CN113788028B

CN113788028B - Vehicle control method, device and computer program product

Info

Publication number: CN113788028B
Application number: CN202111168011.7A
Authority: CN
Inventors: 杜海宁
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2021-09-29
Filing date: 2021-09-29
Publication date: 2023-01-10
Anticipated expiration: 2041-09-29
Also published as: CN113788028A

Abstract

The application discloses a vehicle control method, a vehicle control device and a computer program product, which can be applied to the field of automatic driving; the method comprises the following steps: controlling the target vehicle to run in an upstream steering lane, wherein the upstream steering lane is communicated with N downstream lanes through an intersection; the intersection includes: m virtual lanes located between the upstream steering lane and the N downstream lanes; determining lane congestion information of each virtual lane in the M virtual lanes, wherein the lane congestion information is information for reflecting the congestion degree of the virtual lanes; selecting one virtual lane from the M virtual lanes as a target virtual lane according to the lane congestion information of each virtual lane; and controlling the target vehicle to enter the target virtual lane so that the target vehicle enters one of the N downstream lanes through the intersection. The method and the device can enable the steering behavior of the target vehicle at the intersection without the steering guide line to be richer and truer, and effectively improve the passing efficiency.

Description

Vehicle control method, device and computer program product

Technical Field

The present application relates to the field of internet technologies, and in particular, to a method and an apparatus for controlling a vehicle, and a computer program product.

Background

With the increasing development of artificial intelligence, the application of artificial intelligence technology in life is more and more extensive, for example, the application in automatic driving technology. Wherein, the traffic simulation is an important stage before the automatic driving technology is applied to landing; by carrying out traffic simulation in advance, the automatic driving technology can keep better performance in practical application. At present, in the process of traffic simulation or in the process of actual automatic driving, a plurality of steering guide lines are usually required to be arranged between an upstream steering lane and a downstream lane communicated with an intersection so as to limit the steering driving path of a vehicle when the vehicle passes through the intersection; therefore, when the vehicle on the turning lane passes through the intersection, the vehicle can run according to the specified turning running path to avoid collision with other vehicles. Therefore, at present, only the condition of the intersection with the steering guide line is usually considered, and the condition of the intersection without the steering guide line is not considered; then, how to control the vehicle to pass through the intersection without the diversion guide line to drive into the downstream lane becomes a research hotspot.

Disclosure of Invention

The embodiment of the application provides a vehicle control method, a vehicle control device and a computer program product, which can enable the steering behavior of a target vehicle at an intersection without a steering guide line to be richer and truer, and effectively improve the traffic efficiency.

In one aspect, an embodiment of the present application provides a vehicle control method, where the method includes:

controlling a target vehicle to run in an upstream steering lane, wherein the upstream steering lane is communicated with N downstream lanes through an intersection; the intersection comprises: m virtual lanes located between the upstream steering lane and the N downstream lanes, N being a positive integer, M being an integer greater than 1;

determining lane congestion information of each virtual lane in the M virtual lanes, wherein the lane congestion information is information for reflecting the congestion degree of the virtual lanes;

selecting one virtual lane from the M virtual lanes as a target virtual lane according to the lane congestion information of each virtual lane;

and controlling the target vehicle to enter the target virtual lane so that the target vehicle enters one of the N downstream lanes through the intersection.

In another aspect, an embodiment of the present application provides a vehicle control apparatus, including:

the control unit is used for controlling a target vehicle to run in an upstream steering lane, and the upstream steering lane is communicated with N downstream lanes through an intersection; the intersection comprises: m virtual lanes located between the upstream steering lane and the N downstream lanes, wherein N is a positive integer, and M is an integer greater than 1;

the processing unit is used for determining lane congestion information of each virtual lane in the M virtual lanes, wherein the lane congestion information is information used for reflecting the congestion degree of the virtual lanes;

the processing unit is further configured to select one virtual lane from the M virtual lanes as a target virtual lane according to the lane congestion information of each virtual lane;

the control unit is further configured to control the target vehicle to enter the target virtual lane, so that the target vehicle enters one of the N downstream lanes through the intersection.

In another aspect, an embodiment of the present application provides a computer device, where the computer device includes an input interface and an output interface, and the computer device further includes:

a processor adapted to implement one or more instructions; and (c) a second step of,

a computer storage medium storing one or more instructions adapted to be loaded by the processor and to perform the steps of:

determining lane congestion information of each virtual lane in the M virtual lanes, wherein the lane congestion information is information for reflecting congestion degree of the virtual lanes;

In yet another aspect, embodiments of the present application provide a computer storage medium having one or more instructions stored thereon, the one or more instructions being adapted to be loaded by a processor and perform the following steps:

controlling a target vehicle to run in an upstream steering lane, wherein the upstream steering lane is communicated with N downstream lanes through an intersection; the intersection comprises: m virtual lanes located between the upstream steering lane and the N downstream lanes, wherein N is a positive integer, and M is an integer greater than 1;

In yet another aspect, an embodiment of the present application provides a computer program product, which includes a computer program; which computer program, when being executed by a processor, carries out the above-mentioned vehicle control method.

According to the embodiment of the application, M virtual lanes are introduced into the intersection, and each virtual lane is located between the upstream turning lane and one downstream lane, so that when a target vehicle running in the upstream turning lane intends to enter the downstream lane through the intersection, one virtual lane can be selected from the M virtual lanes as the target virtual lane according to the lane congestion information of each virtual lane, the target vehicle is controlled to enter the target virtual lane, and then the target vehicle enters one of the N downstream lanes on the basis of the target virtual lane. Therefore, the target virtual lane is selected by considering the congestion condition of each virtual lane, so that the steering behavior of the target vehicle executed based on the target virtual lane can better accord with the actual condition, and the authenticity of the steering behavior of the target vehicle at the intersection without a steering guide line can be effectively improved; the target vehicle can be prevented from entering the relatively blocked virtual lane, and the passing efficiency can be effectively improved. Moreover, by introducing M virtual lanes, the steering behavior of the target vehicle at the intersection without the steering guide lines can be enriched, and the target vehicle and other vehicles can run along the respective selected virtual lanes at the intersection, so that the probability of vehicle collision can be effectively reduced, and the traffic efficiency and the running safety of the vehicle can be further improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1a is a schematic view of an intersection provided by an embodiment of the present application;

FIG. 1b is a schematic view of an upstream steering lane and a downstream lane provided by an embodiment of the present application;

FIG. 1c is a schematic diagram of a positional relationship between a decision-line and a stop-line provided by an embodiment of the present application;

FIG. 1d is a schematic view of a virtual lane provided in an embodiment of the present application;

FIG. 2 is a schematic flow chart diagram illustrating a vehicle control method provided by an embodiment of the present application;

FIG. 3a is a schematic diagram illustrating a communication relationship between an upstream steering lane and a plurality of downstream lanes provided by an embodiment of the present application;

FIG. 3b is a schematic diagram of M virtual lanes between an upstream steering lane and a plurality of downstream lanes provided by embodiments of the present application;

FIG. 3c is a schematic diagram of the communication between an upstream steering lane and a downstream lane provided by embodiments of the present application;

FIG. 3d is a schematic diagram of M virtual lanes between an upstream steering lane and a downstream lane according to an embodiment of the present disclosure;

FIG. 3e is an enlarged schematic view of an area provided by an embodiment of the present application;

FIG. 3f is an enlarged schematic view of another area provided by an embodiment of the present application;

fig. 3g is an explanatory diagram of the queuing length of a virtual lane according to the embodiment of the present application;

fig. 3h is a schematic diagram illustrating a queuing length of another virtual lane provided in the embodiment of the present application;

fig. 3i is a schematic diagram of introducing a virtual lane at a right-hand intersection according to an embodiment of the present application;

FIG. 4 is a schematic flow chart diagram of a vehicle control method provided by another embodiment of the present application;

FIG. 5 is a schematic flow chart of traffic simulation based on a vehicle control method according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a vehicle control device according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the implementation method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making. The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like.

As artificial intelligence technology has been researched and developed, artificial intelligence technology has been developed and applied in a variety of fields, such as: automatic driving, unmanned, general smart home, intelligent wearable device, virtual assistant, intelligent speaker, intelligent marketing, unmanned aerial vehicle, robot, intelligent medical treatment, intelligent customer service, intelligent video service, and so on. The automatic driving technology generally comprises technologies such as high-precision maps, environmental perception, behavior decision, path planning, motion control and the like. The automatic driving technology generally comprises traffic simulation and real vehicle test (namely, controlling the vehicle to run on a real lane), and the traffic simulation is used as a zero-risk, fast-iteration and reproducible test method, thereby laying a solid foundation for the automatic driving technology to go on the road. The so-called traffic simulation, which can be called road traffic simulation, is an important tool for researching complex traffic problems; especially, when a system is too complex to be described by a simple abstract mathematical model, the traffic simulation effect is more prominent. The traffic simulation can clearly assist in analyzing and predicting the sections and reasons of traffic jam, and compare and evaluate the relevant schemes of city planning, traffic engineering and traffic management, so that the problems can be avoided or prepared as much as possible before the problems become realistic. In summary, the traffic simulation technology is a simulation model technology that reflects system behavior or process by applying simulation hardware and simulation software through simulation experiments and by means of some numerical calculations and problem solving.

