CN115771526A

CN115771526A - Method and device for controlling left turn of vehicle in automatic driving and automatic driving vehicle

Info

Publication number: CN115771526A
Application number: CN202211395898.8A
Authority: CN
Inventors: 张宽
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2022-11-08
Filing date: 2022-11-08
Publication date: 2023-03-10

Abstract

The invention provides a method and a device for controlling left turning of a vehicle in automatic driving, electronic equipment, a readable storage medium and the automatic driving vehicle, and relates to the technical field of artificial intelligence such as automatic driving, intelligent transportation, deep learning and computer vision. The method for controlling the left turn of the vehicle in automatic driving comprises the following steps: determining an avoidance position according to a left-turning reference line and a target lane line of the vehicle; planning an avoidance path according to the avoidance position, and controlling the vehicle to avoid; determining that the target exits the lane under the condition that the current vehicle information of the opposite lane is determined to meet the left-turn passing condition; and planning a left-turn path according to the target exit lane, and controlling the vehicle to turn left. The control method and the control device can improve the passing efficiency and the passing flexibility when the vehicle is controlled to turn left in automatic driving, and further improve the driving safety of the vehicle.

Description

Method and device for controlling left turn of vehicle in automatic driving and automatic driving vehicle

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular to the field of artificial intelligence technologies such as automatic driving, intelligent transportation, deep learning, and computer vision. A method, a device, an electronic device, a readable storage medium and an automatic driving vehicle for controlling the left turn of the vehicle in automatic driving are provided.

Background

In the prior art, high-precision map labeling is relied on when automatic driving path planning is carried out. When controlling a vehicle to turn left, for example, automatic driving usually plans a left-turn path according to a highly accurate map-labeled left-turn reference line (virtual labeled lane).

Disclosure of Invention

According to a first aspect of the present disclosure, there is provided a method of controlling a left turn of a vehicle in autonomous driving, comprising: determining an avoidance position according to a left-turn reference line of the vehicle and a target lane line; planning an avoidance path according to the avoidance position, and controlling the vehicle to avoid; determining that the target exits the lane under the condition that the current vehicle information of the opposite lane is determined to meet the left-turn passing condition; and planning a left-turn path according to the target exit lane, and controlling the vehicle to turn left.

According to a second aspect of the present disclosure, there is provided an apparatus for controlling a left turn of a vehicle in automatic driving, comprising: the first determining unit is used for determining an avoidance position according to a left-turning reference line and a target lane line of the vehicle; the first planning unit is used for planning an avoidance path according to the avoidance position and controlling the vehicle to avoid; a second determination unit configured to determine that the target exits the lane, in a case where it is determined that the vehicle information current to the oncoming lane satisfies the left-turn passing condition; and the second planning unit is used for planning a left-turn path according to the target exit lane and controlling the vehicle to turn left.

According to a third aspect of the present disclosure, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described above.

According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method as described above.

According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method as described above.

According to a sixth aspect of the present disclosure, there is provided an autonomous vehicle comprising the above-mentioned electronic device, wherein the at least one processor is capable of performing the above-mentioned method.

According to the technical scheme, the purpose of controlling the left turn of the vehicle by planning the avoidance path and then planning the left turn path is achieved by stages of path planning, and the problems that the avoidance space is insufficient, the blockage is easily caused, the path planning is hard, and the like due to the fact that the left turn path is directly planned according to the left turn reference line of the vehicle in the prior art can be effectively solved, so that the passing efficiency and the passing flexibility when the left turn of the vehicle is controlled are improved, and the running safety of the vehicle is further improved.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic illustration according to a first embodiment of the present disclosure;

FIG. 2 is a schematic diagram according to a second embodiment of the present disclosure;

FIG. 3 is a schematic illustration according to a third embodiment of the present disclosure;

FIG. 4 is a schematic diagram according to a fourth embodiment of the present disclosure;

fig. 5 is a block diagram of an electronic device for implementing a method of controlling a left turn of a vehicle in autonomous driving according to an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of embodiments of the present disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 is a schematic diagram according to a first embodiment of the present disclosure. As shown in fig. 1, the method for controlling a left turn of a vehicle in automatic driving of the present embodiment specifically includes the following steps:

s101, determining an avoidance position according to a left-turn reference line of a vehicle and a target lane line;

s102, planning an avoidance path according to the avoidance position, and controlling the vehicle to avoid;

s103, under the condition that the current vehicle information of the opposite lane meets the left-turn passing condition, determining that the target exits the lane;

and S104, controlling the vehicle to turn left according to the left-turning path planned by the target exit lane.

