WO2023025007A1 - Vehicle avoidance method and apparatus, vehicle-mounted device, and storage medium - Google Patents

Abstract

A vehicle avoidance method, comprising: in response to determining that a target vehicle is in an autonomous driving state, detecting a driving behavior of a neighbor vehicle within a preset distance; and in response to determining that in the current lane to which the target vehicle belongs, at least one neighbor vehicle among neighbor vehicles in front of the target vehicle and at least one neighbor vehicle among neighbor vehicles behind the target vehicle respectively have an avoidance behavior, and a vehicle to be avoided is present behind the target vehicle in the current lane, controlling the target vehicle to perform avoidance. Also comprised are a vehicle avoidance apparatus, a vehicle-mounted device, and a storage medium.

Description

Vehicle avoidance method, device, vehicle-mounted equipment and storage medium

This application claims priority to a Chinese patent application with application number 202110986477.1 filed with the China Patent Office on August 26, 2021, the entire contents of which are incorporated herein by reference.

technical field

Embodiments of the present application relate to the technical field of self-driving vehicles, for example, to a vehicle avoidance method, device, vehicle-mounted equipment, and storage medium.

Background technique

When performing emergency tasks, special vehicles shall have the right of priority in road passage, and other vehicles and pedestrians shall give way. In real traffic environments, self-driving vehicles may encounter special vehicles performing emergency tasks and need to perform automatic emergency avoidance.

In the related technology, sound sensing equipment can be installed on the self-driving vehicle to identify the special vehicle according to the alarm sound of the special vehicle, and avoid the special vehicle in time. It is also possible to receive information such as the position and speed of special vehicles from the vehicle-mounted terminal through navigation to judge the special vehicles around the self-driving vehicle for timely avoidance. It is also possible to identify special vehicles for avoidance by installing visual sensors on self-driving vehicles and through methods such as image information processing and deep learning.

However, the above needs to install additional sound sensing equipment on the self-driving vehicle, which is specially used for the identification of special vehicles, which causes an increase in the manufacturing cost of the self-driving vehicle. To receive the location of special vehicles through navigation, it is necessary to ensure that multiple special vehicles are in the Internet of Vehicles, otherwise, it will be difficult to identify them. The above image information processing and deep learning methods cannot identify untrained special vehicle types, which will cause errors and omissions in identifying special vehicles and affect emergency avoidance.

Contents of the invention

Embodiments of the present application provide a vehicle avoidance method, device, vehicle-mounted equipment, and storage medium, which can quickly perform avoidance driving according to the driving behavior of neighboring vehicles.

In a first aspect, an embodiment of the present application provides a vehicle avoidance method, the method comprising:

In response to determining that the target vehicle is in an automatic driving state, detecting the driving behavior of neighbor vehicles within a preset distance;

Responsive to determining that in the current lane to which the target vehicle belongs, there is at least one neighbor vehicle in an avoidance behavior among neighbor vehicles located in front of and behind the target vehicle respectively, and the target vehicle in the current lane There is a vehicle to be evaded behind the vehicle, and the target vehicle is controlled to evade.

In the second aspect, the embodiment of the present application also provides a vehicle avoidance device, which includes:

The driving behavior detection module is configured to detect the driving behavior of neighbor vehicles within a preset distance in response to determining that the target vehicle is in an automatic driving state;

The target vehicle avoidance module is configured to detect that in the current lane to which the target vehicle belongs, there is at least one neighbor vehicle in an avoidance behavior in the neighbor vehicles in front of and behind the target vehicle respectively, and There is a vehicle to be avoided behind the target vehicle in the current lane, and the target vehicle is controlled to avoid.

In a third aspect, the embodiment of the present application also provides a vehicle-mounted device, the vehicle-mounted device includes:

one or more processors;

storage means configured to store one or more programs,

When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle avoidance method described in any one of the embodiments of the present application.

In a fourth aspect, the embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the vehicle avoidance method as described in any one of the embodiments of the present application is implemented.

Description of drawings

FIG. 1 is a schematic flow chart of a vehicle avoidance method provided in an embodiment of the present application;

FIG. 2 is a schematic flow chart of a vehicle avoidance method provided in another embodiment of the present application;

FIG. 3 is a schematic flowchart of a vehicle avoidance method provided in another embodiment of the present application;

FIG. 4 is a schematic structural diagram of an on-board sensor in a target vehicle provided by an embodiment of the present application;

Fig. 5 is a schematic structural diagram of a vehicle avoidance device provided by an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a vehicle-mounted device provided by an embodiment of the present application.