Whether during an autonomous traffic simulation or during an autonomous real-vehicle test, it is often the case that a vehicle traveling in an upstream turn lane is required to pass through an intersection without a steering leader to enter the corresponding downstream lane. The intersection (1) can be called a plane intersection, and specifically refers to a position where two or more roads intersect on the same plane; for example, as shown in the black part in fig. 1a, the intersection may be a junction, a t-junction, or an intersection, etc., and for convenience of illustration, the intersection will be described as an intersection in the following. (2) The upstream steering lane means: a lane that supports a vehicle to enter the intersection and performs a turning behavior, among a plurality of lanes connected to the intersection; for example, the upstream turn-around lane may be the vehicle left turn-supporting lane R1 shown in FIG. 1b, or the upstream turn-around lane may also be the vehicle right turn-supporting lane R2 shown in FIG. 1b, and so on. (3) The downstream lane is: among a plurality of lanes connected to an intersection, a vehicle passes through a lane into which a turning behavior is performed in the intersection. For example, see FIG. 1b for an illustration: after entering the intersection, the vehicle on the lane R1 may enter the lane R3 or the lane R4 by performing a left turn in the intersection, and thus the downstream lane corresponding to the upstream turn lane R1 may include the lane R3 and the lane R4; the vehicle on the lane R2 can enter the lane R5 and the lane R6 by performing the right-turn behavior at the intersection after entering the intersection, and thus the downstream lane corresponding to the upstream-turn lane R2 can include the lane R5 and the lane R6.

Based on this, the embodiment of the application provides a vehicle control method to ensure the safety and the passing efficiency when a vehicle passes through an intersection without a steering guide line. The vehicle control method may be executed by a computer device, which may be a terminal or a server; the terminal mentioned herein may include, but is not limited to: smart phones, tablet computers, notebook computers, desktop computers, smart watches, smart televisions, smart vehicle terminals, and the like; the server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), a big data and artificial intelligence platform, and the like. In addition, the computer device may be located outside the blockchain network or within the blockchain network, which is not limited to this.

Specifically, the general principle of the vehicle control method is as follows: by arranging M virtual lanes (M is an integer larger than 1) between the upstream steering lane and the corresponding downstream lane in the intersection without the steering flow guide line, each vehicle in the upstream steering lane can drive into one of the M virtual lanes, so that the vehicle can drive into the corresponding downstream lane by completing steering behavior based on the driven virtual lane; therefore, the steering behaviors of all vehicles at the intersection without the steering guide lines can be effectively enriched, and the probability of collision among the vehicles can be effectively reduced because all the vehicles run along the respectively selected virtual lanes in the intersection, so that the traffic efficiency and the running safety of the vehicles are improved. Further, when any vehicle in the upstream turning lane intends to enter the downstream lane through the intersection, a virtual lane with a lower congestion degree can be selected from the M virtual lanes according to the congestion degree of each virtual lane, and is used as a virtual lane to be entered by the any vehicle; therefore, the vehicle can be effectively prevented from entering the relatively blocked virtual lane, and the traffic efficiency is further effectively improved. Furthermore, after any vehicle enters the selected virtual lane, different lane changing strategies can be selected according to the running condition of any vehicle, so that any vehicle can execute lane changing operation in the intersection, and the steering behavior of any vehicle in the intersection without the steering guide line is richer and more real.

The virtual lane is: a lane that is virtually recognized at an intersection and does not exist in the real world. Specifically, when the vehicle performs a steering action, it is determined at a certain place which virtual lane is to be taken, so that the position where the vehicle is located when the target virtual lane is determined may be referred to as a steering decision line; a virtual lane can then be understood as a lane that is virtually visualized in the intersection, starting from the steering decision line and ending at the beginning of the downstream lane. It should be understood that the specific location of the turning decision line is not limited in the embodiments of the present application, as it is considered that the vehicle does not generally decide which virtual lane to drive to before reaching the stop line of the intersection (i.e., the solid line marking indicating the stop position where the vehicle waits to pass when the traffic signal is red), but rather makes a decision at the time when the vehicle drives over the stop line or at some time after driving over the stop line, so that the turning decision line may be located at no earlier position in the intersection than the stop line of the intersection in the driving direction corresponding to the time when the vehicle does not drive into the intersection. Taking the position of the steering decision line later than the position of the stop line of the intersection as an example, a schematic diagram of the positions between the steering decision line and the stop line can be seen in fig. 1 c; a schematic view of a virtual lane can then be seen in fig. 1 d. In addition, the width and the curve shape of the virtual lane are not limited, and the virtual lane meets the requirements of vehicle dynamics and the geometric shape of the intersection; the width of the virtual lane may be taken to be around 3 meters, for example, depending on the width of most vehicles and safety examples between vehicles.

It should be further noted that the above-mentioned vehicle control method can be applied to the real vehicle test process of automatic driving by computer equipment; in this case, the computer device may control the vehicle to safely and efficiently pass through the intersection without the turning guide line during the automatic driving using the vehicle control method. Alternatively, the above-mentioned vehicle control method may also be applied by a computer device in an autonomous driving traffic simulation process; in this case, at least simulation software may be included in the computer device. The simulation software referred to herein may be a micro traffic simulation software that may include, but is not limited to, simulation software that requires or does not require networking; it can be understood that the traffic simulation is divided into macroscopic simulation, mesoscopic simulation and microscopic simulation according to the accuracy and range of the simulation, and the microscopic traffic simulation describes the simulation of the state of each vehicle in the traffic system with the behavior of the individual vehicle as a research object. When the computer device comprises simulation software, a logic algorithm related to the vehicle control method provided by the embodiment of the application can be embedded in the simulation software to perform simulation on the steering behavior of the vehicle in the intersection without the steering guide line; in the simulation software, the simulated vehicle can determine the virtual lane to be driven according to the congestion condition of each virtual lane, and can further execute lane changing operation according to the actual driving condition, so that the steering behavior of the simulated vehicle in the intersection without the steering guide line is richer and more real.

Based on the above description, the following describes the vehicle control method proposed in the embodiment of the present application with reference to the flowchart shown in fig. 2. Referring to fig. 2, the vehicle control method may include the following steps S201 to S204:

s201, the control target vehicle travels in the upstream steering lane.

The target vehicle may be any simulated vehicle in a traffic simulation process, or may be any vehicle in an automatic driving state in an actual vehicle test process, which is not limited to this. The upstream steering lane on which the target vehicle is traveling may be a lane supporting a left turn of the vehicle, or a lane supporting a right turn of the vehicle; for convenience of explanation, the following description will be given by taking the example in which the upstream steering lane is a lane for supporting a left turn of the vehicle. The upstream steering lane can be communicated with N downstream lanes through an intersection, and the meaning that the upstream steering lane is communicated with the downstream lanes is as follows: vehicles on the upstream turning lane can successfully drive into the downstream lane through the intersection. The intersections may include: m virtual lanes located between the upstream steering lane and N downstream lanes, wherein M is an integer greater than 1, and N is a positive integer; further, the intersection may also include a steering decision line.

When N is greater than 1, it means that the upstream turning lane may be communicated with a plurality of downstream lanes through the intersection, i.e. the upstream turning lane may correspond to a plurality of downstream lanes, as shown in fig. 3 a; wherein the dashed line between any two lanes in fig. 3a is used to indicate that the two lanes are in a connected state. In this case, one virtual lane in the intersection may correspond to one downstream lane, that is, a virtual lane exists between two lanes at the upstream and downstream, and the value of M is the same as the value of N. For example, if the intersection shown in fig. 3a is followed and the upstream turn lane is a left turn lane turning to the left from the north, and there are 3 downstream lanes corresponding to the upstream turn lane, 3 virtual lanes, which may be the virtual lane 31, the virtual lane 32 and the virtual lane 33 shown in fig. 3b, may be defined in the intersection. As can be seen from fig. 3 b: under the condition that the upstream steering lane corresponds to a plurality of downstream lanes, the N downstream lanes correspond to the M virtual lanes one by one, and the virtual lane corresponding to any downstream lane starts from the steering decision line and ends at the start of the any downstream lane. Also, in this case, the target vehicle may have a one-to-many relationship of travel paths or trajectories when passing through the intersection to enter the downstream lane; as the target vehicle may travel through the intersection to enter one of the downstream lanes along a travel path indicated by virtual lane 31 or virtual lane 32 or virtual lane 33.

