that a user can drive in a correct lane only by carrying out lane change for multiple times in left turn control in the related art, the left turn path control method of the embodiment of the invention determines the target lane corresponding to left turn by acquiring the target driving direction of the user vehicle at the next intersection, plans the path from the current lane of the user vehicle at the current intersection to the target lane based on the size relationship between the lane length of the target lane and the passing threshold value, and can acquire the target driving direction of the next intersection in advance before the user vehicle turns left at the current intersection, thereby determining the target lane when the user vehicle turns left at the current intersection, planning the path from the current lane to the target lane of the user vehicle, and further improving the passing efficiency of the user vehicle at the next intersection after turning left.

Fig. 6 shows a schematic structural diagram of an embodiment of a vehicle provided by the present invention, and the specific embodiment of the present invention is not limited to the specific implementation of the vehicle. The vehicle has the left turn path control device shown in fig. 6. The vehicle may include: a processor 602, a communication interface (Communications Interface), a memory 606, and a communication bus 608.

Wherein: processor 602, communication interface 604, and memory 606 perform communication with each other via communication bus 608. Communication interface 604 is used to communicate with network elements of other devices, such as clients or other servers. The processor 602 is configured to execute the program 610, and may specifically perform the relevant steps used in the method embodiment described above.

In particular, program 610 may include program code comprising computer-executable instructions.

The processor 602 may be a central processing unit CPU or a specific integrated circuit ASIC (Application Specific Integrated Circuit) or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors comprised by the vehicle may be of the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.

A memory 606 for storing a program 610. The memory 606 may comprise high-speed RAM memory or may further comprise non-volatile memory (non-volatile memory), such as at least one disk memory.

Fig. 7 shows another schematic structural view of the vehicle provided by the present invention. As shown in fig. 7, the vehicle further includes: the rear-angle millimeter wave radar 2, the front millimeter wave radar 3, the side-view camera 5, the front-view binocular camera 4, the laser radar 8, the driving auxiliary function hard switch 1, the look-around camera 6, the ultrasonic probe 7, the vehicle body stabilizing system 10, the electric steering system 11, the whole vehicle controller 12, the vehicle body controller 13, the instrument 14, the central control screen 15 and the remote monitoring module 16. The rear-angle millimeter wave radar 2, the front millimeter wave radar 3, the side-view camera 5, the front-view binocular camera 4, the laser radar 8, the driving auxiliary function hard switch 1, the look-around camera 6, the ultrasonic probe 7, the vehicle body stabilizing system 10, the electric steering system 11, the vehicle controller 12, the vehicle controller 13, the instrument 14, the central control screen 15 and the remote monitoring module 16 are all in communication connection with the processor 602, and in addition, the remote monitoring module 16 can also be in communication connection with the cloud 18 and the mobile phone APP 17.

In the embodiment, the rear-angle millimeter wave radar 2 can adopt a 77GHz millimeter wave radar which is arranged at the left side and the right side of the rear guard, and the detection distance can reach about 80 m;

in the embodiment, the front millimeter wave radar 3 can adopt a 77GHz millimeter wave radar which is arranged right in front of the vehicle, and the detection distance can reach about 160 m;

in the embodiment, the side view camera 5 can adopt a 100-degree wide-angle two-megapixel camera, the side front view is arranged in the rearview mirror, the side rear view is arranged above the fender, and the detection distance can reach about 70 m;

in the embodiment, 2 cameras can be adopted for the forward-looking binocular camera 4, the visual field range is divided into small, medium and large angles, and the furthest detectable distance can reach about 200 m;

in this embodiment, the laser radar 8 is installed at the junction between the roof and the windshield, and the furthest detection distance can reach about 250 meters.

The functions which can be realized by the vehicle comprise self-adaptive cruising, integrated cruising, pilot assisted driving, front collision early warning, automatic emergency braking, lane departure, lane keeping, driving lever lane changing, autonomous lane changing and the like.