According to the method for controlling the left turn of the vehicle in the automatic driving, the purpose of controlling the left turn of the vehicle by planning the avoidance path and then planning the left turn path in stages is achieved, and the problems that in the prior art, the avoidance space is insufficient, the blockage is easily caused, the path planning is hard, and the like due to the fact that the left turn path is directly planned according to the left turn reference line of the vehicle can be effectively avoided, so that the passing efficiency and the passing flexibility when the left turn of the vehicle is controlled are improved, and the driving safety of the vehicle is further improved.

In this embodiment, the left-turn reference line is a virtual left-turn lane marked by a high-precision map when the vehicle is automatically driven, and the left-turn reference line is used for planning a left-turn path (path) of the vehicle.

In this embodiment, a lane (lane) where the vehicle is currently located is a current lane, the current lane is an entering lane, the entering lane is a lane entering the intersection in the driving direction, and the exiting lane is a lane far away from the intersection in the driving direction; the road where the entering lane is located is an entering road, the road where the exiting lane is located is an exiting road, and the entering road and the exiting road are in a communication relation.

Specifically, in this embodiment, when S101 is executed to determine an avoidance position according to a left-turn reference line and a target lane line of a vehicle, an optional implementation manner that can be adopted is as follows: taking a first point of intersection of the extension line of the target lane line and the left-turn reference line as a central point; determining a target direction, and moving the central point according to the determined target direction; and under the condition that the vehicle does not invade the opposite lane when being positioned at the moved central point, taking the position of the current central point as an avoidance position.

That is to say, in the embodiment, after the central point is obtained according to the left-turn reference line and the target lane line, the avoidance position is determined in a manner that the central point is moved in the target direction, on one hand, it can be ensured that the vehicle does not affect the driving of the opposite vehicle (opposite straight vehicle and/or opposite left-turn vehicle) when being located at the avoidance position, and on the other hand, the problems that the driving of other vehicles turning left in the same direction is affected and the subsequent passing distance is increased due to the fact that the avoidance position is located at a later position are avoided, so that the accuracy and the rationality when the avoidance position is determined, and the passing efficiency and the driving safety of the vehicle when the vehicle is controlled to turn left are improved.

When the embodiment executes S101, the target lane line is a left boundary line of a current lane of the vehicle or a right boundary line of a rightmost lane in the oncoming lane; the opposite lane in this embodiment may be an opposite straight lane, and the rightmost lane may be a rightmost straight lane.

The present embodiment may use a preset horizontal direction as the target direction when performing S101 to determine the target direction, that is, the present embodiment moves the center point in the horizontal direction.

In order to further improve the accuracy and the rationality when determining the avoidance position, in the present embodiment, when performing S101 to determine the target direction, the normal direction of the central point on the left-turn reference line may also be taken as the target direction, that is, the central point is moved in the normal direction by the present embodiment.

In this embodiment, when executing S101 to determine an avoidance position according to the left-turn reference line and the target lane line of the vehicle, the following contents may be further included: acquiring current driving data of a vehicle, such as the current position of the vehicle, an image of a current intersection where the vehicle is located, and the like; and under the condition that the current left-turn scene is determined to be an unprotected left-turn scene according to the acquired driving data, determining an avoidance position according to a left-turn reference line and a target lane line of the vehicle.

In this embodiment, the unprotected left turn scene refers to a scene in which a straight green light and a left turn green light at the current intersection are simultaneously lit; in executing S101, the present embodiment may determine whether the straight green light and the left turn green light of the current intersection are simultaneously turned on according to the current position of the vehicle or the image of the intersection where the vehicle is currently located.