When N is equal to 1, it means that the upstream turning lane may communicate with one downstream lane through the intersection, i.e., the upstream turning lane may correspond to one downstream lane, as shown in fig. 3 c. In this case, each virtual lane in the intersection can correspond to the downstream lane, that is, more than one virtual lane exists between two lanes at the upstream and downstream; the value of M is different from that of N, and the value of M can be set according to an empirical value or a service requirement. For example, if the intersection shown in fig. 3c is accepted and the upstream turning lane is a left-turning lane turning to the left from the north, and the total number of the downstream lanes corresponding to the upstream turning lane is 1, then if 3 virtual lanes are defined in the intersection, the 3 virtual lanes may be the virtual lane 34, the virtual lane 35, and the virtual lane 36 shown in fig. 3d, respectively. As can be seen from fig. 3 d: in the case where the upstream steering lane corresponds to a downstream lane, each virtual lane starts at the steering decision line and ends at the start of the downstream lane. Also, in this case, even if there is only one downstream lane, when the target vehicle passes through the intersection to enter the downstream lane, there may be a plurality of travel paths or trajectories between the upstream turn lane and the downstream lane; as the target vehicle may travel through the intersection to enter a downstream lane along a travel path indicated by virtual lane 34 or virtual lane 35 or virtual lane 36.

S202, determining lane congestion information of each virtual lane in the M virtual lanes.

The lane congestion information is information for reflecting the congestion level of the virtual lane. For example, the lane congestion information of the mth virtual lane may include: the estimated time required by the mth virtual lane is passed; as another example, the m-th virtual length of lane congestion information may include: the queue length of the mth virtual lane, the so-called queue length, can be measured as: and the distance between the start of the downstream lane corresponding to the mth virtual lane and the farthest position where the vehicle is allowed to run in the mth virtual lane currently. Wherein m is from [1,M ]. For convenience of illustration, the following description mainly takes the example that the lane congestion information of the mth virtual lane includes the queue length of the mth virtual lane.

Practice has shown that there are often overlapping areas between virtual lanes in an intersection. For example, referring to fig. 3b, when the upstream turn lane corresponds to a plurality of downstream lanes, since the starting points of the M virtual lanes in the intersection are the same, there must be an overlapping area in a certain area (such as the area marked with the reference number 30 in fig. 3 b) near the starting points of the M virtual lanes, an area where all of the 3 virtual lanes overlap, an area where only the virtual lane 31 and the virtual lane 32 overlap, and so on; as shown in fig. 3d, when the upstream steering lane corresponds to a downstream lane, since the starting point and the ending point of each virtual lane are the same, there are necessarily overlapped regions, such as a region where 3 virtual lanes are overlapped, a region where only the virtual lane 34 and the virtual lane 35 are overlapped, and the like, in a certain region near the starting point (such as the region marked with the reference numeral 37 in fig. 3 d) and a certain region near the ending point (such as the region marked with the reference numeral 38 in fig. 3 d) of each virtual lane.

In the embodiment of the present application, a region of overlap between virtual lanes may be defined as a trajectory overlap region; also, one trajectory overlapping region may be a region where two or more virtual lanes overlap each other. Then, in order to prevent a vehicle collision, the trajectory overlap region can be occupied by at most one vehicle at any time in the lateral direction; that is, when there is a vehicle stopped in this trajectory overlap region, the following vehicle does not lie laterally alongside this vehicle, but merely waits behind. Wherein, the transverse direction mentioned here refers to the direction perpendicular to the central line of the lane, and the longitudinal direction mentioned later refers to the direction parallel to the central line of the lane; based on this, the driving parameters of the vehicle in the direction perpendicular to the lane center line may be referred to as lateral driving parameters, and the driving parameters of the vehicle in the direction parallel to the lane center line may be referred to as longitudinal driving parameters. Optionally, the driving parameters in the embodiment of the present application include speed, acceleration, and position parameters. It should be understood that when one vehicle stops in a certain trajectory overlapping area, the stopped vehicle only affects other vehicles in the virtual lanes related to the trajectory overlapping area where the stopped vehicle is located, and does not affect other virtual lanes not related to the trajectory overlapping area.

For example, see the enlarged schematic view of region 30 shown in FIG. 3 e: when the vehicle a stops in the virtual lane 36 and the stopped position thereof is in the trajectory overlap area a (the area marked with 41 in fig. 3 e), since the trajectory overlap area a only relates to the virtual lane 33 and the virtual lane 32, which do not overlap with the virtual lane 31, the vehicle a does not affect the vehicle traveling on the virtual lane 31 or the other vehicle entering the virtual lane 31, and the vehicle a only cannot make the other vehicle enter the trajectory overlap area a. When the vehicle B stops at the virtual lane 32 and the stopped position thereof is in the trajectory overlap region B (the region marked with 42 in fig. 3 e), the vehicle B may cause no other vehicle to enter the trajectory overlap region B because the trajectory overlap region B relates to all the virtual lanes. For another example, see the enlarged schematic view of region 38 shown in FIG. 3 f: when the vehicle C stops in the virtual lane 36 and the stopped position is in the trajectory overlap region C (the region marked with 44 in fig. 3 f), since the trajectory overlap region C only relates to the virtual lane 36 and the virtual lane 35 and does not overlap with the virtual lane 34, the vehicle C does not affect the vehicle running on the virtual lane 34 or the other vehicle entering the virtual lane 34, and the vehicle a only cannot make the other vehicle enter the trajectory overlap region C. When the vehicle D stops in the virtual lane 35 and the stopped position is in the trajectory overlap region D (the region marked with 45 in fig. 3 f), the vehicle D may cause no other vehicle to enter the trajectory overlap region D because the trajectory overlap region D relates to all virtual lanes.

Of course, it should be understood that: referring to fig. 3d, when the upstream turning lane corresponds to a downstream lane, each virtual lane can be roughly divided into three parts: region 37, side-by-side travel region, and region 38; in the parallel driving areas, the shapes of the virtual lanes can meet the requirement that when several vehicles stop on the respective virtual lanes simultaneously in parallel, the vehicles still meet the transverse safety distance, so when the vehicle in any virtual lane stops in the parallel driving areas in any virtual lane, the vehicle does not influence the driving of the vehicles in other virtual lanes.

Based on the above description, when the lane congestion information of the mth virtual lane includes the queue length of the mth virtual lane, a specific implementation of step S202 may include: the computer device may detect whether the N downstream lanes are congested. When no congestion exists in the N downstream lanes, the method can indicate that all vehicles can normally run through the intersection, namely, no vehicle waiting in line exists in each virtual lane in the intersection; then the computer device may set the queuing length of each of the M virtual lanes to the same queuing length when there is no congestion in the N downstream lanes, e.g., may set the queuing length of each virtual lane to 0.

When congestion exists in the N downstream lanes, one or more track overlapping areas corresponding to the mth virtual lane may be determined in an area where the M virtual lanes are located, where one track overlapping area corresponding to the mth virtual lane is: and an area where the m-th virtual lane overlaps at least one other virtual lane. If the vehicles do not stop in each track overlapping area, determining the length between the starting point and the ending point of the queue of the vehicle queue corresponding to the mth virtual lane as the queuing length of the mth virtual lane; the vehicle queuing queue corresponding to the mth virtual lane may refer to: the present invention is not limited to the vehicle queue formed by vehicles in a queuing state in the mth virtual lane, or the vehicle queue formed by vehicles in a queuing state in the mth virtual lane and a downstream lane corresponding to the mth virtual lane. And if the vehicle stops in at least one track overlapping area, setting the queuing length of the mth virtual lane and the queuing lengths of other virtual lanes related to the track overlapping area in which the vehicle stops to be the same queuing length.

For example, the following steps are carried out: assuming that the mth virtual lane is the virtual lane 33 shown in fig. 3e, the trajectory overlap region corresponding to the mth virtual lane may include a trajectory overlap region a and a trajectory overlap region B. If there is no stopped vehicle in both the trajectory overlap area a and the trajectory overlap area B, but there is a vehicle queue in the area located before the trajectory overlap area a in the traveling direction of the target vehicle, the queue length of the m-th virtual lane is equal to the length of the vehicle queue, as shown in fig. 3 g. If there is a stopped vehicle in the virtual lane 34, and the stopped vehicle is specifically stopped in the trajectory overlap area a, but there is no stopped vehicle in the trajectory overlap area B, since the other virtual lanes related to the trajectory overlap area a are only the virtual lane 32, the queue length of the mth virtual lane and the queue length of the virtual lane 32 may be set to be the same queue length, as shown in fig. 3 h.

And S203, selecting one virtual lane from the M virtual lanes as a target virtual lane according to the lane congestion information of each virtual lane.

In one specific implementation, if the lane congestion information of each virtual lane includes: the queuing length of each virtual lane; a specific implementation of step S203 may include: and if the queuing lengths of the virtual lanes are the same, randomly selecting one virtual lane from the M virtual lanes as a target virtual lane. If the queuing lengths of at least two virtual lanes are different, selecting the virtual lane with the shortest queuing length from the M virtual lanes as a target virtual lane; it should be understood that, in this case, if the number of the virtual lanes whose queuing length is the shortest is at least two, the computer device may randomly select one virtual lane from the virtual lanes whose queuing length is the shortest as the target virtual lane.

In another specific implementation, if the lane congestion information of each virtual lane includes: the estimated time length required by each virtual lane is passed; specific embodiments of step S203 may include: if the estimated time length corresponding to each virtual lane is the same, randomly selecting one virtual lane from the M virtual lanes as a target virtual lane; and if the estimated time lengths corresponding to at least two virtual lanes are different, selecting the virtual lane with the shortest estimated time length from the M virtual lanes as a target virtual lane.