As shown in fig. 8, the vehicle provided by the embodiment of the invention includes 3 millimeter wave radars, 10 cameras, a processor 602, a body stabilization system 10, an electric steering system 11, a whole vehicle controller 12, a body controller 13, an instrument 14, a central control screen 15, a steering lamp and the like, the sensor unit communicates with an automatic driving controller through a private CANFD network, and other related systems communicate with the automatic driving controller through CANFD. The functions of the main relevant components are as follows:

The angle millimeter wave radar is arranged at the left side and the right side of the rear guard, and is used for sending out radio waves (radar waves) and then receiving echoes, and measuring the position data of the target according to the time difference between the receiving and the transmitting, wherein the detection distance can reach 80m, and parameters such as the time distance and the relative speed of the obstacle from the vehicle can be accurately detected through millimeter waves.

The front millimeter wave radar 3 is installed under the license plate of the vehicle, and is used for sending out radio waves (radar waves) and then receiving echoes, and measuring position data of a target according to time difference between receiving and transmitting, wherein the detection distance can reach 160m, and parameters such as the time distance and the relative speed of an obstacle from the vehicle can be accurately detected through millimeter waves.

The front-view binocular camera 4 is a camera combination of 2 high pixels with different visual angles, can detect obstacles with the distance of about 200m at the maximum in front of the outside, can identify lane line information, and can identify the cut-in and cut-out of a close-range vehicle;

the side view camera 5 can make up for the problem of poor recognition under the low-speed scene of the angle radar, and can quickly and early capture the cutting trend of other vehicles and the short-distance cutting scene, so that the automatic driving controller can early process the cutting scene;

the processor identifies lane lines, vehicles running on roads, road edges, obstacles and the like through an algorithm by acquiring a sensing module (the sensing module comprises a millimeter wave radar, an intelligent camera group, a side view camera 5, an IMU integrated in the interior and the like), reasonably plans a track plan of driving assistance, controls the transverse direction and the longitudinal direction of the vehicle, realizes the functions of constant-speed cruising, avoiding rear collision vehicles, stopping and automatically starting when the vehicles are in collision with the obstacles and the vehicles are not in collision with the obstacles, and sends a corner request, a deceleration request, a torque request and the like to each associated system in the control process.

The body stabilization system 10 (ESC for short) is used for receiving the deceleration request command sent by the automatic driving controller, and feeding back the body data such as deceleration, yaw angle, speed, wheel speed, etc. of the vehicle for the processor to perform the longitudinal control calculation of the vehicle.

The electric power steering (EPS for short) is used for executing the steering angle and the steering angle acceleration request sent by the autopilot controller, controlling the steering wheel to steer to the angle instructed by the autopilot controller, and if the EPS fails or the driver intervenes in parking, feeding back the reason for exiting the control to the autopilot controller.

The vehicle controller 12 (VCU) is configured to receive a torque request from an autopilot controller, perform acceleration control, and feed back a gear position of the vehicle, a response torque, etc. in real time.

The body controller 13 (BCM) is configured to receive control requests from a steering lamp, a hazard warning lamp, a wiper, a lamp, and the like for automatic driving control.

The meter 14 (IC for short) is used for displaying a man-machine interaction interface, text, pictures and sound reminders in the process of activating the auxiliary driving function.

The central control screen 15 (HU for short) displays a scene reconstruction interface for the pilot auxiliary function during the activation process, and user-defined setting of an entry and the like.

The turn signal lamp is used for responding to the lighting request of the vehicle body controller 13 in the automatic driving process to remind other vehicles of driving safety.

The embodiment of the invention also provides a computer readable storage medium, wherein the storage medium stores at least one executable instruction, and the executable instruction causes the vehicle/left-turn path control device to execute the left-turn path control method in any of the above method embodiments when the executable instruction runs on the vehicle/left-turn path control device.

The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. In addition, embodiments of the present invention are not directed to any particular programming language.

In the description provided herein, numerous specific details are set forth. It will be appreciated, however, that embodiments of the invention may be practiced without such specific details. Similarly, in the above description of exemplary embodiments of the invention, various features of embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. Wherein the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Except that at least some of such features and/or processes or elements are mutually exclusive.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.