In addition, when the step S101 is executed to determine the avoidance position according to the left-turn reference line and the target lane line of the vehicle, the embodiment may further include the following steps: acquiring current vehicle information of an opposite lane, wherein the vehicle information in the embodiment can be whether vehicles exist in the opposite lane, the number of the vehicles, the running speed of the vehicles and the like; and under the condition that the acquired vehicle information meets the left-turn avoidance condition, determining an avoidance position according to a left-turn reference line and a target lane line of the vehicle.

In executing S101, the present embodiment may determine that the acquired vehicle information satisfies a left-turn avoidance condition when there is a vehicle in the oncoming lane; when the number of vehicles in the opposite lane exceeds a preset number threshold, the acquired vehicle information is determined to meet a left-turn avoidance condition; the acquired vehicle information can be determined to meet the left-turn avoidance condition when the running speed of the vehicle in the opposite lane is high (namely, the vehicle collision can occur).

It can be understood that, in executing S101, the present embodiment may directly execute the operation of determining the avoidance position after determining that the vehicle information satisfies the left turn avoidance condition; or after the situation that the current left-turn scene is determined to be an unprotected left-turn scene and the vehicle information meets the left-turn avoidance condition is determined, the operation of determining the avoidance position can be executed.

That is to say, in the present embodiment, whether to execute the operation of determining the avoidance position is determined by determining whether the left turn scene is unprotected and/or whether the vehicle information satisfies the left turn avoidance condition, so that the waste of computing resources can be avoided, and the accuracy in executing the operation of determining the avoidance position is improved.

In the embodiment, after the avoidance position of the vehicle is determined in step S101, step S102 is performed to plan an avoidance path according to the avoidance position, and then the vehicle is controlled to avoid through the avoidance path.

In this embodiment, when the step S102 is executed to plan the avoidance path according to the avoidance position, the avoidance path can be directly planned according to the current position and the avoidance position of the vehicle, so as to control the vehicle to travel to the avoidance position through the avoidance path.

In this embodiment, when the step S102 is executed to plan the avoidance path according to the avoidance position, the optional implementation manner that may be adopted is as follows: obtaining a constraint boundary according to a current lane and an exit road, wherein the exit road in the embodiment is a road into which a vehicle turns left to enter; and planning an avoidance path according to the obtained constraint boundary and the avoidance position.

In this embodiment, when S102 is executed to obtain the constraint boundary according to the current lane and the exit road, the optional implementation manners that may be adopted are: taking an intersection point between an extension line of the right boundary line of the current lane and an extension line of the right boundary line of the exit road as a first boundary point; taking the terminal point of the right boundary of the current lane as a second boundary point; taking the starting point of the right boundary of the exit road as a third boundary point; and taking a connecting line between the first boundary point and the second boundary point and a connecting line between the first boundary point and the third boundary point as constraint boundaries.

That is to say, the embodiment plans the avoidance path according to the constraint boundary obtained by the current lane and the exit road, so that the avoidance path does not intrude into the same-direction straight lane or collide with the shoulder of the exit road, thereby improving the accuracy of the planned avoidance path and the driving safety of the vehicle.

In this embodiment, after the planning in S102 is executed to obtain the avoidance trajectory, the vehicle may be controlled to avoid through the avoidance trajectory so as to travel to the avoidance position.

After executing S102 to control the vehicle to avoid, the present embodiment executes S103 to determine that the target exits the lane in the case where it is determined that the current vehicle information of the opposite lane satisfies the left-turn passing condition.

In the embodiment, when the step S103 is executed to determine that the current vehicle information of the opposite lane satisfies the left-turn passing condition, the target exit lane may be determined by adopting the following optional implementation manners: in the process that a vehicle carries out avoidance according to an avoidance path, obtaining current vehicle information of an opposite lane, wherein the vehicle information comprises whether vehicles exist in the opposite lane (such as an opposite straight lane), the number of the vehicles, the running speed of the vehicles and the like; in a case where it is determined that the acquired vehicle information satisfies the left-turn passage condition, it is determined that the target exits the lane.

In addition, the embodiment may further adopt the following manner when determining that the target exits the lane in the case where it is determined that the vehicle information current in the opposite lane satisfies the left-turn passing condition at execution S103: under the condition that the vehicle is determined to reach an avoidance position according to an avoidance path, current vehicle information of an opposite lane is obtained; in a case where it is determined that the acquired vehicle information satisfies the left-turn passage condition, it is determined that the target exits the lane.