S204, controlling the target vehicle to drive into the target virtual lane so that the target vehicle drives into one of the N downstream lanes through the intersection.

In a specific implementation, after the target virtual lane is selected in step S203, the target vehicle may be controlled to enter the target virtual lane, so that the target vehicle may pass through the intersection based on the target virtual lane and then enter one of the N downstream lanes. In one case, after the target vehicle enters the target virtual lane, the computer device may control the target vehicle to travel in the target virtual lane until entering the corresponding downstream lane through the intersection; in this case, then, the downstream lane that the target vehicle finally enters is the downstream lane corresponding to the target virtual lane among the N downstream lanes. Or in another case, after the target vehicle enters the target virtual lane, the computer device may also control the target vehicle to perform one or more lane changing operations; in this case, the downstream lane that the target vehicle finally enters is a downstream lane corresponding to the virtual lane that the target vehicle enters through the last lane change operation among the N downstream lanes.

It should be noted that, all of fig. 3a to fig. 3h are described as examples where the upstream turning lane is a left-turning lane of the vehicle, but this does not limit an application scenario of the vehicle control method proposed in the embodiment of the present application. In practical application, the vehicle control method is not only suitable for a left-turn intersection without a steering guide line, but also suitable for a right-turn intersection without a steering guide line; for example, a schematic diagram of introducing a virtual lane in a right-hand intersection by the vehicle control method can be seen in fig. 3 i.

According to the embodiment of the application, M virtual lanes are introduced into the intersection, and each virtual lane is located between the upstream steering lane and one downstream lane, so that when a target vehicle running in the upstream steering lane intends to enter the downstream lane through the intersection, one virtual lane can be selected from the M virtual lanes as the target virtual lane according to the lane congestion information of each virtual lane, the target vehicle is controlled to enter the target virtual lane, and then the target vehicle enters one of the N downstream lanes based on the target virtual lane. Therefore, the target virtual lane is selected by considering the congestion condition of each virtual lane, so that the steering behavior of the target vehicle executed based on the target virtual lane can better accord with the actual condition, and the authenticity of the steering behavior of the target vehicle at the intersection without a steering guide line can be effectively improved; and the target vehicle can be prevented from entering the relatively blocked virtual lane, and the traffic efficiency can be effectively improved. Moreover, by introducing M virtual lanes, the steering behavior of the target vehicle at the intersection without the steering guide lines can be enriched, and the target vehicle and other vehicles can run along the respective selected virtual lanes at the intersection, so that the probability of vehicle collision can be effectively reduced, and the traffic efficiency and the running safety of the vehicle can be further improved.

Fig. 4 is a schematic flowchart of another vehicle control method provided in the embodiment of the present application, where the vehicle control method can be executed by the aforementioned computer device. As shown in fig. 4, the vehicle control method may include the following steps S401 to S408:

s401, the control target vehicle travels in the upstream steering lane.

Wherein, the upstream turning lane is communicated with N downstream lanes through the crossroad; the intersection includes: m virtual lanes located between the upstream steering lane and the N downstream lanes.

S402, determining lane congestion information of each virtual lane in the M virtual lanes, wherein the lane congestion information is information for reflecting the congestion degree of the virtual lanes.

And S403, selecting one virtual lane from the M virtual lanes as a target virtual lane according to the lane congestion information of each virtual lane, and controlling the target vehicle to drive into the target virtual lane.

In the specific implementation, the specific implementation of steps S401 to S403 may refer to the related description of steps S201 to S204 mentioned in the above method embodiment, and is not described herein again. After the target vehicle enters the target virtual lane, the following steps S404 to S406 may be performed in the longitudinal direction to follow the target vehicle, or the following steps S407 to S408 may be performed in the lateral direction to switch the lane of the target vehicle. It should be understood that the embodiment of the present application is described by taking the steps S404 to S406 as an example, and then the steps S407 to S408 as an example; however, in other embodiments, the steps S407 to S408 may be executed to perform lane change control on the target vehicle, and then the following logic similar to the steps S404 to S406 may be adopted to perform following control on the target vehicle in the virtual lane after the lane change.

S404, after the target vehicle enters the target virtual lane, a target leading vehicle of the target vehicle is searched along the target virtual lane and the adjacent virtual lanes of the target virtual lane.

The target leading vehicle is a leading vehicle which is closest to the target vehicle and has a position satisfying a position condition, among all leading vehicles of the target vehicle, and the leading vehicle is a vehicle which is located ahead of the target vehicle in the longitudinal direction. Specifically, the location conditions may include: the front guide vehicle is positioned in the target virtual lane; alternatively, the location conditions include: the leading vehicle is located in the adjacent virtual lane, and the leading vehicle is located in a track overlapping area between the target virtual lane and the adjacent virtual lane. Optionally, the location condition may further include: the front guide vehicle is positioned in a downstream lane corresponding to the target virtual lane; that is, in this case, when the target leading vehicle is searched downstream along the target virtual lane, the extension of the target virtual lane (i.e., the corresponding downstream lane) may also be considered, and if the target leading vehicle is not found in both the target virtual lane and the adjacent virtual lane, the target leading vehicle may be further considered to be searched in the downstream lane corresponding to the target virtual lane.

In a specific implementation, the computer device may sequentially traverse each leading vehicle of the target vehicle along the target virtual lane and adjacent virtual lanes of the target virtual lane in a traversal order from small to large distances between the target vehicle and the leading vehicles. If the position of the currently traversed front vehicle meets the position condition, stopping traversing, and taking the currently traversed front vehicle as a target front vehicle of the target vehicle; and if the position of the currently traversed leading vehicle does not meet the position condition, continuing traversing to find the target leading vehicle of the target vehicle. The distance between the target vehicle and each lead vehicle can be calculated by using a Frenet (S-T) coordinate system, which is a coordinate system used in the automatic driving technique.

Based on the above description of step S404, the following further explains the way of the computer device to find the target leading vehicle; specifically, the process of finding the target leading vehicle may be as follows:

when the target vehicle runs in the target virtual lane, a leading vehicle closest to the target vehicle can be found in the target virtual lane and the adjacent virtual lane through Frenet (S-T) coordinates. If the distance between the found leading vehicle and the target vehicle is greater than the distance threshold, it can be considered that the leading vehicle closest to the target vehicle is not found, and at this time, the target leading vehicle can be considered as a virtual vehicle infinitely distant from the target vehicle, and the target vehicle can accelerate freely in this case. If the distance between the found front guide vehicle and the target vehicle is smaller than the distance threshold value, whether the found front guide vehicle is located in the target virtual lane or the adjacent virtual lane can be further judged. If the found front guide vehicle is positioned on the target virtual lane, taking the front guide vehicle as a target front guide vehicle in a vehicle following algorithm; and if the found front guide vehicle is positioned on the adjacent virtual lane, judging whether the found front guide vehicle is positioned in a track overlapping area between the target virtual lane and the adjacent virtual lane. If the target leading vehicle is located in the track overlapping area, taking the leading vehicle as a target leading vehicle in a vehicle following algorithm; if the vehicle is not located in the track overlapping area, the leading vehicle is considered not to have longitudinal influence on the target vehicle, so that the leading vehicle can be ignored, the leading vehicles on the target virtual lane and the adjacent virtual lane can be continuously searched downstream, and the like. It should be noted that, when the target leading vehicle is searched downstream along the target virtual lane, the extension of the target virtual lane, i.e. the corresponding downstream lane, is also considered.

S405, if the target leading vehicle is found, determining longitudinal driving parameters of the target vehicle based on the target leading vehicle, and controlling the target vehicle to drive in the target virtual lane according to the longitudinal driving parameters.

In a specific implementation process, a vehicle following algorithm (or referred to as a vehicle following algorithm) may be used to process a longitudinal speed of the target vehicle and a longitudinal distance between the target leading vehicle and the target vehicle through a Frenet (S-T) coordinate, so as to obtain a longitudinal driving parameter of the target vehicle. Then, the target vehicle may be controlled to travel in the target virtual lane according to the longitudinal travel parameter. The longitudinal driving parameters may include, but are not limited to: the maximum driving speed and the minimum safe inter-vehicle distance of the target vehicle; the maximum driving speed is used for indicating the maximum speed (such as road speed limit) which cannot be exceeded by the target vehicle in the driving process, and the minimum safe inter-vehicle distance is used for indicating the minimum inter-vehicle distance which needs to be maintained by the target vehicle all the time in the driving process.

And S406, if the target leading vehicle is not found, controlling the target vehicle to accelerate in the target virtual lane. Or if the target leading vehicle is not found, controlling the target vehicle to run at a constant speed in the target virtual lane according to the current speed; the current speed refers to the speed used by the target vehicle when the target front vehicle is not found.

S407, in the process that the target vehicle runs on the target virtual lane, if the target vehicle has a lane change intention, acquiring a lane change condition of the target vehicle.