Claims (10)

1. A left turn path control method, characterized by being applied to a host vehicle, the method comprising:

acquiring a target driving direction of the self-vehicle at the next intersection, and determining a target lane corresponding to left turn;

obtaining the lane length of a target lane, wherein the lane length is the length of the target lane between a current intersection and the next intersection;

and planning a path of the own vehicle from the current lane of the current intersection to the target lane based on the magnitude relation between the lane length of the target lane and the passing threshold.

2. The method of claim 1, wherein planning a path for a host vehicle to turn left from a current lane of a current intersection to the target lane based on a magnitude relationship between a lane length of the target lane and a traffic threshold comprises:

if the lane length of the target lane is smaller than or equal to the passing threshold value, determining that the path planning mode is to directly turn left from the current lane to the target lane, and determining whether the target lane is unique;

and if the target lane is unique, planning a path of the own vehicle from the current lane to the target lane based on the path planning mode.

3. The method of claim 2, wherein planning a path for a host vehicle to turn left from a current lane of a current intersection to the target lane based on a magnitude relationship between a lane length of the target lane and a traffic threshold, further comprises:

if the target lane is not unique, acquiring a first path score of the own vehicle from the current lane to each target lane, wherein the first path score is determined based on each target lane and the target driving direction;

and planning a path of the own vehicle from the current lane to the target lane in a left-turn mode based on the path planning mode and the first path score.

4. The method of claim 2, wherein planning a path for a host vehicle to turn left from a current lane of a current intersection to the target lane based on a magnitude relationship between a lane length of the target lane and a traffic threshold, further comprises:

if the lane length of the target lane is greater than the passing threshold, determining that the path planning mode comprises directly turning left to the target lane and turning left to other lanes from the current lane and then turning to the target lane;

Obtaining a second path score of entering a lane after left turn corresponding to each path planning mode;

and planning a path for the own vehicle to turn left from the current lane of the current intersection to the target lane based on the path planning mode and the second path score.

5. The method of claim 4, wherein the obtaining the second path score of the left turn entering lane corresponding to each of the path planning modes comprises:

obtaining path parameters and corresponding parameter weights of the self-vehicle from the current intersection lane change to each lane, wherein the path parameters comprise a detour parameter, a turning failure parameter, a left turn passing time and a direct parameter reaching the target lane of the self-vehicle;

and obtaining a second path score of entering the lane after the left turn corresponding to each path planning mode based on each parameter in the path parameters and the corresponding parameter weight.

6. The method according to any one of claims 2 to 5, wherein if the path planning method is to directly turn left from the current lane to the target lane, planning a path of a host vehicle to turn left from the current lane to the target lane, comprising:

Acquiring the current position point of the own vehicle;

fitting the current position point of the vehicle and the central line of the target lane to obtain a fitting result;

and planning a path of the own vehicle from the current lane to the target lane in a left-turn mode based on the fitting result.

7. The method of claim 1, wherein the manner of determining the pass threshold comprises:

acquiring congestion information of a current road of a passable lane, wherein the passable lane comprises a lane between the current intersection and the next intersection;

determining a congestion level of the travelable lane based on the congestion information;

and determining the passing threshold based on the congestion level and a minimum lane change threshold, wherein the minimum lane change threshold is the minimum distance required for changing lanes from the adjacent lane of the target lane to the target lane after the vehicle turns left.

8. A left turn path control device, characterized by being applied to a host vehicle, comprising:

the lane acquisition module is used for acquiring the target driving direction of the self-vehicle at the next intersection and determining a target lane corresponding to left turn;

the length acquisition module is used for acquiring the lane length of a target lane, wherein the lane length is the length of the target lane between a current intersection and the next intersection;

And the path planning module is used for planning a path for the vehicle to turn left from the current lane of the current intersection to the target lane based on the magnitude relation between the lane length of the target lane and the passing threshold value.

9. A vehicle, characterized by comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;

the memory is configured to store at least one executable instruction that causes the processor to perform the operations of the left turn path control method according to any one of claims 1-7.

10. A computer-readable storage medium, wherein at least one executable instruction is stored in the storage medium, which when run on a vehicle/device causes the vehicle/device to perform the operations of the left turn path control method according to any one of claims 1-7.