Detailed ways

Fig. 1 is a schematic flow chart of a vehicle avoidance method provided by an embodiment of the present application. This embodiment is applicable to situations in which a vehicle avoidance is performed in a timely manner when encountering a special vehicle that needs to be avoided during automatic driving. The method can It is executed by the vehicle avoidance device, which can be implemented in the form of software and/or hardware, and the hardware can be vehicle-mounted equipment and the like.

As shown in Figure 1, the method of this embodiment includes the following steps:

S110. When the target vehicle is in an automatic driving state, detect the driving behavior of neighboring vehicles within a preset distance.

Wherein, the target vehicle may be a vehicle with an automatic driving function. The automatic driving state may be an operating state in which the automatic driving vehicle performs automatic driving according to a preset route. The preset distance may be a distance that can be detected by the vehicle-mounted sensor on the target vehicle, and may include a longitudinal preset distance and a lateral preset distance. The neighbor vehicles may be vehicles within a preset distance of the target vehicle. The driving behavior may be straight driving, turning, etc., or normal driving, avoidance driving, etc.

For example, when it is detected that the target vehicle is in the state of automatic driving, in order to ensure the safety and accuracy of the target vehicle during automatic driving, the surrounding environment can be detected through the on-board sensors on the target vehicle. Furthermore, the driving direction, driving speed, etc. of the neighboring vehicles within the preset distance of the target vehicle can be determined, and the driving behavior of the neighboring vehicles can also be determined.

Exemplarily, the longitudinal detection range of the forward sensor and the rear sensor of the target vehicle can reach 200m, that is, the longitudinal preset distance is 200m, and the lateral detection range of the lateral sensor can reach 20m, that is, the lateral preset distance is 20m. When the target vehicle is in the state of automatic driving, it can obtain road information and neighbor vehicle information through cameras, ultrasonic radar and other on-board sensors to determine the driving behavior of neighbor vehicles.

S120. If it is detected that in the current lane to which the target vehicle belongs, there is at least one neighbor vehicle in an avoidance behavior in both the front and rear neighbor vehicles of the target vehicle, and in the current lane, there is a vehicle to be avoided behind the target vehicle , then control the target vehicle to avoid.

Wherein, the current lane may be a lane in which the target vehicle is driving. The avoidance behavior may be a behavior of leaving the current lane and driving to the next lane. The vehicle to be avoided can be a vehicle driving in the current lane without avoiding behavior, or it can be a special vehicle.

For example, the current lane to which the target vehicle belongs is determined according to the sensor data collected by the on-board sensor, and then, whether there is at least one neighbor vehicle in the current lane in front of and behind the target vehicle in the current lane to avoid behavior can also be determined through the on-board sensor. If so, it can be determined that the front neighbor vehicle and the rear neighbor vehicle of the target vehicle have performed the avoidance behavior of changing lanes. At this time, there may be vehicles that need to avoid vehicles behind the current lane to which the target vehicle belongs. If there is a fast-moving neighbor vehicle behind the target vehicle, the neighbor vehicle can be regarded as the vehicle to be avoided, and the target vehicle can be controlled to avoid automatically.

It should be noted that judging the avoidance behavior of neighbor vehicles in front and behind of the target vehicle in the current lane to which the target vehicle belongs may be to first judge the rear neighbor vehicle and then judge the front neighbor vehicle, because the vehicle to be avoided usually starts from the current lane. Drive behind the target vehicle in the lane. Certainly, it is also possible to first determine the front neighbor vehicle and then determine the rear neighbor vehicle. Therefore, the determination order of the neighbor vehicles in front of and behind the target vehicle can be set according to the actual situation, which is not specifically limited in this embodiment.

For example, if there is at least one neighbor vehicle continuously approaching the target vehicle behind the target vehicle in the current lane, then at least one neighbor vehicle is determined as the vehicle to be avoided.

For example, if in the current lane, there are neighboring vehicles avoiding driving in the front and rear of the target vehicle, it indicates that there may be vehicles to be avoided. At this time, if at least one neighbor vehicle is detected by the on-board sensor and the distance between the vehicle and the target vehicle is getting closer and closer, it indicates that the vehicle is most likely a special vehicle, and the neighbor vehicles that avoid the vehicle are all If the vehicle is to be avoided, then the vehicle can be regarded as the vehicle to be avoided.