In the specific implementation, in the process that the target vehicle runs in the target virtual lane, the vehicles in the adjacent virtual lanes can be judged; when the lane change will and the lane change condition of the target vehicle are met, the target vehicle can be controlled to start the lane change behavior to change to the adjacent virtual lane for driving. Specifically, the lane change probability may be set as a function of the degree of aggressiveness of the target vehicle, where the calculation form of the function is not limited; for example, it may be set that the more aggressive the vehicle, the more likely it is to change lanes between virtual lanes in the intersection. In the embodiment of the present application, a floating point number a between (0,1) may be used to represent the aggressiveness of the target vehicle, where 0 represents the most conservative type, and 1 represents the most aggressive type; the target vehicle can adopt different driving behaviors to reflect the diversity of traffic flows according to different degrees of acceleration.

The higher the vehicle is excited, the more the vehicle is excited; the lower the aggressiveness of the vehicle, the more conservative the vehicle is. For example, if the vehicle a and the vehicle B travel on a straight lane and simultaneously see an intersection ahead at the same distance, the vehicle a may change lanes earlier than the vehicle B and the lane change speed of the vehicle a is faster if the vehicles a and B want to change lanes. Therefore, the way for determining whether the target vehicle has the intention to change lanes may be as follows: acquiring the degree of acceleration of a target vehicle; if the aggressive degree of the target vehicle is higher than or equal to the preset aggressive degree, determining that the target vehicle has a lane change intention; and if the aggressive degree of the target vehicle is lower than the preset aggressive degree, determining that the target vehicle has no intention of changing lanes.

And S408, when the target vehicle meets the lane change condition, controlling the target vehicle to run from the target virtual lane to the adjacent virtual lane of the target virtual lane.

The lane change condition of the target vehicle may include, but is not limited to: the distance between the nearest vehicle in the adjacent virtual lanes, which is longitudinally positioned in front of the target vehicle, and the target vehicle is required to be greater than the preset safety distance; and the distance between the nearest vehicle longitudinally behind the target vehicle in the adjacent virtual lanes and the target vehicle is required to be greater than the preset safety distance. Accordingly, the computer device may calculate a distance between a nearest vehicle located longitudinally ahead of the target vehicle in the adjacent virtual lane and the target vehicle by using Frenet (S-T) coordinates, to obtain a first distance; and calculating the distance between the nearest vehicle longitudinally behind the target vehicle in the adjacent virtual lanes and the target vehicle to obtain a second distance. If the first distance and the second distance are both greater than the preset safe distance, determining that the target vehicle meets the lane changing condition; otherwise, determining that the target vehicle does not meet the lane changing condition.

In a case where the target vehicle satisfies the lane change condition, the computer device may calculate a lateral traveling parameter of the target vehicle based on a regular lane change algorithm, thereby controlling the target vehicle to travel from the target virtual lane to an adjacent virtual lane of the target virtual lane according to the lateral traveling parameter. It should be understood that if the target vehicle does not satisfy the lane change condition, the target vehicle may be controlled to continue traveling in the target virtual lane.

Further, considering that in the actual driving process, there may be a case that at least two vehicles want to simultaneously enter the same track overlapping area, then the problem of which vehicle is moving first and which vehicle is moving later, that is, the problem of which vehicle is moving into the track overlapping area first can be faced at this time. See, for example, the foregoing FIG. 3f for an illustration: the vehicle C and the vehicle on the virtual lane 34 (referred to as the vehicle E) do not affect each other in the lateral direction at this time; however, when the vehicle D moves out of the trajectory overlap region 45 to enter the downstream lane, the vehicle C and the vehicle E face a situation in which the vehicle D moves into the trajectory overlap region 45 first. In this case, in order to ensure the safety of vehicle driving, the embodiment of the present application may consider the time interval between the vehicles with potential lateral competition and the overlapping area of the trajectory to be driven into, and the vehicle with the smaller time interval may have the right of way ahead, so as to start driving first. If the time intervals of all vehicles are identical, a more aggressive vehicle can be selected according to the aggressive degree of the vehicles so as to have the foreright. If the aggressiveness of each vehicle is the same, then a vehicle can be randomly selected to have the right of way. For the vehicle without the right of way ahead, a parking waiting is selected, and the vehicle tail waiting for the vehicle with the right of way ahead exceeds the vehicle head of the vehicle in the longitudinal distance to consider starting. The time interval refers to the interval duration required by the vehicle to pass through the track overlapping area to be driven in.

Based on the above, in the process that the target vehicle runs in the target virtual lane, if K target track overlapping areas corresponding to the target virtual lane exist in the area where the M virtual lanes are located, wherein K is a positive integer; when the target vehicle is about to drive into the k-th target track overlapping area, the computer device may further detect a transverse competing vehicle in M-1 virtual lanes of the M virtual lanes except the target virtual lane; the so-called transverse competing vehicles are: and in the M-1 virtual lanes, a vehicle which is about to drive into the k-th target track overlapping area belongs to [1,K ]. If the transverse competitive vehicle is not detected, the target vehicle can be controlled to continue to run in the target virtual lane so as to enter the k-th target track overlapping area; and if at least one transverse competitive vehicle is detected, selecting a vehicle with the right of way in the target vehicle and the at least one transverse competitive vehicle, and controlling the target vehicle to run in the target virtual lane according to the selection result.

The specific implementation manner of selecting the vehicle with the right of way in advance from the target vehicle and the at least one transverse competing vehicle may include: and determining the time distance between the target vehicle and the k target track overlapping area and the time distance between each transverse competing vehicle and the k target track overlapping area. If the determined time intervals are different, selecting the vehicle with the minimum time interval from the target vehicle and at least one transverse competitive vehicle as the vehicle with the right of way ahead; and if the determined time intervals are the same, selecting the vehicle with the priority from the target vehicle and at least one transverse competitive vehicle according to the degree of the target vehicle and the degree of the transverse competitive vehicle. Specifically, if the aggressiveness degree of each vehicle in the target vehicle and each transverse competitive vehicle is different, selecting the vehicle with the highest aggressiveness degree from the target vehicle and at least one transverse competitive vehicle as the vehicle with the right of way ahead; and if the excitation degrees of the target vehicle and each vehicle in the transverse competitive vehicles are the same, randomly selecting one vehicle from the target vehicle and at least one transverse competitive vehicle as the vehicle with the right of way.

The specific implementation method for controlling the target vehicle to run in the target virtual lane according to the selection result may include: if the selection result indicates that the vehicle with the right of way ahead is the target vehicle, controlling the target vehicle to continue running in the target virtual lane so as to drive into the k-th target track overlapping area; and if the selection result indicates that the vehicle with the right of way ahead is not the target vehicle, controlling the target vehicle to stop waiting, starting the target vehicle and controlling the target vehicle to continue running in the target lane after the tail of the vehicle with the right of way ahead exceeds the head of the target vehicle in the longitudinal direction so as to drive into the k-th target track overlapping area.

The embodiment of the application introduces the virtual lane and the track overlapping area in the intersection without the steering guide line, and correspondingly provides a set of driving rules. On one hand, the target vehicle in the upstream steering lane can steer without being limited by the connecting line at the intersection, so that the steering behavior of the target vehicle at the intersection without the steering guide line is richer and more real; on the other hand, when the downstream lane is congested, the target vehicle can fully utilize the space in the intersection to stop and wait, so that the downstream lane has enough space and then sequentially passes through the intersection to drive into the downstream lane, and therefore, when the target vehicle passes through the intersection to drive into the corresponding downstream lane, safety and traffic efficiency can be both considered.

Based on the above description of the vehicle control method shown in fig. 2 and fig. 4, the following description will be given by taking as an example that the vehicle control method is applied to a traffic simulation process, and a target vehicle is a left-turn simulated vehicle (hereinafter simply referred to as a simulated vehicle) in the traffic simulation process, and referring to the flowchart shown in fig. 5, an application process of the vehicle control method is described:

s50, the simulation step size for the left turn vehicle begins.

And s51, judging whether the left-turning vehicle runs on the virtual lane or not during the running process of the left-turning vehicle. If the left-turn vehicle is not driving on the virtual lane, step s52 may be further performed; if the left-turn vehicle is traveling on the virtual lane, step s55 may be further performed.

And s52, judging whether the left-turning vehicle reaches a steering decision line of the intersection or not. If the left-turning vehicle has reached the steering decision line, step s53 may be further performed; if the left-turning vehicle does not reach the steering decision line, step s54 may be further performed.

And s53, selecting the virtual lane with the shortest queuing length as the target virtual lane according to the queuing lengths of the virtual lanes, and controlling the target vehicle to drive into the target virtual lane. After step s53 is performed, step s55 may be continued.