That is to say, the embodiment may determine whether the vehicle can currently turn left by acquiring the current vehicle information of the opposite lane during the avoidance process of the vehicle or after the avoidance is finished, and further determine that the target exits the lane when it is determined that the left-turn passing condition is satisfied.

The present embodiment, in executing S103, may determine that the acquired vehicle information satisfies the left-turn passing condition when there is no vehicle in the oncoming lane; or when the number of vehicles in the opposite lane does not exceed a preset number threshold, determining that the acquired vehicle information meets the left-turn passing condition; it may also be determined that the acquired vehicle information satisfies the left-turn passing condition when the traveling speed of the vehicle in the oncoming lane is slow (i.e., no vehicle collision occurs).

When the step S103 is executed to determine that the target exits the lane, the present embodiment may adopt the following optional implementation manners: acquiring attribute information of each candidate exit lane, wherein the candidate exit lanes are all lanes in the exit road; obtaining cost values of all candidate exit lanes according to the attribute information; and taking the candidate exit lane with the lowest cost value as a target exit lane.

In the embodiment, when S103 is executed to obtain the cost value of each candidate exit lane according to the attribute information, the following manner may be adopted: inputting attribute information of the candidate exit lane into a lane evaluation model; and taking the output result of the lane evaluation model as a cost value of the candidate exit lane.

In this embodiment, the attribute information of the candidate exit lane may include information such as lane priority, lane blocking information, lane subsequent passing distance, and execution difficulty of lane planning result; the priority of the lane is preset, and the priority is higher the lane is farther to the outside; the lane blocking information is used for indicating whether a lane is under construction or has an accident or the like; the lane subsequent passing distance is used for indicating how much distance the vehicle can travel on the lane after the vehicle travels to the lane; the execution difficulty of the lane planning result is preset, and the closer the lane is, the higher the execution difficulty is.

The lane evaluation model used in S103 in this embodiment may be obtained by pre-training in the following manner: acquiring a training sample, wherein the acquired training sample comprises attribute information of a lane and a cost value labeling result of the lane; inputting the attribute information of the lane into a neural network model to obtain a cost value prediction result output by the neural network model; calculating a loss function value according to the cost value labeling result and the cost value prediction result; and adjusting parameters of the neural network model according to the loss function value until the neural network model converges to obtain the lane evaluation model.

After executing S103 to determine the target exit lane, the present embodiment executes S104 to plan a left turn path according to the target exit lane, and controls the vehicle to make a left turn.

In the embodiment, when the step S104 of planning the left turn path according to the target exit lane is executed, the left turn path may be directly planned according to the current position of the vehicle and the target exit lane, so as to control the vehicle to travel to the target exit lane, thereby completing the left turn.

That is to say, in the avoidance process or after the avoidance is finished, the target exit lane can be selected from the candidate exit lanes according to the attribute information of the candidate exit lanes, so that the adaptive selection of the exit lanes is realized, the problem that only the exit lane corresponding to the left-turn reference line is rigid when the exit lane is used as the target exit lane is avoided, the left-turn of the vehicle can be completed more quickly and flexibly, and the passing efficiency and the passing flexibility when the vehicle is controlled to turn left are improved.

In addition, the present embodiment may further include the following contents: when determining that other vehicles exist in front of the vehicle, acquiring a running track of the front vehicle; and controlling the vehicle to turn left according to the acquired running track, for example, planning a left-turning path of the vehicle according to the acquired running track, and controlling the vehicle to turn left according to the planned left-turning path.

Fig. 2 is a schematic diagram according to a second embodiment of the present disclosure. A schematic diagram of the prior art when controlling a vehicle to make a left turn is shown in fig. 2: the lines marked by arrows in fig. 2 are a left-turn reference line and a left-turn path, respectively, that is, the prior art performs left-turn according to the left-turn path obtained by planning with the left-turn reference line.