Exemplarily, detecting that the neighbor vehicle continues to approach the target vehicle may be detected by the radar sensor as the distance between the neighbor vehicle and the target vehicle continues to decrease, then it is considered that the neighbor vehicle is rapidly approaching the target vehicle, and the target vehicle is required to perform evasive driving.

In the technical solution of the embodiment of the present application, when the target vehicle is in the automatic driving state, by detecting the driving behavior of the neighbor vehicles within the preset distance, if it is detected that the target vehicle is in the current lane to which the target vehicle belongs, it is located in front of and behind the target vehicle. If there is at least one neighbor vehicle avoiding behavior among the neighbor vehicles, and there is a vehicle to be avoided behind the target vehicle in the current lane, then the target vehicle is controlled to avoid the situation, which avoids the high manufacturing cost caused by external sensors and through When the deep learning model recognizes special vehicles, the calculation is complicated, and it can quickly avoid driving according to the driving behavior of neighboring vehicles.

Fig. 2 is a schematic flow chart of a vehicle avoidance method provided by another embodiment of the present application. On the basis of the above-mentioned multiple embodiments, this embodiment can detect the driving behavior of neighbor vehicles and the avoidance driving method of the target vehicle. Refer to the technical solution of this embodiment. Wherein, explanations of terms that are the same as or corresponding to the above multiple embodiments are not repeated here.

As shown in Figure 2, the method of this embodiment includes the following steps:

S210. When the target vehicle is in the automatic driving state, determine the driving behavior of neighbor vehicles located in front and behind the target vehicle within a preset distance in the current lane through the vehicle-mounted longitudinal sensor of the target vehicle.

Wherein, the vehicle-mounted longitudinal sensor includes at least one of a forward-looking camera, a millimeter-wave radar, a millimeter-wave angle radar, an ultrasonic radar, and a surround-view camera. The driving behavior includes normal driving behavior and avoidance driving behavior. The normal driving behavior may be the behavior of the neighbor vehicle driving along the lane to which the neighbor vehicle belongs, and the avoidance driving behavior may be the driving behavior of the neighbor vehicle changing lanes.

For example, when the target vehicle is in the state of automatic driving, the on-board longitudinal sensor is used to detect the behavior of neighbor vehicles in front and behind the lane to which the target vehicle belongs, so as to subsequently determine whether the target vehicle needs to avoid.

It should be noted that the on-board longitudinal sensor can detect road information such as lane line position, lane line type, lane line color, road sign position, road sign direction, etc., and can also detect information such as the distance between the target vehicle and surrounding neighbor vehicles.

S220. If it is detected that in the current lane to which the target vehicle belongs, there is at least one neighbor vehicle in an avoidance behavior in both the front and rear neighbor vehicles of the target vehicle, and in the current lane, there is a vehicle to be avoided behind the target vehicle , then based on the pre-acquired road information, the avoidable lane is determined, and the target vehicle is controlled to drive to the avoidable lane.

Among them, the road information may include the position of the lane line, the type of the lane line, the color of the lane line, the position of the road surface marking, the direction of the road surface marking, etc. acquired based on the vehicle sensor, and may also include the driving direction of the lane determined based on the vehicle map, etc. The driving direction of the lane may include Through lanes, left turn lanes and right turn lanes. The avoidable lane may be a lane into which the target vehicle can drive to avoid the vehicle to be avoided.

For example, if it is detected that in the current lane to which the target vehicle belongs, there is at least one neighbor vehicle in the neighbor vehicles located in front of and behind the target vehicle in an avoidance behavior, and in the current lane, there is a vehicle to be avoided behind the target vehicle , it can be considered that the target vehicle needs to avoid driving. Furthermore, it can be determined based on the road information acquired by the on-board sensor and/or the on-board map whether there is a lane that can be avoided on both sides of the current lane, and if there is a lane that can be avoided, then the lane is determined as an avoidable lane, and then the target vehicle It can automatically drive into the avoidable lane to avoid vehicles to be avoided.

For example, the way to determine the avoidable lane may be: determine the neighbor lane that has the same target traveling direction as the current lane and has an avoidable section as the avoidable lane.