And s54, judging whether the target vehicle passes through the stop line of the intersection. If the stop line is driven, executing step s59; and if the vehicle does not drive through the stop line, judging whether the signal lamp state of the intersection is a green lamp state. If the light is in the green state, executing step s59; if the vehicle is not in the green light state, the left-turning vehicle is controlled to decelerate and stop, and whether the left-turning vehicle is located in the lane changing prohibition area or not is judged. If not, step s60 can be executed; if the vehicle is located in the lane change forbidding area, the following/lane change judgment of the left-turning vehicle can be determined to be completed in the simulation step length.

s55, detecting whether a transverse competitive vehicle exists in the adjacent virtual lane of the current virtual lane where the left-turning vehicle is currently located; if so, step s56 is executed, and if not, step s57 is executed.

s56, detecting whether the left-turning vehicle has the right of way; if yes, step s57 is executed, and if not, step s58 is executed.

s57, controlling the left-turning vehicle to continue running in the current virtual lane; after step s57 is performed, step s59 may be continued.

And s58, judging whether the tail of the vehicle with the right of way ahead exceeds the head of the left-turning vehicle in the longitudinal direction. If yes, controlling the left-turning vehicle to accelerate and start, and executing step s59; if not, the control target vehicle decelerates to stop or decelerates to travel, and then step s60 may be executed.

And s59, searching a leading vehicle which is closest to the left-turning vehicle in the longitudinal direction in the virtual lane where the left-turning vehicle is located and the adjacent virtual lane, and judging whether the leading vehicle is found. If the virtual vehicle is not found, the virtual vehicle with the infinite distance can be found, and the infinite leading vehicle is used as a target leading vehicle to calculate the longitudinal driving parameters of the left-turn vehicle; if the vehicle is found, whether the found leading vehicle is located in a virtual lane where the left-turn vehicle is located or a downstream lane corresponding to the virtual lane is judged. If so, taking the found front guide vehicle as a target front guide vehicle to calculate longitudinal driving parameters of the left-turning vehicle; if not, the found front vehicle is indicated to be located in the adjacent virtual lane, and whether the found front vehicle is located in the track overlapping area can be further judged at the moment. If the vehicle is located in the track overlapping area, the found front vehicle is used as a target front vehicle to calculate longitudinal driving parameters of a left-turning vehicle; and if the vehicle is not located in the track overlapping area, ignoring the found leading vehicle, and continuously executing the step of searching the leading vehicle which is closest to the left-turning vehicle in the longitudinal direction in the virtual lane where the left-turning vehicle is located and the adjacent virtual lane. After the longitudinal running parameter is obtained, the target vehicle may be controlled to run in the virtual lane according to the longitudinal running parameter, and step s60 is performed.

And s60, judging whether to change the lane according to the aggressive degree of the left-turning vehicle. If the lane is changed, judging whether the target vehicle meets the lane changing condition; and if the simulation step length is not met, determining that the following/lane changing judgment of the left-turning vehicle is finished in the simulation step length. If the lane is not changed, the following/lane changing judgment of the left-turning vehicle can be directly determined to be completed in the simulation step length.

Based on the description, the traffic simulation can be carried out on the intersection without the steering guide line, the traffic efficiency can be guaranteed while the collision of motor vehicles is avoided, the traffic simulation effect is closer to reality, the traffic simulation at the virtual city level is realized, and the automatic driving service is better served.

Based on the description of the above vehicle control method embodiments, the embodiments of the present application also disclose a vehicle control apparatus, which may be a computer program (including program code) running in a computer device. The vehicle control apparatus may execute the vehicle control methods shown in fig. 2, 4, and 5. Referring to fig. 6, the vehicle control apparatus may operate the following units:

a control unit 601 for controlling a target vehicle to travel in an upstream turn lane, the upstream turn lane being communicated with N downstream lanes through an intersection; the intersection comprises: m virtual lanes located between the upstream steering lane and the N downstream lanes, N being a positive integer, M being an integer greater than 1;

a processing unit 602, configured to determine lane congestion information of each virtual lane in the M virtual lanes, where the lane congestion information is information used to reflect congestion degrees of the virtual lanes;

the processing unit 602 is further configured to select one virtual lane from the M virtual lanes as a target virtual lane according to the lane congestion information of each virtual lane;

the control unit 601 is further configured to control the target vehicle to enter the target virtual lane, so that the target vehicle enters one of the N downstream lanes through the intersection.

In one embodiment, the intersection further comprises: a steering decision line;

when N is equal to 1, each virtual lane starts from the steering decision line and ends at the start of the downstream lane;

when N is larger than 1, the N downstream lanes correspond to the M virtual lanes one by one; and the virtual lane corresponding to any downstream lane starts from the steering decision line and ends at the start of any downstream lane.

In another embodiment, the lane congestion information of the mth virtual lane includes: the queuing length of the mth virtual lane is m ∈ [1,M ]; accordingly, when the processing unit 602 is configured to determine lane congestion information of each virtual lane of the M virtual lanes, it may specifically be configured to:

when the N downstream lanes are congested, determining one or more track overlapping areas corresponding to the mth virtual lane in an area where the M virtual lanes are located, wherein one track overlapping area is an area where the mth virtual lane and at least one other virtual lane are overlapped;

if the vehicles do not stop in each track overlapping area, determining the length between the starting point and the ending point of the queue of the vehicle queue corresponding to the mth virtual lane as the queuing length of the mth virtual lane;

and if the vehicle stops in at least one track overlapping area, setting the queuing length of the mth virtual lane and the queuing lengths of other virtual lanes related to the track overlapping area in which the vehicle stops to be the same queuing length.

In another embodiment, when the processing unit 602 is configured to determine lane congestion information of each virtual lane of the M virtual lanes, the processing unit may further be configured to:

and when the N downstream lanes are not congested, setting the queuing length of each virtual lane in the M virtual lanes as the same queuing length.

In another embodiment, the lane congestion information of each virtual lane includes: the queuing length of each virtual lane; correspondingly, when the processing unit 602 is configured to select one virtual lane from the M virtual lanes as the target virtual lane according to the lane congestion information of each virtual lane, it may specifically be configured to:

if the queuing lengths of the virtual lanes are the same, randomly selecting a virtual lane from the M virtual lanes as a target virtual lane;

and if at least two virtual lanes have different queuing lengths, selecting the virtual lane with the shortest queuing length from the M virtual lanes as a target virtual lane.

In another embodiment, in the area where the M virtual lanes are located, there are K target track overlapping areas corresponding to the target virtual lane, where K is a positive integer; accordingly, the control unit 601 is further configured to:

when the target vehicle is about to drive into a k-th target track overlapping area, detecting transverse competitive vehicles in M-1 virtual lanes except the target virtual lane in the M virtual lanes; the transverse competing vehicles are: in the M-1 virtual lanes, a vehicle which is to be driven into the k target track overlapping area belongs to [1,K ];

if the transverse competitive vehicle is not detected, controlling the target vehicle to continuously run in the target virtual lane so as to enter the k-th target track overlapping area;

and if at least one transverse competitive vehicle is detected, selecting a vehicle with a right of way in the target vehicle and the at least one transverse competitive vehicle, and controlling the target vehicle to run in the target virtual lane according to a selection result.

In another embodiment, when the control unit 601 is configured to control the target vehicle to travel in the target virtual lane according to the selection result, it may specifically be configured to:

if the selection result indicates that the vehicle with the right of way ahead is the target vehicle, controlling the target vehicle to continue running in the target virtual lane so as to drive into the k-th target track overlapping area;

and if the selection result indicates that the vehicle with the right of way ahead is not the target vehicle, controlling the target vehicle to stop waiting, starting the target vehicle and controlling the target vehicle to continue running in the target lane after the tail of the vehicle with the right of way ahead exceeds the head of the target vehicle in the longitudinal direction so as to drive into the k-th target track overlapping area.

In another embodiment, the control unit 601, when being configured to select a vehicle with a right of way among the target vehicle and the at least one laterally competing vehicle, may be specifically configured to:

determining a time distance between the target vehicle and the k-th target track overlapping area and a time distance between each transverse competing vehicle and the k-th target track overlapping area;

if the determined time intervals are different, selecting the vehicle with the minimum time interval from the target vehicle and the at least one transverse competitive vehicle as the vehicle with the right of way ahead;

and if the determined time intervals are the same, selecting a vehicle with priority from the target vehicle and the at least one transverse competitive vehicle according to the degree of aggressiveness of the target vehicle and the degree of aggressiveness of each transverse competitive vehicle.

In another embodiment, when the control unit 601 is configured to select a vehicle with priority from the target vehicle and the at least one laterally competing vehicle according to the aggressiveness of the target vehicle and the aggressiveness of each laterally competing vehicle, it may specifically be configured to:

if the degree of aggressiveness of each vehicle in the target vehicle and each transverse competitive vehicle is different, selecting the vehicle with the highest degree of aggressiveness from the target vehicle and the at least one transverse competitive vehicle as the vehicle with the right of way ahead;

and if the excitation degrees of each vehicle in the target vehicle and the transverse competitive vehicles are the same, randomly selecting one vehicle from the target vehicle and the at least one transverse competitive vehicle as the vehicle with the right of way.