Fig. 3 is a schematic diagram according to a third embodiment of the present disclosure. Fig. 3 is a schematic diagram of the present embodiment when determining an avoidance position, and fig. 3 shows that there are 3 left-turn reference lines of the vehicle, and the uppermost left-turn reference line is taken as an example in the present embodiment for explanation; a point D in fig. 3 is a central point, and D' is an avoidance position after the central point moves in the normal direction on the left-turn reference line; in addition, a point B in fig. 3 is a first boundary point, a point a is a second boundary point, a point C is a third boundary point, and a connection line AB and a connection line BC are constraint boundaries of the avoidance path.

Compared with the prior art, in the method for controlling the left turn of the vehicle in the automatic driving provided by the embodiment, in the case that the left-turn reference line of the vehicle is the uppermost left-turn reference line in fig. 3, the uppermost exit lane candidate may not be selected as the target exit lane, but the exit lane with the smallest cost value is used as the target exit lane, for example, the middle exit lane candidate, according to the attribute information of each exit lane candidate.

Fig. 4 is a schematic diagram according to a fourth embodiment of the present disclosure. As shown in fig. 4, the apparatus 400 for controlling the left turn of the vehicle in the automated driving of the present embodiment includes:

the first determining unit 401 is configured to determine an avoidance position according to a left-turn reference line of the vehicle and a target lane line;

the first planning unit 402 is configured to plan an avoidance path according to the avoidance position, and control the vehicle to avoid;

a second determining unit 403 for determining that the target exits the lane in a case where it is determined that the current vehicle information of the oncoming lane satisfies the left-turn passing condition;

and the second planning unit 404 is configured to plan a left-turn path according to the target exit lane, and control the vehicle to turn left.

Specifically, when the first determining unit 401 determines the avoidance position according to the left-turn reference line and the target lane line of the vehicle, the optional implementation manner that may be adopted is as follows: taking a first point of intersection of the extension line of the target lane line and the left-turn reference line as a central point; determining a target direction, and moving the central point according to the determined target direction; and under the condition that the vehicle does not invade the opposite lane when being positioned at the moved central point, taking the position of the current central point as an avoidance position.

That is to say, after obtaining the central point according to the left-turn reference line and the target lane line, the first determining unit 401 determines the avoidance position by moving the central point in the target direction, on one hand, it can be ensured that the vehicle does not affect the traveling of the oncoming vehicle (the oncoming straight vehicle and/or the oncoming left-turn vehicle) when being located at the avoidance position, and on the other hand, the problems that the vehicle will affect the traveling of other co-turning left-turn vehicles and increase the subsequent passing distance due to the fact that the avoidance position is located at a later position are avoided, so that the accuracy and the rationality when determining the avoidance position are improved, and the passing efficiency and the traveling safety of the vehicle when controlling the vehicle to turn left are improved.

The first determination unit 401 may take a preset horizontal direction as a target direction, i.e., move the center point in the horizontal direction, when determining the target direction.

In order to further improve the accuracy and the rationality in determining the avoidance position, the first determining unit 401 may further use a normal direction of the center point on the left-turn reference line as the target direction when determining the target direction, that is, move the center point in the normal direction.

When the first determining unit 401 determines the avoidance position according to the left-turn reference line of the vehicle and the target lane line, the following contents may be further included: acquiring current driving data of a vehicle; and under the condition that the current left-turn scene is determined to be an unprotected left-turn scene according to the acquired driving data, determining an avoidance position according to a left-turn reference line and a target lane line of the vehicle.

In addition, when the first determining unit 401 determines the avoidance position based on the left-turn reference line of the vehicle and the target lane line, the following contents may be further included: acquiring current vehicle information of an opposite lane; and under the condition that the acquired vehicle information meets the left-turning avoidance condition, determining an avoidance position according to a left-turning reference line and a target lane line of the vehicle.

The first determination unit 401 may determine that the acquired vehicle information satisfies a left-turn avoidance condition when there is a vehicle in the oncoming lane; when the number of vehicles in the opposite lane exceeds a preset number threshold, the acquired vehicle information is determined to meet a left-turn avoidance condition; the acquired vehicle information can be determined to meet the left-turn avoidance condition when the running speed of the vehicle in the opposite lane is high (namely, the vehicle collision can occur).

It is understood that the first determination unit 401 may directly perform the operation of determining the avoidance position after determining that the vehicle information satisfies the left turn avoidance condition; or after the situation that the current left-turn scene is determined to be an unprotected left-turn scene and the vehicle information meets the left-turn avoidance condition is determined, the operation of determining the avoidance position can be executed.