Wherein, the target travel direction may be the current travel direction of the target vehicle or the current travel direction in the automatic driving path planning. The avoidable section may be a section that can accommodate the entry of the target vehicle. Neighbor lanes may be lanes adjacent to the current lane. For example, according to the on-board sensors, the road information and vehicle driving information around the target vehicle can be obtained, and the lane that is in the same direction as the current lane’s target travel direction can be determined to ensure that the automatic driving route is not changed. For example, it is determined that there is an avoidable section neighbor lane to ensure that the target vehicle can drive into the neighbor lane for avoidance. Furthermore, a neighbor lane that has the same target traveling direction as the current lane and has an avoidable section can be used as an avoidable lane.

For example, the steps for determining avoidable lanes could be:

Step 1: Judging whether there is an optional lane in the neighbor lanes of the current lane to which the target vehicle belongs in the same target traveling direction as the current lane.

Wherein, the optional lane may be a neighboring lane with the same target traveling direction as the current lane, and may be the left lane and/or the right lane of the current lane.

For example, the traveling direction of the current lane and the neighboring lanes of the current lane can be determined according to the on-board map configured in the target vehicle, and the traveling direction of the current lane and the neighboring lanes of the current lane can also be determined according to the signs around the road identified by the on-board sensors. Furthermore, it can be determined whether there is an optional lane in the neighbor lane that has the same target traveling direction as the current lane. If there is an optional lane, you can proceed to the next step of judgment. If there is no optional lane, it means that avoidance driving will lead to a change in the automatic driving route. A reminder message can be generated and sent to the driver user of the target vehicle so that the driving The driver user judges how to avoid driving.

Step 2: If there is an optional lane, determine whether there is an avoidable section in the optional lane according to the road information.

Wherein, the road information may include driving information of neighbor vehicles currently driving in the optional lane, such as distance from the target vehicle, driving speed, and the like.

For example, if there is an optional lane, it can be further judged whether the optional lane is available for the target vehicle to drive into. The vehicle-mounted sensor determines the speed of the neighbor vehicle that is currently driving in the optional lane and the distance to the target vehicle, and the automatic driving system analyzes whether there is an avoidable section that can accommodate the target vehicle in the optional lane. If there is no avoidable section, a reminder message can be generated and sent to the driver user of the target vehicle, so that the driver user can judge how to avoid driving.

Step 3: If there is an avoidable section, determine the optional lane as the avoidable lane.

For example, an optional lane with an avoidable section is taken as an avoidable lane. If the neighbor lanes on the left and right sides of the current lane are avoidable lanes, then the subsequent target vehicle can drive into any avoidable lane for vehicle avoidance.

It should be noted that by analyzing the driving information of neighbor vehicles in the avoidable lane, it is possible to judge when and at what speed the target vehicle will change lanes, so as to complete vehicle avoidance safely and accurately.

S230. If there is no avoidable lane, control the target vehicle to send a reminder message.

Wherein, the reminding information may be sound information or text information.

For example, if there is no avoidable lane, the automatic driving system of the target vehicle can generate prompt information to remind the driver user that an avoidance operation is currently required, but the automatic driving state cannot perform the avoidance operation.

Exemplarily, if the reminder information is sound information, the reminder information can be sent to the driver user's mobile terminal device through the sound playback device of the target vehicle, so that the reminder information can be played through the mobile terminal device. If the reminder information is text information, the text information can be displayed on the vehicle-mounted display device of the target vehicle, or the reminder information can be sent to the mobile terminal device of the driver user, so as to remind the driver through a pop-up window or a strong reminder through the mobile terminal device. Pay attention to the operator and user, and take over the target vehicle manually in time.

In the technical solution of the embodiment of the present application, when the target vehicle is in the automatic driving state, the vehicle-mounted longitudinal sensor of the target vehicle is used to determine the driving behavior of neighbor vehicles within a preset distance and located in front and behind the target vehicle in the current lane, If it is detected that in the current lane to which the target vehicle belongs, there is at least one neighbor vehicle in the neighbor vehicles located in front of and behind the target vehicle, and there is an avoidance behavior in the current lane, and there is a vehicle to be avoided behind the target vehicle in the current lane, then Based on the pre-acquired road information, the avoidable lane is determined, and the target vehicle is controlled to drive to the avoidable lane. If there is no avoidable lane, the target vehicle is controlled to send a reminder message, which avoids the high manufacturing cost caused by external sensors and through When the deep learning model recognizes special vehicles, the calculation is complicated, and it can quickly avoid driving according to the driving behavior of neighboring vehicles.