In another embodiment, the control unit 601 may further be configured to:

after the target vehicle enters the target virtual lane, searching a target front guide vehicle of the target vehicle along the target virtual lane and an adjacent virtual lane of the target virtual lane; the target leading vehicle is a leading vehicle which is closest to the target vehicle and has a position meeting a position condition in all leading vehicles of the target vehicle, and the leading vehicle is a vehicle which is positioned in front of the target vehicle in the longitudinal direction;

if the target leading vehicle is found, determining longitudinal driving parameters of the target vehicle based on the target leading vehicle, and controlling the target vehicle to drive in the target virtual lane according to the longitudinal driving parameters;

and if the target leading vehicle is not found, controlling the target vehicle to run in the target virtual lane in an accelerated manner.

In another embodiment, the control unit 601, when configured to find the target leading vehicle of the target vehicle along the target virtual lane and the adjacent virtual lane of the target virtual lane, may specifically be configured to:

sequentially traversing each leading vehicle of the target vehicle along the target virtual lane and the adjacent virtual lane of the target virtual lane according to the traversing sequence of the distance between the target vehicle and the leading vehicle from small to large;

if the position of the currently traversed leading vehicle meets the position condition, stopping traversing, and taking the currently traversed leading vehicle as a target leading vehicle of the target vehicle;

if the position of the currently traversed leading vehicle does not meet the position condition, continuing traversing to find the target leading vehicle of the target vehicle;

wherein the location condition includes: the leading vehicle is positioned in the target virtual lane; the position condition includes: the leading vehicle is located in the adjacent virtual lane, and the leading vehicle is located in a track overlapping area between the target virtual lane and the adjacent virtual lane.

In another embodiment, the control unit 601 may further be configured to:

in the process that the target vehicle runs on the target virtual lane, if the target vehicle has a lane change intention, acquiring a lane change condition of the target vehicle;

and when the target vehicle meets the lane changing condition, controlling the target vehicle to run from the lane changing of the target virtual lane to the adjacent virtual lane of the target virtual lane.

In another embodiment, the control unit 601 may further be configured to:

acquiring the degree of aggressiveness of the target vehicle;

if the aggressive degree of the target vehicle is higher than or equal to the preset aggressive degree, determining that the target vehicle has a lane change intention;

and if the aggressive degree of the target vehicle is lower than the preset aggressive degree, determining that the target vehicle does not have the lane change will.

According to an embodiment of the present application, each step involved in the methods shown in fig. 2, 4, and 5 may be performed by each unit in the vehicle control device shown in fig. 6. For example, step S201 and step S204 shown in fig. 2 can both be performed by the control unit 601 shown in fig. 6, and steps S202 to S203 can both be performed by the processing unit 602 shown in fig. 6; as another example, step S401 shown in fig. 4 may be performed by the control unit 601 shown in fig. 6, the step of "selecting one virtual lane from M virtual lanes as the target virtual lane according to the lane congestion information of each virtual lane" in step S402 and step S403 may be performed by the processing unit 602 shown in fig. 6, the step of "controlling the target vehicle to enter the target virtual lane" in step S403 and steps S404 to S408 may be performed by the control unit 601 shown in fig. 6, and so on.

According to another embodiment of the present application, the units in the vehicle control device shown in fig. 6 may be respectively or entirely combined into one or several other units to form the unit, or some unit(s) may be further split into multiple functionally smaller units to form the unit(s), which may achieve the same operation without affecting the achievement of the technical effects of the embodiments of the present application. The units are divided based on logic functions, and in practical application, the functions of one unit can be realized by a plurality of units, or the functions of a plurality of units can be realized by one unit. In other embodiments of the present application, the vehicle-based control device may also include other units, and in practical applications, these functions may also be implemented by assistance of other units, and may be implemented by cooperation of a plurality of units.

According to another embodiment of the present application, the vehicle control apparatus device as shown in fig. 6 may be constructed by running a computer program (including program codes) capable of executing the steps involved in the respective methods as shown in fig. 2, fig. 4 or fig. 5 on a general-purpose computing device such as a computer including a Central Processing Unit (CPU), a random access storage medium (RAM), a read-only storage medium (ROM) and the like processing elements and storage elements, and implementing the vehicle control method of the embodiment of the present application. The computer program may be recorded on a computer-readable recording medium, for example, and loaded and executed in the above-described computing apparatus via the computer-readable recording medium.

According to the embodiment of the application, M virtual lanes are introduced into the intersection, and each virtual lane is located between the upstream steering lane and one downstream lane, so that when a target vehicle running in the upstream steering lane intends to enter the downstream lane through the intersection, one virtual lane can be selected from the M virtual lanes as the target virtual lane according to the lane congestion information of each virtual lane, the target vehicle is controlled to enter the target virtual lane, and then the target vehicle enters one of the N downstream lanes based on the target virtual lane. Therefore, the target virtual lane is selected by considering the congestion condition of each virtual lane, so that the steering behavior of the target vehicle executed based on the target virtual lane can better accord with the actual condition, and the authenticity of the steering behavior of the target vehicle at the intersection without a steering guide line can be effectively improved; the target vehicle can be prevented from entering the relatively blocked virtual lane, and the passing efficiency can be effectively improved. Moreover, by introducing M virtual lanes, the steering behavior of the target vehicle at the intersection without the steering guide lines can be enriched, and the target vehicle and other vehicles can run along the respective selected virtual lanes at the intersection, so that the probability of vehicle collision can be effectively reduced, and the traffic efficiency and the running safety of the vehicle can be further improved.

Based on the description of the method embodiment and the device embodiment, the embodiment of the application further provides a computer device. Referring to fig. 7, the computer device includes at least a processor 701, an input interface 702, an output interface 703, and a computer storage medium 704. The processor 701, the input interface 702, the output interface 703, and the computer storage medium 704 in the computer device may be connected by a bus or other means. A computer storage medium 704 may be stored in the memory of the computer device, the computer storage medium 704 being used to store a computer program comprising program instructions, the processor 701 being used to execute the program instructions stored by the computer storage medium 704. The processor 701 (or CPU) is a computing core and a control core of the computer device, and is adapted to implement one or more instructions, and in particular, is adapted to load and execute one or more instructions to implement a corresponding method flow or a corresponding function.

In one embodiment, the processor 701 according to the embodiment of the present application may be used to perform a series of vehicle controls, specifically including: controlling a target vehicle to run in an upstream steering lane, wherein the upstream steering lane is communicated with N downstream lanes through an intersection; the intersection comprises: m virtual lanes located between the upstream steering lane and the N downstream lanes, N being a positive integer, M being an integer greater than 1; determining lane congestion information of each virtual lane in the M virtual lanes, wherein the lane congestion information is information for reflecting the congestion degree of the virtual lanes; selecting one virtual lane from the M virtual lanes as a target virtual lane according to the lane congestion information of each virtual lane; and controlling the target vehicle to enter the target virtual lane so that the target vehicle enters one of the N downstream lanes through the intersection, and the like.

An embodiment of the present application further provides a computer storage medium (Memory), which is a Memory device in a computer device and is used to store programs and data. It is understood that the computer storage medium herein may include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. Computer storage media provide storage space that stores an operating system for a computer device. Also stored in this memory space are one or more instructions, which may be one or more computer programs (including program code), suitable for loading and execution by processor 701. It should be noted that the computer storage medium herein may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk memory; in the alternative, the computer storage media may be at least one computer storage medium located remotely from the processor.

In one embodiment, one or more instructions stored in a computer storage medium may be loaded and executed by a processor to perform the corresponding steps of the methods described above with respect to the vehicle control method embodiments shown in FIG. 2, FIG. 4, or FIG. 5; in particular implementations, one or more instructions in a computer storage medium are loaded by a processor and perform the steps of:

when N is larger than 1, the N downstream lanes correspond to the M virtual lanes one by one; and the virtual lane corresponding to any downstream lane starts from the steering decision line and ends at the start of the downstream lane.

In another embodiment, the lane congestion information of the mth virtual lane includes: the queuing length of the mth virtual lane is m ∈ [1,M ]; accordingly, in determining lane congestion information for each of the M virtual lanes, the one or more instructions may be loaded by a processor and specifically executed to:

In another embodiment, when determining lane congestion information of each of the M virtual lanes, the one or more instructions may be further loaded by a processor and specifically executed to:

In another embodiment, the lane congestion information of each virtual lane includes: the queuing length of each virtual lane; correspondingly, when one virtual lane is selected from the M virtual lanes as a target virtual lane according to the lane congestion information of each virtual lane, the one or more instructions may be loaded and specifically executed by the processor:

if the queuing lengths of the virtual lanes are the same, randomly selecting one virtual lane from the M virtual lanes as a target virtual lane;

and if the queuing lengths of at least two virtual lanes are different, selecting the virtual lane with the shortest queuing length from the M virtual lanes as a target virtual lane.