That is to say, the first determining unit 401 determines whether to execute the operation of determining the avoidance position by determining whether the vehicle information satisfies the left-turn avoidance condition and/or determining whether to execute the unprotected left-turn scene, so that the waste of computing resources can be avoided, and the accuracy in executing the operation of determining the avoidance position can be improved.

In this embodiment, after the first determining unit 401 determines the avoidance position of the vehicle, the first planning unit 402 plans the avoidance path according to the avoidance position, and then controls the vehicle to avoid through the avoidance path.

When planning the avoidance path according to the avoidance position, the first planning unit 402 may directly plan the avoidance path according to the current position and the avoidance position of the vehicle, so as to control the vehicle to travel to the avoidance position through the avoidance path.

When the first planning unit 402 plans the avoidance path according to the avoidance position, the optional implementation manner that can be adopted is as follows: obtaining a constraint boundary according to the current lane and the exit road; and planning an avoidance path according to the obtained constraint boundary and the avoidance position.

When obtaining the constraint boundary according to the current lane and the exit road, the first planning unit 402 may adopt an optional implementation manner as follows: taking an intersection point between an extension line of the right boundary line of the current lane and an extension line of the right boundary line of the exit road as a first boundary point; taking the terminal point of the right boundary of the current lane as a second boundary point; taking the starting point of the right boundary of the exit road as a third boundary point; and taking a connecting line between the first boundary point and the second boundary point and a connecting line between the first boundary point and the third boundary point as constraint boundaries.

That is to say, the first planning unit 402 plans the avoidance path according to the constraint boundary obtained by the current lane and the exit road, so that the avoidance path does not intrude into the same-direction straight lane or collide with the shoulder of the exit road, thereby improving the accuracy of the planned avoidance path and the driving safety of the vehicle.

After the avoidance trajectory is obtained by planning, the first planning unit 402 may control the vehicle to avoid through the avoidance trajectory so as to travel to the avoidance position.

After the first planning unit 402 controls the vehicle to avoid, the second determining unit 403 determines that the target exits the lane when determining that the current vehicle information of the opposite lane satisfies the left-turn passing condition.

The second determining unit 403 determines that the target exit lane in the case where it is determined that the vehicle information currently in the opposite lane satisfies the left-turn passing condition, and may adopt alternative implementations as follows: acquiring current vehicle information of an opposite lane in the process of avoiding the vehicle according to the avoiding path; in a case where it is determined that the acquired vehicle information satisfies the left-turn passage condition, it is determined that the target exits the lane.

In addition, the second determining unit 403 may also adopt the following manner when determining that the target exits the lane in the case where it is determined that the vehicle information current in the oncoming lane satisfies the left-turn passing condition: under the condition that the vehicle is determined to reach an avoidance position according to an avoidance path, current vehicle information of an opposite lane is obtained; in a case where it is determined that the acquired vehicle information satisfies the left-turn passage condition, it is determined that the target exits the lane.

That is, the second determination unit 403 may determine whether the vehicle is currently able to turn left by acquiring the current vehicle information of the oncoming lane during avoidance of the vehicle or after the end of avoidance, and then determine that the target exits the lane in a case where it is determined that the left-turn passing condition is satisfied.

The second determining unit 403 may determine that the acquired vehicle information satisfies the left-turn passing condition when there is no vehicle in the oncoming lane; or when the number of vehicles in the opposite lane does not exceed a preset number threshold, determining that the acquired vehicle information meets the left-turn passing condition; it may also be determined that the acquired vehicle information satisfies the left-turn passing condition when the traveling speed of the vehicle in the oncoming lane is slow (i.e., no vehicle collision occurs).

When determining that the target exits the lane, the second determining unit 403 may adopt alternative implementations as follows: acquiring attribute information of each candidate exit lane, wherein the candidate exit lanes are all lanes in the exit road; obtaining cost values of all candidate exit lanes according to the attribute information; and taking the candidate exit lane with the lowest cost value as a target exit lane.

When obtaining the cost value of each candidate exit lane according to the attribute information, the second determining unit 403 may adopt the following manner: inputting attribute information of the candidate exit lane into a lane evaluation model; and taking the output result of the lane evaluation model as a cost value of the candidate exit lane.