As an exemplary implementation of the above-mentioned multiple embodiments, FIG. 3 is a schematic flowchart of a vehicle avoidance method provided in another embodiment of the present application. Wherein, explanations of terms that are the same as or corresponding to the above multiple embodiments are not repeated here.

As shown in Figure 3, the steps of the vehicle avoidance method are as follows:

The first step is to start the target vehicle and identify the current traffic situation through the on-board sensor.

The second step is to judge whether the target vehicle is in the automatic driving state, if yes, enter the third step of judgment, if not, end the judgment, and return to identify the traffic situation, so that the driver user manually drives the target vehicle.

The third step is to identify the situation in this lane (current lane), and judge whether the rear vehicle in this lane avoids to the left or to the right lane (neighbor lane), and there is a vehicle (vehicle to be avoided) approaching quickly, if so, Enter the fourth step of judgment, if not, end the judgment, and return to execute the identification of the situation in this lane.

The fourth step is to judge whether the vehicles in front of the lane are avoiding to the left or the right lane, if yes, enter the fifth step to judge, if not, end the judgment, and return to the third step.

Step 5, judging whether the left or right lane is the same direction of travel (the target direction of travel is the same) lane (avoidable lane). If yes, change lanes to the lane in the same direction of travel, and return to the third step, if no, immediately remind the driver and user to take over.

The target vehicle can use the front-view camera, surround-view camera, millimeter-wave radar, and ultrasonic radar to obtain road information and neighbor vehicle information. The target vehicle can also obtain the target vehicle's speed, acceleration, steering wheel angle and other vehicle information through the vehicle sensor. Furthermore, the road information provided by the vehicle network map is obtained, the lane line information identified by the vehicle front-view camera and the surround-view camera are determined, and multiple vehicle sensors are combined with the vehicle Controller Area Network (CAN) bus to transmit the target-level signal. Send it to the vehicle controller ADV (Automatic Driving Vehicle) in real time, so that the automatic driving system of the target vehicle can automatically judge whether there is a special vehicle to be avoided, and perform an avoidance operation.

FIG. 4 is a schematic structural diagram of an on-board sensor in a target vehicle provided by an embodiment of the present application. As shown in Figure 4, a forward-looking camera, a surround-view camera, a millimeter-wave radar, four millimeter-wave angle radars, and 12 ultrasonic radars can send signals to the ADV controller through the vehicle CAN bus. Map positioning can send the road information provided by the network map to the ADV controller through Ethernet. In addition, the ADV controller can exchange information with other vehicle-mounted devices via a gateway.

It should be noted that in a good environment, the forward and backward vehicle-mounted sensors can detect target objects (such as: neighbor vehicles, lane lines, etc.), and the longitudinal detection range can reach 200m, and the lateral vehicle-mounted sensors can detect To the target object, the horizontal detection range can reach 20m. The position of the lane line, the type of the lane line, the color of the lane line, the position of the road marking, the direction of the road marking, etc. can be detected by the on-board sensor. The lane driving direction (straight lane, left-turn lane and right-turn lane) of the own lane and adjacent lanes (wheel-base vehicles) can be detected through map positioning.

In the technical solution of this embodiment, the vehicle-mounted sensor is used to obtain the information of roads and neighboring vehicles, and the vehicle-mounted controller is used to make real-time judgments to determine whether there are special vehicles around to perform emergency tasks, avoiding relying on sound sensors and V2X for special vehicle identification, and In the case of avoidance, the self-driving vehicle can quickly and accurately perform avoidance driving.

FIG. 5 is a schematic structural diagram of a vehicle avoidance device provided in an embodiment of the present application, which includes: a driving behavior detection module 510 and a target vehicle avoidance module 520 .

Among them, the driving behavior detection module 510 is set to detect the driving behavior of neighbor vehicles within a preset distance when the target vehicle is in the automatic driving state; the target vehicle avoidance module 520 is set to In the lane, if there is at least one neighbor vehicle in an avoidance behavior among the neighbor vehicles located in front of and behind the target vehicle, and in the current lane, there is a vehicle to be avoided behind the target vehicle, then control the The target vehicle evades.

For example, the device further includes: a vehicle to be avoided determination module, configured to if there is at least one neighbor vehicle that is located behind the target vehicle in the current lane and continues to approach the target vehicle, then the at least A neighbor vehicle is determined as the vehicle to be avoided.