In another embodiment, in the area where the M virtual lanes are located, there are K target track overlapping areas corresponding to the target virtual lane, where K is a positive integer; accordingly, the one or more instructions may also be loaded and specifically executed by a processor to:

when the target vehicle is about to drive into a kth target track overlapping region, detecting transverse competitive vehicles in M-1 virtual lanes except the target virtual lane in the M virtual lanes; the transverse competing vehicles are: in the M-1 virtual lanes, a vehicle which is to be driven into the k target track overlapping area belongs to [1,K ];

In another embodiment, when the target vehicle is controlled to travel in the target virtual lane according to the selection result, the one or more instructions may be loaded and specifically executed by the processor:

In another embodiment, when selecting the vehicle with preemption among the target vehicle and the at least one competing vehicle in a lateral direction, the one or more instructions are loaded and specifically executed by the processor to:

In another embodiment, when a vehicle with a priority is selected from the target vehicle and the at least one laterally competing vehicle according to the aggressiveness of the target vehicle and the aggressiveness of each laterally competing vehicle, the one or more instructions may be loaded and specifically executed by the processor:

In another embodiment, the one or more instructions may also be loaded and specifically executed by a processor to:

after the target vehicle enters the target virtual lane, searching a target front guide vehicle of the target vehicle along the target virtual lane and an adjacent virtual lane of the target virtual lane; the target leading vehicle is a leading vehicle which is closest to the target vehicle and has a position meeting a position condition in all leading vehicles of the target vehicle, and the leading vehicle is a vehicle which is located in front of the target vehicle in the longitudinal direction;

In another embodiment, when finding a target leading vehicle of the target vehicle along the target virtual lane and an adjacent virtual lane of the target virtual lane, the one or more instructions may be loaded by the processor and specifically executed to:

if the position of the currently traversed leading vehicle does not meet the position condition, continuing traversing to find a target leading vehicle of the target vehicle;

acquiring the degree of aggressiveness of the target vehicle;

if the aggressive degree of the target vehicle is higher than or equal to the preset aggressive degree, determining that the target vehicle has a lane changing intention;

According to the embodiment of the application, M virtual lanes are introduced into the intersection, and each virtual lane is located between the upstream turning lane and one downstream lane, so that when a target vehicle running in the upstream turning lane intends to enter the downstream lane through the intersection, one virtual lane can be selected from the M virtual lanes as the target virtual lane according to the lane congestion information of each virtual lane, the target vehicle is controlled to enter the target virtual lane, and then the target vehicle enters one of the N downstream lanes on the basis of the target virtual lane. Therefore, the target virtual lane is selected by considering the congestion condition of each virtual lane, so that the steering behavior of the target vehicle executed based on the target virtual lane can better accord with the actual condition, and the authenticity of the steering behavior of the target vehicle at the intersection without a steering guide line can be effectively improved; the target vehicle can be prevented from entering the relatively blocked virtual lane, and the passing efficiency can be effectively improved. Moreover, by introducing M virtual lanes, the steering behavior of the target vehicle at the intersection without the steering guide lines can be richer, and the target vehicle and other vehicles can drive along the respective selected virtual lanes at the intersection, so that the probability of vehicle collision can be effectively reduced, and the traffic efficiency and the driving safety of the vehicles are further improved.

It should be noted that according to an aspect of the present application, a computer program product or a computer program is also provided, and the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions are read by a processor of a computer device from a computer-readable storage medium, and the computer instructions are executed by the processor to cause the computer device to perform the methods provided in the various alternatives in the aspect of the embodiment of the vehicle control method shown in fig. 2, 4 or 5 described above.

It should be understood that the above-described embodiments are merely illustrative of the preferred embodiments of the present invention, which should not be taken as limiting the scope of the invention, but rather the scope of the invention is defined by the appended claims.

Claims

1. A vehicle control method characterized by comprising:

controlling a target vehicle to run in an upstream steering lane, wherein the upstream steering lane is communicated with N downstream lanes through an intersection; the intersection comprises: a steering decision line, M virtual lanes located between the upstream steering lane and the N downstream lanes, N being a positive integer, M being an integer greater than 1; when N is equal to 1, each virtual lane starts from the steering decision line and ends at the start of the downstream lane; when N is larger than 1, the N downstream lanes correspond to the M virtual lanes one by one; the virtual lane corresponding to any downstream lane starts from the steering decision line and ends at the start of any downstream lane;

determining lane congestion information of each virtual lane in the M virtual lanes, wherein the lane congestion information is information for reflecting the congestion degree of the virtual lanes; the lane congestion information of the mth virtual lane includes: the queuing length of the mth virtual lane is m ∈ [1,M ]; when the N downstream lanes are not congested, the queuing length of each virtual lane in the M virtual lanes is the same queuing length; when congestion exists in the N downstream lanes, determining one or more track overlapping areas corresponding to the mth virtual lane in the area where the M virtual lanes are located, wherein one track overlapping area refers to an area where the mth virtual lane and at least one other virtual lane overlap each other, if no vehicle stops in each track overlapping area, the queuing length of the mth virtual lane is the length between the starting point and the ending point of the queue of the vehicle corresponding to the mth virtual lane, and if the vehicle stops in at least one track overlapping area, the queuing length of the mth virtual lane and the queuing length of the other virtual lanes related to the track overlapping area where the vehicle stops are the same queuing length;

2. The method of claim 1, wherein said determining lane congestion information for each of said M virtual lanes comprises:

when the N downstream lanes are congested, determining one or more track overlapping areas corresponding to the M-th virtual lane in the area where the M virtual lanes are located;

3. The method of claim 2, wherein said determining lane congestion information for each of said M virtual lanes further comprises:

4. The method of claim 1, wherein the lane congestion information for each virtual lane comprises: the queuing length of each virtual lane; the selecting one virtual lane from the M virtual lanes as a target virtual lane according to the lane congestion information of each virtual lane includes:

5. The method of claim 1, wherein K target track overlapping regions corresponding to the target virtual lane exist in the region where the M virtual lanes are located, wherein K is a positive integer; the method further comprises the following steps:

6. The method of claim 5, wherein said controlling the target vehicle to travel in the target virtual lane based on the pick-up comprises:

7. The method of claim 5, wherein said selecting a vehicle with preemption among said target vehicle and said at least one laterally competing vehicle comprises:

and if the determined time intervals are the same, selecting a vehicle with priority from the target vehicle and the at least one transverse competitive vehicle according to the aggressive degree of the target vehicle and the aggressive degree of each transverse competitive vehicle.

8. The method of claim 7, wherein said selecting a vehicle having priority from said target vehicle and said at least one laterally competing vehicle based on the aggressiveness of said target vehicle and the aggressiveness of said respective laterally competing vehicles comprises:

9. The method of claim 1, wherein the method further comprises:

after the target vehicle enters the target virtual lane, searching a target leading vehicle of the target vehicle along the target virtual lane and an adjacent virtual lane of the target virtual lane; the target leading vehicle is a leading vehicle which is closest to the target vehicle and has a position meeting a position condition in all leading vehicles of the target vehicle, and the leading vehicle is a vehicle which is located in front of the target vehicle in the longitudinal direction;

10. The method of claim 9, wherein said finding a target leading vehicle of the target vehicle along the target virtual lane and adjacent virtual lanes of the target virtual lane comprises:

sequentially traversing each leading vehicle of the target vehicle along the target virtual lane and the adjacent virtual lane of the target virtual lane according to a traversing sequence that the distance between the target vehicle and the leading vehicle is from small to large;

wherein the location condition includes: the leading vehicle is positioned in the target virtual lane; alternatively, the location condition includes: the leading vehicle is located in the adjacent virtual lane, and the leading vehicle is located in a track overlapping region between the target virtual lane and the adjacent virtual lane.

11. The method of claim 1, wherein the method further comprises:

12. The method of claim 11, wherein the method further comprises:

acquiring the degree of aggressiveness of the target vehicle;

13. A vehicle control apparatus characterized by comprising:

the control unit is used for controlling a target vehicle to run in an upstream steering lane, and the upstream steering lane is communicated with N downstream lanes through an intersection; the intersection comprises: a steering decision line, M virtual lanes located between the upstream steering lane and the N downstream lanes, N being a positive integer, M being an integer greater than 1; when N is equal to 1, each virtual lane starts from the steering decision line and ends at the start of the downstream lane; when N is larger than 1, the N downstream lanes correspond to the M virtual lanes one by one; the virtual lane corresponding to any downstream lane starts from the steering decision line and ends at the start of any downstream lane;

the processing unit is used for determining lane congestion information of each virtual lane in the M virtual lanes, wherein the lane congestion information is information used for reflecting the congestion degree of the virtual lanes; the lane congestion information of the mth virtual lane includes: the queuing length of the mth virtual lane is m ∈ [1,M ]; when the N downstream lanes are not congested, the queuing length of each virtual lane in the M virtual lanes is the same queuing length; when congestion exists in the N downstream lanes, determining one or more track overlapping areas corresponding to the mth virtual lane in the area where the M virtual lanes are located, wherein one track overlapping area refers to an area where the mth virtual lane and at least one other virtual lane overlap each other, if no vehicle stops in each track overlapping area, the queuing length of the mth virtual lane is the length between the starting point and the ending point of the queue of the vehicle corresponding to the mth virtual lane, and if the vehicle stops in at least one track overlapping area, the queuing length of the mth virtual lane and the queuing length of the other virtual lanes related to the track overlapping area where the vehicle stops are the same queuing length;

14. A computer storage medium having one or more instructions stored thereon, the one or more instructions adapted to be loaded by a processor and to perform a vehicle control method as claimed in any one of claims 1-12.