The lane evaluation model used by the second determining unit 403 may be obtained by pre-training in the following manner: acquiring a training sample, wherein the acquired training sample comprises attribute information of a lane and a cost value labeling result of the lane; inputting the attribute information of the lane into a neural network model to obtain a cost value prediction result output by the neural network model; calculating a loss function value according to the cost value labeling result and the cost value prediction result; and adjusting parameters of the neural network model according to the loss function value until the neural network model converges to obtain the lane evaluation model.

After the second determining unit 403 determines that the target exits the lane, the second planning unit 404 plans a left-turn path according to the target exits the lane, and controls the vehicle to turn left.

When planning the left-turn path according to the target exit lane, the second planning unit 404 may plan the left-turn path directly according to the current position of the vehicle and the target exit lane, and then control the vehicle to travel to the target exit lane to complete the left-turn.

In addition, the second planning unit 404 may also include the following: when determining that other vehicles exist in front of the vehicle, acquiring a running track of the front vehicle; and controlling the vehicle to turn left according to the acquired running track, for example, planning a left-turning path of the vehicle according to the acquired running track, and controlling the vehicle to turn left according to the planned left-turning path.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

As shown in fig. 5, is a block diagram of an electronic device for a method of controlling a left turn of a vehicle in autonomous driving according to an embodiment of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 5, the apparatus 500 comprises a computing unit 501 which may perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM) 502 or a computer program loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data required for the operation of the device 500 can also be stored. The calculation unit 501, the ROM502, and the RAM503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

A number of components in the device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, or the like; an output unit 507 such as various types of exhibitors, speakers, etc.; a storage unit 508, such as a magnetic disk, optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The computing unit 501 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 501 executes the respective methods and processes described above, such as a method of controlling a left turn of the vehicle in automatic driving. For example, in some embodiments, the method of controlling a left turn of a vehicle in autonomous driving may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 508.

In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM502 and/or the communication unit 509. When the computer program is loaded into RAM503 and executed by computing unit 501, one or more steps of the above-described method for controlling a left turn of a vehicle in autonomous driving may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured in any other suitable way (e.g., by means of firmware) to perform a method of controlling a left turn of a vehicle in autonomous driving.

Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable autopilot apparatus for controlling a left turn of a vehicle, such that the program codes, when executed by the processor or controller, cause the functions/acts specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a presentation device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for presenting information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server can be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.

It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method of controlling a left turn of a vehicle in autonomous driving, comprising:

determining an avoidance position according to a left-turn reference line of the vehicle and a target lane line;

planning an avoidance path according to the avoidance position, and controlling the vehicle to avoid;

determining that the target exits the lane under the condition that the current vehicle information of the opposite lane meets the left-turn passing condition;

and controlling the vehicle to turn left according to the left-turning path planned by the target exit lane.

2. The method of claim 1, wherein determining an avoidance position based on a left turn reference line of the vehicle and a target lane line comprises:

taking a first point of intersection of the extension line of the target lane line and the left-turn reference line as a central point;

determining a target direction, and moving the central point according to the target direction;

and under the condition that the vehicle does not invade the opposite lane when being positioned at the moved central point, taking the position of the current central point as the avoidance position.

3. The method of claim 2, wherein the determining a target direction comprises:

and taking the normal direction of the central point on the left-turning reference line as the target direction.

4. The method according to any one of claims 1-3, wherein the planning an avoidance path according to the avoidance position includes:

obtaining a constraint boundary according to the current lane and the exit road of the vehicle;

and planning the avoidance path according to the constraint boundary and the avoidance position.

5. The method of claim 4, wherein said deriving a constraint boundary based on a current lane and an exit road of the vehicle comprises:

taking an intersection point between an extension line of the right boundary line of the current lane and an extension line of the right boundary line of the exit road as a first boundary point;

taking the terminal point of the right boundary of the current lane as a second boundary point;

taking the starting point of the right boundary of the exit road as a third boundary point;

and using a connecting line between the first boundary point and the second boundary point and a connecting line between the first boundary point and the third boundary point as the constraint boundary.