For example, the target vehicle avoidance module 520 is configured to determine an avoidable lane based on pre-acquired road information; and control the target vehicle to drive to the avoidable lane.

For example, the target vehicle avoidance module 520 is configured to determine that a neighbor lane that has the same target traveling direction as the current lane and that has an avoidable section is an avoidable lane.

For example, the target vehicle avoidance module 520 is configured to determine whether there is an optional lane in the adjacent lanes of the current lane to which the target vehicle belongs to which is the same as the target traveling direction of the current lane; if there is the optional lane, then according to The road information determines whether there is an avoidable section in the optional lane; if there is an avoidable section, then determine the optional lane as an avoidable lane.

For example, the device further includes: a reminder module, configured to control the target vehicle to issue a reminder if there is no avoidable lane.

For example, the driving behavior detection module 510 is configured to determine the driving behavior of the neighbor vehicles located in front and behind the target vehicle within a preset distance in the current lane through the vehicle-mounted longitudinal sensor of the target vehicle; Wherein, the vehicle-mounted longitudinal sensor includes at least one of a front-view camera, a millimeter-wave radar, a millimeter-wave angle radar, an ultrasonic radar, and a surround-view camera; the driving behavior includes a normal driving behavior and an avoidance driving behavior.

In the technical solution of the embodiment of the present application, when the target vehicle is in the automatic driving state, by detecting the driving behavior of the neighbor vehicles within the preset distance, if it is detected that the target vehicle is in the current lane to which the target vehicle belongs, it is located in front of and behind the target vehicle. If there is at least one neighbor vehicle avoiding behavior among the neighbor vehicles, and there is a vehicle to be avoided behind the target vehicle in the current lane, then the target vehicle is controlled to avoid the situation, which avoids the high manufacturing cost caused by external sensors and through When the deep learning model recognizes special vehicles, the calculation is complicated, and it can quickly avoid driving according to the driving behavior of neighboring vehicles.

The vehicle avoidance device provided in the embodiment of the present application can execute the vehicle avoidance method provided in any embodiment of the present application, and has corresponding functional modules and beneficial effects for executing the method.

It is worth noting that the multiple units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be realized; in addition, the specific names of multiple functional units It is only for the convenience of distinguishing each other, and is not used to limit the protection scope of the embodiment of the present application.

FIG. 6 is a schematic structural diagram of a vehicle-mounted device provided by an embodiment of the present application. FIG. 6 shows a block diagram of an exemplary vehicle-mounted device 60 suitable for implementing the embodiments of the present application. The vehicle-mounted device 60 shown in FIG. 6 is only an example, and should not impose any limitation on the functions and application scope of the embodiment of the present application.

As shown in FIG. 6, the on-vehicle device 60 takes the form of a general-purpose computing device. The components of the onboard device 60 may include, but are not limited to: one or more processors or processing units 601 , a system memory 602 , and a bus 603 connecting different system components (including the system memory 602 and the processing unit 601 ).

Bus 603 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures. These architectures include, by way of example, but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect ( PCI) bus.

The on-vehicle device 60 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the onboard device 60, including volatile and non-volatile media, removable and non-removable media.

System memory 602 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 604 and/or cache memory 605 . The onboard device 60 may include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 606 may be configured to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard drive"). Although not shown in FIG. 6, a disk drive for reading and writing to removable non-volatile disks (such as "floppy disks") may be provided, as well as for removable non-volatile optical disks (such as CD-ROM, DVD-ROM or other optical media) CD-ROM drive. In these cases, each drive may be connected to bus 603 via one or more data media interfaces. System memory 602 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments of the present application.

A program/utility 608 having a set (at least one) of program modules 607, such as but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include the implementation of the network environment. The program module 607 generally executes the functions and/or methods in the embodiments described in this application.

The in-vehicle device 60 may also communicate with one or more external devices 609 (such as a keyboard, a pointing device, a display 610, etc.), and may also communicate with one or more devices that allow the user to interact with the in-vehicle device 60, and/or communicate with Any device (eg, network card, modem, etc.) that enables the on-board device 60 to communicate with one or more other computing devices. Such communication may occur through input/output (I/O) interface 611 . Moreover, the vehicle-mounted device 60 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and/or a public network such as the Internet) through the network adapter 612 . As shown, the network adapter 612 communicates with other modules of the in-vehicle device 60 through the bus 603 . It should be appreciated that although not shown in FIG. 6, other hardware and/or software modules may be used in conjunction with onboard device 60, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, magnetic tape Drives and data backup storage systems, etc.

The processing unit 601 executes a variety of functional applications and data processing by running the programs stored in the system memory 602, for example, implementing the vehicle avoidance method provided by the embodiment of the present application.

The embodiment of the present application also provides a storage medium containing computer-executable instructions, the computer-executable instructions are configured to execute a vehicle avoidance method when executed by a computer processor, the method comprising:

When the target vehicle is in an automatic driving state, detect the driving behavior of neighbor vehicles within a preset distance;

If it is detected that in the current lane to which the target vehicle belongs, there is at least one neighbor vehicle in an avoidance behavior among the neighbor vehicles in front of and behind the target vehicle, and in the current lane, the target vehicle If there is a vehicle to be evaded behind, the target vehicle is controlled to evade.

The computer storage medium in the embodiments of the present application may use any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (non-exhaustive list) of computer readable storage media include: electrical connections with one or more leads, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. The computer readable storage medium may be a non-transitory computer readable storage medium.

A computer readable signal medium may include a data signal carrying computer readable program code in baseband or as part of a carrier wave. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. .

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including - but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program codes for performing the operations of the embodiments of the present application may be written in one or more programming languages or combinations thereof, the programming languages including object-oriented programming languages—such as Java, Smalltalk, C++, including A conventional procedural programming language - such as "C" or a similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through an Internet service provider). Internet connection).

Claims (10)

1. A vehicle avoidance method, comprising:

   In response to determining that the target vehicle is in an automatic driving state, detecting the driving behavior of neighbor vehicles within a preset distance;

   Responsive to determining that in the current lane to which the target vehicle belongs, there is at least one neighbor vehicle in an avoidance behavior among neighbor vehicles located in front of and behind the target vehicle respectively, and the target vehicle in the current lane There is a vehicle to be evaded behind the vehicle, and the target vehicle is controlled to evade.
2. The method according to claim 1, further comprising:

   In response to determining that there is at least one neighbor vehicle located behind the target vehicle in the current lane and continuously approaching the target vehicle, the at least one neighbor vehicle is determined as a vehicle to be avoided.
3. The method according to claim 1, wherein said controlling the target vehicle to avoid avoidance comprises:

   Based on the pre-acquired road information, determine the avoidable lane;

   The target vehicle is controlled to travel to the avoidable lane.
4. The method according to claim 3, wherein said determining an avoidable lane comprises:

   Determining a neighbor lane that has the same target traveling direction as the current lane and has an avoidable section as an avoidable lane.
5. The method according to claim 3, wherein said determining an avoidable lane comprises:

   Judging whether there is an optional lane in the neighbor lane of the current lane to which the target vehicle belongs to which is the same as the target traveling direction of the current lane;

   Based on the judgment result of the existence of the optional lane, according to the road information, determine whether there is an avoidable section in the optional lane;

   In response to determining that the avoidable section exists, the optional lane is determined as an avoidable lane.
6. The method according to claim 3, further comprising:

   Based on the judgment result that there is no avoidable lane, the target vehicle is controlled to issue a reminder message.
7. The method according to claim 1, wherein said detecting the driving behavior of neighbor vehicles within a preset distance comprises:

   Determining the driving behavior of neighbor vehicles within a preset distance and located in front and behind the target vehicle in the current lane through the vehicle-mounted longitudinal sensor of the target vehicle;

   Wherein, the vehicle-mounted longitudinal sensor includes at least one of a front-view camera, a millimeter-wave radar, a millimeter-wave angle radar, an ultrasonic radar, and a surround-view camera; the driving behavior includes a normal driving behavior and an avoidance driving behavior.
8. A vehicle avoidance device, comprising:

   The driving behavior detection module is configured to detect the driving behavior of neighbor vehicles within a preset distance in response to determining that the target vehicle is in an automatic driving state;

   The target vehicle avoidance module is configured to detect that in the current lane to which the target vehicle belongs, there is at least one neighbor vehicle in an avoidance behavior in the neighbor vehicles in front of and behind the target vehicle respectively, and There is a vehicle to be avoided behind the target vehicle in the current lane, and the target vehicle is controlled to avoid.
9. A vehicle-mounted device, comprising:

   one or more processors;

   storage means configured to store one or more programs,

   When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle avoidance method according to any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the vehicle avoidance method according to any one of claims 1-7 is realized.

Images