6. The method according to any one of claims 1-5, wherein the determining that the target exit lane includes, in the event that it is determined that the current vehicle information for the oncoming lane satisfies a left-turn passing condition:

acquiring current vehicle information of an opposite lane in the process of avoiding the vehicle according to the avoiding path;

determining that the target exits the lane if it is determined that the vehicle information satisfies a left-turn traffic condition.

7. The method according to any one of claims 1-5, wherein the determining that the target exit lane includes, in the event that it is determined that the current vehicle information of the oncoming lane satisfies a left-turn passing condition:

under the condition that the vehicle is determined to reach the avoidance position according to the avoidance path, current vehicle information of an opposite lane is obtained;

8. The method of any of claims 1-7, wherein the determining a target exit lane comprises:

acquiring attribute information of each candidate exit lane;

obtaining the cost value of each candidate exit lane according to the attribute information;

and taking the candidate exit lane with the lowest cost value as the target exit lane.

9. The method of claim 8, wherein the deriving the cost value for each candidate exit lane according to attribute information comprises:

inputting attribute information of the candidate exit lane into a lane evaluation model;

and taking the output result of the lane evaluation model as the cost value of the candidate exit lane.

10. The method of claim 1, wherein the determining an avoidance position based on a left turn reference line and a target lane line of the vehicle comprises:

acquiring current driving data of the vehicle;

and under the condition that the current left-turn scene is determined to be an unprotected left-turn scene according to the driving data, determining the avoidance position according to a left-turn reference line and a target lane line of the vehicle.

11. The method of claim 1, wherein determining an avoidance position based on a left turn reference line of the vehicle and a target lane line comprises:

acquiring current vehicle information of an opposite lane;

and under the condition that the vehicle information is determined to meet the left-turn avoidance condition, determining the avoidance position according to the left-turn reference line and the target lane line of the vehicle.

12. An apparatus for controlling a left turn of a vehicle in automatic driving, comprising:

the first determining unit is used for determining an avoidance position according to a left-turning reference line and a target lane line of the vehicle;

the first planning unit is used for planning an avoidance path according to the avoidance position and controlling the vehicle to avoid;

a second determination unit configured to determine that the target exits the lane, in a case where it is determined that the vehicle information current to the oncoming lane satisfies the left-turn passing condition;

and the second planning unit is used for planning a left-turn path according to the target exit lane and controlling the vehicle to turn left.

13. The apparatus according to claim 12, wherein the first determining unit, when determining the avoidance position based on the left-turn reference line and the target lane line of the vehicle, specifically performs:

14. The apparatus according to claim 13, wherein the first determining unit, when determining the target direction, specifically performs:

15. The apparatus according to any one of claims 12-14, wherein the second planning unit, when planning an avoidance path according to the avoidance position, specifically performs:

16. The apparatus according to claim 15, wherein the second planning unit, when obtaining a constraint boundary according to the current lane and the exit road of the vehicle, specifically performs:

17. The apparatus according to any one of claims 12 to 16, wherein the second determining unit, in the case where it is determined that the vehicle information current to the oncoming lane satisfies the left-turn passing condition, specifically performs:

18. The apparatus according to any one of claims 12 to 16, wherein the second determination unit, when determining that the target exits the lane in a case where it is determined that the vehicle information current in the oncoming lane satisfies the left-turn passing condition, specifically performs:

19. The apparatus according to any one of claims 12-18, wherein the second determining unit, when determining that the target exits the lane, specifically performs:

acquiring attribute information of each candidate exit lane;

20. The apparatus according to claim 19, wherein the second determination unit, when obtaining the cost value of each of the candidate exit lanes from the attribute information, specifically performs:

21. The apparatus according to claim 12, wherein the first determining unit, when determining the avoidance position based on the left-turn reference line and the target lane line of the vehicle, specifically performs:

acquiring current driving data of the vehicle;

22. The apparatus according to claim 12, wherein the first determining unit, when determining the avoidance position based on the left-turn reference line and the target lane line of the vehicle, specifically performs:

acquiring current vehicle information of an opposite lane;

23. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.

24. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-11.

25. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-11.

26. An autonomous vehicle comprising the electronic device of claim 23, wherein the at least one processor is capable of performing the method of any of claims 1-11.